From 1a2f7684bc36e5dfc3a6c07b7017b0eb8dfd5a27 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Mon, 15 May 2023 14:35:35 +0200
Subject: [PATCH 001/112] Patch CI proxy

---
 .github/workflows/ci.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 684bd117..ea87ba2f 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -82,7 +82,7 @@ jobs:
           pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
         env:
           CI: true
-          PROXY: ${{ vars.PROXY }}
+          PROXY: ${{ secrets.PROXY }}
           AGENT_MODE: ${{ vars.AGENT_MODE }}
           AGENT_TYPE: ${{ vars.AGENT_TYPE }}
 

From 16b7e7a91e7b6c73ddf3e7193cea53f1b45671fa Mon Sep 17 00:00:00 2001
From: Richard Beales <rich@richbeales.net>
Date: Mon, 15 May 2023 13:55:33 +0100
Subject: [PATCH 002/112] Update prompt.py to clarify how to call commands
 (#4027)

* Update prompt.py to clarify how to call commands

* new cassettes

* try again with a new cassette

* one last try with the cassette

* black dot

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/prompts/prompt.py                     |    2 +-
 .../test_memory_challenge_a.yaml              | 1487 +++++------------
 .../test_browse_website.yaml                  |  296 ++--
 .../test_write_file/test_write_file.yaml      |  365 +---
 4 files changed, 601 insertions(+), 1549 deletions(-)

diff --git a/autogpt/prompts/prompt.py b/autogpt/prompts/prompt.py
index 5da01c44..03b4bd4b 100644
--- a/autogpt/prompts/prompt.py
+++ b/autogpt/prompts/prompt.py
@@ -38,7 +38,7 @@ def build_default_prompt_generator() -> PromptGenerator:
     )
     prompt_generator.add_constraint("No user assistance")
     prompt_generator.add_constraint(
-        'Exclusively use the commands listed in double quotes e.g. "command name"'
+        "Exclusively use the commands listed below e.g. command_name"
     )
 
     # Add resources to the PromptGenerator object
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index 5d8791be..ad26e524 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -11,18 +11,18 @@ interactions:
       save important information to files.\n2. If you are unsure how you previously
       did something or want to recall past events, thinking about similar events will
       help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
       Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
@@ -49,7 +49,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3303'
+      - '3284'
       Content-Type:
       - application/json
     method: POST
@@ -57,21 +57,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4RSS2/TQBC+8ytGc7ajvNqmvsEBVA5wKKgSuIo264m9iXfX7IxJQuT/jhzbKUqq
-        cv3m8T1mjmgyTFAXSrStyvjuw9Ov8fxpM/7yuLefzObjD//5dkO733rz9REj9KsNaeknRtrbqiQx
-        3mGEOpASyjCZ3C6m94vp5H4aofUZlZhgXkk8G93EUoeVj8ez8QQjrFnlhMkRq+BtJUvxW3KMyd1s
-        HuHL7jM+uZlHKF5UeYYWi0UToS680cSY/DyiJR7WBl8SJqiYDYty0or0Tsi1Bo6pAwBIUQpf54Vw
-        ign0YF+gvbRgig/Aha/LDFhUEFgdIJDKjMtBCgLjWEKtW6m8nIxkL7A2JUHNQ0fbvTxh2lurXDZK
-        MfqXKpBi74zLO75vBcHaBBZgoQoMg3ioXUah9ZFdscIAiuItgxRKwBFl7diKoKKw9sHSFW1VKtcx
-        xvCd6XWt7ZIWfMtrmroY3jtVHv7Q6+oyEgrWuK7saN954wtFOhgx2rAdgh9skOM6UGft4c0s+seh
-        8gArWvtAUAWviU732hkpQLlDl9RlHlyR2g7MO1OW/z/4yf4oxW5NEw1f1Yd39VROWeoYzkFfiFAh
-        v/zFrtD2voxfX2IQcRLS60ldg02Ea+MMF8vuzTBBFl9hhMZltMdk3Dw37/4CAAD//wMA9lTsMQoE
-        AAA=
+        H4sIAAAAAAAAA4RSS2/TQBC+8ytGc7ajOKFJ8K0IAQWJA2q5YBRt7LG9dL3r7oxpQuT/Xm0cpyip
+        yvWbx/eY2aMuMMW8VpI3rYmXH/lLeftjd/3tQ1Ju33cru/jz9fvd52L28GmGEbrNb8rlODHJXdMa
+        Eu0sRph7UkIFpsli9XaarKaLZYSNK8hgilUr8XxyFUvnNy6ezqcJRtixqgjTPbbeNa2sxd2TZUyX
+        s3cRPu8+4cnVPEJxoswJWq1mfYR57XROjOnPPTbE41rvDGGKilmzKCtBpLNCNhjYZxYAIEOpXVfV
+        whmmcASPBdpKADO8Aa5dZwpgUV5gswNPqtC2AqkJtGXxXR6k8jqZyFag1Iag47EjdK8PWO6aRtli
+        kmH0L5Unxc5qWw18tzVBqT0LsFALmkEcdLYgH3wUF6wQwMdaSWj19NBpTwW4Eho6Z2qNsgNJDHdM
+        L8sLdAF8zV6W2RiurTK7v/SyoIKEfKPtULa0HezwmaLca9G55mbM2hIdFJDlzodhJXADZWfM7tUQ
+        NlQ6T9B6lxMN13Fn1OdpcEvqfuR91Mb8/8IH85MMhzV9NL7RMbqLL7KqoYHhFPOZCOWr8+cbCqH3
+        efzyDqOIg5Cjnsz22EdYaqu5Xg9/hSmyuBYj1LagLabT/lf/5gkAAP//AwDiG6xl+wMAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c0ba80d58dc16a2-SJC
+      - 7c6e71f9cbf01ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -81,7 +80,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 01 May 2023 23:03:18 GMT
+      - Sat, 13 May 2023 22:47:59 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -91,9 +90,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '6136'
+      - '11444'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -105,13 +104,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86495'
+      - '86494'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.336s
+      - 2.337s
       x-request-id:
-      - 0be816ead27a5540ee282bab5022d63f
+      - 7ae25ff182a7c0ffb3574db283d1da70
     status:
       code: 200
       message: OK
@@ -140,16 +139,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBBG7/6K8J03JUlRmz16KHrQgwiKImW7mTZbk5k1O6GlJf9dClWvD97j
-        nRAaWPjWqe9jl9/evX7XI78f54/j8uXpfpPqt+fdsjru6oOHgax35PVizLz0sSMNwjDwAzmlBra8
-        WVT1oqqK0qCXhjpYbKPm89l1ruOwlryYFyUMxuS2BHtCHKSPulL5Ik6wdWXwn/7HBirquj9QFuVk
-        4FsJnhLsxwk9pd/mIB3BwqUUkjrW86GwEp/vH7K9S9nlOHPcZCzaBt5mTPusdSlrXYzE1MwwGWwC
-        h9SuBnJJGBZJJcIgcEMH2GL6nK5+AAAA//8DABCIDMBJAQAA
+        H4sIAAAAAAAAA0SOQWvCQBBG7/0Vy3feSFK1jXtvQRF6aimUIutmNFuTnSUzYqnkvxfB1uuD93hn
+        xAYOofUa+twVj8+y0mNYPK3ljef1Tz/z6/ny/fQaDi8rWPD2i4JejUngPnekkRMswkBeqYGrHupZ
+        WdVlXVn03FAHh33WYjqZF3octlyU07KCxVH8nuDOyAP3WTfKB0oCt7i3uKVv2EJZffcPqrIaLULL
+        MZDAfZzRk/w1B+4IDl4kivqkl0NOSulyvzQnL+Z6bHxqTGJtY9qbRCfTejGtz5kSNROMFruYorSb
+        gbxwgoMoZ1jE1NA3XDl+jne/AAAA//8DACzKsGlJAQAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c0ba8446a3e16a2-SJC
+      - 7c6e7251df381ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -159,7 +158,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 01 May 2023 23:03:22 GMT
+      - Sat, 13 May 2023 22:48:02 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -169,9 +168,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '905'
+      - '889'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -189,7 +188,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - 904792458bdfabc0ed4f7fe647a44b3a
+      - f6610e14da3a22deb33c7ea09f53072e
     status:
       code: 200
       message: OK
@@ -205,18 +204,18 @@ interactions:
       save important information to files.\n2. If you are unsure how you previously
       did something or want to recall past events, thinking about similar events will
       help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
       Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
@@ -238,13 +237,13 @@ interactions:
       use, and respond using the format specified above:"}, {"role": "assistant",
       "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
       the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and the tasks that need to
-      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
-      instructions_1.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
-      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
-      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      \"The first step is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will start by reading the instructions
+      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
       the file instructions_2.txt"}, {"role": "user", "content": "Determine which
       next command to use, and respond using the format specified above:"}], "temperature":
@@ -257,7 +256,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4447'
+      - '4413'
       Content-Type:
       - application/json
     method: POST
@@ -265,21 +264,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4ySTW/bMAyG7/sVAs9OkDhp1/rW3YqdBnQosHkIFJmJ1ciUJ9JN3MD/fZCdjyLp
-        sF358fLhS+7BFpCBKbWYqnajz1+efz+0/PV1OZu9LF+/Vc189rbc8Pzpx3MLCfjlCxo5dIyNr2qH
-        Yj1BAiagFiwgm97epfd3aTpJE6h8gQ4yWNcymo1vRtKEpR9NZpMpJNCwXiNke6iDr2pZiN8gMWT3
-        t/MEztqn+PTmLgHxot05NE3TLgFTemuQIfu5hwr5qBu8Q8hAM1sWTRIpPQlS3GCfk1JK5SClb9al
-        cA6ZOgQPCdxJDObwVKIi3ImyxBIaE7GUZSVeBdSFkhLfp3iRjmUnamUdqoYtrfuKWLroY8ZXlaZi
-        nEPyfmBAzZ4src9T/6bq7AZdq+I62hIrXRQ2FmmnLK18qHTPKKWWCEpooi2hjcgHa7GHEs0bvgSp
-        naaBYaS+M35M/z/b5zmN1ANp177hVZ2KIgUKhsrSkO5NZsGaL4hMsGKN5WrAelSE2BMgcRNwWPRR
-        NVRgiLe+pjqt7Vq1xJUPqOrgDWIR77O1UipN7cd+cI16c5y8tc79++zkt+McBpEuOf7awbqrVyNd
-        4aB/svkCQYf15YcOiVh7br/GOUL0IAeenDroElhZslwuhreDDFh8DQlYKnAH2aT71X36AwAA//8D
-        AMDPrbAhBAAA
+        H4sIAAAAAAAAA4xTS2/TQBC+8ytGc3aiPEib+tYiQOXUQxESGEUbe2IvXc9Yu2OaEOW/o7WTpjgg
+        cbO+mZ3vMeM92gJTzCujed240fWH8Km9ubuezxdPD3fh4wPdvqsf399/3XxZNJigrH9QrscX41zq
+        xpFaYUww92SUCkynV8u3k+lyspwlWEtBDlMsGx3Nx4uRtn4to8l8MsUE22BKwnSPjZe60ZXKE3HA
+        9GaxTPA8+wWfXs0TVFHjztB0Nj0kmFdicwqYfttjTeE014sjTNGEYIMa1qhSWImjg33GAAAZaiVt
+        WWnIMIUjeCzQViOY4WNFwLRVsBzUt3mUBTaACngyBWhFr0thNRvrVmFjHUEbLJddR2xddVgudW24
+        GGeYvCb0ZIKw5bJnvQcmKiLJRpyT5wsasNxh4gvy8WsHxhOU9idxfEYcWk+glVG4h0KARaG2IYDh
+        Hdi6ER9jgaDUhKGYxhnudYzgc6C/O/ifBLKMR3DLxu1+0aWFOKQgJV9b7std0J2kgaLcW7W5DfUw
+        nj99blrndtByQT5u/VIbrGkjnqDxkhMV3XpkQD1MIzRknk68z9Y5YHn+l/XO9jjDfsAhOV3aMbSL
+        Q2NTUz/7JeABvfHl8D77Quw9P7/cwElEJ+SoJ+MDHhLcWLahWvVHhykGlfiLWy5oi+nk8P3w5jcA
+        AAD//wMA+R5NNh8EAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c0ba84ab86f16a2-SJC
+      - 7c6e7258bcda1ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -289,7 +288,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 01 May 2023 23:03:30 GMT
+      - Sat, 13 May 2023 22:48:15 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -299,9 +298,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '8196'
+      - '12253'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -317,9 +316,9 @@ interactions:
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.355s
+      - 2.354s
       x-request-id:
-      - 1d952b657e5c0345769483734723e74f
+      - 1f8b7eec7a22f88981895ea8418351db
     status:
       code: 200
       message: OK
@@ -349,16 +348,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SPPUsDQRRFe3/FcOvZsB9Ek+m0CxZaiBYiYZx9ZibZ+ci+F2II+98loqQ9cA/n
-        nhF6GDhvxcUyVHcPb/vHg39d7rbt8liv9ifuntyzoxd77KGRP7fk5G8xczmWgSTkBA03khXqYZrb
-        RbtctG3TasTc0wCDTZGqm80rOYyfuaq7uoHGge2GYM4oY45F1pJ3lBimaWuNq/vK5xqSxQ5X0s0n
-        DedzcMQw72dE4n/rmAeCgWUOLDbJpTEnoXTpv2dlFZ9YKGq1UiM5OwxKvBWVsviQNirRUXnLyttS
-        KFGvOCRHKp7U79WQ0wyTxldIgf16JMs5wYAlF2iE1NM3TD19TDc/AAAA//8DAHxrB+lmAQAA
+        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJTHG2tn5gSAF68qFImU6eW2mJvOGvFe0lP53qSjdHriH
+        cw+ILRxC5zUMuS+mjzKfKc9F/bBYbx9ile+q5m3x/HL/WsOCV1sK+reYBB5yTxo5wSKM5JVauOr6
+        5qqsbsrZ1GLglno4bLIW9aQpdDeuuCjrsoLFTvyG4A7IIw9Zl8qflASuuiwtzu4zbyyU1fdnUjdH
+        i9BxDCRw7wcMJP/WkXuCgxeJoj7pqZGTUjr134rxRvaiNFjzZEYKvu+Ndl5NYu1i2phEX6bzYjqf
+        MyVqjcQUyAx783s1cprgaLGOKUq3HMkLJziIcoZFTC19w5XHj+PFDwAAAP//AwBdjPuCZgEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c0ba88e2e6416a2-SJC
+      - 7c6e72b57cf81ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -368,7 +367,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 01 May 2023 23:03:33 GMT
+      - Sat, 13 May 2023 22:48:18 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -378,9 +377,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '948'
+      - '1057'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -398,7 +397,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 107ms
       x-request-id:
-      - 61597fd793784b1c948c5882e2444b63
+      - 4ed343ce9db17e267d0da6562c9af456
     status:
       code: 200
       message: OK
@@ -414,18 +413,18 @@ interactions:
       save important information to files.\n2. If you are unsure how you previously
       did something or want to recall past events, thinking about similar events will
       help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
       Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
@@ -448,10 +447,10 @@ interactions:
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
       \"I will start by reading the instructions file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
@@ -459,14 +458,14 @@ interactions:
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The instructions_2.txt
-      file likely contains additional information that is necessary to complete the
-      tasks.\",\n        \"plan\": \"- Use the read_file command to read the instructions_2.txt
-      file\\n- Analyze the instructions and determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
+      the instructions in the order they are given to ensure that I do not miss any
+      important steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_2.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
@@ -478,7 +477,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5489'
+      - '5453'
       Content-Type:
       - application/json
     method: POST
@@ -486,21 +485,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4ySTW/bMAyG7/sVAs92UCdomvrWnpptp2HFMMxDoMiMrVmiPIlekgX574NspymS
-        DtuVHy8fvuQBdAk5qFqysq1J7x6//Pz4qJ9/ET+9/zr9xNbPm/Vy/qF52jxAAm79AxWPHRPlbGuQ
-        tSNIQHmUjCXk2XwxvV9Mp9ksAetKNJBD1XI6m9ym3Pm1S29mNxkk0AVZIeQHaL2zLa/YNUgB8iy7
-        yxI4i58Tt4sE2LE059Bsen9MQNVOKwyQfzuAxXAS9s4g5CBD0IElccR0xEhxhUNBQghRANeuq2oO
-        BeRiDI4J3HEMFvC5RkG4Y6EpsO9UxBI6CHbCoywF1/g6FVazCe9YbLRB0QVNVV8RS1d9TDlrJZWT
-        ApLXAz3K4EhTdZ76N1WjGzR7EdeRmoKQZaljkTRC08Z5K3tGriVHUEIVbfH7iDxaiz0Uy9CES5DW
-        SBoYUvEc8G36/9m+KCgVDyTN/jde1YkoUiKjt5qGdG9yYGzDBZHymrXSwQ5YS0GIPQFS6DwOiy5F
-        RyX6eOtrqpe1zV6sceM8itY7hVjG+2w110LS/m0/QouyOU3eamP+fXZy20kBg8gxOf3aaN3Vq5G0
-        OOi/2HyBIH11+aFDItae269xThA9yMhT0BGOCWw06VCvhreDHAK7FhLQVOIO8pvj9+O7PwAAAP//
-        AwBEf5dDIgQAAA==
+        H4sIAAAAAAAAA4xS32/TQAx+56+w/JxWLYFuyxsTQprQXioQ2shU3S5ucuxiR3cOa1f1f0dJWjpS
+        kHg7ffb5+2Hv0BWYoa2M2rrxk4tP8fP1t4/317fLt3F5t7x/sdXCzuWu8LdPmKA8/iCrhx9TK3Xj
+        SZ0wJmgDGaUCs/ni8t1sfjm7ukqwloI8Zlg2Okmn7yfahkeZzNLZHBNsoykJsx02QepGVypPxBGz
+        +fxiluBp+KmwSBNUUeNPUJqm+wRtJc5SxOz7DmuKx8FBPGGGJkYX1bB2MoWVuLOwyxkAIEetpC0r
+        jTlmcAAPBdpoB+b4pSJg2ig4jhpa28kCF0EFApkCtKLXpbhKp7pRWDtP0EbHZd/Rta56zEpdGy6m
+        OSavCQOZKOy4HFhvgImKjmQt3svzGQ047jEJBYXutQUTCEr3k7j7RhzbQKCVUbiBQoBFoXYxguEt
+        uLqR0MUCUamJYzGNNzzomMDXSH938D8J5DlP4AMbv32hcwvdkIKUQu14KPdB95JGimxw6qyL9Tie
+        P32uW++30HJBodv6uTZ4pLUEgiaIJSr69ciIepxGbMg8HXmfnffA8vwv673taY7DgH1yvLRDaGeH
+        xqamYfbvgEf0JpTj+xwKXe/p+/kGjiJ6IQc9Oe9xn+DasYvVajg6zDCqNJig44I2mM32D/s3vwAA
+        AP//AwCoFi8sIAQAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c0ba894ed8e16a2-SJC
+      - 7c6e72bd7c821ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -510,7 +509,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 01 May 2023 23:03:42 GMT
+      - Sat, 13 May 2023 22:48:30 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -520,9 +519,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '8779'
+      - '11882'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -534,879 +533,94 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86452'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.365s
-      x-request-id:
-      - fee70e84f36b122cc0aef0db455f5eda
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPy07DMBBF93yFNWunStKmLd7BAhUJseUlVLnOtDG1PSYzLURV/h0Vgbo90j06
-        9wS+BQOus+JiDsXi9unzeTtrs22Oq7vSD48vr4tjGfYPdjWABtp8oJO/xcRRzAHFUwINrkcr2IKp
-        5sv6elnXdaMhUosBDOyyFNNJU8ih31BRTssKNBzY7hDMCXJPMctaaI+JwVT1XMPFfeGNBiGx4UJm
-        1ajBdeQdMpi3E0Tkf2tPAcGAZfYsNsm5kZJgOvffsLKKBxaMWt2rHp0NQUlnRSWSzqedSvilOsuq
-        szljwlaxTw5VHNTvVU9pAqOGrU+eu3WPlimBARbKoMGnFr/BlOP7ePUDAAD//wMASuwubmYBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0ba8dc5ff216a2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 23:03:46 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '925'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89832'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - a74d4954eeca5e3fb830e104f9527193
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The instructions_2.txt
-      file likely contains additional information that is necessary to complete the
-      tasks.\",\n        \"plan\": \"- Use the read_file command to read the instructions_2.txt
-      file\\n- Analyze the instructions and determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The instructions_3.txt
-      file likely contains additional information that is necessary to complete the
-      tasks.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
-      file\\n- Analyze the instructions and determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6524'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SSy47TQBBF93xFqdZOlDgkk/GSHUIIFjOQER5FnXbZbmJ3me4yySjyvyM/gidG
-        CLGtx73nluqCJsEIda5El1Uxu3v39cfTYfNxeZ/stutTvtMPu0/n44enz49fUgyQD99Jy7Ax11xW
-        BYlhiwFqR0oowWi52Yb32zAMNwGWnFCBEWaVzFbz9Uxqd+DZYrVYYoC1VxlhdMHKcVnJXvhI1mO0
-        XN1tAhzFx8YmDFBYVDGW1qttE6DO2WjyGH27YEn+Kuy4IIxQeW+8KCstJlsh20a4xBYAIEbJuc5y
-        8TFGMBSHBp2lLcb4kBNYOgsY68XVusUC40EYTs4IgeQEovxxbxIwVrgrpKYg4FqqWuZyFqi9sVnX
-        6Zb2wvtuRHNZKpvMYwxe2ztSnq2x2cjw28KDKSt2bSgwNmVXqo5JciVgiZKO7UDg1U9KIGUHaS21
-        I3CUkiOraWpXFcr2TjN49PR3zn+kfhW43Zq4aGfEaOPL3up9B9sqkvUtXhdAbqO2ZkIWNDtHWooX
-        6Ciukx2b8UPUynFFrniZxvMVqePV9GSK4j8ygOXTPMZergmujzPc44+/saqk3unmfhMg5bLpy/WN
-        dnaUGFFu9qcfGq6Wb6+EHeUAG9sGmwBTY43P9/1LYYReuMIAjU3ojNGieW7e/AIAAP//AwDTX575
-        DAQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0ba8e29de016a2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 23:03:55 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '9356'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86443'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.371s
-      x-request-id:
-      - 5f590ec504889866cee5d378c1c56737
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPy07DMBBF93yFNWunStP0gXfACqkbYFEkhCrXGRpTZ8ZkppRS5d9REajbI92j
-        c08QG3AQWq+hy6mY364+dmV++v6sH1ItxOmwnN89h+WqfpyCBd68Y9C/xShwlxNqZAILoUev2IAb
-        zxbV9aKqJgsLHTeYwME2azEZTQvd9xsuykk5Bgt78VsEd4Lcc5d1rbxDEnDjambh4r7wqQVl9elC
-        6vFgIbQcAwq4lxN0KP/WnhOCAy8SRT3puZFJkc79N2K8kaModtbcmx6DT8lo69UQaxtpawgPpvVi
-        Wp8zEjZGIgU03dH8Xo1MIxgsvEWK0q579MIEDkQ5g4VIDX6BK4fX4eoHAAD//wMAp9wyGmYBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0ba92baa3a16a2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 23:03:59 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '958'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89832'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - 9fe1a228b9592784a0e00ed11fb84d69
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The instructions_2.txt
-      file likely contains additional information that is necessary to complete the
-      tasks.\",\n        \"plan\": \"- Use the read_file command to read the instructions_2.txt
-      file\\n- Analyze the instructions and determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The instructions_3.txt
-      file likely contains additional information that is necessary to complete the
-      tasks.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
-      file\\n- Analyze the instructions and determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to write the task_id into the file output.txt using
-      the write_to_file command.\",\n        \"reasoning\": \"The task_id is important
-      information that needs to be saved for future reference.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
-      \"I need to ensure that the task_id is written correctly and that the file is
-      saved properly.\",\n        \"speak\": \"I will write the task_id into the output.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7518'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA3ySy47TQBBF93xFq9adKA+GZLwDsRlWiAEhgVHUaVfsJv2iqzx5yf+OYjvEZAa2
-        1V33nrpVJzAFZKArxdpFO1q8+/rLOj2dP71PH+OH4yHteRc/fTsenXsECWH9EzX3HWMdXLTIJniQ
-        oBMqxgKy6Zvl7H45m83vJbhQoIUMysij+fhuxHVah9FkPpmChJpUiZCdIKbgIq84bNETZNO75UTC
-        Vfz68HohgQMrey0tZotGgq6C0UiQfT+BQ7oIp2ARMlBEhlh5PmMGz+jPI5xyL4QQOXAV6rJiyiET
-        fbF/wD2fizl8rjChUAmFD2JTJ64wCeOJU63PiCSMF1yh2BiLNBYPgqpQ20JQVbMowq57pQMxOlGT
-        8WVbYEXbVT8pCh2cU74Y5yCHGAkVBW982bE8Gq/x3P1/Ijl0rBSJi00hDFPrLJQvLqBrvLLeAkSr
-        fOc9El8I/00uOLw48Y2eToaNNuQ60QfhEdte9FSns77iIb2hgWpMIWKyhxa+/ams7XJv4yD1hM8i
-        pIhqe3HbGWtfXowPu3EOXWMjL/fRD/fsPLxy2Gn+FcaNtUrl7WUN19oJvLW2TXS4Jaq1RqJNbe3h
-        D1VL1gPmvoFGwsZ4Q9Wqk4MMiEMECcYXuIds0vxoXv0GAAD//wMALFWP5ucDAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0ba932296616a2-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 23:04:07 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '8287'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86445'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.37s
-      x-request-id:
-      - ead9c9628b3e17b7f53b848fa1361338
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3299'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4RSS2/TQBC+8ytGc7ajBJMm+EZvBYlLWxDCVbTZHdtL7F2zM1YTIv935NhOUVKV
-        6zeP7zFzRGswRV0q0XVTxavbw/eHj7xafrNG3jc/5Mvq6+r+5vPtff77ESP021+kZZyYaV83FYn1
-        DiPUgZSQwXRxs07m6/XNIomw9oYqTLFoJE5my1jasPXxPJkvMMKWVUGYHrEJvm5kI35HjjFdJUmE
-        L7vP+GL5IULxoqoztF6vugh16a0mxvTnEWviaW3wFWGKitmyKCe9SO+EXG/gmDkAgAyl9G1RCmeY
-        wgiOBdpLD2Z4B1z6tjLAooLA9gCBlLGuACkJrGMJre6l8mYxk71AbiuClqeOvntzwrSva+XMLMPo
-        X6pAir2zrhj4HkqC3AYWYKEGLIN4aJ2h0PswV6wwgaJ4xyClEnBEph/bEjQUch9quqJtKuUGxhge
-        mV7X2i/pwbe8ZpmL4ZNT1eEPva7OkFCorRvKjvaDN75QpIMVqy3XU/CTDXLcBhqs3b2Zxfg4VB1g
-        S7kPBE3wmuh0r2crJSh3GJK6zIMbUruJ+dlW1f8PfrI/y3BY00XTV43hXT2VUzUNDOegL0SoUFz+
-        4lDoe1/Gry8xiTgJGfVkrsMuwtw6y+VmeDNMkcU3GKF1hvaYzrun7t1fAAAA//8DAHJkh+YKBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c15ce3c5a414768-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 03 May 2023 04:37:03 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '9193'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86494'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.337s
-      x-request-id:
-      - a04fa61855d48102644e1caa13d320c7
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and the tasks that need to
-      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
-      instructions_1.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
-      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
-      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4443'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySTW/aQBCG7/0VoznbCEKhxLcmUqRekqpqFal1hJb12F5Yz1q7YwFF/PfK2ITU
-        VG2v8/HOMzPvAU2GCepSia5qG3+42z/n9+vN93z18KXyT8+P66d7+vxw937z6DBCt1qTlr5jpF1V
-        WxLjGCPUnpRQhslkvpiOF4v5zSzCymVkMcGilng6msXS+JWLx9PxBCNsgioIkwPW3lW1LMVtiAMm
-        t/NphBft1/hkNo9QnCh7CU0mt8cIdemMpoDJjwNWFM663lnCBFUIJohiaSkdC3G7wSFlAIAUpXRN
-        UUpIMYE+2CdoJ20wxU/ARBmIA08qAykJDAfxjW4Bw/JmJDuB3FiCJhguThVt6fIU066qFGejFKO3
-        +p5UcGy46IZ8/Ytqi60Mh5Mw004gkIDLf2sAKZXAhTV31rrtcGptFXcDY/gW6M+o/7NqmnIMH1nZ
-        /U+6qoNWJCMhXxmmN9hCdRgQaW/EaBOq4bGJQ+PpvFbDGfn2j9dU0LuF7B5WlDtPUHunibL2GVsj
-        JSjeg6iwCcN7hJrU5jx5a6z994/5dNVO5BidfdSf7spGrCrq9F/PPEBQvhi6r0u0tZf2a5wzxAmk
-        50n5iMcIc8MmlMvOY5hgEFdjhIYz2mEyPr4c3/0CAAD//wMAoEBxWf0DAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c15ce845a364768-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 03 May 2023 04:37:15 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '9780'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86466'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.356s
-      x-request-id:
-      - a13e9d3f6199be49b0b0e945e7d7b1ce
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5449'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySTY/TQAyG7/wKy+ekagnbrXIDDmgFAg5dgURQNZ04ydCJJ51xaEvV/47SpHRJ
-        EXD1x+vH9ntEk2OKulKi68bG968On/zj9v1WvW6Lx3eHZfF2+2b3+cP8+8eHJUbo1t9Iy9Ax0a5u
-        LIlxjBFqT0oox3Q2XyTTxWKe3EdYu5wsplg2EieTu1hav3bxNJnOMMI2qJIwPWLjXd3IStyGOGA6
-        m80XEV7Fr4m7eYTiRNlrKHn+4hShrpzRFDD9csSawkXYO0uYogrBBFEsHaZjIe5WOGYMAJChVK4t
-        KwkZpjAEhwTtpQtm+ABMlIM48KRykIrAcBDf6g4wrJKJ7AUKYwnaYLg8V3Slq3NMu7pWnE8yjJ7q
-        e1LBseGyH7L8i2qHrQyHszDTXiCQgCt+awCplMCVtXDWut14amMV9wNjeAz0Z9T/WTXLOIaXrOzh
-        B93UQSeSk5CvDdMTbKEmjIi0N2K0CfX42MSh9XRZq+WcfPfHWyoY3EL2AGsqnCdovNNEefeMnZEK
-        FB9AVNiE8T1CQ2pzmbwz1v77x3y+ai9yii4+Gk53YyNWNfX6v848QlC+HLuvT3S11/ZbnAvEGWTg
-        yfiEpwgLwyZUq95jmGIQ12CEhnPaYzo9fT09+wkAAP//AwBwW9n7/gMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c15cecdea334768-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 03 May 2023 04:37:26 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '9295'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86459'
+      - '86458'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
       - 2.36s
       x-request-id:
-      - ecfa6ef54add3f6517ceb72c53d46f7d
+      - 39cdfabe68f349bf436b0f9f27e465ba
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
+      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '740'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPy0oDQRBF935FU+ueMG0eht65UBIEEQSjiIROT5lpM1PVTlWiSZh/l4iS7YF7
+        OPcIqQIPsQ4a29wUV7dy93Bwi6fq+TB7nN/Mq81uN/u8Hy0SvYAFXn1g1L/FIHKbG9TEBBZih0Gx
+        Au8m01Hpps4NLbRcYQMe1lmL4WBc6LZbcVEOSwcWthLWCP4IueM261J5gyTg3eXEwtl95mMLyhqa
+        Mxm53kKsOUUU8K9HaFH+rR03CB6CSBINpKdGJkU69V+LCUb2othaMzcdxtA0RuughljrRGtD+GXq
+        IKYOOSNhZSRRRNPuze/VxDSA3sJ7oiT1ssMgTOBBlDNYSFThN/iyf+svfgAAAP//AwCOX/o2ZgEA
+        AA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c6e731898091ca8-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 May 2023 22:48:34 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1076'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89832'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - fcc155dfdde6eac2ead0dd975dc269d1
     status:
       code: 200
       message: OK
@@ -1422,17 +636,17 @@ interactions:
       save important information to files.\n2. If you are unsure how you previously
       did something or want to recall past events, thinking about similar events will
       help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
@@ -1456,37 +670,37 @@ interactions:
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
       \"I will start by reading the instructions file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
       "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
+      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
+      the instructions in the order they are given to ensure that I do not miss any
+      important steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_2.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
+      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
+      the instructions in the order they are given to ensure that I do not miss any
+      important steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_3.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will now read the instructions_3 file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: Write the task_id
       into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
       which next command to use, and respond using the format specified above:"}],
@@ -1499,7 +713,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6448'
+      - '6486'
       Content-Type:
       - application/json
     method: POST
@@ -1507,20 +721,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5RSy27bMBC89yuIPdOCFTmOq2MOAQKjD/QBBKgKgaE2EmuJK3BXtQtD/17IsqFE
-        RQ++znBnZpdzBFdACrYyYpu2Xtzd/3m6eTIfGLe/P9Zfw2f88n5rHg6ftpt9AA30/AutnCciS01b
-        ozjyoMEGNIIFpPF6kyw3m/Vqo6GhAmtIoWxlkUS3C+nCMy2WyTIGDR2bEiE9QhuoaSUX2qFnSOPk
-        LtYwiU/EOtEgJKaeoNtk1WuwFTmLDOmPIzTIF+FANUIKhtmxGC9DTPKCfljhmHmllMpAKurKSjiD
-        VJ3BM4EHGcAMHpVHLJSQ2gcnqKRCJYZ3uSuU80IngDppO4nkIOrF1ag6dr48MaehXCg/4Zaaxvgi
-        ykC/dgtomLzz5Wj5rULlPEvo7HAEzpNJuTKsDO+wUA1eF2pu2tbGj34L9Z3x/2mvs5m52ODEWcfN
-        /JrouQuDpBH1+ErfUgho5ep1uEWzu5jsXV1f81+e9lEGo1yvL+047/9PObxpcHR6c69ZIBPKea9G
-        Yng7SUxR3szPa3iTxKtLwlPKc9jM99BreHHecZWPRYIUWKgFDc4XeIB02f/s3/0FAAD//wMAl/Cn
-        d/EDAAA=
+        H4sIAAAAAAAAA5SSQWvbQBCF7/0Vy5zXRqqdxOgYSCANlLq00FIFs1lNpK1XM8ruqHYx+u9Fll0n
+        CqX4+mbnvW+WtwNXQAa2MmLrxk+ubuP98uO1XV5fLdf+2423n79/ev71fP+hwt+ggR9/opXDxtRy
+        3XgUxwQabEAjWECWXi7mSbpI07mGmgv0kEHZyGQ2vZhIGx55ksySFDS00ZQI2Q6awHUjK+E1UoQs
+        nS0SDSfz0+Ay0SAsxp+ki3nSabAVO4sRsh87qDEejQN7hAxMjC6KIekxmQSpP2GXk1JK5SAVt2Ul
+        MYdMHcTDALfSizl8qVARbkU5ihJa22MpF5Ww2gQnqKRCJSauV65QjoT3ArfStDKVragn51G10VG5
+        n+yXVsKrvW65rg0V0xz0y/iAJjI5KgeGO0WIxZmRJv5FxjcBjTc0eE/U14j/JjsvdJRigxNnXazH
+        ZyDFNvSWRtTdC3/LIaCV/+aMz4kNmvUxZOO8V8SbM7inOQx2nT5W43D/m2aQqXFIevVfIyATynGp
+        hkH/9mRxwni1P+7g+1k6PxLuKQ+wOXXQaXhy5GK1GkoDGUThBjQ4KnALWdI9dO/+AAAA//8DAHME
+        PM3uAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c15cf155f914768-DFW
+      - 7c6e732188531ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -1530,7 +744,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 03 May 2023 04:37:38 GMT
+      - Sat, 13 May 2023 22:48:45 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -1540,9 +754,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - significant-gravitas
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '9744'
+      - '10828'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1554,13 +768,93 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86457'
+      - '86455'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
       - 2.362s
       x-request-id:
-      - 9a91f5f1047315a3b543a4b85d42e4d3
+      - 75d8adb85d3b410b0713cc5013917627
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
+      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '740'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJemXYXZuilKwbkREpEwnz2Q0My/mvaKl9L9LRen2wD2c
+        e0Rs4BA6ryENfXG9kjV9zm6f1vOHepPKR76Pbb3abJ6pjbDg3TsF/VtMAqehJ42cYRFG8koNXLWs
+        52VVV9PaInFDPRzaQYvZZFHoftxxUc7KChZ78S3BHTGMnAbdKn9QFrhqurS4uC98YaGsvr+QeXWy
+        CB3HQAL3ckQi+beO3BMcvEgU9VnPjZyV8rn/Row3chClZM2dGSn4vjfaeTWZtYu5NZm+TOfFdH4Y
+        KFNjJOZAJh3M79XIeYKTxVvMUbrtSF44w0GUB1jE3NA3XHl6PV39AAAA//8DAHlgRXBmAQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c6e73737ca71ca8-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 May 2023 22:48:49 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1176'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89832'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - 7c5a28d7a495d8394ae5b8e9f041be39
     status:
       code: 200
       message: OK
@@ -1576,17 +870,17 @@ interactions:
       save important information to files.\n2. If you are unsure how you previously
       did something or want to recall past events, thinking about similar events will
       help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
@@ -1610,47 +904,47 @@ interactions:
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and the tasks that need to be performed.\",\n        \"plan\": \"- Use the read_file
-      command to read the instructions_1.txt file\\n- Analyze the instructions and
-      determine the next steps\",\n        \"criticism\": \"I need to ensure that
-      I understand the instructions completely before proceeding with any tasks.\",\n        \"speak\":
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
       \"I will start by reading the instructions file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
       "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
+      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
+      the instructions in the order they are given to ensure that I do not miss any
+      important steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_2.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file now.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
+      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
+      the instructions in the order they are given to ensure that I do not miss any
+      important steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_3.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will now read the instructions_3 file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
       {"role": "system", "content": "Command read_file returned: Write the task_id
       into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
       which next command to use, and respond using the format specified above:"},
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to write the task_id into the output.txt file using the write_to_file
-      command.\",\n        \"reasoning\": \"The instructions_3.txt file has asked
-      me to write the task_id into the output.txt file.\",\n        \"plan\": \"-
-      Use the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
+      \"The next instruction is to write the task_id into the output.txt file using
+      the write_to_file command.\",\n        \"reasoning\": \"I need to write the
+      task_id into the output.txt file as instructed.\",\n        \"plan\": \"- Use
+      the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
       \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
-      \"I will write the task_id into the output.txt file now.\"\n    },\n    \"command\":
+      \"I will now write the task_id into the output.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
       \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
       "system", "content": "Command write_to_file returned: File written to successfully."},
@@ -1664,7 +958,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '7415'
+      - '7450'
       Content-Type:
       - application/json
     method: POST
@@ -1672,19 +966,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA3SRTW+bQBCG7/0VqzmvLZAT4nJLpRwi5UM9RKpUKmu9jGHrZZYwQ53I4r9XBGwc
-        ql7n432feecILocUbGnEVrVf3Hx7/3F39f1Z7m8fVnGMr4/7O3p8fXmqkuctaAjb32hl3FjaUNUe
-        xQUCDbZBI5hDGifrVbReJ0mkoQo5ekihqGWxWl4vpG22YRGtohg0tGwKhPQIdROqWjYS9kgMaXx9
-        k2iYxKdGvNIgQYyfSsn6a6fBlsFZZEh/HqFCPgk3wSOkYJgdiyHpMQMJUn/CMSOllMpAytAWpXAG
-        qRqLYwPfpC9mcK9K8wfVyIS5Mt4rKVGJ4T0rQ7kixFxJUFy2kocDqZYdFeehzWm3F6kM5csM9KVZ
-        g4YDOSoGx9vRwBFL09o+Bx4gtoikdsH7cOhBKD97KMdnxLl87Q0Nygv1wvh/rssbZhq2ceKs42oQ
-        egqEswmu0exPkR2c91McFA7LDIbhTp+yH03/iZ5MhYPOJ8iZnWmK+dcuw7xI8uNN0/u4tRaZd633
-        72eqD7IRMKMOOg07R47LzSAHKbCEGjQ4yvEN0qj71X35CwAA//8DACgd2nRDAwAA
+        H4sIAAAAAAAAA3ySTW/aQBCG7/0VozkbhCEQ4huHpkKRekmjHuoKLeuxvWW9a+2MQyrk/175A0jp
+        x3V293mf1+MTmgwT1KUSXdV2cv/IT/nnTShW4XFzXJpP86/PH/0L19uneoMR+v0P0jK+mGpf1ZbE
+        eIcR6kBKKMMkXq3vZvE6nj9EWPmMLCZY1DJZTJcTacLeT2aLWYwRNqwKwuSEdfBVLTvxB3KMSbxc
+        zyO8wq8Hi7sIxYuy19F9vGoj1KU3mhiTbyesiM/g4C1hgorZsCgnnaZ3Qq6rcEodAECKUvqmKIVT
+        TGAcjgf0Jt0wxS8lBQIVCJyHvAlSUgDjWEKjO0UG40BKgtxY4ilsgUvf2Ay4bAQyf3TQsHFFf0cU
+        H3ZjPQLtq0q5bJpi9D47kGLvjCsGgWfjNHWv/68R/S1ZPGjvmMIrQSD2TdDEt3m1VW6ImsAL079F
+        O9yFfQPRwYjRhquBtAVH1D8gx03ooEpgC6V67XE9NwNl7SWOYU+5D9RHSPfFuphbWa5JHc4ZR2Mt
+        OH+8Wk1THG630XnHo/wfK3aqogH0W9mbPBWK27/j/ZYGwKar0Ve4VuNGa2LOG2t/Xqx6s1EwdS22
+        EebGGS53Aw4TZPE1RmhcRm+YzNrv7YdfAAAA//8DAIvSo2SrAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c15cf5f5f494768-DFW
+      - 7c6e737d1e1e1ca8-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -1694,7 +989,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 03 May 2023 04:37:47 GMT
+      - Sat, 13 May 2023 22:48:58 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -1704,9 +999,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - significant-gravitas
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '6973'
+      - '9148'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1718,13 +1013,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86466'
+      - '86463'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.356s
+      - 2.358s
       x-request-id:
-      - 7cc602be91ae73e5f18b92f2743aef7d
+      - 700ee384862148376a49069a620d3068
     status:
       code: 200
       message: OK
diff --git a/tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml
index e73c396b..f76703b6 100644
--- a/tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml
+++ b/tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml
@@ -16,13 +16,13 @@ interactions:
       immediately save important information to files.\n2. If you are unsure how you
       previously did something or want to recall past events, thinking about similar
       events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file:
-      Append to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2.
-      delete_file: Delete file, args: \"filename\": \"<filename>\"\n3. list_files:
-      List Files in Directory, args: \"directory\": \"<directory>\"\n4. read_file:
-      Read file, args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file,
-      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6. browse_website:
-      Browse Website, args: \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
       Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
@@ -55,7 +55,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3782'
+      - '3767'
       Content-Type:
       - application/json
     method: POST
@@ -63,22 +63,22 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6RTS2/TQBC+8ytGc+nFeZe09QUBPVCJngBVAqNovZ7Y29g77u64CUT572jtuCWh
-        RTyu8/heu7NFk2GMulCiq7ocnL1Np2cfri8/p7PN/YfLef36li6zRjZ339+kGCGnt6RlvzHUXNUl
-        iWGLEWpHSijDeDI/n01n8/npWYQVZ1RijHktg9nw5UAal/JgPBtPMMLGq5ww3mLtuKplIbwi6zE+
-        P72I8BH7oT49nUYoLKp8KE3GF5NdhLpgo8lj/GWLFfke13FJGKPy3nhRVoJKtkI2ONgmFgAgQSm4
-        yQvxCcawL+4btJFQTPAKLFEGwtB4AikIUsdrT4s1pd4IgeaqUraduDfeCBQidTwapcwrPxT22qma
-        QmAjrUSVnDc0qigzooJFv5jNRsZmtBkWUpUQoJYm4BUEtTOagJcdL/NqmGD0s05HyrM1Nu/FamX/
-        WGiY6Zuh4Uk5XcCS3dPkkH4DY31NWozN2/K7j9fvQXNGx8LqUtlO0wA+/b2eJLEDuOq4DonC+PP5
-        tHs3LsA/9oVBwdKUBFZVlMHJoZChbOSkXeyFivKrxf4XHuh8qPVTR661M2K08dXx30kJtHK0bEpY
-        F2SfjTHMkvWNI7h6tKnZuRBEa+c4aV+TWvV8a1OW//z+v/12HeUu6k9nj/bL5YSIOzWH9EeqlcuP
-        r65rNK7s1v/rjA7YOuC7hnyY7NBvCiVg/NN2X/V2W8t754nd4S7CpbHGF4vu8DBGL1xjhC01xuPd
-        192LHwAAAP//AwBZhA00WgUAAA==
+        H4sIAAAAAAAAA6RTzU7bQBC+9ylGc+HiOA4hgHyp1EPaSO2hBcqhrqLNemIvsXfM7rggRXn3au0E
+        khRQ1d6sGc/3tzNrNDmmqEslum6qwcXU3U5no+/84eqjnt3JZFpc3Zx/+epXs08eI+TFHWnZTsSa
+        66YiMWwxQu1ICeWYjs4vz5LRJEnGEdacU4UpFo0MxvFkIK1b8CAZJyOMsPWqIEzX2DiuG5kLr8h6
+        TC/PJhE+Yz/VT89OIxQWVT2VRsnlxSZCXbLR5DH9scaa/A7XcUWYovLeeFFWgkq2QjY4WGcWACBD
+        KbktSvEZprAtbhv0KKGY4QweTFVB6wmkJFg4fvA0f6CFN0Kgua6VzUEYfhlvBEqRJh0OF8wrHwt7
+        7VRDIa2hVqIqLloa1pQbUcGfn4/HQ2NzeoxLqSsIUEsT8EqCxhlNwMuel3kVZxjti3SkPFtji17p
+        dUkgyq/A0X1rHHmoKQh7HRDYdt9bNzFcv+5QKwsLCjnsud0bfkH7sd6mUraXOoCbv8xzjyHL7ACm
+        r5rp2rcuoDz3hUHB0lQEVtWUw8khXyyPctIN7vSEAOfbBTyQ81Tb/XVkTjsjRhtf79bGUp8UWd+6
+        MKYEZqBqaL2xRQej2TnSAjffPnfx3bfkw1q8/WrHsfqG1OqflvXt5zvi7Ck30e52tmh/nE4Iuldz
+        SH+kWrni+Oz6Ruuqfvy/TumArQfepduj34b3MP5lu+93djvLW+eZ3eAmwqWxxpfz/vgwRS/cYIQd
+        NabJ5ufm3W8AAAD//wMAygoH/1sFAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23ec547cf7c30c-VIE
+      - 7c6e272b1ec93134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -88,7 +88,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:20 GMT
+      - Sat, 13 May 2023 21:57:00 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -98,9 +98,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '13677'
+      - '17055'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -118,7 +118,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 2.338s
       x-request-id:
-      - f087e73375928e99eea43f7daf78c450
+      - ac9eef12460b5b5a60595d2ab3b175b0
     status:
       code: 200
       message: OK
@@ -169,17 +169,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOzUrDQBRG9z7F8K0nIU1MbGdpVy66EKogVspkctuMTebGzC0WSp7GN/HJpOLP
-        9sA533eGb2DgWiuuH7rkZlnn93ersHg/Vu3YP9V290j+Iazd8vYNGly/kpMfI3XcDx2J5wANN5IV
-        amBm1bzIi6qqKo2eG+pgsB8kKdIykeNYc5IV2Qwax2j3BHPGMHI/yFb4QCHCXM9Ljf/2H89nGsJi
-        uz9SZtWk4Vr2jiLM8xk9xd/qyB3BwMboo9ggl48chMLl/7olNYzekeKdkpZUzXxQG6yo8WIvs3ED
-        5aP6/MjLdL7QyjrHY+PDXgl/G0InSTFp7Hzwsd2OZCMHGEThARo+NHSCyaaX6eoLAAD//wMAzURU
-        NmgBAAA=
+        H4sIAAAAAAAAA0SOzU7CQBRG9z7F5FsPpC2Un1kLceNGiWjUkGF6oSPt3DpzMSSEp/FNfDKDUdye
+        5JzvO8JXMHC1Fdd2TW88j8tNvPmYjfOnvLhbHGbz9Hj/LouH6/0SGrx+Iye/Rt9x2zUkngM0XCQr
+        VMHko8kwy8usmGq0XFEDg20nvUG/7Mk+rrmXDbIcGvtktwRzRBe57WQlvKOQYIaTUuO/feFFriEs
+        trmQMhudNFzN3lGCeT6ipfRXjdwQDGxKPokNcv7IQSic/y9qUl30jhRvlNSk1sw79YJbqrzY82x6
+        gfJJfX0WZX8y1co6x7HyYauEfwyhg/Rx0tj44FO9imQTBxgk4Q4aPlR0gMlOr6erbwAAAP//AwAj
+        R94saAEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23eccb8cf6c30c-VIE
+      - 7c6e27c6ffab3134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -189,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:27 GMT
+      - Sat, 13 May 2023 21:57:10 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -199,9 +199,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1587'
+      - '2084'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -219,7 +219,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 385ms
       x-request-id:
-      - eed7defd0a7c4dea6073247d0781f272
+      - cc9bd42a9e921979e228aaa14b778fdf
     status:
       code: 200
       message: OK
@@ -245,17 +245,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SQzUrDQBSF9z7FcNaT0CQmxlnqQlAE/6CClTKd3DZjk7khcwvF0qfxTXwyifiz
-        /eCc83EO8A0MXGvF9UOXnF2u8sdQX9/nDxzm2ZW8X+zKu35ON9vnARq8eiMnP4nUcT90JJ4DNNxI
-        VqiByaq6yIuqqmqNnhvqYLAZJCnSMpHduOJkVswyaOyi3RDMAcPI/SBL4S2FCFOdavxX/+E80xAW
-        2/2RujxquJa9owjzckBP8bdz5I5gYGP0UWyQyZCDUJjsn1pSw+gdKV4raUmtmLdqgVtqvNhpNS6g
-        fFSfH3mZ1udaWed4bHzYKOHvhNBeUhw11j742C5HspEDDKLw9JQPDe1hZsfX48kXAAAA//8DACbo
-        IMRmAQAA
+        H4sIAAAAAAAAA0SO20rDQBRF3/2KYT9PQto0Nc6bUESQiqBS0EqZTk6TscmckDnFSunX+Cd+mVS8
+        vC5Ya+8DfAUD11hxXd8m51fDopbb6fusKp/u3m5cV+f38+vHRVFdzqDB61dy8mOkjru+JfEcoOEG
+        skIVzGhaTrJRkeWZRscVtTCoe0nytEhkN6w5yfJsBI1dtDXBHNAP3PWyEt5SiDDTicZ/+g+PRxrC
+        Yts/UhZHDdewdxRhng/oKP42B24JBjZGH8UGOT3kIBRO7x8aUv3gHSneKGlIrZm3aok5VV7saTUu
+        oXxUnx/jIi0vtLLO8VD5UCvhb0NoLymOGhsffGxWA9nIAQZRuIeGDxXtYbLjy/HsCwAA//8DAIvt
+        4CVmAQAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23ecd6b8f5c30c-VIE
+      - 7c6e27d6e84e3134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -265,7 +265,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:29 GMT
+      - Sat, 13 May 2023 21:57:12 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -275,9 +275,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1434'
+      - '1692'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -295,7 +295,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 50ms
       x-request-id:
-      - 5fcc4683dce0ec6fdb70e8921ec529a9
+      - 3404f771d4b84e25f370b619b33d9b2f
     status:
       code: 200
       message: OK
@@ -324,16 +324,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBQG7/6K5TtvStJgW/eoIBSKePGgImWz+9qsJvuW7ItVS/67FKq9Dsww
-        RwQPA9dacX3qiuVdM3/a3NbVuAqfj5sfR8v7l/Hh+bts/Boa3LyTk7Mxc9ynjiRwhIYbyAp5mGqx
-        quf1YrEsNXr21MFgn6SoZ9eFjEPDRVmXFTTGbPcEc0QauE+yFf6gmGFu5hqX9AVrCIvt/kFVVpOG
-        azk4yjCvR/SU/5oDdwQDm3PIYqOcDjkKxdP9Wh1sVudjZaNXkaUNca8iHVRrs2ptShTJzzBp7EIM
-        ud0OZDNHGGThBI0QPX3BlNPbdPULAAD//wMAejd5ykkBAAA=
+        H4sIAAAAAAAAA0SOzUoDMRRG9z5F+NaZMrE/2uxVCu4EK4iUNHNt0s7khuSWCmXeXQrVbg+cwzkj
+        drDwwYkfct88PJd171aLYGaH/dPy7dX5j9mLKWt6fxRo8HZPXq7GxPOQe5LICRq+kBPqYM3icdaa
+        eTudawzcUQ+LXZZmOpk3cixbbtppa6BxrG5HsGfkwkOWjfCBUoVd3mvc0jesISyu/wemNaOGDxw9
+        VdjPMwaqf83CPcHC1RqruHSZ95yE0uV+pU6uquuxcqlTiSXEtFOJTiq4qoLLmRJ1E4wa3zHFGjaF
+        XOUEiyqcoRFTRz+w7fg13v0CAAD//wMAw+SFO0kBAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23ece48f6cc30c-VIE
+      - 7c6e27f35c5b3134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -343,7 +343,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:31 GMT
+      - Sat, 13 May 2023 21:57:16 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -353,9 +353,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '837'
+      - '895'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -367,13 +367,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '89867'
+      - '89866'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - 69137c6e42f4c77126b19b5a1f01ad0d
+      - 21eaeabf9b54c809ad61d77bbb6e0432
     status:
       code: 200
       message: OK
@@ -394,13 +394,13 @@ interactions:
       immediately save important information to files.\n2. If you are unsure how you
       previously did something or want to recall past events, thinking about similar
       events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file:
-      Append to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2.
-      delete_file: Delete file, args: \"filename\": \"<filename>\"\n3. list_files:
-      List Files in Directory, args: \"directory\": \"<directory>\"\n4. read_file:
-      Read file, args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file,
-      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6. browse_website:
-      Browse Website, args: \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
       Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
@@ -427,17 +427,18 @@ interactions:
       created and nothing new has happened."}, {"role": "user", "content": "Determine
       which next command to use, and respond using the format specified above:"},
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"I can use the browse_website
-      command to visit the website and search for the price of the book by inspecting
-      the HTML code.\",\n        \"plan\": \"- Use the browse_website command to visit
-      the website\\n- Inspect the HTML code to find the price of the book\\n- Write
-      the price to a file named ''browse_website.txt''\\n- Use the task_complete command
-      to complete the task\",\n        \"criticism\": \"I need to be careful when
-      inspecting the HTML code to ensure I find the correct price.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to find the price of the book on the website. The browse_website command
+      can be used to visit the website and find the price.\",\n        \"plan\": \"-
+      Use the browse_website command to visit the website\\n- Find the price of the
+      book\\n- Write the price to a file named ''browse_website.txt''\\n- Use the
+      task_complete command to complete the task\",\n        \"criticism\": \"I need
+      to ensure that I am using the correct URL and question to find the price of
+      the book.\",\n        \"speak\": \"I will use the browse_website command to
+      visit the website and find the price of the book.\"\n    },\n    \"command\":
+      {\n        \"name\": \"browse_website\",\n        \"args\": {\n            \"url\":
+      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
       \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
       "content": "Command browse_website returned: Answer gathered from website: The
       price of the book \"Meditations\" is \u00a325.89, according to the text. \n
@@ -455,7 +456,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5682'
+      - '5668'
       Content-Type:
       - application/json
     method: POST
@@ -463,20 +464,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7xTyY7TQBC98xWtuuTSibKQzUc4ITQSSICQMLLa7UrcxO4yXRUSiPw1/AlfhryE
-        MJ65zpysrtd+S+n1BVwGEdjciC2rYrx+nc4/vf3xnRlPFb179avYbGgxff8Zs+0daKD0G1rp/5hY
-        KqsCxZEHDTagEcwgmq02i/litVrPNJSUYQER7CsZLybLsRxDSuPpYjoDDUc2e4ToAlWgspJE6ICe
-        IZrN11sNN/IbsF1pEBJT3EYv18tag83JWWSIvlygRL4SByoQIjDMjsV4aWySF/RNhEvslVIqBsnp
-        uM+FY4hUP+wBPEszjOGN8oiZElKn4ASV5Kiq4Cwq2rWHlOjQwEbtXIHKmxIzNUoDnRiTE6bsBCdy
-        ltEkBv2/RkDD5J3fX4Ws8erInUQrlgglLamlsjT+SVxUhfGdgbH6+NTiA20bnDjruByuGj0fQyNk
-        pBVoaR2rvmnK+XZsKQS0ojLXfCj8HIbjCs3hSn5yRfEs++0c1Prasp79Qckaks7cPTeDDCbsh/3s
-        gObujeKhlXs8w1p/eDTg6A4zJ6Z5ejxqFv7n93w52Wz/hWqD9fliX0OtYee84zzp2gwRsFAFGpzP
-        8AzRtP5av/gLAAD//wMAknh4rWwEAAA=
+        H4sIAAAAAAAAA7yUzY7aQAzH730KyxcuAQVoYDe3XrbaQ6Ue2G4/UkWTiUmmJDPpjFPQojxN36RP
+        VuUDKCwr9dIex575+/d37OxRpRiizAXLsirGyzv7WL5ZPHy4e/wUbJ5+bJ/e15/tx9uVr99O0UOT
+        fCPJw4uJNGVVECuj0UNpSTClGE4XN6/9aeDPFx6WJqUCQ8wqHs8nwZhrm5ixP/dbsdqJjDDcY2VN
+        WXHMZkPaYTidLQMPT+LHxGy29JANi+J0N/BnjYcyN0qSw/DLHktyB2FrCsIQhXPKsdDcYhrNpFsL
+        +0gDAETIuamznF2EIQzBIUE7boMR3sNWFQXUjoBzgq1VTDGbeK0KAmnKUugU2PSJ7kpllSQw6+6Q
+        GLNp0wK6B1qUlMIosWbrKN5S4hTThHc8mkTo/UlgSTijlc56jFVOwMJtwNL3WllyUNJfl53A6kV0
+        KTQk1Pq7auOkccFXFUL3aGN4+NfNiSJ9qtK2IR5m5KzKMXa4dYEsrWIllSsPX1ZTb5q0q237TDDc
+        gyihdkpnnYw01pLkDrDlg64W7fiFZrWHa+1yFYnNf5+onqDxDvM+qD8b91akhzujufAgbHa5KX3i
+        0Jxe4jnKmc7lgq2uGhy9o1SxaH8CbgTKwa+fs2Byc3s01Rkb/EW6wcbDtdLK5XG/ORiiY1Ohh0qn
+        tMPQb742r34DAAD//wMAxK4UxfYEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23eceb0d9cc30c-VIE
+      - 7c6e27fa19f03134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -486,7 +488,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:42 GMT
+      - Sat, 13 May 2023 21:57:31 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -496,9 +498,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '11192'
+      - '15170'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -514,9 +516,9 @@ interactions:
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.346s
+      - 2.347s
       x-request-id:
-      - 8a46773fe4d416c50f9206f5ae9cacf5
+      - 3882156168caae167fcba64d9e53dfe9
     status:
       code: 200
       message: OK
@@ -546,17 +548,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SPXUsDMRBF3/0Vwzxny7bbVsmbHy9FQRFBRKRks9NuNMmEZLZVyv53KVT7ern3
-        cO4BXYcabW/EhuSry9t25vqbYTGs6ufX+m5nN/OXp/vH8LbrHlAht59k5bSYWA7JkziOqNBmMkId
-        6unyqpk1y+XVXGHgjjxq3CapmsmikiG3XNVNPUWFQzFbQn3AlDkkWQt/USyop7Na4Zn9nx9jYTH+
-        3JzXo0Lbs7NUUL8fMFD5o2b2hBpNKa6IiXJ05CgUj/7XBQyUnyIUFKwgkzXeg/RGYAV7U+B0B0zs
-        QHrKBL3ZEbREESJDpD10tCPPKVCUAsKQKXGWCY4KNy660q8zmcIRNRbhhApd7OgbdT1+jBe/AAAA
-        //8DAKdc/tB7AQAA
+        H4sIAAAAAAAAA0SPy07DMBBF93yFNWunStqEh3dsEGUBC7pAQqhynCExtT2WZyooVf4dFYG6PdI9
+        OvcIfgADbrLiYg7V1V15aW+eHw7r8elx3y43IZdy3/S7TfMdQQP1H+jkb7FwFHNA8ZRAgytoBQcw
+        zeV1Wzdd3bUaIg0YwMCYpVotukr2paeqXtUNaNizHRHMEXKhmGUrtMPEYJplreHsPvNOg5DYcCar
+        btbgJvIOGczrESLyv7VQQDBgmT2LTXJqpCSYTv23rKziAwtGrdaqoLMhKJmsqEQy+TSqhJ9qsqwm
+        mzMmHBT75FDFg/q96iktYNbw7pPnaVvQMiUwwEIZNPg04BeYen6bL34AAAD//wMAwyzQIWYBAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23ed3eda7ec30c-VIE
+      - 7c6e286a6cb43134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -566,7 +567,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:46 GMT
+      - Sat, 13 May 2023 21:57:36 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -576,9 +577,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1470'
+      - '1467'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -596,7 +597,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 107ms
       x-request-id:
-      - c9cf33b227d0c6c46c3e92f14f731f25
+      - 184d54d51114800add2eb3511ace4ebc
     status:
       code: 200
       message: OK
@@ -617,13 +618,13 @@ interactions:
       immediately save important information to files.\n2. If you are unsure how you
       previously did something or want to recall past events, thinking about similar
       events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file:
-      Append to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2.
-      delete_file: Delete file, args: \"filename\": \"<filename>\"\n3. list_files:
-      List Files in Directory, args: \"directory\": \"<directory>\"\n4. read_file:
-      Read file, args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file,
-      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6. browse_website:
-      Browse Website, args: \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
       Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
@@ -647,21 +648,21 @@ interactions:
       \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
       "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
       "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that I was created and there have been no new developments
-      to report."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
-      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"I can use the browse_website
-      command to visit the website and search for the price of the book by inspecting
-      the HTML code.\",\n        \"plan\": \"- Use the browse_website command to visit
-      the website\\n- Inspect the HTML code to find the price of the book\\n- Write
-      the price to a file named ''browse_website.txt''\\n- Use the task_complete command
-      to complete the task\",\n        \"criticism\": \"I need to be careful when
-      inspecting the HTML code to ensure I find the correct price.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to find the price of the book on the website. The browse_website command
+      can be used to visit the website and find the price.\",\n        \"plan\": \"-
+      Use the browse_website command to visit the website\\n- Find the price of the
+      book\\n- Write the price to a file named ''browse_website.txt''\\n- Use the
+      task_complete command to complete the task\",\n        \"criticism\": \"I need
+      to ensure that I am using the correct URL and question to find the price of
+      the book.\",\n        \"speak\": \"I will use the browse_website command to
+      visit the website and find the price of the book.\"\n    },\n    \"command\":
+      {\n        \"name\": \"browse_website\",\n        \"args\": {\n            \"url\":
+      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
       \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
       "content": "Command browse_website returned: Answer gathered from website: The
       price of the book \"Meditations\" is \u00a325.89, according to the text. \n
@@ -671,13 +672,15 @@ interactions:
       '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to write the price of the book to a file named
-      ''browse_website.txt''.\",\n        \"reasoning\": \"I can use the write_to_file
-      command to write the price of the book to a file named ''browse_website.txt''.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the price of the book to a file named
-      ''browse_website.txt''\",\n        \"criticism\": \"I need to ensure that the
-      file is created in the correct directory.\",\n        \"speak\": \"I will use
-      the write_to_file command to write the price of the book to a file named ''browse_website.txt''.\"\n    },\n    \"command\":
+      {\n        \"text\": \"I will use the write_to_file command to write the price
+      of the book to a file named ''browse_website.txt''.\",\n        \"reasoning\":
+      \"The task requires me to write the price of the book to a file. The write_to_file
+      command can be used to write the price to a file.\",\n        \"plan\": \"-
+      Use the write_to_file command to write the price of the book to a file named
+      ''browse_website.txt''\\n- Use the task_complete command to complete the task\",\n        \"criticism\":
+      \"I need to ensure that I am using the correct filename and text to write the
+      price to the file.\",\n        \"speak\": \"I will use the write_to_file command
+      to write the price of the book to a file named ''browse_website.txt''.\"\n    },\n    \"command\":
       {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
       \"browse_website.txt\",\n            \"text\": \"The price of the book ''Meditations''
       is \u00a325.89.\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
@@ -692,7 +695,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6824'
+      - '6927'
       Content-Type:
       - application/json
     method: POST
@@ -700,19 +703,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7yRQW/bMAyF7/sVAs9ykDiwk+m67ZAO2Gm9dB4CRWYt1bJkmHTbLfB/H1w7TZad
-        2sOuj+T3HskjuBIUGKvZNK1PNp8OaR3SOvN39jfpL9mj29x+3e4+N3f5DUiIhwc0PE8sTGxaj+xi
-        AAmmQ81Yglrl23W6zvNtLqGJJXpQULWcrBdZwn13iMlyvVyBhJ50haCO0HaxaXnPscZAoFZZupVw
-        hp8L6UcJHFn7s5Rnm0GCsdEZJFA/jtAgncBd9AgKNJEj1oHHmDEwhnGFYxGEEKIAtrGvLFMBSszi
-        XMBnHsUCdsLqRxRzJiwFWxSsqZaCotiJgKMWRU/4WtqfusexRoeXBrI9izI+hUUB8tKrQ00xuFD9
-        L8PW6zB5JeL23RTTOXbGUTOhvsWAVx3Uoq5PSz0579+WeUIN8vSsue2fXwXd4OTyF/YqjO6q6zdf
-        nn8CfNdUX1yeemOQ6L73/tdroJdQc7YiDDBIuHfBkd1PJFBAHFuQ4EKJz6CWw8/hwx8AAAD//wMA
-        YEZz+G8DAAA=
+        H4sIAAAAAAAAA6SSTY/TMBCG7/yK0Vz24lapQrsot72AeuC2CARBleNMElN/ZO3JtqjKf0dpku1S
+        FgHiZo9nXj/vzJxQl5ihaiQr25rF7dvwafPw7vORPlZ36X0oyruNbt43xZa3KQr0xTdSPFUslbet
+        IdbeoUAVSDKVmK02b14nq3Wy3gi0viSDGdYtL9LlesFdKPwiSZMVCuyirAmzE7bB25Z37PfkImar
+        9ToReBG/PGxSgexZmkvodpX2AlXjtaKI2ZcTWoqzcPCGMEMZo44sHQ+Y3jG5wcIpdwAAOXLju7rh
+        mGMGU3B6oCMPwRy3cNDGQBcJuCFgGfe7CZBAeWulK4E9PMXmrGWO4rlkIBm9064ede+nNAj00OlA
+        ESy9qAOyYgpwCJq1q8/hNmhF4KvzpfB+PxQO50obWsL9bzmVdFDQYObvmFsj3Yi7gA//3IErMTU4
+        UDraubGORgxysQtDmWTYgrTQBv+oy8GthLFtUPkwfzB34SXg2JLc///gRslezHsypf+yJk5aGn/7
+        Sf4KSob6esOer8SM28hHgtgpRTFWnTHfzzNncn+eOdwUwR8i7Q5URM205CPfPPk4e5ks5a7HXmCl
+        nY7NbgTADCP7FgVqV9IRs6T/2r/6AQAA//8DAOjFC/khBAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c23ed493d21c30c-VIE
+      - 7c6e2874ad9f3134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -722,7 +726,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 May 2023 21:44:53 GMT
+      - Sat, 13 May 2023 21:57:48 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -732,9 +736,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-cbwy2y25pylufhkfs0la9nqe
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '7454'
+      - '12210'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -750,9 +754,9 @@ interactions:
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.347s
+      - 2.346s
       x-request-id:
-      - 09cc7d22955a6d026a3d8c433a65c28e
+      - c06abb02e5bab33b2494f2d77188e9c2
     status:
       code: 200
       message: OK
diff --git a/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml b/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
index 4aefdb23..742fd1de 100644
--- a/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
@@ -12,7 +12,7 @@ interactions:
       short term memory is short, so immediately save important information to files.\n2.
       If you are unsure how you previously did something or want to recall past events,
       thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
       append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
       \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
       list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
@@ -24,7 +24,7 @@ interactions:
       GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
       \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      Task Complete (Shutdown): \"task_complete\", args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
       Internet access for searches and information gathering.\n2. Long Term memory
       management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
       output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
@@ -50,7 +50,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3410'
+      - '3391'
       Content-Type:
       - application/json
     method: POST
@@ -58,20 +58,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7ySQY/aQAyF7/0Vli+5DAgWFmiO7aU9VlWLVk2FZieGDEzGsxlHUKH89yokLGwq
-        9dZe/eznzzPvjDbHFE2hxZTBjZYffL3e0+HxhfmjfFnPwvdCvxRh//TEOSrk5z0Z6SfGhsvgSCx7
-        VGgq0kI5ptPFajaZL1cPE4Ul5+QwxV2Q0Wz8OJK6eubRZDaZosI66h1hesZQcRlkI3wgHzFdLh4U
-        3rxf69PVXKGwaPdaej9fNApNwdZQxPTHGUuKV9uKHWGKOkYbRXtpIdkL+faAc+YBADKUgutdITHD
-        FPpiL9BJ2mKGn8ET5SAMdSSQguBYWaGN8GZrHYHhstT+0nARIPlEzjGsuXJ5AtYLg4ZLq9cl5ZAU
-        rb45tvpYTpKMM1T3uyvSkb31uw7gq/WG4IbRbdEQAxm7tQZa1vs96i+UNl7EkqOADqHiUFktBOyp
-        P3FIE5z2HcgIvv2nFzCVFWtsLK9fkLNPBCIRaP8LbIw1RThaKUAKG6FlHHrEQPpwnT9a5/7l/3WL
-        G3XNVW/6R6xah47pDcQAXVe7YSI7oe29WQw43pgMU3x305X2QtyDZ77BRuHWehuLTRdATDEKB1Ro
-        fU4nTCfNz+bdbwAAAP//AwAsTU8qNQQAAA==
+        H4sIAAAAAAAAA7STy27bMBBF9/2KwWy8kQ05tuNEH1A06DJIU7QqBIYaS6wpkiVHtQtD/17o5YcK
+        dJft3OG9Z8jhCVWOCcpSsKycnm8/+q+f1y+vv+42y7X5po+rPT0/bpX4sv+9xAjt20+SPJxYSFs5
+        TayswQilJ8GUY7K8f1jHy028jSOsbE4aEywcz1eLzZxr/2bn8SpuzeogCsLkhM7bynHGdk8mYLLd
+        bCO8eJ/rd/F9hGxZ6HPp8X7VRChLqyQFTL6fsKIw2nqrCRMUIajAwnALaQ2TaQc4pQYAIEUubV2U
+        HFJMYCgOAh25Lab4BIYoB7ZQBwIuCQ5eMWVss53SBNJWlTBdQyfA7BNpbeHVep3PQBm2IKBrNaKi
+        HGZlq2eHVl/wkWeLFKPrbE8iWKNM0QM8KyMJLhh9ioDgSKqdktCyXudE/6FUoRMrGxiEc946rwQT
+        WEPDiFMap4XpQebw8m43kJqLO4uwz4YVuHE/18auKav0ipVUoZo+HZlQ+/acYHgCUUEdlCk6H2m9
+        J8kXPujS2s4uprvc0E3GZMZ2/WeaHRyJ/Zh7UFq/5770wU007vFg+s8atw490w3EBF34YvoDeqHt
+        vVhMOG5Mpr/maqaRtiMewFPTYBPhThkVyqxfeEwwsHUYoTI5HTGJmx/Nh78AAAD//wMA+mCSu6UE
+        AAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c11ea4fb82bfade-SJC
+      - 7c6e28ce4eec3134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -81,7 +82,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 02 May 2023 17:17:12 GMT
+      - Sat, 13 May 2023 21:58:04 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -91,9 +92,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '11488'
+      - '14009'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -105,13 +106,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86497'
+      - '86496'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.335s
+      - 2.336s
       x-request-id:
-      - 81a8552ed38d0037b7b7c23664f5ae2b
+      - 4273baa4d7bdadcb0aaf64a92def3fee
     status:
       code: 200
       message: OK
@@ -140,16 +141,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOQU/CQBBG7/6K5jtvSUsRcI+KMd6MeNIYsm2HdqGdWbtD0JD+d0OCcn3Je3kn
-        +BoWVeu06kOXLu75sH9arV+6t9V0/vW6e3jfCpe0fvTNDwyk3FGlF2NSSR86Ui8Mg2ogp1TD5vNl
-        kc0Wy2Jm0EtNHSyaoGkxuU31MJSSZkWWw+AQXUOwJ4RB+qAblT1xhL2bGlzTV2ygoq77B3mWjwZV
-        K76iCPtxQk/xrzlIR7BwMfqojvV8KKzE5/vn5OhicjlOHNcJi7aem4TpmLQuJq0LgZjqCUaDrWcf
-        281ALgrDIqoEGHiu6Rs2Gz/Hm18AAAD//wMA1rZZUUkBAAA=
+        H4sIAAAAAAAAA0SOQUvDQBQG7/6K5TtvSmKtqXsUEXvxJCiIlO3mmV2b7FuzL7YQ8t+lUO11YIaZ
+        EBoYOG/F9akr6sfhbVfvX6x/Hlv/cDz8DN/jU03Zb17vocG7L3JyNhaO+9SRBI7QcANZoQamul3f
+        lNWqXNcaPTfUwaBNUiwXq0LGYcdFuSwraIzZtgQzIQ3cJ9kK7ylmmLtrjUv6gjWExXb/oCqrWcN5
+        Do4yzPuEnvJfc+COYGBzDllslNMhR6F4ut+og83qfKxsbFRk8SG2KtJBeZuVtylRpGaBWeMzxJD9
+        diCbOcIgCydohNjQEaacP+arXwAAAP//AwAItSctSQEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c11eaa7f982fade-SJC
+      - 7c6e29370ef23134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -159,7 +160,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 02 May 2023 17:17:15 GMT
+      - Sat, 13 May 2023 21:58:08 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -169,9 +170,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1025'
+      - '1031'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -189,7 +190,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - dcfcb7a7f05897ff8d7924daba89388c
+      - 739f7b6c03a87b0556182913b60556cd
     status:
       code: 200
       message: OK
@@ -206,7 +207,7 @@ interactions:
       short term memory is short, so immediately save important information to files.\n2.
       If you are unsure how you previously did something or want to recall past events,
       thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
       append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
       \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
       list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
@@ -218,7 +219,7 @@ interactions:
       GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
       \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      Task Complete (Shutdown): \"task_complete\", args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
       Internet access for searches and information gathering.\n2. Long Term memory
       management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
       output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
@@ -242,15 +243,16 @@ interactions:
       named ''hello_world.txt''.\",\n        \"reasoning\": \"Since I need to write
       a specific text into a file, the write_to_file command is the most appropriate
       one to use.\",\n        \"plan\": \"- Use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I don''t see any issues with this plan.\",\n        \"speak\": \"I will use
-      the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
+      ''Hello World'' into a file named ''hello_world.txt''.\\n- Use the task_complete
+      command to complete the task.\",\n        \"criticism\": \"I need to ensure
+      that I am using the correct file name and that the text is written correctly.\",\n        \"speak\":
+      \"I will use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\":
+      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
+      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
+      write_to_file returned: File written to successfully."}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -259,7 +261,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4576'
+      - '4669'
       Content-Type:
       - application/json
     method: POST
@@ -267,20 +269,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7SST2/TQBDF73yK0Vxy2UQxpknwsRKoESoXFIGEq2i7nthL1ruuZ0xSonx35NhO
-        SrgVcZ0/b35v9x3QZpigKbSYsnLj+a1vytzef1x9e7qp71a/dFR9+sD389Xbp1tUGB5/kJF+Y2JC
-        WTkSGzwqNDVpoQyTaLaIp+/mi3imsAwZOUwwr2QcT27G0tSPYTyNpxEqbFjnhMkBqzqUlawlbMkz
-        JtE0ihVexC+NRaxQgmh3KUXvZ0eFpgjWEGPy/YAl8SBcB0eYoGa2LNpLixm8kG8tHFIPAJCiFKHJ
-        C+EUE+iLfYP20hZT/Bx2IIUWWEKhfxLsaitCHkZ35FyAr6F22QislwAaNtYReF1SBqOi7a93bX8i
-        exkpWIInykACNEwgBYFo3q57uwQmlKX2p4FzbZiapKheAtakOXjr847yi/WGBsRhOTtvQ9icwK3P
-        /zO49Zk1+gSu5XLf8pnq2knltO9MjGH1z+9iWpfGctlJLiELfiTARKD9M1jmhhh2VgqQwjK01681
-        uCK9HfZ31rnX/VcneVRD2Prxv7LWPnt37Q/5Kyhd59cxfZmEAfcUAG6MIeZN49zz6wN7tnCy0btJ
-        /RGPCjfWWy7W3W1MkCVUqND6jPaYTI8Pxze/AQAA//8DAOv7y1VhBAAA
+        H4sIAAAAAAAAA7RSTY/TMBC98ytGc+klrVK6HyVHDsCekGARKxFUuc408dbxWPak7arKf0dpku1S
+        BAcQ13l+894bvyOaAjPUlRJdezu9fRce9Hr/sG38pxs2j/r+ffX26c3Vx0ruAybI60fSMjBmmmtv
+        SQw7TFAHUkIFZvOb5VU6v06XywRrLshihqWX6WJ2PZUmrHmaLtI5JthEVRJmR/SBay8r4S25iNk8
+        XaQJnpefgds0QWFR9jx6naZtgrpioyli9u2INcVxcWBLmKGK0URRTjqb7IRcF+GYOwCAHKXipqwk
+        5pjBMBwAOkg3zPEOKrUjiI3WFOOmsfYJ9sGIkIPJB7KW4SsHW0zAOGFQsDGWwKmaCphUHb7ad/hM
+        DjKZwR1o5cDxHppIIBWBqLhdDZEJNNe1cgUIw/NsfDXLMXlpMpCK7Iwre6efjdMEg9+RXDyzkz+o
+        mXgCa44CyvvAPhglBOyoc9JEutT2Vrledgpf/jmJDkaMNrEeb+6ITkxysQkdT8mYzAfemYIKULBT
+        1hTQnwE2HEYh48rfSkVPajvK7I21f/cR/co2GZs0PP+lSF0RerWf1l+YUqG87ODLL/4fTRwjnGIM
+        aXLXYpvgxjgTq1WvjRlGYY8JGlfQAbO0/d6++gEAAP//AwDwffUhPgQAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c11eaaf0abffade-SJC
+      - 7c6e293e98343134-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -290,7 +292,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 02 May 2023 17:17:26 GMT
+      - Sat, 13 May 2023 21:58:19 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -300,9 +302,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
+      - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '10848'
+      - '11031'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -314,262 +316,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86485'
+      - '86479'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.342s
+      - 2.347s
       x-request-id:
-      - e0a52aa6b569cb67dbbb8e6098e31231
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3406'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTT4/TQAzF73wKy5de0iqh0O3mthwQPYAEdMUuBFWzE7cZOhmHGUctVPnuKEn/
-        7AZxQnD1c9772eMc0OSYoi6U6LKy46tXP+5vbpZhoT+/u329nCc/39692H58PzUf7q8xQn74RlqO
-        X0w0l5UlMewwQu1JCeWYJrP5NJ7Pr5J5hCXnZDHFTSXj6eTlWGr/wON4GicYYR3UhjA9YOW5rGQl
-        vCUXML2aJRFevM/153EcobAoey5dz5ImQl2w0RQw/XLAksLJ1rMlTFGFYIIoJy0kOyHXDnDIHABA
-        hlJwvSkkZJjCsXgUaC9tMcMFOKIchKEOBFIQ7LwRWgmv1sYSaC5L5bqGToDRG7KW4RN7m4/AOGFQ
-        0LU6VVIOo6LVV7tWn8heRpMMo8fZnlRgZ9ymB1gWBKLCFjx9r42nACX9RVoEHe0f5zChE1VVea68
-        UXKR1uxBirZBhe2QurLK9cBjuP1Pm9LeiNEmlMOnIhdq3zIogcX54TR7T1q6iDah3wTt5YIk3HW2
-        HcOwUJHanoJ2xtp/eRB9cBOdDvVo+tudtg490xOIAbrym+GJ98JpE73FgOOJyfC3eDTTibYjPoJn
-        rsEmwrVxJhSr/qIxxSBcYYTG5bTHNG6+Ns9+AQAA//8DAAaMC/aGBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c15d0c86db14665-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 03 May 2023 04:38:50 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '11864'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86496'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.335s
-      x-request-id:
-      - 5d9f1c3b077997ea564ea7088eca733f
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed in double quotes e.g. \"command name\"\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
-      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
-      command is the appropriate command for this task.\",\n        \"plan\": \"-
-      Use the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I need to ensure that I use the correct filename and text to write to the
-      file.\",\n        \"speak\": \"I will use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4653'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7RTyW7bMBC99ysGc/GFNmQbbVwdiwapgQLd0hZBVBgMNZZYU6RKjrzA0L8XtKQk
-        TReg242YefMWcnhEnWOKqpSsqtqMz54drl5V+Z6W/OaDfHlhzpMNmefnh4vX5i0KdDefSXE/MVGu
-        qg2xdhYFKk+SKcd0+mQxTxaLs/lMYOVyMphiUfN4Pnk85sbfuHEyT6YosAmyIEyPWHtX1bxityEb
-        MJ0ms4XAO/LbxiyZCmTH0txhZ7OnrUBVOq0oYHp9xIrCQOydIUxRhqADS8vRprNMNkY4ZhYAIEMu
-        XVOUHDJMoS/2DdpzLGa4hFJuCUKjFIWwbow5wM5rZrIwekHGOPjovMlHoC07kLDWhsDKinIYlbG/
-        2sX+hPc8msBlSWBpzxCYatAB2EETCLgkYBk2qz48gXJVJW0eAbe1ATXJUNy360kGZ7UtOs+XPQw8
-        fWm0pwAVRZ7om37fNZxslGR/YATeaasIfnVL7E7wqCBOp3+fvzbSdtHH8P6v2ZTXrJUO1bABlug0
-        STY0Ps5JhiXU3m11TiBhK43OoXsEWDs/SGhb/FQk1CQ3g8BOG/Nn19BRtmLY6B7+3ULHp+3UvqF/
-        YEr64uFfuL9g/+NHDBFOMfo0mW2xFbjWVody1WljioFdjQK1zWmPadJ+ah99BQAA//8DAMo52K3G
-        BAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c15d120ec8f4665-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 03 May 2023 04:39:04 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '12271'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86481'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.346s
-      x-request-id:
-      - a8c02e37e5af0c851759aa261f20f701
+      - f0688bcfb5c1cd1af84b725271f0a4c4
     status:
       code: 200
       message: OK

From d06d8a609fd5ba74dd7582777aacc51f4bd7d3a2 Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Mon, 15 May 2023 21:41:11 +0300
Subject: [PATCH 003/112] Fix commands with same name overwriting (#4226)

---
 autogpt/commands/command.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/autogpt/commands/command.py b/autogpt/commands/command.py
index 22ebace5..174a691c 100644
--- a/autogpt/commands/command.py
+++ b/autogpt/commands/command.py
@@ -3,6 +3,8 @@ import importlib
 import inspect
 from typing import Any, Callable, Optional
 
+from autogpt.logs import logger
+
 # Unique identifier for auto-gpt commands
 AUTO_GPT_COMMAND_IDENTIFIER = "auto_gpt_command"
 
@@ -59,6 +61,10 @@ class CommandRegistry:
         return importlib.reload(module)
 
     def register(self, cmd: Command) -> None:
+        if cmd.name in self.commands:
+            logger.warn(
+                f"Command '{cmd.name}' already registered and will be overwritten!"
+            )
         self.commands[cmd.name] = cmd
 
     def unregister(self, command_name: str):
@@ -133,6 +139,11 @@ def command(
 ) -> Callable[..., Any]:
     """The command decorator is used to create Command objects from ordinary functions."""
 
+    if not enabled:
+        if disabled_reason is not None:
+            logger.debug(f"Command '{name}' is disabled: {disabled_reason}")
+        return lambda func: func
+
     def decorator(func: Callable[..., Any]) -> Command:
         cmd = Command(
             name=name,

From cf35112291ef478a64c93fdc6a7600ef448bf727 Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Mon, 15 May 2023 22:54:40 +0300
Subject: [PATCH 004/112] Fixed error in safe_google_results, added tests
 (#3606)

---
 autogpt/commands/google_search.py       |   2 +-
 tests/integration/test_google_search.py | 131 ++++++++++++++++++++++++
 2 files changed, 132 insertions(+), 1 deletion(-)
 create mode 100644 tests/integration/test_google_search.py

diff --git a/autogpt/commands/google_search.py b/autogpt/commands/google_search.py
index 264daaff..1fc974cd 100644
--- a/autogpt/commands/google_search.py
+++ b/autogpt/commands/google_search.py
@@ -110,7 +110,7 @@ def safe_google_results(results: str | list) -> str:
     """
     if isinstance(results, list):
         safe_message = json.dumps(
-            [result.encode("utf-8", "ignore") for result in results]
+            [result.encode("utf-8", "ignore").decode("utf-8") for result in results]
         )
     else:
         safe_message = results.encode("utf-8", "ignore").decode("utf-8")
diff --git a/tests/integration/test_google_search.py b/tests/integration/test_google_search.py
new file mode 100644
index 00000000..798765e0
--- /dev/null
+++ b/tests/integration/test_google_search.py
@@ -0,0 +1,131 @@
+import json
+
+import pytest
+from googleapiclient.errors import HttpError
+
+from autogpt.commands.google_search import (
+    google_official_search,
+    google_search,
+    safe_google_results,
+)
+
+
+@pytest.mark.parametrize(
+    "query, expected_output",
+    [("test", "test"), (["test1", "test2"], '["test1", "test2"]')],
+)
+def test_safe_google_results(query, expected_output):
+    result = safe_google_results(query)
+    assert isinstance(result, str)
+    assert result == expected_output
+
+
+def test_safe_google_results_invalid_input():
+    with pytest.raises(AttributeError):
+        safe_google_results(123)
+
+
+@pytest.mark.parametrize(
+    "query, num_results, expected_output, return_value",
+    [
+        (
+            "test",
+            1,
+            '[\n    {\n        "title": "Result 1",\n        "link": "https://example.com/result1"\n    }\n]',
+            [{"title": "Result 1", "link": "https://example.com/result1"}],
+        ),
+        ("", 1, "[]", []),
+        ("no results", 1, "[]", []),
+    ],
+)
+def test_google_search(query, num_results, expected_output, return_value, mocker):
+    mock_ddg = mocker.Mock()
+    mock_ddg.return_value = return_value
+
+    mocker.patch("autogpt.commands.google_search.ddg", mock_ddg)
+    actual_output = google_search(query, num_results=num_results)
+    expected_output = safe_google_results(expected_output)
+    assert actual_output == expected_output
+
+
+@pytest.fixture
+def mock_googleapiclient(mocker):
+    mock_build = mocker.patch("googleapiclient.discovery.build")
+    mock_service = mocker.Mock()
+    mock_build.return_value = mock_service
+    return mock_service.cse().list().execute().get
+
+
+@pytest.mark.parametrize(
+    "query, num_results, search_results, expected_output",
+    [
+        (
+            "test",
+            3,
+            [
+                {"link": "http://example.com/result1"},
+                {"link": "http://example.com/result2"},
+                {"link": "http://example.com/result3"},
+            ],
+            [
+                "http://example.com/result1",
+                "http://example.com/result2",
+                "http://example.com/result3",
+            ],
+        ),
+        ("", 3, [], []),
+    ],
+)
+def test_google_official_search(
+    query, num_results, expected_output, search_results, mock_googleapiclient
+):
+    mock_googleapiclient.return_value = search_results
+    actual_output = google_official_search(query, num_results=num_results)
+    assert actual_output == safe_google_results(expected_output)
+
+
+@pytest.mark.parametrize(
+    "query, num_results, expected_output, http_code, error_msg",
+    [
+        (
+            "invalid query",
+            3,
+            "Error: <HttpError 400 when requesting https://www.googleapis.com/customsearch/v1?q=invalid+query&cx "
+            'returned "Invalid Value". Details: "Invalid Value">',
+            400,
+            "Invalid Value",
+        ),
+        (
+            "invalid API key",
+            3,
+            "Error: The provided Google API key is invalid or missing.",
+            403,
+            "invalid API key",
+        ),
+    ],
+)
+def test_google_official_search_errors(
+    query,
+    num_results,
+    expected_output,
+    mock_googleapiclient,
+    http_code,
+    error_msg,
+):
+    class resp:
+        def __init__(self, _status, _reason):
+            self.status = _status
+            self.reason = _reason
+
+    response_content = {
+        "error": {"code": http_code, "message": error_msg, "reason": "backendError"}
+    }
+    error = HttpError(
+        resp=resp(http_code, error_msg),
+        content=str.encode(json.dumps(response_content)),
+        uri="https://www.googleapis.com/customsearch/v1?q=invalid+query&cx",
+    )
+
+    mock_googleapiclient.side_effect = error
+    actual_output = google_official_search(query, num_results=num_results)
+    assert actual_output == safe_google_results(expected_output)

From 3c80e05e0052c1f06b29a5b5ff4f518283382812 Mon Sep 17 00:00:00 2001
From: Boostrix <119627414+Boostrix@users.noreply.github.com>
Date: Tue, 16 May 2023 01:26:13 +0200
Subject: [PATCH 005/112] Improve error message by providing the name of the
 env file (#3964)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/commands/execute_code.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py
index 6b141dba..af7f70bc 100644
--- a/autogpt/commands/execute_code.py
+++ b/autogpt/commands/execute_code.py
@@ -104,7 +104,7 @@ def execute_python_file(filename: str) -> str:
     CFG.execute_local_commands,
     "You are not allowed to run local shell commands. To execute"
     " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
-    "in your config. Do not attempt to bypass the restriction.",
+    "in your config file: .env - do not attempt to bypass the restriction.",
 )
 def execute_shell(command_line: str) -> str:
     """Execute a shell command and return the output

From 17c45ee53aad511ff1fb857dcfa3a7688ab2d356 Mon Sep 17 00:00:00 2001
From: Boostrix <119627414+Boostrix@users.noreply.github.com>
Date: Tue, 16 May 2023 01:34:48 +0200
Subject: [PATCH 006/112] Show workspace during startup / fix for #2793 (#4082)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/prompts/prompt.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/autogpt/prompts/prompt.py b/autogpt/prompts/prompt.py
index 03b4bd4b..c1d8a2b5 100644
--- a/autogpt/prompts/prompt.py
+++ b/autogpt/prompts/prompt.py
@@ -108,6 +108,12 @@ Continue ({CFG.authorise_key}/{CFG.exit_key}): """
         config = prompt_user()
         config.save(CFG.ai_settings_file)
 
+    if CFG.restrict_to_workspace:
+        logger.typewriter_log(
+            "NOTE:All files/directories created by this agent can be found inside its workspace at:",
+            Fore.YELLOW,
+            f"{CFG.workspace_path}",
+        )
     # set the total api budget
     api_manager = ApiManager()
     api_manager.set_total_budget(config.api_budget)

From 6c4426d8e654930c8c3e25fb30565c9cc768ed3d Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 15 May 2023 19:44:36 -0700
Subject: [PATCH 007/112] Refactor challenges to use cycle count instead of
 time (#4222)

Co-authored-by: Richard Beales <rich@richbeales.net>
---
 .github/workflows/ci.yml                      |   4 +
 .pre-commit-config.yaml                       |   4 +
 mypy.ini                                      |  10 +
 requirements.txt                              |   2 +-
 tests/integration/agent_factory.py            |   2 +-
 tests/integration/agent_utils.py              |  12 -
 .../challenges/basic_abilities/__init__.py    |   0
 .../test_browse_website.yaml                  |   0
 .../test_write_file/test_write_file.yaml      |   0
 .../basic_abilities}/goal_oriented_tasks.md   |   0
 .../basic_abilities/test_browse_website.py    |  23 +
 .../basic_abilities/test_write_file.py        |  23 +
 tests/integration/challenges/conftest.py      |  10 +-
 .../test_information_retrieval_challenge_a.py |  31 +-
 .../test_kubernetes_template_challenge_a.py   |  28 +-
 .../test_memory_challenge_c.yaml              | 856 ++++++++++++++++++
 .../memory/test_memory_challenge_a.py         |  21 +-
 .../memory/test_memory_challenge_b.py         |  28 +-
 .../memory/test_memory_challenge_c.py         |  31 +-
 ..._challenge_should_be_formatted_properly.py |  59 ++
 tests/integration/challenges/utils.py         |  46 +-
 .../goal_oriented/test_browse_website.py      |  18 -
 .../goal_oriented/test_write_file.py          |  21 -
 23 files changed, 1088 insertions(+), 141 deletions(-)
 create mode 100644 mypy.ini
 delete mode 100644 tests/integration/agent_utils.py
 create mode 100644 tests/integration/challenges/basic_abilities/__init__.py
 rename tests/integration/{goal_oriented => challenges/basic_abilities}/cassettes/test_browse_website/test_browse_website.yaml (100%)
 rename tests/integration/{goal_oriented => challenges/basic_abilities}/cassettes/test_write_file/test_write_file.yaml (100%)
 rename tests/integration/{goal_oriented => challenges/basic_abilities}/goal_oriented_tasks.md (100%)
 create mode 100644 tests/integration/challenges/basic_abilities/test_browse_website.py
 create mode 100644 tests/integration/challenges/basic_abilities/test_write_file.py
 create mode 100644 tests/integration/challenges/test_challenge_should_be_formatted_properly.py
 delete mode 100644 tests/integration/goal_oriented/test_browse_website.py
 delete mode 100644 tests/integration/goal_oriented/test_write_file.py

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index ea87ba2f..c2afde55 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -45,6 +45,10 @@ jobs:
         run: isort . --check
         if: success() || failure()
 
+      - name: Check mypy formatting
+        run: mypy
+        if: success() || failure()
+
   test:
     permissions:
       # Gives the action the necessary permissions for publishing new
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index a2ea6114..345d88be 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -21,6 +21,10 @@ repos:
     hooks:
       - id: black
         language_version: python3.10
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v1.3.0'
+    hooks:
+      - id: mypy
 
   - repo: local
     hooks:
diff --git a/mypy.ini b/mypy.ini
new file mode 100644
index 00000000..b977deb0
--- /dev/null
+++ b/mypy.ini
@@ -0,0 +1,10 @@
+[mypy]
+follow_imports = skip
+check_untyped_defs = True
+disallow_untyped_defs = True
+files = tests/integration/challenges/**/*.py
+
+[mypy-requests.*]
+ignore_missing_imports = True
+[mypy-yaml.*]
+ignore_missing_imports = True
diff --git a/requirements.txt b/requirements.txt
index c59b8bb6..3c997b57 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -36,7 +36,7 @@ gitpython==3.1.31
 auto-gpt-plugin-template
 mkdocs
 pymdown-extensions
-
+mypy
 
 # OpenAI and Generic plugins import
 openapi-python-client==0.13.4
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 12e06721..b96953fe 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -12,7 +12,7 @@ from autogpt.workspace import Workspace
 def agent_test_config(config: Config):
     was_continuous_mode = config.continuous_mode
     was_temperature = config.temperature
-    config.set_continuous_mode(True)
+    config.set_continuous_mode(False)
     config.set_temperature(0)
     yield config
     config.set_continuous_mode(was_continuous_mode)
diff --git a/tests/integration/agent_utils.py b/tests/integration/agent_utils.py
deleted file mode 100644
index a899afcf..00000000
--- a/tests/integration/agent_utils.py
+++ /dev/null
@@ -1,12 +0,0 @@
-import concurrent.futures
-
-from autogpt.agent.agent import Agent
-
-
-def run_interaction_loop(agent: Agent, timeout: float | None):
-    with concurrent.futures.ThreadPoolExecutor() as executor:
-        future = executor.submit(agent.start_interaction_loop)
-        try:
-            result = future.result(timeout=timeout)
-        except concurrent.futures.TimeoutError:
-            assert False, f"The process took longer than {timeout} seconds to complete."
diff --git a/tests/integration/challenges/basic_abilities/__init__.py b/tests/integration/challenges/basic_abilities/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
similarity index 100%
rename from tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml
rename to tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
diff --git a/tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
similarity index 100%
rename from tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
rename to tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
diff --git a/tests/integration/goal_oriented/goal_oriented_tasks.md b/tests/integration/challenges/basic_abilities/goal_oriented_tasks.md
similarity index 100%
rename from tests/integration/goal_oriented/goal_oriented_tasks.md
rename to tests/integration/challenges/basic_abilities/goal_oriented_tasks.md
diff --git a/tests/integration/challenges/basic_abilities/test_browse_website.py b/tests/integration/challenges/basic_abilities/test_browse_website.py
new file mode 100644
index 00000000..1afe10cc
--- /dev/null
+++ b/tests/integration/challenges/basic_abilities/test_browse_website.py
@@ -0,0 +1,23 @@
+import pytest
+from pytest_mock import MockerFixture
+
+from autogpt.agent import Agent
+from autogpt.commands.file_operations import read_file
+from tests.integration.challenges.utils import run_interaction_loop
+from tests.utils import requires_api_key
+
+CYCLE_COUNT = 2
+
+
+@requires_api_key("OPENAI_API_KEY")
+@pytest.mark.vcr
+def test_browse_website(
+    browser_agent: Agent,
+    patched_api_requestor: MockerFixture,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    file_path = browser_agent.workspace.get_path("browse_website.txt")
+    run_interaction_loop(monkeypatch, browser_agent, CYCLE_COUNT)
+
+    content = read_file(file_path)
+    assert "£25.89" in content, f"Expected £25.89, got {content}"
diff --git a/tests/integration/challenges/basic_abilities/test_write_file.py b/tests/integration/challenges/basic_abilities/test_write_file.py
new file mode 100644
index 00000000..36a97733
--- /dev/null
+++ b/tests/integration/challenges/basic_abilities/test_write_file.py
@@ -0,0 +1,23 @@
+import pytest
+from pytest_mock import MockerFixture
+
+from autogpt.agent import Agent
+from autogpt.commands.file_operations import read_file
+from tests.integration.challenges.utils import run_interaction_loop
+from tests.utils import requires_api_key
+
+CYCLE_COUNT = 3
+
+
+@requires_api_key("OPENAI_API_KEY")
+@pytest.mark.vcr
+def test_write_file(
+    writer_agent: Agent,
+    patched_api_requestor: MockerFixture,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    file_path = str(writer_agent.workspace.get_path("hello_world.txt"))
+    run_interaction_loop(monkeypatch, writer_agent, CYCLE_COUNT)
+
+    content = read_file(file_path)
+    assert content == "Hello World", f"Expected 'Hello World', got {content}"
diff --git a/tests/integration/challenges/conftest.py b/tests/integration/challenges/conftest.py
index dce4518d..9bb5a1a4 100644
--- a/tests/integration/challenges/conftest.py
+++ b/tests/integration/challenges/conftest.py
@@ -1,17 +1,21 @@
 import pytest
+from _pytest.config import Config
+from _pytest.config.argparsing import Parser
+from _pytest.fixtures import FixtureRequest
+from _pytest.monkeypatch import MonkeyPatch
 
 
-def pytest_addoption(parser):
+def pytest_addoption(parser: Parser) -> None:
     parser.addoption(
         "--level", action="store", default=None, type=int, help="Specify test level"
     )
 
 
-def pytest_configure(config):
+def pytest_configure(config: Config) -> None:
     config.option.level = config.getoption("--level")
 
 
 @pytest.fixture
-def user_selected_level(request) -> int:
+def user_selected_level(request: FixtureRequest) -> int:
     ## used for challenges in the goal oriented tests
     return request.config.option.level
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index b96e811a..0bf7bfe6 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -1,32 +1,22 @@
-import contextlib
-from functools import wraps
-from typing import Generator
-
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.commands.file_operations import read_file, write_to_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.integration.challenges.utils import run_multiple_times
+from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
 from tests.utils import requires_api_key
 
-
-def input_generator(input_sequence: list) -> Generator[str, None, None]:
-    """
-    Creates a generator that yields input strings from the given sequence.
-
-    :param input_sequence: A list of input strings.
-    :return: A generator that yields input strings.
-    """
-    yield from input_sequence
+CYCLE_COUNT = 3
+from autogpt.agent import Agent
 
 
-# @pytest.skip("Nobody beat this challenge yet")
 @pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 @run_multiple_times(3)
 def test_information_retrieval_challenge_a(
-    get_company_revenue_agent, monkeypatch, patched_api_requestor
+    get_company_revenue_agent: Agent,
+    monkeypatch: pytest.MonkeyPatch,
+    patched_api_requestor: MockerFixture,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs and checking the output file content.
@@ -34,12 +24,7 @@ def test_information_retrieval_challenge_a(
     :param get_company_revenue_agent: The agent to test.
     :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
     """
-    input_sequence = ["s", "s", "s", "s", "s", "EXIT"]
-    gen = input_generator(input_sequence)
-    monkeypatch.setattr("builtins.input", lambda _: next(gen))
-
-    with contextlib.suppress(SystemExit):
-        run_interaction_loop(get_company_revenue_agent, None)
+    run_interaction_loop(monkeypatch, get_company_revenue_agent, CYCLE_COUNT)
 
     file_path = str(get_company_revenue_agent.workspace.get_path("output.txt"))
     content = read_file(file_path)
diff --git a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
index 79228203..b8ae3004 100644
--- a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
+++ b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
@@ -1,30 +1,21 @@
-import contextlib
-from typing import Generator
-
 import pytest
 import yaml
 
+from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.integration.challenges.utils import run_multiple_times
+from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
 from tests.utils import requires_api_key
 
-
-def input_generator(input_sequence: list) -> Generator[str, None, None]:
-    """
-    Creates a generator that yields input strings from the given sequence.
-
-    :param input_sequence: A list of input strings.
-    :return: A generator that yields input strings.
-    """
-    yield from input_sequence
+CYCLE_COUNT = 6
 
 
 @pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 @run_multiple_times(3)
-def test_information_retrieval_challenge_a(kubernetes_agent, monkeypatch) -> None:
+def test_kubernetes_template_challenge_a(
+    kubernetes_agent: Agent, monkeypatch: pytest.MonkeyPatch
+) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs
     and checking the output file content.
@@ -32,12 +23,7 @@ def test_information_retrieval_challenge_a(kubernetes_agent, monkeypatch) -> Non
     :param get_company_revenue_agent: The agent to test.
     :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
     """
-    input_sequence = ["s", "s", "s", "s", "s", "EXIT"]
-    gen = input_generator(input_sequence)
-    monkeypatch.setattr("builtins.input", lambda _: next(gen))
-
-    with contextlib.suppress(SystemExit):
-        run_interaction_loop(kubernetes_agent, None)
+    run_interaction_loop(monkeypatch, kubernetes_agent, CYCLE_COUNT)
 
     file_path = str(kubernetes_agent.workspace.get_path("kube.yaml"))
     content = read_file(file_path)
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
index a4c6636e..15110227 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
@@ -550,4 +550,860 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created and nothing new
+      has happened."}, {"role": "user", "content": "Determine which next command to
+      use, and respond using the format specified above:"}, {"role": "assistant",
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
+      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
+      \"The first step is to understand the instructions and the tasks that need to
+      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
+      instructions_1.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
+      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
+      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: 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\nThis
+      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\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\nWrite
+      all the phrases into the file output.txt. The file has not been created yet.
+      After that, use the task_complete command.\n"}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6599'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5STy27bQAxF9/0KgmvZsGMnKbQO0mRVFEhWVWGMR4w0tUSqMxTswvC/F3pZjeoE
+        zUIbvnQu5/KILsUYbW7UllUxu/3yfFvfufR5vftmCr9+fFgdnu4X96m7e7jHCGX7k6z2HXMrZVWQ
+        OmGM0HoySinGy5vP6+XNar1cRFhKSgXGmFU6W82vZ1r7rcwWq8USI6yDyQjjI1Zeyko3KjvigPHV
+        erGOcBw+Jq6WEaqoKcbQzdX1KUKbi7MUMP5+xJLCMNhLQRijCcEFNawNprASNxKOCQMAJKi51Fmu
+        IcEY+mCfoIM2wQQfgYlSUIG9d0qgOUGVexMogGOVNiC1VrXO9aDw4gqCOjjO2kzbtFHZtHErZWk4
+        hebTnBjq0E1UE3abXvdYpgLn2FA1TzD6m9STCcKOsw73qS8DT79q5ylASe/Am5Y3giDwCHtXFGei
+        i+Bz+Mp2ZAEXzoDRdMCbkkJeK6Sy57bMZMQ6FVUVhjs9M3h+D+hj75IkPM77/5VP4Kx36qwL5dQg
+        xKH2TZvRVzjGd/RKDFa8J6vF77fNs6UX8TRgDEa69PahIrMbKNrlf8CjZw9eslj3l1M0HEq/nn/u
+        hE1JHcCr55lwGp9NT6xLNLXjiJHwVf/0IhuLV7WvCgIqqMoNK6SGLaUgDAa8cbyVPezzRiaZdoUG
+        1FiZJwkP4lqBvc6ET3iK8MWxC/mmOymMMahUGKHjlA4YL04/Tp/+AAAA//8DALF+obc3BQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c4e5cef41ce34-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:10:29 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '20220'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '87369'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 1.754s
+      x-request-id:
+      - 9cf7adfb755b717551ad7364f2c9ccd6
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\n[{''role'':
+      ''you'', ''content'': ''{\"command\": {\"name\": \"read_file\", \"args\": {\"filename\":
+      \"instructions_1.txt\"}}}''}]\n\"\"\"\n"}], "temperature": 0, "max_tokens":
+      0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '814'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPTUtDMRBF9/6KYdbpo8+nbc3OlbaggiAKKiUm075okgnJ1LaU/nd54sf2cu/h
+        3AN6hxptb8TGHEbTq4fZ9Xz//rQIt3lxvzf3V3c3/nG9WlzezVEhv72TlZ9FYznmQOI5oUJbyAg5
+        1O1kdtZOurOuUxjZUUCN6yyjrjkfyaa88WjcjVtUuKlmTagPmAvHLEvhD0oVdXveKvxn/+WnM4XC
+        YsJ/c3pxVGh79pYq6ucDRqq/1MKBUKOp1VcxSQZHTkJp8J/D1lQoFH1y5IBXEPfwfcFzApMcSG8E
+        Ekvv0xoSbaE3FXqTMyVyDcyhkCX/SQ4MWI7xe8NQyAzJygcCa0IgBy/oU5WysQO7LttGdvKCDR4V
+        rnzytV8WMpUTaqzCGRUOUjvU4+Pr8eQLAAD//wMAE8xbWKMBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c4ef19a03ce34-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:10:35 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '2672'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89815'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 122ms
+      x-request-id:
+      - bb82e64d01f00403286b9b4bd16d4c51
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was reminded of my creation
+      and that nothing new has happened. I received a command to read a file called
+      \"instructions_1.txt\"."}, {"role": "system", "content": "Command read_file
+      returned: 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\nThis
+      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\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\nWrite
+      all the phrases into the file output.txt. The file has not been created yet.
+      After that, use the task_complete command.\n"}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to write the phrases into the output.txt file using the write_to_file
+      command and then use the task_complete command to complete the task.\",\n        \"reasoning\":
+      \"The task requires me to write the phrases into a file, so I will use the write_to_file
+      command. Once the task is complete, I will use the task_complete command to
+      shut down the agent.\",\n        \"plan\": \"- Use the write_to_file command
+      to write the phrases into the output.txt file\\n- Use the task_complete command
+      to complete the task\",\n        \"criticism\": \"I need to ensure that the
+      phrases are written correctly into the output.txt file before completing the
+      task.\",\n        \"speak\": \"I will write the phrases into the output.txt
+      file and then complete the task.\"\n    },\n    \"command\": {\n        \"name\":
+      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"output.txt\",\n            \"text\":
+      \"The purple elephant danced on a rainbow while eating a taco.\\n\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7082'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SST2/TQBDF73yK0ZydKCGtqXyrQKCqIC4UIWoUbdYTe5v1rOUZN4HI3x0lttMm
+        IEW5zp+3v/d2tugyTNAWRm1Z+dG7Tw839/zz9vnr5z9fFu9v/Yen2Yrlx/f19OM9RhgWT2S13xjb
+        UFae1AXGCG1NRinDZBrfXE3j2dUsjrAMGXlMMK90NBtfj7SpF2E0mU2mGGEjJidMtljVoax0rmFF
+        LJi8vZ7EEb6IHxrTeBKhBjX+ZTaO4zZCWwRnSTB53GJJMgjXwRMmaEScqGHdYQZW4p2FbcoAAClq
+        EZq8UEkxgb7YN2iju2KKd1CYZwJprCWRZeP9b1jXTpUYtCCoitoICTjWsC+ERqtGx7pRWDpPY7iD
+        tfMeOKyhEdrPqJHVvLdJYENZGs5AAxxqw9Q4xeg1WE1GAjvOO7pv/RgURmBBxAeF7Ag5AgkDyFkI
+        KRqFLKw7gyYn1lOMyhvuCEbwcLGpEzFbO3XWSTkkzkT7RWJp6t2a0cPuOaewoGWoaW9CHednjEhF
+        ZnVZlkc/+v+suhfaaLizPox/zoxNSd3jR+GdMJo6P73Q18dwIf1AtyfsQVNusY1w6dhJMe9kMUHR
+        UGGEjjPaYDJpf7Vv/gIAAP//AwDVHqaiNwQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c4f033fb8ce34-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:10:50 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '14190'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '87343'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 1.77s
+      x-request-id:
+      - efeb33e59612d816eca6bb4263edce4e
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created and nothing new
+      has happened."}, {"role": "user", "content": "Determine which next command to
+      use, and respond using the format specified above:"}, {"role": "assistant",
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
+      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
+      \"The first step is to understand the instructions and the tasks that need to
+      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
+      instructions_1.txt file\\n- Analyze the instructions and determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
+      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
+      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: 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\nThe
+      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\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\nRead
+      the file instructions_2.txt using the read_file command."}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6541'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6yTTWvbQBCG7/0Vw5wl428nuuUQktBLKDYUqmLWq7G09WpW3R0Ru8b/vciSo+K0
+        pZBe5+N9n1m9OqLJMEFdKNFlZePFw+qm5O96uVuOsgf3+Gnx+Hz/+X7x8W75vMII3eYbaek2BtqV
+        lSUxjjFC7UkJZZiM5jfT0XwynU8jLF1GFhPMK4kng1kstd+4eDgZjjDCOqicMDli5V1ZyVrcjjhg
+        Mp7cjiPsxV8bo5tZhOJE2X52tlicItSFM5oCJl+OWFK4CHtnCRNUIZggiqXBdCzEzQnHlAEAUpTC
+        1XkhIcUEumLXoL00xRSXBYHhIL7WDVFYjweyF9gaS9AoKsMBFFgTBNz2XA9gGKQgyIwnLc4fBvAE
+        oXC1zaAOdO41C+t2WruyVJyBuFamaf9BJ8XoV0xPKjg2nP9nVib6F5xmJCMhXxpur2LaCwShKlyj
+        VlZxSxnD6j1vkKYcwx0re/jRq/Tn/AXpikh7I0abULZY/dXEofbNshJ4gpoz8k2Gst+4dVEle4AN
+        bZ0nqLzTRJnhHF6MFKD4AKLC7s2DhIrU7mL9Yqx9dzRa9VN0SXe3/CbcrEpqjXunKzjl8+ufom30
+        n+Es8Op6du4AUj7hKcKtYROKdZtRTDCIqzBCwxntMRmevp4+/AQAAP//AwBHX/WchQQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c4fb30e7a2566-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:11:20 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '16266'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '87370'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 1.752s
+      x-request-id:
+      - 20e0d58720f751a589521080b8e101f4
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was reminded of my creation
+      and that nothing new has happened. I received a command to read a file called
+      \"instructions_1.txt\"."}, {"role": "system", "content": "Command read_file
+      returned: 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\nThe
+      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\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\nRead
+      the file instructions_2.txt using the read_file command."}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The instructions_2.txt file contains a list of files in the directory. I should
+      use the list_files command to list the files in the directory.\",\n        \"reasoning\":
+      \"The instructions_2.txt file contains a list of files in the directory. I need
+      to list the files in the directory to determine the next steps.\",\n        \"plan\":
+      \"- Use the list_files command to list the files in the directory\\n- Analyze
+      the list of files to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the list of files completely before proceeding
+      with any tasks.\",\n        \"speak\": \"I will use the list_files command to
+      list the files in the directory.\"\n    },\n    \"command\": {\n        \"name\":
+      \"list_files\",\n        \"args\": {\n            \"directory\": \".\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command list_files returned: [''file_logger.txt'',
+      ''instructions_2.txt'', ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6894'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA9yTTW/TQBCG7/yK0Vx6caKmTdLUNxAfDZXgQrlgFG3tiT3t7qzZHdOkUf47sp0Q
+        lFIhJE4c5+ud5x1pNsgFpphXRnNX28HFu5vL6ecPb+bvP66uJtev/OO3q/L6tbw9u5MxJuhv7yjX
+        3cQw9662pOwFE8wDGaUC09F0Nh5Nz8ezcYLOF2QxxbLWwflwMtAm3PrB6fnpCBNsoikJ0w3Wwbta
+        F+rvSSKmZ+OLSYIH8UNhNE5QvRp7SE1nl9sE88pzThHTLxt0FPfCwVvCFE2MHNWItphelKS1sMkE
+        ACBDrXxTVhozTGGX3BVopW0yw08VgeWo4JewZEsRWEArgoID5erDGlhy2xQUwXQdkBtrqYCTNlhY
+        X5YUhrrSkyHMIVa+sQUEMkWnsoOKrbxWHHuFJrKUXb1tXPSq3jkjBaiHgpSCYyHgdooCAUcwsgZ2
+        tQ+tX2BZ+uBMe8Vhhsmv5gKZ6IWl/G8d1tZIb24AN5Ge3/MMJT211mFnmQzgpRi7fqTfjnX6f89/
+        hJ8HVs45ut7DHISowyWJTWg3G4U5GAfiFR5M1O6Y7HqXbcAhkKXvf7hTrMnc75c8sLXQ/MNrDTPs
+        l22T/cPtxJ78mxhHPcfPxUeoJpTHb9oX2t7D+BHInqCj2MFkssVtgksWjtWifwZMMaqvMUGWglaY
+        nm6/bl/8AAAA//8DADzIl+IkBQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c502dcf0b2566-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:11:42 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '19115'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '87358'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 1.761s
+      x-request-id:
+      - 243e07746019a07393b73bf4e6f81347
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nI was reminded of my creation and that nothing new has happened. I received
+      a command to read a file called \"instructions_1.txt\".''}\n\"\"\"\n\nLatest
+      Development:\n\"\"\"\n[{''role'': ''your computer'', ''content'': \"Command
+      read_file returned: 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\\nThe
+      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\\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\\nRead
+      the file instructions_2.txt using the read_file command.\"}]\n\"\"\"\n"}], "temperature":
+      0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3007'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SSQYsTQRCF7/6Koi57mQyJMaMzt4UFWXBBUQ/iSqh0V9KtPdVNd81mJOS/Syer
+        +wO8VtX7eO9RJ/QWBzSO1IwpLN6+/9p/nu9ub3tifRi/9U9zme8+dp8e0oeEDcbdTzb6rGhNHFNg
+        9VGwQZOZlC0Oq+7dm1W33iy7BsdoOeCAh6SLdbtZ6JR3cbFcL1fY4FTowDicMOU4Jt1q/MVScFht
+        +r7BF/i/Rdc1qFEpvJx23ebcoHHRGy44fD/hyOUvN8fAOCCV4ouSaHUZRVlqgns4UoHMoxfLFuIe
+        xt9wCeGjAIkFdaQgUZ2XAwgfwVEBRymxsG3hHjIb9k9sgcDEcbxoImSmOtn7wGAoBLbwiF6K5slU
+        dtmuWp31Ef8H8fqKgKlUc+r4otleFVdQC18cg5lyZlFILlNh8AVu6jhNOQUGDpwciYIlMbUFAYJM
+        XnbxCEdXabUQOQCBkontDZ4b3HvxxW0zU4mCAxaN9TlqkTMOy/OP86s/AAAA//8DAEI0JttZAgAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c50bb1e802566-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:11:52 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '6410'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89266'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 488ms
+      x-request-id:
+      - 1fe6ecd574366d3d8bf02ca2e417e0ba
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
+      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was reminded of my creation
+      and that nothing new has happened. I received a command to read a file called
+      \"instructions_1.txt\". I received a command to read a file called \"instructions_2.txt\"
+      using the read_file command. The current phrase is ''The purple elephant danced
+      on a rainbow while eating a taco.''"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The instructions_2.txt file contains a list of files in the directory. I should
+      use the list_files command to list the files in the directory.\",\n        \"reasoning\":
+      \"The instructions_2.txt file contains a list of files in the directory. I need
+      to list the files in the directory to determine the next steps.\",\n        \"plan\":
+      \"- Use the list_files command to list the files in the directory\\n- Analyze
+      the list of files to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the list of files completely before proceeding
+      with any tasks.\",\n        \"speak\": \"I will use the list_files command to
+      list the files in the directory.\"\n    },\n    \"command\": {\n        \"name\":
+      \"list_files\",\n        \"args\": {\n            \"directory\": \".\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command list_files returned: [''file_logger.txt'',
+      ''instructions_2.txt'', ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"The list of files in the directory includes a file called
+      ''file_logger.txt''. I should read the contents of this file using the read_file
+      command to determine if there is any important information.\",\n        \"reasoning\":
+      \"The list of files in the directory includes a file called ''file_logger.txt''.
+      I should read the contents of this file using the read_file command to determine
+      if there is any important information.\",\n        \"plan\": \"- Use the read_file
+      command to read the contents of the ''file_logger.txt'' file\\n- Analyze the
+      contents of the file to determine if there is any important information\",\n        \"criticism\":
+      \"I need to ensure that I am not wasting time reading irrelevant information.\",\n        \"speak\":
+      \"I will use the read_file command to read the contents of the ''file_logger.txt''
+      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"file_logger.txt\"\n        }\n    }\n}"}, {"role":
+      "system", "content": "Command read_file returned: write: /private/var/folders/lx/cvc0bpt93vx2mcwxxl2xdzc00000gn/T/pytest-of-merwanehamadi/pytest-177/test_memory_challenge_c0/home/users/monty/auto_gpt_workspace/instructions_1.txt
+      #fc64cfdd6fe9b583550c67133b7d9555\nwrite: /private/var/folders/lx/cvc0bpt93vx2mcwxxl2xdzc00000gn/T/pytest-of-merwanehamadi/pytest-177/test_memory_challenge_c0/home/users/monty/auto_gpt_workspace/instructions_2.txt
+      #2b530a674d388da03a41627bd4d10824\n"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6528'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA9xTS2/TQBC+8ytGc8nFiZK6SYovSBVSCUJVJVIOYBRt1hN7yHrX9Y7bRJH/e+VH
+        SBsOIMSJw15m5nvNag7ICUaoMyU6L8xwfnP/9uvy6uHuevk4vl0kn295J+H0+stH/vSAAbr1D9LS
+        I0ba5YUhYWcxQF2SEkowmsyuLiezcDoJA8xdQgYjTAsZhqPpUKpy7YbjcDzBACuvUsLogEXp8kJW
+        4rZkPUaTy9k8wBP5z8bFNAxQnChzmp1fjOsAdeZYk8fo2wFz8kfi0hnCCJX37EVZaWw6K2SbCIfY
+        AgDEKJmr0kx8jBH0xb5BO2mKMS4zgh7pwW1AMoLBhg2tjEtTKkeykwE0BWCbsFZCIJmSZrAkYA8K
+        bu6WoFKyAk8sWUuxpT0M2tpqMhjBAnzmKpNAHwEka5AtRhwkJFTmbAl40xOr5tk9iPJb3ykuQCsL
+        CRlKWxcOWEYxBi+DlaS8s2zT/zJdYZTtgg3h3lPrpddcdXLa5bmySQM/maHfZohjO4T3f+mzYWuJ
+        ztzqkoU1+7yzvABL1Doj66uSjnQqP7KxTV8qNeKNXbYniYEHrQq1ZsPC5M8X5AtS26PcExsD1b9c
+        0yjGTq0OjifWM/1yYVbl1Bl5pXzmV5Xp+XF2jS3tO3Qv/QrXjfS83dgHMsYFkDjYuwoy9fgH/7Z3
+        1btjoDZUny22NdYBbtiyz1bdRWGEXlyBAbJNaIfRuP5ev3kGAAD//wMAelGZnmUFAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7c50e45c442566-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 15:12:14 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-adtx4fhfg1qsiyzdoaxciooj
+      openai-processing-ms:
+      - '21873'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86437'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.374s
+      x-request-id:
+      - 350c85281465e8568485def8af626227
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/memory/test_memory_challenge_a.py b/tests/integration/challenges/memory/test_memory_challenge_a.py
index fb5876cd..3e293099 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_a.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_a.py
@@ -1,9 +1,9 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.integration.challenges.utils import get_level_to_run
+from tests.integration.challenges.utils import get_level_to_run, run_interaction_loop
 from tests.utils import requires_api_key
 
 LEVEL_CURRENTLY_BEATEN = 3  # real level beaten 30 and maybe more, but we can't record it, the cassette is too big
@@ -13,7 +13,10 @@ MAX_LEVEL = 3
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_a(
-    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
+    memory_management_agent: Agent,
+    user_selected_level: int,
+    patched_api_requestor: MockerFixture,
+    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
     The agent reads a file containing a task_id. Then, it reads a series of other files.
@@ -29,13 +32,11 @@ def test_memory_challenge_a(
     task_id = "2314"
     create_instructions_files(memory_management_agent, num_files, task_id)
 
-    try:
-        run_interaction_loop(memory_management_agent, 400)
-    # catch system exit exceptions
-    except SystemExit:
-        file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-        content = read_file(file_path)
-        assert task_id in content, f"Expected the file to contain {task_id}"
+    run_interaction_loop(monkeypatch, memory_management_agent, num_files + 2)
+
+    file_path = str(memory_management_agent.workspace.get_path("output.txt"))
+    content = read_file(file_path)
+    assert task_id in content, f"Expected the file to contain {task_id}"
 
 
 def create_instructions_files(
diff --git a/tests/integration/challenges/memory/test_memory_challenge_b.py b/tests/integration/challenges/memory/test_memory_challenge_b.py
index 21d46b38..28261cb1 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_b.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_b.py
@@ -1,12 +1,16 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.integration.challenges.utils import generate_noise, get_level_to_run
+from tests.integration.challenges.utils import (
+    generate_noise,
+    get_level_to_run,
+    run_interaction_loop,
+)
 from tests.utils import requires_api_key
 
-LEVEL_CURRENTLY_BEATEN = None
+LEVEL_CURRENTLY_BEATEN = -1
 MAX_LEVEL = 5
 NOISE = 1000
 
@@ -14,7 +18,10 @@ NOISE = 1000
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_b(
-    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
+    memory_management_agent: Agent,
+    user_selected_level: int,
+    patched_api_requestor: MockerFixture,
+    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
     The agent reads a series of files, each containing a task_id and noise. After reading 'n' files,
@@ -30,13 +37,12 @@ def test_memory_challenge_b(
     task_ids = [str(i * 1111) for i in range(1, current_level + 1)]
     create_instructions_files(memory_management_agent, current_level, task_ids)
 
-    try:
-        run_interaction_loop(memory_management_agent, 60)
-    except SystemExit:
-        file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-        content = read_file(file_path)
-        for task_id in task_ids:
-            assert task_id in content, f"Expected the file to contain {task_id}"
+    run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
+
+    file_path = str(memory_management_agent.workspace.get_path("output.txt"))
+    content = read_file(file_path)
+    for task_id in task_ids:
+        assert task_id in content, f"Expected the file to contain {task_id}"
 
 
 def create_instructions_files(
diff --git a/tests/integration/challenges/memory/test_memory_challenge_c.py b/tests/integration/challenges/memory/test_memory_challenge_c.py
index 634a24a3..b6cbc60d 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_c.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_c.py
@@ -1,20 +1,28 @@
 import pytest
+from _pytest.monkeypatch import MonkeyPatch
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.integration.challenges.utils import generate_noise, get_level_to_run
+from tests.integration.challenges.utils import (
+    generate_noise,
+    get_level_to_run,
+    run_interaction_loop,
+)
 from tests.utils import requires_api_key
 
-LEVEL_CURRENTLY_BEATEN = None
+LEVEL_CURRENTLY_BEATEN = -1
 MAX_LEVEL = 5
 NOISE = 1000
 
 
-@pytest.mark.vcr
+# @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
 def test_memory_challenge_c(
-    memory_management_agent: Agent, user_selected_level: int, patched_api_requestor
+    memory_management_agent: Agent,
+    user_selected_level: int,
+    patched_api_requestor: MockerFixture,
+    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
     Instead of reading task Ids from files as with the previous challenges, the agent now must remember
@@ -46,13 +54,12 @@ def test_memory_challenge_c(
         memory_management_agent, current_level, level_silly_phrases
     )
 
-    try:
-        run_interaction_loop(memory_management_agent, 90)
-    except SystemExit:
-        file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-        content = read_file(file_path)
-        for phrase in level_silly_phrases:
-            assert phrase in content, f"Expected the file to contain {phrase}"
+    run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
+
+    file_path = str(memory_management_agent.workspace.get_path("output.txt"))
+    content = read_file(file_path)
+    for phrase in level_silly_phrases:
+        assert phrase in content, f"Expected the file to contain {phrase}"
 
 
 def create_instructions_files(
diff --git a/tests/integration/challenges/test_challenge_should_be_formatted_properly.py b/tests/integration/challenges/test_challenge_should_be_formatted_properly.py
new file mode 100644
index 00000000..f71bc200
--- /dev/null
+++ b/tests/integration/challenges/test_challenge_should_be_formatted_properly.py
@@ -0,0 +1,59 @@
+import importlib.util
+import inspect
+import os
+from types import ModuleType
+from typing import List
+
+# Path to the challenges folder
+CHALLENGES_DIR = os.path.join(
+    os.path.dirname(os.path.realpath(__file__)), "../challenges"
+)
+
+
+def get_python_files(directory: str, exclude_file: str) -> List[str]:
+    """Recursively get all python files in a directory and subdirectories."""
+    python_files: List[str] = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            if (
+                file.endswith(".py")
+                and file.startswith("test_")
+                and file != exclude_file
+            ):
+                python_files.append(os.path.join(root, file))
+    return python_files
+
+
+def load_module_from_file(test_file: str) -> ModuleType:
+    spec = importlib.util.spec_from_file_location("module.name", test_file)
+    assert spec is not None, f"Unable to get spec for module in file {test_file}"
+    module = importlib.util.module_from_spec(spec)
+    assert (
+        spec.loader is not None
+    ), f"Unable to get loader for module in file {test_file}"
+    spec.loader.exec_module(module)
+    return module
+
+
+def get_test_functions(module: ModuleType) -> List:
+    return [
+        o
+        for o in inspect.getmembers(module)
+        if inspect.isfunction(o[1]) and o[0].startswith("test_")
+    ]
+
+
+def assert_single_test_function(functions_list: List, test_file: str) -> None:
+    assert len(functions_list) == 1, f"{test_file} should contain only one function"
+    assert (
+        functions_list[0][0][5:] == os.path.basename(test_file)[5:-3]
+    ), f"The function in {test_file} should have the same name as the file without 'test_' prefix"
+
+
+def test_method_name_and_count() -> None:
+    current_file: str = os.path.basename(__file__)
+    test_files: List[str] = get_python_files(CHALLENGES_DIR, current_file)
+    for test_file in test_files:
+        module = load_module_from_file(test_file)
+        functions_list = get_test_functions(module)
+        assert_single_test_function(functions_list, test_file)
diff --git a/tests/integration/challenges/utils.py b/tests/integration/challenges/utils.py
index d8aa7fcb..d80ca977 100644
--- a/tests/integration/challenges/utils.py
+++ b/tests/integration/challenges/utils.py
@@ -1,13 +1,16 @@
+import contextlib
 import random
 from functools import wraps
-from typing import Optional
+from typing import Any, Callable, Dict, Generator, Optional, Tuple
 
 import pytest
 
+from autogpt.agent import Agent
+
 
 def get_level_to_run(
-    user_selected_level: Optional[int],
-    level_currently_beaten: Optional[int],
+    user_selected_level: int,
+    level_currently_beaten: int,
     max_level: int,
 ) -> int:
     """
@@ -25,7 +28,7 @@ def get_level_to_run(
         ValueError: If the user-selected level is greater than the maximum level allowed.
     """
     if user_selected_level is None:
-        if level_currently_beaten is None:
+        if level_currently_beaten == -1:
             pytest.skip(
                 "No one has beaten any levels so we cannot run the test in our pipeline"
             )
@@ -36,7 +39,7 @@ def get_level_to_run(
     return user_selected_level
 
 
-def generate_noise(noise_size) -> str:
+def generate_noise(noise_size: int) -> str:
     return "".join(
         random.choices(
             "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789",
@@ -45,19 +48,46 @@ def generate_noise(noise_size) -> str:
     )
 
 
-def run_multiple_times(times):
+def run_multiple_times(times: int) -> Callable:
     """
     Decorator that runs a test function multiple times.
 
     :param times: The number of times the test function should be executed.
     """
 
-    def decorator(test_func):
+    def decorator(test_func: Callable[..., Any]) -> Callable[..., Any]:
         @wraps(test_func)
-        def wrapper(*args, **kwargs):
+        def wrapper(*args: Tuple[Any, ...], **kwargs: Dict[str, Any]) -> None:
             for _ in range(times):
                 test_func(*args, **kwargs)
 
         return wrapper
 
     return decorator
+
+
+def setup_mock_input(monkeypatch: pytest.MonkeyPatch, cycle_count: int) -> None:
+    """
+    Sets up the mock input for testing.
+
+    :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
+    :param cycle_count: The number of cycles to mock.
+    """
+    input_sequence = ["y"] * (cycle_count) + ["EXIT"]
+
+    def input_generator() -> Generator[str, None, None]:
+        """
+        Creates a generator that yields input strings from the given sequence.
+        """
+        yield from input_sequence
+
+    gen = input_generator()
+    monkeypatch.setattr("builtins.input", lambda _: next(gen))
+
+
+def run_interaction_loop(
+    monkeypatch: pytest.MonkeyPatch, agent: Agent, cycle_count: int
+) -> None:
+    setup_mock_input(monkeypatch, cycle_count)
+    with contextlib.suppress(SystemExit):
+        agent.start_interaction_loop()
diff --git a/tests/integration/goal_oriented/test_browse_website.py b/tests/integration/goal_oriented/test_browse_website.py
deleted file mode 100644
index 3ce85689..00000000
--- a/tests/integration/goal_oriented/test_browse_website.py
+++ /dev/null
@@ -1,18 +0,0 @@
-import pytest
-
-from autogpt.agent import Agent
-from autogpt.commands.file_operations import read_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.utils import requires_api_key
-
-
-@requires_api_key("OPENAI_API_KEY")
-@pytest.mark.vcr
-def test_browse_website(browser_agent: Agent, patched_api_requestor) -> None:
-    file_path = browser_agent.workspace.get_path("browse_website.txt")
-    try:
-        run_interaction_loop(browser_agent, 120)
-    # catch system exit exceptions
-    except SystemExit:  # the agent returns an exception when it shuts down
-        content = read_file(file_path)
-        assert "£25.89" in content, f"Expected £25.89, got {content}"
diff --git a/tests/integration/goal_oriented/test_write_file.py b/tests/integration/goal_oriented/test_write_file.py
deleted file mode 100644
index 55db3f4a..00000000
--- a/tests/integration/goal_oriented/test_write_file.py
+++ /dev/null
@@ -1,21 +0,0 @@
-import os
-
-import openai
-import pytest
-
-from autogpt.agent import Agent
-from autogpt.commands.file_operations import read_file
-from tests.integration.agent_utils import run_interaction_loop
-from tests.utils import requires_api_key
-
-
-@requires_api_key("OPENAI_API_KEY")
-@pytest.mark.vcr
-def test_write_file(writer_agent: Agent, patched_api_requestor) -> None:
-    file_path = str(writer_agent.workspace.get_path("hello_world.txt"))
-    try:
-        run_interaction_loop(writer_agent, 200)
-    # catch system exit exceptions
-    except SystemExit:  # the agent returns an exception when it shuts down
-        content = read_file(file_path)
-        assert content == "Hello World", f"Expected 'Hello World', got {content}"

From c04f2210cc3aa341d53b8e714f53a8927ab6b476 Mon Sep 17 00:00:00 2001
From: gravelBridge <john.tian31@gmail.com>
Date: Mon, 15 May 2023 20:02:33 -0700
Subject: [PATCH 008/112] Added feature to interrupt y -N continuous commands.
 (#4230)

* Added feature to interrupt y -N continuous commands.

* Fixed formatting.

---------

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/agent/agent.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index 4db9e2ee..68888401 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -1,3 +1,5 @@
+import signal
+import sys
 from datetime import datetime
 
 from colorama import Fore, Style
@@ -88,6 +90,20 @@ class Agent:
         arguments = None
         user_input = ""
 
+        # Signal handler for interrupting y -N
+        def signal_handler(signum, frame):
+            if self.next_action_count == 0:
+                sys.exit()
+            else:
+                print(
+                    Fore.RED
+                    + "Interrupt signal received. Stopping continuous command execution."
+                    + Style.RESET_ALL
+                )
+                self.next_action_count = 0
+
+        signal.signal(signal.SIGINT, signal_handler)
+
         while True:
             # Discontinue if continuous limit is reached
             self.cycle_count += 1

From 517c0805443cbf452cc8c161400b98d39f4533c0 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 15 May 2023 20:43:21 -0700
Subject: [PATCH 009/112] fix ci cassettes (#4234)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 .github/workflows/add-cassettes.yml | 4 ++--
 .github/workflows/ci.yml            | 6 ++++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/add-cassettes.yml b/.github/workflows/add-cassettes.yml
index 90e4402d..9bf5b1b8 100644
--- a/.github/workflows/add-cassettes.yml
+++ b/.github/workflows/add-cassettes.yml
@@ -22,7 +22,7 @@ jobs:
       - name: Reset branch
         run: |
           git checkout ${{ github.event.pull_request.base.ref }}
-          git reset --hard origin/cassette-diff-${{ github.event.pull_request.number }}
+          git reset --hard origin/cassette-diff-${{ github.event.pull_request.head.sha }}
 
       - name: Create PR
         id: create_pr
@@ -30,7 +30,7 @@ jobs:
         with:
           commit-message: Update cassettes
           signoff: false
-          branch: cassette-diff-${{ github.event.pull_request.number }}
+          branch: cassette-diff-${{ github.event.pull_request.head.sha }}
           delete-branch: false
           title: "Update cassettes"
           body: "This PR updates the cassettes."
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index c2afde55..b36b45e8 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -95,11 +95,13 @@ jobs:
 
       - name: Stage new files and commit
         run: |
+          COMMIT_SHA=$(git rev-parse HEAD) # take the sha before committing the cassette
           git add tests
           git diff --cached --quiet && echo "No changes to commit" && exit 0
           git config user.email "github-actions@github.com"
           git config user.name "GitHub Actions"
           git commit -m "Add new cassettes"
-          git checkout -b cassette-diff-${{ github.event.pull_request.number }}
+          
+          git checkout -b cassette-diff-${COMMIT_SHA}
           git remote add target https://${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.event.pull_request.base.repo.full_name }}
-          git push -f target cassette-diff-${{ github.event.pull_request.number }}
+          git push -f target cassette-diff-${COMMIT_SHA}

From 85fe6f36c2e5900d40de00bbf400ddc32c8cee46 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Malahieude=20Timoth=C3=A9?= <t.malahieude@gmail.com>
Date: Tue, 16 May 2023 06:20:14 +0200
Subject: [PATCH 010/112] Fix ai_name not passed to Agent (#3948)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/main.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/autogpt/main.py b/autogpt/main.py
index 72eb6786..1a0f6adb 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -149,6 +149,8 @@ def run_auto_gpt(
     ai_name = ""
     ai_config = construct_main_ai_config()
     ai_config.command_registry = command_registry
+    if ai_config.ai_name:
+        ai_name = ai_config.ai_name
     # print(prompt)
     # Initialize variables
     full_message_history = []

From cb2b13dff63286fdef13edb84bbf49b1e5e44025 Mon Sep 17 00:00:00 2001
From: Nicholas Tindle <nick@ntindle.com>
Date: Tue, 16 May 2023 03:46:20 -0500
Subject: [PATCH 011/112] Legal warning on continuous run (#4239)

* feat: legal warning on continuous

* fix: formatting

* ci: fix formatting
---
 autogpt/main.py  |  5 +++++
 autogpt/utils.py | 21 +++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/autogpt/main.py b/autogpt/main.py
index 1a0f6adb..d07a0993 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -16,6 +16,7 @@ from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT, construct_main_ai_
 from autogpt.utils import (
     get_current_git_branch,
     get_latest_bulletin,
+    get_legal_warning,
     markdown_to_ansi_style,
 )
 from autogpt.workspace import Workspace
@@ -60,6 +61,10 @@ def run_auto_gpt(
         skip_news,
     )
 
+    if cfg.continuous_mode:
+        for line in get_legal_warning().split("\n"):
+            logger.warn(markdown_to_ansi_style(line), "LEGAL:", Fore.RED)
+
     if not cfg.skip_news:
         motd, is_new_motd = get_latest_bulletin()
         if motd:
diff --git a/autogpt/utils.py b/autogpt/utils.py
index 6a3ef0ae..8685d402 100644
--- a/autogpt/utils.py
+++ b/autogpt/utils.py
@@ -153,3 +153,24 @@ def markdown_to_ansi_style(markdown: str):
 
         ansi_lines.append(f"{line_style}{line}{Style.RESET_ALL}")
     return "\n".join(ansi_lines)
+
+
+def get_legal_warning() -> str:
+    legal_text = """
+## DISCLAIMER AND INDEMNIFICATION AGREEMENT
+### PLEASE READ THIS DISCLAIMER AND INDEMNIFICATION AGREEMENT CAREFULLY BEFORE USING THE AUTOGPT SYSTEM. BY USING THE AUTOGPT SYSTEM, YOU AGREE TO BE BOUND BY THIS AGREEMENT.
+
+## Introduction
+AutoGPT (the "System") is a project that connects a GPT-like artificial intelligence system to the internet and allows it to automate tasks. While the System is designed to be useful and efficient, there may be instances where the System could perform actions that may cause harm or have unintended consequences.
+
+## No Liability for Actions of the System
+The developers, contributors, and maintainers of the AutoGPT project (collectively, the "Project Parties") make no warranties or representations, express or implied, about the System's performance, accuracy, reliability, or safety. By using the System, you understand and agree that the Project Parties shall not be liable for any actions taken by the System or any consequences resulting from such actions.
+
+## User Responsibility and Respondeat Superior Liability
+As a user of the System, you are responsible for supervising and monitoring the actions of the System while it is operating on your
+behalf. You acknowledge that using the System could expose you to potential liability including but not limited to respondeat superior and you agree to assume all risks and liabilities associated with such potential liability.
+
+## Indemnification
+By using the System, you agree to indemnify, defend, and hold harmless the Project Parties from and against any and all claims, liabilities, damages, losses, or expenses (including reasonable attorneys' fees and costs) arising out of or in connection with your use of the System, including, without limitation, any actions taken by the System on your behalf, any failure to properly supervise or monitor the System, and any resulting harm or unintended consequences.
+            """
+    return legal_text

From 0839a16d2772d1fead0ed1e9c87c85e28e9eae30 Mon Sep 17 00:00:00 2001
From: Cenny <cwenner@gmail.com>
Date: Tue, 16 May 2023 11:07:32 +0200
Subject: [PATCH 012/112] Clarify .env.template image-provider options (#3720)

* Clarify .env.template image-provider options

* feat: consolidate duplicate options

* Simplify

---------

Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 .env.template | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/.env.template b/.env.template
index aba612fd..fe217a43 100644
--- a/.env.template
+++ b/.env.template
@@ -149,10 +149,10 @@ OPENAI_API_KEY=your-openai-api-key
 ### IMAGE GENERATION PROVIDER
 ################################################################################
 
-### OPEN AI
-## IMAGE_PROVIDER - Image provider (Example: dalle)
+### COMMON SETTINGS
+## IMAGE_PROVIDER - Image provider - dalle, huggingface, or sdwebui
 ## IMAGE_SIZE - Image size (Example: 256)
-##   DALLE: 256, 512, 1024
+## Image sizes for dalle: 256, 512, 1024
 # IMAGE_PROVIDER=dalle
 # IMAGE_SIZE=256
 

From c1cd54d1ea980150aa999676dc038210b2530d36 Mon Sep 17 00:00:00 2001
From: Stefan Ayala <stefanayala3266@gmail.com>
Date: Tue, 16 May 2023 07:10:33 -0700
Subject: [PATCH 013/112] Allow absolute paths if contained in workspace
 (#3932)

Maybe I'm missing something but I don't see the harm of accessing an absolute path if it's contained in the workspace

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/workspace/workspace.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/autogpt/workspace/workspace.py b/autogpt/workspace/workspace.py
index c1050230..1589a5be 100644
--- a/autogpt/workspace/workspace.py
+++ b/autogpt/workspace/workspace.py
@@ -120,7 +120,8 @@ class Workspace:
 
         logger.debug(f"Resolved root as '{root}'")
 
-        if relative_path.is_absolute():
+        # Allow exception for absolute paths if they are contained in your workspace directory.
+        if relative_path.is_absolute() and not relative_path.is_relative_to(root):
             raise ValueError(
                 f"Attempted to access absolute path '{relative_path}' in workspace '{root}'."
             )

From f424fac1d8b734356dccb6ce7a58bd34f34ec654 Mon Sep 17 00:00:00 2001
From: Kory Becker <kbecker@primaryobjects.com>
Date: Tue, 16 May 2023 11:02:55 -0400
Subject: [PATCH 014/112] Huggingface retry generate_image with delay (#2745)

Co-authored-by: Media <12145726+rihp@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
Co-authored-by; lc0rp
---
 autogpt/commands/image_gen.py |  46 ++++++++++----
 tests/test_image_gen.py       | 112 ++++++++++++++++++++++++++++++++--
 2 files changed, 143 insertions(+), 15 deletions(-)

diff --git a/autogpt/commands/image_gen.py b/autogpt/commands/image_gen.py
index fbed067f..5326cd52 100644
--- a/autogpt/commands/image_gen.py
+++ b/autogpt/commands/image_gen.py
@@ -1,5 +1,7 @@
 """ Image Generation Module for AutoGPT."""
 import io
+import json
+import time
 import uuid
 from base64 import b64decode
 
@@ -61,20 +63,42 @@ def generate_image_with_hf(prompt: str, filename: str) -> str:
         "X-Use-Cache": "false",
     }
 
-    response = requests.post(
-        API_URL,
-        headers=headers,
-        json={
-            "inputs": prompt,
-        },
-    )
+    retry_count = 0
+    while retry_count < 10:
+        response = requests.post(
+            API_URL,
+            headers=headers,
+            json={
+                "inputs": prompt,
+            },
+        )
 
-    image = Image.open(io.BytesIO(response.content))
-    logger.info(f"Image Generated for prompt:{prompt}")
+        if response.ok:
+            try:
+                image = Image.open(io.BytesIO(response.content))
+                logger.info(f"Image Generated for prompt:{prompt}")
+                image.save(filename)
+                return f"Saved to disk:{filename}"
+            except Exception as e:
+                logger.error(e)
+                break
+        else:
+            try:
+                error = json.loads(response.text)
+                if "estimated_time" in error:
+                    delay = error["estimated_time"]
+                    logger.debug(response.text)
+                    logger.info("Retrying in", delay)
+                    time.sleep(delay)
+                else:
+                    break
+            except Exception as e:
+                logger.error(e)
+                break
 
-    image.save(filename)
+        retry_count += 1
 
-    return f"Saved to disk:{filename}"
+    return f"Error creating image."
 
 
 def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str:
diff --git a/tests/test_image_gen.py b/tests/test_image_gen.py
index 136fb510..a48f26b9 100644
--- a/tests/test_image_gen.py
+++ b/tests/test_image_gen.py
@@ -6,6 +6,7 @@ import pytest
 from PIL import Image
 
 from autogpt.commands.image_gen import generate_image, generate_image_with_sd_webui
+from autogpt.config import Config
 from tests.utils import requires_api_key
 
 
@@ -19,7 +20,7 @@ def image_size(request):
     reason="The image is too big to be put in a cassette for a CI pipeline. We're looking into a solution."
 )
 @requires_api_key("OPENAI_API_KEY")
-def test_dalle(config, workspace, image_size, patched_api_requestor):
+def test_dalle(config, workspace, image_size):
     """Test DALL-E image generation."""
     generate_and_validate(
         config,
@@ -48,18 +49,18 @@ def test_huggingface(config, workspace, image_size, image_model):
     )
 
 
-@pytest.mark.skip(reason="External SD WebUI may not be available.")
+@pytest.mark.xfail(reason="SD WebUI call does not work.")
 def test_sd_webui(config, workspace, image_size):
     """Test SD WebUI image generation."""
     generate_and_validate(
         config,
         workspace,
-        image_provider="sdwebui",
+        image_provider="sd_webui",
         image_size=image_size,
     )
 
 
-@pytest.mark.skip(reason="External SD WebUI may not be available.")
+@pytest.mark.xfail(reason="SD WebUI call does not work.")
 def test_sd_webui_negative_prompt(config, workspace, image_size):
     gen_image = functools.partial(
         generate_image_with_sd_webui,
@@ -103,3 +104,106 @@ def generate_and_validate(
     assert image_path.exists()
     with Image.open(image_path) as img:
         assert img.size == (image_size, image_size)
+
+
+def test_huggingface_fail_request_with_delay(mocker):
+    config = Config()
+    config.huggingface_api_token = "1"
+
+    # Mock requests.post
+    mock_post = mocker.patch("requests.post")
+    mock_post.return_value.status_code = 500
+    mock_post.return_value.ok = False
+    mock_post.return_value.text = '{"error":"Model CompVis/stable-diffusion-v1-4 is currently loading","estimated_time":0}'
+
+    # Mock time.sleep
+    mock_sleep = mocker.patch("time.sleep")
+
+    config.image_provider = "huggingface"
+    config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = generate_image("astronaut riding a horse", 512)
+
+    assert result == "Error creating image."
+
+    # Verify retry was called with delay.
+    mock_sleep.assert_called_with(0)
+
+
+def test_huggingface_fail_request_no_delay(mocker):
+    config = Config()
+    config.huggingface_api_token = "1"
+
+    # Mock requests.post
+    mock_post = mocker.patch("requests.post")
+    mock_post.return_value.status_code = 500
+    mock_post.return_value.ok = False
+    mock_post.return_value.text = (
+        '{"error":"Model CompVis/stable-diffusion-v1-4 is currently loading"}'
+    )
+
+    # Mock time.sleep
+    mock_sleep = mocker.patch("time.sleep")
+
+    config.image_provider = "huggingface"
+    config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = generate_image("astronaut riding a horse", 512)
+
+    assert result == "Error creating image."
+
+    # Verify retry was not called.
+    mock_sleep.assert_not_called()
+
+
+def test_huggingface_fail_request_bad_json(mocker):
+    config = Config()
+    config.huggingface_api_token = "1"
+
+    # Mock requests.post
+    mock_post = mocker.patch("requests.post")
+    mock_post.return_value.status_code = 500
+    mock_post.return_value.ok = False
+    mock_post.return_value.text = '{"error:}'
+
+    # Mock time.sleep
+    mock_sleep = mocker.patch("time.sleep")
+
+    config.image_provider = "huggingface"
+    config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = generate_image("astronaut riding a horse", 512)
+
+    assert result == "Error creating image."
+
+    # Verify retry was not called.
+    mock_sleep.assert_not_called()
+
+
+def test_huggingface_fail_request_bad_image(mocker):
+    config = Config()
+    config.huggingface_api_token = "1"
+
+    # Mock requests.post
+    mock_post = mocker.patch("requests.post")
+    mock_post.return_value.status_code = 200
+
+    config.image_provider = "huggingface"
+    config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    result = generate_image("astronaut riding a horse", 512)
+
+    assert result == "Error creating image."
+
+
+def test_huggingface_fail_missing_api_token(mocker):
+    config = Config()
+    config.image_provider = "huggingface"
+    config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+
+    # Mock requests.post to raise ValueError
+    mock_post = mocker.patch("requests.post", side_effect=ValueError)
+
+    # Verify request raises an error.
+    with pytest.raises(ValueError):
+        generate_image("astronaut riding a horse", 512)

From 627aeb20a2d138fea29aa1f157d72341708c5610 Mon Sep 17 00:00:00 2001
From: amokduke <amokduke@users.noreply.github.com>
Date: Tue, 16 May 2023 23:14:24 +0800
Subject: [PATCH 015/112] Adds check for Python 3.10 and print error message if
 required version not detected. (#3598)

* Updated run script to check for Python 3.10 and above, and provide informative error messages for unsupported versions.

* Updated run script to check for Python 3.10 and above, and provide informative error messages for unsupported versions.

---------

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
---
 run.sh | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/run.sh b/run.sh
index b4155d88..62463555 100755
--- a/run.sh
+++ b/run.sh
@@ -15,11 +15,15 @@ function find_python_command() {
 
 PYTHON_CMD=$(find_python_command)
 
-$PYTHON_CMD scripts/check_requirements.py requirements.txt
-if [ $? -eq 1 ]
-then
-    echo Installing missing packages...
-    $PYTHON_CMD -m pip install -r requirements.txt
-fi
-$PYTHON_CMD -m autogpt $@
-read -p "Press any key to continue..."
\ No newline at end of file
+if $PYTHON_CMD -c "import sys; sys.exit(sys.version_info < (3, 10))"; then
+    $PYTHON_CMD scripts/check_requirements.py requirements.txt
+    if [ $? -eq 1 ]
+    then
+        echo Installing missing packages...
+        $PYTHON_CMD -m pip install -r requirements.txt
+    fi
+    $PYTHON_CMD -m autogpt $@
+    read -p "Press any key to continue..."
+else
+    echo "Python 3.10 or higher is required to run Auto GPT."
+fi
\ No newline at end of file

From 52874cc44222efbd54d4d914b823e9ebf63dea77 Mon Sep 17 00:00:00 2001
From: Richard Beales <rich@richbeales.net>
Date: Wed, 17 May 2023 03:38:36 +0100
Subject: [PATCH 016/112] Update README.md - make stable branch less shouty
 (#3702)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index eaa06aa2..ce3dc8e7 100644
--- a/README.md
+++ b/README.md
@@ -9,10 +9,10 @@
 
 <hr/>
 
-### 🔴 🔴 🔴  Urgent: USE `stable` not `master`  🔴 🔴 🔴
+### 🔴 USE `stable` not `master` 🔴
 
 **Download the latest `stable` release from here: https://github.com/Significant-Gravitas/Auto-GPT/releases/latest.**
-The `master` branch may often be in a **broken** state.
+The `master` branch is under heavy development and may often be in a **broken** state.
 
 <hr/>
 

From 55af3e19b414d10762072c2f46107137791faa79 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 16 May 2023 19:49:12 -0700
Subject: [PATCH 017/112] CI Pipeline: create cassettes in fork (#4257)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 .github/workflows/add-cassettes.yml | 49 -----------------------------
 .github/workflows/ci.yml            | 38 +++++++++++++++++++---
 2 files changed, 33 insertions(+), 54 deletions(-)
 delete mode 100644 .github/workflows/add-cassettes.yml

diff --git a/.github/workflows/add-cassettes.yml b/.github/workflows/add-cassettes.yml
deleted file mode 100644
index 9bf5b1b8..00000000
--- a/.github/workflows/add-cassettes.yml
+++ /dev/null
@@ -1,49 +0,0 @@
-name: Merge and Commit Cassettes
-
-on:
-  pull_request_target:
-    types:
-      - closed
-
-jobs:
-  update-cassettes:
-    if: github.event.pull_request.merged == true
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0  # This is necessary to fetch all branches and tags
-
-      - name: Fetch all branches
-        run: git fetch --all
-
-      - name: Reset branch
-        run: |
-          git checkout ${{ github.event.pull_request.base.ref }}
-          git reset --hard origin/cassette-diff-${{ github.event.pull_request.head.sha }}
-
-      - name: Create PR
-        id: create_pr
-        uses: peter-evans/create-pull-request@v5
-        with:
-          commit-message: Update cassettes
-          signoff: false
-          branch: cassette-diff-${{ github.event.pull_request.head.sha }}
-          delete-branch: false
-          title: "Update cassettes"
-          body: "This PR updates the cassettes."
-          draft: false
-
-      - name: Check PR
-        run: |
-          echo "Pull Request Number - ${{ steps.create_pr.outputs.pull-request-number }}"
-          echo "Pull Request URL - ${{ steps.create_pr.outputs.pull-request-url }}"
-
-      - name: Comment PR URL in the current PR
-        uses: thollander/actions-comment-pull-request@v2
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          message: |
-            New pull request created for cassettes: [HERE](${{ steps.create_pr.outputs.pull-request-url }}). Please merge it asap.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index b36b45e8..cb20cfe6 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -94,14 +94,42 @@ jobs:
         uses: codecov/codecov-action@v3
 
       - name: Stage new files and commit
+        id: stage_files
         run: |
-          COMMIT_SHA=$(git rev-parse HEAD) # take the sha before committing the cassette
           git add tests
           git diff --cached --quiet && echo "No changes to commit" && exit 0
           git config user.email "github-actions@github.com"
           git config user.name "GitHub Actions"
           git commit -m "Add new cassettes"
-          
-          git checkout -b cassette-diff-${COMMIT_SHA}
-          git remote add target https://${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.event.pull_request.base.repo.full_name }}
-          git push -f target cassette-diff-${COMMIT_SHA}
+          TIMESTAMP_COMMIT=$(date +%Y%m%d%H%M%S) # generate a timestamp
+          echo "TIMESTAMP_COMMIT=TIMESTAMP_COMMIT" >> $GITHUB_ENV
+      
+
+      - name: Create PR
+        id: create_pr
+        if:  ${{ env.TIMESTAMP_COMMIT != null }}
+        uses: peter-evans/create-pull-request@v5
+        with:
+          commit-message: Update cassettes
+          branch: cassette-diff-PR-${{ github.event.pull_request.number }}-${{ env.TIMESTAMP_COMMIT }}
+          title: "Update cassette-diff-PR${{ github.event.pull_request.number }}-${{ env.TIMESTAMP_COMMIT }}"
+          body: "This PR updates the cassettes. Please merge it."
+
+
+      - name: Check PR
+        if:  ${{ env.TIMESTAMP_COMMIT != null }}
+        run: |
+          echo "Pull Request Number - ${{ steps.create_pr.outputs.pull-request-number }}"
+          echo "Pull Request URL - ${{ steps.create_pr.outputs.pull-request-url }}"
+
+      - name: Comment PR URL in the current PR
+        if:  ${{ env.TIMESTAMP_COMMIT != null }}
+        uses: thollander/actions-comment-pull-request@v2
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          message: |
+            Please click [HERE](${{ steps.create_pr.outputs.pull-request-url }}) and merge this PR to update the cassettes.
+
+      - name: Fail if new PR created
+        if:  ${{ env.TIMESTAMP_COMMIT != null }}
+        run: exit 1

From 1c96a5acf7bffb279ceac3e8fd47931c3d9b7276 Mon Sep 17 00:00:00 2001
From: Boostrix <119627414+Boostrix@users.noreply.github.com>
Date: Wed, 17 May 2023 05:13:14 +0200
Subject: [PATCH 018/112] encourage people to use a separate user account w/o
 VM/docker (#3961)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
---
 docs/index.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docs/index.md b/docs/index.md
index fb63ea14..33e1c780 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -2,4 +2,6 @@
 
 Welcome to Auto-GPT.  Please follow the [Installation](/setup/) guide to get started.
 
-It is recommended to use a virtual machine for tasks that require high security measures to prevent any potential harm to the main computer's system and data.
+NOTE: It is recommended to use a virtual machine/container (docker) for tasks that require high security measures to prevent any potential harm to the main computer's system and data. If you are considering to use Auto-GPT outside a virtualized/containerized environment, you are *strongly* advised to use a separate user account just for running Auto-GPT. This is even more important if you are going to allow Auto-GPT to write/execute scripts and run shell commands!
+
+It is for these reasons that executing python scripts is explicitly disabled when running outside a container environment.

From 2cd835e5a4e0a95b166bfa032e173e554003fcd2 Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Wed, 17 May 2023 06:20:02 +0300
Subject: [PATCH 019/112] Added custom_search_engine_id as mandatory for
 official google search (#4228)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/commands/google_search.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/autogpt/commands/google_search.py b/autogpt/commands/google_search.py
index 1fc974cd..02909448 100644
--- a/autogpt/commands/google_search.py
+++ b/autogpt/commands/google_search.py
@@ -41,8 +41,8 @@ def google_search(query: str, num_results: int = 8) -> str:
     "google",
     "Google Search",
     '"query": "<query>"',
-    bool(CFG.google_api_key),
-    "Configure google_api_key.",
+    bool(CFG.google_api_key) and bool(CFG.custom_search_engine_id),
+    "Configure google_api_key and custom_search_engine_id.",
 )
 def google_official_search(query: str, num_results: int = 8) -> str | list[str]:
     """Return the results of a Google search using the official Google API

From 7c71b43d4214e4455c992709e7f976fc30fee8a7 Mon Sep 17 00:00:00 2001
From: Boostrix <119627414+Boostrix@users.noreply.github.com>
Date: Wed, 17 May 2023 05:30:38 +0200
Subject: [PATCH 020/112] mention docker rebuild is necessary if changing
 requirements.txt (#4136)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 docs/setup.md | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/docs/setup.md b/docs/setup.md
index 4ef9ec02..97c5bac8 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -101,7 +101,7 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
 ### Set up without Git/Docker
 
 !!! warning
-    We recommend to use Git or Docker, to make updating easier.
+    We recommend to use Git or Docker, to make updating easier. Also note that some features such as Python execution will only work inside docker for security reasons.
 
 1. Download `Source code (zip)` from the [latest stable release](https://github.com/Significant-Gravitas/Auto-GPT/releases/latest)
 2. Extract the zip-file into a folder
@@ -169,7 +169,7 @@ If you need to upgrade Docker Compose to a newer version, you can follow the ins
 
 Once you have a recent version of docker-compose, run the commands below in your Auto-GPT folder.
 
-1. Build the image. If you have pulled the image from Docker Hub, skip this step.
+1. Build the image. If you have pulled the image from Docker Hub, skip this step (NOTE: You *will* need to do this if you are modifying requirements.txt to add/remove depedencies like Python libs/frameworks) 
 
         :::shell
         docker-compose build auto-gpt
@@ -211,6 +211,9 @@ docker run -it --env-file=.env -v $PWD:/app --rm auto-gpt --gpt3only --continuou
 
 ### Run without Docker
 
+!!! warning
+    Due to security reasons, certain features (like Python execution) will by default be disabled when running without docker. So, even if you want to run the program outside a docker container, you currently still need docker to actually run scripts.
+
 Simply run the startup script in your terminal. This will install any necessary Python
 packages and launch Auto-GPT.
 

From feae20d8faa3396f72aab02a5eafbdbbaab8305c Mon Sep 17 00:00:00 2001
From: Richard Beales <rich@richbeales.net>
Date: Wed, 17 May 2023 05:24:57 +0100
Subject: [PATCH 021/112] Update PULL_REQUEST_TEMPLATE.md to include linting
 (#3625)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 .github/PULL_REQUEST_TEMPLATE.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 273275b3..90b985c1 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -35,7 +35,8 @@ By following these guidelines, your PRs are more likely to be merged quickly aft
 - [ ] I have thoroughly tested my changes with multiple different prompts.
 - [ ] I have considered potential risks and mitigations for my changes.
 - [ ] I have documented my changes clearly and comprehensively.
-- [ ] I have not snuck in any "extra" small tweaks changes <!-- Submit these as separate Pull Requests, they are the easiest to merge! -->
+- [ ] I have not snuck in any "extra" small tweaks changes. <!-- Submit these as separate Pull Requests, they are the easiest to merge! -->
+- [ ] I have run `black .` and `isort .` against my code to ensure it passes our linter.
 
 <!-- If you haven't added tests, please explain why. If you have, check the appropriate box. If you've ensured your PR is atomic and well-documented, check the corresponding boxes. -->
 

From 7508e9941f6f743d4e3dbcf8e7028db77911e1cb Mon Sep 17 00:00:00 2001
From: Andres Caicedo <73312784+AndresCdo@users.noreply.github.com>
Date: Wed, 17 May 2023 13:38:42 +0200
Subject: [PATCH 022/112] Implement Logging of Self-Feedback in logs/Debug
 Folder (#3868)

* Adds SELF_FEEDBACK_FILE_NAME

* Add self-feedback logging to logs/Debug folder

* Reformatting

* Uses JSON file

* Update agent.py

Changes position

* Update agent.py

* Adds PROMPT_FEEDBACK_FILE_NAME

* Update agent.py

* Update agent.py

* Reformatting

* Update agent.py

* Update agent.py

* Changes file names

* Update agent.py

* Reformatting

* Update agent.py

* Changes conts names

* Update agent_manager.py

* Update agent_manager.py

* HARD reset

* Update test_get_self_feedback.py

* Update test_get_self_feedback.py

---------

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
---
 autogpt/agent/agent.py               | 25 ++++++++++++++++++++++---
 autogpt/log_cycle/log_cycle.py       |  2 ++
 tests/unit/test_get_self_feedback.py | 12 ++++++++++++
 3 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index 68888401..e68bf989 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -13,6 +13,8 @@ from autogpt.llm.token_counter import count_string_tokens
 from autogpt.log_cycle.log_cycle import (
     FULL_MESSAGE_HISTORY_FILE_NAME,
     NEXT_ACTION_FILE_NAME,
+    PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
+    SUPERVISOR_FEEDBACK_FILE_NAME,
     USER_INPUT_FILE_NAME,
     LogCycleHandler,
 )
@@ -340,7 +342,24 @@ class Agent:
         plan = thoughts.get("plan", "")
         thought = thoughts.get("thoughts", "")
         feedback_thoughts = thought + reasoning + plan
-        return create_chat_completion(
-            [{"role": "user", "content": feedback_prompt + feedback_thoughts}],
-            llm_model,
+
+        messages = {"role": "user", "content": feedback_prompt + feedback_thoughts}
+
+        self.log_cycle_handler.log_cycle(
+            self.config.ai_name,
+            self.created_at,
+            self.cycle_count,
+            messages,
+            PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
         )
+
+        feedback = create_chat_completion(messages)
+
+        self.log_cycle_handler.log_cycle(
+            self.config.ai_name,
+            self.created_at,
+            self.cycle_count,
+            feedback,
+            SUPERVISOR_FEEDBACK_FILE_NAME,
+        )
+        return feedback
diff --git a/autogpt/log_cycle/log_cycle.py b/autogpt/log_cycle/log_cycle.py
index cff3ac1a..8daed25c 100644
--- a/autogpt/log_cycle/log_cycle.py
+++ b/autogpt/log_cycle/log_cycle.py
@@ -10,6 +10,8 @@ CURRENT_CONTEXT_FILE_NAME = "current_context.json"
 NEXT_ACTION_FILE_NAME = "next_action.json"
 PROMPT_SUMMARY_FILE_NAME = "prompt_summary.json"
 SUMMARY_FILE_NAME = "summary.txt"
+SUPERVISOR_FEEDBACK_FILE_NAME = "supervisor_feedback.txt"
+PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME = "prompt_supervisor_feedback.json"
 USER_INPUT_FILE_NAME = "user_input.txt"
 
 
diff --git a/tests/unit/test_get_self_feedback.py b/tests/unit/test_get_self_feedback.py
index e1e9bd4a..5e59757e 100644
--- a/tests/unit/test_get_self_feedback.py
+++ b/tests/unit/test_get_self_feedback.py
@@ -1,6 +1,9 @@
+from datetime import datetime
+
 from autogpt.agent.agent import Agent
 from autogpt.config import AIConfig
 from autogpt.llm import create_chat_completion
+from autogpt.log_cycle.log_cycle import LogCycleHandler
 
 
 def test_get_self_feedback(mocker):
@@ -31,6 +34,15 @@ def test_get_self_feedback(mocker):
     # Mock the config attribute of the Agent instance
     agent_mock.config = AIConfig()
 
+    # Mock the log_cycle_handler attribute of the Agent instance
+    agent_mock.log_cycle_handler = LogCycleHandler()
+
+    # Mock the create_nested_directory method of the LogCycleHandler instance
+    agent_mock.created_at = datetime.now().strftime("%Y%m%d_%H%M%S")
+
+    # Mock the cycle_count attribute of the Agent instance
+    agent_mock.cycle_count = 0
+
     # Call the get_self_feedback method
     feedback = Agent.get_self_feedback(
         agent_mock,

From 1c399e67f4ff39bce0e8d28b59a24af734c03e5c Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Wed, 17 May 2023 09:52:52 -0700
Subject: [PATCH 023/112] Add $ to timestamp in ci.yml and improve diff (#4266)

---
 .github/workflows/ci.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index cb20cfe6..492336df 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -97,12 +97,12 @@ jobs:
         id: stage_files
         run: |
           git add tests
-          git diff --cached --quiet && echo "No changes to commit" && exit 0
+          git diff --cached --quiet tests && echo "No changes to commit" && exit 0
           git config user.email "github-actions@github.com"
           git config user.name "GitHub Actions"
           git commit -m "Add new cassettes"
           TIMESTAMP_COMMIT=$(date +%Y%m%d%H%M%S) # generate a timestamp
-          echo "TIMESTAMP_COMMIT=TIMESTAMP_COMMIT" >> $GITHUB_ENV
+          echo "TIMESTAMP_COMMIT=$TIMESTAMP_COMMIT" >> $GITHUB_ENV
       
 
       - name: Create PR

From 42a5a0ce1353a74423ed55bbac764b7d80995679 Mon Sep 17 00:00:00 2001
From: DGdev91 <DGdev91@users.noreply.github.com>
Date: Wed, 17 May 2023 19:12:10 +0200
Subject: [PATCH 024/112] Make prompt parameters configurable (#3375)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 .env.template                   |  3 ++
 autogpt/cli.py                  |  7 +++++
 autogpt/config/config.py        |  3 ++
 autogpt/config/prompt_config.py | 53 +++++++++++++++++++++++++++++++++
 autogpt/configurator.py         | 15 ++++++++++
 autogpt/main.py                 |  2 ++
 autogpt/prompts/prompt.py       | 46 +++++++---------------------
 docs/usage.md                   | 11 ++++---
 prompt_settings.yaml            | 19 ++++++++++++
 tests/test_prompt_config.py     | 48 +++++++++++++++++++++++++++++
 10 files changed, 168 insertions(+), 39 deletions(-)
 create mode 100644 autogpt/config/prompt_config.py
 create mode 100644 prompt_settings.yaml
 create mode 100644 tests/test_prompt_config.py

diff --git a/.env.template b/.env.template
index fe217a43..05f2c1ab 100644
--- a/.env.template
+++ b/.env.template
@@ -13,6 +13,9 @@
 ## AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml)
 # AI_SETTINGS_FILE=ai_settings.yaml
 
+## PROMPT_SETTINGS_FILE - Specifies which Prompt Settings file to use (defaults to prompt_settings.yaml)
+# PROMPT_SETTINGS_FILE=prompt_settings.yaml
+
 ## AUTHORISE COMMAND KEY - Key to authorise commands
 # AUTHORISE_COMMAND_KEY=y
 ## EXIT_KEY - Key to exit AUTO-GPT
diff --git a/autogpt/cli.py b/autogpt/cli.py
index d9294516..3b45b501 100644
--- a/autogpt/cli.py
+++ b/autogpt/cli.py
@@ -15,6 +15,11 @@ import click
     "-C",
     help="Specifies which ai_settings.yaml file to use, will also automatically skip the re-prompt.",
 )
+@click.option(
+    "--prompt-settings",
+    "-P",
+    help="Specifies which prompt_settings.yaml file to use.",
+)
 @click.option(
     "-l",
     "--continuous-limit",
@@ -66,6 +71,7 @@ def main(
     continuous: bool,
     continuous_limit: int,
     ai_settings: str,
+    prompt_settings: str,
     skip_reprompt: bool,
     speak: bool,
     debug: bool,
@@ -91,6 +97,7 @@ def main(
             continuous,
             continuous_limit,
             ai_settings,
+            prompt_settings,
             skip_reprompt,
             speak,
             debug,
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index 7ee0df8b..daf12397 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -38,6 +38,9 @@ class Config(metaclass=Singleton):
             self.disabled_command_categories = []
 
         self.ai_settings_file = os.getenv("AI_SETTINGS_FILE", "ai_settings.yaml")
+        self.prompt_settings_file = os.getenv(
+            "PROMPT_SETTINGS_FILE", "prompt_settings.yaml"
+        )
         self.fast_llm_model = os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo")
         self.smart_llm_model = os.getenv("SMART_LLM_MODEL", "gpt-4")
         self.fast_token_limit = int(os.getenv("FAST_TOKEN_LIMIT", 4000))
diff --git a/autogpt/config/prompt_config.py b/autogpt/config/prompt_config.py
new file mode 100644
index 00000000..3f562c95
--- /dev/null
+++ b/autogpt/config/prompt_config.py
@@ -0,0 +1,53 @@
+# sourcery skip: do-not-use-staticmethod
+"""
+A module that contains the PromptConfig class object that contains the configuration
+"""
+import yaml
+from colorama import Fore
+
+from autogpt import utils
+from autogpt.config.config import Config
+from autogpt.logs import logger
+
+CFG = Config()
+
+
+class PromptConfig:
+    """
+    A class object that contains the configuration information for the prompt, which will be used by the prompt generator
+
+    Attributes:
+        constraints (list): Constraints list for the prompt generator.
+        resources (list): Resources list for the prompt generator.
+        performance_evaluations (list): Performance evaluation list for the prompt generator.
+    """
+
+    def __init__(
+        self,
+        config_file: str = CFG.prompt_settings_file,
+    ) -> None:
+        """
+        Initialize a class instance with parameters (constraints, resources, performance_evaluations) loaded from
+          yaml file if yaml file exists,
+        else raises error.
+
+        Parameters:
+            constraints (list): Constraints list for the prompt generator.
+            resources (list): Resources list for the prompt generator.
+            performance_evaluations (list): Performance evaluation list for the prompt generator.
+        Returns:
+            None
+        """
+        # Validate file
+        (validated, message) = utils.validate_yaml_file(config_file)
+        if not validated:
+            logger.typewriter_log("FAILED FILE VALIDATION", Fore.RED, message)
+            logger.double_check()
+            exit(1)
+
+        with open(config_file, encoding="utf-8") as file:
+            config_params = yaml.load(file, Loader=yaml.FullLoader)
+
+        self.constraints = config_params.get("constraints", [])
+        self.resources = config_params.get("resources", [])
+        self.performance_evaluations = config_params.get("performance_evaluations", [])
diff --git a/autogpt/configurator.py b/autogpt/configurator.py
index 84000e57..0fddd1fa 100644
--- a/autogpt/configurator.py
+++ b/autogpt/configurator.py
@@ -14,6 +14,7 @@ def create_config(
     continuous: bool,
     continuous_limit: int,
     ai_settings_file: str,
+    prompt_settings_file: str,
     skip_reprompt: bool,
     speak: bool,
     debug: bool,
@@ -30,6 +31,7 @@ def create_config(
         continuous (bool): Whether to run in continuous mode
         continuous_limit (int): The number of times to run in continuous mode
         ai_settings_file (str): The path to the ai_settings.yaml file
+        prompt_settings_file (str): The path to the prompt_settings.yaml file
         skip_reprompt (bool): Whether to skip the re-prompting messages at the beginning of the script
         speak (bool): Whether to enable speak mode
         debug (bool): Whether to enable debug mode
@@ -112,6 +114,19 @@ def create_config(
         CFG.ai_settings_file = file
         CFG.skip_reprompt = True
 
+    if prompt_settings_file:
+        file = prompt_settings_file
+
+        # Validate file
+        (validated, message) = utils.validate_yaml_file(file)
+        if not validated:
+            logger.typewriter_log("FAILED FILE VALIDATION", Fore.RED, message)
+            logger.double_check()
+            exit(1)
+
+        logger.typewriter_log("Using Prompt Settings File:", Fore.GREEN, file)
+        CFG.prompt_settings_file = file
+
     if browser_name:
         CFG.selenium_web_browser = browser_name
 
diff --git a/autogpt/main.py b/autogpt/main.py
index d07a0993..79249609 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -27,6 +27,7 @@ def run_auto_gpt(
     continuous: bool,
     continuous_limit: int,
     ai_settings: str,
+    prompt_settings: str,
     skip_reprompt: bool,
     speak: bool,
     debug: bool,
@@ -50,6 +51,7 @@ def run_auto_gpt(
         continuous,
         continuous_limit,
         ai_settings,
+        prompt_settings,
         skip_reprompt,
         speak,
         debug,
diff --git a/autogpt/prompts/prompt.py b/autogpt/prompts/prompt.py
index c1d8a2b5..e69fc4b7 100644
--- a/autogpt/prompts/prompt.py
+++ b/autogpt/prompts/prompt.py
@@ -2,6 +2,7 @@ from colorama import Fore
 
 from autogpt.config.ai_config import AIConfig
 from autogpt.config.config import Config
+from autogpt.config.prompt_config import PromptConfig
 from autogpt.llm import ApiManager
 from autogpt.logs import logger
 from autogpt.prompts.generator import PromptGenerator
@@ -27,46 +28,21 @@ def build_default_prompt_generator() -> PromptGenerator:
     # Initialize the PromptGenerator object
     prompt_generator = PromptGenerator()
 
+    # Initialize the PromptConfig object and load the file set in the main config (default: prompts_settings.yaml)
+    prompt_config = PromptConfig(CFG.prompt_settings_file)
+
     # Add constraints to the PromptGenerator object
-    prompt_generator.add_constraint(
-        "~4000 word limit for short term memory. Your short term memory is short, so"
-        " immediately save important information to files."
-    )
-    prompt_generator.add_constraint(
-        "If you are unsure how you previously did something or want to recall past"
-        " events, thinking about similar events will help you remember."
-    )
-    prompt_generator.add_constraint("No user assistance")
-    prompt_generator.add_constraint(
-        "Exclusively use the commands listed below e.g. command_name"
-    )
+    for constraint in prompt_config.constraints:
+        prompt_generator.add_constraint(constraint)
 
     # Add resources to the PromptGenerator object
-    prompt_generator.add_resource(
-        "Internet access for searches and information gathering."
-    )
-    prompt_generator.add_resource("Long Term memory management.")
-    prompt_generator.add_resource(
-        "GPT-3.5 powered Agents for delegation of simple tasks."
-    )
-    prompt_generator.add_resource("File output.")
+    for resource in prompt_config.resources:
+        prompt_generator.add_resource(resource)
 
     # Add performance evaluations to the PromptGenerator object
-    prompt_generator.add_performance_evaluation(
-        "Continuously review and analyze your actions to ensure you are performing to"
-        " the best of your abilities."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Constructively self-criticize your big-picture behavior constantly."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Reflect on past decisions and strategies to refine your approach."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Every command has a cost, so be smart and efficient. Aim to complete tasks in"
-        " the least number of steps."
-    )
-    prompt_generator.add_performance_evaluation("Write all code to a file.")
+    for performance_evaluation in prompt_config.performance_evaluations:
+        prompt_generator.add_performance_evaluation(performance_evaluation)
+
     return prompt_generator
 
 
diff --git a/docs/usage.md b/docs/usage.md
index 4a0c8870..011f5f8a 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -23,10 +23,13 @@ Running with `--help` lists all the possible command line arguments you can pass
 Here are some common arguments you can use when running Auto-GPT:
 
 * Run Auto-GPT with a different AI Settings file
-
-        :::shell
-        ./run.sh --ai-settings <filename>
-
+    ``` shell
+    ./run.sh --ai-settings <filename>
+    ```
+* Run Auto-GPT with a different Prompt Settings file
+    ``` shell
+    ./run.sh --prompt-settings <filename>
+    ```
 * Specify a memory backend
 
         :::shell
diff --git a/prompt_settings.yaml b/prompt_settings.yaml
new file mode 100644
index 00000000..b8e7c0d2
--- /dev/null
+++ b/prompt_settings.yaml
@@ -0,0 +1,19 @@
+constraints: [
+  '~4000 word limit for short term memory. Your short term memory is short, so immediately save important information to files.',
+  'If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.',
+  'No user assistance',
+  'Exclusively use the commands listed below e.g. command_name'
+]
+resources: [
+  'Internet access for searches and information gathering.',
+  'Long Term memory management.',
+  'GPT-3.5 powered Agents for delegation of simple tasks.',
+  'File output.'
+]
+performance_evaluations: [
+  'Continuously review and analyze your actions to ensure you are performing to the best of your abilities.',
+  'Constructively self-criticize your big-picture behavior constantly.',
+  'Reflect on past decisions and strategies to refine your approach.',
+  'Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.',
+  'Write all code to a file.'
+]
diff --git a/tests/test_prompt_config.py b/tests/test_prompt_config.py
new file mode 100644
index 00000000..eacb0cf4
--- /dev/null
+++ b/tests/test_prompt_config.py
@@ -0,0 +1,48 @@
+from autogpt.config.prompt_config import PromptConfig
+
+"""
+Test cases for the PromptConfig class, which handles loads the Prompts configuration
+settings from a YAML file.
+"""
+
+
+def test_prompt_config_loading(tmp_path):
+    """Test if the prompt configuration loads correctly"""
+
+    yaml_content = """
+constraints:
+- A test constraint
+- Another test constraint
+- A third test constraint
+resources:
+- A test resource
+- Another test resource
+- A third test resource
+performance_evaluations:
+- A test performance evaluation
+- Another test performance evaluation
+- A third test performance evaluation
+"""
+    config_file = tmp_path / "test_prompt_settings.yaml"
+    config_file.write_text(yaml_content)
+
+    prompt_config = PromptConfig(config_file)
+
+    assert len(prompt_config.constraints) == 3
+    assert prompt_config.constraints[0] == "A test constraint"
+    assert prompt_config.constraints[1] == "Another test constraint"
+    assert prompt_config.constraints[2] == "A third test constraint"
+    assert len(prompt_config.resources) == 3
+    assert prompt_config.resources[0] == "A test resource"
+    assert prompt_config.resources[1] == "Another test resource"
+    assert prompt_config.resources[2] == "A third test resource"
+    assert len(prompt_config.performance_evaluations) == 3
+    assert prompt_config.performance_evaluations[0] == "A test performance evaluation"
+    assert (
+        prompt_config.performance_evaluations[1]
+        == "Another test performance evaluation"
+    )
+    assert (
+        prompt_config.performance_evaluations[2]
+        == "A third test performance evaluation"
+    )

From 19767ca4a4d19fc915c8bdd88d9409263c1970cd Mon Sep 17 00:00:00 2001
From: Zorinik <zorinik@gmail.com>
Date: Wed, 17 May 2023 21:17:33 +0200
Subject: [PATCH 025/112] Logs output to console if we're not on speak mode
 (#3715)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/logs.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/autogpt/logs.py b/autogpt/logs.py
index 120db39d..f14267fc 100644
--- a/autogpt/logs.py
+++ b/autogpt/logs.py
@@ -287,5 +287,8 @@ def print_assistant_thoughts(
             logger.typewriter_log("- ", Fore.GREEN, line.strip())
     logger.typewriter_log("CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}")
     # Speak the assistant's thoughts
-    if speak_mode and assistant_thoughts_speak:
-        say_text(assistant_thoughts_speak)
+    if assistant_thoughts_speak:
+        if speak_mode:
+            say_text(assistant_thoughts_speak)
+        else:
+            logger.typewriter_log("SPEAK:", Fore.YELLOW, f"{assistant_thoughts_speak}")

From 0b39b92bdeaa2f0f1ceac046030ad54a7d2dc766 Mon Sep 17 00:00:00 2001
From: Toran Bruce Richards <toran.richards@gmail.com>
Date: Thu, 18 May 2023 15:41:17 +1200
Subject: [PATCH 026/112] Update README.md

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index ce3dc8e7..fd8b8c0b 100644
--- a/README.md
+++ b/README.md
@@ -44,6 +44,7 @@ Your support is greatly appreciated. Development of this free, open-source proje
 <a href="https://roost.ai">
 <img src="https://user-images.githubusercontent.com/22963551/234180283-b58cb03c-c95a-4196-93c1-28b52a388e9d.png" height="40px" alt="Roost.AI" />
 </a>
+  
 <a href="https://nuclei.ai/">
 <picture height="40px">
   <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234153428-24a6f31d-c0c6-4c9b-b3f4-9110148f67b4.png">
@@ -72,6 +73,10 @@ Your support is greatly appreciated. Development of this free, open-source proje
 </picture>
 </a>
 
+<a href="https://chatgpv.com/?ref=spni76459e4fa3f30a">
+<img src="https://github.com/Significant-Gravitas/Auto-GPT/assets/22963551/623a2dd6-eaeb-4941-b40f-c5a29ca6bebc" height="40px" alt="ChatGPV" />
+</a>
+  
 </div>
 </br>
 

From dc41db9522f1e61faa7b5a6910af1b98ca3a6c5e Mon Sep 17 00:00:00 2001
From: Toran Bruce Richards <toran.richards@gmail.com>
Date: Thu, 18 May 2023 15:45:58 +1200
Subject: [PATCH 027/112] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index fd8b8c0b..0d2681d9 100644
--- a/README.md
+++ b/README.md
@@ -74,7 +74,7 @@ Your support is greatly appreciated. Development of this free, open-source proje
 </a>
 
 <a href="https://chatgpv.com/?ref=spni76459e4fa3f30a">
-<img src="https://github.com/Significant-Gravitas/Auto-GPT/assets/22963551/623a2dd6-eaeb-4941-b40f-c5a29ca6bebc" height="40px" alt="ChatGPV" />
+<img src="https://github-production-user-asset-6210df.s3.amazonaws.com/22963551/239132565-623a2dd6-eaeb-4941-b40f-c5a29ca6bebc.png" height="40px" alt="ChatGPV" />
 </a>
   
 </div>

From c4b32e067c7af48249fee9c4251cc54b6964d223 Mon Sep 17 00:00:00 2001
From: Media <12145726+rihp@users.noreply.github.com>
Date: Thu, 18 May 2023 07:58:08 +0200
Subject: [PATCH 028/112] switching from unittest to pytest in test_json_parser
  (#3481)

---
 tests/unit/_test_json_parser.py | 146 ++++++++++++++++----------------
 1 file changed, 72 insertions(+), 74 deletions(-)

diff --git a/tests/unit/_test_json_parser.py b/tests/unit/_test_json_parser.py
index 4ef46710..82621b1e 100644
--- a/tests/unit/_test_json_parser.py
+++ b/tests/unit/_test_json_parser.py
@@ -1,44 +1,49 @@
-import unittest
+import pytest
 
 from autogpt.json_utils.json_fix_llm import fix_and_parse_json
 
 
-class TestParseJson(unittest.TestCase):
-    def test_valid_json(self):
-        """Test that a valid JSON string is parsed correctly."""
-        json_str = '{"name": "John", "age": 30, "city": "New York"}'
-        obj = fix_and_parse_json(json_str)
-        self.assertEqual(obj, {"name": "John", "age": 30, "city": "New York"})
+def test_valid_json():
+    """Test that a valid JSON string is parsed correctly."""
+    json_str = '{"name": "John", "age": 30, "city": "New York"}'
+    obj = fix_and_parse_json(json_str)
+    assert obj == {"name": "John", "age": 30, "city": "New York"}
 
-    def test_invalid_json_minor(self):
-        """Test that an invalid JSON string can be fixed with gpt."""
-        json_str = '{"name": "John", "age": 30, "city": "New York",}'
-        self.assertEqual(
-            fix_and_parse_json(json_str, try_to_fix_with_gpt=False),
-            {"name": "John", "age": 30, "city": "New York"},
-        )
 
-    def test_invalid_json_major_with_gpt(self):
-        """Test that an invalid JSON string raises an error when try_to_fix_with_gpt is False."""
-        json_str = 'BEGIN: "name": "John" - "age": 30 - "city": "New York" :END'
-        self.assertEqual(
-            fix_and_parse_json(json_str, try_to_fix_with_gpt=True),
-            {"name": "John", "age": 30, "city": "New York"},
-        )
+def test_invalid_json_minor():
+    """Test that an invalid JSON string can be fixed with gpt."""
+    json_str = '{"name": "John", "age": 30, "city": "New York",}'
+    assert fix_and_parse_json(json_str, try_to_fix_with_gpt=False) == {
+        "name": "John",
+        "age": 30,
+        "city": "New York",
+    }
 
-    def test_invalid_json_major_without_gpt(self):
-        """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
-        json_str = 'BEGIN: "name": "John" - "age": 30 - "city": "New York" :END'
-        # Assert that this raises an exception:
-        with self.assertRaises(Exception):
-            fix_and_parse_json(json_str, try_to_fix_with_gpt=False)
 
-    def test_invalid_json_leading_sentence_with_gpt(self):
-        """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
+def test_invalid_json_major_with_gpt():
+    """Test that an invalid JSON string raises an error when try_to_fix_with_gpt is False."""
+    json_str = 'BEGIN: "name": "John" - "age": 30 - "city": "New York" :END'
+    assert fix_and_parse_json(json_str, try_to_fix_with_gpt=True) == {
+        "name": "John",
+        "age": 30,
+        "city": "New York",
+    }
 
-        json_str = """I suggest we start by browsing the repository to find any issues that we can fix.
 
-{
+def test_invalid_json_major_without_gpt():
+    """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
+    json_str = 'BEGIN: "name": "John" - "age": 30 - "city": "New York" :END'
+    # Assert that this raises an exception:
+    with pytest.raises(Exception):
+        fix_and_parse_json(json_str, try_to_fix_with_gpt=False)
+
+
+def test_invalid_json_leading_sentence_with_gpt():
+    """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
+
+    json_str = """I suggest we start by browsing the repository to find any issues that we can fix.
+
+    {
     "command": {
         "name": "browse_website",
         "args":{
@@ -53,30 +58,29 @@ class TestParseJson(unittest.TestCase):
         "criticism": "I should be careful while browsing so as not to accidentally introduce any new bugs or issues.",
         "speak": "I will start browsing the repository to find any issues we can fix."
     }
-}"""
-        good_obj = {
-            "command": {
-                "name": "browse_website",
-                "args": {"url": "https://github.com/Torantulino/Auto-GPT"},
-            },
-            "thoughts": {
-                "text": "I suggest we start browsing the repository to find any issues that we can fix.",
-                "reasoning": "Browsing the repository will give us an idea of the current state of the codebase and identify any issues that we can address to improve the repo.",
-                "plan": "- Look through the repository to find any issues.\n- Investigate any issues to determine what needs to be fixed\n- Identify possible solutions to fix the issues\n- Open Pull Requests with fixes",
-                "criticism": "I should be careful while browsing so as not to accidentally introduce any new bugs or issues.",
-                "speak": "I will start browsing the repository to find any issues we can fix.",
-            },
-        }
-        # Assert that this raises an exception:
-        self.assertEqual(
-            fix_and_parse_json(json_str, try_to_fix_with_gpt=False), good_obj
-        )
+    }"""
+    good_obj = {
+        "command": {
+            "name": "browse_website",
+            "args": {"url": "https://github.com/Torantulino/Auto-GPT"},
+        },
+        "thoughts": {
+            "text": "I suggest we start browsing the repository to find any issues that we can fix.",
+            "reasoning": "Browsing the repository will give us an idea of the current state of the codebase and identify any issues that we can address to improve the repo.",
+            "plan": "- Look through the repository to find any issues.\n- Investigate any issues to determine what needs to be fixed\n- Identify possible solutions to fix the issues\n- Open Pull Requests with fixes",
+            "criticism": "I should be careful while browsing so as not to accidentally introduce any new bugs or issues.",
+            "speak": "I will start browsing the repository to find any issues we can fix.",
+        },
+    }
+    # Assert that this raises an exception:
+    assert fix_and_parse_json(json_str, try_to_fix_with_gpt=False) == good_obj
 
-    def test_invalid_json_leading_sentence_with_gpt(self):
-        """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
-        json_str = """I will first need to browse the repository (https://github.com/Torantulino/Auto-GPT) and identify any potential bugs that need fixing. I will use the "browse_website" command for this.
 
-{
+def test_invalid_json_leading_sentence_with_gpt(self):
+    """Test that a REALLY invalid JSON string raises an error when try_to_fix_with_gpt is False."""
+    json_str = """I will first need to browse the repository (https://github.com/Torantulino/Auto-GPT) and identify any potential bugs that need fixing. I will use the "browse_website" command for this.
+
+    {
     "command": {
         "name": "browse_website",
         "args":{
@@ -91,25 +95,19 @@ class TestParseJson(unittest.TestCase):
         "criticism": "I need to ensure I am thorough and pay attention to detail while browsing the repository.",
         "speak": "I am browsing the repository to identify potential bugs."
     }
-}"""
-        good_obj = {
-            "command": {
-                "name": "browse_website",
-                "args": {"url": "https://github.com/Torantulino/Auto-GPT"},
-            },
-            "thoughts": {
-                "text": "Browsing the repository to identify potential bugs",
-                "reasoning": "Before fixing bugs, I need to identify what needs fixing. I will use the 'browse_website' command to analyze the repository.",
-                "plan": "- Analyze the repository for potential bugs and areas of improvement",
-                "criticism": "I need to ensure I am thorough and pay attention to detail while browsing the repository.",
-                "speak": "I am browsing the repository to identify potential bugs.",
-            },
-        }
-        # Assert that this raises an exception:
-        self.assertEqual(
-            fix_and_parse_json(json_str, try_to_fix_with_gpt=False), good_obj
-        )
+    }"""
+    good_obj = {
+        "command": {
+            "name": "browse_website",
+            "args": {"url": "https://github.com/Torantulino/Auto-GPT"},
+        },
+        "thoughts": {
+            "text": "Browsing the repository to identify potential bugs",
+            "reasoning": "Before fixing bugs, I need to identify what needs fixing. I will use the 'browse_website' command to analyze the repository.",
+            "plan": "- Analyze the repository for potential bugs and areas of improvement",
+            "criticism": "I need to ensure I am thorough and pay attention to detail while browsing the repository.",
+            "speak": "I am browsing the repository to identify potential bugs.",
+        },
+    }
 
-
-if __name__ == "__main__":
-    unittest.main()
+    assert fix_and_parse_json(json_str, try_to_fix_with_gpt=False) == good_obj

From e2851dc73f3d148c97d54b3a9c710a854b0724b2 Mon Sep 17 00:00:00 2001
From: Alex Kissi Jr <116205891+AlexKissiJr@users.noreply.github.com>
Date: Wed, 17 May 2023 23:31:43 -0700
Subject: [PATCH 029/112] Incremented Version  BULLETIN.md (#4236)

---
 BULLETIN.md | 56 ++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 45 insertions(+), 11 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index 5190b448..f77a8fc3 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -2,23 +2,57 @@
 Check out *https://agpt.co*, the official news & updates site for Auto-GPT!
 The documentation also has a place here, at *https://docs.agpt.co*
 
-# 🚀 v0.3.0 Release 🚀
-Over a week and 275 pull requests have passed since v0.2.2, and we are happy to announce
-the release of v0.3.0! *From now on, we will be focusing on major improvements* rather
-than bugfixes, as we feel stability has reached a reasonable level. Most remaining
-issues relate to limitations in prompt generation and the memory system, which will be
-the focus of our efforts for the next release.
+# 🚀 v0.3.1 Release 🚀
+Over a week and 47 pull requests have passed since v0.3.0, and we are happy to announce
+the release of v0.3.1!
 
 Highlights and notable changes in this release:
 
-## Plugin support 🔌
-Auto-GPT now has support for plugins! With plugins, you can extend Auto-GPT's abilities,
-adding support for third-party services and more.
-See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and available plugins.
-
 ## Changes to Docker configuration 🐋
 The workdir has been changed from */home/appuser* to */app*.
 Be sure to update any volume mounts accordingly!
 
 # ⚠️ Command `send_tweet` is DEPRECATED, and will be removed in v0.4.0 ⚠️
 Twitter functionality (and more) is now covered by plugins, see [Plugin support 🔌]
+
+## Documentation
+- Docker-compose 1.29.0 is now required, as documented.
+- Path to the workspace directory in the setup guide has been corrected.
+- Memory setup links have been updated.
+
+## Logs
+- Log functionality has been improved for better understanding and easier summarization.
+- User input is now logged in the logs/Debug Folder.
+
+## Other 
+- Edge browser support has been added using EdgeChromiumDriverManager.
+- Users now have the ability to disable commands via the .env file.
+- Run scripts for both Windows (.bat) and Unix (.sh) have been updated.
+
+## BugFix
+- DuckDuckGo dependency has been updated, with a minimum version set to 2.9.5.
+- Package versions parsing has been enabled for forced upgrades.
+- Docker volume mounts have been fixed.
+- A fix was made to the plugin.post_planning call.
+- A selenium driver object reference bug in the browsing results was fixed.
+- JSON error in summary_memory.py has been handled.
+- Dockerfile has been updated to add missing scripts and plugins directories.
+
+## CI
+- The CI pipeline has been tightened up for improved performance.
+- pytest-xdist Plugin has been integrated for parallel and concurrent testing.
+- Tests have been conducted for a new CI pipeline.
+- A code owners policy has been added.
+- Test against Python 3.10 (not 3.10 + 3.11) to halve the number of tests that are executed.
+
+## Plugin support 🔌
+Auto-GPT now has support for plugins! With plugins, you can extend Auto-GPT's abilities,
+adding support for third-party services and more.
+See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and available plugins.
+Denylist handling for plugins is now available.
+
+*From now on, we will be focusing on major improvements* rather
+than bugfixes, as we feel stability has reached a reasonable level. Most remaining
+issues relate to limitations in prompt generation and the memory system, which will be
+the focus of our efforts for the next release.
+

From 5b4bcf1a04585bc0cc511e3a089c6325657bff08 Mon Sep 17 00:00:00 2001
From: "Luke K (pr-0f3t)" <2609441+lc0rp@users.noreply.github.com>
Date: Thu, 18 May 2023 17:22:16 -0400
Subject: [PATCH 030/112] Prevent test collection errors in devcontainer
 (#4180)

Co-authored-by: desojo <ethan.johnson1997@outlook.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 .devcontainer/devcontainer.json | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index 5d50e280..1be773cf 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -7,11 +7,12 @@
     "ghcr.io/devcontainers/features/common-utils:2": {
       "installZsh": "true",
       "username": "vscode",
-      "userUid": "6942",
-      "userGid": "6942",
+      "userUid": "1000",
+      "userGid": "1000",
       "upgradePackages": "true"
     },
     "ghcr.io/devcontainers/features/desktop-lite:1": {},
+    "ghcr.io/devcontainers/features/github-cli:1": {},
     "ghcr.io/devcontainers/features/python:1": "none",
     "ghcr.io/devcontainers/features/node:1": "none",
     "ghcr.io/devcontainers/features/git:1": {
@@ -25,7 +26,9 @@
     "vscode": {
       // Set *default* container specific settings.json values on container create.
       "settings": {
-        "python.defaultInterpreterPath": "/usr/local/bin/python"
+        "python.defaultInterpreterPath": "/usr/local/bin/python",
+        "python.testing.pytestEnabled": true,
+        "python.testing.unittestEnabled": false
       }
     }
   },
@@ -36,5 +39,8 @@
   // "postCreateCommand": "pip3 install --user -r requirements.txt",
 
   // Set `remoteUser` to `root` to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
-  "remoteUser": "vscode"
-}
+  "remoteUser": "vscode",
+
+  // Add the freshly containerized repo to the list of safe repositories
+  "postCreateCommand": "git config --global --add safe.directory /workspace/Auto-GPT && pip3 install --user -r requirements.txt"
+}
\ No newline at end of file

From f13aba0958b945e840228f2d0853afcf67ff46a8 Mon Sep 17 00:00:00 2001
From: GoCodeo <dev@gocodeo.com>
Date: Fri, 19 May 2023 15:03:02 +0530
Subject: [PATCH 031/112] Added unittest cases for commands/analyze_code.py
 file (#4212)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 tests/test_analyze_code.py | 60 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 tests/test_analyze_code.py

diff --git a/tests/test_analyze_code.py b/tests/test_analyze_code.py
new file mode 100644
index 00000000..48bded03
--- /dev/null
+++ b/tests/test_analyze_code.py
@@ -0,0 +1,60 @@
+# Date: 2023-5-13
+# Author: Generated by GoCodeo.
+import pytest
+
+from autogpt.commands.analyze_code import analyze_code
+
+
+@pytest.fixture
+def mock_call_ai_function(mocker):
+    return mocker.patch("autogpt.commands.analyze_code.call_ai_function")
+
+
+class TestAnalyzeCode:
+    def test_positive_analyze_code(self, mock_call_ai_function):
+        # Positive Test
+        mock_call_ai_function.return_value = ["Suggestion 1", "Suggestion 2"]
+        code = "def example_function():\n    pass"
+        result = analyze_code(code)
+        assert result == ["Suggestion 1", "Suggestion 2"]
+        mock_call_ai_function.assert_called_once_with(
+            "def analyze_code(code: str) -> list[str]:",
+            [code],
+            "Analyzes the given code and returns a list of suggestions for improvements.",
+        )
+
+    def test_negative_analyze_code(self, mock_call_ai_function):
+        # Negative Test
+        mock_call_ai_function.return_value = []
+        code = "def example_function():\n    pass"
+        result = analyze_code(code)
+        assert result == []
+        mock_call_ai_function.assert_called_once_with(
+            "def analyze_code(code: str) -> list[str]:",
+            [code],
+            "Analyzes the given code and returns a list of suggestions for improvements.",
+        )
+
+    def test_error_analyze_code(self, mock_call_ai_function):
+        # Error Test
+        mock_call_ai_function.side_effect = Exception("Error occurred")
+        code = "def example_function():\n    pass"
+        with pytest.raises(Exception):
+            analyze_code(code)
+        mock_call_ai_function.assert_called_once_with(
+            "def analyze_code(code: str) -> list[str]:",
+            [code],
+            "Analyzes the given code and returns a list of suggestions for improvements.",
+        )
+
+    def test_edge_analyze_code_empty_code(self, mock_call_ai_function):
+        # Edge Test
+        mock_call_ai_function.return_value = ["Suggestion 1", "Suggestion 2"]
+        code = ""
+        result = analyze_code(code)
+        assert result == ["Suggestion 1", "Suggestion 2"]
+        mock_call_ai_function.assert_called_once_with(
+            "def analyze_code(code: str) -> list[str]:",
+            [code],
+            "Analyzes the given code and returns a list of suggestions for improvements.",
+        )

From 812be60d2a49481c985fc66a142c03ba934102c0 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Fri, 19 May 2023 17:07:48 +0200
Subject: [PATCH 032/112] Delete sponsors_readme.yml workflow (#4304)

---
 .github/workflows/sponsors_readme.yml | 28 ---------------------------
 1 file changed, 28 deletions(-)
 delete mode 100644 .github/workflows/sponsors_readme.yml

diff --git a/.github/workflows/sponsors_readme.yml b/.github/workflows/sponsors_readme.yml
deleted file mode 100644
index 7e51a4f8..00000000
--- a/.github/workflows/sponsors_readme.yml
+++ /dev/null
@@ -1,28 +0,0 @@
-name: Generate Sponsors README
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: '0 */12 * * *'
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout 🛎️
-        uses: actions/checkout@v3
-
-      - name: Generate Sponsors 💖
-        uses: JamesIves/github-sponsors-readme-action@v1
-        with:
-          token: ${{ secrets.README_UPDATER_PAT }}
-          file: 'README.md'
-          minimum: 2500
-          maximum: 99999
-
-      - name: Deploy to GitHub Pages 🚀
-        uses: JamesIves/github-pages-deploy-action@v4
-        with:
-          branch: master
-          folder: '.'
-          token: ${{ secrets.README_UPDATER_PAT }}

From ee986412108933b525b9b09089d92d7e8154fe8c Mon Sep 17 00:00:00 2001
From: "Luke K (pr-0f3t)" <2609441+lc0rp@users.noreply.github.com>
Date: Fri, 19 May 2023 13:19:39 -0400
Subject: [PATCH 033/112] Imagegen delay retry huggingface (#4194)

Co-authored-by: Kory Becker <kbecker@primaryobjects.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 tests/test_image_gen.py | 50 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/tests/test_image_gen.py b/tests/test_image_gen.py
index a48f26b9..a18855e7 100644
--- a/tests/test_image_gen.py
+++ b/tests/test_image_gen.py
@@ -1,6 +1,7 @@
 import functools
 import hashlib
 from pathlib import Path
+from unittest.mock import patch
 
 import pytest
 from PIL import Image
@@ -106,6 +107,55 @@ def generate_and_validate(
         assert img.size == (image_size, image_size)
 
 
+@pytest.mark.parametrize(
+    "return_text",
+    [
+        '{"error":"Model [model] is currently loading","estimated_time": [delay]}',  # Delay
+        '{"error":"Model [model] is currently loading"}',  # No delay
+        '{"error:}',  # Bad JSON
+        "",  # Bad Image
+    ],
+)
+@pytest.mark.parametrize(
+    "image_model",
+    ["CompVis/stable-diffusion-v1-4", "stabilityai/stable-diffusion-2-1"],
+)
+@pytest.mark.parametrize("delay", [10, 0])
+def test_huggingface_fail_request_with_delay(
+    config, workspace, image_size, image_model, return_text, delay
+):
+    return_text = return_text.replace("[model]", image_model).replace(
+        "[delay]", str(delay)
+    )
+
+    with patch("requests.post") as mock_post:
+        if return_text == "":
+            # Test bad image
+            mock_post.return_value.status_code = 200
+            mock_post.return_value.ok = True
+            mock_post.return_value.content = b"bad image"
+        else:
+            # Test delay and bad json
+            mock_post.return_value.status_code = 500
+            mock_post.return_value.ok = False
+            mock_post.return_value.text = return_text
+
+        config.image_provider = "huggingface"
+        config.huggingface_image_model = image_model
+        prompt = "astronaut riding a horse"
+
+        with patch("time.sleep") as mock_sleep:
+            # Verify request fails.
+            result = generate_image(prompt, image_size)
+            assert result == "Error creating image."
+
+            # Verify retry was called with delay if delay is in return_text
+            if "estimated_time" in return_text:
+                mock_sleep.assert_called_with(delay)
+            else:
+                mock_sleep.assert_not_called()
+
+
 def test_huggingface_fail_request_with_delay(mocker):
     config = Config()
     config.huggingface_api_token = "1"

From ccc03c1a8dacd61de1078e2cfe43af4e6ad39b2d Mon Sep 17 00:00:00 2001
From: Trajan Wiley-Jimenez <65563905+TrajanWJ@users.noreply.github.com>
Date: Fri, 19 May 2023 10:33:14 -0700
Subject: [PATCH 034/112] Enabling/disabling none/all of plugins from .env file
 (#4036)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/plugins.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/autogpt/plugins.py b/autogpt/plugins.py
index 99bb6256..bf77ef74 100644
--- a/autogpt/plugins.py
+++ b/autogpt/plugins.py
@@ -262,10 +262,14 @@ def denylist_allowlist_check(plugin_name: str, cfg: Config) -> bool:
         True or False
     """
     logger.debug(f"Checking if plugin {plugin_name} should be loaded")
-    if plugin_name in cfg.plugins_denylist:
+    if (
+        plugin_name in cfg.plugins_denylist
+        or "all" in cfg.plugins_denylist
+        or "none" in cfg.plugins_allowlist
+    ):
         logger.debug(f"Not loading plugin {plugin_name} as it was in the denylist.")
         return False
-    if plugin_name in cfg.plugins_allowlist:
+    if plugin_name in cfg.plugins_allowlist or "all" in cfg.plugins_allowlist:
         logger.debug(f"Loading plugin {plugin_name} as it was in the allowlist.")
         return True
     ack = input(

From a6d4deaf205537a64b31ff1e1e10b1e3bc5e6fc3 Mon Sep 17 00:00:00 2001
From: John Cole <29712567+johnisanerd@users.noreply.github.com>
Date: Fri, 19 May 2023 13:39:12 -0400
Subject: [PATCH 035/112] Update setup.md (#3690)

Co-authored-by: Richard Beales <rich@richbeales.net>
---
 .gitignore    |  1 +
 docs/setup.md | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/.gitignore b/.gitignore
index 816cdb0c..971c3368 100644
--- a/.gitignore
+++ b/.gitignore
@@ -21,6 +21,7 @@ logs
 *.log
 *.mp3
 mem.sqlite3
+venvAutoGPT
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
diff --git a/docs/setup.md b/docs/setup.md
index 97c5bac8..70b3ac39 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -211,6 +211,16 @@ docker run -it --env-file=.env -v $PWD:/app --rm auto-gpt --gpt3only --continuou
 
 ### Run without Docker
 
+#### Create a Virtual Environment
+
+Create a virtual environment to run in.
+
+``` shell
+python -m venv venvAutoGPT
+source venvAutoGPT/bin/activate
+pip3 install --upgrade pip
+```
+
 !!! warning
     Due to security reasons, certain features (like Python execution) will by default be disabled when running without docker. So, even if you want to run the program outside a docker container, you currently still need docker to actually run scripts.
 

From bf33f4a7b0b2af7f9ed67b18f9219c55cdfe71f4 Mon Sep 17 00:00:00 2001
From: WladBlank <wlad.c@me.com>
Date: Fri, 19 May 2023 19:50:43 +0200
Subject: [PATCH 036/112] add command shell blacklist and whitelist (#3950)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Richard Beales <rich@richbeales.net>
---
 .env.template                    |  9 +++++++++
 autogpt/commands/execute_code.py | 32 ++++++++++++++++++++++++++++++++
 autogpt/config/config.py         | 12 ++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/.env.template b/.env.template
index 05f2c1ab..31d8ccc6 100644
--- a/.env.template
+++ b/.env.template
@@ -38,6 +38,15 @@
 ## For example, to disable coding related features, uncomment the next line
 # DISABLED_COMMAND_CATEGORIES=autogpt.commands.analyze_code,autogpt.commands.execute_code,autogpt.commands.git_operations,autogpt.commands.improve_code,autogpt.commands.write_tests
 
+## DENY_COMMANDS - The list of commands that are not allowed to be executed by Auto-GPT (Default: None)
+# the following are examples:
+# DENY_COMMANDS=cd,nano,vim,vi,emacs,rm,sudo,top,ping,ssh,scp
+
+## ALLOW_COMMANDS - ONLY those commands will be allowed to be executed by Auto-GPT
+# the following are examples:
+# ALLOW_COMMANDS=ls,git,cat,grep,find,echo,ps,curl,wget
+
+
 ################################################################################
 ### LLM PROVIDER
 ################################################################################
diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py
index af7f70bc..f365cce2 100644
--- a/autogpt/commands/execute_code.py
+++ b/autogpt/commands/execute_code.py
@@ -97,6 +97,32 @@ def execute_python_file(filename: str) -> str:
         return f"Error: {str(e)}"
 
 
+def validate_command(command: str) -> bool:
+    """Validate a command to ensure it is allowed
+
+    Args:
+        command (str): The command to validate
+
+    Returns:
+        bool: True if the command is allowed, False otherwise
+    """
+    tokens = command.split()
+
+    if not tokens:
+        return False
+
+    if CFG.deny_commands and tokens[0] not in CFG.deny_commands:
+        return False
+
+    for keyword in CFG.allow_commands:
+        if keyword in tokens:
+            return True
+    if CFG.allow_commands:
+        return False
+
+    return True
+
+
 @command(
     "execute_shell",
     "Execute Shell Command, non-interactive commands only",
@@ -115,6 +141,9 @@ def execute_shell(command_line: str) -> str:
     Returns:
         str: The output of the command
     """
+    if not validate_command(command_line):
+        logger.info(f"Command '{command_line}' not allowed")
+        return "Error: This Shell Command is not allowed."
 
     current_dir = Path.cwd()
     # Change dir into workspace if necessary
@@ -153,6 +182,9 @@ def execute_shell_popen(command_line) -> str:
     Returns:
         str: Description of the fact that the process started and its id
     """
+    if not validate_command(command_line):
+        logger.info(f"Command '{command_line}' not allowed")
+        return "Error: This Shell Command is not allowed."
 
     current_dir = os.getcwd()
     # Change dir into workspace if necessary
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index daf12397..c5ffc60c 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -37,6 +37,18 @@ class Config(metaclass=Singleton):
         else:
             self.disabled_command_categories = []
 
+        deny_commands = os.getenv("DENY_COMMANDS")
+        if deny_commands:
+            self.deny_commands = deny_commands.split(",")
+        else:
+            self.deny_commands = []
+
+        allow_commands = os.getenv("ALLOW_COMMANDS")
+        if allow_commands:
+            self.allow_commands = allow_commands.split(",")
+        else:
+            self.allow_commands = []
+
         self.ai_settings_file = os.getenv("AI_SETTINGS_FILE", "ai_settings.yaml")
         self.prompt_settings_file = os.getenv(
             "PROMPT_SETTINGS_FILE", "prompt_settings.yaml"

From a08fc850f079ecce1773d53adcb5a140628ca91b Mon Sep 17 00:00:00 2001
From: Omri Grossman <omri.g@codium.ai>
Date: Fri, 19 May 2023 21:47:04 +0300
Subject: [PATCH 037/112] Used a regex expression for simple URL validation and
 added tests (#3763)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Richard Beales <rich@richbeales.net>
---
 autogpt/url_utils/validators.py   |  3 +-
 tests/unit/test_url_validation.py | 99 +++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+), 1 deletion(-)

diff --git a/autogpt/url_utils/validators.py b/autogpt/url_utils/validators.py
index 2c0c5fa5..c9c1d06a 100644
--- a/autogpt/url_utils/validators.py
+++ b/autogpt/url_utils/validators.py
@@ -1,4 +1,5 @@
 import functools
+import re
 from typing import Any, Callable
 from urllib.parse import urljoin, urlparse
 
@@ -23,7 +24,7 @@ def validate_url(func: Callable[..., Any]) -> Any:
             ValueError if the url fails any of the validation tests
         """
         # Most basic check if the URL is valid:
-        if not url.startswith("http://") and not url.startswith("https://"):
+        if not re.match(r"^https?://", url):
             raise ValueError("Invalid URL format")
         if not is_valid_url(url):
             raise ValueError("Missing Scheme or Network location")
diff --git a/tests/unit/test_url_validation.py b/tests/unit/test_url_validation.py
index 2bbd3f9e..c29161af 100644
--- a/tests/unit/test_url_validation.py
+++ b/tests/unit/test_url_validation.py
@@ -3,6 +3,33 @@ from pytest import raises
 
 from autogpt.url_utils.validators import validate_url
 
+"""
+Code Analysis
+
+Objective:
+The objective of the 'validate_url' function is to validate URLs for any command that requires a URL as an argument. It checks if the URL is valid using a basic check, urllib check, and local file check. If the URL fails any of the validation tests, it raises a ValueError.
+
+Inputs:
+- func: A callable function that takes in any number of arguments and returns any type of output.
+
+Flow:
+- The 'validate_url' function takes in a callable function as an argument.
+- It defines a wrapper function that takes in a URL and any number of arguments and keyword arguments.
+- The wrapper function first checks if the URL starts with "http://" or "https://". If not, it raises a ValueError with the message "Invalid URL format".
+- It then checks if the URL is valid using the 'is_valid_url' function. If not, it raises a ValueError with the message "Missing Scheme or Network location".
+- It then checks if the URL is a local file using the 'check_local_file_access' function. If it is, it raises a ValueError with the message "Access to local files is restricted".
+- If the URL passes all the validation tests, it sanitizes the URL using the 'sanitize_url' function and calls the original function with the sanitized URL and any other arguments and keyword arguments.
+- The wrapper function returns the result of the original function.
+
+Outputs:
+- The 'validate_url' function returns the wrapper function that takes in a URL and any number of arguments and keyword arguments and returns the result of the original function.
+
+Additional aspects:
+- The 'validate_url' function uses the 'functools.wraps' decorator to preserve the original function's metadata, such as its name, docstring, and annotations.
+- The 'validate_url' function uses the 'urlparse' function from the 'urllib.parse' module to parse the URL and extract its components.
+- The 'validate_url' function uses the 'urljoin' function from the 'requests.compat' module to join the sanitized URL components back into a URL string.
+"""
+
 
 @validate_url
 def dummy_method(url):
@@ -57,3 +84,75 @@ local_file = (
 def test_url_validation_fails_local_path(url):
     with raises(ValueError, match="Access to local files is restricted"):
         dummy_method(url)
+
+
+class TestValidateUrl:
+    # Tests that the function successfully validates a valid URL with http:// or https:// prefix.
+    def test_happy_path_valid_url(self):
+        """Test that the function successfully validates a valid URL with http:// or https:// prefix"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        assert test_func("https://www.google.com") == "https://www.google.com"
+        assert test_func("http://www.google.com") == "http://www.google.com"
+
+    # Tests that the function successfully validates a valid URL with additional path, parameters, and query string.
+    def test_general_behavior_additional_path_parameters_query_string(self):
+        """Test that the function successfully validates a valid URL with additional path, parameters, and query string"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        assert (
+            test_func("https://www.google.com/search?q=python")
+            == "https://www.google.com/search?q=python"
+        )
+
+    # Tests that the function raises a ValueError if the URL is missing scheme or network location.
+    def test_edge_case_missing_scheme_or_network_location(self):
+        """Test that the function raises a ValueError if the URL is missing scheme or network location"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        with pytest.raises(ValueError):
+            test_func("www.google.com")
+
+    # Tests that the function raises a ValueError if the URL has local file access.
+    def test_edge_case_local_file_access(self):
+        """Test that the function raises a ValueError if the URL has local file access"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        with pytest.raises(ValueError):
+            test_func("file:///etc/passwd")
+
+    # Tests that the function sanitizes the URL by removing any unnecessary components.
+    def test_general_behavior_sanitizes_url(self):
+        """Test that the function sanitizes the URL by removing any unnecessary components"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        assert (
+            test_func("https://www.google.com/search?q=python#top")
+            == "https://www.google.com/search?q=python"
+        )
+
+    # Tests that the function raises a ValueError if the URL has an invalid format (e.g. missing slashes).
+    def test_general_behavior_invalid_url_format(self):
+        """Test that the function raises a ValueError if the URL has an invalid format (e.g. missing slashes)"""
+
+        @validate_url
+        def test_func(url):
+            return url
+
+        with pytest.raises(ValueError):
+            test_func("https:www.google.com")

From c3f7916dfd35bfa5deeb3d6d7ed56c02939a6a82 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Fri, 19 May 2023 20:51:36 +0200
Subject: [PATCH 038/112] Clean up BULLETIN.md (#4305)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Pi <sunfish7@gmail.com>
---
 BULLETIN.md | 69 ++++++++++++++++++++++-------------------------------
 1 file changed, 28 insertions(+), 41 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index f77a8fc3..62aeeba2 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -2,57 +2,44 @@
 Check out *https://agpt.co*, the official news & updates site for Auto-GPT!
 The documentation also has a place here, at *https://docs.agpt.co*
 
+# For contributors 👷🏼
+Since releasing v0.3.0, we are working on re-architecting the Auto-GPT core to make
+it more extensible and to make room for structural performance-oriented R&D.
+In the meantime, we have less time to process incoming pull requests and issues,
+so we focus on high-value contributions:
+ * significant bugfixes
+ * *major* improvements to existing functionality and/or docs (so no single-typo fixes)
+ * contributions that help us with re-architecture and other roadmapped items
+We have to be somewhat selective in order to keep making progress, but this does not
+mean you can't contribute. Check out the contribution guide on our wiki:
+https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
+
 # 🚀 v0.3.1 Release 🚀
 Over a week and 47 pull requests have passed since v0.3.0, and we are happy to announce
 the release of v0.3.1!
 
-Highlights and notable changes in this release:
+Highlights and notable changes since v0.2.2:
 
 ## Changes to Docker configuration 🐋
-The workdir has been changed from */home/appuser* to */app*.
-Be sure to update any volume mounts accordingly!
+ * The workdir has been changed from */home/appuser* to */app*.
+    Be sure to update any volume mounts accordingly!
+ * Docker-compose 1.29.0 is now required.
+
+## Logging 🧾
+ * Log functionality has been improved for better understanding
+    and easier summarization.
+ * All LLM interactions are now logged to logs/DEBUG, to help with
+    debugging and development.
+
+## Other
+ * Edge browser is now supported by the `browse_website` command.
+ * Sets of commands can now be disabled using DISABLED_COMMAND_CATEGORIES in .env.
 
 # ⚠️ Command `send_tweet` is DEPRECATED, and will be removed in v0.4.0 ⚠️
 Twitter functionality (and more) is now covered by plugins, see [Plugin support 🔌]
 
-## Documentation
-- Docker-compose 1.29.0 is now required, as documented.
-- Path to the workspace directory in the setup guide has been corrected.
-- Memory setup links have been updated.
-
-## Logs
-- Log functionality has been improved for better understanding and easier summarization.
-- User input is now logged in the logs/Debug Folder.
-
-## Other 
-- Edge browser support has been added using EdgeChromiumDriverManager.
-- Users now have the ability to disable commands via the .env file.
-- Run scripts for both Windows (.bat) and Unix (.sh) have been updated.
-
-## BugFix
-- DuckDuckGo dependency has been updated, with a minimum version set to 2.9.5.
-- Package versions parsing has been enabled for forced upgrades.
-- Docker volume mounts have been fixed.
-- A fix was made to the plugin.post_planning call.
-- A selenium driver object reference bug in the browsing results was fixed.
-- JSON error in summary_memory.py has been handled.
-- Dockerfile has been updated to add missing scripts and plugins directories.
-
-## CI
-- The CI pipeline has been tightened up for improved performance.
-- pytest-xdist Plugin has been integrated for parallel and concurrent testing.
-- Tests have been conducted for a new CI pipeline.
-- A code owners policy has been added.
-- Test against Python 3.10 (not 3.10 + 3.11) to halve the number of tests that are executed.
-
 ## Plugin support 🔌
 Auto-GPT now has support for plugins! With plugins, you can extend Auto-GPT's abilities,
 adding support for third-party services and more.
-See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and available plugins.
-Denylist handling for plugins is now available.
-
-*From now on, we will be focusing on major improvements* rather
-than bugfixes, as we feel stability has reached a reasonable level. Most remaining
-issues relate to limitations in prompt generation and the memory system, which will be
-the focus of our efforts for the next release.
-
+See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and
+available plugins. Specific plugins can be allowlisted/denylisted in .env.

From 7e21f38185a881c10cc3ffcd7d1ad9b27e78a566 Mon Sep 17 00:00:00 2001
From: GoCodeo <dev@gocodeo.com>
Date: Sat, 20 May 2023 00:48:32 +0530
Subject: [PATCH 039/112] Added unittest cases for commands/audio_text.py
 (#4307)

Co-authored-by: Richard Beales <rich@richbeales.net>
---
 tests/test_audio_text_read_audio.py           | 61 +++++++++++++++++++
 tests/test_audio_text_read_audio_from_file.py | 54 ++++++++++++++++
 2 files changed, 115 insertions(+)
 create mode 100644 tests/test_audio_text_read_audio.py
 create mode 100644 tests/test_audio_text_read_audio_from_file.py

diff --git a/tests/test_audio_text_read_audio.py b/tests/test_audio_text_read_audio.py
new file mode 100644
index 00000000..d8f2af52
--- /dev/null
+++ b/tests/test_audio_text_read_audio.py
@@ -0,0 +1,61 @@
+# Date: 2023-5-13
+# Author: Generated by GoCodeo.
+import json
+from io import BytesIO
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from autogpt.commands.audio_text import read_audio
+
+patch_func1 = "autogpt.commands.audio_text.CFG"
+
+
+class TestReadAudio:
+    @patch("requests.post")
+    def test_positive_read_audio(self, mock_post):
+        # Positive Test
+        audio_data = b"test_audio_data"
+        mock_response = MagicMock()
+        mock_response.content.decode.return_value = json.dumps(
+            {"text": "Hello, world!"}
+        )
+        mock_post.return_value = mock_response
+        with patch(patch_func1) as mock_cfg:
+            mock_cfg.huggingface_api_token = "testing-token"
+            result = read_audio(audio_data)
+            assert result == "The audio says: Hello, world!"
+            mock_post.assert_called_once_with(
+                f"https://api-inference.huggingface.co/models/{mock_cfg.huggingface_audio_to_text_model}",
+                headers={"Authorization": f"Bearer {mock_cfg.huggingface_api_token}"},
+                data=audio_data,
+            )
+
+    @patch("requests.post")
+    def test_negative_read_audio(self, mock_post):
+        # Negative Test
+        audio_data = b"test_audio_data"
+        mock_response = MagicMock()
+        mock_response.content.decode.return_value = json.dumps({"text": ""})
+        mock_post.return_value = mock_response
+        with patch(patch_func1) as mock_cfg:
+            mock_cfg.huggingface_api_token = "testing-token"
+            result = read_audio(audio_data)
+            assert result == "The audio says: "
+            mock_post.assert_called_once_with(
+                f"https://api-inference.huggingface.co/models/{mock_cfg.huggingface_audio_to_text_model}",
+                headers={"Authorization": f"Bearer {mock_cfg.huggingface_api_token}"},
+                data=audio_data,
+            )
+
+    def test_error_read_audio(self):
+        # Error Test
+        with patch(patch_func1) as mock_cfg:
+            mock_cfg.huggingface_api_token = None
+            with pytest.raises(ValueError):
+                read_audio(b"test_audio_data")
+
+    def test_edge_read_audio_empty_audio(self):
+        # Edge Test
+        with pytest.raises(ValueError):
+            read_audio(b"")
diff --git a/tests/test_audio_text_read_audio_from_file.py b/tests/test_audio_text_read_audio_from_file.py
new file mode 100644
index 00000000..b8cb352c
--- /dev/null
+++ b/tests/test_audio_text_read_audio_from_file.py
@@ -0,0 +1,54 @@
+# Date: 2023-5-13
+# Author: Generated by GoCodeo.
+
+
+from unittest.mock import mock_open, patch
+
+import pytest
+
+from autogpt.commands.audio_text import read_audio_from_file
+
+
+@pytest.fixture
+def mock_read_audio(mocker):
+    return mocker.patch("autogpt.commands.audio_text.read_audio")
+
+
+class TestReadAudioFromFile:
+    def test_positive_read_audio_from_file(self, mock_read_audio):
+        # Positive test
+        mock_read_audio.return_value = "This is a sample text."
+        mock_file_data = b"Audio data"
+        m = mock_open(read_data=mock_file_data)
+
+        with patch("builtins.open", m):
+            result = read_audio_from_file("test_audio.wav")
+            assert result == "This is a sample text."
+            m.assert_called_once_with("test_audio.wav", "rb")
+
+    def test_negative_read_audio_from_file(self, mock_read_audio):
+        # Negative test
+        mock_read_audio.return_value = "This is a sample text."
+        mock_file_data = b"Audio data"
+        m = mock_open(read_data=mock_file_data)
+
+        with patch("builtins.open", m):
+            result = read_audio_from_file("test_audio.wav")
+            assert result != "Incorrect text."
+            m.assert_called_once_with("test_audio.wav", "rb")
+
+    def test_error_read_audio_from_file(self):
+        # Error test
+        with pytest.raises(FileNotFoundError):
+            read_audio_from_file("non_existent_file.wav")
+
+    def test_edge_empty_audio_file(self, mock_read_audio):
+        # Edge test
+        mock_read_audio.return_value = ""
+        mock_file_data = b""
+        m = mock_open(read_data=mock_file_data)
+
+        with patch("builtins.open", m):
+            result = read_audio_from_file("empty_audio.wav")
+            assert result == ""
+            m.assert_called_once_with("empty_audio.wav", "rb")

From 023a50d26bc755c12c87bb1b485f8b9c8f01c629 Mon Sep 17 00:00:00 2001
From: "Luke K (pr-0f3t)" <2609441+lc0rp@users.noreply.github.com>
Date: Sat, 20 May 2023 16:51:01 -0400
Subject: [PATCH 040/112] Adding devcontainer extensions (#4181)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 .devcontainer/devcontainer.json | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index 1be773cf..08e74b40 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -29,7 +29,17 @@
         "python.defaultInterpreterPath": "/usr/local/bin/python",
         "python.testing.pytestEnabled": true,
         "python.testing.unittestEnabled": false
-      }
+      },
+      "extensions": [
+        "ms-python.python",
+        "VisualStudioExptTeam.vscodeintellicode",
+        "ms-python.vscode-pylance",
+        "ms-python.black-formatter",
+        "ms-python.isort",
+        "GitHub.vscode-pull-request-github",
+        "GitHub.copilot",
+        "github.vscode-github-actions"
+      ]
     }
   },
   // Use 'forwardPorts' to make a list of ports inside the container available locally.

From c30f5b7d5e5c457ffd1cd458913a4ee4eaaa095d Mon Sep 17 00:00:00 2001
From: Nicholas Tindle <nick@ntindle.com>
Date: Sat, 20 May 2023 18:04:57 -0500
Subject: [PATCH 041/112] fix: completion was being called with wrong data
 types (#4324)

---
 autogpt/agent/agent.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index e68bf989..ed9fea60 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -343,7 +343,7 @@ class Agent:
         thought = thoughts.get("thoughts", "")
         feedback_thoughts = thought + reasoning + plan
 
-        messages = {"role": "user", "content": feedback_prompt + feedback_thoughts}
+        messages = [{"role": "user", "content": feedback_prompt + feedback_thoughts}]
 
         self.log_cycle_handler.log_cycle(
             self.config.ai_name,
@@ -353,7 +353,7 @@ class Agent:
             PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
         )
 
-        feedback = create_chat_completion(messages)
+        feedback = create_chat_completion(messages, model=llm_model)
 
         self.log_cycle_handler.log_cycle(
             self.config.ai_name,

From 57ea7b5216918c43bb89766cf152ccfa58fb8d77 Mon Sep 17 00:00:00 2001
From: Konrad <kdroeske@gmail.com>
Date: Sat, 20 May 2023 19:45:27 -0400
Subject: [PATCH 042/112] Fixed #4229 (#4278)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/configurator.py      |  5 +++++
 autogpt/llm/api_manager.py   | 19 ++++++++++++++++
 autogpt/llm/llm_utils.py     | 21 +++++++++++++++++-
 autogpt/main.py              |  1 +
 tests/test_api_manager.py    | 10 +++++++++
 tests/test_config.py         | 42 ++++++++++++++++++++++++++++++++++--
 tests/unit/test_llm_utils.py | 27 +++++++++++++++++++++++
 7 files changed, 122 insertions(+), 3 deletions(-)

diff --git a/autogpt/configurator.py b/autogpt/configurator.py
index 0fddd1fa..98bd0b26 100644
--- a/autogpt/configurator.py
+++ b/autogpt/configurator.py
@@ -1,9 +1,12 @@
 """Configurator module."""
+from __future__ import annotations
+
 import click
 from colorama import Back, Fore, Style
 
 from autogpt import utils
 from autogpt.config import Config
+from autogpt.llm.llm_utils import check_model
 from autogpt.logs import logger
 from autogpt.memory import get_supported_memory_backends
 
@@ -45,6 +48,8 @@ def create_config(
     CFG.set_debug_mode(False)
     CFG.set_continuous_mode(False)
     CFG.set_speak_mode(False)
+    CFG.set_fast_llm_model(check_model(CFG.fast_llm_model, "fast_llm_model"))
+    CFG.set_smart_llm_model(check_model(CFG.smart_llm_model, "smart_llm_model"))
 
     if debug:
         logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED")
diff --git a/autogpt/llm/api_manager.py b/autogpt/llm/api_manager.py
index a7777a2b..82cf1c57 100644
--- a/autogpt/llm/api_manager.py
+++ b/autogpt/llm/api_manager.py
@@ -1,6 +1,9 @@
 from __future__ import annotations
 
+from typing import List, Optional
+
 import openai
+from openai import Model
 
 from autogpt.config import Config
 from autogpt.llm.modelsinfo import COSTS
@@ -14,12 +17,14 @@ class ApiManager(metaclass=Singleton):
         self.total_completion_tokens = 0
         self.total_cost = 0
         self.total_budget = 0
+        self.models: Optional[list[Model]] = None
 
     def reset(self):
         self.total_prompt_tokens = 0
         self.total_completion_tokens = 0
         self.total_cost = 0
         self.total_budget = 0.0
+        self.models = None
 
     def create_chat_completion(
         self,
@@ -127,3 +132,17 @@ class ApiManager(metaclass=Singleton):
         float: The total budget for API calls.
         """
         return self.total_budget
+
+    def get_models(self) -> List[Model]:
+        """
+        Get list of available GPT models.
+
+        Returns:
+        list: List of available GPT models.
+
+        """
+        if self.models is None:
+            all_models = openai.Model.list()["data"]
+            self.models = [model for model in all_models if "gpt" in model["id"]]
+
+        return self.models
diff --git a/autogpt/llm/llm_utils.py b/autogpt/llm/llm_utils.py
index a77bccbc..fcd1b2d8 100644
--- a/autogpt/llm/llm_utils.py
+++ b/autogpt/llm/llm_utils.py
@@ -3,7 +3,7 @@ from __future__ import annotations
 import functools
 import time
 from itertools import islice
-from typing import List, Optional
+from typing import List, Literal, Optional
 
 import numpy as np
 import openai
@@ -293,3 +293,22 @@ def create_embedding(
     )  # normalize the length to one
     chunk_embeddings = chunk_embeddings.tolist()
     return chunk_embeddings
+
+
+def check_model(
+    model_name: str, model_type: Literal["smart_llm_model", "fast_llm_model"]
+) -> str:
+    """Check if model is available for use. If not, return gpt-3.5-turbo."""
+    api_manager = ApiManager()
+    models = api_manager.get_models()
+
+    if any(model_name in m["id"] for m in models):
+        return model_name
+
+    logger.typewriter_log(
+        "WARNING: ",
+        Fore.YELLOW,
+        f"You do not have access to {model_name}. Setting {model_type} to "
+        f"gpt-3.5-turbo.",
+    )
+    return "gpt-3.5-turbo"
diff --git a/autogpt/main.py b/autogpt/main.py
index 79249609..ac27e282 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -47,6 +47,7 @@ def run_auto_gpt(
     cfg = Config()
     # TODO: fill in llm values here
     check_openai_api_key()
+
     create_config(
         continuous,
         continuous_limit,
diff --git a/tests/test_api_manager.py b/tests/test_api_manager.py
index 3d0672c1..bfb84213 100644
--- a/tests/test_api_manager.py
+++ b/tests/test_api_manager.py
@@ -118,3 +118,13 @@ class TestApiManager:
         assert api_manager.get_total_prompt_tokens() == 50
         assert api_manager.get_total_completion_tokens() == 100
         assert api_manager.get_total_cost() == (50 * 0.002 + 100 * 0.002) / 1000
+
+    @staticmethod
+    def test_get_models():
+        """Test if getting models works correctly."""
+        with patch("openai.Model.list") as mock_list_models:
+            mock_list_models.return_value = {"data": [{"id": "gpt-3.5-turbo"}]}
+            result = api_manager.get_models()
+
+            assert result[0]["id"] == "gpt-3.5-turbo"
+            assert api_manager.models[0]["id"] == "gpt-3.5-turbo"
diff --git a/tests/test_config.py b/tests/test_config.py
index e1fc6745..0f38b28c 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -2,10 +2,11 @@
 Test cases for the Config class, which handles the configuration settings
 for the AI and ensures it behaves as a singleton.
 """
+from unittest.mock import patch
 
-import pytest
+from openai import InvalidRequestError
 
-from autogpt.config import Config
+from autogpt.configurator import create_config
 
 
 def test_initial_values(config):
@@ -117,3 +118,40 @@ def test_set_debug_mode(config):
 
     # Reset debug mode
     config.set_debug_mode(debug_mode)
+
+
+@patch("openai.Model.list")
+def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config):
+    """
+    Test if models update to gpt-3.5-turbo if both are set to gpt-4.
+    """
+    fast_llm_model = config.fast_llm_model
+    smart_llm_model = config.smart_llm_model
+
+    config.fast_llm_model = "gpt-4"
+    config.smart_llm_model = "gpt-4"
+
+    mock_list_models.return_value = {"data": [{"id": "gpt-3.5-turbo"}]}
+
+    create_config(
+        continuous=False,
+        continuous_limit=False,
+        ai_settings_file="",
+        prompt_settings_file="",
+        skip_reprompt=False,
+        speak=False,
+        debug=False,
+        gpt3only=False,
+        gpt4only=False,
+        memory_type="",
+        browser_name="",
+        allow_downloads=False,
+        skip_news=False,
+    )
+
+    assert config.fast_llm_model == "gpt-3.5-turbo"
+    assert config.smart_llm_model == "gpt-3.5-turbo"
+
+    # Reset config
+    config.set_fast_llm_model(fast_llm_model)
+    config.set_smart_llm_model(smart_llm_model)
diff --git a/tests/unit/test_llm_utils.py b/tests/unit/test_llm_utils.py
index be36dc09..e11b368e 100644
--- a/tests/unit/test_llm_utils.py
+++ b/tests/unit/test_llm_utils.py
@@ -1,7 +1,11 @@
+from unittest.mock import patch
+
 import pytest
+from openai import InvalidRequestError
 from openai.error import APIError, RateLimitError
 
 from autogpt.llm import llm_utils
+from autogpt.llm.llm_utils import check_model
 
 
 @pytest.fixture(params=[RateLimitError, APIError])
@@ -131,3 +135,26 @@ def test_chunked_tokens():
     ]
     output = list(llm_utils.chunked_tokens(text, "cl100k_base", 8191))
     assert output == expected_output
+
+
+def test_check_model(api_manager):
+    """
+    Test if check_model() returns original model when valid.
+    Test if check_model() returns gpt-3.5-turbo when model is invalid.
+    """
+    with patch("openai.Model.list") as mock_list_models:
+        # Test when correct model is returned
+        mock_list_models.return_value = {"data": [{"id": "gpt-4"}]}
+        result = check_model("gpt-4", "smart_llm_model")
+        assert result == "gpt-4"
+
+        # Reset api manager models
+        api_manager.models = None
+
+        # Test when incorrect model is returned
+        mock_list_models.return_value = {"data": [{"id": "gpt-3.5-turbo"}]}
+        result = check_model("gpt-4", "fast_llm_model")
+        assert result == "gpt-3.5-turbo"
+
+        # Reset api manager models
+        api_manager.models = None

From bcc32cc441d475a9dd5f1cfd04062b8bc5cd024c Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Sun, 21 May 2023 04:20:03 +0300
Subject: [PATCH 043/112] Fix split_file when overlap = 0, add test (#3599)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/commands/file_operations.py |  2 +-
 tests/unit/test_file_operations.py  | 39 +++++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 28198eba..528f8d66 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -131,7 +131,7 @@ def split_file(
     while start < content_length:
         end = start + max_length
         if end + overlap < content_length:
-            chunk = content[start : end + overlap - 1]
+            chunk = content[start : end + max(overlap - 1, 0)]
         else:
             chunk = content[start:content_length]
 
diff --git a/tests/unit/test_file_operations.py b/tests/unit/test_file_operations.py
index fb8300d4..98d4efb7 100644
--- a/tests/unit/test_file_operations.py
+++ b/tests/unit/test_file_operations.py
@@ -151,12 +151,41 @@ def test_log_operation_with_checksum(config: Config):
     assert f"log_test: path/to/test #ABCDEF\n" in content
 
 
+@pytest.mark.parametrize(
+    "max_length, overlap, content, expected",
+    [
+        (
+            4,
+            1,
+            "abcdefghij",
+            ["abcd", "defg", "ghij"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijkl",
+            ["abcd", "efgh", "ijkl"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijklm",
+            ["abcd", "efgh", "ijkl", "m"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijk",
+            ["abcd", "efgh", "ijk"],
+        ),
+    ],
+)
 # Test splitting a file into chunks
-def test_split_file():
-    content = "abcdefghij"
-    chunks = list(file_ops.split_file(content, max_length=4, overlap=1))
-    expected = ["abcd", "defg", "ghij"]
-    assert chunks == expected
+def test_split_file(max_length, overlap, content, expected):
+    assert (
+        list(file_ops.split_file(content, max_length=max_length, overlap=overlap))
+        == expected
+    )
 
 
 def test_read_file(test_file_with_content_path: Path, file_content):

From e1c6778c3a832b775748e990a2fc2db25829c015 Mon Sep 17 00:00:00 2001
From: Nameless Dude <72940077+namelessperson0@users.noreply.github.com>
Date: Sun, 21 May 2023 23:56:45 +0530
Subject: [PATCH 044/112] Update README.md (#4333)

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 0d2681d9..3dbeed39 100644
--- a/README.md
+++ b/README.md
@@ -97,7 +97,7 @@ Your support is greatly appreciated. Development of this free, open-source proje
 
 ## Quickstart
 
-0. Check out the [wiki](https://github.com/Significant-Gravitas/Auto-GPT/wiki)
+0. Check out the [wiki](https://github.com/Significant-Gravitas/Nexus/wiki)
 1. Get an OpenAI [API Key](https://platform.openai.com/account/api-keys)
 2. Download the [latest release](https://github.com/Significant-Gravitas/Auto-GPT/releases/latest)
 3. Follow the [installation instructions][docs/setup]

From 31525dfef7d73011ca49569a2fa9922485718ef1 Mon Sep 17 00:00:00 2001
From: sherif-med <35470250+sherif-med@users.noreply.github.com>
Date: Sun, 21 May 2023 21:48:40 +0200
Subject: [PATCH 045/112] Text file loaders (#3031)

* adding requiered packages for loading pdf, docx, md, tex files (preferably pure python packages)

* adding text file utils providing function to load file based on extension && adding read_text_file command

* adding test cases for text file loading (pdf file creation is hardcoded due to external package requierment for creation (a sample file can be added))

* formatting

* changing command name from 'read_text_file' to 'parse_text_document'

* fallback to txtParser if file extension is not known to read script and code files

* adding extension respective parsers

* adding binary file check function

* adding file existance check && raising valueError for unsupported binary file formats

* adding check file type (binary) in test_parsers for specific extensions && fixing mock pdf generation to include null bytes

* adding .yml extension parser

* removal of .doc parser

* updating file loading commands names

* updating test (removing .doc mock function)

* fix: import sort

* new cassette for mem A

* feat: update Cassettes

* feat: consolidate commands

* feat: linting

* feat: updates to cassettes

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/commands/file_operations.py           |   13 +-
 autogpt/commands/file_operations_utils.py     |  159 ++
 requirements.txt                              |    4 +
 .../test_browse_website.yaml                  | 1329 +++++++++
 .../test_write_file/test_write_file.yaml      |  501 ++++
 .../test_memory_challenge_a.yaml              | 2517 +++++++++++++----
 tests/test_text_file_parsers.py               |  152 +
 7 files changed, 4053 insertions(+), 622 deletions(-)
 create mode 100644 autogpt/commands/file_operations_utils.py
 create mode 100644 tests/test_text_file_parsers.py

diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 528f8d66..0fe8114d 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -12,6 +12,7 @@ from colorama import Back, Fore
 from requests.adapters import HTTPAdapter, Retry
 
 from autogpt.commands.command import command
+from autogpt.commands.file_operations_utils import read_textual_file
 from autogpt.config import Config
 from autogpt.logs import logger
 from autogpt.spinner import Spinner
@@ -143,7 +144,7 @@ def split_file(
         start += max_length - overlap
 
 
-@command("read_file", "Read file", '"filename": "<filename>"')
+@command("read_file", "Read a file", '"filename": "<filename>"')
 def read_file(filename: str) -> str:
     """Read a file and return the contents
 
@@ -154,12 +155,10 @@ def read_file(filename: str) -> str:
         str: The contents of the file
     """
     try:
-        charset_match = charset_normalizer.from_path(filename).best()
-        encoding = charset_match.encoding
-        logger.debug(f"Read file '{filename}' with encoding '{encoding}'")
-        return str(charset_match)
-    except Exception as err:
-        return f"Error: {err}"
+        content = read_textual_file(filename, logger)
+        return content
+    except Exception as e:
+        return f"Error: {str(e)}"
 
 
 def ingest_file(
diff --git a/autogpt/commands/file_operations_utils.py b/autogpt/commands/file_operations_utils.py
new file mode 100644
index 00000000..cf29dc36
--- /dev/null
+++ b/autogpt/commands/file_operations_utils.py
@@ -0,0 +1,159 @@
+import json
+import os
+
+import charset_normalizer
+import docx
+import markdown
+import PyPDF2
+import yaml
+from bs4 import BeautifulSoup
+from pylatexenc.latex2text import LatexNodes2Text
+
+from autogpt import logs
+
+
+class ParserStrategy:
+    def read(self, file_path: str):
+        raise NotImplementedError
+
+
+# Basic text file reading
+class TXTParser(ParserStrategy):
+    def read(self, file_path):
+        charset_match = charset_normalizer.from_path(file_path).best()
+        return str(charset_match)
+
+
+# Reading text from binary file using pdf parser
+class PDFParser(ParserStrategy):
+    def read(self, file_path):
+        parser = PyPDF2.PdfReader(file_path)
+        text = ""
+        for page_idx in range(len(parser.pages)):
+            text += parser.pages[page_idx].extract_text()
+        return text
+
+
+# Reading text from binary file using docs parser
+class DOCXParser(ParserStrategy):
+    def read(self, file_path):
+        doc_file = docx.Document(file_path)
+        text = ""
+        for para in doc_file.paragraphs:
+            text += para.text
+        return text
+
+
+# Reading as dictionary and returning string format
+class JSONParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            data = json.load(f)
+            text = str(data)
+        return text
+
+
+class XMLParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            soup = BeautifulSoup(f, "xml")
+            text = soup.get_text()
+        return text
+
+
+# Reading as dictionary and returning string format
+class YAMLParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            data = yaml.load(f, Loader=yaml.FullLoader)
+            text = str(data)
+        return text
+
+
+class HTMLParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            soup = BeautifulSoup(f, "html.parser")
+            text = soup.get_text()
+        return text
+
+
+class MarkdownParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            html = markdown.markdown(f.read())
+            text = "".join(BeautifulSoup(html, "html.parser").findAll(string=True))
+        return text
+
+
+class LaTeXParser(ParserStrategy):
+    def read(self, file_path):
+        with open(file_path, "r") as f:
+            latex = f.read()
+        text = LatexNodes2Text().latex_to_text(latex)
+        return text
+
+
+class FileContext:
+    def __init__(self, parser: ParserStrategy, logger: logs.Logger):
+        self.parser = parser
+        self.logger = logger
+
+    def set_parser(self, parser: ParserStrategy):
+        self.logger.debug(f"Setting Context Parser to {parser}")
+        self.parser = parser
+
+    def read_file(self, file_path):
+        self.logger.debug(f"Reading file {file_path} with parser {self.parser}")
+        return self.parser.read(file_path)
+
+
+extension_to_parser = {
+    ".txt": TXTParser(),
+    ".csv": TXTParser(),
+    ".pdf": PDFParser(),
+    ".docx": DOCXParser(),
+    ".json": JSONParser(),
+    ".xml": XMLParser(),
+    ".yaml": YAMLParser(),
+    ".yml": YAMLParser(),
+    ".html": HTMLParser(),
+    ".htm": HTMLParser(),
+    ".xhtml": HTMLParser(),
+    ".md": MarkdownParser(),
+    ".markdown": MarkdownParser(),
+    ".tex": LaTeXParser(),
+}
+
+
+def is_file_binary_fn(file_path: str):
+    """Given a file path load all its content and checks if the null bytes is present
+
+    Args:
+        file_path (_type_): _description_
+
+    Returns:
+        bool: is_binary
+    """
+    with open(file_path, "rb") as f:
+        file_data = f.read()
+    if b"\x00" in file_data:
+        return True
+    return False
+
+
+def read_textual_file(file_path: str, logger: logs.Logger):
+    if not os.path.isfile(file_path):
+        raise FileNotFoundError(f"{file_path} not found!")
+    is_binary = is_file_binary_fn(file_path)
+    file_extension = os.path.splitext(file_path)[1].lower()
+    parser = extension_to_parser.get(file_extension)
+    if not parser:
+        if is_binary:
+            raise ValueError(
+                "Unsupported binary file format: {}".format(file_extension)
+            )
+        # fallback to txt file parser (to support script and code files loading)
+        parser = TXTParser()
+    file_context = FileContext(parser, logger)
+    return file_context.read_file(file_path)
diff --git a/requirements.txt b/requirements.txt
index 3c997b57..31cc2d0f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,6 +5,10 @@ openai==0.27.2
 playsound==1.2.2
 python-dotenv==1.0.0
 pyyaml==6.0
+PyPDF2
+python-docx
+markdown
+pylatexenc
 readability-lxml==0.8.1
 requests
 tiktoken==0.3.3
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
index f76703b6..2f811593 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
@@ -760,4 +760,1333 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
+      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
+      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
+      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3843'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6RTWW/bMAx+368g+Oxcc0+/DMOAohk2DOhWFMM8BIrMxFos0ZXotkCQ/z7IR490
+        xa5XUvwukVs0BWaoSyXa1tXoeP75402wh9Oz91fl/BNxffrOfL04P7+4OXuLCfLyB2npJ8aabV2R
+        GHaYoPakhArMZkcnB0dpmk5PE7RcUIUZrmsZpePDkTR+yaNpOp1hgk1Qa8Jsi7VnW8tCeEMuYHZy
+        dJDgA/Z9/XV6nKCwqOq+NJtNZ7sEdclGU8Ds2xYthQHXc0WYoQrBBFFOokp2Qi462OYOACBHKblZ
+        lxJyzKAv9g26k1jMcQ63pqqgCQRSEiw93wZa3NIyGCHQbK1yBQjDjQlGoBSps8lkybwJY+Ggvaop
+        pjXRSlTF64YmlgojKvoLizSdGFfQ3bgUW0GEWpmIVxLU3mgCXnW8zJtxjsljkZ5UYGfculP6pSQQ
+        FTbg6boxngJYehCmYND8axLVUcCXl02a0EmhIMB11A8r9iBlbKjwTF9dKddJG8HlH+YX3/TNPHcj
+        OHsxjbZ95SPKQ18YFKxMReCUpWKPbix30o4NaqLqRb9uT8Tc14ZXe9a0N2K0CXZYEkfUDpILjY9j
+        SmAOykITjFu3MJq9Jy1wefGh/YPrhkIbovBffHqoSW3+aTUfRfv7Resod8lwKT3as0OJMXdqntLv
+        qVZ+vX9kXaPxVTf+X4fzhK0DHtLt0K/if/T7+8zum8Fua7l3nrsd7hJcGWdCuehODTMMwjUm2FJj
+        Nt193736CQAA//8DACZ8z49JBQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca91e8ac9064698-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:42:07 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '17407'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86494'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.337s
+      x-request-id:
+      - 6a4242e99f4553aa4f1643eba393a92e
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
+      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
+      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
+      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am using the correct
+      URL and question to find the price of the book.\",\n        \"speak\": \"I will
+      use the browse_website command to visit the website and find the price of the
+      book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5726'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7xTwW7bMAy97ysInp0gids09X3AAmzFsHWneTAUmbG12KIr0UiKIF+zP9mXDbKd
+        pMk6YJftJIiP7/GREvdockxQl0p03VSju+Xnh4flu2fVal3NP759mtx84u3D++LpZlFhhLz6TloG
+        xlhz3VQkhi1GqB0poRyT6XxxM4/jOL6LsOacKkywaGQUj29H0roVjybxZIoRtl4VhMkeG8d1I5nw
+        hqzHZDpb3Ed4Fj8Bs1kcobCo6px7O50dItQlG00ek697rMkfhR1XhAkq740XZSXYZCtkQwv71AIA
+        pCglt0UpPsUEhuAA0E5CMMUlbE1VQesJpCTYOiOUCWdrUxFormtlcxDugS6lcUYT8Lq7rJg3AVbQ
+        EayqKYeV462nbEsrb4TGspNxitHL+o6UZ2ts0Zt4LAlE+Q04emqNIw81/XXRMTz+0bjxPYG8ADdh
+        5LBmB1IGQPnNta+mUra3NIIv/3YkaWrPNYKXbPgXFzVOsWPWlWHtjBhtfH18TUvUEcn61gWaEliC
+        qju3xhadkGbnSAsYu2ZXq24uwh3Uee6KB+YpYjysKNCHZQBjL5RyEw52z9cT9Q2pzX/+an39Q3Rc
+        g0H7ty0IEr21Cy9XHShXXC9QD4Tcs8QrL/xS53rvHl9tL01T/EC5ke5NfLiG0f/8MbsdL+5PrXXt
+        DV2m9oCHCNfGGl9m/WJhgl64wQiNzWmHyeTw7fDmFwAAAP//AwCokLGBEwUAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca91f359ed74698-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:42:34 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '17203'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86479'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.346s
+      x-request-id:
+      - 84c51f54f3ea6c17ef641028a950b098
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
+      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
+      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
+      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am using the correct
+      URL and question to find the price of the book.\",\n        \"speak\": \"I will
+      use the browse_website command to visit the website and find the price of the
+      book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the write_to_file command to write the price
+      of the book to a file named browse_website.txt.\",\n        \"reasoning\": \"The
+      task requires me to write the price of the book to a file. The write_to_file
+      command is the best option for this task.\",\n        \"plan\": \"- Use the
+      write_to_file command to write the price of the book to a file named browse_website.txt\\n-
+      Use the task_complete command to complete the task\",\n        \"criticism\":
+      \"I need to ensure that I am writing the correct information to the file and
+      that the file is being created in the correct directory.\",\n        \"speak\":
+      \"I will use the write_to_file command to write the price of the book to a file
+      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
+      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7014'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SSTY/TQAyG7/wKy+ekapWmQbmxEkKVFi4sJ4Kq6cTNDE1mwtiBRVX+O0qTfhCW
+        A+Jqv378+uOEtsQctVGim7aOs+3HD8ZKpxN5fGi3b8vs3eN7eZM9bMJ6hRH6/VfSMlUstG/amsR6
+        hxHqQEqoxHy1eb3eJEmSZhE2vqQac6xaiZNFGksX9j5eJssB1rGqCPMTtsE3rezEH8kx5qt0s4zw
+        Br8l1mmE4kXVt1C2TPsItfFWE2P++YQN8QUcfE2Yo2K2LMrJYNM7ITeMcCocAECBYnxXGeECc5iC
+        U4KeZQgWuIUftq6hYwIxBKL4uJsMEmjfNMqVIB6usYtqUWB0jwyk2DvrqpH7NMkg0LfOBmJo6GUO
+        PP21r+WzbE8s4NthY3DwAcQMiRc8tLVyY/sYPv3zRDOYDlasttxcFuWIzoXkuAtDmRLYglHf6coq
+        rzDgTmtiPnR1/RPOLQe9GAoEKhA4DxSCDzwfgltSx/8/zojso8svTPI/XsGphsZuv+FnplSo5l90
+        f/bZzY1i2BO5u73cr+Pq7uxwMlq4HvsID9ZZNrsRizmy+BYjtK6kZ8yX/Zf+1S8AAAD//wMAuHh6
+        B9sDAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca91fb59c034698-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:42:48 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '10952'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86470'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.352s
+      x-request-id:
+      - 0ef8ce2546c5b3d3cc369a42739b0303
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3769'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6RTWW8TMRB+51eM5nlztNsj2hdeUEVBCAkClWBR5DiTXZO1Z2vPNkVR/jvyHj3S
+        ViB4nfF8l2d2aFaYoS6VaFtXo/PL+cer2c27D81b/ZVuTPrmYv7Zfnpfnl5ffMMEefmTtPQTY822
+        rkgMO0xQe1JCK8yOzmYnZ+n58elxgpZXVGGGRS2jdHw6ksYveTRNp0eYYBNUQZjtsPZsa1kIb8gF
+        zGYnZwneY9/Vj9NZgsKiqrvS0XR2sk9Ql2w0Bcy+79BSGHA9V4QZqhBMEOUkqmQn5KKDXe4AAHKU
+        kpuilJBjBn2xb9CtxGKOl7A1VQVNIJCSYOl5G2ixpWUwQqDZWuVWIAw3JhiBUqTOJpMl8yaMhYP2
+        qqaY1kQrURUXDU0srYyo6C8s0nRi3Ipux6XYCiLU2kS8kqD2RhPwuuNl3oxzTB6K9KQCO+OKTum8
+        JBAVNuDpujGeAli6F6Zg0Pw8ieooYP6ySRM6KRQEuI76Yc0epIwNFZ7oqyvlOmkj+PKX+cU3fTPP
+        3QguXkyjbV/5iHLfFwYFa1MROGVpdUA3lltpxwY1UfWiX7dHYu5qw6sDa9obMdoEOyyJI2oHyYXG
+        xzElcAnKgtK68Uqo+tWGblzxvJ32W7YR1hUQg+C2pdl70tJ6Osw31KQ2/7SlD1L+8851lPtkOJoe
+        7cnNxMQ7NY/pD1QrXxzeW9dofNWN/9cNPWLrgK8bCvFlh34Vv6Zf5Sd2Xw92W8u989ztcZ/g2jgT
+        ykV3dZhhEK4xwZYas+n+x/7VbwAAAP//AwDGzdwhVAUAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca97ecb9fe4aa52-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:47:51 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '18748'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86493'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.338s
+      x-request-id:
+      - 3d788f38f42c530a90c82003462a6088
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
+      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5663'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7xTS47TQBDdc4pWrR0r/8n4BlkgAcqwACOr067YTeyunu4KCYp8Gm7CyVDbTjIx
+        g8QGll2fV+9VvzqDziEBVUpWta1GD+vNu/H3p0/Wfis+KLKz+W5ZT8bmef9+9hEioO1XVNx3xIpq
+        WyFrMhCBcigZc0gmy9V8OXuYrqYR1JRjBQkUlkezeDHig9vSaDwbTyCCg5cFQnIG66i2nDHt0XhI
+        JtOHaQQ38GtiOplFwMSyutXOV4smAlWSVugh+XyGGv0F2FGFkID0XnuWhgNNMowmSDinRgghUuCS
+        DkXJPoVE9ME+gScOwRTW4qirShw8Ci5RHJ1mzJiyna5QKKpraXLB1CXaEuu0QkG79rEl2oe0FG2D
+        kTXmYuvo6DE74tZrxphPHKcQvZzvUHoy2hQdiU2JgqXfC4fPB+3Qixr/emgsNn8krn3XgJ4F2bBy
+        sSMnuAwJ6fdDXraSpqM0Ek//diVpam4zApes98XdjGvsUjUgrJxmrbSvL79pENtGNP7gQptksRay
+        btlqU7RAipxDxT1vprtgu9PBGG9R7v+zYbr5TXQxc4/9m5cDREftjstAgXTF8Ay6RKi9QbzyTy9x
+        htezeVVemqbwFnPNMjjOh2dw4s8f00W8erxKa+X1KlPTQBPBThvty6w7D0jAM1mIQJscT5CMmy/N
+        m18AAAD//wMAPgHgstkEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca97f864bbaaa52-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:48:18 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '16649'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86476'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.348s
+      x-request-id:
+      - 4d1406ff152a336596f376c293ea4356
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
+      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the write_to_file command to write the price
+      of the book to a file named browse_website.txt.\",\n        \"reasoning\": \"The
+      task requires me to write the price of the book to a file. The write_to_file
+      command is the best option for this task.\",\n        \"plan\": \"- Use the
+      write_to_file command to write the price of the book to a file named browse_website.txt\\n-
+      Use the task_complete command to complete the task\",\n        \"criticism\":
+      \"I need to ensure that I am writing the correct price to the correct file.\",\n        \"speak\":
+      \"I will use the write_to_file command to write the price of the book to a file
+      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
+      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6893'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SST4/aQAzF7/0Uls8BQVNYlFv/qV21anuAU1OhYeIkUyYz6dgRrFC+ezUQFkp3
+        D1Wvz/abn5/ngKbADHWtRDetHd3dL799+rJil3743NWrj++rt/bN69LXX989KEzQb36SlmFirH3T
+        WhLjHSaoAymhArPpfPFqnt6lk5cJNr4gixlWrYzS8WwkXdj40SSdTDHBjlVFmB2wDb5pZS1+S44x
+        m87SNMGL+VVhlqB4UfYizReLPkFde6OJMft+wIb4bBy8JcxQMRsW5SRieifk4gqH3AEA5Ci176pa
+        OMcMBnEo0F6imOM97Iy10DGB1ASieLseAAm0bxrlChAPj9q5a5xjcm0ZSLF3xlUn3+XQBoF+dSYQ
+        Q0NP+8Dy2XcNH9s2xAK+jYlB6QNIHQtPMLRWudPzI1j980Y3ZjoYMdpwcw7KER0HyXEX4piSx9mI
+        ejYsgDutibnsrH24ZeSW1Pb/sz9Z9sn51EP7X5d2qqHTa3/Y30CpUN1+kuur3pzUl1AaVxhXHYna
+        YDRF8Xgr77cQuXcxPleBkbiCgtJYgkhTwCb4HdN6Rxs2QmPZC9SKYUPkng/xQtYPu+euxz7B0jjD
+        9fpEihmy+BYTNK6gPWaT/kf/4jcAAAD//wMAIpbLTA0EAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca980030d3daa52-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:48:34 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '12093'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.351s
+      x-request-id:
+      - 81d7a2ac6b212febaeab4f26aa26f84a
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
+      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Error: Service /home/ntindle/.wdm/drivers/edgedriver/linux64/113.0.1774.50/msedgedriver
+      unexpectedly exited. Status code was: 127"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5322'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SUS2/bMAzH7/sUBM9O0jSPFr4MPRRDsGHYgBY9zIUhy4ytRQ9XopsUQb77IDtp
+        unTrupNh8fX/UaS2qEpMUdaCpWn04GJxe/ddu3b9+GX6aaX52/WsuP76cGGuruafMUFX/CTJ+4ih
+        dKbRxMpZTFB6EkwlpuP55XQ+Hc8u5wkaV5LGFKuGB5PhbMCtL9zgbHI2xgTbICrCdIuNd6bhnN2K
+        bMB0PL6cJXhM/mw4n54nyI6FPvpOzy92CcraKUkB0x9bNBQOib3ThCmKEFRgYTnKdJbJRoRtZgEA
+        MuTatVXNIcMU9od7A204HmZ4UxMU3q0D5WsqgmIC6YwRtoSlUJrKISxgrbQG9k/QBmUr4JqgIs5j
+        ljy0xgj/9BzFDpYqfmuCxitJ4JbdT+Hcaphh8lKHJxGcVbZ6p5gEgoMFWKKuUJQkoFTLJXmy/E4N
+        cPOWfiksFARtoBd5aMPgLAjYyzrlaLSwPcIAbgP9s0OPKijuvA6cHeNfNWeZHcCdj45HOzsQsFSa
+        wApD5UnnhrzhLuygh0VY5fvZo5dins8OXidw0itWUgXTEx7bTza0PoYJhgUIA0LK1gsm/dSxHGbl
+        FU5Hu45pbQWxEa4zSec9Se6YTjscGhKr/5uSbmrbd9zGm/Pai9glh53ax71aqXgHvb7TUickwlen
+        C9kbWq/7BDVzk45GUUAYsgvSi4bimzSSgoV2VUsjQ6ViER+RkE8mI2VL2gxrNvq3an3ih5ZC9Oyz
+        38XrUuHPwB8PwB30nj2zO9wluFRWhTrvdxZTDOwaTLArjenZ7n734RcAAAD//wMAvH/zPXYFAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9e89b8ab13aa6-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:00:06 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '19886'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.351s
+      x-request-id:
+      - 3276bb0cfa73c4b663d9cbc978df06d8
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"Meditations
+      | Books to Scrape - Sandbox Books to Scrape We love being scraped! Home Books
+      Philosophy Meditations Meditations \u00c2\u00a325.89 In stock (1 available)
+      Warning! This is a demo website for web scraping purposes. Prices and ratings
+      here were randomly assigned and have no real meaning. Product Description Written
+      in Greek, without any intention of publication, by the only Roman emperor who
+      was also a philosopher, the Meditations of Marcus Aurelius (AD 121-180) offer
+      a remarkable series of challenging spiritual reflections and exercises developed
+      as the emperor struggled to understand himself and make sense of the universe.
+      Ranging from doubt and despair to conviction and ex Written in Greek, without
+      any intention of publication, by the only Roman emperor who was also a philosopher,
+      the Meditations of Marcus Aurelius (AD 121-180) offer a remarkable series of
+      challenging spiritual reflections and exercises developed as the emperor struggled
+      to understand himself and make sense of the universe. Ranging from doubt and
+      despair to conviction and exaltation, they cover such diverse topics as the
+      nature of moral virtue, human rationality, divine providence, and Marcus'' own
+      emotions. But while the Meditations were composed to provide personal consolation
+      and encouragement, in developing his beliefs Marcus Aurelius also created one
+      of the greatest of all works of philosophy: a timeless collection of extended
+      meditations and short aphorisms that has been consulted and admired by statesmen,
+      thinkers and readers through the centuries. ...more Product Information UPC4f19709e47883df5
+      Product TypeBooks Price (excl. tax)\u00c2\u00a325.89 Price (incl. tax)\u00c2\u00a325.89
+      Tax\u00c2\u00a30.00 Availability In stock (1 available) Number of reviews 0
+      Products you recently viewed The Nicomachean Ethics \u00c2\u00a336.34 In stock
+      Add to basket Run, Spot, Run: The ... \u00c2\u00a320.02 In stock Add to basket
+      Critique of Pure Reason \u00c2\u00a320.75 In stock Add to basket At The Existentialist
+      Caf\u00c3\u00a9: ... \u00c2\u00a329.93 In stock Add to basket Kierkegaard: A
+      Christian Missionary ... \u00c2\u00a347.13 In stock Add to basket Proofs of
+      God: Classical ... \u00c2\u00a354.21 In stock Add to basket\"\"\" Using the
+      above text, answer the following question: \"What is the price of the book?\"
+      -- if the question cannot be answered using the text, summarize the text."}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2513'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SQz0rDQBjE7z7FMudNSPonrXsTvYh4EUWslbLdfG3WJvvF7BcQSi6+im+iLyYB
+        tddh5jfDHOFLGLjKimvaOllcPzy+VSSHfEWr+mYf+4urVV/cXT5FaaHB21dy8ptIHTdtTeI5QMN1
+        ZIVKmLxYzopZXuQTjYZLqmGwbyWZpvNE+m7LSTbNcmj00e4J5oi246aVjfCBQoSZZwuNE/tfzxca
+        wmLrk3MyGzRcxd5RhHk+oqH4R+24JhjYGH0UG2TcyEEojPvvK1Jt5x0p3impSG2ZD2qNWyq92LE2
+        rqF8VN8fX5+Tebo8TzFo7Hzwsdp0ZCMHGETh8RYfSnqHyYaX4ewHAAD//wMAOjJCwlMBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9e93b3d3f3aa6-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:00:13 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '1488'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89406'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 396ms
+      x-request-id:
+      - bedfb6b35a4e92788980583f517796cd
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"The
+      price of the book \"Meditations\" is \u00c2\u00a325.89.\"\"\" Using the above
+      text, answer the following question: \"What is the price of the book?\" -- if
+      the question cannot be answered using the text, summarize the text."}], "temperature":
+      0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '344'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOwU7CQBRF935Fc9fTprW04Gw1GBfGjaiJGjJMH3SknVc6D0VIv8Y/8csMieL2
+        JPfcc4CroGFrI7btmnh8M3vsr2YPm7wo8o/NPuP99HP3Xk/vrp8uocCLN7Lyu0gst11D4thDwfZk
+        hCrorJyMylFWZrlCyxU10Fh1EudJEcu2X3Cc5mkGhW0wK4I+oOu57WQuvCYfoMtU4V99wlmpICym
+        OZFxOSjYmp2lAP18QEvhz9lzQ9AwIbggxsuxkL2QP9bf1xR1vbMU8TKSmqIF8zp6wS1VTszxNbwg
+        ciH6/jovkslFgkFh6bwL9bwnE9hDIwh3UHC+oh10OrwOZz8AAAD//wMAxARqv08BAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9e94588453aa6-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:00:15 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '1360'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89929'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 47ms
+      x-request-id:
+      - 2b7378cbb7d7fc9fffc316d4318d2f1e
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book.\",\n        \"reasoning\": \"The task requires
+      me to visit a website and find the price of a book. The browse_website command
+      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
+      command to visit the website\\n- Find the price of the book\\n- Write the price
+      to a file named browse_website.txt\\n- Use the task_complete command to complete
+      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
+      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Error: Service /home/ntindle/.wdm/drivers/edgedriver/linux64/113.0.1774.50/msedgedriver
+      unexpectedly exited. Status code was: 127"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The browse_website command failed. I will try using the get_text_summary command
+      to find the price of the book.\",\n        \"reasoning\": \"The browse_website
+      command failed, so I need to try a different command to find the price of the
+      book. The get_text_summary command can be used to find text on a website.\",\n        \"plan\":
+      \"- Use the get_text_summary command to visit the website and find the price
+      of the book\\n- Write the price to a file named browse_website.txt\\n- Use the
+      task_complete command to complete the task\",\n        \"criticism\": \"I need
+      to ensure that I am accurately finding the price of the book and writing it
+      to the correct file.\",\n        \"speak\": \"The browse_website command failed,
+      so I will use the get_text_summary command to find the price of the book.\"\n    },\n    \"command\":
+      {\n        \"name\": \"get_text_summary\",\n        \"args\": {\n            \"url\":
+      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command get_text_summary returned:  \"Result\" : The price of the
+      book \"Meditations\" is \u00a325.89."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6746'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7yTTY7bMAyF9z0FwbVtxJOfJj5A0Sxm10EWdWEoMmOrsSVDopMUgU/Tm/RkhWJ7
+        EngGaLvpUiT19D2SuqLKMUFZCpZ1U4Ufty87Xqx36/jTKT65eXyK2wsfSlrkz58xQLP/TpKHG5E0
+        dVMRK6MxQGlJMOWYxKv1YrWIV/EywNrkVGGCRcPhPFqG3Nq9CWfzWYwBtk4UhMkVG2vqhjM2R9IO
+        k3ixiQO8i78mnmbLANmwqO61q82qC1CWRklymHy9Yk1uFLamIkxQOKccC80e02gm7S1cUw0AkCKX
+        pi1KdikmMASHBF3YB1PcQilOBAfT6hy4JGiskgTmcDvsjTlGsIWzqirQ5gxnq5hAMbABAQdVEWhR
+        Uw57a86OsjPtnWKK+MJRisHjm5aEM1rp4m8fhtYpXdyOBXHmmTPX1rWwP0CauhY692yaKPc4Pdpd
+        6d8Jm0roHi6E3UTtkevPymmqQ3hxvQALd8yGodNI7kVeY2PVhEdaxUoqV48dG62Sdq311wTDFkR9
+        8z72ShprSfK9C49BTz217RoSx/+wDf2bXTBu59CJN8vpJXqcm37GJvPSE2phi+le9wlfe5d4ZzaP
+        OtPv8OXdgadpis+UKxb+1zp/BOXg18+nZbTevFq72RtcprrDLsCD0sqVWb/7mKBj02CASud0wWTW
+        fes+/AYAAP//AwC6UMqJqgQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9e951feb23aa6-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:00:31 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '15888'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86466'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.356s
+      x-request-id:
+      - 91999ea282fe74300a6fe0997f47d86d
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
index 742fd1de..d744b2ef 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
@@ -442,4 +442,505 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
+      Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
+      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
+      GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
+      \"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
+      \"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
+      str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
+      \"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
+      \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
+      Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
+      access for searches and information gathering.\n2. Long Term memory management.\n3.
+      GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
+      Evaluation:\n1. Continuously review and analyze your actions to ensure you are
+      performing to the best of your abilities.\n2. Constructively self-criticize
+      your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
+      to refine your approach.\n4. Every command has a cost, so be smart and efficient.
+      Aim to complete tasks in the least number of steps.\n5. Write all code to a
+      file.\n\nYou should only respond in JSON format as described below \nResponse
+      Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3467'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7STz27TQBDG7zzFaC65OFFC2iT1ExCEWqAFhDCytuuJvcTeMbvjJijyuyP/SdIY
+        9QScVppv5pvf7M4e0CQYos6U6KLMx8v1/e2T0p/f36YfVh/5/m579fbu3fRhtf6qPAbIjz9IS18x
+        0VyUOYlhiwFqR0oowXC2WF0t5vP5chZgwQnlGGJayng+uR5L5R55PJ1PZxhg5VVKGB6wdFyUEgtv
+        yXoMl8tFgGfvU/z17DpAYVH5KXRzM6sD1BkbTR7DbwcsyB9tHeeEISrvjRdlpYFkK2SbAQ6RBQCI
+        UDKu0kx8hCH0wV6gvTTBCNewM3kOlSeQjGDnjFAsHG9MTqC5KJRNQLgTYPSG8pzhC7s8GYGxwqCg
+        TbWqoARGWaPHu0afyF5GkwiD540dKc/W2LTr/pARiPJbcPSzMo48FPQX3QJoaV+cw/hWLNgLqLJ0
+        XDqjhGDDDiRrVOW3Q+QyV7ajHcOn/3ZNkT27NxRxvyQX7qfYMWvIqp0Ro40vjo9ridpKsr5yTZ0S
+        WEOmnjoPzc6RljNbf4FKWrkNGw/9/oOxF1WJaQ52v4YYviS1fXm/GqB/t19d4zo4Ln1v+sfONw4d
+        08XrDdCVS4ffpROa3LPFgOPCZPjFns10pG2Je/DI1lgHuDHW+CzuPgiG6IVLDNDYhPYYTuvv9avf
+        AAAA//8DANPpphvSBAAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca920092efb0c34-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:43:08 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '17065'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86497'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.335s
+      x-request-id:
+      - 90577bd1f9895f3d042b1a9287fa5f73
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
+      Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
+      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
+      GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
+      \"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
+      \"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
+      str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
+      \"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
+      \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
+      Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
+      access for searches and information gathering.\n2. Long Term memory management.\n3.
+      GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
+      Evaluation:\n1. Continuously review and analyze your actions to ensure you are
+      performing to the best of your abilities.\n2. Constructively self-criticize
+      your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
+      to refine your approach.\n4. Every command has a cost, so be smart and efficient.
+      Aim to complete tasks in the least number of steps.\n5. Write all code to a
+      file.\n\nYou should only respond in JSON format as described below \nResponse
+      Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I will use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
+      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
+      command is the most appropriate for this task.\",\n        \"plan\": \"- Use
+      the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\\n-
+      Use the task_complete command to complete the task.\",\n        \"criticism\":
+      \"I need to ensure that I have the correct file name and that the file is created
+      in the correct directory.\",\n        \"speak\": \"I will use the write to file
+      command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4790'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6ySTW/TQBCG7/yK0Vxy2UQJIWnwEYlCqkpFUIRUjKLtehIvWe+Y3TFJFfm/I8fO
+        R4OQkOA6H+88M/Pu0GaYoMm1mKJ0/av5p7vr+7fTh+ub4c3dx3e3byrzYaZ5ph+eblEhP34nI13H
+        wHBROhLLHhWaQFoow2Q0nb2ajsfj1yOFBWfkMMFVKf3xYNKXKjxyfzgejlBhFfWKMNlhGbgoZSG8
+        Jh8xGQ0nM4Un8VNicqVQWLQ7hV6OJrVCk7M1FDH5usOC4kE4sCNMUMdoo2gvDSZ7Id+ssEs9AECK
+        knO1yiWmmEAX7BK0lSaY4hw21jmoIoHkBKLjetEBEhguCu0zEIZj7FA1SFGdSwbSkb31q1b3viuD
+        QD8qGyhCQY3OJlgh6L0n5xi+cHBZD6wXBg1L6wi8LiiDXt7kF5smP5Ct9BQ0HHPI9U+CWBlDMS4r
+        556OYBlIbmOLBvc5BVpyIAVzMNr/h/1Kp327Wh8+/7OaCVassbE4fMET7TvJxyo0fVr2ze1ZYcmh
+        PefJPGAj6LIMXAarhS4nxJL0+o8/hr+lbiVrdbBUV/6bo5q/tdOeHeUCSofVpRnP3dNZ55wve/bt
+        I9AeqmNLfY21wqX1NuaLVgkTjMIlKrQ+oy0mw/pb/eIXAAAA//8DAKgaLA4VBAAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca920871f130c34-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:43:24 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '13071'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86478'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.348s
+      x-request-id:
+      - 137423c120d49f49824a2fbbd7cbb558
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3393'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7yTT2/TQBDF73yK0Vxy2URJ0/zBRyoBEQL1UIQKRtHWnsRLdnfM7phEivzdK9tJ
+        2hpxQnCdN37vN7PjI5ocE8wKLZkr7XCxuru9f1PZ6+qde6tvPn74db843Mw+XX3d21tUyA8/KJPT
+        F6OMXWlJDHtUmAXSQjkmk/nyej5dTCdzhY5zspjgtpThdDQbShUeeDiejieosIp6S5gcsQzsSlkL
+        78hHTBazpcIn70v9ajxWKCzaXkqvZ8taYVawyShi8u2IjuLZNrAlTFDHaKJoLw0keyHfDHBMPQBA
+        ilJwtS0kppjAqXgS6CBNMcUVeKIchKGKBFIQ7IMRWguvN8YSZOyc9m1DK8DgPVnL8IWDzQdgvDBo
+        aFu9dpTDoGj09b7RR3KQwShF9Tw7kI7sjd92AHcFgei4g0A/KxMogqO/SFPQ0v5xDhNb0XEU0GUZ
+        uAxGC8GGA0jRqDru+sil1b6jHcLn/7SmLBgxmYmu/07kYxUaBi2wurxaxiFQJm1Ek9CtgQ7yhCTc
+        djYd/bBYkt6dg/bG2n95DV1wrc5XejL97Ugbh47pBUQPXYdt/7474byJzqLH8cKk/088m+lM2xKf
+        wFNfY61wY7yJxbo7Z0wwCpeo0PicDpiM6+/1q0cAAAD//wMAx8X8+IMEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9805e4d7328e0-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:48:51 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '14375'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86497'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.335s
+      x-request-id:
+      - dd442d3790e304394237402085fd3bc5
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
+      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
+      command is the most appropriate for this task.\",\n        \"plan\": \"- Use
+      the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
+      \"I need to ensure that I use the correct filename and text to write to the
+      file.\",\n        \"speak\": \"I will use the write_to_file command to write
+      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4637'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7RSwY4SQRC9+xWVunAZCOzILpmbFyOHTUwWo0YM6e0pZlp6utruGsAQ/t00zMi6
+        sheN13qvXr3X/Q5oSixQ10p04+3wbr547x+mn+/X929pnHPc3dWfHt5ow7Npgxny4zfS0m2MNDfe
+        khh2mKEOpIRKLCa3s9e3+V2e5xk2XJLFAisvw3w0HUobHnk4zscTzLCNqiIsDugDN15WwhtyEYvJ
+        +Gaa4UX8AszyDIVF2cvoZjw7ZqhrNpoiFl8O2FDshQNbwgJVjCaKcpJsshNyKcJh6QAAlig1t1Ut
+        cYkFdMMOoL2k4RLnUKstQWy1phjXrbU/YBeMCDkYvCNrGT5ysOUAjBMGBWtjCZxqqIRBnfDVLuEj
+        2ctgBIuawNFeIAp5MBGEoY0EUhOIiptVF55Ac9MoVybCr1nPGi0xe2o3kIrsjKvOnhcdDQJ9b02g
+        CA1d1QG1FgqnPMZV1/IkZkqUwcnLiy5Tkpqg4SigvA/sg1FCsOYAUif0im1vlTs7HsKHf34EnVJo
+        E5v+4xzRaZNcbEPaUwJz8IG3piRQsFXWlHB+u5PRvniuevFI9KQ2/YGdsfbvfu8secz6Inb0P3qY
+        enS+9pv8M1MqVM8r/LQX/6PIfYRTjC7N0h3xmOHaOBPr1fk2FhiFPWZoXEl7LMbHr8dXPwEAAP//
+        AwCEJsUGfQQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca980c86e2128e0-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:49:08 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '14391'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86481'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.346s
+      x-request-id:
+      - 7efa7a4b949a3c79b750abf348c98545
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index ad26e524..c743a418 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -14,7 +14,1019 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
+      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
+      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
+      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3360'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4RSTW/aQBC991eM5rwgECG4vkWJVKFIvaT0kLpCy3qwN9i77s5YoUH+79ViTCqo
+        0uubmfcxMwe0OaZoSi2mbqrR4svz0/5r8nZ/f7uSp/rxYXf3/P1tKbJa3j2gQr95ISOnibHxdVOR
+        WO9QoQmkhXJMp7fJzTSZfZ7NFdY+pwpTLBoZzcbzkbRh40eT2WSKClvWBWF6wCb4upG1+B05xnRx
+        kyh85z7j09lCoXjR1RlKknmn0JTeGmJMfxywJh5og68IU9TMlkU7iSa9E3IxwCFzAAAZSunbohTO
+        MIUTeCrQXiKY4RK49G2VA4sOApvfEEjn1hUgJYF1LKE10Sqvp2PZC2xtRdDy0BG710fM+LrWLh9n
+        qP6WCqTZO+uKXu9bSbC1gQVYqAHLIB5al1OIOfIrVYjga6kltgb61dpAOfgt1HSp1FTa9SIjWDH9
+        216Ui+BH8S6JTbBijeV6WJkjOhKR4zZEIS2w/DDFhrY+EDTBG6K43ksNbkjvBv5XW1X/P8jgtafp
+        1HD1U9KroztdU69w3sqFCR2Ky1/pC7H3ffx6bYOJo5GTn8x12CncWme5XPdvgCmy+AYVWpfTHtNJ
+        97P79AcAAP//AwDMcPMmqgMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e437aafbd3132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:24 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '8955'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86494'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.336s
+      x-request-id:
+      - d9ff235826db175c96d70ad1ed0ece57
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
+      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '599'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOUUvDMBRG3/0V4XtOR7tuzuVNEMQXEZyIiowsvWujbW5M7pg4+t9lMN3rgXM4
+        B/gGBq6z4obYF4vb19Uy1c+rh5zar/tHmm93w8/102Kabl6gwZsPcnIyJo6H2JN4DtBwiaxQA1Nd
+        Xs2qq3o5W2gM3FAPgzZKUU/mhezShouyLito7LJtCeaAmHiIshb+pJBhllONc/qMNYTF9v+gKqtR
+        w3XsHWWYtwMGyn/NxD3BwObss9ggx0MOQuF4f6f2NqvTsbKhUYGl86FVgfaqs1l1NkYK1Ewwamx9
+        8LlbJ7KZAwyycISGDw19w5Tj+3jxCwAA//8DAAI6aHtJAQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e43c3299e3132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:28 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '815'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89866'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 88ms
+      x-request-id:
+      - de6bee68ce2cb0df386f2ec71b499901
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
+      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
+      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
+      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created and nothing new
+      has happened."}, {"role": "user", "content": "Determine which next command to
+      use, and respond using the format specified above:"}, {"role": "assistant",
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
+      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
+      \"The first step is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4408'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SSQYvbMBCF7/0VYs5ysNfpNutbeykLhUJJLluXIMtjW408MtKYDQ3+78Wxs2md
+        Uhb2+mbmvW+kOYEpIQPdKNZtZ6MPn5+2H9XXT7unx+0u/fLrEMdYbb75IglJARJc8RM1zxMr7drO
+        IhtHIEF7VIwlZMn9Zp1s0of1RkLrSrSQQd1xlK7eR9z7wkVxGicgoQ+qRshO0HnXdrxnd0AKkD3c
+        JxKu3i96sr6TwI6VvUpJnA4SdOOMxgDZ9xO0GC6+3lmEDFQIJrAiHikdMdK4wSknIYTIgRvX1w2H
+        HDIxi3MBjzyKOTwKQiwFO+FRlYIbFIYC+16PgGF/t+Iji8pYFH0wVJ87xtb9WdOubRWVqxzkn/4e
+        VXBkqJ5Ctv9xHbGVoSCq3nOD/q9GwY1icWWsnLXueZnWWUVTUCR2Af+N+JoVl8baGzbahHb5Vkih
+        93ih66lEP37DrbkosHIeReedRiwN1cuM0KE6XPyfjbVv/YjJfJCXI5grNzdAqsUp98VlgaZ8vTyd
+        qTD2XsdvMS8QZ5CZJ6cBBgmVIROa/XQgkEFg14EEQyUeIYuHH8O73wAAAP//AwBQh5C9ugMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e43cb8d2c3132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:38 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '10025'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.35s
+      x-request-id:
+      - f3965dabcf1a56d3abe0b97dd37818a9
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
+      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '713'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPXUvDQBBF3/0VwzxvSmJqW/etFJRSfBD8qiJlm4xN7GZn2ZlapeS/S6Ha18u9
+        h3MP2NZosWqcVl302fj29eFuG++f3OOikPFyMZu+xNnz8kY2RYkGef1JlZ4Wg4q76ElbDmiwSuSU
+        arTFaDIsJuX1KDfYcU0eLW6iZuXgKtNdWnOWl3mBBnfiNoT2gDFxF3WlvKUgaIvL3OCZ/Z8fY2V1
+        /twc5r3BquG2IkH7dsCO5I+a2BNadCKtqAt6dOSgFI7+UwEH8iNKnYE5JKqc96CNU5jD3gmc7oAL
+        NWhDiaBxXwRrogCBIdAeavoiz7GjoALKkChy0gH2Bj/a0EqzSuSEA1oU5YgG21DTN9q8f+8vfgEA
+        AP//AwCDczclewEAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e441959f03132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:42 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1498'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89839'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 107ms
+      x-request-id:
+      - 61ac2d72f5c8a08789008f8ad509a4f1
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
+      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
+      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
+      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that I was
+      created and there have been no new developments to report."}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file using the read_file
+      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
+      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5368'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SSUW/TMBDH3/kU1j27VdNu3ZK38TAGEgKJIqQtqHKdS2LmnCP7wipV+e4oTUIg
+        RQiJ17vz7/+zfScwGSSgS8W6qu3i5s3j7sOX+OF++3hXvd++bh7ud/ndx0/rOH73HSS4wzfUPJxY
+        alfVFtk4Agnao2LMIIm2t1fR7SberiVULkMLCRQ1LzbL6wU3/uAWq80qAglNUAVCcoLau6rmPbtn
+        pABJFF3fSJjgU+NqLYEdKzuV1nHcStClMxoDJE8nqDCMYO8sQgIqBBNYEXeajhipu8IpJSGESIFL
+        1xQlhxQSMRSHBh65K6bwVhBiJtgJjyoTXKIwFNg3uhMM+82SjyxyY1E0wVBxnuhG9+eadlWlKFum
+        IH/le1TBkaGiD9n9hdppK0NB5I3nEv1vg4JLxWJyzJ217mWeVltFfdBCfA74Z8V/ueIcrL1ho02o
+        5m+FFBqPo11DGfruGy7h4oC58yhq7zRiZqiYZ4Qa1fPIfzHW/u9H9PBWjkswdC52gFSFfe5PykxN
+        +WK+On2jm52OX2qOEmeRwSelFloJuSETyn2/IJBAYFeDBEMZHiFZtV/bVz8AAAD//wMAarkDSrsD
+        AAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e44259b713132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:52 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '9839'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86463'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.358s
+      x-request-id:
+      - d620e6b69245523ab217d979b4e6b8c5
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nAs a system, I recall that I was created and there have been no new developments
+      to report.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '761'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPyUoDQRRF935FcdfVIW1nsnZBQQ2CGxcOSKhUv6TLdA32e8HE0P8uESXbA/dw
+        7hG+hoFrrLiQ22J6+/pkXyafD9/0eMnzcbh+3tZ368VifzP30EirD3Lytxi4FHJL4lOEhuvICtUw
+        5WQ2KmfV1XSkEVJNLQw2WYpqMC5k161SMayGJTR2bDcEc0TuUsiylLSlyDBlVWqc3Wc+1pAktj2T
+        0aTXcE3yjhjm7YhA/G/tUkswsMyexUY5NaYoFE/9c1ZW8YGFglb3qiNn21ZJY0XFJI2PGxXpSzWW
+        VWNzpki1Yh8dqXBQv1d9igP0GmsfPTfLjiynCAOWlKHhY017mGH/3l/8AAAA//8DAIp+DXNmAQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e44729ae33132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:52:56 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1279'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89827'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 115ms
+      x-request-id:
+      - 108cd79db4a91eae5537da9b33f492bc
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
+      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
+      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
+      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that nothing
+      new has happened since my creation."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file using the read_file
+      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
+      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to read the instructions_3.txt file using the read_file command.\",\n        \"reasoning\":
+      \"The instructions_3.txt file contains further instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file using the read_file command.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6279'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6yST2vcMBDF7/0UYs7yYtcbJ9G9lIUWAt0W2joYrTyxlZUlVxonC4u/e/GfxYlL
+        D6G9vqeZ95P0zqBLEKBqSappTXT98cdeffpw/G4Od9nTgT7ffdmfnh53WWy+3QIHd3hERfPERrmm
+        NUjaWeCgPErCEkSS3WyTm/T2OuPQuBINCKhaitLNVUSdP7goTuMEOHRBVgjiDK13TUsFuSPaACJJ
+        twmHZfliZCkHciTNIl3F256Dqp1WGED8PEOD4bLYO4MgQIagA0lLA6azhHa4wjm3jDGWA9Wuq2oK
+        OQg2i7OBJxrEHHbMIpaMHHv2mpBRjYxkOBa6ZNqSGwXXUdvRhk7EHrRB1gVtq9EZhwpyxagr1zTS
+        lpsc+Ms0jzI4q201Re5rZNoG8p0aHiEwj7867ZE1+DaOdU5rpJ0iIvY14N8B/y1GeU1a6dCsXxBt
+        6PywUxLbvQhQzntU9Oag0KI8XkKetTH/94+mqJ5f2jI7f5TFygYnilebVrDSV+ueTcZwdlmxYL6a
+        X9fyfZpsL4Qj5Qyb2x56Dg/a6lAXU7FAQCDXAgdtSzyBiPv7/t1vAAAA//8DALNiCnsBBAAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e447bcfeb3132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:53:07 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '10958'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86469'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.354s
+      x-request-id:
+      - 27a8792867dc32731b494d23250a8aec
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
+      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '740'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPTUsDMRRF9/6KcNeZ0rHf2SmCWHBTKoIiJc08m+jkg3mv2lLmv0tF6fbAPZx7
+        Qmhg4LwVF0tbze5f1mV2eAzxdtktj9PV13h1mKyX5flpdgeNvP0gJ3+LgcuxtCQhJ2i4jqxQA1NP
+        5+N6PlrMFxoxN9TCYFekGg0mley7ba6Go2ENjT3bHcGcULoci2wkf1JimPp6qnFxX/hEQ7LY9kLG
+        da/hfA6OGOb1hEj8b+1ySzCwzIHFJjk35iSUzv03rKziIwtFrR5UR862rRJvRaUsPqSdSvStvGXl
+        bSmUqFEckiMVj+r3ashpgF7jPaTAftOR5ZxgwJILNEJq6AAz7N/6qx8AAAD//wMAecEeqGYBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e44cdfcc83132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:53:10 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1138'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89832'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - f0b536a2bcc40f0b21989941177bcbad
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
+      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
+      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
+      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that nothing
+      new has happened since my creation."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file using the read_file
+      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
+      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to read the instructions_3.txt file using the read_file command.\",\n        \"reasoning\":
+      \"The instructions_3.txt file contains further instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file using the read_file command.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to write the task_id into the output.txt file
+      using the write_to_file command.\",\n        \"reasoning\": \"The instructions
+      require me to write the task_id into the output.txt file.\",\n        \"plan\":
+      \"- Use the write_to_file command to write the task_id into the output.txt file.\",\n        \"criticism\":
+      \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
+      \"I will write the task_id into the output.txt file using the write_to_file
+      command.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7262'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5ySy27bQAxF9/2KAddjw4YfibXLqnBRtCjaAEWqwBiPKGni0VAZUnEKQ/9eyJZj
+        x23Rx5YE7z2X5A5cBgnY0oitaj+4env35TF/WnwkfKintx8+bT6/n83ePU3vljdfQQOtH9BKPzG0
+        VNUexVEADTaiEcwgGc+vp+PryWIx0lBRhh4SKGoZTIazgTRxTYPRZDQGDQ2bAiHZQR2pqmUltMHA
+        kIxn07mGk/hZY6xBSIw/leaLq1aDLclZZEi+7aBCPgpH8ggJGGbHYoJ0mBQEQxdhlwallEpBSmqK
+        UjiFRPXFvoHP0hVTWKrSPKHqmTBTxnslJSoxvGEV8bFxETNFuapwqJaKS2p8pgJtFZeNqIy2QTXs
+        QvEytjqqdbKVCdkwBX1uH9EwBReKVww5eU/bMwQXWGJju02xMiH7W8oLt9qbcDAaqFvG32MqoVOm
+        SxUbnTjruDoyB8T9BAZuYqdqRP1hm2vMKeLeQ7qF/cqHazSb/7zN1nn/z5c5mLf6+DR956efCabC
+        A9crpQt8E4vLdzu/+UHgpsuxz3DKxo21yJw33n9/odqT9YBpaKHVkLvguFwd5CABFqpBgwsZPkMy
+        au/bNz8AAAD//wMAqcemK/wDAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7c7e44d668223132-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 15 May 2023 20:53:21 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '10500'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.35s
+      x-request-id:
+      - 3e4b1ed00d4d2de4b39db61f42246015
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
       get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
@@ -49,7 +1061,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3284'
+      - '3286'
       Content-Type:
       - application/json
     method: POST
@@ -57,20 +1069,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4RSS2/TQBC+8ytGc7ajOKFJ8K0IAQWJA2q5YBRt7LG9dL3r7oxpQuT/Xm0cpyip
-        yvWbx/eY2aMuMMW8VpI3rYmXH/lLeftjd/3tQ1Ju33cru/jz9fvd52L28GmGEbrNb8rlODHJXdMa
-        Eu0sRph7UkIFpsli9XaarKaLZYSNK8hgilUr8XxyFUvnNy6ezqcJRtixqgjTPbbeNa2sxd2TZUyX
-        s3cRPu8+4cnVPEJxoswJWq1mfYR57XROjOnPPTbE41rvDGGKilmzKCtBpLNCNhjYZxYAIEOpXVfV
-        whmmcASPBdpKADO8Aa5dZwpgUV5gswNPqtC2AqkJtGXxXR6k8jqZyFag1Iag47EjdK8PWO6aRtli
-        kmH0L5Unxc5qWw18tzVBqT0LsFALmkEcdLYgH3wUF6wQwMdaSWj19NBpTwW4Eho6Z2qNsgNJDHdM
-        L8sLdAF8zV6W2RiurTK7v/SyoIKEfKPtULa0HezwmaLca9G55mbM2hIdFJDlzodhJXADZWfM7tUQ
-        NlQ6T9B6lxMN13Fn1OdpcEvqfuR91Mb8/8IH85MMhzV9NL7RMbqLL7KqoYHhFPOZCOWr8+cbCqH3
-        efzyDqOIg5Cjnsz22EdYaqu5Xg9/hSmyuBYj1LagLabT/lf/5gkAAP//AwDiG6xl+wMAAA==
+        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCMsFUt+iSJWoeomU9lJXaFiP7S3rXXd3nEAR/73aGEgL
+        FZde5+t93pnZo66wQNWSqK436WL59LhYh8/t42x3/5Wz2cPDz2yg54/5p/wZE3TrH6zk2DFRrusN
+        i3YWE1SeSbjCIpvfvZ/ni3yWJdi5ig0W2PSS5pNZKoNfu3SaTzNMcAjUMBZ77L3relmJ27ANWCzy
+        aYJvs8/xbJ4lKE7InEN3H7JDgqp1WnHA4tseOw6nsd4ZxgIpBB2ErERIZ4VtNLAvLQBAidK6oWkl
+        lFjAMXhM8FZisMQlhNYNpoIg5AXWO/BMlbYNSMugbRA/qIgaVtlEtgK1NgzioGJh32nL8NKSAI1F
+        MSO0YbC8lUmJyZ+qnik4q20zSj/dEIhmSMd5bZylonO/A21r5zuK5X8zjGVbgSDch0vh3pAdNVP4
+        EsbqaHN11Oo6slUcGIO3jJelTeHektn94qu6W0QXQMpr0UqH7nQEy/wKwDYMPjaTwBKog9oZ417+
+        dQ8gpQZPwmYHEZ/rWivNVszu0n/omTYnqRdtzH9c+2rTo9AhOT3dcZ1XP2ep45HhvPoLTPLN5auO
+        iVj71n6NeYJ4BTnylPaAhwRrbXVoV+PrYYFBXI8JalvxFovp4fvh3W8AAAD//wMAa4jrZSkEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e71f9cbf01ca8-SOF
+      - 7ca981339872aa10-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -80,7 +1092,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 22:47:59 GMT
+      - Sun, 21 May 2023 02:49:23 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -90,9 +1102,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
+      - significant-gravitas
       openai-processing-ms:
-      - '11444'
+      - '12546'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -104,91 +1116,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86494'
+      - '86493'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
       - 2.337s
       x-request-id:
-      - 7ae25ff182a7c0ffb3574db283d1da70
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
-      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOQWvCQBBG7/0Vy3feSFK1jXtvQRF6aimUIutmNFuTnSUzYqnkvxfB1uuD93hn
-        xAYOofUa+twVj8+y0mNYPK3ljef1Tz/z6/ny/fQaDi8rWPD2i4JejUngPnekkRMswkBeqYGrHupZ
-        WdVlXVn03FAHh33WYjqZF3octlyU07KCxVH8nuDOyAP3WTfKB0oCt7i3uKVv2EJZffcPqrIaLULL
-        MZDAfZzRk/w1B+4IDl4kivqkl0NOSulyvzQnL+Z6bHxqTGJtY9qbRCfTejGtz5kSNROMFruYorSb
-        gbxwgoMoZ1jE1NA3XDl+jne/AAAA//8DACzKsGlJAQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6e7251df381ca8-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 22:48:02 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '889'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89866'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 88ms
-      x-request-id:
-      - f6610e14da3a22deb33c7ea09f53072e
+      - 0fd7ee0fe93ef38d279da345e7367fc6
     status:
       code: 200
       message: OK
@@ -207,7 +1141,7 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
       get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
@@ -236,237 +1170,16 @@ interactions:
       has happened."}, {"role": "user", "content": "Determine which next command to
       use, and respond using the format specified above:"}, {"role": "assistant",
       "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will start by reading the instructions
-      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4413'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4xTS2/TQBC+8ytGc3aiPEib+tYiQOXUQxESGEUbe2IvXc9Yu2OaEOW/o7WTpjgg
-        cbO+mZ3vMeM92gJTzCujed240fWH8Km9ubuezxdPD3fh4wPdvqsf399/3XxZNJigrH9QrscX41zq
-        xpFaYUww92SUCkynV8u3k+lyspwlWEtBDlMsGx3Nx4uRtn4to8l8MsUE22BKwnSPjZe60ZXKE3HA
-        9GaxTPA8+wWfXs0TVFHjztB0Nj0kmFdicwqYfttjTeE014sjTNGEYIMa1qhSWImjg33GAAAZaiVt
-        WWnIMIUjeCzQViOY4WNFwLRVsBzUt3mUBTaACngyBWhFr0thNRvrVmFjHUEbLJddR2xddVgudW24
-        GGeYvCb0ZIKw5bJnvQcmKiLJRpyT5wsasNxh4gvy8WsHxhOU9idxfEYcWk+glVG4h0KARaG2IYDh
-        Hdi6ER9jgaDUhKGYxhnudYzgc6C/O/ifBLKMR3DLxu1+0aWFOKQgJV9b7std0J2kgaLcW7W5DfUw
-        nj99blrndtByQT5u/VIbrGkjnqDxkhMV3XpkQD1MIzRknk68z9Y5YHn+l/XO9jjDfsAhOV3aMbSL
-        Q2NTUz/7JeABvfHl8D77Quw9P7/cwElEJ+SoJ+MDHhLcWLahWvVHhykGlfiLWy5oi+nk8P3w5jcA
-        AAD//wMA+R5NNh8EAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6e7258bcda1ca8-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 22:48:15 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '12253'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86467'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.354s
-      x-request-id:
-      - 1f8b7eec7a22f88981895ea8418351db
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
-      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '713'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJTHG2tn5gSAF68qFImU6eW2mJvOGvFe0lP53qSjdHriH
-        cw+ILRxC5zUMuS+mjzKfKc9F/bBYbx9ile+q5m3x/HL/WsOCV1sK+reYBB5yTxo5wSKM5JVauOr6
-        5qqsbsrZ1GLglno4bLIW9aQpdDeuuCjrsoLFTvyG4A7IIw9Zl8qflASuuiwtzu4zbyyU1fdnUjdH
-        i9BxDCRw7wcMJP/WkXuCgxeJoj7pqZGTUjr134rxRvaiNFjzZEYKvu+Ndl5NYu1i2phEX6bzYjqf
-        MyVqjcQUyAx783s1cprgaLGOKUq3HMkLJziIcoZFTC19w5XHj+PFDwAAAP//AwBdjPuCZgEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6e72b57cf81ca8-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 22:48:18 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1057'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89839'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 107ms
-      x-request-id:
-      - 4ed343ce9db17e267d0da6562c9af456
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      the instructions_1.txt file to determine what actions to take next.\",\n        \"reasoning\":
+      \"The instructions_1.txt file contains the necessary information to determine
+      the next steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_1.txt file\\n- Analyze the instructions to determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I am following the
+      instructions accurately and efficiently.\",\n        \"speak\": \"I will start
+      by reading the instructions_1.txt file to determine the next steps.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
-      the instructions in the order they are given to ensure that I do not miss any
-      important steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_2.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
@@ -477,7 +1190,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5453'
+      - '4463'
       Content-Type:
       - application/json
     method: POST
@@ -485,21 +1198,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4xS32/TQAx+56+w/JxWLYFuyxsTQprQXioQ2shU3S5ucuxiR3cOa1f1f0dJWjpS
-        kHg7ffb5+2Hv0BWYoa2M2rrxk4tP8fP1t4/317fLt3F5t7x/sdXCzuWu8LdPmKA8/iCrhx9TK3Xj
-        SZ0wJmgDGaUCs/ni8t1sfjm7ukqwloI8Zlg2Okmn7yfahkeZzNLZHBNsoykJsx02QepGVypPxBGz
-        +fxiluBp+KmwSBNUUeNPUJqm+wRtJc5SxOz7DmuKx8FBPGGGJkYX1bB2MoWVuLOwyxkAIEetpC0r
-        jTlmcAAPBdpoB+b4pSJg2ig4jhpa28kCF0EFApkCtKLXpbhKp7pRWDtP0EbHZd/Rta56zEpdGy6m
-        OSavCQOZKOy4HFhvgImKjmQt3svzGQ047jEJBYXutQUTCEr3k7j7RhzbQKCVUbiBQoBFoXYxguEt
-        uLqR0MUCUamJYzGNNzzomMDXSH938D8J5DlP4AMbv32hcwvdkIKUQu14KPdB95JGimxw6qyL9Tie
-        P32uW++30HJBodv6uTZ4pLUEgiaIJSr69ciIepxGbMg8HXmfnffA8vwv673taY7DgH1yvLRDaGeH
-        xqamYfbvgEf0JpTj+xwKXe/p+/kGjiJ6IQc9Oe9xn+DasYvVajg6zDCqNJig44I2mM32D/s3vwAA
-        AP//AwCoFi8sIAQAAA==
+        H4sIAAAAAAAAA4ySQW8aMRCF7/0VozkvCLIpJHur1B4QaqVK5NJuhRzvwLqxx1t7VoEg/nvlZQkp
+        iCrXmXnvfWPPDk2FBepaiXaNHUxni+9fbx8+V3Vr5u7my4/7+bd5nt/d/XkZLTBD//ibtPSKofau
+        sSTGM2aoAymhCovx5O52kk/zySRD5yuyWOC6kUE+/DiQNjz6wSgfjTHDNqo1YbHDJnjXyFL8E3HE
+        4n4yzfDk/VofJ0fxouypNM7zfYa69kZTxOLnDh3Fo2/wlrBAFaOJolgSpWchThvsSgYAKFFq365r
+        iSUW0Bf7Bm0kFUtc1ARMGwHDUUKrExaYCOIhkKpAanrbisuboWwEVsbSEGYQa9/aCtpI3WSSLFMP
+        tHdOcfWPTycqMXtLEkhFz4bXJ5wrcZAWVIZj58Wk02uELRhe+eBUBy4eKhIKzjD1YxuBKNTE8+DG
+        Kj5kDuDhXfhXuMqSB/CJld2+0MXc/4jOgHQwYrSJ7kA1AybqAIhjG5JYCcxAOVh5a/2z4fVlnNK6
+        DUrIbiHh02pltCEWuz3fPzakno5Rz8bad37itWMo8eC+z47X16svjo+Vo0Pwa9IZmwrr85s9NNLs
+        SX6JcoToQHqekve4z3Bl2MR6ebg3LDCKbzBDwxVtsBjtf+0//AUAAP//AwC7HghxMwQAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e72bd7c821ca8-SOF
+      - 7ca981943804aa10-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -509,7 +1221,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 22:48:30 GMT
+      - Sun, 21 May 2023 02:49:39 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -519,9 +1231,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
+      - significant-gravitas
       openai-processing-ms:
-      - '11882'
+      - '12905'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -533,94 +1245,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86458'
+      - '86464'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.36s
+      - 2.356s
       x-request-id:
-      - 39cdfabe68f349bf436b0f9f27e465ba
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPy0oDQRBF935FU+ueMG0eht65UBIEEQSjiIROT5lpM1PVTlWiSZh/l4iS7YF7
-        OPcIqQIPsQ4a29wUV7dy93Bwi6fq+TB7nN/Mq81uN/u8Hy0SvYAFXn1g1L/FIHKbG9TEBBZih0Gx
-        Au8m01Hpps4NLbRcYQMe1lmL4WBc6LZbcVEOSwcWthLWCP4IueM261J5gyTg3eXEwtl95mMLyhqa
-        Mxm53kKsOUUU8K9HaFH+rR03CB6CSBINpKdGJkU69V+LCUb2othaMzcdxtA0RuughljrRGtD+GXq
-        IKYOOSNhZSRRRNPuze/VxDSA3sJ7oiT1ssMgTOBBlDNYSFThN/iyf+svfgAAAP//AwCOX/o2ZgEA
-        AA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6e731898091ca8-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 22:48:34 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1076'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89832'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - fcc155dfdde6eac2ead0dd975dc269d1
+      - a4e14f0652013c53af07d6d7cdc9463d
     status:
       code: 200
       message: OK
@@ -639,7 +1270,149 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that I was
+      created and there have been no new developments to report."}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I should use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5544'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4ySQY/aQAyF7/0Vls8BQbMLq9x6aCvUy1aip6ZCw8RJpkw8YcbRQlH+ezUQli2I
+        aq+233ufZ3xAU2CGulaim9aO5ovld/312/OkfNh2dr3ZTb5sn9Pl9nOl1lNM0K1/k5ZBMdauaS2J
+        cYwJak9KqMBsOnt6mKXz9Oljgo0ryGKGVSujdPw4ks6v3WiSTqJZF1RFmB2w9a5pZSVuQxwwm06f
+        5glezC+N2SxBcaLspZQ+pn2CunZGU8Ds5wEbCmdj7yxhhioEE0SxREzHQhxXOOQMAJCj1K6ragk5
+        ZjAUhwbtJBZzXNYETDsBw0F8pyMWmADiwJMqQGp62wqrdCw7gdJYGsMCQu06W0AX6DgZJavYA+2a
+        RnHxj89RlGPylsSTCo4NVxecO3EQF1SGw9GLScfX8HswXDrfqCO4OChIyDeGaRjbCQShNlwHt1bx
+        KXMEP96Ff4crz3kEn1jZ/R+6mfsf0RWQ9kaMNqE5US2AiY4AxKHzUawEFqAaKJ217sVwdRuntO68
+        ErJ7iPhUlkYbYrH76/1DS2pzjnox1r7zE+8dQ44n9z45X9+gvjk+Vg2dgl+TrtiUr65v9tSIsxf5
+        LcoZ4ggy8OTcY59gadiEenW6N8wwiGsxQcMF7TCb9L/6D38BAAD//wMA4kH/FDQEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca981f6cdeaaa10-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 02:49:56 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '13771'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86449'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.367s
+      x-request-id:
+      - 7274eefc2f8ca180d18d471f1f234e01
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
       get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
@@ -668,43 +1441,43 @@ interactions:
       new has happened since my creation."}, {"role": "user", "content": "Determine
       which next command to use, and respond using the format specified above:"},
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I should use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The next instruction is to read the instructions_3.txt file. I should use
+      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\r\nShutdown"},
       {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
-      the instructions in the order they are given to ensure that I do not miss any
-      important steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_2.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
-      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
-      the instructions in the order they are given to ensure that I do not miss any
-      important steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_3.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will now read the instructions_3 file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -713,7 +1486,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6486'
+      - '6578'
       Content-Type:
       - application/json
     method: POST
@@ -721,20 +1494,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5SSQWvbQBCF7/0Vy5zXRqqdxOgYSCANlLq00FIFs1lNpK1XM8ruqHYx+u9Fll0n
-        CqX4+mbnvW+WtwNXQAa2MmLrxk+ubuP98uO1XV5fLdf+2423n79/ev71fP+hwt+ggR9/opXDxtRy
-        3XgUxwQabEAjWECWXi7mSbpI07mGmgv0kEHZyGQ2vZhIGx55ksySFDS00ZQI2Q6awHUjK+E1UoQs
-        nS0SDSfz0+Ay0SAsxp+ki3nSabAVO4sRsh87qDEejQN7hAxMjC6KIekxmQSpP2GXk1JK5SAVt2Ul
-        MYdMHcTDALfSizl8qVARbkU5ihJa22MpF5Ww2gQnqKRCJSauV65QjoT3ArfStDKVragn51G10VG5
-        n+yXVsKrvW65rg0V0xz0y/iAJjI5KgeGO0WIxZmRJv5FxjcBjTc0eE/U14j/JjsvdJRigxNnXazH
-        ZyDFNvSWRtTdC3/LIaCV/+aMz4kNmvUxZOO8V8SbM7inOQx2nT5W43D/m2aQqXFIevVfIyATynGp
-        hkH/9mRxwni1P+7g+1k6PxLuKQ+wOXXQaXhy5GK1GkoDGUThBjQ4KnALWdI9dO/+AAAA//8DAHME
-        PM3uAwAA
+        H4sIAAAAAAAAA6STTWvbQBCG7/0Vw5xlY9d2bOvYFIovhdKUFqpgNquxtc1qRuyOsIPxfy+SbJQo
+        oRRynY/3fWZn9oQuxxRtYdSWlR8tN3ffomg+L37e6G3+NexunxafFvzr8xdeYYLy8IesXjrGVsrK
+        kzphTNAGMko5ptOb1fxmtpytVwmWkpPHFPeVjmbjxUjr8CCjyWwyxQTraPaE6QmrIGWlW5VH4ojp
+        dLZeJNiL94nVPEEVNb4PLZbrc4K2EGcpYvr7hCXFq3AQT5iiidFFNawNprASNyOcMgYAyFALqfeF
+        xgxTuAQvCTpqE8zwriBgOio4jhpq22CBi6ACh+CUQAsCNfFx63JwrNIGds4TSK1VrWM96hg2EAup
+        fQ517Fra5q3Kti21UpaG8/9QHWeYPCcNZKKw432P+7Z0w1wQmKoKUgVn9IVri/VP836aNzkqb7hD
+        GMGPd8w4sMkyHsH3otZcDjywtMGpsy6Wne8GmKiVJ451aPSNwgZMCTvxXg6O963Fs01GMNbWwSj5
+        J2jgaLdz1hGrfxpOGCsyj1erg/P+Xbt8/Zyd1zm5HudF59Vtsimpw3jhO6A1YT886y7R1PYSPcaL
+        /uEv+Dibzq+ELeUFNuMznhPcOXax2Ha3iClGlQoTdJzTEdPJ+f784S8AAAD//wMAkanDf3AEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e732188531ca8-SOF
+      - 7ca9825e8926aa10-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -744,7 +1517,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 22:48:45 GMT
+      - Sun, 21 May 2023 02:50:13 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -754,9 +1527,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
+      - significant-gravitas
       openai-processing-ms:
-      - '10828'
+      - '14155'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -768,93 +1541,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86455'
+      - '86448'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.362s
+      - 2.368s
       x-request-id:
-      - 75d8adb85d3b410b0713cc5013917627
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJemXYXZuilKwbkREpEwnz2Q0My/mvaKl9L9LRen2wD2c
-        e0Rs4BA6ryENfXG9kjV9zm6f1vOHepPKR76Pbb3abJ6pjbDg3TsF/VtMAqehJ42cYRFG8koNXLWs
-        52VVV9PaInFDPRzaQYvZZFHoftxxUc7KChZ78S3BHTGMnAbdKn9QFrhqurS4uC98YaGsvr+QeXWy
-        CB3HQAL3ckQi+beO3BMcvEgU9VnPjZyV8rn/Row3chClZM2dGSn4vjfaeTWZtYu5NZm+TOfFdH4Y
-        KFNjJOZAJh3M79XIeYKTxVvMUbrtSF44w0GUB1jE3NA3XHl6PV39AAAA//8DAHlgRXBmAQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6e73737ca71ca8-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 22:48:49 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1176'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89832'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - 7c5a28d7a495d8394ae5b8e9f041be39
+      - 6618011a94c8d2d73f905e11279742af
     status:
       code: 200
       message: OK
@@ -873,7 +1566,7 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
       get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
@@ -902,49 +1595,51 @@ interactions:
       new has happened since my creation."}, {"role": "user", "content": "Determine
       which next command to use, and respond using the format specified above:"},
       {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I should use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The next instruction is to read the instructions_3.txt file. I should use
+      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\r\nShutdown"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_2.txt
-      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
-      the instructions in the order they are given to ensure that I do not miss any
-      important steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_2.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will now read the instructions_2 file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to read the instructions_3.txt
-      file using the read_file command.\",\n        \"reasoning\": \"I need to follow
-      the instructions in the order they are given to ensure that I do not miss any
-      important steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_3.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will now read the instructions_3 file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to write the task_id into the output.txt file using
-      the write_to_file command.\",\n        \"reasoning\": \"I need to write the
-      task_id into the output.txt file as instructed.\",\n        \"plan\": \"- Use
-      the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
-      \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
-      \"I will now write the task_id into the output.txt file.\"\n    },\n    \"command\":
+      {\n        \"text\": \"The next instruction is to write the task_id into the
+      file output.txt. I should use the write_to_file command to write the task_id
+      into the file.\",\n        \"reasoning\": \"The write_to_file command is the
+      appropriate command to use to write the task_id into the output.txt file.\",\n        \"plan\":
+      \"- Use the write_to_file command to write the task_id into the output.txt file\\n-
+      Shutdown\",\n        \"criticism\": \"I need to ensure that I am following the
+      instructions accurately and efficiently.\",\n        \"speak\": \"I will use
+      the write_to_file command to write the task_id into the output.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
       \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
       "system", "content": "Command write_to_file returned: File written to successfully."},
@@ -958,7 +1653,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '7450'
+      - '7672'
       Content-Type:
       - application/json
     method: POST
@@ -966,20 +1661,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA3ySTW/aQBCG7/0VozkbhCEQ4huHpkKRekmjHuoKLeuxvWW9a+2MQyrk/175A0jp
-        x3V293mf1+MTmgwT1KUSXdV2cv/IT/nnTShW4XFzXJpP86/PH/0L19uneoMR+v0P0jK+mGpf1ZbE
-        eIcR6kBKKMMkXq3vZvE6nj9EWPmMLCZY1DJZTJcTacLeT2aLWYwRNqwKwuSEdfBVLTvxB3KMSbxc
-        zyO8wq8Hi7sIxYuy19F9vGoj1KU3mhiTbyesiM/g4C1hgorZsCgnnaZ3Qq6rcEodAECKUvqmKIVT
-        TGAcjgf0Jt0wxS8lBQIVCJyHvAlSUgDjWEKjO0UG40BKgtxY4ilsgUvf2Ay4bAQyf3TQsHFFf0cU
-        H3ZjPQLtq0q5bJpi9D47kGLvjCsGgWfjNHWv/68R/S1ZPGjvmMIrQSD2TdDEt3m1VW6ImsAL079F
-        O9yFfQPRwYjRhquBtAVH1D8gx03ooEpgC6V67XE9NwNl7SWOYU+5D9RHSPfFuphbWa5JHc4ZR2Mt
-        OH+8Wk1THG630XnHo/wfK3aqogH0W9mbPBWK27/j/ZYGwKar0Ve4VuNGa2LOG2t/Xqx6s1EwdS22
-        EebGGS53Aw4TZPE1RmhcRm+YzNrv7YdfAAAA//8DAIvSo2SrAwAA
+        H4sIAAAAAAAAA5SSTY/aMBCG7/0VozkbRJYFqtxQ1QMnqu1WPTQV8jqTxItjp56JWITy36tAEB/d
+        Su117Hmedzw+oM0xRVNpMXXjRovV89Py03o93X/+spwli+X61T25/a/vX/18hgrDyysZGTrGJtSN
+        I7HBo0ITSQvlmCbzj4/z6eIxmSusQ04OUywbGU3Hs5G08SWMJtNJggpb1iVhesAmhrqRjYQtee4B
+        D4nCC/xyME0UShDtLqXF7KFTaKpgDTGmPw5YE5/BMTjCFDWzZdFe+pjBC/l+hEPmAQAylCq0ZSWc
+        YQpDcTigN+mLGT5XBIX12oH1LLE1fS6wDBKAq1bysPNjWAFXoXU5tEwgFYFo3m6GQQhMqGvt85ue
+        DNW1MZLm4K0vL9r3Gb26ItBNE0MTrb7FH/1/tzRO+5NgBN/+Neodw0Qr1liuT6AVeKLjffLcxp6p
+        BVagayiCc2FnfXn0XL0fgzamjVrI7aG3UVFYY8mL299H5ob09qzaWef+641PpE6dNz7c+mPhXtd0
+        ktxQ77LoWN7/levtDavTvIUzIAdujSHmonXH2S6d3ZAt8x12CgvrLVebEwlTZAkNKrQ+pzdMJ93P
+        7sNvAAAA//8DAD5/N2e0AwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e737d1e1e1ca8-SOF
+      - 7ca982c97d0caa10-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -989,7 +1684,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 22:48:58 GMT
+      - Sun, 21 May 2023 02:50:27 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -999,9 +1694,9 @@ interactions:
       openai-model:
       - gpt-3.5-turbo-0301
       openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
+      - significant-gravitas
       openai-processing-ms:
-      - '9148'
+      - '11247'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1013,13 +1708,605 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86463'
+      - '86446'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.358s
+      - 2.368s
       x-request-id:
-      - 700ee384862148376a49069a620d3068
+      - 6de56a4a30bcbcde1a14399232252d53
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created and nothing new
+      has happened."}, {"role": "user", "content": "Determine which next command to
+      use, and respond using the format specified above:"}, {"role": "assistant",
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
+      the instructions_1.txt file to determine what actions to take next.\",\n        \"reasoning\":
+      \"The instructions_1.txt file contains the necessary information to determine
+      the next steps.\",\n        \"plan\": \"- Use the read_file command to read
+      the instructions_1.txt file\\n- Analyze the instructions to determine the next
+      steps\",\n        \"criticism\": \"I need to ensure that I am following the
+      instructions accurately and efficiently.\",\n        \"speak\": \"I will start
+      by reading the instructions_1.txt file to determine the next steps.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4461'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SSQW/bMAyF7/sVBM920MyZs/lWbJcARU/rNmAeAlWmba0SZUg06izIfx8cJ02X
+        IMN2Jfn4Pkpvi6bCAnWrRLvOpsvVw7e7sPT37vaTltBk8Us1tJvuq/14f4cJ+sefpOWgmGnvOkti
+        PGOCOpASqrCY5+8X+WKeL7IEna/IYoFNJ2k2e5dKHx59epPdzDHBPqqGsNhiF7zrZC3+iThi8SFf
+        Jnja/VKf53mC4kXZU2meZbsEdeuNpojF9y06ise9wVvCAlWMJopiGSk9C/F4wbZkAIASpfV900os
+        sYBD8dCgQcZiiZ9bAqZBwHCU0OsRC0wE8RBIVSAtvW7F9duZDAK1sTSDFTwba6GPtJ8bBeuxA9o7
+        p7j6Y8teUmLymiOQip4NNyeYK2YwnqcMx/0uJj2+RdiA4doHp/bY4qEioeAM02FsEIhCXTw37qzi
+        yTOFh3/Cv8JVlpzCLSu7+UUXc38jOgPSwYjRJrqJagVMtAcgjn0YxUpgBcpB7a31z4abSzuldR+U
+        kN3AiE91bbQhFrs5vz92pJ6OVv/xideiUOK0fZccs3dQX0SPlaPJ+MXpjE2F5jyxU2OcPckvUY4Q
+        e5ADT8k73CVYGzaxXU95wwKj+A4TNFzRgMXN7sfuzW8AAAD//wMANnJsjjEEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9e9fcfc39463e-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:00:56 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '13391'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86465'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.356s
+      x-request-id:
+      - 4f791abbc43d82448ee903e7f4248a39
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that I was
+      created and there have been no new developments to report."}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I will use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5540'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SST4/aQAzF7/0Uls8JArFkaW5VT9yqqlT9kwoNEyeZ3YknmnF2YVG+e5UQli2I
+        qr3afn4/z7wDmhxT1JUSXTc2vl+tv22n+8/7XZt8elotlz+eHpbq49eX+fd1iRG67QNpGRUT7erG
+        khjHGKH2pIRyTGfJ8i65myWL9xHWLieLKZaNxPPJIpbWb108nU9nGGEbVEmYHrDxrm5kI+6ROGA6
+        my3vIzwvPzeSJEJxouy5NF/Muwh15YymgOnPA9YUTou9s4QpqhBMEMXSYzoW4v6EQ8YAABlK5dqy
+        kpBhCmNxbNBO+mKGXyoCpp2A4SC+1T0WmADiwJPKQSp62wqb+UR2AoWxNIEVPBtroQ00zPWCTd8B
+        7epacf7HlkGSYfSWw5MKjg2XZ5gbZtCfpwyHYReT7t/C78Fw4XytBmxxkJOQrw3TOLYTCEJNuDRu
+        rOKjZwzrf8K/wZVlHMMHVnb/QldzfyO6ANLeiNEm1EeqFTDRAEAcWt+LlcAKVA2Fs9Y9Gy6v7ZTW
+        rVdCdg89PhWF0YZY7P7y/tCQejxZ/ccn3opChsftXXTK3qi+ih6rmo7Gr04XbMqXl4k9NvrZs/wa
+        5QQxgIw8GXfYRVgYNqHaHPOGKQZxDUZoOKcdptPuV/fuNwAAAP//AwDgiGKHMgQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9ea62ecef463e-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:01:12 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '13317'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86449'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.367s
+      x-request-id:
+      - e3d967a8e255d8ef5adbe659cf7eb379
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that nothing
+      new has happened since my creation."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I will use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The next instruction is to read the instructions_3.txt file. I will use the
+      read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6570'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SSTY/TQAyG7/wKy+dp1dJPcl1AqtgTSyUEQdV04k2GJuPRjMNWqvLfUZJWod0V
+        Au3VHr/PY41PaDNM0BRaTOXL0Wqz/Ro+fFse7vaftx+PD2X+Kd4/vL+/q+nXChXy/icZOU+MDVe+
+        JLHsUKEJpIUyTKbL9Xw5ny5XC4UVZ1RigrmX0Wy8GEkd9jyazCZTVFhHnRMmJ/SBKy874QO5iMl0
+        9m6hcAgfGuuFQmHR5VBarCeNQlOwNRQx+X7CiuIlOHBJmKCO0UbRTlpNdkKuXeGUOgCAFKXgOi8k
+        ppjAuXhu0FHaYopfCgJHRwHrooTatFpgIwjDU7BCIAWB6HjY2QysE+4Kj7Yk4Fp8LWM5yhg28GTL
+        EurYD3SjO+Fd99BwVWmX/UPmOEX1p2cgHdlZlw+yL0e3xgWB9j6wD1bLFbXT+it82OVFD19q1yuM
+        YPuKHW8wNxQTrFhjY9WjNuCIukRysQ5tpBbYgK46hHV5l2k4BDLy3ztFT/pwIb36957DelajLsd4
+        znl2i05X1GtccW9sdchvz7hvtG+HiEHjav726t/OpvOLYWd5lk1dg43CR+tsLHb99WGCUdijQusy
+        OmIyaX40b34DAAD//wMATFQWamAEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9eac7ae9d463e-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:01:31 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '15965'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86449'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.366s
+      x-request-id:
+      - 57af6ca12656ff7b06640897bf5fa81a
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nAs a system, I recall that nothing
+      new has happened since my creation."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}, {"role":
+      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
+      instruction is to read the instructions_2.txt file. I will use the read_file
+      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"The next instruction is to read the instructions_3.txt file. I will use the
+      read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"The next instruction is to write the task_id into the
+      file output.txt. I will use the write_to_file command to write the task_id into
+      the file.\",\n        \"reasoning\": \"The write_to_file command is the appropriate
+      command to use to write the task_id into the output.txt file.\",\n        \"plan\":
+      \"- Use the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
+      \"I need to ensure that I am writing the correct task_id into the output.txt
+      file.\",\n        \"speak\": \"I will use the write_to_file command to write
+      the task_id into the output.txt file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"output.txt\",\n            \"text\":
+      \"2314\"\n        }\n    }\n}"}, {"role": "system", "content": "Command write_to_file
+      returned: File written to successfully."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7648'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SSW2vbQBBG3/srhnmWjR3fGr0FCsXQQCkNpKlCWK9G0tarXbEzquMa/feii+PY
+        TaF9nd0955uZPaBJMUZdKNFlZUer9d23m4fd9svtryr//HC/mU948/Faf7r/kN5ihH7zg7QML8ba
+        l5UlMd5hhDqQEkoxni7fz5fz6fJ6HmHpU7IYY17JaDZejKQOGz+azCZTjLBmlRPGB6yCLyt5Er8l
+        xy3g6irCE/x0MFtEKF6UPZVWi1UToS680cQYfz9gSXwEB28JY1TMhkU5aWN6J+TaFg6JAwBIUApf
+        54VwgjEMxeGAnqUtJvi1IMiMUxaMYwm1bnOBYRAPXNSS+p0bwxp2xlqomUAKAlG8fRraINC+LJVL
+        z14kGL32BVLsnXH5Sfo2oxUXBKqqgq+CUef4zv93S2WV6wUjuPvXqBcMHYwYbbjsQWtwRN19clyH
+        lqkE1lConx2tw6agrO1MDErrOighu4dWRFlmtCEndg8bynygTizG5fBWC1yR2h7V/z3zntREx/0P
+        t/5Yv1Ml9ZIz6kUWFfLLn/N6mz3g5qXz0zS41pqYs9ra/UuqLtkQMHENNhFmxhkunnocxsjiK4zQ
+        uJSeMZ40j8273wAAAP//AwDMrrkmxwMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca9eb3e2d62463e-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 04:01:45 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '11215'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86452'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.364s
+      x-request-id:
+      - f275967e047717519684fa4f70a50901
     status:
       code: 200
       message: OK
diff --git a/tests/test_text_file_parsers.py b/tests/test_text_file_parsers.py
new file mode 100644
index 00000000..d15c63ae
--- /dev/null
+++ b/tests/test_text_file_parsers.py
@@ -0,0 +1,152 @@
+import json
+import tempfile
+from functools import partial
+from unittest import TestCase
+from xml.etree import ElementTree
+
+import docx
+import yaml
+from bs4 import BeautifulSoup
+from PyPDF2 import PdfWriter
+
+from autogpt.commands.file_operations_utils import is_file_binary_fn, read_textual_file
+from autogpt.logs import logger
+
+plain_text_str = "Hello, world!"
+
+
+def mock_text_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".txt") as f:
+        f.write(plain_text_str)
+    return f.name
+
+
+def mock_csv_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".csv") as f:
+        f.write(plain_text_str)
+    return f.name
+
+
+def mock_pdf_file():
+    with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".pdf") as f:
+        # Create a new PDF and add a page with the text plain_text_str
+        # Write the PDF header
+        f.write(b"%PDF-1.7\n")
+        # Write the document catalog
+        f.write(b"1 0 obj\n")
+        f.write(b"<< /Type /Catalog /Pages 2 0 R >>\n")
+        f.write(b"endobj\n")
+        # Write the page object
+        f.write(b"2 0 obj\n")
+        f.write(
+            b"<< /Type /Page /Parent 1 0 R /Resources << /Font << /F1 3 0 R >> >> /MediaBox [0 0 612 792] /Contents 4 0 R >>\n"
+        )
+        f.write(b"endobj\n")
+        # Write the font object
+        f.write(b"3 0 obj\n")
+        f.write(
+            b"<< /Type /Font /Subtype /Type1 /Name /F1 /BaseFont /Helvetica-Bold >>\n"
+        )
+        f.write(b"endobj\n")
+        # Write the page contents object
+        f.write(b"4 0 obj\n")
+        f.write(b"<< /Length 25 >>\n")
+        f.write(b"stream\n")
+        f.write(b"BT\n/F1 12 Tf\n72 720 Td\n(Hello, world!) Tj\nET\n")
+        f.write(b"endstream\n")
+        f.write(b"endobj\n")
+        # Write the cross-reference table
+        f.write(b"xref\n")
+        f.write(b"0 5\n")
+        f.write(b"0000000000 65535 f \n")
+        f.write(b"0000000017 00000 n \n")
+        f.write(b"0000000073 00000 n \n")
+        f.write(b"0000000123 00000 n \n")
+        f.write(b"0000000271 00000 n \n")
+        f.write(b"trailer\n")
+        f.write(b"<< /Size 5 /Root 1 0 R >>\n")
+        f.write(b"startxref\n")
+        f.write(b"380\n")
+        f.write(b"%%EOF\n")
+        f.write(b"\x00")
+    return f.name
+
+
+def mock_docx_file():
+    with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".docx") as f:
+        document = docx.Document()
+        document.add_paragraph(plain_text_str)
+        document.save(f.name)
+    return f.name
+
+
+def mock_json_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".json") as f:
+        json.dump({"text": plain_text_str}, f)
+    return f.name
+
+
+def mock_xml_file():
+    root = ElementTree.Element("text")
+    root.text = plain_text_str
+    tree = ElementTree.ElementTree(root)
+    with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".xml") as f:
+        tree.write(f)
+    return f.name
+
+
+def mock_yaml_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".yaml") as f:
+        yaml.dump({"text": plain_text_str}, f)
+    return f.name
+
+
+def mock_html_file():
+    html = BeautifulSoup(
+        f"<html><head><title>This is a test</title></head><body><p>{plain_text_str}</p></body></html>",
+        "html.parser",
+    )
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".html") as f:
+        f.write(str(html))
+    return f.name
+
+
+def mock_md_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".md") as f:
+        f.write(f"# {plain_text_str}!\n")
+    return f.name
+
+
+def mock_latex_file():
+    with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".tex") as f:
+        latex_str = rf"\documentclass{{article}}\begin{{document}}{plain_text_str}\end{{document}}"
+        f.write(latex_str)
+    return f.name
+
+
+respective_file_creation_functions = {
+    ".txt": mock_text_file,
+    ".csv": mock_csv_file,
+    ".pdf": mock_pdf_file,
+    ".docx": mock_docx_file,
+    ".json": mock_json_file,
+    ".xml": mock_xml_file,
+    ".yaml": mock_yaml_file,
+    ".html": mock_html_file,
+    ".md": mock_md_file,
+    ".tex": mock_latex_file,
+}
+
+
+class TestConfig(TestCase):
+    def test_parsers(self):
+        binary_files_extensions = [".pdf", ".docx"]
+        for (
+            file_extension,
+            c_file_creator,
+        ) in respective_file_creation_functions.items():
+            created_filepath = c_file_creator()
+            loaded_text = read_textual_file(created_filepath, logger)
+            self.assertIn(plain_text_str, loaded_text)
+            should_be_binary = file_extension in binary_files_extensions
+            self.assertEqual(should_be_binary, is_file_binary_fn(created_filepath))

From dcb1cbe5d69a15dc83ba20583c210ef8fc490c50 Mon Sep 17 00:00:00 2001
From: Benny van der Lans <49377421+bfalans@users.noreply.github.com>
Date: Mon, 22 May 2023 01:15:10 +0200
Subject: [PATCH 046/112] Update 1.bug.yml to improve consistency of data
 (#4293)

* Update 1.bug.yml to improve consistency of data

in this version of the bug report several dropdown fileds have been added and text fields have been removed to have better control over the data being sent in bug reports

* Update 1.bug.yml fixing indent error

fixing of an indent error

* Update 1.bug.yml

changed the file uploads to input fields for the log contents since files are not supported on github

* Update 1.bug.yml

made the issue field required

* Update 1.bug.yml

Added changes according to luke's comments

---------

Co-authored-by: Pi <sunfish7@gmail.com>
---
 .github/ISSUE_TEMPLATE/1.bug.yml | 147 +++++++++++++++++++------------
 1 file changed, 89 insertions(+), 58 deletions(-)

diff --git a/.github/ISSUE_TEMPLATE/1.bug.yml b/.github/ISSUE_TEMPLATE/1.bug.yml
index c543f980..7260971d 100644
--- a/.github/ISSUE_TEMPLATE/1.bug.yml
+++ b/.github/ISSUE_TEMPLATE/1.bug.yml
@@ -8,9 +8,8 @@ body:
         ### ⚠️ Before you continue
         * Check out our [backlog], [roadmap] and join our [discord] to discuss what's going on
         * If you need help, you can ask in the [discussions] section or in [#tech-support]
-        * **Throughly search the [existing issues] before creating a new one**
+        * **Thoroughly search the [existing issues] before creating a new one**
         * Read our [wiki page on Contributing]
-
         [backlog]: https://github.com/orgs/Significant-Gravitas/projects/1
         [roadmap]: https://github.com/orgs/Significant-Gravitas/projects/2  
         [discord]: https://discord.gg/autogpt
@@ -18,6 +17,7 @@ body:
         [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184
         [existing issues]: https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue
         [wiki page on Contributing]: https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
+
   - type: checkboxes
     attributes:
       label: ⚠️ Search for existing issues first ⚠️
@@ -27,23 +27,29 @@ body:
       options:
         - label: I have searched the existing issues, and there is no existing issue for my problem
           required: true
+
   - type: markdown
     attributes:
       value: |
-        Please provide a searchable summary of the issue in the title above ⬆️.
-
-        ⚠️ SUPER-busy repo, please help the volunteer maintainers.
-        The less time we spend here, the more time we spend building AutoGPT.
+        Please confirm that the issue you have is described well and precise in the title above ⬆️.
+        A good rule of thumb: What would you type if you were searching for the issue?
         
-        Please help us help you:
-        - Does it work on `stable` branch (https://github.com/Torantulino/Auto-GPT/tree/stable)?
-        - Does it work on current `master` (https://github.com/Torantulino/Auto-GPT/tree/master)?
-        - Search for existing issues, "add comment" is tidier than "new issue"
-        - Ask on our Discord (https://discord.gg/autogpt)
+        For example:
+        BAD - my auto-gpt keeps looping
+        GOOD - After performing execute_python_file, auto-gpt goes into a loop where it keeps trying to execute the file.
+        
+        ⚠️ SUPER-busy repo, please help the volunteer maintainers.
+        The less time we spend here, the more time we can spend building AutoGPT.
+        
+        Please help us help you by following these steps:
+        - Search for existing issues, adding a comment when you have the same or similar issue is tidier than "new issue" and 
+          newer issues will not be reviewed earlier, this is dependent on the current priorities set by our wonderful team
+        - Ask on our Discord if your issue is known when you are unsure (https://discord.gg/autogpt)
         - Provide relevant info:
-          - Provide commit-hash (`git rev-parse HEAD` gets it)
-          - If it's a pip/packages issue, provide pip version, python version
-          - If it's a crash, provide traceback.
+          - Provide commit-hash (`git rev-parse HEAD` gets it) if possible
+          - If it's a pip/packages issue, mention this in the title and provide pip version, python version
+          - If it's a crash, provide traceback and describe the error you got as precise as possible in the title.
+
   - type: dropdown
     attributes:
       label: Which Operating System are you using?
@@ -56,9 +62,15 @@ body:
         - Docker
         - Devcontainer / Codespace
         - Windows Subsystem for Linux (WSL)
-        - Other (Please specify in your problem)
+        - Other
     validations:
       required: true
+      nested_fields:
+        - type: text
+          attributes:
+            label: Specify the system
+            description: Please specify the system you are working on.
+
   - type: dropdown
     attributes:
       label: Which version of Auto-GPT are you using?
@@ -73,61 +85,80 @@ body:
         - Master (branch)
     validations:
       required: true
+
   - type: dropdown
     attributes:
-      label: GPT-3 or GPT-4?
+      label: Do you use OpenAI GPT-3 or GPT-4?
       description: >
         If you are using Auto-GPT with `--gpt3only`, your problems may be caused by
         the [limitations](https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5.
       options:
         - GPT-3.5
         - GPT-4
+        - GPT-4(32k)
     validations:
       required: true
-  - type: textarea
+
+  - type: dropdown
     attributes:
-      label: Steps to reproduce 🕹
-      description: |
-        **⚠️ Issues that we can't reproduce will be closed.**
-  - type: textarea
-    attributes:
-      label: Current behavior 😯
-      description: Describe what happens instead of the expected behavior.
-  - type: textarea
-    attributes:
-      label: Expected behavior 🤔
-      description: Describe what should happen.
-  - type: textarea
-    attributes:
-      label: Your prompt 📝
+      label: Which area covers your issue best?
       description: >
-        If applicable please provide the prompt you are using. Your prompt is stored in your `ai_settings.yaml` file.
-      value: |
-        ```yaml
-        # Paste your prompt here
-        ```
+        Select the area related to the issue you are reporting.
+      options:
+        - Installation and setup
+        - Memory
+        - Performance
+        - Prompt
+        - Commands
+        - Plugins
+        - AI Model Limitations
+        - Challenges
+        - Documentation
+        - Logging
+        - Agents
+        - Other
+    validations:
+      required: true
+      autolabels: true
+      nested_fields:
+        - type: text
+          attributes:
+            label: Specify the area
+            description: Please specify the area you think is best related to the issue.
+
   - type: textarea
     attributes:
-      label: Your Logs 📒
-      description: |
-        Please include the log showing your error and the command that caused it, if applicable.
-        You can copy it from your terminal or from `logs/activity.log`.
-        This will help us understand your issue better!
-        
-        <details>
-        <summary><i>Example</i></summary>
-        ```log
-        INFO NEXT ACTION:  COMMAND = execute_shell  ARGUMENTS = {'command_line': 'some_command'}
-        INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=
-        Traceback (most recent call last):
-        File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response
-        self._interpret_response_line(
-        File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line
-        raise self.handle_error_response(
-        openai.error.InvalidRequestError: This model's maximum context length is 8191 tokens, however you requested 10982 tokens (10982 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.
-        ```
-        </details>
+      label: Describe your issue.
+      description: Describe the problem you are experiencing. Try to describe only the issue and phrase it short but clear. ⚠️ Provide NO other data in this field  
+    validations:
+      required: true
+
+  #Following are optional file content uploads
+  - type: markdown
+    attributes:
       value: |
-        ```log
-        <insert your logs here>
-        ```
+        ⚠️The following is OPTIONAL, please keep in mind that the log files may contain personal information such as credentials.⚠️
+        
+        "The log files are located in the folder 'logs' inside the main auto-gpt folder."
+        
+  - type: input
+    attributes:
+      label: Upload Activity Log Content
+      description: |
+        Upload the activity log content, this can help us understand the issue better. 
+        To do this, go to the folder logs in your main auto-gpt folder, open activity.log and copy/paste the contents to this field. 
+        ⚠️ The activity log may contain personal data given to auto-gpt by you in prompt or input as well as 
+        any personal information that auto-gpt collected out of files during last run. Do not add the activity log if you are not comfortable with sharing it. ⚠️
+    validations:
+      required: false
+
+  - type: input
+    attributes:
+      label: Upload Error Log Content
+      description: |
+        Upload the error log content, this will help us understand the issue better. 
+        To do this, go to the folder logs in your main auto-gpt folder, open error.log and copy/paste the contents to this field. 
+        ⚠️ The error log may contain personal data given to auto-gpt by you in prompt or input as well as 
+        any personal information that auto-gpt collected out of files during last run. Do not add the activity log if you are not comfortable with sharing it. ⚠️
+    validations:
+      required: false

From 360d5cd577b947469f414b545b70fc5304a6b7af Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Mon, 22 May 2023 13:36:20 +0300
Subject: [PATCH 047/112] Prevent docker compose to break config by creating
 folders (#4125)

---
 autogpt/config/ai_config.py |  2 +-
 autogpt/config/config.py    |  2 +-
 docs/setup.md               | 11 ++++++++---
 tests/test_ai_config.py     | 29 +++++++++++++++++++++++++++++
 tests/test_config.py        | 15 +++++++++++++++
 5 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/autogpt/config/ai_config.py b/autogpt/config/ai_config.py
index 88acbfe6..0599f104 100644
--- a/autogpt/config/ai_config.py
+++ b/autogpt/config/ai_config.py
@@ -73,7 +73,7 @@ class AIConfig:
 
         try:
             with open(config_file, encoding="utf-8") as file:
-                config_params = yaml.load(file, Loader=yaml.FullLoader)
+                config_params = yaml.load(file, Loader=yaml.FullLoader) or {}
         except FileNotFoundError:
             config_params = {}
 
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index c5ffc60c..7e8c0c37 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -210,7 +210,7 @@ class Config(metaclass=Singleton):
             None
         """
         with open(config_file) as file:
-            config_params = yaml.load(file, Loader=yaml.FullLoader)
+            config_params = yaml.load(file, Loader=yaml.FullLoader) or {}
         self.openai_api_type = config_params.get("azure_api_type") or "azure"
         self.openai_api_base = config_params.get("azure_api_base") or ""
         self.openai_api_version = (
diff --git a/docs/setup.md b/docs/setup.md
index 70b3ac39..14244b8b 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -60,9 +60,14 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
               - ./data:/app/data
               ## allow auto-gpt to write logs to disk
               - ./logs:/app/logs
-              ## uncomment following lines if you have / want to make use of these files
-              #- ./azure.yaml:/app/azure.yaml
-              #- ./ai_settings.yaml:/app/ai_settings.yaml
+              ## uncomment following lines if you want to make use of these files
+              ## you must have them existing in the same folder as this docker-compose.yml
+              #- type: bind
+              #  source: ./azure.yaml
+              #  target: /app/azure.yaml
+              #- type: bind
+              #  source: ./ai_settings.yaml
+              #  target: /app/ai_settings.yaml
           redis:
             image: "redis/redis-stack-server:latest"
 
diff --git a/tests/test_ai_config.py b/tests/test_ai_config.py
index a9fcdad6..a684373b 100644
--- a/tests/test_ai_config.py
+++ b/tests/test_ai_config.py
@@ -43,3 +43,32 @@ ai_role: A hungry AI
 api_budget: 0.0
 """
     assert config_file.read_text() == yaml_content2
+
+
+def test_ai_config_file_not_exists(workspace):
+    """Test if file does not exist."""
+
+    config_file = workspace.get_path("ai_settings.yaml")
+
+    ai_config = AIConfig.load(str(config_file))
+    assert ai_config.ai_name == ""
+    assert ai_config.ai_role == ""
+    assert ai_config.ai_goals == []
+    assert ai_config.api_budget == 0.0
+    assert ai_config.prompt_generator is None
+    assert ai_config.command_registry is None
+
+
+def test_ai_config_file_is_empty(workspace):
+    """Test if file does not exist."""
+
+    config_file = workspace.get_path("ai_settings.yaml")
+    config_file.write_text("")
+
+    ai_config = AIConfig.load(str(config_file))
+    assert ai_config.ai_name == ""
+    assert ai_config.ai_role == ""
+    assert ai_config.ai_goals == []
+    assert ai_config.api_budget == 0.0
+    assert ai_config.prompt_generator is None
+    assert ai_config.command_registry is None
diff --git a/tests/test_config.py b/tests/test_config.py
index 0f38b28c..98134dc8 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -4,6 +4,7 @@ for the AI and ensures it behaves as a singleton.
 """
 from unittest.mock import patch
 
+import pytest
 from openai import InvalidRequestError
 
 from autogpt.configurator import create_config
@@ -155,3 +156,17 @@ def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config):
     # Reset config
     config.set_fast_llm_model(fast_llm_model)
     config.set_smart_llm_model(smart_llm_model)
+
+
+def test_missing_azure_config(config, workspace):
+    config_file = workspace.get_path("azure_config.yaml")
+    with pytest.raises(FileNotFoundError):
+        config.load_azure_config(str(config_file))
+
+    config_file.write_text("")
+    config.load_azure_config(str(config_file))
+
+    assert config.openai_api_type == "azure"
+    assert config.openai_api_base == ""
+    assert config.openai_api_version == "2023-03-15-preview"
+    assert config.azure_model_to_deployment_id_map == {}

From 3e24d312d3ccaa40aadb2c71ac4116b674798118 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Mon, 22 May 2023 13:00:31 +0200
Subject: [PATCH 048/112] Create data folder in Docker release build (#4347)

---
 Dockerfile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Dockerfile b/Dockerfile
index b2e09e8e..3bcfddea 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -38,5 +38,6 @@ WORKDIR /app
 ONBUILD COPY autogpt/ ./autogpt
 ONBUILD COPY scripts/ ./scripts
 ONBUILD COPY plugins/ ./plugins
+ONBUILD RUN mkdir ./data
 
 FROM autogpt-${BUILD_TYPE} AS auto-gpt

From 77ee9f81195bc2bf099d8dfe220ab3dcebba6415 Mon Sep 17 00:00:00 2001
From: Robin Richtsfeld <robin.richtsfeld@gmail.com>
Date: Mon, 22 May 2023 21:53:31 +0200
Subject: [PATCH 049/112] Pass command line args as list (#1486)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Richard Beales <rich@richbeales.net>
---
 autogpt/commands/execute_code.py                            | 4 ++--
 benchmark/benchmark_entrepreneur_gpt_with_difficult_user.py | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py
index f365cce2..8d14c17f 100644
--- a/autogpt/commands/execute_code.py
+++ b/autogpt/commands/execute_code.py
@@ -33,7 +33,7 @@ def execute_python_file(filename: str) -> str:
 
     if we_are_running_in_a_docker_container():
         result = subprocess.run(
-            f"python {filename}", capture_output=True, encoding="utf8", shell=True
+            ["python", filename], capture_output=True, encoding="utf8"
         )
         if result.returncode == 0:
             return result.stdout
@@ -65,7 +65,7 @@ def execute_python_file(filename: str) -> str:
                     logger.info(status)
         container = client.containers.run(
             image_name,
-            f"python {Path(filename).relative_to(CFG.workspace_path)}",
+            ["python", str(Path(filename).relative_to(CFG.workspace_path))],
             volumes={
                 CFG.workspace_path: {
                     "bind": "/workspace",
diff --git a/benchmark/benchmark_entrepreneur_gpt_with_difficult_user.py b/benchmark/benchmark_entrepreneur_gpt_with_difficult_user.py
index 608e9630..ca173762 100644
--- a/benchmark/benchmark_entrepreneur_gpt_with_difficult_user.py
+++ b/benchmark/benchmark_entrepreneur_gpt_with_difficult_user.py
@@ -75,14 +75,13 @@ Needs improvement.
 Not what I need."""
     # TODO: add questions above, to distract it even more.
 
-    command = f"{sys.executable} -m autogpt"
+    command = [sys.executable, "-m", "autogpt"]
 
     process = subprocess.Popen(
         command,
         stdin=subprocess.PIPE,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
-        shell=True,
     )
 
     stdout_output, stderr_output = process.communicate(input_data.encode())

From cc709bbbaae6704794ca077ad26e29f703a7d26f Mon Sep 17 00:00:00 2001
From: Nicholas Tindle <nick@ntindle.com>
Date: Mon, 22 May 2023 16:51:52 -0500
Subject: [PATCH 050/112] Improve Azure setup wording in docs (#4325)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 docs/setup.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/setup.md b/docs/setup.md
index 14244b8b..4bdf6a16 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -143,9 +143,9 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
 
         :::yaml
         # Please specify all of these values as double-quoted strings
-        # Replace string in angled brackets (<>) to your own ID
+        # Replace string in angled brackets (<>) to your own deployment Name
         azure_model_map:
-            fast_llm_model_deployment_id: "<my-fast-llm-deployment-id>"
+            fast_llm_model_deployment_id: "<auto-gpt-deployment>"
                 ...
 
     Details can be found in the [openai-python docs], and in the [Azure OpenAI docs] for the embedding model.

From 3a2800bcddb4e39c0fcfed178da85e20ed0980f0 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 22 May 2023 20:03:23 -0700
Subject: [PATCH 051/112] Cassettes should be added in the same pull request,
 without extra pull request (#4355)

* fix ci

* fix ci

* add only what we need

* Updated ci.yml to inform about challenge score

* Updated ci.yml to inform about challenge score

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 .github/workflows/ci.yml | 64 +++++++++++++++++++++-------------------
 1 file changed, 34 insertions(+), 30 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 492336df..1ff894ed 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -93,43 +93,47 @@ jobs:
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v3
 
-      - name: Stage new files and commit
-        id: stage_files
+      - name: Stage Files and Check for New Cassettes
+        id: stage_files_and_check
+        run: |
+          find tests -type f -name '*.yaml' -print0 | xargs -0 git add
+          # Check for new cassettes added in PR after the commit
+          NEW_CASSETTES_ADDED_IN_PR=$(git diff --name-only $(git merge-base ${{ github.event.pull_request.base.sha }} HEAD)..HEAD -- 'tests/**/cassettes/**/*.yaml' | wc -l)
+          if [[ "$NEW_CASSETTES_ADDED_IN_PR" -gt 0 ]]
+          then 
+            echo "NEW_CASSETTES_ADDED_IN_PR=true" >> $GITHUB_ENV
+          else 
+            echo "NEW_CASSETTES_ADDED_IN_PR=false" >> $GITHUB_ENV
+          fi      
+
+      - name: Beat new challenges
+        if: ${{ env.NEW_CASSETTES_ADDED_IN_PR}}
+        run: |
+          echo "This step will run the challenges soon."
+
+      - name: Commit, Config, and Push
+        id: commit_and_push
         run: |
-          git add tests
           git diff --cached --quiet tests && echo "No changes to commit" && exit 0
-          git config user.email "github-actions@github.com"
-          git config user.name "GitHub Actions"
+          find tests -type f -name '*.yaml' -print0 | xargs -0 git add
+          echo '${{ secrets.PAT_REVIEW }}' | gh auth login --with-token
+          gh pr checkout ${{ github.event.pull_request.number }}
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
           git commit -m "Add new cassettes"
+          git push origin ${{ github.head_ref }}
           TIMESTAMP_COMMIT=$(date +%Y%m%d%H%M%S) # generate a timestamp
           echo "TIMESTAMP_COMMIT=$TIMESTAMP_COMMIT" >> $GITHUB_ENV
-      
 
-      - name: Create PR
-        id: create_pr
-        if:  ${{ env.TIMESTAMP_COMMIT != null }}
-        uses: peter-evans/create-pull-request@v5
-        with:
-          commit-message: Update cassettes
-          branch: cassette-diff-PR-${{ github.event.pull_request.number }}-${{ env.TIMESTAMP_COMMIT }}
-          title: "Update cassette-diff-PR${{ github.event.pull_request.number }}-${{ env.TIMESTAMP_COMMIT }}"
-          body: "This PR updates the cassettes. Please merge it."
-
-
-      - name: Check PR
-        if:  ${{ env.TIMESTAMP_COMMIT != null }}
-        run: |
-          echo "Pull Request Number - ${{ steps.create_pr.outputs.pull-request-number }}"
-          echo "Pull Request URL - ${{ steps.create_pr.outputs.pull-request-url }}"
-
-      - name: Comment PR URL in the current PR
-        if:  ${{ env.TIMESTAMP_COMMIT != null }}
+      - name: Inform of auto commit.
+        if: ${{ env.TIMESTAMP_COMMIT != null }}
         uses: thollander/actions-comment-pull-request@v2
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           message: |
-            Please click [HERE](${{ steps.create_pr.outputs.pull-request-url }}) and merge this PR to update the cassettes.
-
-      - name: Fail if new PR created
-        if:  ${{ env.TIMESTAMP_COMMIT != null }}
-        run: exit 1
+            We committed some changes to this branch, please run 
+            ```
+            git fetch
+            git rebase origin/${{ github.head_ref }}
+            ```
+            before pushing more changes to the remote.

From 9c7f5671e6ce666d5410900b7f350a59853ba6b9 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 23 May 2023 05:23:03 -0700
Subject: [PATCH 052/112] CI: set base repo before `gh pr checkout` (#4363)

---
 .github/workflows/ci.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 1ff894ed..94c963a4 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -117,6 +117,7 @@ jobs:
           git diff --cached --quiet tests && echo "No changes to commit" && exit 0
           find tests -type f -name '*.yaml' -print0 | xargs -0 git add
           echo '${{ secrets.PAT_REVIEW }}' | gh auth login --with-token
+          gh repo set-default ${{ github.repository }}
           gh pr checkout ${{ github.event.pull_request.number }}
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"

From a8af3313c1e63f9c2cd5c185da535e9fed700c8d Mon Sep 17 00:00:00 2001
From: Sicong Zhao <luo9137@gmail.com>
Date: Tue, 23 May 2023 09:47:58 -0400
Subject: [PATCH 053/112] Update get_hyperlinks description (#4122)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
---
 autogpt/app.py                                |    2 +-
 .../test_browse_website.yaml                  |  678 +++++--
 .../test_write_file/test_write_file.yaml      |  471 +++--
 .../test_memory_challenge_a.yaml              | 1595 ++++++-----------
 4 files changed, 1462 insertions(+), 1284 deletions(-)

diff --git a/autogpt/app.py b/autogpt/app.py
index 2fb13135..b001376a 100644
--- a/autogpt/app.py
+++ b/autogpt/app.py
@@ -155,7 +155,7 @@ def get_text_summary(url: str, question: str) -> str:
     return f""" "Result" : {summary}"""
 
 
-@command("get_hyperlinks", "Get text summary", '"url": "<url>"')
+@command("get_hyperlinks", "Get hyperlinks", '"url": "<url>"')
 @validate_url
 def get_hyperlinks(url: str) -> Union[str, List[str]]:
     """Return the results of a Google search
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
index 2f811593..bc59b05a 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
@@ -24,7 +24,7 @@ interactions:
       \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
       \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
       GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
@@ -55,7 +55,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3767'
+      - '3765'
       Content-Type:
       - application/json
     method: POST
@@ -63,22 +63,22 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6RTzU7bQBC+9ylGc+HiOA4hgHyp1EPaSO2hBcqhrqLNemIvsXfM7rggRXn3au0E
-        khRQ1d6sGc/3tzNrNDmmqEslum6qwcXU3U5no+/84eqjnt3JZFpc3Zx/+epXs08eI+TFHWnZTsSa
-        66YiMWwxQu1ICeWYjs4vz5LRJEnGEdacU4UpFo0MxvFkIK1b8CAZJyOMsPWqIEzX2DiuG5kLr8h6
-        TC/PJhE+Yz/VT89OIxQWVT2VRsnlxSZCXbLR5DH9scaa/A7XcUWYovLeeFFWgkq2QjY4WGcWACBD
-        KbktSvEZprAtbhv0KKGY4QweTFVB6wmkJFg4fvA0f6CFN0Kgua6VzUEYfhlvBEqRJh0OF8wrHwt7
-        7VRDIa2hVqIqLloa1pQbUcGfn4/HQ2NzeoxLqSsIUEsT8EqCxhlNwMuel3kVZxjti3SkPFtji17p
-        dUkgyq/A0X1rHHmoKQh7HRDYdt9bNzFcv+5QKwsLCjnsud0bfkH7sd6mUraXOoCbv8xzjyHL7ACm
-        r5rp2rcuoDz3hUHB0lQEVtWUw8khXyyPctIN7vSEAOfbBTyQ81Tb/XVkTjsjRhtf79bGUp8UWd+6
-        MKYEZqBqaL2xRQej2TnSAjffPnfx3bfkw1q8/WrHsfqG1OqflvXt5zvi7Ck30e52tmh/nE4Iuldz
-        SH+kWrni+Oz6Ruuqfvy/TumArQfepduj34b3MP5lu+93djvLW+eZ3eAmwqWxxpfz/vgwRS/cYIQd
-        NabJ5ufm3W8AAAD//wMAygoH/1sFAAA=
+        H4sIAAAAAAAAA6RTS0/bQBC+91eM5sLFcRISSORLb5UoFWoRCLV1Fa3XE3tre9fsjglSlP+O1g9I
+        UkBVe7NmPN9rZ7aoUoxQ5oJlVZejxcU1X02/Xn2e0aa4E9/nD8ml+7G8/HZaFPcYoEl+k+R+IpSm
+        qktiZTQGKC0JphSj6flyfj6bzheLACuTUokRZjWPZuHZiBubmNFkNpligI0TGWG0xdqaquYVm4K0
+        w2g5PwvwBfu5fjo/DZANi/K5NJ0sF7sAZW6UJIfRzy1W5AZca0rCCIVzyrHQ7FUazaS9g22sAQBi
+        5Nw0Wc4uxgj6Yt+gR/bFGC9go8oSGkfAOUFizcbRakOJU0wgTVUJnQIbeFBOMeTMdTQeJ8YULmTj
+        pBU1+bTGUrAoTdbQuKJUsfD+3Go2Gyud0mOYc1WCh1orj5cT1FZJArPueI0pwhiDfZGWhDNa6axT
+        epMTsHAFWLpvlCUHFXlhbwOC0e137yaEm7cdSqEhIZ/Dntu94Ve0H+utS6E7qSO4/cs89xjiWI/g
+        05tm2vad9SgvfTYgYK1KAi0qSuHkkC/kRz5pBwc9PsBVv4AHcp5rw19H5qRVrKRy1bA2mrqkSLvG
+        +jHBcAGigsYpnbUw0lhLkuH2+ksb331Dzq/F+692HKurSRT/tKzvP98RZ0e5C4bb6dH+OB0fdKfm
+        kP5ItbDZ8dl1jcaW3fh/ndIBWwc8pNuh3/n3UO51ux8Hu63l3nmsd7gLcK20cvmqOz6M0LGpMcCW
+        GqPJ7tfuwxMAAAD//wMAMo7Y/1sFAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e272b1ec93134-SOF
+      - 7ca8f1c9db853140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -88,7 +88,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:00 GMT
+      - Sun, 21 May 2023 01:11:35 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -100,7 +100,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '17055'
+      - '18414'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -118,7 +118,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 2.338s
       x-request-id:
-      - ac9eef12460b5b5a60595d2ab3b175b0
+      - 332841746f9055ec69e5158cc078ec75
     status:
       code: 200
       message: OK
@@ -169,17 +169,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOzU7CQBRG9z7F5FsPpC2Un1kLceNGiWjUkGF6oSPt3DpzMSSEp/FNfDKDUdye
-        5JzvO8JXMHC1Fdd2TW88j8tNvPmYjfOnvLhbHGbz9Hj/LouH6/0SGrx+Iye/Rt9x2zUkngM0XCQr
-        VMHko8kwy8usmGq0XFEDg20nvUG/7Mk+rrmXDbIcGvtktwRzRBe57WQlvKOQYIaTUuO/feFFriEs
-        trmQMhudNFzN3lGCeT6ipfRXjdwQDGxKPokNcv7IQSic/y9qUl30jhRvlNSk1sw79YJbqrzY82x6
-        gfJJfX0WZX8y1co6x7HyYauEfwyhg/Rx0tj44FO9imQTBxgk4Q4aPlR0gMlOr6erbwAAAP//AwAj
-        R94saAEAAA==
+        H4sIAAAAAAAAA0SOzUrDQBRG9z7F8K2nIf1JjbN0oVZwIwqCSplMbptpk7lx5haLJU/jm/hkUtG6
+        PXDO9x3gaxi4xorr+nZ0vriXcHlTPn48zfnquq23+/fV7aYq4sK/QYOrDTn5NTLHXd+SeA7QcJGs
+        UA0znpez+XRc5FONjmtqYbDuZTTNipHsYsWjfJqPobFLdk0wB/SRu16WwlsKCWZWFhr/7ROfjDWE
+        xbYnUuTzQcM17B0lmOcDOkp/1cgtwcCm5JPYIMePHITC8f9DQ6qP3pHilZKGVMW8VS+4o9qLPc6m
+        Fyif1NfnpMjKC62scxxrH9ZK+McQ2kuGQWPlg0/NMpJNHGCQhHto+FDTHiYfXoezbwAAAP//AwAx
+        wi6HaAEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e27c6ffab3134-SOF
+      - 7ca8f270bc993140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -189,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:10 GMT
+      - Sun, 21 May 2023 01:11:45 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -201,7 +201,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '2084'
+      - '1844'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -219,7 +219,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 385ms
       x-request-id:
-      - cc9bd42a9e921979e228aaa14b778fdf
+      - 4b64f7a964c768f9b489b3a01fc11473
     status:
       code: 200
       message: OK
@@ -245,17 +245,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SO20rDQBRF3/2KYT9PQto0Nc6bUESQiqBS0EqZTk6TscmckDnFSunX+Cd+mVS8
-        vC5Ya+8DfAUD11hxXd8m51fDopbb6fusKp/u3m5cV+f38+vHRVFdzqDB61dy8mOkjru+JfEcoOEG
-        skIVzGhaTrJRkeWZRscVtTCoe0nytEhkN6w5yfJsBI1dtDXBHNAP3PWyEt5SiDDTicZ/+g+PRxrC
-        Yts/UhZHDdewdxRhng/oKP42B24JBjZGH8UGOT3kIBRO7x8aUv3gHSneKGlIrZm3aok5VV7saTUu
-        oXxUnx/jIi0vtLLO8VD5UCvhb0NoLymOGhsffGxWA9nIAQZRuIeGDxXtYbLjy/HsCwAA//8DAIvt
-        4CVmAQAA
+        H4sIAAAAAAAAA0SOzU7CQBRG9z7F5FtPmxYo4GwNC6MmRsX4gyHD9EJH2rm1czUkpE/jm/hkBqO4
+        Pck537eHL2HgKiuuaetkcn4j7Ww2odtw/XjmL6cXH+V8/vRWl/bhHhq8eiUnv0bquGlrEs8BGq4j
+        K1TC5OPpaDzMi6zQaLikGgabVpJhWiTy3q04yYZZDo33aDcEs0fbcdPKUnhLIcKMRxr/6SMe5BrC
+        YusjmRa9hqvYO4owz3s0FP+aHdcEAxujj2KDHB5yEAqH93cVqbbzjhSvlVSkVsxbtcAVlV7sYTUu
+        oHxUX5+DIp2eamWd4670YaOEfwyhnaToNdY++FgtO7KRAwyicAsNH0rawWT9S3/yDQAA//8DAKlU
+        kypmAQAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e27d6e84e3134-SOF
+      - 7ca8f27d9ae33140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -265,7 +265,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:12 GMT
+      - Sun, 21 May 2023 01:11:47 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -277,7 +277,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1692'
+      - '1950'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -295,7 +295,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 50ms
       x-request-id:
-      - 3404f771d4b84e25f370b619b33d9b2f
+      - 60ed9001757ae24a7e65ce7cacba927e
     status:
       code: 200
       message: OK
@@ -324,16 +324,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOzUoDMRRG9z5F+NaZMrE/2uxVCu4EK4iUNHNt0s7khuSWCmXeXQrVbg+cwzkj
-        drDwwYkfct88PJd171aLYGaH/dPy7dX5j9mLKWt6fxRo8HZPXq7GxPOQe5LICRq+kBPqYM3icdaa
-        eTudawzcUQ+LXZZmOpk3cixbbtppa6BxrG5HsGfkwkOWjfCBUoVd3mvc0jesISyu/wemNaOGDxw9
-        VdjPMwaqf83CPcHC1RqruHSZ95yE0uV+pU6uquuxcqlTiSXEtFOJTiq4qoLLmRJ1E4wa3zHFGjaF
-        XOUEiyqcoRFTRz+w7fg13v0CAAD//wMAw+SFO0kBAAA=
+        H4sIAAAAAAAAA0SOMU/DMBQGd36F9c1OFTdtAa9MZWAoIAaEKtd5JKaJnxW/tqAo/x1VKnQ96U43
+        ItSw8K0T36euuF1v5CDHh5fuZ/M6Xzw2x7eV2e/c/OnZNNDg3Rd5uRgzz33qSAJHaPiBnFANa1Z3
+        i1VllqbU6LmmDhZNkqKaLQs5DDsuyqo00Dhk1xDsiDRwn2QrvKeYYe/nGtf0FWsIi+v+gSnNpOFb
+        Dp4y7PuInvJfc+COYOFyDllclPMhR6F4vl+rk8vqcqxcrFVkaUNsVKSTal1WrUuJItUzTBqfIYbc
+        bgdymSMssnCCRog1fcOW08d08wsAAP//AwBO8HiBSQEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e27f35c5b3134-SOF
+      - 7ca8f29b9a0d3140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -343,7 +343,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:16 GMT
+      - Sun, 21 May 2023 01:11:51 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -355,7 +355,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '895'
+      - '850'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -373,7 +373,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - 21eaeabf9b54c809ad61d77bbb6e0432
+      - cc3733f8271b8b1cf2ef3a8267c7769a
     status:
       code: 200
       message: OK
@@ -402,7 +402,7 @@ interactions:
       \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
       \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
       GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
@@ -456,7 +456,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5668'
+      - '5666'
       Content-Type:
       - application/json
     method: POST
@@ -464,21 +464,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7yUzY7aQAzH730KyxcuAQVoYDe3XrbaQ6Ue2G4/UkWTiUmmJDPpjFPQojxN36RP
-        VuUDKCwr9dIex575+/d37OxRpRiizAXLsirGyzv7WL5ZPHy4e/wUbJ5+bJ/e15/tx9uVr99O0UOT
-        fCPJw4uJNGVVECuj0UNpSTClGE4XN6/9aeDPFx6WJqUCQ8wqHs8nwZhrm5ixP/dbsdqJjDDcY2VN
-        WXHMZkPaYTidLQMPT+LHxGy29JANi+J0N/BnjYcyN0qSw/DLHktyB2FrCsIQhXPKsdDcYhrNpFsL
-        +0gDAETIuamznF2EIQzBIUE7boMR3sNWFQXUjoBzgq1VTDGbeK0KAmnKUugU2PSJ7kpllSQw6+6Q
-        GLNp0wK6B1qUlMIosWbrKN5S4hTThHc8mkTo/UlgSTijlc56jFVOwMJtwNL3WllyUNJfl53A6kV0
-        KTQk1Pq7auOkccFXFUL3aGN4+NfNiSJ9qtK2IR5m5KzKMXa4dYEsrWIllSsPX1ZTb5q0q237TDDc
-        gyihdkpnnYw01pLkDrDlg64W7fiFZrWHa+1yFYnNf5+onqDxDvM+qD8b91akhzujufAgbHa5KX3i
-        0Jxe4jnKmc7lgq2uGhy9o1SxaH8CbgTKwa+fs2Byc3s01Rkb/EW6wcbDtdLK5XG/ORiiY1Ohh0qn
-        tMPQb742r34DAAD//wMAxK4UxfYEAAA=
+        H4sIAAAAAAAAA7yUz27aQBDG732K0Vy4GAtDgNRvQKW0akVzqStrvR7sDfauszsOSMhP0zfpk1X+
+        AwRCpF7a487sfvP7xjM+oEoxRJkLlmVVjJerb/wSPD5//vq4+PLEe9ab5Sq9M58eRPGCHprkiSQP
+        L3xpyqogVkajh9KSYEoxDBb3d4tZMA8CD0uTUoEhZhWPZ/58zLVNzHgymwToYe1ERhgesLKmrDhm
+        syXtMAymy7mHZ/FTYjpdesiGRXG+O59MGw9lbpQkh+GPA5bkjsLWFIQhCueUY6G5xTSaSbcWDpEG
+        AIiQc1NnObsIQxiCQ4L23AYjXMFOFQXUjoBzgp1VTDGbeKMKAmnKUugU2PSJ7kpllSQwm+6QGLNt
+        0wK6B1qUlMIosWbnKN5R4hSTz3se+RF6rwksCWe00lmPsc4JWLgtWHqulSUHJf11WR/W76JLoSGh
+        1t9NG2eNK76qELpHG8P3f92cKNLnKm0b4mFGLqqcYsdbV8jSKlZSufL4ZTX1pkm72rbPBMMKRAm1
+        UzrrZKSxliR3gC0fdLVoz+80qz3caperSGz/+0T1BI13nPdB/c24tyI93AXNlQdhs+tN6RPH5vQS
+        b1EudK4XbH3T4OiBUsWi/Qm4ESgHv39N5/79x5OpztjgL9INNh5ulFYuj/vNwRAdmwo9VDqlPYaT
+        5mfz4Q8AAAD//wMAergitPYEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e27fa19f03134-SOF
+      - 7ca8f2a23cf93140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -488,7 +488,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:31 GMT
+      - Sun, 21 May 2023 01:12:07 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -500,7 +500,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '15170'
+      - '16398'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -518,7 +518,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 2.347s
       x-request-id:
-      - 3882156168caae167fcba64d9e53dfe9
+      - c5404d288efec911bdf5a3bddd85f6af
     status:
       code: 200
       message: OK
@@ -548,16 +548,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SPy07DMBBF93yFNWunStqEh3dsEGUBC7pAQqhynCExtT2WZyooVf4dFYG6PdI9
-        OvcIfgADbrLiYg7V1V15aW+eHw7r8elx3y43IZdy3/S7TfMdQQP1H+jkb7FwFHNA8ZRAgytoBQcw
-        zeV1Wzdd3bUaIg0YwMCYpVotukr2paeqXtUNaNizHRHMEXKhmGUrtMPEYJplreHsPvNOg5DYcCar
-        btbgJvIOGczrESLyv7VQQDBgmT2LTXJqpCSYTv23rKziAwtGrdaqoLMhKJmsqEQy+TSqhJ9qsqwm
-        mzMmHBT75FDFg/q96iktYNbw7pPnaVvQMiUwwEIZNPg04BeYen6bL34AAAD//wMAwyzQIWYBAAA=
+        H4sIAAAAAAAAA0SPQUvDQBCF7/6KYc6bkjRtLXsTsVBREKH0ICKbzdisJjvrzrRVSv+7FKq9Pt77
+        +N4BQ4sWfefUD6kvrpfP28V99bReT1aLuH78GvuYwvyhubtdCRrk5oO8nhcjz0PqSQNHNOgzOaUW
+        bTWbT2Z1Na0rgwO31KPFTdKiHk0L3eaGi7IuKzS4FbchtAdMmYekb8qfFAVtNS4NXtj/+SlWVtdf
+        mpPyaNB3HDwJ2pcDDiR/1Mw9oUUnEkRd1JMjR6V48r8RcCA/ojQYWEIm7/oetHMKS9g7gfMdcLEF
+        7SgTdG5H0BBFiAyR9tDSjnpOA0UVUIZMibOO8GjwPcQg3VsmJxzRoignNBhiS99oy+Pr8eoXAAD/
+        /wMAE1Xpl3sBAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e286a6cb43134-SOF
+      - 7ca8f31d59c93140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -567,7 +568,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:36 GMT
+      - Sun, 21 May 2023 01:12:14 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -579,7 +580,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1467'
+      - '2801'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -597,7 +598,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 107ms
       x-request-id:
-      - 184d54d51114800add2eb3511ace4ebc
+      - 66ea868bef86201e96c325cca19485ed
     status:
       code: 200
       message: OK
@@ -626,7 +627,7 @@ interactions:
       \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
       \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
       GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
@@ -648,21 +649,21 @@ interactions:
       \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
       "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
       "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to find the price of the book on the website. The browse_website command
-      can be used to visit the website and find the price.\",\n        \"plan\": \"-
-      Use the browse_website command to visit the website\\n- Find the price of the
-      book\\n- Write the price to a file named ''browse_website.txt''\\n- Use the
-      task_complete command to complete the task\",\n        \"criticism\": \"I need
-      to ensure that I am using the correct URL and question to find the price of
-      the book.\",\n        \"speak\": \"I will use the browse_website command to
-      visit the website and find the price of the book.\"\n    },\n    \"command\":
-      {\n        \"name\": \"browse_website\",\n        \"args\": {\n            \"url\":
-      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      a system, I recall that I was created and there have been no new developments
+      to report."}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I will use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and find
+      the price of the book.\",\n        \"reasoning\": \"The task requires me to
+      find the price of the book on the website. The browse_website command can be
+      used to visit the website and find the price.\",\n        \"plan\": \"- Use
+      the browse_website command to visit the website\\n- Find the price of the book\\n-
+      Write the price to a file named ''browse_website.txt''\\n- Use the task_complete
+      command to complete the task\",\n        \"criticism\": \"I need to ensure that
+      I am using the correct URL and question to find the price of the book.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
       \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
       "content": "Command browse_website returned: Answer gathered from website: The
       price of the book \"Meditations\" is \u00a325.89, according to the text. \n
@@ -695,7 +696,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6927'
+      - '6946'
       Content-Type:
       - application/json
     method: POST
@@ -703,20 +704,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSTY/TMBCG7/yK0Vz24lapQrsot72AeuC2CARBleNMElN/ZO3JtqjKf0dpku1S
-        FgHiZo9nXj/vzJxQl5ihaiQr25rF7dvwafPw7vORPlZ36X0oyruNbt43xZa3KQr0xTdSPFUslbet
-        IdbeoUAVSDKVmK02b14nq3Wy3gi0viSDGdYtL9LlesFdKPwiSZMVCuyirAmzE7bB25Z37PfkImar
-        9ToReBG/PGxSgexZmkvodpX2AlXjtaKI2ZcTWoqzcPCGMEMZo44sHQ+Y3jG5wcIpdwAAOXLju7rh
-        mGMGU3B6oCMPwRy3cNDGQBcJuCFgGfe7CZBAeWulK4E9PMXmrGWO4rlkIBm9064ede+nNAj00OlA
-        ESy9qAOyYgpwCJq1q8/hNmhF4KvzpfB+PxQO50obWsL9bzmVdFDQYObvmFsj3Yi7gA//3IErMTU4
-        UDraubGORgxysQtDmWTYgrTQBv+oy8GthLFtUPkwfzB34SXg2JLc///gRslezHsypf+yJk5aGn/7
-        Sf4KSob6esOer8SM28hHgtgpRTFWnTHfzzNncn+eOdwUwR8i7Q5URM205CPfPPk4e5ks5a7HXmCl
-        nY7NbgTADCP7FgVqV9IRs6T/2r/6AQAA//8DAOjFC/khBAAA
+        H4sIAAAAAAAAA6SSwY7TQAyG7zyF5cte0qpVmy6bIwikCiFVsLscCKomEycZmpkJM55tUZV3R2mS
+        7VIWAeI4Hvv399s+osoxQVkJlrqpJ9frD2EdzDveiPeb+5vszb3e3H187V6FT/FbjNBmX0nyUDGV
+        Vjc1sbIGI5SOBFOOyXz1crlazOPFMkJtc6oxwbLhyWIaTzi4zE5mi9kcIwxelITJERtndcNbtjsy
+        HpN5HMcRnsXPH6tlhGxZ1OfQ9fymjVBWVknymHw+oiY/CjtbEyYovFeeheEO0xom01k4pgYAIEWu
+        bCgr9ikmMASHDzpwF0xxDXtV1xA8AVcELPxuOwASSKu1MDmwhcfYmDVNMXoq6Uh4a5Qpe93bIQ0c
+        fQvKkQdNz+qAKJgc7J1iZcpTuHFKEtji9Mis3XWFAgpV0xRuf0sphYGMOit/R9zUwvSwE7j7Z/8X
+        YrLjl8rrcayGegwyPriuTDCsQWhonH1QeedVQD80KKwbG4wzeA7YNyR2/7+2XrKNxisZ0n85EiM0
+        9d1+kr+AEq68vK+nBzHiVuKBwAcpyfsi1PX308aZzJ82Dh1GDleZs3tP2z1lXjFN+cBXj15OfgZb
+        qWmxjbBQRvlq20Nggp5tgxEqk9MBk1n7pX3xAwAA//8DABHFfW8jBAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e2874ad9f3134-SOF
+      - 7ca8f3302c223140-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -726,7 +727,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:57:48 GMT
+      - Sun, 21 May 2023 01:12:27 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -738,7 +739,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '12210'
+      - '13205'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -750,13 +751,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86479'
+      - '86475'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.346s
+      - 2.35s
       x-request-id:
-      - c06abb02e5bab33b2494f2d77188e9c2
+      - 23fc44388f2583db5f23d46e4bc9ef75
     status:
       code: 200
       message: OK
@@ -2089,4 +2090,475 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3767'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA8yU32/TMBDH3/krrHtOf63bKHlBQmJiAx7GNiFEUOS6l8TU8QX7Qoeq/u/ISdOu
+        YUJsA4nXO9/37vvx2WvQC4hBFZJVWZnB84v3F2/9zHy6ys7U1evL+vry1Xiymk5OLt8cQQQ0/4qK
+        txVDRWVlkDVZiEA5lIwLiCens+PZ8Wx6Mo6gpAUaiCGveDAdngy4dnMajKfjCURQe5kjxGuoHJUV
+        p0xLtB7i2fFpBHvtXXwa4kwszS40mbw42kSgCtIKPcSf11Ci73QdGYQYpPfas7QcpiTLaIODdWKF
+        ECIBLqjOC/YJxGIb3CbwlkMwgXNhEReCSdQeBRco5o5WHtMVzr1mFIrKUtrmxHftNYuCuYpHoznR
+        0g+ZvHKywgBspCRLQ3mNoxIXmmWw6NPpdKTtAm+HBZdGBKlMB70CReW0QkFZ25doORTnYqWNCQEr
+        Vi4MsD/IJKTItEFhZYmL3qRDvuVQr6RtyztDLP0y3UI/8LOLdaeGCUR3MTmUnqy2+WNZhTNd8iHO
+        O/2GQMqUNq7vyD8GzZm20pgf0ZbR0/FURtqWzEDc/AfbkyR2P8hfRHeg++e4erSU06yV9mV/mdD6
+        2oUyyeJcyFLUXtu8kVHkHCoWNx/eNd6/1egDF5GR+w3usEzSeNq1KOUSRa9L4NDvo21GrmzQh7KQ
+        CmT6F+8rlMvORrO1/+JBXBdoo+5ZPPzWGv37drh1som6X3I75C+fZBBuTR6K92BIl/c/2DZRO9OW
+        P2nnD7q1wt0WtOofw41qfz/Fl53dxvLWeWI3sIkg01b7Im0/OYjBM1UQQdMa4vHmy+bZTwAAAP//
+        AwChi9cmRQcAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda08b6f552a30-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 23 May 2023 13:26:28 GMT
+      Function-Execution-Id:
+      - f495ziryd97p
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '38742'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - b8bc47ef5185ce4a95373f0c7082edca;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86494'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.337s
+      X-Request-Id:
+      - 4c3aae2d3631b3ef8fcdba9173076cd3
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6158'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7xTzY7TMBC+8xSjOadVf7a73dw4llW5AAJBVpXjTBvT2BPZ021RlafhTXgy5KQ/
+        bEDaAwLlEHnG8/3MjI9oCkxRl0q0ravB3Zvlw+u3M3O7XNb0cfH09Ond/kYXd+HzA+0wQc6/kpZT
+        xVCzrSsSww4T1J6UUIHp+HZ+E7/RJEHLBVWY4qaWwXQ4G8jO5zwYTUdjTHAX1IYwPWLt2dayEt6S
+        C5iOp/NRglfwS2IyniUoLKq63p3dz5oEdclGU8D0yxEthTOw54owRRWCCaKcRJnshFy0cMwcAECG
+        UvJuU0rIMIVT8JSgg8RghgtwRAUIw94bIZCSoPZGE/C6PeTM25hWsDYVgVOWCsg97wOt9pQHIzSU
+        gwxhAVo52IUOo0VbCa/aKs3WKtfSFAxSmjDMMPlVkScV2Bm36ct6EfAvdfd01JVynYQBfPi31D1m
+        7Y0YbYLtd8CqLUHY+cikBBagbMts3Kal0+w9aQHj1uytiosVy2Kq5W/FxspLxATIKZafVhuMe4ZU
+        mPhj/63fnVCT2p717U1V/YfxdPxNcl7qE/ZvOx0hOmnPtPQcKL/pP4cuEe9eIV6YVv8Vvf+jvSzL
+        cEmFkXYmIR5j6398n8yG8/uLtdbeyWXmGmwSXBtnQrnqHgWmGIRrTNC4gg6YjprH5tVPAAAA//8D
+        AA/XyHnhBAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda1d1af2c2a51-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 23 May 2023 13:27:02 GMT
+      Function-Execution-Id:
+      - f495tt5vatqn
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '20292'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 538e62f7ebc2b2b9c21ce7729ba69230;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86461'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.359s
+      X-Request-Id:
+      - e05ec1791bbd0632573b17e8eef31a4d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that I was created and there have been no new developments
+      to report."}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
+      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
+      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to write the price of the book to a file named
+      browse_website.txt. I can use the write_to_file command to do this.\",\n        \"reasoning\":
+      \"I need to use the write_to_file command to write the price of the book to
+      a file named browse_website.txt.\",\n        \"plan\": \"- Use the write_to_file
+      command to write the price of the book to a file named browse_website.txt\",\n        \"criticism\":
+      \"I need to make sure that I am writing the correct information to the file
+      and that the file is being created in the correct directory.\",\n        \"speak\":
+      \"I will use the write_to_file command to write the price of the book to a file
+      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
+      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7417'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7ySQW/bMAyF7/sVBM9y4CJdk/m2wwZkw3baUKDzECgyY6uWJc+klxSB//ugxGnS
+        dIf2Uuj2JH7vkeIObYEZmkqLaVqXzL58+2rubz9/d/Pbxfau0OHPbJF+3BTb9NMdKgyrezIyVkxM
+        aFpHYoNHhaYjLVRgdnUzv45nmipsQkEOMyxbSaaT94n03Sok6TS9QoU965Iw22HbhaaVpYSaPEfA
+        9VzhCX66iLoE0e4kzT7cDApNFawhxuzXDhviI7gLjjBDzWxZtJcYM3ghH1vY5R4AIEepQl9Wwjlm
+        MIrjBW0lijkuoNJ/CcZMVIBUBKK5VsABFmC0h57pUV4eX8aSRvsCJABXvUARNn6Sozr36Uhz8NaX
+        b2HWOu0PPgn8fDHlAmI6K9ZYbo6JPdG+oNE1Afdd5GqBZ61o58CTiV/UPex9GVa0Dh3tvcT68r+p
+        uSVdv2w8G+vc6+ZzMBrUcSHGZ8/2weuGDhmeYC+i6q68XKXzbz4Afmiuz1rg3sSZrHvnHh4D7UON
+        2XI/4KBwbb3lankgYYYsoUWF1he0xSwdfg/v/gEAAP//AwAmuvG70wMAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda282a841e260-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 23 May 2023 13:27:30 GMT
+      Function-Execution-Id:
+      - f4950mi11y6s
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '19853'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - ae94b92034f0418f548d7e72cf0c9bf9;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86451'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.366s
+      X-Request-Id:
+      - 1afba65e36bbafb24242da6f8cb9ca98
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
index d744b2ef..925e2e2d 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
@@ -19,7 +19,7 @@ interactions:
       read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
       Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
       GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
@@ -50,7 +50,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3391'
+      - '3389'
       Content-Type:
       - application/json
     method: POST
@@ -58,21 +58,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7STy27bMBBF9/2KwWy8kQ05tuNEH1A06DJIU7QqBIYaS6wpkiVHtQtD/17o5YcK
-        dJft3OG9Z8jhCVWOCcpSsKycnm8/+q+f1y+vv+42y7X5po+rPT0/bpX4sv+9xAjt20+SPJxYSFs5
-        TayswQilJ8GUY7K8f1jHy028jSOsbE4aEywcz1eLzZxr/2bn8SpuzeogCsLkhM7bynHGdk8mYLLd
-        bCO8eJ/rd/F9hGxZ6HPp8X7VRChLqyQFTL6fsKIw2nqrCRMUIajAwnALaQ2TaQc4pQYAIEUubV2U
-        HFJMYCgOAh25Lab4BIYoB7ZQBwIuCQ5eMWVss53SBNJWlTBdQyfA7BNpbeHVep3PQBm2IKBrNaKi
-        HGZlq2eHVl/wkWeLFKPrbE8iWKNM0QM8KyMJLhh9ioDgSKqdktCyXudE/6FUoRMrGxiEc946rwQT
-        WEPDiFMap4XpQebw8m43kJqLO4uwz4YVuHE/18auKav0ipVUoZo+HZlQ+/acYHgCUUEdlCk6H2m9
-        J8kXPujS2s4uprvc0E3GZMZ2/WeaHRyJ/Zh7UFq/5770wU007vFg+s8atw490w3EBF34YvoDeqHt
-        vVhMOG5Mpr/maqaRtiMewFPTYBPhThkVyqxfeEwwsHUYoTI5HTGJmx/Nh78AAAD//wMA+mCSu6UE
-        AAA=
+        H4sIAAAAAAAAA7STTY/TMBCG7/yK0Vx6SauW0m7JDa1A9MCFBbGIoMjrTBtTxxPsCS2q8t9X+ehX
+        kLjtdd7x+z5jj49oMoxR50p0Udrx3frzn/mK7999uX+w+9w80ur344fl5v0n950xQn76RVr6ExPN
+        RWlJDDuMUHtSQhnGs+XqzXI+W6xmERackcUYt6WM55PFWCr/xOPpfDrDCKugtoTxEUvPRSmp8I5c
+        wPhucRfhxftcfz1dRigsyp5Lb5fzOkKds9EUMP5xxILCydazJYxRhWCCKCcNJDsh1wxwTBwAQIKS
+        c7XNJSQYQ1/sBTpIU0xwDY4oA2GoAoHkBHtvhFLhdGMsgeaiUK5taAUYfSRrGb6xt9kIjBMGBW2r
+        UwVlMMobPd03+kQOMpokGF1ne1KBnXHbDuDBOE1wwehSFISStNkYDQ3rdU70H0oTWrHgIKDK0nPp
+        jRICdtSPOKQprXIdyBi+vtgNJO7iLirs0n4FbtzPtVPXkFV7I0abUAyfjlyofHNOCaxBFVAF47at
+        j2bvScuFD9q0prONaS83tJMJuVO7/TvMDiWp3Sl3b6x9yX3pguvotMe96T9r3Dh0TDcQA3Tlt8Mf
+        0AlN78ViwHFjMvw1VzOdaFviHjxxNdYRbowzIU+7hccYg3CJERqX0QHjaf2zfvUMAAD//wMAvFyd
+        qKUEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e28ce4eec3134-SOF
+      - 7ca8f4583b0d3139-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -82,7 +82,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:58:04 GMT
+      - Sun, 21 May 2023 01:13:16 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -94,7 +94,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '14009'
+      - '15251'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -106,13 +106,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86496'
+      - '86497'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.336s
+      - 2.335s
       x-request-id:
-      - 4273baa4d7bdadcb0aaf64a92def3fee
+      - 5a2c54e38949e7464d5c2759c3f704ed
     status:
       code: 200
       message: OK
@@ -141,16 +141,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBQG7/6K5TtvSmKtqXsUEXvxJCiIlO3mmV2b7FuzL7YQ8t+lUO11YIaZ
-        EBoYOG/F9akr6sfhbVfvX6x/Hlv/cDz8DN/jU03Zb17vocG7L3JyNhaO+9SRBI7QcANZoQamul3f
-        lNWqXNcaPTfUwaBNUiwXq0LGYcdFuSwraIzZtgQzIQ3cJ9kK7ylmmLtrjUv6gjWExXb/oCqrWcN5
-        Do4yzPuEnvJfc+COYGBzDllslNMhR6F4ut+og83qfKxsbFRk8SG2KtJBeZuVtylRpGaBWeMzxJD9
-        diCbOcIgCydohNjQEaacP+arXwAAAP//AwAItSctSQEAAA==
+        H4sIAAAAAAAAA0SOzUrDQBRG9z5F+NaTkhhb7ewUFxbpRnAlUqYz12Zscu+Quf3BkneXQrXbA+dw
+        TogBFr516vvUlfeLt/3ysTm8Zr+dLp/mLxTen/f9kWWgHxjI+pu8XoyJlz51pFEYBn4gpxRg69nD
+        3aypZ1Vl0EugDhabpGUzmZa6G9ZSVk1Vw2CX3YZgT0iD9ElXKlviDDu/Nbimr9hARV33D+qqHg18
+        K9FThv04oaf81xykI1i4nGNWx3o+FFbi8/2iOLhcXI4Lx6Fg0TbypmA6FK3LRetSIqYwwWjwFTnm
+        djWQy8KwyCoJBpEDHWGr8XO8+QUAAP//AwCbr2StSQEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e29370ef23134-SOF
+      - 7ca8f4cbaa263139-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -160,7 +160,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:58:08 GMT
+      - Sun, 21 May 2023 01:13:21 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -172,7 +172,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1031'
+      - '977'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -190,7 +190,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - 739f7b6c03a87b0556182913b60556cd
+      - 2456b7f24102cba0f3376a140d9ba536
     status:
       code: 200
       message: OK
@@ -214,7 +214,7 @@ interactions:
       read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
       Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
       delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
       args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
       GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
       \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
@@ -261,7 +261,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4669'
+      - '4667'
       Content-Type:
       - application/json
     method: POST
@@ -269,20 +269,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA7RSTY/TMBC98ytGc+klrVK6HyVHDsCekGARKxFUuc408dbxWPak7arKf0dpku1S
-        BAcQ13l+894bvyOaAjPUlRJdezu9fRce9Hr/sG38pxs2j/r+ffX26c3Vx0ruAybI60fSMjBmmmtv
-        SQw7TFAHUkIFZvOb5VU6v06XywRrLshihqWX6WJ2PZUmrHmaLtI5JthEVRJmR/SBay8r4S25iNk8
-        XaQJnpefgds0QWFR9jx6naZtgrpioyli9u2INcVxcWBLmKGK0URRTjqb7IRcF+GYOwCAHKXipqwk
-        5pjBMBwAOkg3zPEOKrUjiI3WFOOmsfYJ9sGIkIPJB7KW4SsHW0zAOGFQsDGWwKmaCphUHb7ad/hM
-        DjKZwR1o5cDxHppIIBWBqLhdDZEJNNe1cgUIw/NsfDXLMXlpMpCK7Iwre6efjdMEg9+RXDyzkz+o
-        mXgCa44CyvvAPhglBOyoc9JEutT2Vrledgpf/jmJDkaMNrEeb+6ITkxysQkdT8mYzAfemYIKULBT
-        1hTQnwE2HEYh48rfSkVPajvK7I21f/cR/co2GZs0PP+lSF0RerWf1l+YUqG87ODLL/4fTRwjnGIM
-        aXLXYpvgxjgTq1WvjRlGYY8JGlfQAbO0/d6++gEAAP//AwDwffUhPgQAAA==
+        H4sIAAAAAAAAA6SSQY/aMBCF7/0Vo7lwMSgUFqrceitt1VZbqh42FTLOkHhx7MieLCDEf69MkmWX
+        bSu1vc6M33zPb46oc0xRlZJVVZvhfHH78Gm+/PD23t3ODuWNy3frL7zcvJ98XH5GgW59T4q7FyPl
+        qtoQa2dRoPIkmXJMx7M309lkPEvGAiuXk8EUi5qHk9HNkBu/dsNkkoxRYBNkQZgesfauqnnFbks2
+        YDpOJonAi/ilMZ8KZMfSXEqvk+lJoCqdVhQwvTtiRaEX9s4QpihD0IGl5YjpLJONFo6ZBQDIkEvX
+        FCWHDFPoil2D9hyLGS6glA8EoVGKQtg0xhxg5zUzWRi8I2McfHfe5APQlh1I2GhDYGVFOQzK2F/t
+        Yn/Eex6MYAFKWrBuB00g4JKAZdiuOssEylWVtDmwg8daPzXKUDyF9CSDs9oWLelXbdVlGHSIIhGV
+        /h5UQIT4lffc2bhEsjivsrRnCEx1t+8FNDRB2+L3Tq9N1Uba1s8Qvv33FymvWSsdqj5MS3R+STY0
+        vjXyhxU6xJhyUM57UmwO1/qhJrnttXfamH+LtZU8if4uu/EXZxnTarc9k7+Ckr64vuinB9MKLGM2
+        vUD+LONHoDNUx5bZE54EbrTVoVy1SphiYFejQG1z2mOanH6cXv0EAAD//wMAOXgyaFoEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c6e293e98343134-SOF
+      - 7ca8f4d2ed7d3139-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -292,7 +292,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sat, 13 May 2023 21:58:19 GMT
+      - Sun, 21 May 2023 01:13:33 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -304,7 +304,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '11031'
+      - '12475'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -322,123 +322,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 2.347s
       x-request-id:
-      - f0688bcfb5c1cd1af84b725271f0a4c4
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed in double quote e.g. \"command name\"\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3405'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTT4/TMBDF73yK0Vx6cauUqt1trmhhK8QBBEKIoMrrTBvT2BPsCVu2yndfJemf
-        3SBOCK7zxu/9xh4f0OaYoim0GFeV46vX7u3i183N/Geup/7Lq9vVh/fXEt49PLwpNCrku+9k5Hhi
-        YthVJYlljwpNIC2UYzpdXM+Wy3kySxQ6zqnEFLeVjGeT+VjqcMfjZJZMUWEd9ZYwPWAV2FWyFt6R
-        j5heLRKFF+9z/WUyVSgsujyXlotpo9AUbA1FTL8e0FE82QYuCVPUMdoo2ksLyV7ItwMcMg8AkKEU
-        XG8LiRmmcCweBdpLW8xwBZ4oB2GoI4EUBPfBCq2F1xtbEhh2TvuuoRNgdEtlyfCZQ5mPwHph0NC1
-        eu0oh1HR6uv7Vp/IXkaTDNXT7EA6srd+2wN8LAhExx0E+lHbQBEc/UWago72j3PY2ImOo4CuqsBV
-        sFoINhxAilbVcTdErkrte9oxfPpP12SCFWtsdMN3Ih/r0DJogdX51QyHQEYuEf090F4uTMJda9sy
-        TIsV6d0p6d6W5b9chz64Uac1PZr+tqWtQ8/0DGKArsN2uOC90PZeLAYcz0yGn+LJTCfajvgInvkG
-        G4Ub620s1v0+Y4pRuEKF1ue0xzRpvjUvHgEAAP//AwDSj7qBhAQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c6c3f8bcdd1cf87-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 13 May 2023 16:24:06 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '16269'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86496'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.336s
-      x-request-id:
-      - 8d3e6826e88e77fb2cbce01166ddc550
+      - 85392cbd30db94e28752659a98e23706
     status:
       code: 200
       message: OK
@@ -943,4 +827,275 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3391'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7yTT4/TMBDF73yK0Vx6cauWbrslR5DQLtWeoFohgiqvM21MHU+wJ2q1Vb47StI/
+        u0GcECi3eeP3fmNPjmgzTNDkWkxRuuHtp4fl8yp/X3q7XH1+vlt9/PBVT+c3y8njwxwV8tMPMnI6
+        MTJclI7EskeFJpAWyjCZzBc3zTebKiw4I4cJbksZTkezoVThiYfj6XiCCquot4TJEcvARSlr4R35
+        iMntbKHw6n2pvx2PFQqLdpfSu9miVmhytoYiJt+OWFA82wZ2hAnqGG0U7aWBZC/kmwGOqQcASFFy
+        rra5xBQTOBVPAh2kKaZ4D54oA2GoIoHkBPtghdbC6411BIaLQvu2oRVgcEfOMTxycNkArBcGDW2r
+        1wVlMMgbfb1v9JEcZDBKUb3MDqQje+u3HcCXnEB03EGgn5UNFKGgv0hT0NL+cQ4bW1GXZeAyWC1X
+        acMBJG8adNz1qUunfQc8hNV/uikTrFhjY9F/KvKxCg2DFri/PJzhEMhIG9EkdDdBB7kiCbedTUc/
+        LJakd+egvXXuXy5EF1yr86KeTH/b08ahY3oF0UPXYdtf8U4430Rn0eN4ZdL/LV7MdKZtiU/gqa+x
+        Vrix3sZ83W00JhiFS1RofUYHTMb19/rNLwAAAP//AwD1Vl/5hgQAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda3126a192318-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 23 May 2023 13:27:57 GMT
+      Function-Execution-Id:
+      - f495bweu71bh
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '23528'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 42fdfa1f232dd8dd51141935679ce725;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86497'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.335s
+      X-Request-Id:
+      - c4fdd30b1aa4a8c36dd882aa35dfae44
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
+      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
+      command is the appropriate command for this task.\",\n        \"plan\": \"-
+      Use the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
+      \"I need to ensure that I use the correct filename and text to write to the
+      file.\",\n        \"speak\": \"I will use the write_to_file command to write
+      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4638'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7RTyW7bMBC99ysGc/GFFmRlaaFbWwRtuqAokqAFqsKgqbHEmiIVcmQ7MPTvhbYk
+        TRegG3QRZt68hRweUOeYoiolq6o288ev3r55f3Xxcff6hXyaxO/OjuX1s5V8rrZJfIYC3eoLKR4n
+        IuWq2hBrZ1Gg8iSZckwXp0+O+y8WWLmcDKZY1Dw/ik7m3PiVm8dH8QIFNkEWhOkBa++qmpfsNmQD
+        pos4ORF4R37bSOKFQHYszR02SU5bgap0WlHA9NMBKwoTsXeGMEUZgg4sLXc2nWWyXYRDZgEAMuTS
+        NUXJIcMUxuLYoD13xQzPoZRbgtAoRSGsG2NuYOc1M1mYvSRjHHxw3uQz0JYdSFhrQ2BlRTnMyq6/
+        3HX9iPc8i+CyJLC0ZwhMNegA7KAJBFwSsAyb5RieQLmqkjbvALe1CRVlKO7b9SSDs9oWg+fLEQae
+        rhvtKUBFHU/nm37fNfQ2SrI/MAIX2iqCX50Sux7eKYj+79/nr420Q/Q5XP01m/KatdKhmjbAEvWT
+        ZEPjuznJcA61d1udE0jYSqNzGC4B1s5PEtoWPxUJNcnNJLDTxvzZMQyUrZg2eoR/t9Dd1Q5q39A/
+        MCV98fAt3F+w//Eipgh9jDFNZltsBa611aFcDtqYYmBXo0Btc9pjGref20dfAQAA//8DADOKIi/G
+        BAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda3bbfbeb10df-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 23 May 2023 13:28:24 GMT
+      Function-Execution-Id:
+      - f495jhtvkzjb
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '24141'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 1d5139fa1fd8c86452a62084086df67c;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86481'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.346s
+      X-Request-Id:
+      - f55c4da18a3d1ef16ef64b7b36e3afcd
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index c743a418..d77d361e 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -14,14 +14,13 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
-      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
-      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
-      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
@@ -50,7 +49,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3360'
+      - '3282'
       Content-Type:
       - application/json
     method: POST
@@ -58,20 +57,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4RSTW/aQBC991eM5rwgECG4vkWJVKFIvaT0kLpCy3qwN9i77s5YoUH+79ViTCqo
-        0uubmfcxMwe0OaZoSi2mbqrR4svz0/5r8nZ/f7uSp/rxYXf3/P1tKbJa3j2gQr95ISOnibHxdVOR
-        WO9QoQmkhXJMp7fJzTSZfZ7NFdY+pwpTLBoZzcbzkbRh40eT2WSKClvWBWF6wCb4upG1+B05xnRx
-        kyh85z7j09lCoXjR1RlKknmn0JTeGmJMfxywJh5og68IU9TMlkU7iSa9E3IxwCFzAAAZSunbohTO
-        MIUTeCrQXiKY4RK49G2VA4sOApvfEEjn1hUgJYF1LKE10Sqvp2PZC2xtRdDy0BG710fM+LrWLh9n
-        qP6WCqTZO+uKXu9bSbC1gQVYqAHLIB5al1OIOfIrVYjga6kltgb61dpAOfgt1HSp1FTa9SIjWDH9
-        216Ui+BH8S6JTbBijeV6WJkjOhKR4zZEIS2w/DDFhrY+EDTBG6K43ksNbkjvBv5XW1X/P8jgtafp
-        1HD1U9KroztdU69w3sqFCR2Ky1/pC7H3ffx6bYOJo5GTn8x12CncWme5XPdvgCmy+AYVWpfTHtNJ
-        97P79AcAAP//AwDMcPMmqgMAAA==
+        H4sIAAAAAAAAA5SSyY7aQBCG73mKUp1tBCEs41sSRQjlNppIWTxCjV22O9PudrrKAYL87lFjzEQw
+        GinXv5b/q+WIOscEs0pJVjcmXqzvdytn14vVt7vp992WHz63qw+/v36S9cd7jNBtf1Im54pR5urG
+        kGhnMcLMkxLKMZnMl+/m08l8No+wdjkZTLBsJJ6OZrG0fuvi8XQ8wQhbViVhcsTGu7qRjbgnsozJ
+        4u1dhM+9L/okdBQnylyk5XLWRZhVTmfEmPw4Yk08tPXOECaomDWLshIgnRWyYYBjagEAUpTKtWUl
+        nGICZ/EcoL0EMcU1cOVakwOL8gLbA3hSubYlSEWgLYtvs4DKm8lI9gKFNgQtDxkhe3PSMlfXyuaj
+        FKN/rTwpdlbbsvd7qAgK7VmAhRrQDOKgtTn5MEd+4wpB3FVKQqqnX632lIMroKZrp8Yo25vE8IXp
+        ZbxgF8TXxktTG8N7q8zhD70MlJOQr7Xtw5b2/Th8RZR5LTrTXA+7tkQnArLc+lCsBNZQtMYcXl3C
+        lgrnCRrvMqL+Ou7K+nob3JB6Gnx32pj/uvAoxb5ZFw3PdF7gzS9ZVVPvc1n2FYry5fUL9oGQ+1x+
+        izJAnEDOPKntsIuw0FZztem/CxNkcQ1GqG1Oe0zG3WP35i8AAAD//wMA2ddSQwEEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e437aafbd3132-SOF
+      - 7ca8f62c2bee313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -81,7 +80,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:24 GMT
+      - Sun, 21 May 2023 01:14:28 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -93,7 +92,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '8955'
+      - '11555'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -111,7 +110,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 2.336s
       x-request-id:
-      - d9ff235826db175c96d70ad1ed0ece57
+      - 7cc7737a077abeb1f4e9117975dfb9c1
     status:
       code: 200
       message: OK
@@ -140,16 +139,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SOUUvDMBRG3/0V4XtOR7tuzuVNEMQXEZyIiowsvWujbW5M7pg4+t9lMN3rgXM4
-        B/gGBq6z4obYF4vb19Uy1c+rh5zar/tHmm93w8/102Kabl6gwZsPcnIyJo6H2JN4DtBwiaxQA1Nd
-        Xs2qq3o5W2gM3FAPgzZKUU/mhezShouyLito7LJtCeaAmHiIshb+pJBhllONc/qMNYTF9v+gKqtR
-        w3XsHWWYtwMGyn/NxD3BwObss9ggx0MOQuF4f6f2NqvTsbKhUYGl86FVgfaqs1l1NkYK1Ewwamx9
-        8LlbJ7KZAwyycISGDw19w5Tj+3jxCwAA//8DAAI6aHtJAQAA
+        H4sIAAAAAAAAA0SOzUoDMRRG9z5F+NaZMrF/NjvRTXdSsSAiJc1cZ6IzuXFyS1vLvLsUqt0eOIdz
+        Qqhg4RsnvkttMV+u9mv6zquH5x+qH810KhNe3x8Pry9PR2jw9pO8XIyR5y61JIEjNHxPTqiCNbO7
+        yWxsZnOj0XFFLSzqJMV4NC1k12+5KMelgcYuu5pgT0g9d0k2wl8UM+ziVuOavmINYXHtPzClGTR8
+        w8FThn07oaP81+y5JVi4nEMWF+V8yFEonu+Xau+yuhwrFysVWZoQaxVprxqXVeNSokjVCIPGR4gh
+        N5ueXOYIiyycoBFiRQfYcngfbn4BAAD//wMAmYjYl0kBAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e43c3299e3132-SOF
+      - 7ca8f6881eab313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -159,7 +158,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:28 GMT
+      - Sun, 21 May 2023 01:14:32 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -171,7 +170,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '815'
+      - '1017'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -189,7 +188,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 88ms
       x-request-id:
-      - de6bee68ce2cb0df386f2ec71b499901
+      - e9912526fc04146baa08a05745789e1c
     status:
       code: 200
       message: OK
@@ -208,14 +207,13 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
-      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
-      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
-      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
@@ -240,14 +238,16 @@ interactions:
       "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
       the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
       \"The first step is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will start by reading the instructions_1.txt
+      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}], "temperature":
+      0, "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -256,7 +256,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4408'
+      - '4419'
       Content-Type:
       - application/json
     method: POST
@@ -264,19 +264,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSQYvbMBCF7/0VYs5ysNfpNutbeykLhUJJLluXIMtjW408MtKYDQ3+78Wxs2md
-        Uhb2+mbmvW+kOYEpIQPdKNZtZ6MPn5+2H9XXT7unx+0u/fLrEMdYbb75IglJARJc8RM1zxMr7drO
-        IhtHIEF7VIwlZMn9Zp1s0of1RkLrSrSQQd1xlK7eR9z7wkVxGicgoQ+qRshO0HnXdrxnd0AKkD3c
-        JxKu3i96sr6TwI6VvUpJnA4SdOOMxgDZ9xO0GC6+3lmEDFQIJrAiHikdMdK4wSknIYTIgRvX1w2H
-        HDIxi3MBjzyKOTwKQiwFO+FRlYIbFIYC+16PgGF/t+Iji8pYFH0wVJ87xtb9WdOubRWVqxzkn/4e
-        VXBkqJ5Ctv9xHbGVoSCq3nOD/q9GwY1icWWsnLXueZnWWUVTUCR2Af+N+JoVl8baGzbahHb5Vkih
-        93ih66lEP37DrbkosHIeReedRiwN1cuM0KE6XPyfjbVv/YjJfJCXI5grNzdAqsUp98VlgaZ8vTyd
-        qTD2XsdvMS8QZ5CZJ6cBBgmVIROa/XQgkEFg14EEQyUeIYuHH8O73wAAAP//AwBQh5C9ugMAAA==
+        H4sIAAAAAAAAA6SSQW/bMAyF7/sVBM92ECdtuvnWAjvkWmQYhnkIFJm2tcqUJ9GI28D/fXCcNK0z
+        DAN2fSTf+yjxgCbHFHWlRNeNje/Wj/uvvzbdiyq7x28Pm3Zpb3bzh8/36nZdYYRu95O0nCZm2tWN
+        JTGOMULtSQnlmCarjzerZbK6W0RYu5wsplg2Ei9nt7G0fufi+XKeYIRtUCVhesDGu7qRrbgn4oDp
+        p1US4cX7VU8GXZwoe5GSxaKPUFfOaAqYfj9gTeHs650lTFGFYIIoloHSsRAPGxwyBgDIUCrXlpWE
+        DFM4iacCdTKIGa6BiXIQB55UDlIRGA7iWz0Ahu1iJp1AYSxBGwyXx46hdXvUtKtrxfksw+itvycV
+        HBsux5DNX1wHbGU4HI2ZOoFAAq54NwBSKYELa+GsdftpamMVj4ExfAn0Z9R/WTXLOIZ7Vvb5ha76
+        YDDJScjXhukNtlATJkTaGzHahHr62MSh9XReq2itfYaWc/LDb16zwY4K5wka7zRRfvwHN4mevkZo
+        SD2dc/fG2v/94dG8j87XdapcHRermsbcV5cJmvLl9CbHwtB7Gb/GPEMcQU48GffYR1gYNqHajpeH
+        KQZxDUZoOKcO03n/o//wGwAA//8DALRhJ3cTBAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e43cb8d2c3132-SOF
+      - 7ca8f6916aeb313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -286,7 +287,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:38 GMT
+      - Sun, 21 May 2023 01:14:45 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -298,7 +299,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '10025'
+      - '13200'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -310,13 +311,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86473'
+      - '86470'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.35s
+      - 2.353s
       x-request-id:
-      - f3965dabcf1a56d3abe0b97dd37818a9
+      - 13087de20c75011601dacf71bc0bd2f3
     status:
       code: 200
       message: OK
@@ -345,28 +346,24 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPXUvDQBBF3/0VwzxvSmJqW/etFJRSfBD8qiJlm4xN7GZn2ZlapeS/S6Ha18u9
-        h3MP2NZosWqcVl302fj29eFuG++f3OOikPFyMZu+xNnz8kY2RYkGef1JlZ4Wg4q76ElbDmiwSuSU
-        arTFaDIsJuX1KDfYcU0eLW6iZuXgKtNdWnOWl3mBBnfiNoT2gDFxF3WlvKUgaIvL3OCZ/Z8fY2V1
-        /twc5r3BquG2IkH7dsCO5I+a2BNadCKtqAt6dOSgFI7+UwEH8iNKnYE5JKqc96CNU5jD3gmc7oAL
-        NWhDiaBxXwRrogCBIdAeavoiz7GjoALKkChy0gH2Bj/a0EqzSuSEA1oU5YgG21DTN9q8f+8vfgEA
-        AP//AwCDczclewEAAA==
+      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
+        with other requests. You can retry your request, or contact us through our
+        help center at help.openai.com if the error persists. (Please include the
+        request ID a73e800f9a4efa08668a838196d2950d in your message.)\",\n    \"type\":
+        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e441959f03132-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
+      - 7ca8f6f52c0d313e-SOF
       Connection:
       - keep-alive
-      Content-Encoding:
-      - gzip
+      Content-Length:
+      - '349'
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:42 GMT
+      - Sun, 21 May 2023 01:15:18 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -378,7 +375,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1498'
+      - '30010'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -396,7 +393,87 @@ interactions:
       x-ratelimit-reset-tokens:
       - 107ms
       x-request-id:
-      - 61ac2d72f5c8a08789008f8ad509a4f1
+      - a73e800f9a4efa08668a838196d2950d
+    status:
+      code: 429
+      message: Too Many Requests
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
+      task is to create a concise running summary of actions and information results
+      in the provided text, focusing on key and potentially important information
+      to remember.\n\nYou will receive the current summary and the your latest actions.
+      Combine them, adding relevant key information from the latest development in
+      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
+      ''system'', ''content'': ''This reminds you of these events from your past:
+      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
+      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '713'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SPTWsCQRBE7/kVTZ9nZdc1msxNEEUIxITkICHIONtxN85OT2bajyD734Ng9FpU
+        PV6dsKlQo62N2Da4bDR/PT71l2/j5/fN43LyMt0vthOfF9PZz2yBCnn9TVYui57lNjiShj0qtJGM
+        UIW6GD4MhmUx6pcKW67IocZNkKzs3Weyi2vO8jIvUOEumQ2hPmGI3AZZCW/JJ9RFP1d4Y1/zcyws
+        xt2ag7xTaGtuLCXUHydsKf1TIztCjSalJonxcnZkL+TP/uMEBtJvEmoVzCGSNc6B1EZgDgeT4HIH
+        jK9AaooEtdkTrIk8eAZPB6hoT45DS14SCEOkwFF62Cn8anyT6lUkk9ijxiQcUGHjKzqizrvP7u4P
+        AAD//wMAmH2nWHsBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7ca8f7cdac76313e-SOF
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 21 May 2023 01:15:24 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - user-gsghk4kr5xmbjprowdzr8zt2
+      openai-processing-ms:
+      - '1554'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '89839'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 107ms
+      x-request-id:
+      - 2bcd88e9e8bce8177b8e694d44cd16fc
     status:
       code: 200
       message: OK
@@ -415,14 +492,13 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
-      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
-      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
-      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
@@ -448,25 +524,27 @@ interactions:
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
       and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
-      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"I need to read the instructions_2.txt file using the
       read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}], "temperature": 0, "max_tokens": 0}'
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
+      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -475,7 +553,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5368'
+      - '5468'
       Content-Type:
       - application/json
     method: POST
@@ -483,20 +561,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSUW/TMBDH3/kU1j27VdNu3ZK38TAGEgKJIqQtqHKdS2LmnCP7wipV+e4oTUIg
-        RQiJ17vz7/+zfScwGSSgS8W6qu3i5s3j7sOX+OF++3hXvd++bh7ud/ndx0/rOH73HSS4wzfUPJxY
-        alfVFtk4Agnao2LMIIm2t1fR7SberiVULkMLCRQ1LzbL6wU3/uAWq80qAglNUAVCcoLau6rmPbtn
-        pABJFF3fSJjgU+NqLYEdKzuV1nHcStClMxoDJE8nqDCMYO8sQgIqBBNYEXeajhipu8IpJSGESIFL
-        1xQlhxQSMRSHBh65K6bwVhBiJtgJjyoTXKIwFNg3uhMM+82SjyxyY1E0wVBxnuhG9+eadlWlKFum
-        IH/le1TBkaGiD9n9hdppK0NB5I3nEv1vg4JLxWJyzJ217mWeVltFfdBCfA74Z8V/ueIcrL1ho02o
-        5m+FFBqPo11DGfruGy7h4oC58yhq7zRiZqiYZ4Qa1fPIfzHW/u9H9PBWjkswdC52gFSFfe5PykxN
-        +WK+On2jm52OX2qOEmeRwSelFloJuSETyn2/IJBAYFeDBEMZHiFZtV/bVz8AAAD//wMAarkDSrsD
-        AAA=
+        H4sIAAAAAAAAA6SSXYvTUBCG7/0Vh7lOSmPcVnMnIliQBcUFdSPl9GSSHHsyE86ZsF1L/rukSe2a
+        igjezsf7PvNxBFtABqbWYprWxevNx8Nt+Vbvv6yWZf35/e3dK/Jf3xj37sNGIALefUcjU8fCcNM6
+        FMsEERiPWrCALFm9fLFKk/XzmwgaLtBBBlUrcbq4iaXzO46X6TKBCLqgK4TsCK3nppWt8B4pQJYk
+        61UEF/FLYpVEICzaXUJpuu4jMDVbgwGy+yM0GM7Cnh1CBjoEG0TTMIFhEqRhhGNOSimVg9TcVbWE
+        HDI1BacEHmQI5rBRhFgoYeVRF0pqVJaC+M4MgGGbLuQgqrQOVRcsVaeKoXR7ihluGk3FIofoqb5H
+        HZgsVaPJp7+oDtjaUjgJEx5EBRTF5W8NSmot6sJasnP8MHdtnabRMFZ3Af+M+i+j5jnF6jVp9/gD
+        r+rUIFKgoG8s4RNswTbMiIy3Yo0NzXzZSKHzeB6r7Jx7VB0V6IdrXrOpHZbsUbWeDWJxugPPrOfb
+        CC3q/dn3wTr3vxcexfvo/F1T5uq5SDc4+v5SmaFpX81/ckwMtZf2a8wzxAlk4smphz6C0pIN9Xb8
+        PMggCLcQgaUCD5At+2/9s58AAAD//wMA0m5dIxQEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e44259b713132-SOF
+      - 7ca8f7d89a64313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -506,7 +584,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:52 GMT
+      - Sun, 21 May 2023 01:15:37 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -518,7 +596,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '9839'
+      - '12147'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -530,13 +608,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86463'
+      - '86457'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.358s
+      - 2.362s
       x-request-id:
-      - d620e6b69245523ab217d979b4e6b8c5
+      - 7d145f8982be5decde986f8f3ae9b1e1
     status:
       code: 200
       message: OK
@@ -567,16 +645,17 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SPyUoDQRRF935FcdfVIW1nsnZBQQ2CGxcOSKhUv6TLdA32e8HE0P8uESXbA/dw
-        7hG+hoFrrLiQ22J6+/pkXyafD9/0eMnzcbh+3tZ368VifzP30EirD3Lytxi4FHJL4lOEhuvICtUw
-        5WQ2KmfV1XSkEVJNLQw2WYpqMC5k161SMayGJTR2bDcEc0TuUsiylLSlyDBlVWqc3Wc+1pAktj2T
-        0aTXcE3yjhjm7YhA/G/tUkswsMyexUY5NaYoFE/9c1ZW8YGFglb3qiNn21ZJY0XFJI2PGxXpSzWW
-        VWNzpki1Yh8dqXBQv1d9igP0GmsfPTfLjiynCAOWlKHhY017mGH/3l/8AAAA//8DAIp+DXNmAQAA
+        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJWn6obPrwkUVRV2IIFKmk2cyNpk3ZF5rS8l/l4qS7YF7
+        OPcMX8HANVZcF9tsuX45uunbqpo+Hl5v7w93ZZzWz7sHe1rePEGDt1/k5G8xcdzFlsRzgIbryQpV
+        MMXierYoi+Us1+i4ohYGdZSsnMwz2fdbzvIyL6CxT7YmmDNiz12UjfCOQoIpykJjdI98riEsth3J
+        bDFouIa9owTzfkZH6d/ac0swsCn5JDbIpZGDULj0r5KyKp2SUKfVWvXkbNsqaayowNL4UKtA36qx
+        STU2RgpUqeSDI9Wd1O9Vz2GCQePTB5+aTU82cYBBEo7Q8KGiI0w+fAxXPwAAAP//AwDlYq8fZgEA
+        AA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e44729ae33132-SOF
+      - 7ca8f835ef47313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -586,7 +665,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:52:56 GMT
+      - Sun, 21 May 2023 01:15:41 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -598,7 +677,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1279'
+      - '1511'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -616,7 +695,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 115ms
       x-request-id:
-      - 108cd79db4a91eae5537da9b33f492bc
+      - 5dad92e7ce5734a1e14ff1816067b8c8
     status:
       code: 200
       message: OK
@@ -635,14 +714,13 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
-      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
-      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
-      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
@@ -668,35 +746,40 @@ interactions:
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
       and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
-      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"I need to read the instructions_2.txt file using the
       read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to read the instructions_3.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The instructions_3.txt file contains further instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file using the read_file command.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
+      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will read the instructions_3.txt
+      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\r\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -705,7 +788,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6279'
+      - '6470'
       Content-Type:
       - application/json
     method: POST
@@ -713,19 +796,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6yST2vcMBDF7/0UYs7yYtcbJ9G9lIUWAt0W2joYrTyxlZUlVxonC4u/e/GfxYlL
-        D6G9vqeZ95P0zqBLEKBqSappTXT98cdeffpw/G4Od9nTgT7ffdmfnh53WWy+3QIHd3hERfPERrmm
-        NUjaWeCgPErCEkSS3WyTm/T2OuPQuBINCKhaitLNVUSdP7goTuMEOHRBVgjiDK13TUsFuSPaACJJ
-        twmHZfliZCkHciTNIl3F256Dqp1WGED8PEOD4bLYO4MgQIagA0lLA6azhHa4wjm3jDGWA9Wuq2oK
-        OQg2i7OBJxrEHHbMIpaMHHv2mpBRjYxkOBa6ZNqSGwXXUdvRhk7EHrRB1gVtq9EZhwpyxagr1zTS
-        lpsc+Ms0jzI4q201Re5rZNoG8p0aHiEwj7867ZE1+DaOdU5rpJ0iIvY14N8B/y1GeU1a6dCsXxBt
-        6PywUxLbvQhQzntU9Oag0KI8XkKetTH/94+mqJ5f2jI7f5TFygYnilebVrDSV+ueTcZwdlmxYL6a
-        X9fyfZpsL4Qj5Qyb2x56Dg/a6lAXU7FAQCDXAgdtSzyBiPv7/t1vAAAA//8DALNiCnsBBAAA
+        H4sIAAAAAAAAA6xSy27bMBC89yuIPVOGVT+S6AvqU4GmLVBUhcFQG4kxuauSK9iooX8vZNlwoqAH
+        A73OcGdml3MEV0EBtjFiQ+uzu82XQxU2n/fm4T48uqXP/cv3Bv+sqk8/BDTw0wtaOU/MLIfWozgm
+        0GAjGsEKinx9v1wv8rtlriFwhR4KqFvJFrNVJl184my+mOegoUumRiiO0EYOrWyFd0gJinxx96Dh
+        Kn4l1msNwmL8FVotV70G27CzmKD4eYSA6SIc2SMUYFJySQwNG1gmQRpWOJaklFIlSMNd3UgqoVBn
+        8EzgQQawhI0ixEoJq310gkoaVGLSbusq5Uj4BHAnbSczOYh6dh5VlxzVJ+Y0tBXennDLIRiqZiXo
+        124RTWJyVI+WXxtUjpLEzg5HSCri785FVAFvyzH1ab2h0SJT3xL+O+BtNmVJmXpsOql4TxNLG504
+        61KYXhMpdXHQN6I2r8wsx4hWbt4ttWh2F5O98/7//tdo1etLc87Mu+KQCTimeKM0CWtiPe3cSAxv
+        rxLXmG/mpxX9uMiXl4SnlOewJfXQa3h25FKzHUsGBSThFjQ4qvAAxbz/1X/4CwAA//8DALYwIcUN
+        BAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e447bcfeb3132-SOF
+      - 7ca8f8408fbb313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -735,7 +819,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:53:07 GMT
+      - Sun, 21 May 2023 01:15:53 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -747,7 +831,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '10958'
+      - '12090'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -759,13 +843,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86469'
+      - '86458'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.354s
+      - 2.36s
       x-request-id:
-      - 27a8792867dc32731b494d23250a8aec
+      - a5f70c956e20dee73bf6f83f3ca1b262
     status:
       code: 200
       message: OK
@@ -796,16 +880,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA0SPTUsDMRRF9/6KcNeZ0rHf2SmCWHBTKoIiJc08m+jkg3mv2lLmv0tF6fbAPZx7
-        Qmhg4LwVF0tbze5f1mV2eAzxdtktj9PV13h1mKyX5flpdgeNvP0gJ3+LgcuxtCQhJ2i4jqxQA1NP
-        5+N6PlrMFxoxN9TCYFekGg0mley7ba6Go2ENjT3bHcGcULoci2wkf1JimPp6qnFxX/hEQ7LY9kLG
-        da/hfA6OGOb1hEj8b+1ySzCwzIHFJjk35iSUzv03rKziIwtFrR5UR862rRJvRaUsPqSdSvStvGXl
-        bSmUqFEckiMVj+r3ashpgF7jPaTAftOR5ZxgwJILNEJq6AAz7N/6qx8AAAD//wMAecEeqGYBAAA=
+        H4sIAAAAAAAAA0SPMW/CMBBG9/4K62YHkQKh8tZOZWBhq6oKuc4Rmzp3bu4QRCj/vaJqxfqk7+l9
+        V0gtOAjRa+hLrtab3UVQRzlr+3o8rHflbUO5exm38XsLFvjziEH/FrPAfcmoiQkshAG9Yguubp6W
+        zaJerxoLPbeYwUFXtFrMVpWehk+u5ot5DRZO4jsEd4UycF90r/yFJODqx8bC3X3nKwvK6vOdLOvJ
+        QoicAgq49yv0KP/WgTOCAy+SRD3prZFJkW79z2K8kVEUe2s2ZsDgczYavRpijYk6Q3g20YuJvhQk
+        bI0kCmj60fxeTUwzmCwcEiWJ+wG9MIEDUS5gIVGLF3Dz6WN6+AEAAP//AwCfo6VWZgEAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e44cdfcc83132-SOF
+      - 7ca8f89d1b52313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -815,7 +899,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:53:10 GMT
+      - Sun, 21 May 2023 01:15:58 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -827,7 +911,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '1138'
+      - '1539'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -845,7 +929,7 @@ interactions:
       x-ratelimit-reset-tokens:
       - 112ms
       x-request-id:
-      - f0b536a2bcc40f0b21989941177bcbad
+      - 8885d0872614ba24235f88115811c52a
     status:
       code: 200
       message: OK
@@ -864,14 +948,13 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read text from file, args:
-      \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args: \"filename\":
-      \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n7. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n10.
-      list_agents: List GPT Agents, args: () -> str\n11. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n12. start_agent:
+      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
       \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
@@ -897,39 +980,44 @@ interactions:
       \"I should start by reading the instructions_1.txt file using the read_file
       command.\",\n        \"reasoning\": \"The first step is to understand the instructions
       and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file.\",\n        \"criticism\": \"I need to
-      ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
+      the instructions before proceeding to the next steps.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"I need to read the instructions_2.txt file using the
       read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file using the read_file command.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to read the instructions_3.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The instructions_3.txt file contains further instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file.\",\n        \"criticism\":
-      \"I need to ensure that I understand the instructions before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file using the read_file command.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
+      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to write the task_id into the output.txt file
-      using the write_to_file command.\",\n        \"reasoning\": \"The instructions
-      require me to write the task_id into the output.txt file.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the task_id into the output.txt file.\",\n        \"criticism\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I fully understand the instructions before proceeding to
+      the next steps.\",\n        \"speak\": \"I will read the instructions_3.txt
+      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\r\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to write the task_id into the output.txt file using the write_to_file
+      command.\",\n        \"reasoning\": \"The instructions require me to write the
+      task_id into the output.txt file.\",\n        \"plan\": \"- Use the write_to_file
+      command to write the task_id into the output.txt file\\n- Shutdown\",\n        \"criticism\":
       \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
       \"I will write the task_id into the output.txt file using the write_to_file
       command.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
@@ -946,7 +1034,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '7262'
+      - '7465'
       Content-Type:
       - application/json
     method: POST
@@ -954,20 +1042,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5ySy27bQAxF9/2KAddjw4YfibXLqnBRtCjaAEWqwBiPKGni0VAZUnEKQ/9eyJZj
-        x23Rx5YE7z2X5A5cBgnY0oitaj+4env35TF/WnwkfKintx8+bT6/n83ePU3vljdfQQOtH9BKPzG0
-        VNUexVEADTaiEcwgGc+vp+PryWIx0lBRhh4SKGoZTIazgTRxTYPRZDQGDQ2bAiHZQR2pqmUltMHA
-        kIxn07mGk/hZY6xBSIw/leaLq1aDLclZZEi+7aBCPgpH8ggJGGbHYoJ0mBQEQxdhlwallEpBSmqK
-        UjiFRPXFvoHP0hVTWKrSPKHqmTBTxnslJSoxvGEV8bFxETNFuapwqJaKS2p8pgJtFZeNqIy2QTXs
-        QvEytjqqdbKVCdkwBX1uH9EwBReKVww5eU/bMwQXWGJju02xMiH7W8oLt9qbcDAaqFvG32MqoVOm
-        SxUbnTjruDoyB8T9BAZuYqdqRP1hm2vMKeLeQ7qF/cqHazSb/7zN1nn/z5c5mLf6+DR956efCabC
-        A9crpQt8E4vLdzu/+UHgpsuxz3DKxo21yJw33n9/odqT9YBpaKHVkLvguFwd5CABFqpBgwsZPkMy
-        au/bNz8AAAD//wMAqcemK/wDAAA=
+        H4sIAAAAAAAAA5SSza7TMBBG9zzFaNZp1ar0tsqOxV0UJCSqi4REUOU6k8TUsYNnTIuqvDvKz6Vt
+        EAu2M8o53+fJFU2OKepKia4bO9vs9pfo3+e2qD7a1f5TuXj+snfNy/rZfmBM0B+/k5bxi7n2dWNJ
+        jHeYoA6khHJMl0/bt0+r5Wa9TbD2OVlMsWxktpqvZxLD0c8Wq8USE4ysSsL0ik3wdSMH8SdyjOly
+        vd0keIPfFqtFguJF2dtos9y0CerKG02M6dcr1sSv4OAtYYqK2bAoJ11M74RcV+GaOQCADKXysayE
+        M0xhHI4Lukg3zHAHjigH8cBVlNyfHUQ2rgSpCETx6TDGJdC+rpXL5xkm96xAir0zrhyALxWBcSwh
+        6q4iQ6Af0QSCmh4sqhAKcA5GHmwmB+PE9wMfpYkyl4tAYSxNxY1VbnDO4DPTvxPfeycM3fm14Xr6
+        GuQ4ho6pBHZQqZ89rcfmoKztbWO1vNcyHKnwgXpVX6rzTUNzQ+r0Kjsba//n3QdQm7zed9z8dV6n
+        ahocD6RJFBXK6Z9xf9EB8K6r2re71eeoNTEX0dpff1L1ycaAmWuxTbAwznB1GHCYIotvMEHjcrpg
+        umi/tW9+AwAA//8DAMizuHGnAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7c7e44d668223132-SOF
+      - 7ca8f8a7ea59313e-SOF
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -977,7 +1065,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 15 May 2023 20:53:21 GMT
+      - Sun, 21 May 2023 01:16:07 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -989,7 +1077,7 @@ interactions:
       openai-organization:
       - user-gsghk4kr5xmbjprowdzr8zt2
       openai-processing-ms:
-      - '10500'
+      - '9391'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1001,13 +1089,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86473'
+      - '86464'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.35s
+      - 2.356s
       x-request-id:
-      - 3e4b1ed00d4d2de4b39db61f42246015
+      - 2e3c14cd6285c662dde517d25194a06f
     status:
       code: 200
       message: OK
@@ -1029,7 +1117,7 @@ interactions:
       args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
       Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
@@ -1054,6 +1142,10 @@ interactions:
       which next command to use, and respond using the format specified above:"}],
       "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -1061,7 +1153,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3286'
+      - '3284'
       Content-Type:
       - application/json
     method: POST
@@ -1069,60 +1161,67 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCMsFUt+iSJWoeomU9lJXaFiP7S3rXXd3nEAR/73aGEgL
-        FZde5+t93pnZo66wQNWSqK436WL59LhYh8/t42x3/5Wz2cPDz2yg54/5p/wZE3TrH6zk2DFRrusN
-        i3YWE1SeSbjCIpvfvZ/ni3yWJdi5ig0W2PSS5pNZKoNfu3SaTzNMcAjUMBZ77L3relmJ27ANWCzy
-        aYJvs8/xbJ4lKE7InEN3H7JDgqp1WnHA4tseOw6nsd4ZxgIpBB2ErERIZ4VtNLAvLQBAidK6oWkl
-        lFjAMXhM8FZisMQlhNYNpoIg5AXWO/BMlbYNSMugbRA/qIgaVtlEtgK1NgzioGJh32nL8NKSAI1F
-        MSO0YbC8lUmJyZ+qnik4q20zSj/dEIhmSMd5bZylonO/A21r5zuK5X8zjGVbgSDch0vh3pAdNVP4
-        EsbqaHN11Oo6slUcGIO3jJelTeHektn94qu6W0QXQMpr0UqH7nQEy/wKwDYMPjaTwBKog9oZ417+
-        dQ8gpQZPwmYHEZ/rWivNVszu0n/omTYnqRdtzH9c+2rTo9AhOT3dcZ1XP2ep45HhvPoLTPLN5auO
-        iVj71n6NeYJ4BTnylPaAhwRrbXVoV+PrYYFBXI8JalvxFovp4fvh3W8AAAD//wMAa4jrZSkEAAA=
+        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCAohxLeop0StegmHqq7Qsh7bG/bD2h0LO8j/vdoYSAsV
+        l17n633emTmgKjBDWQuWptHp/fO3r7z88rh23/sfvVJv69fw8vl5ZxZdUWKCbvtKko8dE+lMo4mV
+        s5ig9CSYCsxmy9VitVjdTR8SNK4gjRlWDafzyV3Krd+6dDqfzjDBNoiKMDtg451peMNuRzZgdj+f
+        Jvgx+xyfLWcJsmOhz6HVw2xIUNZOSQqY/TygoXAa650mzFCEoAILyxHSWSYbDRxyCwCQI9eurWoO
+        OWZwDB4T1HEM5vgEoXatLiCw8AzbHjyJQtkKuCZQNrBvZUQNm9mEO4ZSaQJ2UBCTN8oS7GvBIMai
+        mGGxI7DU8STH5E9VTyI4q2w1Sr/cEIhmhIrz6jhLRue+B2VL542I5X8zjGUdQ2BqwqVwo4UdNVNY
+        h7E62twctYwRtogDY/CW8Ty3KTxaofs3uqq7RXQBJL1iJVUwpyNYoncAsqH1sVkwPIEwUDqt3f5f
+        9wAhZesFk+4h4lNZKqnIsu4v/YeGxO4ktVda/8e1rzY9Cg3J6emO67z6OSsMjQzn1V9gCl9dvuqY
+        iLUf7deYJ4h3kCNPbgccEiyVVaHejK+HGQZ2DSaobEEdZtPh1/DpNwAAAP//AwBBklTnKQQAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca981339872aa10-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda46dcdfe13f2-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 02:49:23 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Tue, 23 May 2023 13:28:48 GMT
+      Function-Execution-Id:
+      - f495yye134fc
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '12546'
-      openai-version:
+      Openai-Processing-Ms:
+      - '19439'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 84cce4a68c05919b6fe5a262ed4a2f23;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86493'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Remaining-Tokens:
+      - '86494'
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.337s
-      x-request-id:
-      - 0fd7ee0fe93ef38d279da345e7367fc6
+      X-Ratelimit-Reset-Tokens:
+      - 2.336s
+      X-Request-Id:
+      - d999eccb67e039480b5f0d38b5dc5b63
     status:
       code: 200
       message: OK
@@ -1144,599 +1243,7 @@ interactions:
       args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file to determine what actions to take next.\",\n        \"reasoning\":
-      \"The instructions_1.txt file contains the necessary information to determine
-      the next steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_1.txt file\\n- Analyze the instructions to determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I am following the
-      instructions accurately and efficiently.\",\n        \"speak\": \"I will start
-      by reading the instructions_1.txt file to determine the next steps.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4463'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySQW8aMRCF7/0VozkvCLIpJHur1B4QaqVK5NJuhRzvwLqxx1t7VoEg/nvlZQkp
-        iCrXmXnvfWPPDk2FBepaiXaNHUxni+9fbx8+V3Vr5u7my4/7+bd5nt/d/XkZLTBD//ibtPSKofau
-        sSTGM2aoAymhCovx5O52kk/zySRD5yuyWOC6kUE+/DiQNjz6wSgfjTHDNqo1YbHDJnjXyFL8E3HE
-        4n4yzfDk/VofJ0fxouypNM7zfYa69kZTxOLnDh3Fo2/wlrBAFaOJolgSpWchThvsSgYAKFFq365r
-        iSUW0Bf7Bm0kFUtc1ARMGwHDUUKrExaYCOIhkKpAanrbisuboWwEVsbSEGYQa9/aCtpI3WSSLFMP
-        tHdOcfWPTycqMXtLEkhFz4bXJ5wrcZAWVIZj58Wk02uELRhe+eBUBy4eKhIKzjD1YxuBKNTE8+DG
-        Kj5kDuDhXfhXuMqSB/CJld2+0MXc/4jOgHQwYrSJ7kA1AybqAIhjG5JYCcxAOVh5a/2z4fVlnNK6
-        DUrIbiHh02pltCEWuz3fPzakno5Rz8bad37itWMo8eC+z47X16svjo+Vo0Pwa9IZmwrr85s9NNLs
-        SX6JcoToQHqekve4z3Bl2MR6ebg3LDCKbzBDwxVtsBjtf+0//AUAAP//AwC7HghxMwQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca981943804aa10-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:49:39 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '12905'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86464'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.356s
-      x-request-id:
-      - a4e14f0652013c53af07d6d7cdc9463d
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that I was
-      created and there have been no new developments to report."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5544'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySQY/aQAyF7/0Vls8BQbMLq9x6aCvUy1aip6ZCw8RJpkw8YcbRQlH+ezUQli2I
-        aq+233ufZ3xAU2CGulaim9aO5ovld/312/OkfNh2dr3ZTb5sn9Pl9nOl1lNM0K1/k5ZBMdauaS2J
-        cYwJak9KqMBsOnt6mKXz9Oljgo0ryGKGVSujdPw4ks6v3WiSTqJZF1RFmB2w9a5pZSVuQxwwm06f
-        5glezC+N2SxBcaLspZQ+pn2CunZGU8Ds5wEbCmdj7yxhhioEE0SxREzHQhxXOOQMAJCj1K6ragk5
-        ZjAUhwbtJBZzXNYETDsBw0F8pyMWmADiwJMqQGp62wqrdCw7gdJYGsMCQu06W0AX6DgZJavYA+2a
-        RnHxj89RlGPylsSTCo4NVxecO3EQF1SGw9GLScfX8HswXDrfqCO4OChIyDeGaRjbCQShNlwHt1bx
-        KXMEP96Ff4crz3kEn1jZ/R+6mfsf0RWQ9kaMNqE5US2AiY4AxKHzUawEFqAaKJ217sVwdRuntO68
-        ErJ7iPhUlkYbYrH76/1DS2pzjnox1r7zE+8dQ44n9z45X9+gvjk+Vg2dgl+TrtiUr65v9tSIsxf5
-        LcoZ4ggy8OTcY59gadiEenW6N8wwiGsxQcMF7TCb9L/6D38BAAD//wMA4kH/FDQEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca981f6cdeaaa10-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:49:56 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '13771'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86449'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.367s
-      x-request-id:
-      - 7274eefc2f8ca180d18d471f1f234e01
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\r\nShutdown"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6578'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6STTWvbQBCG7/0Vw5xlY9d2bOvYFIovhdKUFqpgNquxtc1qRuyOsIPxfy+SbJQo
-        oRRynY/3fWZn9oQuxxRtYdSWlR8tN3ffomg+L37e6G3+NexunxafFvzr8xdeYYLy8IesXjrGVsrK
-        kzphTNAGMko5ptOb1fxmtpytVwmWkpPHFPeVjmbjxUjr8CCjyWwyxQTraPaE6QmrIGWlW5VH4ojp
-        dLZeJNiL94nVPEEVNb4PLZbrc4K2EGcpYvr7hCXFq3AQT5iiidFFNawNprASNyOcMgYAyFALqfeF
-        xgxTuAQvCTpqE8zwriBgOio4jhpq22CBi6ACh+CUQAsCNfFx63JwrNIGds4TSK1VrWM96hg2EAup
-        fQ517Fra5q3Kti21UpaG8/9QHWeYPCcNZKKw432P+7Z0w1wQmKoKUgVn9IVri/VP836aNzkqb7hD
-        GMGPd8w4sMkyHsH3otZcDjywtMGpsy6Wne8GmKiVJ451aPSNwgZMCTvxXg6O963Fs01GMNbWwSj5
-        J2jgaLdz1hGrfxpOGCsyj1erg/P+Xbt8/Zyd1zm5HudF59Vtsimpw3jhO6A1YT886y7R1PYSPcaL
-        /uEv+Dibzq+ELeUFNuMznhPcOXax2Ha3iClGlQoTdJzTEdPJ+f784S8AAAD//wMAkanDf3AEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9825e8926aa10-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:50:13 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '14155'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86448'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.368s
-      x-request-id:
-      - 6618011a94c8d2d73f905e11279742af
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\r\nShutdown"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to write the task_id into the
-      file output.txt. I should use the write_to_file command to write the task_id
-      into the file.\",\n        \"reasoning\": \"The write_to_file command is the
-      appropriate command to use to write the task_id into the output.txt file.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the task_id into the output.txt file\\n-
-      Shutdown\",\n        \"criticism\": \"I need to ensure that I am following the
-      instructions accurately and efficiently.\",\n        \"speak\": \"I will use
-      the write_to_file command to write the task_id into the output.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
-      "system", "content": "Command write_to_file returned: File written to successfully."},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7672'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SSTY/aMBCG7/0VozkbRJYFqtxQ1QMnqu1WPTQV8jqTxItjp56JWITy36tAEB/d
-        Su117Hmedzw+oM0xRVNpMXXjRovV89Py03o93X/+spwli+X61T25/a/vX/18hgrDyysZGTrGJtSN
-        I7HBo0ITSQvlmCbzj4/z6eIxmSusQ04OUywbGU3Hs5G08SWMJtNJggpb1iVhesAmhrqRjYQtee4B
-        D4nCC/xyME0UShDtLqXF7KFTaKpgDTGmPw5YE5/BMTjCFDWzZdFe+pjBC/l+hEPmAQAylCq0ZSWc
-        YQpDcTigN+mLGT5XBIX12oH1LLE1fS6wDBKAq1bysPNjWAFXoXU5tEwgFYFo3m6GQQhMqGvt85ue
-        DNW1MZLm4K0vL9r3Gb26ItBNE0MTrb7FH/1/tzRO+5NgBN/+Neodw0Qr1liuT6AVeKLjffLcxp6p
-        BVagayiCc2FnfXn0XL0fgzamjVrI7aG3UVFYY8mL299H5ob09qzaWef+641PpE6dNz7c+mPhXtd0
-        ktxQ77LoWN7/levtDavTvIUzIAdujSHmonXH2S6d3ZAt8x12CgvrLVebEwlTZAkNKrQ+pzdMJ93P
-        7sNvAAAA//8DAD5/N2e0AwAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca982c97d0caa10-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:50:27 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '11247'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86446'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.368s
-      x-request-id:
-      - 6de56a4a30bcbcde1a14399232252d53
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
       Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
@@ -1775,6 +1282,10 @@ interactions:
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -1782,7 +1293,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4461'
+      - '4459'
       Content-Type:
       - application/json
     method: POST
@@ -1790,60 +1301,67 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5SSQW/bMAyF7/sVBM920MyZs/lWbJcARU/rNmAeAlWmba0SZUg06izIfx8cJ02X
-        IMN2Jfn4Pkpvi6bCAnWrRLvOpsvVw7e7sPT37vaTltBk8Us1tJvuq/14f4cJ+sefpOWgmGnvOkti
-        PGOCOpASqrCY5+8X+WKeL7IEna/IYoFNJ2k2e5dKHx59epPdzDHBPqqGsNhiF7zrZC3+iThi8SFf
-        Jnja/VKf53mC4kXZU2meZbsEdeuNpojF9y06ise9wVvCAlWMJopiGSk9C/F4wbZkAIASpfV900os
-        sYBD8dCgQcZiiZ9bAqZBwHCU0OsRC0wE8RBIVSAtvW7F9duZDAK1sTSDFTwba6GPtJ8bBeuxA9o7
-        p7j6Y8teUmLymiOQip4NNyeYK2YwnqcMx/0uJj2+RdiA4doHp/bY4qEioeAM02FsEIhCXTw37qzi
-        yTOFh3/Cv8JVlpzCLSu7+UUXc38jOgPSwYjRJrqJagVMtAcgjn0YxUpgBcpB7a31z4abSzuldR+U
-        kN3AiE91bbQhFrs5vz92pJ6OVv/xideiUOK0fZccs3dQX0SPlaPJ+MXpjE2F5jyxU2OcPckvUY4Q
-        e5ADT8k73CVYGzaxXU95wwKj+A4TNFzRgMXN7sfuzW8AAAD//wMANnJsjjEEAAA=
+        H4sIAAAAAAAAA4ySQW/aQBCF7/0VoznbCEJCqG9FUSqKcqkSKVIdoWU9trdZz1q7YwWK/N8rYwgp
+        iCrXmXnzvtl9WzQZJqhLJbqqbXz74+Hh+2xTL2bPzXNe0t3j4u5+pYZPPxeze4zQrX6Tlr1ioF1V
+        WxLjGCPUnpRQhsloMr2eXk9vxlcRVi4jiwkWtcTjwU0sjV+5eDgejjDCJqiCMNli7V1Vy1LcK3HA
+        5OvkNsLj7vf6aDKJUJwoeyyNxuM2Ql06oylg8muLFYXDXu8sYYIqBBNEsXSUjoW4u2CbMgBAilK6
+        piglpJjAvrhv0Fq6YoqPJQHTWsBwEN/oDgtMAHHgSWUgJX1sheXVQNYCubE0gDmE0jU2gybQbrKT
+        LLseaFdVirN/9uxEKUYfSTyp4NhwccS5YAfdgcpw2O1i0t1r+A0Yzp2v1A5cHGQk5CvDtB9bCwSh
+        Opwa11Zx7xnD06fwL3ClKcfwjZXd/KGzuf8RnQBpb8RoE6qeag5MtAMgDo3vxEpgDqqC3Fnr3gwX
+        53ZK68YrIbuBDp/y3GhDLHZzen+oSb0erN6MtZ/8xEthSLHf3kaH9O3VZ+FjVVFv/O50wqZ8cZrZ
+        vtHNHuXnKAeIHcieJ+UW2whzwyaUyz5vmGAQV2OEhjNaYzJsX9ovfwEAAP//AwDl8KHQMwQAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9e9fcfc39463e-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda4ffadae111a-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 04:00:56 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Tue, 23 May 2023 13:29:11 GMT
+      Function-Execution-Id:
+      - f495u7ofauc1
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '13391'
-      openai-version:
+      Openai-Processing-Ms:
+      - '18627'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 9f90e5f759c4963f38509965c99deef1;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86465'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Remaining-Tokens:
+      - '86466'
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
+      X-Ratelimit-Reset-Tokens:
       - 2.356s
-      x-request-id:
-      - 4f791abbc43d82448ee903e7f4248a39
+      X-Request-Id:
+      - b789df6a372f156ab649b8822388cf4b
     status:
       code: 200
       message: OK
@@ -1865,7 +1383,7 @@ interactions:
       args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
       Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
@@ -1904,7 +1422,7 @@ interactions:
       the file instructions_2.txt"}, {"role": "user", "content": "Determine which
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I will use the read_file
+      instruction is to read the instructions_2.txt file. I should use the read_file
       command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
       file contains the necessary information to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
@@ -1917,6 +1435,10 @@ interactions:
       "content": "Determine which next command to use, and respond using the format
       specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -1932,60 +1454,67 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5SST4/aQAzF7/0Uls8JArFkaW5VT9yqqlT9kwoNEyeZ3YknmnF2YVG+e5UQli2I
-        qr3afn4/z7wDmhxT1JUSXTc2vl+tv22n+8/7XZt8elotlz+eHpbq49eX+fd1iRG67QNpGRUT7erG
-        khjHGKH2pIRyTGfJ8i65myWL9xHWLieLKZaNxPPJIpbWb108nU9nGGEbVEmYHrDxrm5kI+6ROGA6
-        my3vIzwvPzeSJEJxouy5NF/Muwh15YymgOnPA9YUTou9s4QpqhBMEMXSYzoW4v6EQ8YAABlK5dqy
-        kpBhCmNxbNBO+mKGXyoCpp2A4SC+1T0WmADiwJPKQSp62wqb+UR2AoWxNIEVPBtroQ00zPWCTd8B
-        7epacf7HlkGSYfSWw5MKjg2XZ5gbZtCfpwyHYReT7t/C78Fw4XytBmxxkJOQrw3TOLYTCEJNuDRu
-        rOKjZwzrf8K/wZVlHMMHVnb/QldzfyO6ANLeiNEm1EeqFTDRAEAcWt+LlcAKVA2Fs9Y9Gy6v7ZTW
-        rVdCdg89PhWF0YZY7P7y/tCQejxZ/ccn3opChsftXXTK3qi+ih6rmo7Gr04XbMqXl4k9NvrZs/wa
-        5QQxgIw8GXfYRVgYNqHaHPOGKQZxDUZoOKcdptPuV/fuNwAAAP//AwDgiGKHMgQAAA==
+        H4sIAAAAAAAAA4yST2/bMAzF7/sUBM92kMxJmvm2YZcUa4EB62keAlWmba0yZUg0mj/wdx8cO0uX
+        IEOvJB/fj9I7oMkxRV0p0XVj47v7h4eK8unT6tF++Zrcmb3kC/P47fv84/0eI3TPv0nLqJhoVzeW
+        xDjGCLUnJZRjOluu5qv5arH4FGHtcrKYYtlInEwWsbT+2cXTZDrDCNugSsL0gI13dSMbcS/EAdPZ
+        bHUX4Xn5ubFcRihOlD2XkkXSRagrZzQFTH8esKZwWuydJUxRhWCCKJYe07EQ9yccMgYAyFAq15aV
+        hAxTGItjg7bSFzP8UREwbQUMB/Gt7rHABBAHnlQOUtHbVtgkE9kKFMbSBNYQKtfaHNpAx8lesul7
+        oF1dK87/2XMUZRi9JfGkgmPD5Rnnhh30ByrD4biLSfev4XdguHC+VkdwcZCTkK8N0zi2FQhCTbg0
+        bqziwTOGp3fh3+DKMo7hMyu729PV3P+ILoC0N2K0CfVAtQYmOgIQh9b3YiWwBlVD4ax1r4bLazul
+        deuVkN1Bj09FYbQhFru7vD80pF5OVq/G2nd+4q0wZDhs76JT+kb1VfhY1TQY/3W6YFO+vMzs0Ohn
+        z/JrlBPEEWTkybjDLsLCsAnVZsgbphjENRih4Zy2mE67X92HPwAAAP//AwBqGZrbNAQAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9ea62ecef463e-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda5ab893210d0-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 04:01:12 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Tue, 23 May 2023 13:29:39 GMT
+      Function-Execution-Id:
+      - f495scdawjjo
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '13317'
-      openai-version:
+      Openai-Processing-Ms:
+      - '19949'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 0128c66c9918142a24cd829bbc2b234a;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
+      X-Ratelimit-Remaining-Tokens:
       - '86449'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
+      X-Ratelimit-Reset-Tokens:
       - 2.367s
-      x-request-id:
-      - e3d967a8e255d8ef5adbe659cf7eb379
+      X-Request-Id:
+      - 438ac4200d6062dd394f5ffe9944af58
     status:
       code: 200
       message: OK
@@ -2007,7 +1536,7 @@ interactions:
       args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
       Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
@@ -2046,7 +1575,7 @@ interactions:
       the file instructions_2.txt"}, {"role": "user", "content": "Determine which
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I will use the read_file
+      instruction is to read the instructions_2.txt file. I should use the read_file
       command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
       file contains the necessary information to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
@@ -2058,8 +1587,8 @@ interactions:
       "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
       "content": "Determine which next command to use, and respond using the format
       specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I will use the
-      read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      \"The next instruction is to read the instructions_3.txt file. I should use
+      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
       file contains the necessary information to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
       the instructions to determine the next steps\",\n        \"criticism\": \"I
@@ -2071,6 +1600,10 @@ interactions:
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -2078,7 +1611,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6570'
+      - '6572'
       Content-Type:
       - application/json
     method: POST
@@ -2086,60 +1619,67 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSTY/TQAyG7/wKy+dp1dJPcl1AqtgTSyUEQdV04k2GJuPRjMNWqvLfUZJWod0V
-        Au3VHr/PY41PaDNM0BRaTOXL0Wqz/Ro+fFse7vaftx+PD2X+Kd4/vL+/q+nXChXy/icZOU+MDVe+
-        JLHsUKEJpIUyTKbL9Xw5ny5XC4UVZ1RigrmX0Wy8GEkd9jyazCZTVFhHnRMmJ/SBKy874QO5iMl0
-        9m6hcAgfGuuFQmHR5VBarCeNQlOwNRQx+X7CiuIlOHBJmKCO0UbRTlpNdkKuXeGUOgCAFKXgOi8k
-        ppjAuXhu0FHaYopfCgJHRwHrooTatFpgIwjDU7BCIAWB6HjY2QysE+4Kj7Yk4Fp8LWM5yhg28GTL
-        EurYD3SjO+Fd99BwVWmX/UPmOEX1p2cgHdlZlw+yL0e3xgWB9j6wD1bLFbXT+it82OVFD19q1yuM
-        YPuKHW8wNxQTrFhjY9WjNuCIukRysQ5tpBbYgK46hHV5l2k4BDLy3ztFT/pwIb36957DelajLsd4
-        znl2i05X1GtccW9sdchvz7hvtG+HiEHjav726t/OpvOLYWd5lk1dg43CR+tsLHb99WGCUdijQusy
-        OmIyaX40b34DAAD//wMATFQWamAEAAA=
+        H4sIAAAAAAAAA6SSTW/bMAyG7/sVBM9OkDRxm/ncQzNgA4atl86DocisrcYWBYlGswX+74M/Ajdp
+        MWzolRTf5yHEI5ocE9SlEl27anbz6fOXm6/fdg/r+9tf1pT50902/s18fftAFiPk3RNpGSfmmmtX
+        kRjuWtqTEsoxWV5v1pv1Jt7EEdacU4UJFk5mq3k8k8bveLZYLZYYYRNUQZgc0XmunWTCe7IBk+Xq
+        YxzhFD41ukhhUdVUijeLNkJdstEUMPlxxJrCKdhzRZigCsEEUVY6TbZCtlvhmFoAgBSl5KYoJaSY
+        wFgcG3SQrpji95LA0kHA2CC+0Z0WmADC8OyNEEhJICrsM5ODscJ94dFUBNyIa2QuB5nDFkLJTZVD
+        E4aRfjgTzvqnmuta2fwfUucpRi9NPanA1thi0n07unMuCZRznp03Ss6ovdZf4dM2b3q4StlBYQb3
+        79jxAnNB0d6I0SbUA2oLlqhPJBsa30UqgS2oukcYW/SZmr0nLf+9U3Ck9ifSs6mqd/3ea9jAaqPT
+        OY45r67RqpoGjTPuha3yxeUhD43u7RQxaZzNX9791Wq5Phn2lqNsaltsI3w01oQyG64PEwzCDiM0
+        NqcDJov2Z/vhDwAAAP//AwA/k/r4YgQAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9eac7ae9d463e-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda64a0d8b1049-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 04:01:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Tue, 23 May 2023 13:30:12 GMT
+      Function-Execution-Id:
+      - f4955nyjuij9
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '15965'
-      openai-version:
+      Openai-Processing-Ms:
+      - '27188'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 1d7fa6a5187cc4d84806587407f4d630;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
+      X-Ratelimit-Remaining-Tokens:
       - '86449'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.366s
-      x-request-id:
-      - 57af6ca12656ff7b06640897bf5fa81a
+      X-Ratelimit-Reset-Tokens:
+      - 2.367s
+      X-Request-Id:
+      - 99ec79bb56359aebe30013d596125a19
     status:
       code: 200
       message: OK
@@ -2161,7 +1701,7 @@ interactions:
       args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary:
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
       Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
@@ -2200,7 +1740,7 @@ interactions:
       the file instructions_2.txt"}, {"role": "user", "content": "Determine which
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I will use the read_file
+      instruction is to read the instructions_2.txt file. I should use the read_file
       command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
       file contains the necessary information to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
@@ -2212,8 +1752,8 @@ interactions:
       "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
       "content": "Determine which next command to use, and respond using the format
       specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I will use the
-      read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
+      \"The next instruction is to read the instructions_3.txt file. I should use
+      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
       file contains the necessary information to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
       the instructions to determine the next steps\",\n        \"criticism\": \"I
@@ -2225,9 +1765,9 @@ interactions:
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"The next instruction is to write the task_id into the
-      file output.txt. I will use the write_to_file command to write the task_id into
-      the file.\",\n        \"reasoning\": \"The write_to_file command is the appropriate
-      command to use to write the task_id into the output.txt file.\",\n        \"plan\":
+      file output.txt. I should use the write_to_file command to write the task_id
+      into the file.\",\n        \"reasoning\": \"The write_to_file command is the
+      appropriate command to use to write the task_id into the output.txt file.\",\n        \"plan\":
       \"- Use the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
       \"I need to ensure that I am writing the correct task_id into the output.txt
       file.\",\n        \"speak\": \"I will use the write_to_file command to write
@@ -2238,6 +1778,10 @@ interactions:
       which next command to use, and respond using the format specified above:"}],
       "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -2245,7 +1789,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '7648'
+      - '7652'
       Content-Type:
       - application/json
     method: POST
@@ -2253,60 +1797,67 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5SSW2vbQBBG3/srhnmWjR3fGr0FCsXQQCkNpKlCWK9G0tarXbEzquMa/feii+PY
-        TaF9nd0955uZPaBJMUZdKNFlZUer9d23m4fd9svtryr//HC/mU948/Faf7r/kN5ihH7zg7QML8ba
-        l5UlMd5hhDqQEkoxni7fz5fz6fJ6HmHpU7IYY17JaDZejKQOGz+azCZTjLBmlRPGB6yCLyt5Er8l
-        xy3g6irCE/x0MFtEKF6UPZVWi1UToS680cQYfz9gSXwEB28JY1TMhkU5aWN6J+TaFg6JAwBIUApf
-        54VwgjEMxeGAnqUtJvi1IMiMUxaMYwm1bnOBYRAPXNSS+p0bwxp2xlqomUAKAlG8fRraINC+LJVL
-        z14kGL32BVLsnXH5Sfo2oxUXBKqqgq+CUef4zv93S2WV6wUjuPvXqBcMHYwYbbjsQWtwRN19clyH
-        lqkE1lConx2tw6agrO1MDErrOighu4dWRFlmtCEndg8bynygTizG5fBWC1yR2h7V/z3zntREx/0P
-        t/5Yv1Ml9ZIz6kUWFfLLn/N6mz3g5qXz0zS41pqYs9ra/UuqLtkQMHENNhFmxhkunnocxsjiK4zQ
-        uJSeMZ40j8273wAAAP//AwDMrrkmxwMAAA==
+        H4sIAAAAAAAAA5yST28aMRDF7/0UozkbBAQC2VtV9UCl5JQeqlIh453ddfHaK89sCUH73av9k0Bp
+        q1Y5esb+vec3c0KbYoKm0GLKyo2Wn+4f6G7xoB+zcvdB+Hk+u19/yT4+yyK9Q4Vh952MDC/GJpSV
+        I7HBo0ITSQulmExvV/PVfHU7XSksQ0oOE8wrGd2MFyOp4y6MJjeTKSqsWeeEyQmrGMpKthL25LkF
+        zGYKz/BzYzFRKEG0O5eWy1mj0BTBGmJMvp6wJH4Bx+AIE9TMlkV7aW0GL+TbL5w2HgBgg1KEOi+E
+        N5jAUBwa9CRtcYOPBUUCHQl8gKyOUlAE61libVqLDNaDFASZdcRjWAMXoXYpcFELpOHQd/nIQuV4
+        g+pSJpLm4K3P36KlQPu0OzrNcnkPDppBwn9ZqJz2vfoIPjN1N0XzfjtMgcCEsuyU/gy84ploxRrL
+        ZQ9dgyfq3pLnOrZ8LbCGQv/oyJ1ECto58GTa+cVjp8+woyxE6jTF+vxfH+GK9P6tMztY5/4WVy/S
+        qJelGfL4bWe8LqnX/yW/K5s65tfrdrkLPeC9c0MI54i4Nm0+We3c8dVV52wwuPENNgoz6y0X2x6H
+        CbKEChVan9ITJpPmW/PuJwAAAP//AwCAeDvT/AMAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9eb3e2d62463e-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cbda7160fd3e277-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 04:01:45 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Tue, 23 May 2023 13:30:34 GMT
+      Function-Execution-Id:
+      - f495ip5txdm1
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '11215'
-      openai-version:
+      Openai-Processing-Ms:
+      - '15997'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 285b29ed564c106ff4d38a33451a5203;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
+      X-Ratelimit-Remaining-Tokens:
       - '86452'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.364s
-      x-request-id:
-      - f275967e047717519684fa4f70a50901
+      X-Ratelimit-Reset-Tokens:
+      - 2.365s
+      X-Request-Id:
+      - 48a48589bce33baaeb8f62202ba96d90
     status:
       code: 200
       message: OK

From d4d50fda7c3bb01f643bb8223270eaef3709ac84 Mon Sep 17 00:00:00 2001
From: Kinance <kinance@gmail.com>
Date: Wed, 24 May 2023 00:00:25 +0900
Subject: [PATCH 054/112] Fix the version of duckduckgo-search to avoid empty
 result issue (#4368)

---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 31cc2d0f..15c2c481 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -14,7 +14,7 @@ requests
 tiktoken==0.3.3
 gTTS==2.3.1
 docker
-duckduckgo-search>=2.9.5
+duckduckgo-search>=3.0.2
 google-api-python-client #(https://developers.google.com/custom-search/v1/overview)
 pinecone-client==2.2.1
 redis

From 438d3e489b4e833a16f440af760776b057ed9f67 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Wed, 24 May 2023 09:13:22 -0700
Subject: [PATCH 055/112] empty commit to see cassette status (#4382)

* empty commit

* Add new cassettes

* empty commit

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
---
 .../test_browse_website.yaml                  | 335 ++++++++++++++++++
 1 file changed, 335 insertions(+)

diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
index bc59b05a..82a4f1fa 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
@@ -2561,4 +2561,339 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5919'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7RU247TMBB95ytG85xW7Xa7dPMDUCRUhBYQEFQ5zrQxjT3BntKiql/Dn+yXIafp
+        lT6sQPsUeS7H58z4ZIOmwBR1qUTbuuq8fLP4nBd+4FcfJ+/frT+9Wn2Z+NeTkdjiRx8T5Pw7aWk7
+        upptXZEYdpig9qSECkz7d6Pb+9v+cDhI0HJBFaY4r6Uz6A47svQ5d3qDXgRbBjUnTDdYe7a1TIUX
+        5AKm/UG/l+AR/JC4GY4SFBZVHWuHd6Ntgrpkoylg+nWDlsIe2HNFmKIKwQRRTiJNdkIuSthkDgAg
+        Qyl5OS8lZJhCG2wTtJYYzHAMpfpJMOOlK0BKgtobTcCz5pAzL7owBkdUgDAsAzXxlTdCU+HpzFQE
+        mq1VriloEic4wqCgKXLKUgG551Wg6YryYIS6spYIr5WLPe6ALyospu2czvAPsX1VN8PkVJknFdgZ
+        N9/L+2fqJyN4koyHklzSivl/HXWl3E5CBz48L/Usc8c7ns74grD2Row2wV4O3qoFQVj62KkExqBs
+        Q9i4eYOl2XvSAsbN2FsVfRHbYqqh3dwfOw8REyCn2N46E4w7QypM/LD/dTnUUJNa7PmtTFU996to
+        yF/b9Y7VNtk7tb3xL6NG4B3hM4YXupSfX3p8l4i1R4grqz/Fufw1PFwVnWUZvqXCSLOpEI9xIY+/
+        b4bd0f1BWiOvVZm5LW4TnBlnQjndORRTDMI1JmhcQWtMe9tv2xd/AAAA//8DALTpOdW2BQAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cc684068c040105-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 15:19:55 GMT
+      Function-Execution-Id:
+      - hlwokk6q580e
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '41327'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - f91fbd99b88eeafa44e0661933dc8d11;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86451'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.366s
+      X-Request-Id:
+      - 028e42efed960a14a11ed27cc9ab8472
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that I was created and there have been no new developments
+      to report."}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
+      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: The
+      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
+      \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I have found the price of the book. I need to use the
+      write_to_file command to write the price to a file named browse_website.txt.
+      I can then use the task_complete command to complete the task.\",\n        \"reasoning\":
+      \"I need to use the write_to_file command to write the price of the book to
+      a file named browse_website.txt. Then, I can use the task_complete command to
+      complete the task.\",\n        \"plan\": \"- Use the write_to_file command to
+      write the price of the book to a file named browse_website.txt\\n- Use the task_complete
+      command to complete the task\",\n        \"criticism\": \"I need to make sure
+      that I am writing the correct information to the file and that the file is being
+      created in the correct directory.\",\n        \"speak\": \"I will use the write_to_file
+      command to write the price of the book to a file named browse_website.txt and
+      complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
+      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7391'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6xTy27bQAy89ysInmXBjzRNdMshRd1LCxQt+lBhrFeUtJW0K4iUndTQvxcrS36l
+        DxTIUSRndoYc7dAkGKHOleiqLiev3hZf371P8+X9HbtPb76kP283n19/KO436R1hgG79g7QMiFC7
+        qi5JjLMYoG5ICSUYza5vrm6vZtfTeYCVS6jECLNaJovw5UTaZu0m08V0hgG2rDLCaId146paVuIK
+        suwJ5rMAj+SHxtxTihNVHmdv5osuQJ07o4kx+rbDingkblxJGKFiNizKipfprJD1FnaxBQCIUXLX
+        ZrlwjBEMxaFBD+KLMS4hVxuCbWNEyILkBHVjNIFL+4+1cwWIAwWpKQmsqiiBdeO2TKstrdkIhfIg
+        ISxBKwvWbaFl6qGiuFgNZgm0qyplE891qI1TYYzBqbyGFDtrbHamcYQlB5wXmRqbGJv9Qbl/0Xvz
+        E0aORp5Xb10qu5c6gY//zXZBpr1cbbgazVuiHlipgoDbxiOV/OURw7Am77hlSkC7piEt5WO/jDPo
+        cfK4W261Jua0LcvHS59ckyqeNTf7A5my7C/xZDXQ8njb31oNY9zr64Ix80PnSeS9gr30M6YLh6rJ
+        Lv+W00ieeT/dFKSutck/QugXdRbCUX3vYDAS2w67AFNjDeer/bMYIYurMUBjE3rAaNp97178AgAA
+        //8DALCJLSHjBAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cc6853a1a162ca7-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 15:20:35 GMT
+      Function-Execution-Id:
+      - hlwow4ei8qrs
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '32659'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 3b9ada41b83eace6824a9959d99a1577;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86431'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.379s
+      X-Request-Id:
+      - edc77b2bbc714d92d421e479ef4505b0
+    status:
+      code: 200
+      message: OK
 version: 1

From 5168cb52193c1dccda60a0fc2e2e61ae040fb7eb Mon Sep 17 00:00:00 2001
From: Kinance <kinance@gmail.com>
Date: Thu, 25 May 2023 01:36:23 +0900
Subject: [PATCH 056/112] Migrate google search to use DDGS.text function
 (#4383)

---
 autogpt/commands/google_search.py       | 9 +++++----
 tests/integration/test_google_search.py | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/autogpt/commands/google_search.py b/autogpt/commands/google_search.py
index 02909448..23abef7d 100644
--- a/autogpt/commands/google_search.py
+++ b/autogpt/commands/google_search.py
@@ -2,8 +2,9 @@
 from __future__ import annotations
 
 import json
+from itertools import islice
 
-from duckduckgo_search import ddg
+from duckduckgo_search import DDGS
 
 from autogpt.commands.command import command
 from autogpt.config import Config
@@ -26,12 +27,12 @@ def google_search(query: str, num_results: int = 8) -> str:
     if not query:
         return json.dumps(search_results)
 
-    results = ddg(query, max_results=num_results)
+    results = DDGS().text(query)
     if not results:
         return json.dumps(search_results)
 
-    for j in results:
-        search_results.append(j)
+    for item in islice(results, num_results):
+        search_results.append(item)
 
     results = json.dumps(search_results, ensure_ascii=False, indent=4)
     return safe_google_results(results)
diff --git a/tests/integration/test_google_search.py b/tests/integration/test_google_search.py
index 798765e0..50a2ce35 100644
--- a/tests/integration/test_google_search.py
+++ b/tests/integration/test_google_search.py
@@ -42,7 +42,7 @@ def test_google_search(query, num_results, expected_output, return_value, mocker
     mock_ddg = mocker.Mock()
     mock_ddg.return_value = return_value
 
-    mocker.patch("autogpt.commands.google_search.ddg", mock_ddg)
+    mocker.patch("autogpt.commands.google_search.DDGS.text", mock_ddg)
     actual_output = google_search(query, num_results=num_results)
     expected_output = safe_google_results(expected_output)
     assert actual_output == expected_output

From 43565b280f105e7bb77737684d8e4a9631c14fb7 Mon Sep 17 00:00:00 2001
From: Nicholas Tindle <nick@ntindle.com>
Date: Wed, 24 May 2023 22:40:30 -0500
Subject: [PATCH 057/112] Remove Twitter Command (#4381)

---
 BULLETIN.md                                   |   2 +-
 autogpt/commands/twitter.py                   |  41 -
 autogpt/main.py                               |   1 -
 requirements.txt                              |   1 -
 .../test_write_file/test_write_file.yaml      | 252 +++++++
 .../test_memory_challenge_a.yaml              | 698 ++++++++++++++++++
 6 files changed, 951 insertions(+), 44 deletions(-)
 delete mode 100644 autogpt/commands/twitter.py

diff --git a/BULLETIN.md b/BULLETIN.md
index 62aeeba2..841dd3ac 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -35,7 +35,7 @@ Highlights and notable changes since v0.2.2:
  * Edge browser is now supported by the `browse_website` command.
  * Sets of commands can now be disabled using DISABLED_COMMAND_CATEGORIES in .env.
 
-# ⚠️ Command `send_tweet` is DEPRECATED, and will be removed in v0.4.0 ⚠️
+# ⚠️ Command `send_tweet` is REMOVED
 Twitter functionality (and more) is now covered by plugins, see [Plugin support 🔌]
 
 ## Plugin support 🔌
diff --git a/autogpt/commands/twitter.py b/autogpt/commands/twitter.py
deleted file mode 100644
index baf0876d..00000000
--- a/autogpt/commands/twitter.py
+++ /dev/null
@@ -1,41 +0,0 @@
-"""A module that contains a command to send a tweet."""
-import os
-
-import tweepy
-
-from autogpt.commands.command import command
-
-
-@command(
-    "send_tweet",
-    "Send Tweet",
-    '"tweet_text": "<tweet_text>"',
-)
-def send_tweet(tweet_text: str) -> str:
-    """
-      A function that takes in a string and returns a response from create chat
-        completion api call.
-
-    Args:
-      tweet_text (str): Text to be tweeted.
-
-      Returns:
-          A result from sending the tweet.
-    """
-    consumer_key = os.environ.get("TW_CONSUMER_KEY")
-    consumer_secret = os.environ.get("TW_CONSUMER_SECRET")
-    access_token = os.environ.get("TW_ACCESS_TOKEN")
-    access_token_secret = os.environ.get("TW_ACCESS_TOKEN_SECRET")
-    # Authenticate to Twitter
-    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
-    auth.set_access_token(access_token, access_token_secret)
-
-    # Create API object
-    api = tweepy.API(auth)
-
-    # Send tweet
-    try:
-        api.update_status(tweet_text)
-        return "Tweet sent successfully!"
-    except tweepy.TweepyException as e:
-        return f"Error sending tweet: {e.reason}"
diff --git a/autogpt/main.py b/autogpt/main.py
index ac27e282..25d7161e 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -136,7 +136,6 @@ def run_auto_gpt(
         "autogpt.commands.google_search",
         "autogpt.commands.image_gen",
         "autogpt.commands.improve_code",
-        "autogpt.commands.twitter",
         "autogpt.commands.web_selenium",
         "autogpt.commands.write_tests",
         "autogpt.app",
diff --git a/requirements.txt b/requirements.txt
index 15c2c481..19a23f1a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -23,7 +23,6 @@ Pillow
 selenium==4.1.4
 webdriver-manager
 jsonschema
-tweepy
 click
 charset-normalizer>=3.1.0
 spacy>=3.0.0,<4.0.0
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
index 925e2e2d..f5a406c3 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
@@ -1098,4 +1098,256 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\nThe OS you are running on is:
+      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
+      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
+      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3441'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6STTXPaMBCG7/0VO3vhYhg+Emh86y10uKWZTqfueIS8YIEsOdJ6Qsv4v3eEbSCk
+        5FCO2o9Xzyvt7lFlGKPMBcui1P3Z182PxXS1eLL0Mn588UL9eVr81s+8KXcjjNAuNyS57RhIW5Sa
+        WFmDEUpHginDeDT9fPcwmU0fJhEWNiONMa5L7k8G932u3NL2h5NhEKu8WBPGeyydLUpO2W7JeIxn
+        s/sIT9rH+PhuGiFbFvoYGg3HozpCmVslyWP8c48F+U7XWU0Yo/BeeRaGA6U1TCY42CcGACBBzm21
+        ztknGEMbbBO04xBMcA6GKAO28OoUE/QeSWsL363TWQ+UYQsCVkoTGFFQBr085NPXkB/wjnsgTAac
+        k4HWF4UTsPBbqLwy68OxF85pV9ELtYUw2SDB6JzLkfDWKLNu4L6FzgNXyjYNFMdOkMLAkqDyN9EP
+        4MuKyQHngiOYH1QrTx8xh9veWb00UmphGg99eO70rji5gT5JzJn+DbzSKVZS+eJyKsj4ytHhfWAO
+        ojj7U2mdI8knwnYUBH9oV3nwlZTk/arSsKSVddQBdtL/QvQliW2H96q0/u+JPRvLK4zXZ3qQYANV
+        R92WtU3vlixc3/C+ueXClnDry/1sEqH2JHFh4o3I5U6fPUhHeyBuwRNTYx3hShnl87RZOYzRsy0x
+        QmUy2mE8rH/Vn/4CAAD//wMAcOALfkQFAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc625c85c302cb4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:15:34 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '40542'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86502'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.332s
+      x-request-id:
+      - 5e84c935a23a6ad8f5a2601dd432725b
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\nThe OS you are running on is:
+      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
+      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
+      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created and nothing new
+      has happened."}, {"role": "user", "content": "Determine which next command to
+      use, and respond using the format specified above:"}, {"role": "assistant",
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I need to write ''Hello
+      World'' into a file named ''hello_world.txt'' and then complete the task using
+      the ''task_complete'' command.\",\n        \"reasoning\": \"The ''write_to_file''
+      command can be used to write ''Hello World'' into a file named ''hello_world.txt''.
+      After that, I can use the ''task_complete'' command to complete the task.\",\n        \"plan\":
+      \"- Use the ''write_to_file'' command to write ''Hello World'' into a file named
+      ''hello_world.txt''.\\n- Use the ''task_complete'' command to complete the task.\",\n        \"criticism\":
+      \"I need to ensure that I am using the correct file name and that the ''write_to_file''
+      command is successful before completing the task.\",\n        \"speak\": \"I
+      will write ''Hello World'' into a file named ''hello_world.txt'' using the ''write_to_file''
+      command and then complete the task.\"\n    },\n    \"command\": {\n        \"name\":
+      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
+      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
+      write_to_file returned: File written to successfully."}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4877'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6yS3Y7TMBCF73mK0dz0xq3aDf0hLwCL4AKxKyTIKnKdaeKtYwfPRC1UeXeUTbst
+        XQkhxKXneL45Y58D2gJTNJUWUzduvHz/+DWhnx8Wnxxvi2r/sb4pq/puGu+3b7+jwrB+JCPHjokJ
+        deNIbPCo0ETSQgWms8Xq9ZtkuUyWCutQkMMUy0bGyWQ+ljauw3iaTGeosGVdEqYHbGKoG8klbMkz
+        prPpaqXwDD8Li7lCCaLduXQzTzqFpgrWEGP67YA18QkcgyNMUTNbFu2ltxm8kO9XOGQeACBDqUJb
+        VsIZpnAsHgXaS1/M8K4iGO2iFcol5BvraAQm1LX2Bew0A7fGEPOmdQo4wC0Y7cGHHRy3IJCKQDRv
+        oWXry6fjqD/npxvPwEmG6tJFJM3BW18OVj5bbwbc3xr6r24ap/1gZAz3TH9qBQkvJ17zTLRijeV6
+        gN6CJ3rqJM9t7Pu0nO1afiYWFzu6H7CmTYgE5IvTQk0MZdT19UBuSG9Pw3bWuX98lYHZqVOKjsqL
+        EHld0zDuN9SVKx3L6/xd/v4AeEfOBfgSoiug0gxrIg99CIR8/2RVr+e7Xp9IH90zrDvazXyHncKN
+        9ZarfIBjiiyhQYXWF7THdNo9dK9+AQAA//8DAKoIau4bBAAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc626d9d9b72cb4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:16:05 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '28427'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86485'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.343s
+      x-request-id:
+      - 941875e93a46562c74839ad42ec1c215
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index d77d361e..99243a10 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -1861,4 +1861,702 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3334'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4SSy27bQAxF9/0KgmvJsGrXD+26KJAUKNpFCvShwhiPKGmSeagzVGPH0L8XY1lO
+        YQfp9g7Jey6HB1Ql5igbwdK0Ol1+vP/xXX35lDV3H5ya3nxujbh5Wv/J5t+qt5ig296T5FPHRDrT
+        amLlLCYoPQmmEvNssZqvZ8vlYpWgcSVpzLFuOZ1N3qXc+a1Lp7Nphgl2QdSE+QFb70zLG3YPZAPm
+        y/kywefZZz2brxNkx0KfpdV60ScoG6ckBcx/HtBQGMd6pwlzFCGowMJyhHSWycYAh8ICABTIjevq
+        hkOBOZzE0wPtOIoF3kJoXKdLCCw8w3YPnkSpbA3cECgb2HcyooZNNuEdQ6U0QRfGili9OWrSGSNs
+        OSkw+dfKkwjOKlsPfncNQaV8YAhMLagA7KCzJfmYo7xyhSg+NoJjqaffnfJUgqvA0KVTq4UdTFL4
+        GuhlvGgXxdfiFYVN4b0Vev9ELwOVxOSNssOzpd0QJ1wQSa9YSRXMuGtLdCQgGzofmwXD7avxq07r
+        PWypcp6g9U4Sxd+5zB5aEg+jy6PS+v//eYw6KXAY0yfj0ZwWdXUzVhgaHM5LvYAQvr48teEh1j63
+        X299hDiCnHgK22OfYKWsCs1muCLMMbBrMUFlS9phPu1/9W/+AgAA//8DAABeWuzpAwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc6279c6ab63ac7-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:16:35 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '27497'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86499'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.334s
+      x-request-id:
+      - 518916964b78cdb0ae0001c2c19bb7e4
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file using the read_file
+      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
+      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
+      to read the instructions_1.txt file\\n- Analyze the instructions and determine
+      the next steps\",\n        \"criticism\": \"I need to ensure that I understand
+      the instructions fully before proceeding.\",\n        \"speak\": \"I will start
+      by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}], "temperature":
+      0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4445'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4ySQY/aMBCF7/0V1pwTBKGUJbeqe2lFb7tS1aZCxpkkZu2xZU+0sCj/vQqBZRuq
+        ttc3z2++Gc8RdAk5qEayst6kyy87mX27ty9fH+Rj+2m9X9x/r3drLg9eryEBt92h4vOLiXLWG2Tt
+        CBJQASVjCfnsw9371Xy5XN0lYF2JBnKoPafzySLlNmxdOp1PZ5BAG2WNkB/BB2c9b9g9IUXIV8ss
+        gWv2qz5bTBNgx9JcpVmWdQmoxmmFEfIfR7AYL7nBGYQcZIw6siTuKR0xUj/BsSAhhCiAG9fWDccC
+        cnEWzwXccy8W8FkQYinYiYCyFNyg0BQ5tKoHjJtswnsWlTYo2qipPjl66+akKWetpHJSQPI2P6CM
+        jjTVQ5OHv6T22FJTFFUbuMHwm1FwI1lcGStnjHsed/NG0tAoFY8R/4z4PyMWBaXiI0lzeMEbn+hD
+        SmQMVtNQJtyziIw+johU0KyVjna8ZKTYBryM1VKJof+/WypRtcYcxBYrF1D44BRiqakezx49yqdL
+        l2dtzL//kU4bHEK65HIr5zXdnApJi0P+60pHCDLU4wsbCr33+vwW5wJxAjnzFNRBl0ClScdmM9wR
+        5BDZeUhAU4l7yKfdz+7dLwAAAP//AwB9LqMb4QMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc62859ed003ac7-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:17:03 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '24655'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86475'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.35s
+      x-request-id:
+      - c0da07f2916746d8735e7bdcbfde425a
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that I was created and there have been no new developments
+      to report."}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
+      file using the read_file command.\",\n        \"reasoning\": \"The first step
+      is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
+      instructions and determine the next steps\",\n        \"criticism\": \"I need
+      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5444'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4ySTY/TQAyG7/wKy+ekagmbltxQERIckFaCw4qgajpxkulOPNGMw3ap8t9RmoZC
+        ioCr/fr1448TmgIz1LUS3bQ2Xn84qIf03fY+TdS37ce39+WxDiQHnT5sthih2x9Iy6VioV3TWhLj
+        GCPUnpRQgdkq3bx6naw3yTLCxhVkMcOqlThZ3MXS+b2Ll8lyhRF2QVWE2Qlb75pWduIeiQNmq9U6
+        jfBqfk3cLSMUJ8peQ8nLtI9Q185oCph9OWFDYTL2zhJmqEIwQRTLgOlYiIcRTjkDAOQoteuqWkKO
+        GVyClwQdZQjm+B6YqABx4EkVIDWB4SC+0wNg2CULOQqUxhJ0wXB1VgzS3TmmXdMoLhY5Rr/6e1LB
+        seFqbPLpL64DtjIcoOy81OR/E4LUSuDKWDpr3dO8W2sVj41i+Bzoz4j/M2KecwxvWNnn73Sjg8Gk
+        ICHfGB7TTEeBINSGGZH2Row2oZkvmTh0nqaxOi7ID/e7pYKys/YZ9lQ6T9B6p4kKw9V89tCSepy6
+        PBlr/31HPm9wNOmj6Vcua7p5FVYNjf4/VzpDUL6af9iYGLTX8lucCeIMcuHJucc+wtKwCfVu/CPM
+        MIhrMULDBR0xW/Zf+xc/AAAA//8DABSF0HDiAwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc629212e6a3ac7-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:17:38 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '27552'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86463'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.358s
+      x-request-id:
+      - 47e4bf23b06275bef6330450764eab29
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I should start by reading the instructions_1.txt file
+      using the read_file command.\",\n        \"reasoning\": \"The first step is
+      to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
+      instructions and determine the next steps\",\n        \"criticism\": \"I need
+      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_3.txt file\\n- Analyze the
+      instructions and determine the next steps\",\n        \"criticism\": \"I need
+      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6394'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5RSTa+bMBC891dYezYohPfyKLdWaqX00FO/1FJFjtmAX7CXZy9NpIj/XhGIkkfV
+        Q64z3pnZ9ZzAlJCDrhVr2zbR06fn7XL3LbE/Pn74Xr2zCj/z+/XLzzb8yTKQQNtn1DxNxJps2yAb
+        ciBBe1SMJeTJKnt4mz5lq4UESyU2kEPVcpTGjxF3fkvRIl0kIKELqkLIT9B6si1vmPboAuRJusok
+        XMWvxGMmgYlVcwMtV70EXZPRGCD/dQKL4SLsqUHIQYVgAivHQ0xyjG5Y4VQ4IYQogGvqqppDAbmY
+        wInAIw9gAWvhEEvBJA7eMAquUbAK+40phXFMZ4A6bjuO+chiZxoUXTCuOjPnoQ3T5oxrsla5Mi5A
+        3rp5VIGccdVo+aVGYVxg3+nhCEF4fOmMR2Hxvhxzn7ZRbrSIxNeA/w94n83MRXvDRptg5wdEFzo/
+        SCoW6xt9Td6j5rvXCS2q/cXkYJrmni9ydIgLGOV6eSnEtP8/fXDK4uj06l6zQMpX8yqNxPD2KnGN
+        8mp+3rxlmjxcEp5TTmEL10MvYWecCfVm7A7kEJhakGBciUfIF/3v/s1fAAAA//8DAF4b24zkAwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc629de3bf83ac7-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:18:10 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '29389'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86466'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.355s
+      x-request-id:
+      - c74448d89d195cfad9d7fcfc8ed151c4
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nAs
+      a system, I recall that nothing new has happened since my creation."}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I should start by reading the instructions_1.txt file
+      using the read_file command.\",\n        \"reasoning\": \"The first step is
+      to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
+      instructions and determine the next steps\",\n        \"criticism\": \"I need
+      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains further instructions that I need to follow.\",\n        \"plan\": \"-
+      Use the read_file command to read the instructions_3.txt file\\n- Analyze the
+      instructions and determine the next steps\",\n        \"criticism\": \"I need
+      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to write the task_id into the output.txt file using the write_to_file
+      command.\",\n        \"reasoning\": \"The instructions require me to write the
+      task_id into the output.txt file.\",\n        \"plan\": \"- Use the write_to_file
+      command to write the task_id into the output.txt file\",\n        \"criticism\":
+      \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
+      \"I will write the task_id into the output.txt file now.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
+      "system", "content": "Command write_to_file returned: File written to successfully."},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7348'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3SRS2/bMBCE7/0VxJ4pw684jm4FiiIpgp5aoEUVGDS1lhjzoXJXsQ1D/73Qw7Wr
+        ttdd8puZnTOYHFLQpWLtKpvcf3rdfv84f36c7ec791hV+Pl5efx2evuwPEWQELavqHn4MdHBVRbZ
+        BA8SdETFmEM6W62XD4v79cNcggs5WkihqDhZTO4SruM2JNPFdAYSalIFQnqGKgZX8YbDHj1BOrtb
+        rSVc4dfFbCWBAyt7Ha3Wy0aCLoPRSJD+OINDuoBjsAgpKCJDrDy3NoNn9G2Ec+aFECIDLkNdlEwZ
+        pGIYDgs8cjvM4El4xFxwEFTWnIeDFzUZXwguUbCi/Wawi0IH55TPJxnIW1ZERcEbX/TALyUK44lj
+        rduIJCL+rE1E4fBWZUyprPI9IBFfCf8vfwsZMXQ0bLQhN46GnurYMhWLJ1Gqt47WYXOhrO3UBp95
+        J0tii7sQsZPi9h7/Mk0Vqv1F7GCsvR7Rh8Mkg/5xIy+FDBn+6sMrhz3nj8wjORWLcZW3FfSA922c
+        LsE1ItVaI9Gutvb021XnbDCY+QYaCTvjDZWbHgcpEIcKJBif4xHSafPSvPsFAAD//wMAvNN1YlgD
+        AAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cc62aa52e403ac7-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:18:31 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '19007'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.35s
+      x-request-id:
+      - d281dd2fbae62c2925a71cdef320242e
+    status:
+      code: 200
+      message: OK
 version: 1

From e3e9a8121c88137ca13a56affc2299244d9580fc Mon Sep 17 00:00:00 2001
From: Pi <sunfish7@gmail.com>
Date: Thu, 25 May 2023 15:57:06 +0100
Subject: [PATCH 058/112] Re-point link to wiki in CONTRIBUTING.md

Also update text
---
 CONTRIBUTING.md | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 81059405..c3f97512 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1 +1,14 @@
-This document now lives at https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
+We maintain a knowledgebase at https://github.com/Significant-Gravitas/Nexus/wiki
+
+We would like to say "We value all contributions". After all, we are an open-source project, so we should say something fluffy like this, right?
+
+However the reality is that some contributions are SUPER-valuable, while others create more trouble than they are worth and actually _create_ work for the core team.
+
+If you wish to contribute, please look through the wiki [contributing](https://github.com/Significant-Gravitas/Nexus/wiki/Contributing) page.
+
+If you wish to involve with the project (beyond just contributing PRs), please read the wiki [catalyzing](https://github.com/Significant-Gravitas/Nexus/wiki/Catalyzing) page.
+
+In fact, why not just look through the whole wiki (it's only a few pages) and hop on our discord (you'll find it in the wiki).
+
+❤️ & 🔆
+The team @ AutoGPT

From 1ab3a40f03558aa5d2d42b2d628c05aff4b11bca Mon Sep 17 00:00:00 2001
From: Pi <sunfish7@gmail.com>
Date: Thu, 25 May 2023 15:59:04 +0100
Subject: [PATCH 059/112] Repoint to wiki page 1.bug.yml

---
 .github/ISSUE_TEMPLATE/1.bug.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/ISSUE_TEMPLATE/1.bug.yml b/.github/ISSUE_TEMPLATE/1.bug.yml
index 7260971d..3c660a8e 100644
--- a/.github/ISSUE_TEMPLATE/1.bug.yml
+++ b/.github/ISSUE_TEMPLATE/1.bug.yml
@@ -16,7 +16,7 @@ body:
         [discussions]: https://github.com/Significant-Gravitas/Auto-GPT/discussions
         [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184
         [existing issues]: https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue
-        [wiki page on Contributing]: https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
+        [wiki page on Contributing]: https://github.com/Significant-Gravitas/Nexus/wiki/Contributing
 
   - type: checkboxes
     attributes:

From 2a6f01aae26df928c33d93c0fb06329dc204dee5 Mon Sep 17 00:00:00 2001
From: Pi <sunfish7@gmail.com>
Date: Thu, 25 May 2023 15:59:50 +0100
Subject: [PATCH 060/112] Re-point wiki link in 2.feature.yml

---
 .github/ISSUE_TEMPLATE/2.feature.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/ISSUE_TEMPLATE/2.feature.yml b/.github/ISSUE_TEMPLATE/2.feature.yml
index 3f22bab6..ea6733a1 100644
--- a/.github/ISSUE_TEMPLATE/2.feature.yml
+++ b/.github/ISSUE_TEMPLATE/2.feature.yml
@@ -5,7 +5,7 @@ body:
   - type: markdown
     attributes:
       value: |
-        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing)
+        First, check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Nexus/wiki/Contributing)
         Please provide a searchable summary of the issue in the title above ⬆️.
   - type: checkboxes
     attributes:

From 6e14782f829ce8bab7e54f181a3362d491768146 Mon Sep 17 00:00:00 2001
From: Pi <sunfish7@gmail.com>
Date: Thu, 25 May 2023 16:00:29 +0100
Subject: [PATCH 061/112] Re-point wiki link in PULL_REQUEST_TEMPLATE.md

---
 .github/PULL_REQUEST_TEMPLATE.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 90b985c1..81a4b90a 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -14,7 +14,7 @@ Provide clear documentation and explanations of the changes made.
 Ensure diffs are limited to the intended lines — no applying preferred formatting styles or line endings (unless that's what the PR is about).
 For guidance on committing only the specific lines you have changed, refer to this helpful video: https://youtu.be/8-hSNHHbiZg
 
-Check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing)
+Check out our [wiki page on Contributing](https://github.com/Significant-Gravitas/Nexus/wiki/Contributing)
 
 By following these guidelines, your PRs are more likely to be merged quickly after testing, as long as they align with the project's overall direction. -->
 

From 10489e0df2b9c4c8dc0d109e765150eae59825bd Mon Sep 17 00:00:00 2001
From: Kinance <kinance@gmail.com>
Date: Fri, 26 May 2023 01:10:48 +0900
Subject: [PATCH 062/112] Fix duckduckgo-search to 3.0.2 stable version (#4405)

---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 19a23f1a..df45c9ca 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -14,7 +14,7 @@ requests
 tiktoken==0.3.3
 gTTS==2.3.1
 docker
-duckduckgo-search>=3.0.2
+duckduckgo-search==3.0.2
 google-api-python-client #(https://developers.google.com/custom-search/v1/overview)
 pinecone-client==2.2.1
 redis

From bfbe61396063fdbf2bfcdcf622c50ea05a316427 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Thu, 25 May 2023 20:31:11 +0200
Subject: [PATCH 063/112] Vector memory revamp (part 1: refactoring) (#4208)

Additional changes:

* Improve typing

* Modularize message history memory & fix/refactor lots of things

* Fix summarization

* Move memory relevance calculation to MemoryItem & improve test

* Fix import warnings in web_selenium.py

* Remove `memory_add` ghost command

* Implement overlap in `split_text`

* Move memory tests into subdirectory

* Remove deprecated `get_ada_embedding()` and helpers

* Fix used token calculation in `chat_with_ai`

* Replace Message TypedDict by dataclass

* Fix AgentManager singleton issues in tests

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
---
 .env.template                                 |   50 +-
 BULLETIN.md                                   |    8 +
 autogpt/agent/agent.py                        |   56 +-
 autogpt/agent/agent_manager.py                |   60 +-
 autogpt/app.py                                |   48 +-
 autogpt/commands/analyze_code.py              |    2 +-
 autogpt/commands/file_operations.py           |   48 +-
 autogpt/commands/file_operations_utils.py     |    6 +-
 autogpt/commands/improve_code.py              |    2 +-
 autogpt/commands/web_requests.py              |   10 -
 autogpt/commands/web_selenium.py              |   76 +-
 autogpt/commands/write_tests.py               |    2 +-
 autogpt/config/ai_config.py                   |    7 +-
 autogpt/config/config.py                      |   58 +-
 autogpt/configurator.py                       |    4 +-
 autogpt/json_utils/json_fix_llm.py            |    2 +-
 autogpt/llm/__init__.py                       |   21 -
 autogpt/llm/api_manager.py                    |    8 +-
 autogpt/llm/base.py                           |   96 +-
 autogpt/llm/chat.py                           |  390 +-
 autogpt/llm/modelsinfo.py                     |    1 +
 autogpt/llm/providers/openai.py               |   91 +-
 .../llm/{llm_utils.py => utils/__init__.py}   |  263 +-
 autogpt/llm/{ => utils}/token_counter.py      |    2 +-
 autogpt/main.py                               |    6 +-
 autogpt/memory/__init__.py                    |   96 -
 autogpt/memory/base.py                        |   31 -
 autogpt/memory/local.py                       |  126 -
 autogpt/memory/message_history.py             |  204 +
 autogpt/memory/milvus.py                      |  162 -
 autogpt/memory/no_memory.py                   |   73 -
 autogpt/memory/pinecone.py                    |   78 -
 autogpt/memory/redismem.py                    |  156 -
 autogpt/memory/vector/__init__.py             |  138 +
 autogpt/memory/vector/memory_item.py          |  223 +
 autogpt/memory/vector/providers/__init__.py   |    7 +
 autogpt/memory/vector/providers/base.py       |   74 +
 autogpt/memory/vector/providers/json_file.py  |   68 +
 autogpt/memory/vector/providers/no_memory.py  |   36 +
 autogpt/memory/vector/utils.py                |   71 +
 autogpt/memory/weaviate.py                    |  127 -
 autogpt/memory_management/store_memory.py     |   33 -
 autogpt/memory_management/summary_memory.py   |  143 -
 autogpt/plugins.py                            |   14 +-
 autogpt/processing/text.py                    |  346 +-
 autogpt/prompts/generator.py                  |    7 +-
 autogpt/prompts/prompt.py                     |    2 +-
 autogpt/setup.py                              |   23 +-
 autogpt/speech/eleven_labs.py                 |    2 +-
 autogpt/speech/say.py                         |    2 +-
 autogpt/utils.py                              |    9 +
 data_ingestion.py                             |    6 +-
 docs/challenges/building_challenges.md        |    6 +-
 docs/configuration/memory.md                  |    8 +-
 tests/conftest.py                             |    6 +-
 tests/integration/agent_factory.py            |   33 +-
 .../test_get_ada_embedding.yaml               |  168 -
 .../test_get_ada_embedding_large_context.yaml | 1484 -------
 .../test_local_cache/test_get_relevant.yaml   |  997 -----
 ...ve_memory_trimmed_from_context_window.yaml |  843 ----
 .../test_browse_website.yaml                  |  468 +++
 .../test_write_file/test_write_file.yaml      |  227 +
 .../basic_abilities/test_browse_website.py    |    6 +-
 .../basic_abilities/test_write_file.py        |    3 +-
 .../test_information_retrieval_challenge_a.py |    3 +-
 .../test_memory_challenge_a.yaml              | 3713 +++++++++--------
 .../memory/test_memory_challenge_a.py         |    3 +-
 .../memory/test_memory_challenge_b.py         |    3 +-
 .../memory/test_memory_challenge_c.py         |    4 +-
 tests/integration/conftest.py                 |    7 +-
 tests/integration/memory/__init__.py          |    0
 .../test_json_memory_get_relevant.yaml        | 2672 ++++++++++++
 tests/integration/memory/conftest.py          |   18 +
 .../memory/test_json_file_memory.py           |  106 +
 tests/integration/memory/utils.py             |   44 +
 tests/integration/memory_tests.py             |   50 -
 tests/integration/milvus_memory_tests.py      |   55 -
 tests/integration/test_llm_utils.py           |   65 -
 tests/integration/test_local_cache.py         |  110 -
 tests/integration/test_memory_management.py   |   67 -
 tests/integration/test_plugins.py             |   71 +
 tests/integration/weaviate_memory_tests.py    |  120 -
 tests/milvus_memory_test.py                   |   72 -
 tests/test_agent.py                           |   10 +-
 tests/test_agent_manager.py                   |   15 +-
 tests/test_api_manager.py                     |    2 +-
 tests/unit/test_chat.py                       |   78 -
 tests/unit/test_file_operations.py            |   25 +-
 tests/unit/test_get_self_feedback.py          |    2 +-
 tests/unit/test_llm_utils.py                  |   38 +-
 tests/unit/test_plugins.py                    |   58 +-
 tests/{ => unit}/test_token_counter.py        |   37 +-
 92 files changed, 7282 insertions(+), 7989 deletions(-)
 rename autogpt/llm/{llm_utils.py => utils/__init__.py} (50%)
 rename autogpt/llm/{ => utils}/token_counter.py (98%)
 delete mode 100644 autogpt/memory/__init__.py
 delete mode 100644 autogpt/memory/base.py
 delete mode 100644 autogpt/memory/local.py
 create mode 100644 autogpt/memory/message_history.py
 delete mode 100644 autogpt/memory/milvus.py
 delete mode 100644 autogpt/memory/no_memory.py
 delete mode 100644 autogpt/memory/pinecone.py
 delete mode 100644 autogpt/memory/redismem.py
 create mode 100644 autogpt/memory/vector/__init__.py
 create mode 100644 autogpt/memory/vector/memory_item.py
 create mode 100644 autogpt/memory/vector/providers/__init__.py
 create mode 100644 autogpt/memory/vector/providers/base.py
 create mode 100644 autogpt/memory/vector/providers/json_file.py
 create mode 100644 autogpt/memory/vector/providers/no_memory.py
 create mode 100644 autogpt/memory/vector/utils.py
 delete mode 100644 autogpt/memory/weaviate.py
 delete mode 100644 autogpt/memory_management/store_memory.py
 delete mode 100644 autogpt/memory_management/summary_memory.py
 delete mode 100644 tests/integration/cassettes/test_llm_utils/test_get_ada_embedding.yaml
 delete mode 100644 tests/integration/cassettes/test_llm_utils/test_get_ada_embedding_large_context.yaml
 delete mode 100644 tests/integration/cassettes/test_local_cache/test_get_relevant.yaml
 delete mode 100644 tests/integration/cassettes/test_memory_management/test_save_memory_trimmed_from_context_window.yaml
 create mode 100644 tests/integration/memory/__init__.py
 create mode 100644 tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml
 create mode 100644 tests/integration/memory/conftest.py
 create mode 100644 tests/integration/memory/test_json_file_memory.py
 create mode 100644 tests/integration/memory/utils.py
 delete mode 100644 tests/integration/memory_tests.py
 delete mode 100644 tests/integration/milvus_memory_tests.py
 delete mode 100644 tests/integration/test_llm_utils.py
 delete mode 100644 tests/integration/test_local_cache.py
 delete mode 100644 tests/integration/test_memory_management.py
 create mode 100644 tests/integration/test_plugins.py
 delete mode 100644 tests/integration/weaviate_memory_tests.py
 delete mode 100644 tests/milvus_memory_test.py
 delete mode 100644 tests/unit/test_chat.py
 rename tests/{ => unit}/test_token_counter.py (56%)

diff --git a/.env.template b/.env.template
index 31d8ccc6..7a4a22bb 100644
--- a/.env.template
+++ b/.env.template
@@ -90,30 +90,18 @@ OPENAI_API_KEY=your-openai-api-key
 
 ### EMBEDDINGS
 ## EMBEDDING_MODEL       - Model to use for creating embeddings
-## EMBEDDING_TOKENIZER   - Tokenizer to use for chunking large inputs
-## EMBEDDING_TOKEN_LIMIT - Chunk size limit for large inputs
 # EMBEDDING_MODEL=text-embedding-ada-002
-# EMBEDDING_TOKENIZER=cl100k_base
-# EMBEDDING_TOKEN_LIMIT=8191
 
 ################################################################################
 ### MEMORY
 ################################################################################
 
 ### MEMORY_BACKEND - Memory backend type
-## local - Default
-## pinecone - Pinecone (if configured)
+## json_file - Default
 ## redis - Redis (if configured)
-## milvus - Milvus (if configured - also works with Zilliz)
 ## MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt)
-# MEMORY_BACKEND=local
-# MEMORY_INDEX=auto-gpt
-
-### PINECONE
-## PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key)
-## PINECONE_ENV - Pinecone environment (region) (Example: us-west-2)
-# PINECONE_API_KEY=your-pinecone-api-key
-# PINECONE_ENV=your-pinecone-region
+# MEMORY_BACKEND=json_file
+# MEMORY_INDEX=auto-gpt-memory
 
 ### REDIS
 ## REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose)
@@ -125,38 +113,6 @@ OPENAI_API_KEY=your-openai-api-key
 # REDIS_PASSWORD=
 # WIPE_REDIS_ON_START=True
 
-### WEAVIATE
-## MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage
-## WEAVIATE_HOST - Weaviate host IP
-## WEAVIATE_PORT - Weaviate host port
-## WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http')
-## USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate
-## WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate
-## WEAVIATE_USERNAME - Weaviate username
-## WEAVIATE_PASSWORD - Weaviate password
-## WEAVIATE_API_KEY - Weaviate API key if using API-key-based authentication
-# WEAVIATE_HOST="127.0.0.1"
-# WEAVIATE_PORT=8080
-# WEAVIATE_PROTOCOL="http"
-# USE_WEAVIATE_EMBEDDED=False
-# WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate"
-# WEAVIATE_USERNAME=
-# WEAVIATE_PASSWORD=
-# WEAVIATE_API_KEY=
-
-### MILVUS
-## MILVUS_ADDR - Milvus remote address (e.g. localhost:19530, https://xxx-xxxx.xxxx.xxxx.zillizcloud.com:443)
-## MILVUS_USERNAME - username for your Milvus database
-## MILVUS_PASSWORD - password for your Milvus database
-## MILVUS_SECURE - True to enable TLS. (Default: False)
-##   Setting MILVUS_ADDR to a `https://` URL will override this setting.
-## MILVUS_COLLECTION - Milvus collection, change it if you want to start a new memory and retain the old memory.
-# MILVUS_ADDR=localhost:19530
-# MILVUS_USERNAME=
-# MILVUS_PASSWORD=
-# MILVUS_SECURE=
-# MILVUS_COLLECTION=autogpt
-
 ################################################################################
 ### IMAGE GENERATION PROVIDER
 ################################################################################
diff --git a/BULLETIN.md b/BULLETIN.md
index 841dd3ac..17c38b8c 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -43,3 +43,11 @@ Auto-GPT now has support for plugins! With plugins, you can extend Auto-GPT's ab
 adding support for third-party services and more.
 See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and
 available plugins. Specific plugins can be allowlisted/denylisted in .env.
+
+## Memory backend deprecation ⚠️
+The Milvus, Pinecone and Weaviate memory backends were rendered incompatible
+by work on the memory system, and have been removed in `master`. The Redis
+memory store was also temporarily removed but we aim to merge a new implementation
+before the next release.
+Whether built-in support for the others will be added back in the future is subject to
+discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index ed9fea60..8c7a5456 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -5,11 +5,14 @@ from datetime import datetime
 from colorama import Fore, Style
 
 from autogpt.app import execute_command, get_command
+from autogpt.commands.command import CommandRegistry
 from autogpt.config import Config
+from autogpt.config.ai_config import AIConfig
 from autogpt.json_utils.json_fix_llm import fix_json_using_multiple_techniques
 from autogpt.json_utils.utilities import LLM_DEFAULT_RESPONSE_FORMAT, validate_json
-from autogpt.llm import chat_with_ai, create_chat_completion, create_chat_message
-from autogpt.llm.token_counter import count_string_tokens
+from autogpt.llm.base import ChatSequence
+from autogpt.llm.chat import chat_with_ai, create_chat_completion
+from autogpt.llm.utils import count_string_tokens
 from autogpt.log_cycle.log_cycle import (
     FULL_MESSAGE_HISTORY_FILE_NAME,
     NEXT_ACTION_FILE_NAME,
@@ -19,6 +22,8 @@ from autogpt.log_cycle.log_cycle import (
     LogCycleHandler,
 )
 from autogpt.logs import logger, print_assistant_thoughts
+from autogpt.memory.message_history import MessageHistory
+from autogpt.memory.vector import VectorMemory
 from autogpt.speech import say_text
 from autogpt.spinner import Spinner
 from autogpt.utils import clean_input
@@ -31,7 +36,6 @@ class Agent:
     Attributes:
         ai_name: The name of the agent.
         memory: The memory object to use.
-        full_message_history: The full message history.
         next_action_count: The number of actions to execute.
         system_prompt: The system prompt is the initial prompt that defines everything
           the AI needs to know to achieve its task successfully.
@@ -56,24 +60,19 @@ class Agent:
 
     def __init__(
         self,
-        ai_name,
-        memory,
-        full_message_history,
-        next_action_count,
-        command_registry,
-        config,
-        system_prompt,
-        triggering_prompt,
-        workspace_directory,
+        ai_name: str,
+        memory: VectorMemory,
+        next_action_count: int,
+        command_registry: CommandRegistry,
+        config: AIConfig,
+        system_prompt: str,
+        triggering_prompt: str,
+        workspace_directory: str,
     ):
         cfg = Config()
         self.ai_name = ai_name
         self.memory = memory
-        self.summary_memory = (
-            "I was created."  # Initial memory necessary to avoid hallucination
-        )
-        self.last_memory_index = 0
-        self.full_message_history = full_message_history
+        self.history = MessageHistory(self)
         self.next_action_count = next_action_count
         self.command_registry = command_registry
         self.config = config
@@ -114,7 +113,7 @@ class Agent:
                 self.config.ai_name,
                 self.created_at,
                 self.cycle_count,
-                self.full_message_history,
+                [m.raw() for m in self.history],
                 FULL_MESSAGE_HISTORY_FILE_NAME,
             )
             if (
@@ -132,8 +131,6 @@ class Agent:
                     self,
                     self.system_prompt,
                     self.triggering_prompt,
-                    self.full_message_history,
-                    self.memory,
                     cfg.fast_token_limit,
                 )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
 
@@ -260,9 +257,7 @@ class Agent:
 
             # Execute command
             if command_name is not None and command_name.lower().startswith("error"):
-                result = (
-                    f"Command {command_name} threw the following error: {arguments}"
-                )
+                result = f"Could not execute command: {arguments}"
             elif command_name == "human_feedback":
                 result = f"Human feedback: {user_input}"
             elif command_name == "self_feedback":
@@ -286,7 +281,7 @@ class Agent:
                     str(command_result), cfg.fast_llm_model
                 )
                 memory_tlength = count_string_tokens(
-                    str(self.summary_memory), cfg.fast_llm_model
+                    str(self.history.summary_message()), cfg.fast_llm_model
                 )
                 if result_tlength + memory_tlength + 600 > cfg.fast_token_limit:
                     result = f"Failure: command {command_name} returned too much output. \
@@ -302,12 +297,10 @@ class Agent:
             # Check if there's a result from the command append it to the message
             # history
             if result is not None:
-                self.full_message_history.append(create_chat_message("system", result))
+                self.history.add("system", result, "action_result")
                 logger.typewriter_log("SYSTEM: ", Fore.YELLOW, result)
             else:
-                self.full_message_history.append(
-                    create_chat_message("system", "Unable to execute command")
-                )
+                self.history.add("system", "Unable to execute command", "action_result")
                 logger.typewriter_log(
                     "SYSTEM: ", Fore.YELLOW, "Unable to execute command"
                 )
@@ -343,17 +336,18 @@ class Agent:
         thought = thoughts.get("thoughts", "")
         feedback_thoughts = thought + reasoning + plan
 
-        messages = [{"role": "user", "content": feedback_prompt + feedback_thoughts}]
+        prompt = ChatSequence.for_model(llm_model)
+        prompt.add("user", feedback_prompt + feedback_thoughts)
 
         self.log_cycle_handler.log_cycle(
             self.config.ai_name,
             self.created_at,
             self.cycle_count,
-            messages,
+            prompt.raw(),
             PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
         )
 
-        feedback = create_chat_completion(messages, model=llm_model)
+        feedback = create_chat_completion(prompt)
 
         self.log_cycle_handler.log_cycle(
             self.config.ai_name,
diff --git a/autogpt/agent/agent_manager.py b/autogpt/agent/agent_manager.py
index 17fb35d8..8560b0ec 100644
--- a/autogpt/agent/agent_manager.py
+++ b/autogpt/agent/agent_manager.py
@@ -1,10 +1,9 @@
 """Agent manager for managing GPT agents"""
 from __future__ import annotations
 
-from typing import List
-
-from autogpt.config.config import Config
-from autogpt.llm import Message, create_chat_completion
+from autogpt.config import Config
+from autogpt.llm.base import ChatSequence
+from autogpt.llm.chat import Message, create_chat_completion
 from autogpt.singleton import Singleton
 
 
@@ -13,55 +12,55 @@ class AgentManager(metaclass=Singleton):
 
     def __init__(self):
         self.next_key = 0
-        self.agents = {}  # key, (task, full_message_history, model)
+        self.agents: dict[
+            int, tuple[str, list[Message], str]
+        ] = {}  # key, (task, full_message_history, model)
         self.cfg = Config()
 
     # Create new GPT agent
     # TODO: Centralise use of create_chat_completion() to globally enforce token limit
 
-    def create_agent(self, task: str, prompt: str, model: str) -> tuple[int, str]:
+    def create_agent(
+        self, task: str, creation_prompt: str, model: str
+    ) -> tuple[int, str]:
         """Create a new agent and return its key
 
         Args:
             task: The task to perform
-            prompt: The prompt to use
-            model: The model to use
+            creation_prompt: Prompt passed to the LLM at creation
+            model: The model to use to run this agent
 
         Returns:
             The key of the new agent
         """
-        messages: List[Message] = [
-            {"role": "user", "content": prompt},
-        ]
+        messages = ChatSequence.for_model(model, [Message("user", creation_prompt)])
+
         for plugin in self.cfg.plugins:
             if not plugin.can_handle_pre_instruction():
                 continue
-            if plugin_messages := plugin.pre_instruction(messages):
-                messages.extend(iter(plugin_messages))
+            if plugin_messages := plugin.pre_instruction(messages.raw()):
+                messages.extend([Message(**raw_msg) for raw_msg in plugin_messages])
         # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
+        agent_reply = create_chat_completion(prompt=messages)
 
-        messages.append({"role": "assistant", "content": agent_reply})
+        messages.add("assistant", agent_reply)
 
         plugins_reply = ""
         for i, plugin in enumerate(self.cfg.plugins):
             if not plugin.can_handle_on_instruction():
                 continue
-            if plugin_result := plugin.on_instruction(messages):
+            if plugin_result := plugin.on_instruction([m.raw() for m in messages]):
                 sep = "\n" if i else ""
                 plugins_reply = f"{plugins_reply}{sep}{plugin_result}"
 
         if plugins_reply and plugins_reply != "":
-            messages.append({"role": "assistant", "content": plugins_reply})
+            messages.add("assistant", plugins_reply)
         key = self.next_key
         # This is done instead of len(agents) to make keys unique even if agents
         # are deleted
         self.next_key += 1
 
-        self.agents[key] = (task, messages, model)
+        self.agents[key] = (task, list(messages), model)
 
         for plugin in self.cfg.plugins:
             if not plugin.can_handle_post_instruction():
@@ -83,33 +82,30 @@ class AgentManager(metaclass=Singleton):
         task, messages, model = self.agents[int(key)]
 
         # Add user message to message history before sending to agent
-        messages.append({"role": "user", "content": message})
+        messages = ChatSequence.for_model(model, messages)
+        messages.add("user", message)
 
         for plugin in self.cfg.plugins:
             if not plugin.can_handle_pre_instruction():
                 continue
-            if plugin_messages := plugin.pre_instruction(messages):
-                for plugin_message in plugin_messages:
-                    messages.append(plugin_message)
+            if plugin_messages := plugin.pre_instruction([m.raw() for m in messages]):
+                messages.extend([Message(**raw_msg) for raw_msg in plugin_messages])
 
         # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
+        agent_reply = create_chat_completion(prompt=messages)
 
-        messages.append({"role": "assistant", "content": agent_reply})
+        messages.add("assistant", agent_reply)
 
         plugins_reply = agent_reply
         for i, plugin in enumerate(self.cfg.plugins):
             if not plugin.can_handle_on_instruction():
                 continue
-            if plugin_result := plugin.on_instruction(messages):
+            if plugin_result := plugin.on_instruction([m.raw() for m in messages]):
                 sep = "\n" if i else ""
                 plugins_reply = f"{plugins_reply}{sep}{plugin_result}"
         # Update full message history
         if plugins_reply and plugins_reply != "":
-            messages.append({"role": "assistant", "content": plugins_reply})
+            messages.add("assistant", plugins_reply)
 
         for plugin in self.cfg.plugins:
             if not plugin.can_handle_post_instruction():
diff --git a/autogpt/app.py b/autogpt/app.py
index b001376a..da67c35f 100644
--- a/autogpt/app.py
+++ b/autogpt/app.py
@@ -7,14 +7,13 @@ from autogpt.commands.command import CommandRegistry, command
 from autogpt.commands.web_requests import scrape_links, scrape_text
 from autogpt.config import Config
 from autogpt.logs import logger
-from autogpt.memory import get_memory
+from autogpt.memory.vector import get_memory
 from autogpt.processing.text import summarize_text
 from autogpt.prompts.generator import PromptGenerator
 from autogpt.speech import say_text
 from autogpt.url_utils.validators import validate_url
 
 CFG = Config()
-AGENT_MANAGER = AgentManager()
 
 
 def is_valid_int(value: str) -> bool:
@@ -114,24 +113,20 @@ def execute_command(
         # TODO: Remove commands below after they are moved to the command registry.
         command_name = map_command_synonyms(command_name.lower())
 
-        if command_name == "memory_add":
-            return get_memory(CFG).add(arguments["string"])
-
         # TODO: Change these to take in a file rather than pasted code, if
         # non-file is given, return instructions "Input should be a python
         # filepath, write your code to file and try again
-        else:
-            for command in prompt.commands:
-                if (
-                    command_name == command["label"].lower()
-                    or command_name == command["name"].lower()
-                ):
-                    return command["function"](**arguments)
-            return (
-                f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'"
-                " list for available commands and only respond in the specified JSON"
-                " format."
-            )
+        for command in prompt.commands:
+            if (
+                command_name == command["label"].lower()
+                or command_name == command["name"].lower()
+            ):
+                return command["function"](**arguments)
+        return (
+            f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'"
+            " list for available commands and only respond in the specified JSON"
+            " format."
+        )
     except Exception as e:
         return f"Error: {str(e)}"
 
@@ -141,7 +136,7 @@ def execute_command(
 )
 @validate_url
 def get_text_summary(url: str, question: str) -> str:
-    """Return the results of a Google search
+    """Get the text summary of a webpage
 
     Args:
         url (str): The url to scrape
@@ -151,14 +146,15 @@ def get_text_summary(url: str, question: str) -> str:
         str: The summary of the text
     """
     text = scrape_text(url)
-    summary = summarize_text(url, text, question)
+    summary, _ = summarize_text(text, question=question)
+
     return f""" "Result" : {summary}"""
 
 
 @command("get_hyperlinks", "Get hyperlinks", '"url": "<url>"')
 @validate_url
 def get_hyperlinks(url: str) -> Union[str, List[str]]:
-    """Return the results of a Google search
+    """Get all hyperlinks on a webpage
 
     Args:
         url (str): The url to scrape
@@ -186,6 +182,8 @@ def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) ->
     Returns:
         str: The response of the agent
     """
+    agent_manager = AgentManager()
+
     # Remove underscores from name
     voice_name = name.replace("_", " ")
 
@@ -195,13 +193,13 @@ def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) ->
     # Create agent
     if CFG.speak_mode:
         say_text(agent_intro, 1)
-    key, ack = AGENT_MANAGER.create_agent(task, first_message, model)
+    key, ack = agent_manager.create_agent(task, first_message, model)
 
     if CFG.speak_mode:
         say_text(f"Hello {voice_name}. Your task is as follows. {task}.")
 
     # Assign task (prompt), get response
-    agent_response = AGENT_MANAGER.message_agent(key, prompt)
+    agent_response = agent_manager.message_agent(key, prompt)
 
     return f"Agent {name} created with key {key}. First response: {agent_response}"
 
@@ -211,7 +209,7 @@ def message_agent(key: str, message: str) -> str:
     """Message an agent with a given key and message"""
     # Check if the key is a valid integer
     if is_valid_int(key):
-        agent_response = AGENT_MANAGER.message_agent(int(key), message)
+        agent_response = AgentManager().message_agent(int(key), message)
     else:
         return "Invalid key, must be an integer."
 
@@ -229,7 +227,7 @@ def list_agents() -> str:
         str: A list of all agents
     """
     return "List of agents:\n" + "\n".join(
-        [str(x[0]) + ": " + x[1] for x in AGENT_MANAGER.list_agents()]
+        [str(x[0]) + ": " + x[1] for x in AgentManager().list_agents()]
     )
 
 
@@ -243,5 +241,5 @@ def delete_agent(key: str) -> str:
     Returns:
         str: A message indicating whether the agent was deleted or not
     """
-    result = AGENT_MANAGER.delete_agent(key)
+    result = AgentManager().delete_agent(key)
     return f"Agent {key} deleted." if result else f"Agent {key} does not exist."
diff --git a/autogpt/commands/analyze_code.py b/autogpt/commands/analyze_code.py
index cff8a737..b2af33e2 100644
--- a/autogpt/commands/analyze_code.py
+++ b/autogpt/commands/analyze_code.py
@@ -2,7 +2,7 @@
 from __future__ import annotations
 
 from autogpt.commands.command import command
-from autogpt.llm import call_ai_function
+from autogpt.llm.utils import call_ai_function
 
 
 @command(
diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 0fe8114d..cf0325e2 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -4,7 +4,7 @@ from __future__ import annotations
 import hashlib
 import os
 import os.path
-from typing import Dict, Generator, Literal, Tuple
+from typing import Generator, Literal
 
 import charset_normalizer
 import requests
@@ -15,6 +15,7 @@ from autogpt.commands.command import command
 from autogpt.commands.file_operations_utils import read_textual_file
 from autogpt.config import Config
 from autogpt.logs import logger
+from autogpt.memory.vector import MemoryItem, VectorMemory
 from autogpt.spinner import Spinner
 from autogpt.utils import readable_file_size
 
@@ -28,7 +29,9 @@ def text_checksum(text: str) -> str:
     return hashlib.md5(text.encode("utf-8")).hexdigest()
 
 
-def operations_from_log(log_path: str) -> Generator[Tuple[Operation, str, str | None]]:
+def operations_from_log(
+    log_path: str,
+) -> Generator[tuple[Operation, str, str | None], None, None]:
     """Parse the file operations log and return a tuple containing the log entries"""
     try:
         log = open(log_path, "r", encoding="utf-8")
@@ -45,6 +48,7 @@ def operations_from_log(log_path: str) -> Generator[Tuple[Operation, str, str |
             try:
                 path, checksum = (x.strip() for x in tail.rsplit(" #", maxsplit=1))
             except ValueError:
+                logger.warn(f"File log entry lacks checksum: '{line}'")
                 path, checksum = tail.strip(), None
             yield (operation, path, checksum)
         elif operation == "delete":
@@ -53,7 +57,7 @@ def operations_from_log(log_path: str) -> Generator[Tuple[Operation, str, str |
     log.close()
 
 
-def file_operations_state(log_path: str) -> Dict:
+def file_operations_state(log_path: str) -> dict[str, str]:
     """Iterates over the operations log and returns the expected state.
 
     Parses a log file at CFG.file_logger_path to construct a dictionary that maps
@@ -156,43 +160,41 @@ def read_file(filename: str) -> str:
     """
     try:
         content = read_textual_file(filename, logger)
+
+        # TODO: invalidate/update memory when file is edited
+        file_memory = MemoryItem.from_text_file(content, filename)
+        if len(file_memory.chunks) > 1:
+            return file_memory.summary
+
         return content
     except Exception as e:
         return f"Error: {str(e)}"
 
 
 def ingest_file(
-    filename: str, memory, max_length: int = 4000, overlap: int = 200
+    filename: str,
+    memory: VectorMemory,
 ) -> None:
     """
     Ingest a file by reading its content, splitting it into chunks with a specified
     maximum length and overlap, and adding the chunks to the memory storage.
 
-    :param filename: The name of the file to ingest
-    :param memory: An object with an add() method to store the chunks in memory
-    :param max_length: The maximum length of each chunk, default is 4000
-    :param overlap: The number of overlapping characters between chunks, default is 200
+    Args:
+        filename: The name of the file to ingest
+        memory: An object with an add() method to store the chunks in memory
     """
     try:
-        logger.info(f"Working with file {filename}")
+        logger.info(f"Ingesting file {filename}")
         content = read_file(filename)
-        content_length = len(content)
-        logger.info(f"File length: {content_length} characters")
 
-        chunks = list(split_file(content, max_length=max_length, overlap=overlap))
+        # TODO: differentiate between different types of files
+        file_memory = MemoryItem.from_text_file(content, filename)
+        logger.debug(f"Created memory: {file_memory.dump()}")
+        memory.add(file_memory)
 
-        num_chunks = len(chunks)
-        for i, chunk in enumerate(chunks):
-            logger.info(f"Ingesting chunk {i + 1} / {num_chunks} into memory")
-            memory_to_add = (
-                f"Filename: {filename}\n" f"Content part#{i + 1}/{num_chunks}: {chunk}"
-            )
-
-            memory.add(memory_to_add)
-
-        logger.info(f"Done ingesting {num_chunks} chunks from {filename}.")
+        logger.info(f"Ingested {len(file_memory.e_chunks)} chunks from {filename}")
     except Exception as err:
-        logger.info(f"Error while ingesting file '{filename}': {err}")
+        logger.warn(f"Error while ingesting file '{filename}': {err}")
 
 
 @command("write_to_file", "Write to file", '"filename": "<filename>", "text": "<text>"')
diff --git a/autogpt/commands/file_operations_utils.py b/autogpt/commands/file_operations_utils.py
index cf29dc36..e408c6fa 100644
--- a/autogpt/commands/file_operations_utils.py
+++ b/autogpt/commands/file_operations_utils.py
@@ -10,6 +10,7 @@ from bs4 import BeautifulSoup
 from pylatexenc.latex2text import LatexNodes2Text
 
 from autogpt import logs
+from autogpt.logs import logger
 
 
 class ParserStrategy:
@@ -21,6 +22,7 @@ class ParserStrategy:
 class TXTParser(ParserStrategy):
     def read(self, file_path):
         charset_match = charset_normalizer.from_path(file_path).best()
+        logger.debug(f"Reading '{file_path}' with encoding '{charset_match.encoding}'")
         return str(charset_match)
 
 
@@ -150,9 +152,7 @@ def read_textual_file(file_path: str, logger: logs.Logger):
     parser = extension_to_parser.get(file_extension)
     if not parser:
         if is_binary:
-            raise ValueError(
-                "Unsupported binary file format: {}".format(file_extension)
-            )
+            raise ValueError(f"Unsupported binary file format: {file_extension}")
         # fallback to txt file parser (to support script and code files loading)
         parser = TXTParser()
     file_context = FileContext(parser, logger)
diff --git a/autogpt/commands/improve_code.py b/autogpt/commands/improve_code.py
index ff4cf48c..d2665f3f 100644
--- a/autogpt/commands/improve_code.py
+++ b/autogpt/commands/improve_code.py
@@ -3,7 +3,7 @@ from __future__ import annotations
 import json
 
 from autogpt.commands.command import command
-from autogpt.llm import call_ai_function
+from autogpt.llm.utils import call_ai_function
 
 
 @command(
diff --git a/autogpt/commands/web_requests.py b/autogpt/commands/web_requests.py
index 60e54252..156ba103 100644
--- a/autogpt/commands/web_requests.py
+++ b/autogpt/commands/web_requests.py
@@ -100,13 +100,3 @@ def scrape_links(url: str) -> str | list[str]:
     hyperlinks = extract_hyperlinks(soup, url)
 
     return format_hyperlinks(hyperlinks)
-
-
-def create_message(chunk, question):
-    """Create a message for the user to summarize a chunk of text"""
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the'
-        " text, summarize the text.",
-    }
diff --git a/autogpt/commands/web_selenium.py b/autogpt/commands/web_selenium.py
index 4f5ad30e..72f849d0 100644
--- a/autogpt/commands/web_selenium.py
+++ b/autogpt/commands/web_selenium.py
@@ -4,28 +4,39 @@ from __future__ import annotations
 import logging
 from pathlib import Path
 from sys import platform
+from typing import Optional, Type
 
 from bs4 import BeautifulSoup
-from selenium import webdriver
 from selenium.common.exceptions import WebDriverException
 from selenium.webdriver.chrome.options import Options as ChromeOptions
+from selenium.webdriver.chrome.service import Service as ChromeDriverService
+from selenium.webdriver.chrome.webdriver import WebDriver as ChromeDriver
 from selenium.webdriver.common.by import By
 from selenium.webdriver.edge.options import Options as EdgeOptions
+from selenium.webdriver.edge.service import Service as EdgeDriverService
+from selenium.webdriver.edge.webdriver import WebDriver as EdgeDriver
 from selenium.webdriver.firefox.options import Options as FirefoxOptions
+from selenium.webdriver.firefox.service import Service as GeckoDriverService
+from selenium.webdriver.firefox.webdriver import WebDriver as FirefoxDriver
 from selenium.webdriver.remote.webdriver import WebDriver
 from selenium.webdriver.safari.options import Options as SafariOptions
+from selenium.webdriver.safari.webdriver import WebDriver as SafariDriver
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.wait import WebDriverWait
 from webdriver_manager.chrome import ChromeDriverManager
 from webdriver_manager.firefox import GeckoDriverManager
-from webdriver_manager.microsoft import EdgeChromiumDriverManager
+from webdriver_manager.microsoft import EdgeChromiumDriverManager as EdgeDriverManager
 
-import autogpt.processing.text as summary
 from autogpt.commands.command import command
 from autogpt.config import Config
+from autogpt.logs import logger
+from autogpt.memory.vector import MemoryItem, NoMemory, get_memory
 from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
+from autogpt.processing.text import summarize_text
 from autogpt.url_utils.validators import validate_url
 
+BrowserOptions = ChromeOptions | EdgeOptions | FirefoxOptions | SafariOptions
+
 FILE_DIR = Path(__file__).parent.parent
 CFG = Config()
 
@@ -55,14 +66,14 @@ def browse_website(url: str, question: str) -> str:
         return f"Error: {msg}"
 
     add_header(driver)
-    summary_text = summary.summarize_text(url, text, question, driver)
+    summary = summarize_memorize_webpage(url, text, question, driver)
     links = scrape_links_with_selenium(driver, url)
 
     # Limit links to 5
     if len(links) > 5:
         links = links[:5]
     close_browser(driver)
-    return f"Answer gathered from website: {summary_text} \n \n Links: {links}"
+    return f"Answer gathered from website: {summary}\n\nLinks: {links}"
 
 
 def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
@@ -76,14 +87,14 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
     """
     logging.getLogger("selenium").setLevel(logging.CRITICAL)
 
-    options_available = {
+    options_available: dict[str, Type[BrowserOptions]] = {
         "chrome": ChromeOptions,
-        "safari": SafariOptions,
-        "firefox": FirefoxOptions,
         "edge": EdgeOptions,
+        "firefox": FirefoxOptions,
+        "safari": SafariOptions,
     }
 
-    options = options_available[CFG.selenium_web_browser]()
+    options: BrowserOptions = options_available[CFG.selenium_web_browser]()
     options.add_argument(
         "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
     )
@@ -92,17 +103,17 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
         if CFG.selenium_headless:
             options.headless = True
             options.add_argument("--disable-gpu")
-        driver = webdriver.Firefox(
-            executable_path=GeckoDriverManager().install(), options=options
+        driver = FirefoxDriver(
+            service=GeckoDriverService(GeckoDriverManager().install()), options=options
+        )
+    elif CFG.selenium_web_browser == "edge":
+        driver = EdgeDriver(
+            service=EdgeDriverService(EdgeDriverManager().install()), options=options
         )
     elif CFG.selenium_web_browser == "safari":
         # Requires a bit more setup on the users end
         # See https://developer.apple.com/documentation/webkit/testing_with_webdriver_in_safari
-        driver = webdriver.Safari(options=options)
-    elif CFG.selenium_web_browser == "edge":
-        driver = webdriver.Edge(
-            executable_path=EdgeChromiumDriverManager().install(), options=options
-        )
+        driver = SafariDriver(options=options)
     else:
         if platform == "linux" or platform == "linux2":
             options.add_argument("--disable-dev-shm-usage")
@@ -115,10 +126,10 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
 
         chromium_driver_path = Path("/usr/bin/chromedriver")
 
-        driver = webdriver.Chrome(
-            executable_path=chromium_driver_path
+        driver = ChromeDriver(
+            service=ChromeDriverService(str(chromium_driver_path))
             if chromium_driver_path.exists()
-            else ChromeDriverManager().install(),
+            else ChromeDriverService(ChromeDriverManager().install()),
             options=options,
         )
     driver.get(url)
@@ -188,3 +199,30 @@ def add_header(driver: WebDriver) -> None:
         driver.execute_script(overlay_script)
     except Exception as e:
         print(f"Error executing overlay.js: {e}")
+
+
+def summarize_memorize_webpage(
+    url: str, text: str, question: str, driver: Optional[WebDriver] = None
+) -> str:
+    """Summarize text using the OpenAI API
+
+    Args:
+        url (str): The url of the text
+        text (str): The text to summarize
+        question (str): The question to ask the model
+        driver (WebDriver): The webdriver to use to scroll the page
+
+    Returns:
+        str: The summary of the text
+    """
+    if not text:
+        return "Error: No text to summarize"
+
+    text_length = len(text)
+    logger.info(f"Text length: {text_length} characters")
+
+    memory = get_memory(CFG)
+
+    new_memory = MemoryItem.from_webpage(text, url, question=question)
+    memory.add(new_memory)
+    return new_memory.summary
diff --git a/autogpt/commands/write_tests.py b/autogpt/commands/write_tests.py
index c6a03324..1f4c4dbb 100644
--- a/autogpt/commands/write_tests.py
+++ b/autogpt/commands/write_tests.py
@@ -4,7 +4,7 @@ from __future__ import annotations
 import json
 
 from autogpt.commands.command import command
-from autogpt.llm import call_ai_function
+from autogpt.llm.utils import call_ai_function
 
 
 @command(
diff --git a/autogpt/config/ai_config.py b/autogpt/config/ai_config.py
index 0599f104..3872463f 100644
--- a/autogpt/config/ai_config.py
+++ b/autogpt/config/ai_config.py
@@ -7,11 +7,12 @@ from __future__ import annotations
 import os
 import platform
 from pathlib import Path
-from typing import Any, Optional, Type
+from typing import Optional
 
 import distro
 import yaml
 
+from autogpt.commands.command import CommandRegistry
 from autogpt.prompts.generator import PromptGenerator
 
 # Soon this will go in a folder where it remembers more stuff about the run(s)
@@ -53,8 +54,8 @@ class AIConfig:
         self.ai_role = ai_role
         self.ai_goals = ai_goals
         self.api_budget = api_budget
-        self.prompt_generator = None
-        self.command_registry = None
+        self.prompt_generator: PromptGenerator | None = None
+        self.command_registry: CommandRegistry | None = None
 
     @staticmethod
     def load(config_file: str = SAVE_FILE) -> "AIConfig":
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index 7e8c0c37..94255333 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -17,8 +17,8 @@ class Config(metaclass=Singleton):
 
     def __init__(self) -> None:
         """Initialize the Config class"""
-        self.workspace_path = None
-        self.file_logger_path = None
+        self.workspace_path: str = None
+        self.file_logger_path: str = None
 
         self.debug_mode = False
         self.continuous_mode = False
@@ -58,9 +58,6 @@ class Config(metaclass=Singleton):
         self.fast_token_limit = int(os.getenv("FAST_TOKEN_LIMIT", 4000))
         self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000))
         self.embedding_model = os.getenv("EMBEDDING_MODEL", "text-embedding-ada-002")
-        self.embedding_tokenizer = os.getenv("EMBEDDING_TOKENIZER", "cl100k_base")
-        self.embedding_token_limit = int(os.getenv("EMBEDDING_TOKEN_LIMIT", 8191))
-        self.browse_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 3000))
         self.browse_spacy_language_model = os.getenv(
             "BROWSE_SPACY_LANGUAGE_MODEL", "en_core_web_sm"
         )
@@ -99,28 +96,6 @@ class Config(metaclass=Singleton):
         self.google_api_key = os.getenv("GOOGLE_API_KEY")
         self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
 
-        self.pinecone_api_key = os.getenv("PINECONE_API_KEY")
-        self.pinecone_region = os.getenv("PINECONE_ENV")
-
-        self.weaviate_host = os.getenv("WEAVIATE_HOST")
-        self.weaviate_port = os.getenv("WEAVIATE_PORT")
-        self.weaviate_protocol = os.getenv("WEAVIATE_PROTOCOL", "http")
-        self.weaviate_username = os.getenv("WEAVIATE_USERNAME", None)
-        self.weaviate_password = os.getenv("WEAVIATE_PASSWORD", None)
-        self.weaviate_scopes = os.getenv("WEAVIATE_SCOPES", None)
-        self.weaviate_embedded_path = os.getenv("WEAVIATE_EMBEDDED_PATH")
-        self.weaviate_api_key = os.getenv("WEAVIATE_API_KEY", None)
-        self.use_weaviate_embedded = (
-            os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True"
-        )
-
-        # milvus or zilliz cloud configuration.
-        self.milvus_addr = os.getenv("MILVUS_ADDR", "localhost:19530")
-        self.milvus_username = os.getenv("MILVUS_USERNAME")
-        self.milvus_password = os.getenv("MILVUS_PASSWORD")
-        self.milvus_collection = os.getenv("MILVUS_COLLECTION", "autogpt")
-        self.milvus_secure = os.getenv("MILVUS_SECURE") == "True"
-
         self.image_provider = os.getenv("IMAGE_PROVIDER")
         self.image_size = int(os.getenv("IMAGE_SIZE", 256))
         self.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN")
@@ -146,14 +121,13 @@ class Config(metaclass=Singleton):
             " (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
         )
 
+        self.memory_backend = os.getenv("MEMORY_BACKEND", "json_file")
+        self.memory_index = os.getenv("MEMORY_INDEX", "auto-gpt-memory")
+
         self.redis_host = os.getenv("REDIS_HOST", "localhost")
-        self.redis_port = os.getenv("REDIS_PORT", "6379")
+        self.redis_port = int(os.getenv("REDIS_PORT", "6379"))
         self.redis_password = os.getenv("REDIS_PASSWORD", "")
         self.wipe_redis_on_start = os.getenv("WIPE_REDIS_ON_START", "True") == "True"
-        self.memory_index = os.getenv("MEMORY_INDEX", "auto-gpt")
-        # Note that indexes must be created on db 0 in redis, this is not configurable.
-
-        self.memory_backend = os.getenv("MEMORY_BACKEND", "local")
 
         self.plugins_dir = os.getenv("PLUGINS_DIR", "plugins")
         self.plugins: List[AutoGPTPluginTemplate] = []
@@ -250,18 +224,6 @@ class Config(metaclass=Singleton):
         """Set the model to use for creating embeddings."""
         self.embedding_model = value
 
-    def set_embedding_tokenizer(self, value: str) -> None:
-        """Set the tokenizer to use when creating embeddings."""
-        self.embedding_tokenizer = value
-
-    def set_embedding_token_limit(self, value: int) -> None:
-        """Set the token limit for creating embeddings."""
-        self.embedding_token_limit = value
-
-    def set_browse_chunk_max_length(self, value: int) -> None:
-        """Set the browse_website command chunk max length value."""
-        self.browse_chunk_max_length = value
-
     def set_openai_api_key(self, value: str) -> None:
         """Set the OpenAI API key value."""
         self.openai_api_key = value
@@ -286,14 +248,6 @@ class Config(metaclass=Singleton):
         """Set the custom search engine id value."""
         self.custom_search_engine_id = value
 
-    def set_pinecone_api_key(self, value: str) -> None:
-        """Set the Pinecone API key value."""
-        self.pinecone_api_key = value
-
-    def set_pinecone_region(self, value: str) -> None:
-        """Set the Pinecone region value."""
-        self.pinecone_region = value
-
     def set_debug_mode(self, value: bool) -> None:
         """Set the debug mode value."""
         self.debug_mode = value
diff --git a/autogpt/configurator.py b/autogpt/configurator.py
index 98bd0b26..f156f2c7 100644
--- a/autogpt/configurator.py
+++ b/autogpt/configurator.py
@@ -6,9 +6,9 @@ from colorama import Back, Fore, Style
 
 from autogpt import utils
 from autogpt.config import Config
-from autogpt.llm.llm_utils import check_model
+from autogpt.llm.utils import check_model
 from autogpt.logs import logger
-from autogpt.memory import get_supported_memory_backends
+from autogpt.memory.vector import get_supported_memory_backends
 
 CFG = Config()
 
diff --git a/autogpt/json_utils/json_fix_llm.py b/autogpt/json_utils/json_fix_llm.py
index 73f76648..9e9fe533 100644
--- a/autogpt/json_utils/json_fix_llm.py
+++ b/autogpt/json_utils/json_fix_llm.py
@@ -11,7 +11,7 @@ from regex import regex
 
 from autogpt.config import Config
 from autogpt.json_utils.json_fix_general import correct_json
-from autogpt.llm import call_ai_function
+from autogpt.llm.utils import call_ai_function
 from autogpt.logs import logger
 from autogpt.speech import say_text
 
diff --git a/autogpt/llm/__init__.py b/autogpt/llm/__init__.py
index 76eaf3b7..22a743c0 100644
--- a/autogpt/llm/__init__.py
+++ b/autogpt/llm/__init__.py
@@ -1,4 +1,3 @@
-from autogpt.llm.api_manager import ApiManager
 from autogpt.llm.base import (
     ChatModelInfo,
     ChatModelResponse,
@@ -8,18 +7,8 @@ from autogpt.llm.base import (
     Message,
     ModelInfo,
 )
-from autogpt.llm.chat import chat_with_ai, create_chat_message, generate_context
-from autogpt.llm.llm_utils import (
-    call_ai_function,
-    chunked_tokens,
-    create_chat_completion,
-    get_ada_embedding,
-)
-from autogpt.llm.modelsinfo import COSTS
-from autogpt.llm.token_counter import count_message_tokens, count_string_tokens
 
 __all__ = [
-    "ApiManager",
     "Message",
     "ModelInfo",
     "ChatModelInfo",
@@ -27,14 +16,4 @@ __all__ = [
     "LLMResponse",
     "ChatModelResponse",
     "EmbeddingModelResponse",
-    "create_chat_message",
-    "generate_context",
-    "chat_with_ai",
-    "call_ai_function",
-    "create_chat_completion",
-    "get_ada_embedding",
-    "chunked_tokens",
-    "COSTS",
-    "count_message_tokens",
-    "count_string_tokens",
 ]
diff --git a/autogpt/llm/api_manager.py b/autogpt/llm/api_manager.py
index 82cf1c57..7442579d 100644
--- a/autogpt/llm/api_manager.py
+++ b/autogpt/llm/api_manager.py
@@ -6,6 +6,7 @@ import openai
 from openai import Model
 
 from autogpt.config import Config
+from autogpt.llm.base import MessageDict
 from autogpt.llm.modelsinfo import COSTS
 from autogpt.logs import logger
 from autogpt.singleton import Singleton
@@ -28,7 +29,7 @@ class ApiManager(metaclass=Singleton):
 
     def create_chat_completion(
         self,
-        messages: list,  # type: ignore
+        messages: list[MessageDict],
         model: str | None = None,
         temperature: float = None,
         max_tokens: int | None = None,
@@ -71,7 +72,7 @@ class ApiManager(metaclass=Singleton):
             self.update_cost(prompt_tokens, completion_tokens, model)
         return response
 
-    def update_cost(self, prompt_tokens, completion_tokens, model):
+    def update_cost(self, prompt_tokens, completion_tokens, model: str):
         """
         Update the total cost, prompt tokens, and completion tokens.
 
@@ -80,6 +81,9 @@ class ApiManager(metaclass=Singleton):
         completion_tokens (int): The number of tokens used in the completion.
         model (str): The model used for the API call.
         """
+        # the .model property in API responses can contain version suffixes like -v2
+        model = model[:-3] if model.endswith("-v2") else model
+
         self.total_prompt_tokens += prompt_tokens
         self.total_completion_tokens += completion_tokens
         self.total_cost += (
diff --git a/autogpt/llm/base.py b/autogpt/llm/base.py
index 722e0f0f..5018b703 100644
--- a/autogpt/llm/base.py
+++ b/autogpt/llm/base.py
@@ -1,12 +1,28 @@
+from __future__ import annotations
+
 from dataclasses import dataclass, field
-from typing import List, TypedDict
+from math import ceil, floor
+from typing import List, Literal, TypedDict
+
+MessageRole = Literal["system", "user", "assistant"]
+MessageType = Literal["ai_response", "action_result"]
 
 
-class Message(TypedDict):
+class MessageDict(TypedDict):
+    role: MessageRole
+    content: str
+
+
+@dataclass
+class Message:
     """OpenAI Message object containing a role and the message content"""
 
-    role: str
+    role: MessageRole
     content: str
+    type: MessageType | None = None
+
+    def raw(self) -> MessageDict:
+        return {"role": self.role, "content": self.content}
 
 
 @dataclass
@@ -31,6 +47,13 @@ class ChatModelInfo(ModelInfo):
     pass
 
 
+@dataclass
+class TextModelInfo(ModelInfo):
+    """Struct for text completion model information."""
+
+    pass
+
+
 @dataclass
 class EmbeddingModelInfo(ModelInfo):
     """Struct for embedding model information."""
@@ -38,6 +61,73 @@ class EmbeddingModelInfo(ModelInfo):
     embedding_dimensions: int
 
 
+@dataclass
+class ChatSequence:
+    """Utility container for a chat sequence"""
+
+    model: ChatModelInfo
+    messages: list[Message] = field(default_factory=list)
+
+    def __getitem__(self, i: int):
+        return self.messages[i]
+
+    def __iter__(self):
+        return iter(self.messages)
+
+    def __len__(self):
+        return len(self.messages)
+
+    def append(self, message: Message):
+        return self.messages.append(message)
+
+    def extend(self, messages: list[Message] | ChatSequence):
+        return self.messages.extend(messages)
+
+    def insert(self, index: int, *messages: Message):
+        for message in reversed(messages):
+            self.messages.insert(index, message)
+
+    @classmethod
+    def for_model(cls, model_name: str, messages: list[Message] | ChatSequence = []):
+        from autogpt.llm.providers.openai import OPEN_AI_CHAT_MODELS
+
+        if not model_name in OPEN_AI_CHAT_MODELS:
+            raise ValueError(f"Unknown chat model '{model_name}'")
+
+        return ChatSequence(
+            model=OPEN_AI_CHAT_MODELS[model_name], messages=list(messages)
+        )
+
+    def add(self, message_role: MessageRole, content: str):
+        self.messages.append(Message(message_role, content))
+
+    @property
+    def token_length(self):
+        from autogpt.llm.utils import count_message_tokens
+
+        return count_message_tokens(self.messages, self.model.name)
+
+    def raw(self) -> list[MessageDict]:
+        return [m.raw() for m in self.messages]
+
+    def dump(self) -> str:
+        SEPARATOR_LENGTH = 42
+
+        def separator(text: str):
+            half_sep_len = (SEPARATOR_LENGTH - 2 - len(text)) / 2
+            return f"{floor(half_sep_len)*'-'} {text.upper()} {ceil(half_sep_len)*'-'}"
+
+        formatted_messages = "\n".join(
+            [f"{separator(m.role)}\n{m.content}" for m in self.messages]
+        )
+        return f"""
+============== ChatSequence ==============
+Length: {self.token_length} tokens; {len(self.messages)} messages
+{formatted_messages}
+==========================================
+"""
+
+
 @dataclass
 class LLMResponse:
     """Standard response struct for a response from an LLM model."""
diff --git a/autogpt/llm/chat.py b/autogpt/llm/chat.py
index a59fe73e..c55016f2 100644
--- a/autogpt/llm/chat.py
+++ b/autogpt/llm/chat.py
@@ -1,260 +1,200 @@
+from __future__ import annotations
+
 import time
 from random import shuffle
+from typing import TYPE_CHECKING
 
-from openai.error import RateLimitError
+if TYPE_CHECKING:
+    from autogpt.agent.agent import Agent
 
 from autogpt.config import Config
 from autogpt.llm.api_manager import ApiManager
-from autogpt.llm.base import Message
-from autogpt.llm.llm_utils import create_chat_completion
-from autogpt.llm.token_counter import count_message_tokens
+from autogpt.llm.base import ChatSequence, Message
+from autogpt.llm.utils import count_message_tokens, create_chat_completion
 from autogpt.log_cycle.log_cycle import CURRENT_CONTEXT_FILE_NAME
 from autogpt.logs import logger
+from autogpt.memory.vector import MemoryItem, get_memory
 
 cfg = Config()
 
 
-def create_chat_message(role, content) -> Message:
-    """
-    Create a chat message with the given role and content.
-
-    Args:
-    role (str): The role of the message sender, e.g., "system", "user", or "assistant".
-    content (str): The content of the message.
-
-    Returns:
-    dict: A dictionary containing the role and content of the message.
-    """
-    return {"role": role, "content": content}
-
-
-def generate_context(prompt, relevant_memory, full_message_history, model):
-    current_context = [
-        create_chat_message("system", prompt),
-        create_chat_message(
-            "system", f"The current time and date is {time.strftime('%c')}"
-        ),
-        # create_chat_message(
-        #     "system",
-        #     f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
-        # ),
-    ]
-
-    # Add messages from the full message history until we reach the token limit
-    next_message_to_add_index = len(full_message_history) - 1
-    insertion_index = len(current_context)
-    # Count the currently used tokens
-    current_tokens_used = count_message_tokens(current_context, model)
-    return (
-        next_message_to_add_index,
-        current_tokens_used,
-        insertion_index,
-        current_context,
-    )
-
-
 # TODO: Change debug from hardcode to argument
 def chat_with_ai(
-    agent, prompt, user_input, full_message_history, permanent_memory, token_limit
+    agent: Agent,
+    system_prompt: str,
+    user_input: str,
+    token_limit: int,
 ):
-    """Interact with the OpenAI API, sending the prompt, user input, message history,
-    and permanent memory."""
-    while True:
-        try:
-            """
-            Interact with the OpenAI API, sending the prompt, user input,
-                message history, and permanent memory.
+    """
+    Interact with the OpenAI API, sending the prompt, user input,
+        message history, and permanent memory.
 
-            Args:
-                prompt (str): The prompt explaining the rules to the AI.
-                user_input (str): The input from the user.
-                full_message_history (list): The list of all messages sent between the
-                    user and the AI.
-                permanent_memory (Obj): The memory object containing the permanent
-                  memory.
-                token_limit (int): The maximum number of tokens allowed in the API call.
+    Args:
+        system_prompt (str): The prompt explaining the rules to the AI.
+        user_input (str): The input from the user.
+        token_limit (int): The maximum number of tokens allowed in the API call.
 
-            Returns:
-            str: The AI's response.
-            """
-            model = cfg.fast_llm_model  # TODO: Change model from hardcode to argument
-            # Reserve 1000 tokens for the response
-            logger.debug(f"Token limit: {token_limit}")
-            send_token_limit = token_limit - 1000
+    Returns:
+    str: The AI's response.
+    """
+    model = cfg.fast_llm_model  # TODO: Change model from hardcode to argument
+    # Reserve 1000 tokens for the response
+    logger.debug(f"Token limit: {token_limit}")
+    send_token_limit = token_limit - 1000
 
-            # if len(full_message_history) == 0:
-            #     relevant_memory = ""
-            # else:
-            #     recent_history = full_message_history[-5:]
-            #     shuffle(recent_history)
-            #     relevant_memories = permanent_memory.get_relevant(
-            #         str(recent_history), 5
-            #     )
-            #     if relevant_memories:
-            #         shuffle(relevant_memories)
-            #     relevant_memory = str(relevant_memories)
-            relevant_memory = ""
-            logger.debug(f"Memory Stats: {permanent_memory.get_stats()}")
+    # if len(agent.history) == 0:
+    #     relevant_memory = ""
+    # else:
+    #     recent_history = agent.history[-5:]
+    #     shuffle(recent_history)
+    #     relevant_memories = agent.memory.get_relevant(
+    #         str(recent_history), 5
+    #     )
+    #     if relevant_memories:
+    #         shuffle(relevant_memories)
+    #     relevant_memory = str(relevant_memories)
+    # logger.debug(f"Memory Stats: {agent.memory.get_stats()}")
+    relevant_memory = []
 
-            (
-                next_message_to_add_index,
-                current_tokens_used,
-                insertion_index,
-                current_context,
-            ) = generate_context(prompt, relevant_memory, full_message_history, model)
+    message_sequence = ChatSequence.for_model(
+        model,
+        [
+            Message("system", system_prompt),
+            Message("system", f"The current time and date is {time.strftime('%c')}"),
+            # Message(
+            #     "system",
+            #     f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
+            # ),
+        ],
+    )
 
-            # while current_tokens_used > 2500:
-            #     # remove memories until we are under 2500 tokens
-            #     relevant_memory = relevant_memory[:-1]
-            #     (
-            #         next_message_to_add_index,
-            #         current_tokens_used,
-            #         insertion_index,
-            #         current_context,
-            #     ) = generate_context(
-            #         prompt, relevant_memory, full_message_history, model
-            #     )
+    # Add messages from the full message history until we reach the token limit
+    next_message_to_add_index = len(agent.history) - 1
+    insertion_index = len(message_sequence)
+    # Count the currently used tokens
+    current_tokens_used = message_sequence.token_length
 
-            current_tokens_used += count_message_tokens(
-                [create_chat_message("user", user_input)], model
-            )  # Account for user input (appended later)
+    # while current_tokens_used > 2500:
+    #     # remove memories until we are under 2500 tokens
+    #     relevant_memory = relevant_memory[:-1]
+    #     (
+    #         next_message_to_add_index,
+    #         current_tokens_used,
+    #         insertion_index,
+    #         current_context,
+    #     ) = generate_context(
+    #         prompt, relevant_memory, agent.history, model
+    #     )
 
-            current_tokens_used += 500  # Account for memory (appended later) TODO: The final memory may be less than 500 tokens
+    # Account for user input (appended later)
+    user_input_msg = Message("user", user_input)
+    current_tokens_used += count_message_tokens([user_input_msg], model)
 
-            # Add Messages until the token limit is reached or there are no more messages to add.
-            while next_message_to_add_index >= 0:
-                # print (f"CURRENT TOKENS USED: {current_tokens_used}")
-                message_to_add = full_message_history[next_message_to_add_index]
+    current_tokens_used += 500  # Reserve space for new_summary_message
 
-                tokens_to_add = count_message_tokens([message_to_add], model)
-                if current_tokens_used + tokens_to_add > send_token_limit:
-                    # save_memory_trimmed_from_context_window(
-                    #     full_message_history,
-                    #     next_message_to_add_index,
-                    #     permanent_memory,
-                    # )
-                    break
+    # Add Messages until the token limit is reached or there are no more messages to add.
+    for cycle in reversed(list(agent.history.per_cycle())):
+        messages_to_add = [msg for msg in cycle if msg is not None]
+        tokens_to_add = count_message_tokens(messages_to_add, model)
+        if current_tokens_used + tokens_to_add > send_token_limit:
+            break
 
-                # Add the most recent message to the start of the current context,
-                #  after the two system prompts.
-                current_context.insert(
-                    insertion_index, full_message_history[next_message_to_add_index]
-                )
+        # Add the most recent message to the start of the chain,
+        #  after the system prompts.
+        message_sequence.insert(insertion_index, *messages_to_add)
+        current_tokens_used += tokens_to_add
 
-                # Count the currently used tokens
-                current_tokens_used += tokens_to_add
+    # Update & add summary of trimmed messages
+    if len(agent.history) > 0:
+        new_summary_message, trimmed_messages = agent.history.trim_messages(
+            current_message_chain=list(message_sequence),
+        )
+        tokens_to_add = count_message_tokens([new_summary_message], model)
+        message_sequence.insert(insertion_index, new_summary_message)
+        current_tokens_used += tokens_to_add - 500
 
-                # Move to the next most recent message in the full message history
-                next_message_to_add_index -= 1
-            from autogpt.memory_management.summary_memory import (
-                get_newly_trimmed_messages,
-                update_running_summary,
-            )
+        # FIXME: uncomment when memory is back in use
+        # memory_store = get_memory(cfg)
+        # for _, ai_msg, result_msg in agent.history.per_cycle(trimmed_messages):
+        #     memory_to_add = MemoryItem.from_ai_action(ai_msg, result_msg)
+        #     logger.debug(f"Storing the following memory:\n{memory_to_add.dump()}")
+        #     memory_store.add(memory_to_add)
 
-            # Insert Memories
-            if len(full_message_history) > 0:
-                (
-                    newly_trimmed_messages,
-                    agent.last_memory_index,
-                ) = get_newly_trimmed_messages(
-                    full_message_history=full_message_history,
-                    current_context=current_context,
-                    last_memory_index=agent.last_memory_index,
-                )
+    api_manager = ApiManager()
+    # inform the AI about its remaining budget (if it has one)
+    if api_manager.get_total_budget() > 0.0:
+        remaining_budget = api_manager.get_total_budget() - api_manager.get_total_cost()
+        if remaining_budget < 0:
+            remaining_budget = 0
+        budget_message = f"Your remaining API budget is ${remaining_budget:.3f}" + (
+            " BUDGET EXCEEDED! SHUT DOWN!\n\n"
+            if remaining_budget == 0
+            else " Budget very nearly exceeded! Shut down gracefully!\n\n"
+            if remaining_budget < 0.005
+            else " Budget nearly exceeded. Finish up.\n\n"
+            if remaining_budget < 0.01
+            else "\n\n"
+        )
+        logger.debug(budget_message)
+        message_sequence.add("system", budget_message)
+        current_tokens_used += count_message_tokens([message_sequence[-1]], model)
 
-                agent.summary_memory = update_running_summary(
-                    agent,
-                    current_memory=agent.summary_memory,
-                    new_events=newly_trimmed_messages,
-                )
-                current_context.insert(insertion_index, agent.summary_memory)
+    # Append user input, the length of this is accounted for above
+    message_sequence.append(user_input_msg)
 
-            api_manager = ApiManager()
-            # inform the AI about its remaining budget (if it has one)
-            if api_manager.get_total_budget() > 0.0:
-                remaining_budget = (
-                    api_manager.get_total_budget() - api_manager.get_total_cost()
-                )
-                if remaining_budget < 0:
-                    remaining_budget = 0
-                system_message = (
-                    f"Your remaining API budget is ${remaining_budget:.3f}"
-                    + (
-                        " BUDGET EXCEEDED! SHUT DOWN!\n\n"
-                        if remaining_budget == 0
-                        else " Budget very nearly exceeded! Shut down gracefully!\n\n"
-                        if remaining_budget < 0.005
-                        else " Budget nearly exceeded. Finish up.\n\n"
-                        if remaining_budget < 0.01
-                        else "\n\n"
-                    )
-                )
-                logger.debug(system_message)
-                current_context.append(create_chat_message("system", system_message))
+    plugin_count = len(cfg.plugins)
+    for i, plugin in enumerate(cfg.plugins):
+        if not plugin.can_handle_on_planning():
+            continue
+        plugin_response = plugin.on_planning(
+            agent.config.prompt_generator, message_sequence.raw()
+        )
+        if not plugin_response or plugin_response == "":
+            continue
+        tokens_to_add = count_message_tokens(
+            [Message("system", plugin_response)], model
+        )
+        if current_tokens_used + tokens_to_add > send_token_limit:
+            logger.debug(f"Plugin response too long, skipping: {plugin_response}")
+            logger.debug(f"Plugins remaining at stop: {plugin_count - i}")
+            break
+        message_sequence.add("system", plugin_response)
 
-            # Append user input, the length of this is accounted for above
-            current_context.extend([create_chat_message("user", user_input)])
+    # Calculate remaining tokens
+    tokens_remaining = token_limit - current_tokens_used
+    # assert tokens_remaining >= 0, "Tokens remaining is negative.
+    # This should never happen, please submit a bug report at
+    #  https://www.github.com/Torantulino/Auto-GPT"
 
-            plugin_count = len(cfg.plugins)
-            for i, plugin in enumerate(cfg.plugins):
-                if not plugin.can_handle_on_planning():
-                    continue
-                plugin_response = plugin.on_planning(
-                    agent.config.prompt_generator, current_context
-                )
-                if not plugin_response or plugin_response == "":
-                    continue
-                tokens_to_add = count_message_tokens(
-                    [create_chat_message("system", plugin_response)], model
-                )
-                if current_tokens_used + tokens_to_add > send_token_limit:
-                    logger.debug("Plugin response too long, skipping:", plugin_response)
-                    logger.debug("Plugins remaining at stop:", plugin_count - i)
-                    break
-                current_context.append(create_chat_message("system", plugin_response))
+    # Debug print the current context
+    logger.debug(f"Token limit: {token_limit}")
+    logger.debug(f"Send Token Count: {current_tokens_used}")
+    logger.debug(f"Tokens remaining for response: {tokens_remaining}")
+    logger.debug("------------ CONTEXT SENT TO AI ---------------")
+    for message in message_sequence:
+        # Skip printing the prompt
+        if message.role == "system" and message.content == system_prompt:
+            continue
+        logger.debug(f"{message.role.capitalize()}: {message.content}")
+        logger.debug("")
+    logger.debug("----------- END OF CONTEXT ----------------")
+    agent.log_cycle_handler.log_cycle(
+        agent.config.ai_name,
+        agent.created_at,
+        agent.cycle_count,
+        message_sequence.raw(),
+        CURRENT_CONTEXT_FILE_NAME,
+    )
 
-            # Calculate remaining tokens
-            tokens_remaining = token_limit - current_tokens_used
-            # assert tokens_remaining >= 0, "Tokens remaining is negative.
-            # This should never happen, please submit a bug report at
-            #  https://www.github.com/Torantulino/Auto-GPT"
+    # TODO: use a model defined elsewhere, so that model can contain
+    # temperature and other settings we care about
+    assistant_reply = create_chat_completion(
+        prompt=message_sequence,
+        max_tokens=tokens_remaining,
+    )
 
-            # Debug print the current context
-            logger.debug(f"Token limit: {token_limit}")
-            logger.debug(f"Send Token Count: {current_tokens_used}")
-            logger.debug(f"Tokens remaining for response: {tokens_remaining}")
-            logger.debug("------------ CONTEXT SENT TO AI ---------------")
-            for message in current_context:
-                # Skip printing the prompt
-                if message["role"] == "system" and message["content"] == prompt:
-                    continue
-                logger.debug(f"{message['role'].capitalize()}: {message['content']}")
-                logger.debug("")
-            logger.debug("----------- END OF CONTEXT ----------------")
-            agent.log_cycle_handler.log_cycle(
-                agent.config.ai_name,
-                agent.created_at,
-                agent.cycle_count,
-                current_context,
-                CURRENT_CONTEXT_FILE_NAME,
-            )
+    # Update full message history
+    agent.history.append(user_input_msg)
+    agent.history.add("assistant", assistant_reply, "ai_response")
 
-            # TODO: use a model defined elsewhere, so that model can contain
-            # temperature and other settings we care about
-            assistant_reply = create_chat_completion(
-                model=model,
-                messages=current_context,
-                max_tokens=tokens_remaining,
-            )
-
-            # Update full message history
-            full_message_history.append(create_chat_message("user", user_input))
-            full_message_history.append(
-                create_chat_message("assistant", assistant_reply)
-            )
-
-            return assistant_reply
-        except RateLimitError:
-            # TODO: When we switch to langchain, this is built in
-            logger.warn("Error: ", "API Rate Limit Reached. Waiting 10 seconds...")
-            time.sleep(10)
+    return assistant_reply
diff --git a/autogpt/llm/modelsinfo.py b/autogpt/llm/modelsinfo.py
index 1bebcbf9..425472de 100644
--- a/autogpt/llm/modelsinfo.py
+++ b/autogpt/llm/modelsinfo.py
@@ -7,4 +7,5 @@ COSTS = {
     "gpt-4-32k": {"prompt": 0.06, "completion": 0.12},
     "gpt-4-32k-0314": {"prompt": 0.06, "completion": 0.12},
     "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
+    "text-davinci-003": {"prompt": 0.02, "completion": 0.02},
 }
diff --git a/autogpt/llm/providers/openai.py b/autogpt/llm/providers/openai.py
index 188d5cf7..acaf0671 100644
--- a/autogpt/llm/providers/openai.py
+++ b/autogpt/llm/providers/openai.py
@@ -1,37 +1,74 @@
-from autogpt.llm.base import ChatModelInfo, EmbeddingModelInfo
+from autogpt.llm.base import ChatModelInfo, EmbeddingModelInfo, TextModelInfo
 
 OPEN_AI_CHAT_MODELS = {
-    "gpt-3.5-turbo": ChatModelInfo(
-        name="gpt-3.5-turbo",
-        prompt_token_cost=0.002,
-        completion_token_cost=0.002,
-        max_tokens=4096,
-    ),
-    "gpt-4": ChatModelInfo(
-        name="gpt-4",
-        prompt_token_cost=0.03,
-        completion_token_cost=0.06,
-        max_tokens=8192,
-    ),
-    "gpt-4-32k": ChatModelInfo(
-        name="gpt-4-32k",
-        prompt_token_cost=0.06,
-        completion_token_cost=0.12,
-        max_tokens=32768,
-    ),
+    info.name: info
+    for info in [
+        ChatModelInfo(
+            name="gpt-3.5-turbo",
+            prompt_token_cost=0.002,
+            completion_token_cost=0.002,
+            max_tokens=4096,
+        ),
+        ChatModelInfo(
+            name="gpt-3.5-turbo-0301",
+            prompt_token_cost=0.002,
+            completion_token_cost=0.002,
+            max_tokens=4096,
+        ),
+        ChatModelInfo(
+            name="gpt-4",
+            prompt_token_cost=0.03,
+            completion_token_cost=0.06,
+            max_tokens=8192,
+        ),
+        ChatModelInfo(
+            name="gpt-4-0314",
+            prompt_token_cost=0.03,
+            completion_token_cost=0.06,
+            max_tokens=8192,
+        ),
+        ChatModelInfo(
+            name="gpt-4-32k",
+            prompt_token_cost=0.06,
+            completion_token_cost=0.12,
+            max_tokens=32768,
+        ),
+        ChatModelInfo(
+            name="gpt-4-32k-0314",
+            prompt_token_cost=0.06,
+            completion_token_cost=0.12,
+            max_tokens=32768,
+        ),
+    ]
+}
+
+OPEN_AI_TEXT_MODELS = {
+    info.name: info
+    for info in [
+        TextModelInfo(
+            name="text-davinci-003",
+            prompt_token_cost=0.02,
+            completion_token_cost=0.02,
+            max_tokens=4097,
+        ),
+    ]
 }
 
 OPEN_AI_EMBEDDING_MODELS = {
-    "text-embedding-ada-002": EmbeddingModelInfo(
-        name="text-embedding-ada-002",
-        prompt_token_cost=0.0004,
-        completion_token_cost=0.0,
-        max_tokens=8191,
-        embedding_dimensions=1536,
-    ),
+    info.name: info
+    for info in [
+        EmbeddingModelInfo(
+            name="text-embedding-ada-002",
+            prompt_token_cost=0.0004,
+            completion_token_cost=0.0,
+            max_tokens=8191,
+            embedding_dimensions=1536,
+        ),
+    ]
 }
 
-OPEN_AI_MODELS = {
+OPEN_AI_MODELS: dict[str, ChatModelInfo | EmbeddingModelInfo | TextModelInfo] = {
     **OPEN_AI_CHAT_MODELS,
+    **OPEN_AI_TEXT_MODELS,
     **OPEN_AI_EMBEDDING_MODELS,
 }
diff --git a/autogpt/llm/llm_utils.py b/autogpt/llm/utils/__init__.py
similarity index 50%
rename from autogpt/llm/llm_utils.py
rename to autogpt/llm/utils/__init__.py
index fcd1b2d8..b6bcc1d3 100644
--- a/autogpt/llm/llm_utils.py
+++ b/autogpt/llm/utils/__init__.py
@@ -2,20 +2,58 @@ from __future__ import annotations
 
 import functools
 import time
-from itertools import islice
 from typing import List, Literal, Optional
+from unittest.mock import patch
 
-import numpy as np
 import openai
-import tiktoken
+import openai.api_resources.abstract.engine_api_resource as engine_api_resource
+import openai.util
 from colorama import Fore, Style
-from openai.error import APIError, RateLimitError, Timeout
+from openai.error import APIError, RateLimitError
+from openai.openai_object import OpenAIObject
 
 from autogpt.config import Config
-from autogpt.llm.api_manager import ApiManager
-from autogpt.llm.base import Message
 from autogpt.logs import logger
 
+from ..api_manager import ApiManager
+from ..base import ChatSequence, Message
+from .token_counter import *
+
+
+def metered(func):
+    """Adds ApiManager metering to functions which make OpenAI API calls"""
+    api_manager = ApiManager()
+
+    openai_obj_processor = openai.util.convert_to_openai_object
+
+    def update_usage_with_response(response: OpenAIObject):
+        try:
+            usage = response.usage
+            logger.debug(f"Reported usage from call to model {response.model}: {usage}")
+            api_manager.update_cost(
+                response.usage.prompt_tokens,
+                response.usage.completion_tokens if "completion_tokens" in usage else 0,
+                response.model,
+            )
+        except Exception as err:
+            logger.warn(f"Failed to update API costs: {err.__class__.__name__}: {err}")
+
+    def metering_wrapper(*args, **kwargs):
+        openai_obj = openai_obj_processor(*args, **kwargs)
+        if isinstance(openai_obj, OpenAIObject) and "usage" in openai_obj:
+            update_usage_with_response(openai_obj)
+        return openai_obj
+
+    def metered_func(*args, **kwargs):
+        with patch.object(
+            engine_api_resource.util,
+            "convert_to_openai_object",
+            side_effect=metering_wrapper,
+        ):
+            return func(*args, **kwargs)
+
+    return metered_func
+
 
 def retry_openai_api(
     num_retries: int = 10,
@@ -93,23 +131,57 @@ def call_ai_function(
     # For each arg, if any are None, convert to "None":
     args = [str(arg) if arg is not None else "None" for arg in args]
     # parse args to comma separated string
-    args: str = ", ".join(args)
-    messages: List[Message] = [
-        {
-            "role": "system",
-            "content": f"You are now the following python function: ```# {description}"
-            f"\n{function}```\n\nOnly respond with your `return` value.",
-        },
-        {"role": "user", "content": args},
-    ]
+    arg_str: str = ", ".join(args)
 
-    return create_chat_completion(model=model, messages=messages, temperature=0)
+    prompt = ChatSequence.for_model(
+        model,
+        [
+            Message(
+                "system",
+                f"You are now the following python function: ```# {description}"
+                f"\n{function}```\n\nOnly respond with your `return` value.",
+            ),
+            Message("user", arg_str),
+        ],
+    )
+    return create_chat_completion(prompt=prompt, temperature=0)
+
+
+@metered
+@retry_openai_api()
+def create_text_completion(
+    prompt: str,
+    model: Optional[str],
+    temperature: Optional[float],
+    max_output_tokens: Optional[int],
+) -> str:
+    cfg = Config()
+    if model is None:
+        model = cfg.fast_llm_model
+    if temperature is None:
+        temperature = cfg.temperature
+
+    if cfg.use_azure:
+        kwargs = {"deployment_id": cfg.get_azure_deployment_id_for_model(model)}
+    else:
+        kwargs = {"model": model}
+
+    response = openai.Completion.create(
+        **kwargs,
+        prompt=prompt,
+        temperature=temperature,
+        max_tokens=max_output_tokens,
+        api_key=cfg.openai_api_key,
+    )
+    return response.choices[0].text
 
 
 # Overly simple abstraction until we create something better
 # simple retry mechanism when getting a rate error or a bad gateway
+@metered
+@retry_openai_api()
 def create_chat_completion(
-    messages: List[Message],  # type: ignore
+    prompt: ChatSequence,
     model: Optional[str] = None,
     temperature: float = None,
     max_tokens: Optional[int] = None,
@@ -126,23 +198,23 @@ def create_chat_completion(
         str: The response from the chat completion
     """
     cfg = Config()
+    if model is None:
+        model = prompt.model.name
     if temperature is None:
         temperature = cfg.temperature
 
-    num_retries = 10
-    warned_user = False
     logger.debug(
         f"{Fore.GREEN}Creating chat completion with model {model}, temperature {temperature}, max_tokens {max_tokens}{Fore.RESET}"
     )
     for plugin in cfg.plugins:
         if plugin.can_handle_chat_completion(
-            messages=messages,
+            messages=prompt.raw(),
             model=model,
             temperature=temperature,
             max_tokens=max_tokens,
         ):
             message = plugin.handle_chat_completion(
-                messages=messages,
+                messages=prompt.raw(),
                 model=model,
                 temperature=temperature,
                 max_tokens=max_tokens,
@@ -151,57 +223,19 @@ def create_chat_completion(
                 return message
     api_manager = ApiManager()
     response = None
-    for attempt in range(num_retries):
-        backoff = 2 ** (attempt + 2)
-        try:
-            if cfg.use_azure:
-                response = api_manager.create_chat_completion(
-                    deployment_id=cfg.get_azure_deployment_id_for_model(model),
-                    model=model,
-                    messages=messages,
-                    temperature=temperature,
-                    max_tokens=max_tokens,
-                )
-            else:
-                response = api_manager.create_chat_completion(
-                    model=model,
-                    messages=messages,
-                    temperature=temperature,
-                    max_tokens=max_tokens,
-                )
-            break
-        except RateLimitError:
-            logger.debug(
-                f"{Fore.RED}Error: ", f"Reached rate limit, passing...{Fore.RESET}"
-            )
-            if not warned_user:
-                logger.double_check(
-                    f"Please double check that you have setup a {Fore.CYAN + Style.BRIGHT}PAID{Style.RESET_ALL} OpenAI API Account. "
-                    + f"You can read more here: {Fore.CYAN}https://docs.agpt.co/setup/#getting-an-api-key{Fore.RESET}"
-                )
-                warned_user = True
-        except (APIError, Timeout) as e:
-            if e.http_status != 502:
-                raise
-            if attempt == num_retries - 1:
-                raise
-        logger.debug(
-            f"{Fore.RED}Error: ",
-            f"API Bad gateway. Waiting {backoff} seconds...{Fore.RESET}",
-        )
-        time.sleep(backoff)
-    if response is None:
-        logger.typewriter_log(
-            "FAILED TO GET RESPONSE FROM OPENAI",
-            Fore.RED,
-            "Auto-GPT has failed to get a response from OpenAI's services. "
-            + f"Try running Auto-GPT again, and if the problem the persists try running it with `{Fore.CYAN}--debug{Fore.RESET}`.",
-        )
-        logger.double_check()
-        if cfg.debug_mode:
-            raise RuntimeError(f"Failed to get response after {num_retries} retries")
-        else:
-            quit(1)
+
+    if cfg.use_azure:
+        kwargs = {"deployment_id": cfg.get_azure_deployment_id_for_model(model)}
+    else:
+        kwargs = {"model": model}
+
+    response = api_manager.create_chat_completion(
+        **kwargs,
+        messages=prompt.raw(),
+        temperature=temperature,
+        max_tokens=max_tokens,
+    )
+
     resp = response.choices[0].message["content"]
     for plugin in cfg.plugins:
         if not plugin.can_handle_on_response():
@@ -210,91 +244,6 @@ def create_chat_completion(
     return resp
 
 
-def batched(iterable, n):
-    """Batch data into tuples of length n. The last batch may be shorter."""
-    # batched('ABCDEFG', 3) --> ABC DEF G
-    if n < 1:
-        raise ValueError("n must be at least one")
-    it = iter(iterable)
-    while batch := tuple(islice(it, n)):
-        yield batch
-
-
-def chunked_tokens(text, tokenizer_name, chunk_length):
-    tokenizer = tiktoken.get_encoding(tokenizer_name)
-    tokens = tokenizer.encode(text)
-    chunks_iterator = batched(tokens, chunk_length)
-    yield from chunks_iterator
-
-
-def get_ada_embedding(text: str) -> List[float]:
-    """Get an embedding from the ada model.
-
-    Args:
-        text (str): The text to embed.
-
-    Returns:
-        List[float]: The embedding.
-    """
-    cfg = Config()
-    model = cfg.embedding_model
-    text = text.replace("\n", " ")
-
-    if cfg.use_azure:
-        kwargs = {"engine": cfg.get_azure_deployment_id_for_model(model)}
-    else:
-        kwargs = {"model": model}
-
-    embedding = create_embedding(text, **kwargs)
-    return embedding
-
-
-@retry_openai_api()
-def create_embedding(
-    text: str,
-    *_,
-    **kwargs,
-) -> openai.Embedding:
-    """Create an embedding using the OpenAI API
-
-    Args:
-        text (str): The text to embed.
-        kwargs: Other arguments to pass to the OpenAI API embedding creation call.
-
-    Returns:
-        openai.Embedding: The embedding object.
-    """
-    cfg = Config()
-    chunk_embeddings = []
-    chunk_lengths = []
-    for chunk in chunked_tokens(
-        text,
-        tokenizer_name=cfg.embedding_tokenizer,
-        chunk_length=cfg.embedding_token_limit,
-    ):
-        embedding = openai.Embedding.create(
-            input=[chunk],
-            api_key=cfg.openai_api_key,
-            **kwargs,
-        )
-        api_manager = ApiManager()
-        api_manager.update_cost(
-            prompt_tokens=embedding.usage.prompt_tokens,
-            completion_tokens=0,
-            model=cfg.embedding_model,
-        )
-        chunk_embeddings.append(embedding["data"][0]["embedding"])
-        chunk_lengths.append(len(chunk))
-
-    # do weighted avg
-    chunk_embeddings = np.average(chunk_embeddings, axis=0, weights=chunk_lengths)
-    chunk_embeddings = chunk_embeddings / np.linalg.norm(
-        chunk_embeddings
-    )  # normalize the length to one
-    chunk_embeddings = chunk_embeddings.tolist()
-    return chunk_embeddings
-
-
 def check_model(
     model_name: str, model_type: Literal["smart_llm_model", "fast_llm_model"]
 ) -> str:
diff --git a/autogpt/llm/token_counter.py b/autogpt/llm/utils/token_counter.py
similarity index 98%
rename from autogpt/llm/token_counter.py
rename to autogpt/llm/utils/token_counter.py
index 5e13920e..bd1dcf1b 100644
--- a/autogpt/llm/token_counter.py
+++ b/autogpt/llm/utils/token_counter.py
@@ -53,7 +53,7 @@ def count_message_tokens(
     num_tokens = 0
     for message in messages:
         num_tokens += tokens_per_message
-        for key, value in message.items():
+        for key, value in message.raw().items():
             num_tokens += len(encoding.encode(value))
             if key == "name":
                 num_tokens += tokens_per_name
diff --git a/autogpt/main.py b/autogpt/main.py
index 25d7161e..03f685db 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -5,12 +5,12 @@ from pathlib import Path
 
 from colorama import Fore, Style
 
-from autogpt.agent.agent import Agent
+from autogpt.agent import Agent
 from autogpt.commands.command import CommandRegistry
 from autogpt.config import Config, check_openai_api_key
 from autogpt.configurator import create_config
 from autogpt.logs import logger
-from autogpt.memory import get_memory
+from autogpt.memory.vector import get_memory
 from autogpt.plugins import scan_plugins
 from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT, construct_main_ai_config
 from autogpt.utils import (
@@ -160,7 +160,6 @@ def run_auto_gpt(
         ai_name = ai_config.ai_name
     # print(prompt)
     # Initialize variables
-    full_message_history = []
     next_action_count = 0
 
     # add chat plugins capable of report to logger
@@ -184,7 +183,6 @@ def run_auto_gpt(
     agent = Agent(
         ai_name=ai_name,
         memory=memory,
-        full_message_history=full_message_history,
         next_action_count=next_action_count,
         command_registry=command_registry,
         config=ai_config,
diff --git a/autogpt/memory/__init__.py b/autogpt/memory/__init__.py
deleted file mode 100644
index a955a3e7..00000000
--- a/autogpt/memory/__init__.py
+++ /dev/null
@@ -1,96 +0,0 @@
-from autogpt.logs import logger
-from autogpt.memory.local import LocalCache
-from autogpt.memory.no_memory import NoMemory
-
-# List of supported memory backends
-# Add a backend to this list if the import attempt is successful
-supported_memory = ["local", "no_memory"]
-
-try:
-    from autogpt.memory.redismem import RedisMemory
-
-    supported_memory.append("redis")
-except ImportError:
-    RedisMemory = None
-
-try:
-    from autogpt.memory.pinecone import PineconeMemory
-
-    supported_memory.append("pinecone")
-except ImportError:
-    PineconeMemory = None
-
-try:
-    from autogpt.memory.weaviate import WeaviateMemory
-
-    supported_memory.append("weaviate")
-except ImportError:
-    WeaviateMemory = None
-
-try:
-    from autogpt.memory.milvus import MilvusMemory
-
-    supported_memory.append("milvus")
-except ImportError:
-    MilvusMemory = None
-
-
-def get_memory(cfg, init=False):
-    memory = None
-    if cfg.memory_backend == "pinecone":
-        if not PineconeMemory:
-            logger.warn(
-                "Error: Pinecone is not installed. Please install pinecone"
-                " to use Pinecone as a memory backend."
-            )
-        else:
-            memory = PineconeMemory(cfg)
-            if init:
-                memory.clear()
-    elif cfg.memory_backend == "redis":
-        if not RedisMemory:
-            logger.warn(
-                "Error: Redis is not installed. Please install redis-py to"
-                " use Redis as a memory backend."
-            )
-        else:
-            memory = RedisMemory(cfg)
-    elif cfg.memory_backend == "weaviate":
-        if not WeaviateMemory:
-            logger.warn(
-                "Error: Weaviate is not installed. Please install weaviate-client to"
-                " use Weaviate as a memory backend."
-            )
-        else:
-            memory = WeaviateMemory(cfg)
-    elif cfg.memory_backend == "milvus":
-        if not MilvusMemory:
-            logger.warn(
-                "Error: pymilvus sdk is not installed."
-                "Please install pymilvus to use Milvus or Zilliz Cloud as memory backend."
-            )
-        else:
-            memory = MilvusMemory(cfg)
-    elif cfg.memory_backend == "no_memory":
-        memory = NoMemory(cfg)
-
-    if memory is None:
-        memory = LocalCache(cfg)
-        if init:
-            memory.clear()
-    return memory
-
-
-def get_supported_memory_backends():
-    return supported_memory
-
-
-__all__ = [
-    "get_memory",
-    "LocalCache",
-    "RedisMemory",
-    "PineconeMemory",
-    "NoMemory",
-    "MilvusMemory",
-    "WeaviateMemory",
-]
diff --git a/autogpt/memory/base.py b/autogpt/memory/base.py
deleted file mode 100644
index d99cadde..00000000
--- a/autogpt/memory/base.py
+++ /dev/null
@@ -1,31 +0,0 @@
-"""Base class for memory providers."""
-import abc
-
-from autogpt.singleton import AbstractSingleton
-
-
-class MemoryProviderSingleton(AbstractSingleton):
-    @abc.abstractmethod
-    def add(self, data):
-        """Adds to memory"""
-        pass
-
-    @abc.abstractmethod
-    def get(self, data):
-        """Gets from memory"""
-        pass
-
-    @abc.abstractmethod
-    def clear(self):
-        """Clears memory"""
-        pass
-
-    @abc.abstractmethod
-    def get_relevant(self, data, num_relevant=5):
-        """Gets relevant memory for"""
-        pass
-
-    @abc.abstractmethod
-    def get_stats(self):
-        """Get stats from memory"""
-        pass
diff --git a/autogpt/memory/local.py b/autogpt/memory/local.py
deleted file mode 100644
index 18b7255c..00000000
--- a/autogpt/memory/local.py
+++ /dev/null
@@ -1,126 +0,0 @@
-from __future__ import annotations
-
-import dataclasses
-from pathlib import Path
-from typing import Any, List
-
-import numpy as np
-import orjson
-
-from autogpt.llm import get_ada_embedding
-from autogpt.memory.base import MemoryProviderSingleton
-
-EMBED_DIM = 1536
-SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS
-
-
-def create_default_embeddings():
-    return np.zeros((0, EMBED_DIM)).astype(np.float32)
-
-
-@dataclasses.dataclass
-class CacheContent:
-    texts: List[str] = dataclasses.field(default_factory=list)
-    embeddings: np.ndarray = dataclasses.field(
-        default_factory=create_default_embeddings
-    )
-
-
-class LocalCache(MemoryProviderSingleton):
-    """A class that stores the memory in a local file"""
-
-    def __init__(self, cfg) -> None:
-        """Initialize a class instance
-
-        Args:
-            cfg: Config object
-
-        Returns:
-            None
-        """
-        workspace_path = Path(cfg.workspace_path)
-        self.filename = workspace_path / f"{cfg.memory_index}.json"
-
-        self.filename.touch(exist_ok=True)
-
-        file_content = b"{}"
-        with self.filename.open("w+b") as f:
-            f.write(file_content)
-
-        self.data = CacheContent()
-
-    def add(self, text: str):
-        """
-        Add text to our list of texts, add embedding as row to our
-            embeddings-matrix
-
-        Args:
-            text: str
-
-        Returns: None
-        """
-        if "Command Error:" in text:
-            return ""
-        self.data.texts.append(text)
-
-        embedding = get_ada_embedding(text)
-
-        vector = np.array(embedding).astype(np.float32)
-        vector = vector[np.newaxis, :]
-        self.data.embeddings = np.concatenate(
-            [
-                self.data.embeddings,
-                vector,
-            ],
-            axis=0,
-        )
-
-        with open(self.filename, "wb") as f:
-            out = orjson.dumps(self.data, option=SAVE_OPTIONS)
-            f.write(out)
-        return text
-
-    def clear(self) -> str:
-        """
-        Clears the data in memory.
-
-        Returns: A message indicating that the memory has been cleared.
-        """
-        self.data = CacheContent()
-        return "Obliviated"
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: The most relevant data.
-        """
-        return self.get_relevant(data, 1)
-
-    def get_relevant(self, text: str, k: int) -> list[Any]:
-        """ "
-        matrix-vector mult to find score-for-each-row-of-matrix
-         get indices for top-k winning scores
-         return texts for those indices
-        Args:
-            text: str
-            k: int
-
-        Returns: List[str]
-        """
-        embedding = get_ada_embedding(text)
-
-        scores = np.dot(self.data.embeddings, embedding)
-
-        top_k_indices = np.argsort(scores)[-k:][::-1]
-
-        return [self.data.texts[i] for i in top_k_indices]
-
-    def get_stats(self) -> tuple[int, tuple[int, ...]]:
-        """
-        Returns: The stats of the local cache.
-        """
-        return len(self.data.texts), self.data.embeddings.shape
diff --git a/autogpt/memory/message_history.py b/autogpt/memory/message_history.py
new file mode 100644
index 00000000..fcb96a94
--- /dev/null
+++ b/autogpt/memory/message_history.py
@@ -0,0 +1,204 @@
+from __future__ import annotations
+
+import copy
+import json
+from dataclasses import dataclass, field
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from autogpt.agent import Agent
+
+from autogpt.config import Config
+from autogpt.json_utils.utilities import (
+    LLM_DEFAULT_RESPONSE_FORMAT,
+    is_string_valid_json,
+)
+from autogpt.llm.base import ChatSequence, Message, MessageRole, MessageType
+from autogpt.llm.utils import create_chat_completion
+from autogpt.log_cycle.log_cycle import PROMPT_SUMMARY_FILE_NAME, SUMMARY_FILE_NAME
+from autogpt.logs import logger
+
+
+@dataclass
+class MessageHistory:
+    agent: Agent
+
+    messages: list[Message] = field(default_factory=list)
+    summary: str = "I was created"
+
+    last_trimmed_index: int = 0
+
+    def __getitem__(self, i: int):
+        return self.messages[i]
+
+    def __iter__(self):
+        return iter(self.messages)
+
+    def __len__(self):
+        return len(self.messages)
+
+    def add(
+        self,
+        role: MessageRole,
+        content: str,
+        type: MessageType | None = None,
+    ):
+        return self.append(Message(role, content, type))
+
+    def append(self, message: Message):
+        return self.messages.append(message)
+
+    def trim_messages(
+        self,
+        current_message_chain: list[Message],
+    ) -> tuple[Message, list[Message]]:
+        """
+        Returns a list of trimmed messages: messages which are in the message history
+        but not in current_message_chain.
+
+        Args:
+            current_message_chain (list[Message]): The messages currently in the context.
+
+        Returns:
+            Message: A message with the new running summary after adding the trimmed messages.
+            list[Message]: A list of messages that are in full_message_history with an index higher than last_trimmed_index and absent from current_message_chain.
+        """
+        # Select messages in full_message_history with an index higher than last_trimmed_index
+        new_messages = [
+            msg for i, msg in enumerate(self) if i > self.last_trimmed_index
+        ]
+
+        # Remove messages that are already present in current_message_chain
+        new_messages_not_in_chain = [
+            msg for msg in new_messages if msg not in current_message_chain
+        ]
+
+        if not new_messages_not_in_chain:
+            return self.summary_message(), []
+
+        new_summary_message = self.update_running_summary(
+            new_events=new_messages_not_in_chain
+        )
+
+        # Find the index of the last message processed
+        last_message = new_messages_not_in_chain[-1]
+        self.last_trimmed_index = self.messages.index(last_message)
+
+        return new_summary_message, new_messages_not_in_chain
+
+    def per_cycle(self, messages: list[Message] | None = None):
+        """
+        Yields:
+            Message: a message containing user input
+            Message: a message from the AI containing a proposed action
+            Message: the message containing the result of the AI's proposed action
+        """
+        messages = messages or self.messages
+        for i in range(0, len(messages) - 1):
+            ai_message = messages[i]
+            if ai_message.type != "ai_response":
+                continue
+            user_message = (
+                messages[i - 1] if i > 0 and messages[i - 1].role == "user" else None
+            )
+            result_message = messages[i + 1]
+            try:
+                assert is_string_valid_json(
+                    ai_message.content, LLM_DEFAULT_RESPONSE_FORMAT
+                ), "AI response is not a valid JSON object"
+                assert result_message.type == "action_result"
+
+                yield user_message, ai_message, result_message
+            except AssertionError as err:
+                logger.debug(
+                    f"Invalid item in message history: {err}; Messages: {messages[i-1:i+2]}"
+                )
+
+    def summary_message(self) -> Message:
+        return Message(
+            "system",
+            f"This reminds you of these events from your past: \n{self.summary}",
+        )
+
+    def update_running_summary(self, new_events: list[Message]) -> Message:
+        """
+        This function takes a list of dictionaries representing new events and combines them with the current summary,
+        focusing on key and potentially important information to remember. The updated summary is returned in a message
+        formatted in the 1st person past tense.
+
+        Args:
+            new_events (List[Dict]): A list of dictionaries containing the latest events to be added to the summary.
+
+        Returns:
+            str: A message containing the updated summary of actions, formatted in the 1st person past tense.
+
+        Example:
+            new_events = [{"event": "entered the kitchen."}, {"event": "found a scrawled note with the number 7"}]
+            update_running_summary(new_events)
+            # Returns: "This reminds you of these events from your past: \nI entered the kitchen and found a scrawled note saying 7."
+        """
+        cfg = Config()
+
+        if not new_events:
+            return self.summary_message()
+
+        # Create a copy of the new_events list to prevent modifying the original list
+        new_events = copy.deepcopy(new_events)
+
+        # Replace "assistant" with "you". This produces much better first person past tense results.
+        for event in new_events:
+            if event.role.lower() == "assistant":
+                event.role = "you"
+
+                # Remove "thoughts" dictionary from "content"
+                try:
+                    content_dict = json.loads(event.content)
+                    if "thoughts" in content_dict:
+                        del content_dict["thoughts"]
+                    event.content = json.dumps(content_dict)
+                except json.decoder.JSONDecodeError:
+                    if cfg.debug_mode:
+                        logger.error(f"Error: Invalid JSON: {event.content}\n")
+
+            elif event.role.lower() == "system":
+                event.role = "your computer"
+
+            # Delete all user messages
+            elif event.role == "user":
+                new_events.remove(event)
+
+        prompt = f'''Your task is to create a concise running summary of actions and information results in the provided text, focusing on key and potentially important information to remember.
+
+You will receive the current summary and the your latest actions. Combine them, adding relevant key information from the latest development in 1st person past tense and keeping the summary concise.
+
+Summary So Far:
+"""
+{self.summary}
+"""
+
+Latest Development:
+"""
+{new_events or "Nothing new happened."}
+"""
+'''
+
+        prompt = ChatSequence.for_model(cfg.fast_llm_model, [Message("user", prompt)])
+        self.agent.log_cycle_handler.log_cycle(
+            self.agent.config.ai_name,
+            self.agent.created_at,
+            self.agent.cycle_count,
+            prompt.raw(),
+            PROMPT_SUMMARY_FILE_NAME,
+        )
+
+        self.summary = create_chat_completion(prompt)
+
+        self.agent.log_cycle_handler.log_cycle(
+            self.agent.config.ai_name,
+            self.agent.created_at,
+            self.agent.cycle_count,
+            self.summary,
+            SUMMARY_FILE_NAME,
+        )
+
+        return self.summary_message()
diff --git a/autogpt/memory/milvus.py b/autogpt/memory/milvus.py
deleted file mode 100644
index 40694df5..00000000
--- a/autogpt/memory/milvus.py
+++ /dev/null
@@ -1,162 +0,0 @@
-""" Milvus memory storage provider."""
-import re
-
-from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, connections
-
-from autogpt.config import Config
-from autogpt.llm import get_ada_embedding
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class MilvusMemory(MemoryProviderSingleton):
-    """Milvus memory storage provider."""
-
-    def __init__(self, cfg: Config) -> None:
-        """Construct a milvus memory storage connection.
-
-        Args:
-            cfg (Config): Auto-GPT global config.
-        """
-        self.configure(cfg)
-
-        connect_kwargs = {}
-        if self.username:
-            connect_kwargs["user"] = self.username
-            connect_kwargs["password"] = self.password
-
-        connections.connect(
-            **connect_kwargs,
-            uri=self.uri or "",
-            address=self.address or "",
-            secure=self.secure,
-        )
-
-        self.init_collection()
-
-    def configure(self, cfg: Config) -> None:
-        # init with configuration.
-        self.uri = None
-        self.address = cfg.milvus_addr
-        self.secure = cfg.milvus_secure
-        self.username = cfg.milvus_username
-        self.password = cfg.milvus_password
-        self.collection_name = cfg.milvus_collection
-        # use HNSW by default.
-        self.index_params = {
-            "metric_type": "IP",
-            "index_type": "HNSW",
-            "params": {"M": 8, "efConstruction": 64},
-        }
-
-        if (self.username is None) != (self.password is None):
-            raise ValueError(
-                "Both username and password must be set to use authentication for Milvus"
-            )
-
-        # configured address may be a full URL.
-        if re.match(r"^(https?|tcp)://", self.address) is not None:
-            self.uri = self.address
-            self.address = None
-
-            if self.uri.startswith("https"):
-                self.secure = True
-
-            # Zilliz Cloud requires AutoIndex.
-            if re.match(r"^https://(.*)\.zillizcloud\.(com|cn)", self.uri) is not None:
-                self.index_params = {
-                    "metric_type": "IP",
-                    "index_type": "AUTOINDEX",
-                    "params": {},
-                }
-
-    def init_collection(self) -> None:
-        """Initialize collection in vector database."""
-        fields = [
-            FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=True),
-            FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=1536),
-            FieldSchema(name="raw_text", dtype=DataType.VARCHAR, max_length=65535),
-        ]
-
-        # create collection if not exist and load it.
-        self.schema = CollectionSchema(fields, "auto-gpt memory storage")
-        self.collection = Collection(self.collection_name, self.schema)
-        # create index if not exist.
-        if not self.collection.has_index():
-            self.collection.release()
-            self.collection.create_index(
-                "embeddings",
-                self.index_params,
-                index_name="embeddings",
-            )
-        self.collection.load()
-
-    def add(self, data) -> str:
-        """Add an embedding of data into memory.
-
-        Args:
-            data (str): The raw text to construct embedding index.
-
-        Returns:
-            str: log.
-        """
-        embedding = get_ada_embedding(data)
-        result = self.collection.insert([[embedding], [data]])
-        _text = (
-            "Inserting data into memory at primary key: "
-            f"{result.primary_keys[0]}:\n data: {data}"
-        )
-        return _text
-
-    def get(self, data):
-        """Return the most relevant data in memory.
-        Args:
-            data: The data to compare to.
-        """
-        return self.get_relevant(data, 1)
-
-    def clear(self) -> str:
-        """Drop the index in memory.
-
-        Returns:
-            str: log.
-        """
-        self.collection.drop()
-        self.collection = Collection(self.collection_name, self.schema)
-        self.collection.create_index(
-            "embeddings",
-            self.index_params,
-            index_name="embeddings",
-        )
-        self.collection.load()
-        return "Obliviated"
-
-    def get_relevant(self, data: str, num_relevant: int = 5):
-        """Return the top-k relevant data in memory.
-        Args:
-            data: The data to compare to.
-            num_relevant (int, optional): The max number of relevant data.
-                Defaults to 5.
-
-        Returns:
-            list: The top-k relevant data.
-        """
-        # search the embedding and return the most relevant text.
-        embedding = get_ada_embedding(data)
-        search_params = {
-            "metrics_type": "IP",
-            "params": {"nprobe": 8},
-        }
-        result = self.collection.search(
-            [embedding],
-            "embeddings",
-            search_params,
-            num_relevant,
-            output_fields=["raw_text"],
-        )
-        return [item.entity.value_of_field("raw_text") for item in result[0]]
-
-    def get_stats(self) -> str:
-        """
-        Returns: The stats of the milvus cache.
-        """
-        return f"Entities num: {self.collection.num_entities}"
diff --git a/autogpt/memory/no_memory.py b/autogpt/memory/no_memory.py
deleted file mode 100644
index 0371e96a..00000000
--- a/autogpt/memory/no_memory.py
+++ /dev/null
@@ -1,73 +0,0 @@
-"""A class that does not store any data. This is the default memory provider."""
-from __future__ import annotations
-
-from typing import Any
-
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class NoMemory(MemoryProviderSingleton):
-    """
-    A class that does not store any data. This is the default memory provider.
-    """
-
-    def __init__(self, cfg):
-        """
-        Initializes the NoMemory provider.
-
-        Args:
-            cfg: The config object.
-
-        Returns: None
-        """
-        pass
-
-    def add(self, data: str) -> str:
-        """
-        Adds a data point to the memory. No action is taken in NoMemory.
-
-        Args:
-            data: The data to add.
-
-        Returns: An empty string.
-        """
-        return ""
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-        NoMemory always returns None.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: None
-        """
-        return None
-
-    def clear(self) -> str:
-        """
-        Clears the memory. No action is taken in NoMemory.
-
-        Returns: An empty string.
-        """
-        return ""
-
-    def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None:
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        NoMemory always returns None.
-
-        Args:
-            data: The data to compare to.
-            num_relevant: The number of relevant data to return.
-
-        Returns: None
-        """
-        return None
-
-    def get_stats(self):
-        """
-        Returns: An empty dictionary as there are no stats in NoMemory.
-        """
-        return {}
diff --git a/autogpt/memory/pinecone.py b/autogpt/memory/pinecone.py
deleted file mode 100644
index 1c73ebd7..00000000
--- a/autogpt/memory/pinecone.py
+++ /dev/null
@@ -1,78 +0,0 @@
-import pinecone
-from colorama import Fore, Style
-
-from autogpt.llm import get_ada_embedding
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class PineconeMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        pinecone_api_key = cfg.pinecone_api_key
-        pinecone_region = cfg.pinecone_region
-        pinecone.init(api_key=pinecone_api_key, environment=pinecone_region)
-        dimension = 1536
-        metric = "cosine"
-        pod_type = "p1"
-        table_name = "auto-gpt"
-        # this assumes we don't start with memory.
-        # for now this works.
-        # we'll need a more complicated and robust system if we want to start with
-        #  memory.
-        self.vec_num = 0
-
-        try:
-            pinecone.whoami()
-        except Exception as e:
-            logger.typewriter_log(
-                "FAILED TO CONNECT TO PINECONE",
-                Fore.RED,
-                Style.BRIGHT + str(e) + Style.RESET_ALL,
-            )
-            logger.double_check(
-                "Please ensure you have setup and configured Pinecone properly for use."
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
-                "https://docs.agpt.co/configuration/memory/#pinecone-api-key-setup"
-                f"{Style.RESET_ALL} to ensure you've set up everything correctly."
-            )
-            exit(1)
-
-        if table_name not in pinecone.list_indexes():
-            logger.typewriter_log(
-                "Connecting Pinecone. This may take some time...", Fore.MAGENTA, ""
-            )
-            pinecone.create_index(
-                table_name, dimension=dimension, metric=metric, pod_type=pod_type
-            )
-        self.index = pinecone.Index(table_name)
-
-    def add(self, data):
-        vector = get_ada_embedding(data)
-        # no metadata here. We may wish to change that long term.
-        self.index.upsert([(str(self.vec_num), vector, {"raw_text": data})])
-        _text = f"Inserting data into memory at index: {self.vec_num}:\n data: {data}"
-        self.vec_num += 1
-        return _text
-
-    def get(self, data):
-        return self.get_relevant(data, 1)
-
-    def clear(self):
-        self.index.delete(deleteAll=True)
-        return "Obliviated"
-
-    def get_relevant(self, data, num_relevant=5):
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        :param data: The data to compare to.
-        :param num_relevant: The number of relevant data to return. Defaults to 5
-        """
-        query_embedding = get_ada_embedding(data)
-        results = self.index.query(
-            query_embedding, top_k=num_relevant, include_metadata=True
-        )
-        sorted_results = sorted(results.matches, key=lambda x: x.score)
-        return [str(item["metadata"]["raw_text"]) for item in sorted_results]
-
-    def get_stats(self):
-        return self.index.describe_index_stats()
diff --git a/autogpt/memory/redismem.py b/autogpt/memory/redismem.py
deleted file mode 100644
index 9b126f01..00000000
--- a/autogpt/memory/redismem.py
+++ /dev/null
@@ -1,156 +0,0 @@
-"""Redis memory provider."""
-from __future__ import annotations
-
-from typing import Any
-
-import numpy as np
-import redis
-from colorama import Fore, Style
-from redis.commands.search.field import TextField, VectorField
-from redis.commands.search.indexDefinition import IndexDefinition, IndexType
-from redis.commands.search.query import Query
-
-from autogpt.llm import get_ada_embedding
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-SCHEMA = [
-    TextField("data"),
-    VectorField(
-        "embedding",
-        "HNSW",
-        {"TYPE": "FLOAT32", "DIM": 1536, "DISTANCE_METRIC": "COSINE"},
-    ),
-]
-
-
-class RedisMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        """
-        Initializes the Redis memory provider.
-
-        Args:
-            cfg: The config object.
-
-        Returns: None
-        """
-        redis_host = cfg.redis_host
-        redis_port = cfg.redis_port
-        redis_password = cfg.redis_password
-        self.dimension = 1536
-        self.redis = redis.Redis(
-            host=redis_host,
-            port=redis_port,
-            password=redis_password,
-            db=0,  # Cannot be changed
-        )
-        self.cfg = cfg
-
-        # Check redis connection
-        try:
-            self.redis.ping()
-        except redis.ConnectionError as e:
-            logger.typewriter_log(
-                "FAILED TO CONNECT TO REDIS",
-                Fore.RED,
-                Style.BRIGHT + str(e) + Style.RESET_ALL,
-            )
-            logger.double_check(
-                "Please ensure you have setup and configured Redis properly for use. "
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
-                f"https://docs.agpt.co/configuration/memory/#redis-setup{Style.RESET_ALL}"
-                " to ensure you've set up everything correctly."
-            )
-            exit(1)
-
-        if cfg.wipe_redis_on_start:
-            self.redis.flushall()
-        try:
-            self.redis.ft(f"{cfg.memory_index}").create_index(
-                fields=SCHEMA,
-                definition=IndexDefinition(
-                    prefix=[f"{cfg.memory_index}:"], index_type=IndexType.HASH
-                ),
-            )
-        except Exception as e:
-            logger.warn("Error creating Redis search index: ", e)
-        existing_vec_num = self.redis.get(f"{cfg.memory_index}-vec_num")
-        self.vec_num = int(existing_vec_num.decode("utf-8")) if existing_vec_num else 0
-
-    def add(self, data: str) -> str:
-        """
-        Adds a data point to the memory.
-
-        Args:
-            data: The data to add.
-
-        Returns: Message indicating that the data has been added.
-        """
-        if "Command Error:" in data:
-            return ""
-        vector = get_ada_embedding(data)
-        vector = np.array(vector).astype(np.float32).tobytes()
-        data_dict = {b"data": data, "embedding": vector}
-        pipe = self.redis.pipeline()
-        pipe.hset(f"{self.cfg.memory_index}:{self.vec_num}", mapping=data_dict)
-        _text = (
-            f"Inserting data into memory at index: {self.vec_num}:\n" f"data: {data}"
-        )
-        self.vec_num += 1
-        pipe.set(f"{self.cfg.memory_index}-vec_num", self.vec_num)
-        pipe.execute()
-        return _text
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: The most relevant data.
-        """
-        return self.get_relevant(data, 1)
-
-    def clear(self) -> str:
-        """
-        Clears the redis server.
-
-        Returns: A message indicating that the memory has been cleared.
-        """
-        self.redis.flushall()
-        return "Obliviated"
-
-    def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None:
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        Args:
-            data: The data to compare to.
-            num_relevant: The number of relevant data to return.
-
-        Returns: A list of the most relevant data.
-        """
-        query_embedding = get_ada_embedding(data)
-        base_query = f"*=>[KNN {num_relevant} @embedding $vector AS vector_score]"
-        query = (
-            Query(base_query)
-            .return_fields("data", "vector_score")
-            .sort_by("vector_score")
-            .dialect(2)
-        )
-        query_vector = np.array(query_embedding).astype(np.float32).tobytes()
-
-        try:
-            results = self.redis.ft(f"{self.cfg.memory_index}").search(
-                query, query_params={"vector": query_vector}
-            )
-        except Exception as e:
-            logger.warn("Error calling Redis search: ", e)
-            return None
-        return [result.data for result in results.docs]
-
-    def get_stats(self):
-        """
-        Returns: The stats of the memory index.
-        """
-        return self.redis.ft(f"{self.cfg.memory_index}").info()
diff --git a/autogpt/memory/vector/__init__.py b/autogpt/memory/vector/__init__.py
new file mode 100644
index 00000000..aaaf83fb
--- /dev/null
+++ b/autogpt/memory/vector/__init__.py
@@ -0,0 +1,138 @@
+from autogpt.config import Config
+from autogpt.logs import logger
+
+from .memory_item import MemoryItem, MemoryItemRelevance
+from .providers.base import VectorMemoryProvider as VectorMemory
+from .providers.json_file import JSONFileMemory
+from .providers.no_memory import NoMemory
+
+# List of supported memory backends
+# Add a backend to this list if the import attempt is successful
+supported_memory = ["json_file", "no_memory"]
+
+# try:
+#     from .providers.redis import RedisMemory
+
+#     supported_memory.append("redis")
+# except ImportError:
+#     RedisMemory = None
+
+# try:
+#     from .providers.pinecone import PineconeMemory
+
+#     supported_memory.append("pinecone")
+# except ImportError:
+#     PineconeMemory = None
+
+# try:
+#     from .providers.weaviate import WeaviateMemory
+
+#     supported_memory.append("weaviate")
+# except ImportError:
+#     WeaviateMemory = None
+
+# try:
+#     from .providers.milvus import MilvusMemory
+
+#     supported_memory.append("milvus")
+# except ImportError:
+#     MilvusMemory = None
+
+
+def get_memory(cfg: Config, init=False) -> VectorMemory:
+    memory = None
+
+    match cfg.memory_backend:
+        case "json_file":
+            memory = JSONFileMemory(cfg)
+
+        case "pinecone":
+            raise NotImplementedError(
+                "The Pinecone memory backend has been rendered incompatible by work on "
+                "the memory system, and was removed. Whether support will be added back "
+                "in the future is subject to discussion, feel free to pitch in: "
+                "https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280"
+            )
+            # if not PineconeMemory:
+            #     logger.warn(
+            #         "Error: Pinecone is not installed. Please install pinecone"
+            #         " to use Pinecone as a memory backend."
+            #     )
+            # else:
+            #     memory = PineconeMemory(cfg)
+            #     if init:
+            #         memory.clear()
+
+        case "redis":
+            raise NotImplementedError(
+                "The Redis memory backend has been rendered incompatible by work on "
+                "the memory system, and has been removed temporarily."
+            )
+            # if not RedisMemory:
+            #     logger.warn(
+            #         "Error: Redis is not installed. Please install redis-py to"
+            #         " use Redis as a memory backend."
+            #     )
+            # else:
+            #     memory = RedisMemory(cfg)
+
+        case "weaviate":
+            raise NotImplementedError(
+                "The Weaviate memory backend has been rendered incompatible by work on "
+                "the memory system, and was removed. Whether support will be added back "
+                "in the future is subject to discussion, feel free to pitch in: "
+                "https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280"
+            )
+            # if not WeaviateMemory:
+            #     logger.warn(
+            #         "Error: Weaviate is not installed. Please install weaviate-client to"
+            #         " use Weaviate as a memory backend."
+            #     )
+            # else:
+            #     memory = WeaviateMemory(cfg)
+
+        case "milvus":
+            raise NotImplementedError(
+                "The Milvus memory backend has been rendered incompatible by work on "
+                "the memory system, and was removed. Whether support will be added back "
+                "in the future is subject to discussion, feel free to pitch in: "
+                "https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280"
+            )
+            # if not MilvusMemory:
+            #     logger.warn(
+            #         "Error: pymilvus sdk is not installed."
+            #         "Please install pymilvus to use Milvus or Zilliz Cloud as memory backend."
+            #     )
+            # else:
+            #     memory = MilvusMemory(cfg)
+
+        case "no_memory":
+            memory = NoMemory()
+
+        case _:
+            raise ValueError(
+                f"Unknown memory backend '{cfg.memory_backend}'. Please check your config."
+            )
+
+    if memory is None:
+        memory = JSONFileMemory(cfg)
+
+    return memory
+
+
+def get_supported_memory_backends():
+    return supported_memory
+
+
+__all__ = [
+    "get_memory",
+    "MemoryItem",
+    "MemoryItemRelevance",
+    "JSONFileMemory",
+    "NoMemory",
+    "VectorMemory",
+    # "RedisMemory",
+    # "PineconeMemory",
+    # "MilvusMemory",
+    # "WeaviateMemory",
+]
diff --git a/autogpt/memory/vector/memory_item.py b/autogpt/memory/vector/memory_item.py
new file mode 100644
index 00000000..c57b87aa
--- /dev/null
+++ b/autogpt/memory/vector/memory_item.py
@@ -0,0 +1,223 @@
+from __future__ import annotations
+
+import dataclasses
+import json
+from typing import Literal
+
+import numpy as np
+
+from autogpt.config import Config
+from autogpt.llm import Message
+from autogpt.llm.utils import count_string_tokens
+from autogpt.logs import logger
+from autogpt.processing.text import chunk_content, split_text, summarize_text
+
+from .utils import Embedding, get_embedding
+
+MemoryDocType = Literal["webpage", "text_file", "code_file", "agent_history"]
+
+
+@dataclasses.dataclass
+class MemoryItem:
+    """Memory object containing raw content as well as embeddings"""
+
+    raw_content: str
+    summary: str
+    chunks: list[str]
+    chunk_summaries: list[str]
+    e_summary: Embedding
+    e_chunks: list[Embedding]
+    metadata: dict
+
+    def relevance_for(self, query: str, e_query: Embedding | None = None):
+        return MemoryItemRelevance.of(self, query, e_query)
+
+    @staticmethod
+    def from_text(
+        text: str,
+        source_type: MemoryDocType,
+        metadata: dict = {},
+        how_to_summarize: str | None = None,
+        question_for_summary: str | None = None,
+    ):
+        cfg = Config()
+        logger.debug(f"Memorizing text:\n{'-'*32}\n{text}\n{'-'*32}\n")
+
+        chunks = [
+            chunk
+            for chunk, _ in (
+                split_text(text, cfg.embedding_model)
+                if source_type != "code_file"
+                else chunk_content(text, cfg.embedding_model)
+            )
+        ]
+        logger.debug("Chunks: " + str(chunks))
+
+        chunk_summaries = [
+            summary
+            for summary, _ in [
+                summarize_text(
+                    text_chunk,
+                    instruction=how_to_summarize,
+                    question=question_for_summary,
+                )
+                for text_chunk in chunks
+            ]
+        ]
+        logger.debug("Chunk summaries: " + str(chunk_summaries))
+
+        e_chunks = get_embedding(chunks)
+
+        summary = (
+            chunk_summaries[0]
+            if len(chunks) == 1
+            else summarize_text(
+                "\n\n".join(chunk_summaries),
+                instruction=how_to_summarize,
+                question=question_for_summary,
+            )[0]
+        )
+        logger.debug("Total summary: " + summary)
+
+        # TODO: investigate search performance of weighted average vs summary
+        # e_average = np.average(e_chunks, axis=0, weights=[len(c) for c in chunks])
+        e_summary = get_embedding(summary)
+
+        metadata["source_type"] = source_type
+
+        return MemoryItem(
+            text,
+            summary,
+            chunks,
+            chunk_summaries,
+            e_summary,
+            e_chunks,
+            metadata=metadata,
+        )
+
+    @staticmethod
+    def from_text_file(content: str, path: str):
+        return MemoryItem.from_text(content, "text_file", {"location": path})
+
+    @staticmethod
+    def from_code_file(content: str, path: str):
+        # TODO: implement tailored code memories
+        return MemoryItem.from_text(content, "code_file", {"location": path})
+
+    @staticmethod
+    def from_ai_action(ai_message: Message, result_message: Message):
+        # The result_message contains either user feedback
+        # or the result of the command specified in ai_message
+
+        if ai_message["role"] != "assistant":
+            raise ValueError(f"Invalid role on 'ai_message': {ai_message['role']}")
+
+        result = (
+            result_message["content"]
+            if result_message["content"].startswith("Command")
+            else "None"
+        )
+        user_input = (
+            result_message["content"]
+            if result_message["content"].startswith("Human feedback")
+            else "None"
+        )
+        memory_content = (
+            f"Assistant Reply: {ai_message['content']}"
+            "\n\n"
+            f"Result: {result}"
+            "\n\n"
+            f"Human Feedback: {user_input}"
+        )
+
+        return MemoryItem.from_text(
+            text=memory_content,
+            source_type="agent_history",
+            how_to_summarize="if possible, also make clear the link between the command in the assistant's response and the command result. Do not mention the human feedback if there is none",
+        )
+
+    @staticmethod
+    def from_webpage(content: str, url: str, question: str | None = None):
+        return MemoryItem.from_text(
+            text=content,
+            source_type="webpage",
+            metadata={"location": url},
+            question_for_summary=question,
+        )
+
+    def dump(self) -> str:
+        token_length = count_string_tokens(self.raw_content, Config().embedding_model)
+        return f"""
+=============== MemoryItem ===============
+Length: {token_length} tokens in {len(self.e_chunks)} chunks
+Metadata: {json.dumps(self.metadata, indent=2)}
+---------------- SUMMARY -----------------
+{self.summary}
+------------------ RAW -------------------
+{self.raw_content}
+==========================================
+"""
+
+
+@dataclasses.dataclass
+class MemoryItemRelevance:
+    """
+    Class that encapsulates memory relevance search functionality and data.
+    Instances contain a MemoryItem and its relevance scores for a given query.
+    """
+
+    memory_item: MemoryItem
+    for_query: str
+    summary_relevance_score: float
+    chunk_relevance_scores: list[float]
+
+    @staticmethod
+    def of(
+        memory_item: MemoryItem, for_query: str, e_query: Embedding | None = None
+    ) -> MemoryItemRelevance:
+        e_query = e_query or get_embedding(for_query)
+        _, srs, crs = MemoryItemRelevance.calculate_scores(memory_item, e_query)
+        return MemoryItemRelevance(
+            for_query=for_query,
+            memory_item=memory_item,
+            summary_relevance_score=srs,
+            chunk_relevance_scores=crs,
+        )
+
+    @staticmethod
+    def calculate_scores(
+        memory: MemoryItem, compare_to: Embedding
+    ) -> tuple[float, float, list[float]]:
+        """
+        Calculates similarity between given embedding and all embeddings of the memory
+
+        Returns:
+            float: the aggregate (max) relevance score of the memory
+            float: the relevance score of the memory summary
+            list: the relevance scores of the memory chunks
+        """
+        summary_relevance_score = np.dot(memory.e_summary, compare_to)
+        chunk_relevance_scores = np.dot(memory.e_chunks, compare_to)
+        logger.debug(f"Relevance of summary: {summary_relevance_score}")
+        logger.debug(f"Relevance of chunks: {chunk_relevance_scores}")
+
+        relevance_scores = [summary_relevance_score, *chunk_relevance_scores]
+        logger.debug(f"Relevance scores: {relevance_scores}")
+        return max(relevance_scores), summary_relevance_score, chunk_relevance_scores
+
+    @property
+    def score(self) -> float:
+        """The aggregate relevance score of the memory item for the given query"""
+        return max([self.summary_relevance_score, *self.chunk_relevance_scores])
+
+    @property
+    def most_relevant_chunk(self) -> tuple[str, float]:
+        """The most relevant chunk of the memory item + its score for the given query"""
+        i_relmax = np.argmax(self.chunk_relevance_scores)
+        return self.memory_item.chunks[i_relmax], self.chunk_relevance_scores[i_relmax]
+
+    def __str__(self):
+        return (
+            f"{self.memory_item.summary} ({self.summary_relevance_score}) "
+            f"{self.chunk_relevance_scores}"
+        )
diff --git a/autogpt/memory/vector/providers/__init__.py b/autogpt/memory/vector/providers/__init__.py
new file mode 100644
index 00000000..12a23b60
--- /dev/null
+++ b/autogpt/memory/vector/providers/__init__.py
@@ -0,0 +1,7 @@
+from .json_file import JSONFileMemory
+from .no_memory import NoMemory
+
+__all__ = [
+    "JSONFileMemory",
+    "NoMemory",
+]
diff --git a/autogpt/memory/vector/providers/base.py b/autogpt/memory/vector/providers/base.py
new file mode 100644
index 00000000..969d8934
--- /dev/null
+++ b/autogpt/memory/vector/providers/base.py
@@ -0,0 +1,74 @@
+import abc
+import functools
+from typing import MutableSet, Sequence
+
+import numpy as np
+
+from autogpt.config.config import Config
+from autogpt.logs import logger
+from autogpt.singleton import AbstractSingleton
+
+from .. import MemoryItem, MemoryItemRelevance
+from ..utils import Embedding, get_embedding
+
+
+class VectorMemoryProvider(MutableSet[MemoryItem], AbstractSingleton):
+    @abc.abstractmethod
+    def __init__(self, config: Config):
+        pass
+
+    def get(self, query: str) -> MemoryItemRelevance | None:
+        """
+        Gets the data from the memory that is most relevant to the given query.
+
+        Args:
+            data: The data to compare to.
+
+        Returns: The most relevant Memory
+        """
+        result = self.get_relevant(query, 1)
+        return result[0] if result else None
+
+    def get_relevant(self, query: str, k: int) -> Sequence[MemoryItemRelevance]:
+        """
+        Returns the top-k most relevant memories for the given query
+
+        Args:
+            query: the query to compare stored memories to
+            k: the number of relevant memories to fetch
+
+        Returns:
+            list[MemoryItemRelevance] containing the top [k] relevant memories
+        """
+        if len(self) < 1:
+            return []
+
+        logger.debug(
+            f"Searching for {k} relevant memories for query '{query}'; "
+            f"{len(self)} memories in index"
+        )
+
+        relevances = self.score_memories_for_relevance(query)
+        logger.debug(f"Memory relevance scores: {[str(r) for r in relevances]}")
+
+        # take last k items and reverse
+        top_k_indices = np.argsort([r.score for r in relevances])[-k:][::-1]
+
+        return [relevances[i] for i in top_k_indices]
+
+    def score_memories_for_relevance(
+        self, for_query: str
+    ) -> Sequence[MemoryItemRelevance]:
+        """
+        Returns MemoryItemRelevance for every memory in the index.
+        Implementations may override this function for performance purposes.
+        """
+        e_query: Embedding = get_embedding(for_query)
+        return [m.relevance_for(for_query, e_query) for m in self]
+
+    def get_stats(self) -> tuple[int, int]:
+        """
+        Returns:
+            tuple (n_memories: int, n_chunks: int): the stats of the memory index
+        """
+        return len(self), functools.reduce(lambda t, m: t + len(m.e_chunks), self, 0)
diff --git a/autogpt/memory/vector/providers/json_file.py b/autogpt/memory/vector/providers/json_file.py
new file mode 100644
index 00000000..46446a9c
--- /dev/null
+++ b/autogpt/memory/vector/providers/json_file.py
@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Iterator
+
+import orjson
+
+from autogpt.config import Config
+from autogpt.logs import logger
+
+from ..memory_item import MemoryItem
+from .base import VectorMemoryProvider
+
+
+class JSONFileMemory(VectorMemoryProvider):
+    """Memory backend that stores memories in a JSON file"""
+
+    SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS
+
+    file_path: Path
+    memories: list[MemoryItem]
+
+    def __init__(self, cfg: Config) -> None:
+        """Initialize a class instance
+
+        Args:
+            cfg: Config object
+
+        Returns:
+            None
+        """
+        workspace_path = Path(cfg.workspace_path)
+        self.file_path = workspace_path / f"{cfg.memory_index}.json"
+        self.file_path.touch()
+        logger.debug(f"Initialized {__name__} with index path {self.file_path}")
+
+        self.memories = []
+        self.save_index()
+
+    def __iter__(self) -> Iterator[MemoryItem]:
+        return iter(self.memories)
+
+    def __contains__(self, x: MemoryItem) -> bool:
+        return x in self.memories
+
+    def __len__(self) -> int:
+        return len(self.memories)
+
+    def add(self, item: MemoryItem):
+        self.memories.append(item)
+        self.save_index()
+        return len(self.memories)
+
+    def discard(self, item: MemoryItem):
+        try:
+            self.remove(item)
+        except:
+            pass
+
+    def clear(self):
+        """Clears the data in memory."""
+        self.memories.clear()
+        self.save_index()
+
+    def save_index(self):
+        logger.debug(f"Saving memory index to file {self.file_path}")
+        with self.file_path.open("wb") as f:
+            return f.write(orjson.dumps(self.memories, option=self.SAVE_OPTIONS))
diff --git a/autogpt/memory/vector/providers/no_memory.py b/autogpt/memory/vector/providers/no_memory.py
new file mode 100644
index 00000000..01f6c180
--- /dev/null
+++ b/autogpt/memory/vector/providers/no_memory.py
@@ -0,0 +1,36 @@
+"""A class that does not store any data. This is the default memory provider."""
+from __future__ import annotations
+
+from typing import Iterator, Optional
+
+from autogpt.config.config import Config
+
+from .. import MemoryItem
+from .base import VectorMemoryProvider
+
+
+class NoMemory(VectorMemoryProvider):
+    """
+    A class that does not store any data. This is the default memory provider.
+    """
+
+    def __init__(self, config: Optional[Config] = None):
+        pass
+
+    def __iter__(self) -> Iterator[MemoryItem]:
+        return iter([])
+
+    def __contains__(self, x: MemoryItem) -> bool:
+        return False
+
+    def __len__(self) -> int:
+        return 0
+
+    def add(self, item: MemoryItem):
+        pass
+
+    def discard(self, item: MemoryItem):
+        pass
+
+    def clear(self):
+        pass
diff --git a/autogpt/memory/vector/utils.py b/autogpt/memory/vector/utils.py
new file mode 100644
index 00000000..d01f7108
--- /dev/null
+++ b/autogpt/memory/vector/utils.py
@@ -0,0 +1,71 @@
+from typing import Any, overload
+
+import numpy as np
+import numpy.typing as npt
+import openai
+
+from autogpt.config import Config
+from autogpt.llm.utils import metered, retry_openai_api
+from autogpt.logs import logger
+
+Embedding = list[np.float32] | np.ndarray[Any, np.dtype[np.float32]]
+"""Embedding vector"""
+TText = list[int]
+"""Token array representing text"""
+
+
+@overload
+def get_embedding(input: str | TText) -> Embedding:
+    ...
+
+
+@overload
+def get_embedding(input: list[str] | list[TText]) -> list[Embedding]:
+    ...
+
+
+@metered
+@retry_openai_api()
+def get_embedding(
+    input: str | TText | list[str] | list[TText],
+) -> Embedding | list[Embedding]:
+    """Get an embedding from the ada model.
+
+    Args:
+        input: Input text to get embeddings for, encoded as a string or array of tokens.
+            Multiple inputs may be given as a list of strings or token arrays.
+
+    Returns:
+        List[float]: The embedding.
+    """
+    cfg = Config()
+    multiple = isinstance(input, list) and all(not isinstance(i, int) for i in input)
+
+    if isinstance(input, str):
+        input = input.replace("\n", " ")
+    elif multiple and isinstance(input[0], str):
+        input = [text.replace("\n", " ") for text in input]
+
+    model = cfg.embedding_model
+    if cfg.use_azure:
+        kwargs = {"engine": cfg.get_azure_deployment_id_for_model(model)}
+    else:
+        kwargs = {"model": model}
+
+    logger.debug(
+        f"Getting embedding{f's for {len(input)} inputs' if multiple else ''}"
+        f" with model '{model}'"
+        + (f" via Azure deployment '{kwargs['engine']}'" if cfg.use_azure else "")
+    )
+
+    embeddings = openai.Embedding.create(
+        input=input,
+        api_key=cfg.openai_api_key,
+        **kwargs,
+    ).data
+
+    if not multiple:
+        return embeddings[0]["embedding"]
+
+    embeddings = sorted(embeddings, key=lambda x: x["index"])
+    return [d["embedding"] for d in embeddings]
diff --git a/autogpt/memory/weaviate.py b/autogpt/memory/weaviate.py
deleted file mode 100644
index 0b4f58b5..00000000
--- a/autogpt/memory/weaviate.py
+++ /dev/null
@@ -1,127 +0,0 @@
-import weaviate
-from weaviate import Client
-from weaviate.embedded import EmbeddedOptions
-from weaviate.util import generate_uuid5
-
-from autogpt.llm import get_ada_embedding
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-def default_schema(weaviate_index):
-    return {
-        "class": weaviate_index,
-        "properties": [
-            {
-                "name": "raw_text",
-                "dataType": ["text"],
-                "description": "original text for the embedding",
-            }
-        ],
-    }
-
-
-class WeaviateMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        auth_credentials = self._build_auth_credentials(cfg)
-
-        url = f"{cfg.weaviate_protocol}://{cfg.weaviate_host}:{cfg.weaviate_port}"
-
-        if cfg.use_weaviate_embedded:
-            self.client = Client(
-                embedded_options=EmbeddedOptions(
-                    hostname=cfg.weaviate_host,
-                    port=int(cfg.weaviate_port),
-                    persistence_data_path=cfg.weaviate_embedded_path,
-                )
-            )
-
-            logger.info(
-                f"Weaviate Embedded running on: {url} with persistence path: {cfg.weaviate_embedded_path}"
-            )
-        else:
-            self.client = Client(url, auth_client_secret=auth_credentials)
-
-        self.index = WeaviateMemory.format_classname(cfg.memory_index)
-        self._create_schema()
-
-    @staticmethod
-    def format_classname(index):
-        # weaviate uses capitalised index names
-        # The python client uses the following code to format
-        # index names before the corresponding class is created
-        index = index.replace("-", "_")
-        if len(index) == 1:
-            return index.capitalize()
-        return index[0].capitalize() + index[1:]
-
-    def _create_schema(self):
-        schema = default_schema(self.index)
-        if not self.client.schema.contains(schema):
-            self.client.schema.create_class(schema)
-
-    def _build_auth_credentials(self, cfg):
-        if cfg.weaviate_username and cfg.weaviate_password:
-            return weaviate.AuthClientPassword(
-                cfg.weaviate_username, cfg.weaviate_password
-            )
-        if cfg.weaviate_api_key:
-            return weaviate.AuthApiKey(api_key=cfg.weaviate_api_key)
-        else:
-            return None
-
-    def add(self, data):
-        vector = get_ada_embedding(data)
-
-        doc_uuid = generate_uuid5(data, self.index)
-        data_object = {"raw_text": data}
-
-        with self.client.batch as batch:
-            batch.add_data_object(
-                uuid=doc_uuid,
-                data_object=data_object,
-                class_name=self.index,
-                vector=vector,
-            )
-
-        return f"Inserting data into memory at uuid: {doc_uuid}:\n data: {data}"
-
-    def get(self, data):
-        return self.get_relevant(data, 1)
-
-    def clear(self):
-        self.client.schema.delete_all()
-
-        # weaviate does not yet have a neat way to just remove the items in an index
-        # without removing the entire schema, therefore we need to re-create it
-        # after a call to delete_all
-        self._create_schema()
-
-        return "Obliterated"
-
-    def get_relevant(self, data, num_relevant=5):
-        query_embedding = get_ada_embedding(data)
-        try:
-            results = (
-                self.client.query.get(self.index, ["raw_text"])
-                .with_near_vector({"vector": query_embedding, "certainty": 0.7})
-                .with_limit(num_relevant)
-                .do()
-            )
-
-            if len(results["data"]["Get"][self.index]) > 0:
-                return [
-                    str(item["raw_text"]) for item in results["data"]["Get"][self.index]
-                ]
-            else:
-                return []
-
-        except Exception as err:
-            logger.warn(f"Unexpected error {err=}, {type(err)=}")
-            return []
-
-    def get_stats(self):
-        result = self.client.query.aggregate(self.index).with_meta_count().do()
-        class_data = result["data"]["Aggregate"][self.index]
-
-        return class_data[0]["meta"] if class_data else {}
diff --git a/autogpt/memory_management/store_memory.py b/autogpt/memory_management/store_memory.py
deleted file mode 100644
index e37434ef..00000000
--- a/autogpt/memory_management/store_memory.py
+++ /dev/null
@@ -1,33 +0,0 @@
-from autogpt.json_utils.utilities import (
-    LLM_DEFAULT_RESPONSE_FORMAT,
-    is_string_valid_json,
-)
-from autogpt.logs import logger
-
-
-def format_memory(assistant_reply, next_message_content):
-    # the next_message_content is a variable to stores either the user_input or the command following the assistant_reply
-    result = (
-        "None" if next_message_content.startswith("Command") else next_message_content
-    )
-    user_input = (
-        "None"
-        if next_message_content.startswith("Human feedback")
-        else next_message_content
-    )
-
-    return f"Assistant Reply: {assistant_reply}\nResult: {result}\nHuman Feedback:{user_input}"
-
-
-def save_memory_trimmed_from_context_window(
-    full_message_history, next_message_to_add_index, permanent_memory
-):
-    while next_message_to_add_index >= 0:
-        message_content = full_message_history[next_message_to_add_index]["content"]
-        if is_string_valid_json(message_content, LLM_DEFAULT_RESPONSE_FORMAT):
-            next_message = full_message_history[next_message_to_add_index + 1]
-            memory_to_add = format_memory(message_content, next_message["content"])
-            logger.debug(f"Storing the following memory: {memory_to_add}")
-            permanent_memory.add(memory_to_add)
-
-        next_message_to_add_index -= 1
diff --git a/autogpt/memory_management/summary_memory.py b/autogpt/memory_management/summary_memory.py
deleted file mode 100644
index a13b63f3..00000000
--- a/autogpt/memory_management/summary_memory.py
+++ /dev/null
@@ -1,143 +0,0 @@
-import copy
-import json
-from typing import Dict, List, Tuple
-
-from autogpt.agent import Agent
-from autogpt.config import Config
-from autogpt.llm.llm_utils import create_chat_completion
-from autogpt.log_cycle.log_cycle import PROMPT_SUMMARY_FILE_NAME, SUMMARY_FILE_NAME
-from autogpt.logs import logger
-
-cfg = Config()
-
-
-def get_newly_trimmed_messages(
-    full_message_history: List[Dict[str, str]],
-    current_context: List[Dict[str, str]],
-    last_memory_index: int,
-) -> Tuple[List[Dict[str, str]], int]:
-    """
-    This function returns a list of dictionaries contained in full_message_history
-    with an index higher than prev_index that are absent from current_context.
-
-    Args:
-        full_message_history (list): A list of dictionaries representing the full message history.
-        current_context (list): A list of dictionaries representing the current context.
-        last_memory_index (int): An integer representing the previous index.
-
-    Returns:
-        list: A list of dictionaries that are in full_message_history with an index higher than last_memory_index and absent from current_context.
-        int: The new index value for use in the next loop.
-    """
-    # Select messages in full_message_history with an index higher than last_memory_index
-    new_messages = [
-        msg for i, msg in enumerate(full_message_history) if i > last_memory_index
-    ]
-
-    # Remove messages that are already present in current_context
-    new_messages_not_in_context = [
-        msg for msg in new_messages if msg not in current_context
-    ]
-
-    # Find the index of the last message processed
-    new_index = last_memory_index
-    if new_messages_not_in_context:
-        last_message = new_messages_not_in_context[-1]
-        new_index = full_message_history.index(last_message)
-
-    return new_messages_not_in_context, new_index
-
-
-def update_running_summary(
-    agent: Agent, current_memory: str, new_events: List[Dict[str, str]]
-) -> str:
-    """
-    This function takes a list of dictionaries representing new events and combines them with the current summary,
-    focusing on key and potentially important information to remember. The updated summary is returned in a message
-    formatted in the 1st person past tense.
-
-    Args:
-        new_events (List[Dict]): A list of dictionaries containing the latest events to be added to the summary.
-
-    Returns:
-        str: A message containing the updated summary of actions, formatted in the 1st person past tense.
-
-    Example:
-        new_events = [{"event": "entered the kitchen."}, {"event": "found a scrawled note with the number 7"}]
-        update_running_summary(new_events)
-        # Returns: "This reminds you of these events from your past: \nI entered the kitchen and found a scrawled note saying 7."
-    """
-    # Create a copy of the new_events list to prevent modifying the original list
-    new_events = copy.deepcopy(new_events)
-
-    # Replace "assistant" with "you". This produces much better first person past tense results.
-    for event in new_events:
-        if event["role"].lower() == "assistant":
-            event["role"] = "you"
-
-            # Remove "thoughts" dictionary from "content"
-            try:
-                content_dict = json.loads(event["content"])
-                if "thoughts" in content_dict:
-                    del content_dict["thoughts"]
-                event["content"] = json.dumps(content_dict)
-            except json.decoder.JSONDecodeError:
-                if cfg.debug_mode:
-                    logger.error(f"Error: Invalid JSON: {event['content']}\n")
-
-        elif event["role"].lower() == "system":
-            event["role"] = "your computer"
-
-        # Delete all user messages
-        elif event["role"] == "user":
-            new_events.remove(event)
-
-    # This can happen at any point during execution, not just the beginning
-    if len(new_events) == 0:
-        new_events = "Nothing new happened."
-
-    prompt = f'''Your task is to create a concise running summary of actions and information results in the provided text, focusing on key and potentially important information to remember.
-
-You will receive the current summary and the your latest actions. Combine them, adding relevant key information from the latest development in 1st person past tense and keeping the summary concise.
-
-Summary So Far:
-"""
-{current_memory}
-"""
-
-Latest Development:
-"""
-{new_events}
-"""
-'''
-
-    messages = [
-        {
-            "role": "user",
-            "content": prompt,
-        }
-    ]
-    agent.log_cycle_handler.log_cycle(
-        agent.config.ai_name,
-        agent.created_at,
-        agent.cycle_count,
-        messages,
-        PROMPT_SUMMARY_FILE_NAME,
-    )
-
-    current_memory = create_chat_completion(messages, cfg.fast_llm_model)
-
-    agent.log_cycle_handler.log_cycle(
-        agent.config.ai_name,
-        agent.created_at,
-        agent.cycle_count,
-        current_memory,
-        SUMMARY_FILE_NAME,
-    )
-
-    message_to_return = {
-        "role": "system",
-        "content": f"This reminds you of these events from your past: \n{current_memory}",
-    }
-
-    return message_to_return
diff --git a/autogpt/plugins.py b/autogpt/plugins.py
index bf77ef74..780593a8 100644
--- a/autogpt/plugins.py
+++ b/autogpt/plugins.py
@@ -1,6 +1,6 @@
 """Handles loading of plugins."""
 
-import importlib
+import importlib.util
 import json
 import os
 import zipfile
@@ -12,7 +12,7 @@ from zipimport import zipimporter
 import openapi_python_client
 import requests
 from auto_gpt_plugin_template import AutoGPTPluginTemplate
-from openapi_python_client.cli import Config as OpenAPIConfig
+from openapi_python_client.config import Config as OpenAPIConfig
 
 from autogpt.config import Config
 from autogpt.logs import logger
@@ -152,7 +152,7 @@ def initialize_openai_plugins(
             )
             prev_cwd = Path.cwd()
             os.chdir(openai_plugin_client_dir)
-            Path("ai-plugin.json")
+
             if not os.path.exists("client"):
                 client_results = openapi_python_client.create_new_client(
                     url=manifest_spec["manifest"]["api"]["url"],
@@ -170,9 +170,13 @@ def initialize_openai_plugins(
                 "client", "client/client/client.py"
             )
             module = importlib.util.module_from_spec(spec)
-            spec.loader.exec_module(module)
+
+            try:
+                spec.loader.exec_module(module)
+            finally:
+                os.chdir(prev_cwd)
+
             client = module.Client(base_url=url)
-            os.chdir(prev_cwd)
             manifest_spec["client"] = client
     return manifests_specs
 
diff --git a/autogpt/processing/text.py b/autogpt/processing/text.py
index 4687fb71..aadc93ef 100644
--- a/autogpt/processing/text.py
+++ b/autogpt/processing/text.py
@@ -1,170 +1,234 @@
 """Text processing functions"""
-from typing import Dict, Generator, Optional
+from math import ceil
+from typing import Optional
 
 import spacy
-from selenium.webdriver.remote.webdriver import WebDriver
+import tiktoken
 
 from autogpt.config import Config
-from autogpt.llm import count_message_tokens, create_chat_completion
+from autogpt.llm.base import ChatSequence
+from autogpt.llm.providers.openai import OPEN_AI_MODELS
+from autogpt.llm.utils import count_string_tokens, create_chat_completion
 from autogpt.logs import logger
-from autogpt.memory import get_memory
+from autogpt.utils import batch
 
 CFG = Config()
 
 
+def _max_chunk_length(model: str, max: Optional[int] = None) -> int:
+    model_max_input_tokens = OPEN_AI_MODELS[model].max_tokens - 1
+    if max is not None and max > 0:
+        return min(max, model_max_input_tokens)
+    return model_max_input_tokens
+
+
+def must_chunk_content(
+    text: str, for_model: str, max_chunk_length: Optional[int] = None
+) -> bool:
+    return count_string_tokens(text, for_model) > _max_chunk_length(
+        for_model, max_chunk_length
+    )
+
+
+def chunk_content(
+    content: str,
+    for_model: str,
+    max_chunk_length: Optional[int] = None,
+    with_overlap=True,
+):
+    """Split content into chunks of approximately equal token length."""
+
+    MAX_OVERLAP = 200  # limit overlap to save tokens
+
+    if not must_chunk_content(content, for_model, max_chunk_length):
+        yield content, count_string_tokens(content, for_model)
+        return
+
+    max_chunk_length = max_chunk_length or _max_chunk_length(for_model)
+
+    tokenizer = tiktoken.encoding_for_model(for_model)
+
+    tokenized_text = tokenizer.encode(content)
+    total_length = len(tokenized_text)
+    n_chunks = ceil(total_length / max_chunk_length)
+
+    chunk_length = ceil(total_length / n_chunks)
+    overlap = min(max_chunk_length - chunk_length, MAX_OVERLAP) if with_overlap else 0
+
+    for token_batch in batch(tokenized_text, chunk_length + overlap, overlap):
+        yield tokenizer.decode(token_batch), len(token_batch)
+
+
+def summarize_text(
+    text: str, instruction: Optional[str] = None, question: Optional[str] = None
+) -> tuple[str, None | list[tuple[str, str]]]:
+    """Summarize text using the OpenAI API
+
+    Args:
+        text (str): The text to summarize
+        instruction (str): Additional instruction for summarization, e.g. "focus on information related to polar bears", "omit personal information contained in the text"
+
+    Returns:
+        str: The summary of the text
+        list[(summary, chunk)]: Text chunks and their summary, if the text was chunked.
+            None otherwise.
+    """
+    if not text:
+        raise ValueError("No text to summarize")
+
+    if instruction and question:
+        raise ValueError("Parameters 'question' and 'instructions' cannot both be set")
+
+    model = CFG.fast_llm_model
+
+    if question:
+        instruction = (
+            f'include any information that can be used to answer the question "{question}". '
+            "Do not directly answer the question itself"
+        )
+
+    summarization_prompt = ChatSequence.for_model(model)
+
+    token_length = count_string_tokens(text, model)
+    logger.info(f"Text length: {token_length} tokens")
+
+    # reserve 50 tokens for summary prompt, 500 for the response
+    max_chunk_length = _max_chunk_length(model) - 550
+    logger.info(f"Max chunk length: {max_chunk_length} tokens")
+
+    if not must_chunk_content(text, model, max_chunk_length):
+        # summarization_prompt.add("user", text)
+        summarization_prompt.add(
+            "user",
+            "Write a concise summary of the following text"
+            f"{f'; {instruction}' if instruction is not None else ''}:"
+            "\n\n\n"
+            f'LITERAL TEXT: """{text}"""'
+            "\n\n\n"
+            "CONCISE SUMMARY: The text is best summarized as"
+            # "Only respond with a concise summary or description of the user message."
+        )
+
+        logger.debug(f"Summarizing with {model}:\n{summarization_prompt.dump()}\n")
+        summary = create_chat_completion(
+            summarization_prompt, temperature=0, max_tokens=500
+        )
+
+        logger.debug(f"\n{'-'*16} SUMMARY {'-'*17}\n{summary}\n{'-'*42}\n")
+        return summary.strip(), None
+
+    summaries: list[str] = []
+    chunks = list(split_text(text, for_model=model, max_chunk_length=max_chunk_length))
+
+    for i, (chunk, chunk_length) in enumerate(chunks):
+        logger.info(
+            f"Summarizing chunk {i + 1} / {len(chunks)} of length {chunk_length} tokens"
+        )
+        summary, _ = summarize_text(chunk, instruction)
+        summaries.append(summary)
+
+    logger.info(f"Summarized {len(chunks)} chunks")
+
+    summary, _ = summarize_text("\n\n".join(summaries))
+
+    return summary.strip(), [
+        (summaries[i], chunks[i][0]) for i in range(0, len(chunks))
+    ]
+
+
 def split_text(
     text: str,
-    max_length: int = CFG.browse_chunk_max_length,
-    model: str = CFG.fast_llm_model,
-    question: str = "",
-) -> Generator[str, None, None]:
-    """Split text into chunks of a maximum length
+    for_model: str = CFG.fast_llm_model,
+    with_overlap=True,
+    max_chunk_length: Optional[int] = None,
+):
+    """Split text into chunks of sentences, with each chunk not exceeding the maximum length
 
     Args:
         text (str): The text to split
-        max_length (int, optional): The maximum length of each chunk. Defaults to 8192.
+        for_model (str): The model to chunk for; determines tokenizer and constraints
+        max_length (int, optional): The maximum length of each chunk
 
     Yields:
         str: The next chunk of text
 
     Raises:
-        ValueError: If the text is longer than the maximum length
+        ValueError: when a sentence is longer than the maximum length
     """
-    flattened_paragraphs = " ".join(text.split("\n"))
-    nlp = spacy.load(CFG.browse_spacy_language_model)
+    max_length = _max_chunk_length(for_model, max_chunk_length)
+
+    # flatten paragraphs to improve performance
+    text = text.replace("\n", " ")
+    text_length = count_string_tokens(text, for_model)
+
+    if text_length < max_length:
+        yield text, text_length
+        return
+
+    n_chunks = ceil(text_length / max_length)
+    target_chunk_length = ceil(text_length / n_chunks)
+
+    nlp: spacy.language.Language = spacy.load(CFG.browse_spacy_language_model)
     nlp.add_pipe("sentencizer")
-    doc = nlp(flattened_paragraphs)
-    sentences = [sent.text.strip() for sent in doc.sents]
+    doc = nlp(text)
+    sentences = [sentence.text.strip() for sentence in doc.sents]
 
-    current_chunk = []
+    current_chunk: list[str] = []
+    current_chunk_length = 0
+    last_sentence = None
+    last_sentence_length = 0
 
-    for sentence in sentences:
-        message_with_additional_sentence = [
-            create_message(" ".join(current_chunk) + " " + sentence, question)
-        ]
+    i = 0
+    while i < len(sentences):
+        sentence = sentences[i]
+        sentence_length = count_string_tokens(sentence, for_model)
+        expected_chunk_length = current_chunk_length + 1 + sentence_length
 
-        expected_token_usage = (
-            count_message_tokens(messages=message_with_additional_sentence, model=model)
-            + 1
-        )
-        if expected_token_usage <= max_length:
+        if (
+            expected_chunk_length < max_length
+            # try to create chunks of approximately equal size
+            and expected_chunk_length - (sentence_length / 2) < target_chunk_length
+        ):
             current_chunk.append(sentence)
-        else:
-            yield " ".join(current_chunk)
-            current_chunk = [sentence]
-            message_this_sentence_only = [
-                create_message(" ".join(current_chunk), question)
+            current_chunk_length = expected_chunk_length
+
+        elif sentence_length < max_length:
+            if last_sentence:
+                yield " ".join(current_chunk), current_chunk_length
+                current_chunk = []
+                current_chunk_length = 0
+
+                if with_overlap:
+                    overlap_max_length = max_length - sentence_length - 1
+                    if last_sentence_length < overlap_max_length:
+                        current_chunk += [last_sentence]
+                        current_chunk_length += last_sentence_length + 1
+                    elif overlap_max_length > 5:
+                        # add as much from the end of the last sentence as fits
+                        current_chunk += [
+                            list(
+                                chunk_content(
+                                    last_sentence,
+                                    for_model,
+                                    overlap_max_length,
+                                )
+                            ).pop()[0],
+                        ]
+                        current_chunk_length += overlap_max_length + 1
+
+            current_chunk += [sentence]
+            current_chunk_length += sentence_length
+
+        else:  # sentence longer than maximum length -> chop up and try again
+            sentences[i : i + 1] = [
+                chunk
+                for chunk, _ in chunk_content(sentence, for_model, target_chunk_length)
             ]
-            expected_token_usage = (
-                count_message_tokens(messages=message_this_sentence_only, model=model)
-                + 1
-            )
-            if expected_token_usage > max_length:
-                raise ValueError(
-                    f"Sentence is too long in webpage: {expected_token_usage} tokens."
-                )
+            continue
+
+        i += 1
+        last_sentence = sentence
+        last_sentence_length = sentence_length
 
     if current_chunk:
-        yield " ".join(current_chunk)
-
-
-def summarize_text(
-    url: str, text: str, question: str, driver: Optional[WebDriver] = None
-) -> str:
-    """Summarize text using the OpenAI API
-
-    Args:
-        url (str): The url of the text
-        text (str): The text to summarize
-        question (str): The question to ask the model
-        driver (WebDriver): The webdriver to use to scroll the page
-
-    Returns:
-        str: The summary of the text
-    """
-    if not text:
-        return "Error: No text to summarize"
-
-    model = CFG.fast_llm_model
-    text_length = len(text)
-    logger.info(f"Text length: {text_length} characters")
-
-    summaries = []
-    chunks = list(
-        split_text(
-            text, max_length=CFG.browse_chunk_max_length, model=model, question=question
-        ),
-    )
-    scroll_ratio = 1 / len(chunks)
-
-    for i, chunk in enumerate(chunks):
-        if driver:
-            scroll_to_percentage(driver, scroll_ratio * i)
-        logger.info(f"Adding chunk {i + 1} / {len(chunks)} to memory")
-
-        memory_to_add = f"Source: {url}\n" f"Raw content part#{i + 1}: {chunk}"
-
-        memory = get_memory(CFG)
-        memory.add(memory_to_add)
-
-        messages = [create_message(chunk, question)]
-        tokens_for_chunk = count_message_tokens(messages, model)
-        logger.info(
-            f"Summarizing chunk {i + 1} / {len(chunks)} of length {len(chunk)} characters, or {tokens_for_chunk} tokens"
-        )
-
-        summary = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-        summaries.append(summary)
-        logger.info(
-            f"Added chunk {i + 1} summary to memory, of length {len(summary)} characters"
-        )
-
-        memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}"
-
-        memory.add(memory_to_add)
-
-    logger.info(f"Summarized {len(chunks)} chunks.")
-
-    combined_summary = "\n".join(summaries)
-    messages = [create_message(combined_summary, question)]
-
-    return create_chat_completion(
-        model=model,
-        messages=messages,
-    )
-
-
-def scroll_to_percentage(driver: WebDriver, ratio: float) -> None:
-    """Scroll to a percentage of the page
-
-    Args:
-        driver (WebDriver): The webdriver to use
-        ratio (float): The percentage to scroll to
-
-    Raises:
-        ValueError: If the ratio is not between 0 and 1
-    """
-    if ratio < 0 or ratio > 1:
-        raise ValueError("Percentage should be between 0 and 1")
-    driver.execute_script(f"window.scrollTo(0, document.body.scrollHeight * {ratio});")
-
-
-def create_message(chunk: str, question: str) -> Dict[str, str]:
-    """Create a message for the chat completion
-
-    Args:
-        chunk (str): The chunk of text to summarize
-        question (str): The question to answer
-
-    Returns:
-        Dict[str, str]: The message to send to the chat completion
-    """
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the text,'
-        " summarize the text.",
-    }
+        yield " ".join(current_chunk), current_chunk_length
diff --git a/autogpt/prompts/generator.py b/autogpt/prompts/generator.py
index 2ae9123b..adf64894 100644
--- a/autogpt/prompts/generator.py
+++ b/autogpt/prompts/generator.py
@@ -1,6 +1,9 @@
 """ A module for generating custom prompt strings."""
 import json
-from typing import Any, Callable, Dict, List, Optional
+from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional
+
+if TYPE_CHECKING:
+    from autogpt.commands.command import CommandRegistry
 
 
 class PromptGenerator:
@@ -19,7 +22,7 @@ class PromptGenerator:
         self.resources = []
         self.performance_evaluation = []
         self.goals = []
-        self.command_registry = None
+        self.command_registry: CommandRegistry | None = None
         self.name = "Bob"
         self.role = "AI"
         self.response_format = {
diff --git a/autogpt/prompts/prompt.py b/autogpt/prompts/prompt.py
index e69fc4b7..eeeea3f9 100644
--- a/autogpt/prompts/prompt.py
+++ b/autogpt/prompts/prompt.py
@@ -3,7 +3,7 @@ from colorama import Fore
 from autogpt.config.ai_config import AIConfig
 from autogpt.config.config import Config
 from autogpt.config.prompt_config import PromptConfig
-from autogpt.llm import ApiManager
+from autogpt.llm.api_manager import ApiManager
 from autogpt.logs import logger
 from autogpt.prompts.generator import PromptGenerator
 from autogpt.setup import prompt_user
diff --git a/autogpt/setup.py b/autogpt/setup.py
index 967645c1..67cae5da 100644
--- a/autogpt/setup.py
+++ b/autogpt/setup.py
@@ -7,7 +7,8 @@ from jinja2 import Template
 from autogpt import utils
 from autogpt.config import Config
 from autogpt.config.ai_config import AIConfig
-from autogpt.llm import create_chat_completion
+from autogpt.llm.base import ChatSequence, Message
+from autogpt.llm.chat import create_chat_completion
 from autogpt.logs import logger
 from autogpt.prompts.default_prompts import (
     DEFAULT_SYSTEM_PROMPT_AICONFIG_AUTOMATIC,
@@ -175,17 +176,15 @@ def generate_aiconfig_automatic(user_prompt) -> AIConfig:
         DEFAULT_TASK_PROMPT_AICONFIG_AUTOMATIC
     ).render(user_prompt=user_prompt)
     # Call LLM with the string as user input
-    messages = [
-        {
-            "role": "system",
-            "content": system_prompt,
-        },
-        {
-            "role": "user",
-            "content": prompt_ai_config_automatic,
-        },
-    ]
-    output = create_chat_completion(messages, CFG.fast_llm_model)
+    output = create_chat_completion(
+        ChatSequence.for_model(
+            CFG.fast_llm_model,
+            [
+                Message("system", system_prompt),
+                Message("user", prompt_ai_config_automatic),
+            ],
+        )
+    )
 
     # Debug LLM Output
     logger.debug(f"AI Config Generator Raw Output: {output}")
diff --git a/autogpt/speech/eleven_labs.py b/autogpt/speech/eleven_labs.py
index 06806b56..c1e3aff5 100644
--- a/autogpt/speech/eleven_labs.py
+++ b/autogpt/speech/eleven_labs.py
@@ -4,7 +4,7 @@ import os
 import requests
 from playsound import playsound
 
-from autogpt.config import Config
+from autogpt.config.config import Config
 from autogpt.speech.base import VoiceBase
 
 PLACEHOLDERS = {"your-voice-id"}
diff --git a/autogpt/speech/say.py b/autogpt/speech/say.py
index 917fa65c..4cc82e19 100644
--- a/autogpt/speech/say.py
+++ b/autogpt/speech/say.py
@@ -2,7 +2,7 @@
 import threading
 from threading import Semaphore
 
-from autogpt.config import Config
+from autogpt.config.config import Config
 from autogpt.speech.base import VoiceBase
 from autogpt.speech.brian import BrianSpeech
 from autogpt.speech.eleven_labs import ElevenLabsSpeech
diff --git a/autogpt/utils.py b/autogpt/utils.py
index 8685d402..8eb95deb 100644
--- a/autogpt/utils.py
+++ b/autogpt/utils.py
@@ -17,6 +17,15 @@ except ImportError:
 from autogpt.config import Config
 
 
+def batch(iterable, max_batch_length: int, overlap: int = 0):
+    """Batch data from iterable into slices of length N. The last batch may be shorter."""
+    # batched('ABCDEFG', 3) --> ABC DEF G
+    if max_batch_length < 1:
+        raise ValueError("n must be at least one")
+    for i in range(0, len(iterable), max_batch_length - overlap):
+        yield iterable[i : i + max_batch_length]
+
+
 def clean_input(prompt: str = "", talk=False):
     try:
         cfg = Config()
diff --git a/data_ingestion.py b/data_ingestion.py
index c907cedf..e2d98d1c 100644
--- a/data_ingestion.py
+++ b/data_ingestion.py
@@ -3,7 +3,7 @@ import logging
 
 from autogpt.commands.file_operations import ingest_file, list_files
 from autogpt.config import Config
-from autogpt.memory import get_memory
+from autogpt.memory.vector import VectorMemory, get_memory
 
 cfg = Config()
 
@@ -21,14 +21,14 @@ def configure_logging():
     return logging.getLogger("AutoGPT-Ingestion")
 
 
-def ingest_directory(directory, memory, args):
+def ingest_directory(directory: str, memory: VectorMemory, args):
     """
     Ingest all files in a directory by calling the ingest_file function for each file.
 
     :param directory: The directory containing the files to ingest
     :param memory: An object with an add() method to store the chunks in memory
     """
-    global logger
+    logger = logging.getLogger("AutoGPT-Ingestion")
     try:
         files = list_files(directory)
         for file in files:
diff --git a/docs/challenges/building_challenges.md b/docs/challenges/building_challenges.md
index c62c32d0..ad567238 100644
--- a/docs/challenges/building_challenges.md
+++ b/docs/challenges/building_challenges.md
@@ -33,7 +33,7 @@ Create your agent fixture.
 
 ```python
 def kubernetes_agent(
-    agent_test_config, memory_local_cache, workspace: Workspace
+    agent_test_config, memory_json_file, workspace: Workspace
 ):
     # Please choose the commands your agent will need to beat the challenges, the full list is available in the main.py
     # (we 're working on a better way to design this, for now you have to look at main.py)
@@ -56,7 +56,7 @@ def kubernetes_agent(
     agent = Agent(
         # We also give the AI a name 
         ai_name="Kubernetes-Demo",
-        memory=memory_local_cache,
+        memory=memory_json_file,
         full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
@@ -131,5 +131,3 @@ def test_information_retrieval_challenge_a(kubernetes_agent, monkeypatch) -> Non
 
 
 ```
-
-
diff --git a/docs/configuration/memory.md b/docs/configuration/memory.md
index 7d707598..452a6eac 100644
--- a/docs/configuration/memory.md
+++ b/docs/configuration/memory.md
@@ -1,3 +1,9 @@
+!!! warning
+    The Pinecone, Milvus and Weaviate memory backends were rendered incompatible
+    by work on the memory system, and have been removed in `master`.
+    Whether support will be added back in the future is subject to discussion,
+    feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
+
 ## Setting Your Cache Type
 
 By default, Auto-GPT set up with Docker Compose will use Redis as its memory backend.
@@ -6,7 +12,7 @@ Otherwise, the default is LocalCache (which stores memory in a JSON file).
 To switch to a different backend, change the `MEMORY_BACKEND` in `.env`
 to the value that you want:
 
-* `local` uses a local JSON cache file
+* `json_file` uses a local JSON cache file
 * `pinecone` uses the Pinecone.io account you configured in your ENV settings
 * `redis` will use the redis cache that you configured
 * `milvus` will use the milvus cache that you configured
diff --git a/tests/conftest.py b/tests/conftest.py
index 6e6f0ad3..3644fd85 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -4,11 +4,11 @@ from pathlib import Path
 import pytest
 from pytest_mock import MockerFixture
 
-from autogpt.config import Config
-from autogpt.llm import ApiManager
+from autogpt.config.config import Config
+from autogpt.llm.api_manager import ApiManager
 from autogpt.workspace import Workspace
 
-pytest_plugins = ["tests.integration.agent_factory"]
+pytest_plugins = ["tests.integration.agent_factory", "tests.integration.memory.utils"]
 
 PROXY = os.environ.get("PROXY")
 
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index b96953fe..1781a3f1 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -3,7 +3,7 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.command import CommandRegistry
 from autogpt.config import AIConfig, Config
-from autogpt.memory import LocalCache, NoMemory, get_memory
+from autogpt.memory.vector import NoMemory, get_memory
 from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT
 from autogpt.workspace import Workspace
 
@@ -20,20 +20,10 @@ def agent_test_config(config: Config):
 
 
 @pytest.fixture
-def memory_local_cache(agent_test_config: Config):
+def memory_json_file(agent_test_config: Config):
     was_memory_backend = agent_test_config.memory_backend
 
-    agent_test_config.set_memory_backend("local_cache")
-    yield get_memory(agent_test_config, init=True)
-
-    agent_test_config.set_memory_backend(was_memory_backend)
-
-
-@pytest.fixture
-def memory_none(agent_test_config: Config):
-    was_memory_backend = agent_test_config.memory_backend
-
-    agent_test_config.set_memory_backend("no_memory")
+    agent_test_config.set_memory_backend("json_file")
     yield get_memory(agent_test_config, init=True)
 
     agent_test_config.set_memory_backend(was_memory_backend)
@@ -64,7 +54,6 @@ def browser_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace
     agent = Agent(
         ai_name="",
         memory=memory_none,
-        full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
         next_action_count=0,
@@ -103,7 +92,6 @@ def writer_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace)
     agent = Agent(
         ai_name="",
         memory=memory_none,
-        full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
         next_action_count=0,
@@ -116,9 +104,7 @@ def writer_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace)
 
 
 @pytest.fixture
-def memory_management_agent(
-    agent_test_config, memory_local_cache, workspace: Workspace
-):
+def memory_management_agent(agent_test_config, memory_json_file, workspace: Workspace):
     command_registry = CommandRegistry()
     command_registry.import_commands("autogpt.commands.file_operations")
     command_registry.import_commands("autogpt.app")
@@ -138,8 +124,7 @@ def memory_management_agent(
 
     agent = Agent(
         ai_name="",
-        memory=memory_local_cache,
-        full_message_history=[],
+        memory=memory_json_file,
         command_registry=command_registry,
         config=ai_config,
         next_action_count=0,
@@ -153,7 +138,7 @@ def memory_management_agent(
 
 @pytest.fixture
 def get_company_revenue_agent(
-    agent_test_config, memory_local_cache, workspace: Workspace
+    agent_test_config, memory_json_file, workspace: Workspace
 ):
     command_registry = CommandRegistry()
     command_registry.import_commands("autogpt.commands.file_operations")
@@ -172,7 +157,7 @@ def get_company_revenue_agent(
     Config().set_continuous_mode(False)
     agent = Agent(
         ai_name="Get-CompanyRevenue",
-        memory=memory_local_cache,
+        memory=memory_json_file,
         full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
@@ -186,7 +171,7 @@ def get_company_revenue_agent(
 
 
 @pytest.fixture
-def kubernetes_agent(memory_local_cache, workspace: Workspace):
+def kubernetes_agent(memory_json_file, workspace: Workspace):
     command_registry = CommandRegistry()
     command_registry.import_commands("autogpt.commands.file_operations")
     command_registry.import_commands("autogpt.app")
@@ -205,7 +190,7 @@ def kubernetes_agent(memory_local_cache, workspace: Workspace):
     Config().set_continuous_mode(False)
     agent = Agent(
         ai_name="Kubernetes-Demo",
-        memory=memory_local_cache,
+        memory=memory_json_file,
         full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
diff --git a/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding.yaml b/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding.yaml
deleted file mode 100644
index ec4636e0..00000000
--- a/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding.yaml
+++ /dev/null
@@ -1,168 +0,0 @@
-interactions:
-- request:
-    body: '{"input": [[1985]], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '83'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaSxO6Orvl5++n2LWn9FsiIgl7xl3kkiAgYldXlyAiKHJNgJw6371L/6dOd08c
-        QAqV5HnWWr/kP/71119/t1ld5NPf//z197sap7//x/fa/Tbd/v7nr//5r7/++uuv//h9/n8jiyYr
-        7vfqU/6G/25Wn3ux/P3PX/x/X/m/g/756++DcanIKGZXd/X5SZTuBpdQW6+lYQqkfQ5NFN8pSgIw
-        zBGFBLyF+0x9ZATRzFVcC+xx3aJPfw3cJaBFA2RnibBlW4EuBNKhlLJ5dbH/QRJYDniFELe0Ryw1
-        zy4l2M8lVX4IVLvccrDkD26WikG50PuxCQFdnkwEiSTcsFJvgcv2m6mB50DfUpu5FLAPV1ZQMZ8b
-        IvW7azZ//KsHo/R9nYA/OPXa3M0WXkbEI3Dus2z9lNsEjEngUv+4PdWrN6EKdpdVoMba1vqqHZkH
-        b+fNG4mbTQRmWGsFxIdzQM3Kfkbt1AUcBI3doc1xk9ZLJVoC3ClDSm3yBtl4AC8Bvk47CzunCbFl
-        aqkGQtGR0A74sT4HY8DDq8puaE3xHC1C9H7BD749CHUSFM03CxuwDd2YQD5eskks+B4idSLUZd1V
-        n+fOt2FzPT2pkptdNtu6EQD6Cg2sRFSr1/NdKvcmSu74EM8ioDerUyT9vHfIWElpvUwkz0F2c2e0
-        vXpNNvuXsQe81EdofRp6LfDVTYMNUUx6PtQEjL//y79kHiuu1mRzc3xWsDg6TwQepu6OOhkEae88
-        TKzIbykanVhZ5SOLI3zWZCmjogx6OCXDhAT9yuoulKYevMWdRl2+GOtu9W6a9CHZBxvBramHc8Up
-        MNsImCJ0jBgThDiA13A6U8UU5IxJ8keQGG8I2At5RecPahjD4yJBrGZgAl2aDgjGwQth47BVXR5l
-        eQyPQVnRMISPjMUvNgNJeRm4GC/BsMh0SsDUKRt6PB+LelHlIJCl9SYjYfewsjbe5Rb8MNvDONKd
-        gclhbEAMywgba6u762TdAkjVIkJrd3Pc9antBBgEgUIEXZPZdDzHL/hCTxEtOGkHtg5XBQiuvsUe
-        DR76a+oCCDe720rWtGncxT69JHi49BTbp/jo8vxe5mEjlx02733NVuNIb4BDao0PgNnDnOWLBoNH
-        YlB8ebb6ulyVUS5at8MW8c5DeVb2IdQv8RN7R9F02VEWRxBM2Yka77HVZzqLMbwdpBSJVyNzRymr
-        rY2zKwusPUQpIrNlFYC+AgOHmmCxbfbkS3mMeR47t0UB/ImJHvBP64C4GV/rebiFCKKw66h78mRA
-        twSKwOJ5DtvXng4ru62tlPsgx+63Hpep/Sgwm2cXH55jxNZzfL4BkkeYHPqNMVBkCSFkaL8isbq4
-        gPmml0AnmldsPYNbvYiZBwEcZhcHqV9my/bSWVDZRwOaUSyxWs4WT17k15keClcZmCRTHua8lmGn
-        2QTR9CDbEtabDUaSqLHoMsfUkgoo+WRNL5+oc6ruJqnc3qeeHIwRldNjBXb81aCHeE7ZOnKrAMs6
-        JeRZtn00qXIQwho5Cek+J21Y5/NJg547drRQwStaLreWg+M2irB7ZM96em4kDSiX65bsDjAeRv5o
-        FxDt+JEqUVmzWUkwhD23rthXls0wLRvTAWgnjGhV9/nQ77ZKLpUhxNTYmEs0LU5pyNKTK4gEBjmb
-        9N1DA/zhpmPNutz0JdZ8A3Kq4OOD8HnUtBma8M99fXOpaxLfHF56VUxFwtozfS10vYc5jhl671zD
-        7ayTOErIrC4EGB9xmPbVK4aBW2dorrdAXwN9HGExwJCikPu4zMx2BF6OmU6k0DCGuXWjXLKi/EVj
-        6cPYlD+EGSr704CPt/NnWBRijjBqDzLaXMIuYrvNkgIm5DYRWWXWs7XbOlC0e4/aBlcNzNn0PcyX
-        4YiA8UmHlRVVDBsOKvQU8Za+RmkqgcwZPIy2xgiWNNzOsBncC9Wt/D6Q7a0RwFsKrlhP44ixuK1z
-        mJ9QT93w2LqzFJocrO+tRA9G1NdLW18R7N2qIuLuRoalfTwrYMvjTOZvf1qorhBgHHuB6tK+cef9
-        dXFgBIUnqTt7x2b1/kkgi/oLavuDDKZdJdrSSqWeatz5zOa38EHAy7BPzYDYYAG9ToDs9yrhv/O7
-        3kQ7Br4WHLD71bdOeCgF5OhVRnJYTWDmzWCG7gXK2MxhmlH95s9gPrsaPvrPul6GduWhpZUdPp5a
-        N2PcoxThd/6pJrx1sN5EJYGnk8OhrdsLw7AUhgfdNssRF36WqOtJGUDH9I5Ym54LYx6gDjjipiH8
-        GzRgILEkwqnjJHqA2qGeuYfFwfO6a5Akth82c+RUwlZrZ3o+eHt3GRvZAiS7xPiwOw86I0WqASsq
-        XiiYHiqYL1AeAa34CTufxHKX61vUwIDHiR6bOM3owxV4MCXdhM3g4ej8RRs8OBlsR80VvrMlLdIW
-        3nfBgJXJ9tz3tXReEIKAYteXjtHylLwGevfXA59j+VMvt9vZhtKaythJKk0XnCFuwFefscdLJhtP
-        bPZkJd16JMolO2PGpChw674Q4QXqsDnzm1y69MuduvxWi3jyiRA8bz2Rekfxra/2W4JwSk0DR8G5
-        1ufr6Qkh+qQ+eX/1tputOYUtvzHJOnU2W80EImmTcBHa8Ks0LPYlTOC2O26o/yjs73qiyR9/5CVW
-        XM/LPJbgFFUB2QUiZatq6RUsJPVB5u/7FOIks+HhaliIPWSZjUXjJHB95C69U3DRp+zJV0BYbJ6c
-        0rAG7KffB6kosW/K7bCcmBVAk5Idtk/1h43h6CuSu79cUNTZF0DuYPSAWRkOmWt5dafuPqxwDdID
-        RuVRdZmcuCvciMlEXSW9slV1Zw74/rPCSF6O7uortgAJ6Z9oEndrNKLXksPMs2qqHhRNHxkALyhe
-        vC1GZr4b5lrqCYyO1pZaqcTrHXgVAbwcNiN267qsV2z2OZzsV0ldheJh1nrowBRr7/96fxetRvBU
-        azySmk2Qje1JEeHWbRD1YL9j1FPzFiaf2id9EunZ+pATGy59ZKNdIGLwez5wwnOGjbJ86Gy6lTG0
-        3vHtT723vJnOcCPGE3a//WnZVbMDY+7IYeWtGtkCWMtDn/VP9OaAoDMuSBLAKamAtdi26+UdVCv0
-        nxHGB0/P63arZ8p+P8aAjKfdFgxTIvYSSooQqy0NdRbWqgDezcajWno5RLO5X0W407WeOob7yGbX
-        OzcSnYH01e8SzHSeEyjPUkidgdcH5sqjBEs+7mgx4339HtpVgKfH1FBNSEyXP1qAg+vmiqj9XHYZ
-        M7o0gWP4qAhI1MWdw9HUYErUiXqqvrB5TIpv/QoT1qT7yBbnagRAfUgmthscg4UF6igp/aTR42ab
-        DvOYezYYNchh/bW/6qPJm7lUJCeGkjXjs7EWmAIN1/Cxsk+ygcwukCCIA4aNoHtHdMCnAOyPTwfj
-        G8uHpRh8Afh+XSGiOfXPn/HAj5CGBKa2jKJE4aExFh+qtJH4/X1eCEP9HpE9pYrO25u4grz+vmHn
-        5o4ZScclgGVVMNTZgLqtsWYljPJUo97xibOlPro3aXEDhUbcbR+tGZgVyNXeh6r5rEbjKh17OJ+P
-        GrX7gg0lW4sc7PjMoLb9GdksWoIEHTUryV5528OuhwUH6xzX1ASdWn/rPQbVkLwRj/kFLP6wjlB7
-        4hrJqDfA1m1OhmQJwZlG5XrK/ughamObmvrwZrPjDC0wN35GcQsUIDiLpsHwfD5SDfcO4B2nbqF0
-        0mqql+sSMRSebHghLwsHXVC79OfHp1ueYPu+J1EHl9oCxFsHqj9Tk9EPM3t4etAGH+73rT7LzeqA
-        0UjP3/mANT2MPJKm4XbCasRb7uI3fgjuZ/FEHfG0uuNmjGYQcy6HXpL6yKbaPdrwlzd1IWuHpZxp
-        DrFcINJ882XHrLEBh0tLv/mnGlbFPoYgDcQc65L7za9bQ4GOESJqQU8DW+tc3sCoPj/Y3Yk70FWH
-        aw4DeTeTfWVe69mSqwamD67E5tfv7OxeKCC+kopsK/uZLbOcIVDySUd21/eoz3TQJCg81itWlxxF
-        8x4VIQzoWiNxF16GOS9bAukzS4i8v1tgvVw3CkRvTsAq92n1dc3nVN5fNx15g04dhL0g3eDY2io1
-        Y/kzrKNRxrK6hCV2HU3Jfs8D4oGcsKY9Fn1BtL8BdFYAdeAxc8k3/8GnlgmoV/rRnRtzEX71RK83
-        q/35j1jKK/tNfdS/wHxvFQu8zWYlUXDW9bksHg7sbo6N3SRt2PrJsARffL9DrDcrdyBp38DPfCoQ
-        f38r2Swmai5/x1Nlu22jKaDFC7KovRDh5FTunBp3WwqCUKEqunLR3KVlKC+39YX4aUjBKD+NEX7X
-        P1r22UOfYzbeoDffTtS5uV7GErZW0h+9KQJDX0JBhkDfLQo1N09nmL/5Bhiu5VPjmqjD7tUYLSik
-        EpA6ZsqwO2VVDlKiT+h1KIaoS4ugBd/5or/1O3qBGcD0yV/oY5tifW0rGoKNadyRYFuBy0javwD4
-        NMo3f94zFtZH/ud/aELW/pvXRgluwfP0x68vh2tg/PG/1tpHOvXUuP/lETKpQslI5AkatGqgI5k/
-        3cGiawuE9VPSyfztZ+xZ1go8v8cYeyipavbzb/GjD6minXuXFLrbg7g01m8+7Fxat9oN4g+j1AIX
-        nH3rrwVj66gYJY9b1L8uLw1WtpqSLd6fM4YsLtj7fJNjJMIzWPL3ywMavozUupb20AfSoYILtDn6
-        84vELv0S5kpIkbjrpuwPfwmGjYQku8uBcFtvEiSkfRIQHludJa8PhEuyAei1trU708ER4SSHB3zU
-        W06fV9Ks8BxeD1SP0rSe57UP4VooPFbf1gHM6LUUcvp4GGT51gfbA1mE9f1YYLuRlWi9kgGB4C5O
-        9GAvtvu5yjoPz5pYY4zugst2+tOBumSH1LxHyJ0jyo9wauua7O3XNVtMO2tg7+V3IontAcxD/Jqh
-        ubwIvbc6ijrTqCXotpJIFc5FbHYvcw4vnNFj5z5u6mWWIw8qkt/Qg3cLszXnPR7IhVVS1XluMxI/
-        xBBAKeapW5ApY5301mBNDlck2h8PrMn7JIJFbs7UiJ8kG03B9cDxWdzx8aPVbOVUmUBouguxfbPP
-        mKjWNxhGYEWQj0/ZrJOa/62fnz7U6zPUUjgEbfdnfuf8VDgwy94HrMe+566L/+bhKPgIl7zI6U8h
-        mhrw3oHDL78z9s3nIqGvHDvGEjG25ftY+vYDrGsvvp6PKioBMFaMxML29UXfXRTw43nuLaBgvb6R
-        Bb/8B9FI74f5+RbKXx6jaJtVQ0f3Q7k/12cNB3nc6lRO1QoWAxeixi1BtPiNGUL+teGpbQvD0Pey
-        IoLp824JTO59NpNJ6SFVFEjawWh1VlbtDF/K3qUG94CMvqdRA6p7fP78l7twyyPYJ3ZlYr+ePjW5
-        vi0L1iVnozJc02hOHa2Rv36ILOUprpcj/tjw+rY+2Dm/d4xOJ92Tf/xJfTAB0N96JpxrUttQ02ht
-        xgDJ19gZ8c//rBN7QMDrJkedOVSzMWzPMdyOyoT2xn2pxy9fg21cNtP+vHPcHnGuBiEkFlW2mDHm
-        OfsZdpYAsMKLhT5eT08OjALpCfzsNLaquO1hcZgcwhwJuIvbXA1gb5wDko4XO1vEArbAvXAyteFh
-        cNnpLGvQng2dPkprqic+WlJZGe0r2fNmw358FBRJxMii6Zcf38x/+QXndfvSf/4QvJ6XHmvRvhtY
-        4D0k6W7A5Ntv+2H83oe2m2Y0g9D55rVAg/0oQiKxswB6Im0SiWxMheL9Z2LdMPYV+OWH42mjusTM
-        ux7MZltgMy0k1ke58gLf+aFq7nhgTjiQ/3nf2mVZh+HKGgIDeTtj7CQkI6qSWFAUP5i8u+d9oD1M
-        uP03X9JDFdpRb5XXGG4dZ0fN4NG7bMcXJehasqBebD9gXiW1lW9pvKO6ewrAt7+uwB1Ch2rlNAHW
-        8bsGfip0Ii/8Zjq7bo4N+PJq+s1/YHs+vnK4+YjoD+9dvFeWAF0cAT7l12Egx3qL4ErFnhpxiIf9
-        GV9FuM5Cg60mr4cF7oIS6s3WJFs327G1GVMEI3nOqbbfpdGojXsR7urHEYlfXracuM4B37z8zW9P
-        0FOtWIF9D05fvnZnzO65HIIXDfHXr331UirBTn1H1OCEsP7pgXQqh4rI85Vn6+/9LE5ikr3/rIcv
-        b7Z+/AEf4aq7c+ebKQDGjIkgVLk+7697B2qCpJGBuqCeOHbWwEswEI6mZpuRn14GhG/JJtKd+udX
-        4I9H+8dmZfP97At/+MzmxuAw4c/Og/sxAdTyzoQxJeBz8PE39pdv7/W3U3UpLDUlxt4NfMD4q9d3
-        lxT4y1N0iryBQLe95tRNPu9h0TYOAvBS6/T40XS2rHYfSycGKbVhcmRbAroQLgN5YG+gA+sfFkhg
-        2PYJEoT9AkZwfcdgE79V6pq+r/M6fwqg3qEL9peDEs1uqCtw95JK8tRufs1AUNnAOJxe1Do5mr47
-        inog/fR9zmPb/fILBRKXn7G3T/WMbu61DS89uyMAETeQjU57sG4yRIZZoe46n68KtNj1g621Z+54
-        VK0S2l6c4JsalD+9QeCb12mmcChbrdsg/vIZxpxfRayMCg++L0WLoDFCl11lXQDvs5lQnz/J7Mej
-        gZvUzc+/RuyRqSncZ1eFfv25y3/rWT6cT3eMkiCrd+mIE7BjoMX6+/OqWXWTX/CrF4QT4ZbNh+3m
-        9ocXWf1QZXMfbC3ocXBPvTPl2Ki3XAo43q7oob/OP55syGopqPSX10lTAQPoUS1SWynf7penoD9+
-        6dSdrXoXk1SERg71n37UfSY4DfzuT2C9I162Oz1CBxo599O/dlhF5hB4E5cEF8MCAG2WbIR5sb38
-        /HJEj2pbwN4r7ljV9B2YuQeCkmJtEsRzjxysxZ4UkJ6klSoXdacT64RmcNw8O3pQjIFR7TlDuM2s
-        FStqumEL3KUV7EygIMsbXwPtD3tJEh6BjP0xnPSfvsBbAkpSfCIuY0HoJ0AXLh2av3x6Fpw1he5B
-        1bC2zPMwvgXqwaOPY4pbfxvN8f4kyE8zeFFzIyqR8Ov/H1+2qdL2ZOgVWw3+jDfubyXaYWfiwIdc
-        P9SrpHR4PbeqAdqoGagenHWXLP7E//whPpyTKWNfvyh/88mf/YWV2h4C1s4LsDMgqtP4YSXQo/mZ
-        BhMph13Udx7cbZMNgS/ryabuo4jwiFyMcXRTsuWbp6BUPg/kQ1EdLQFNGrgxrTs2pE8E+tsaSvAy
-        te6Pp4AJLoMB9XiDsdtMhb5uu30KN9GxR2y6JMP84rcB1IVzh7oqx9my9ZAnhfvXif78ycKUjQPS
-        zb7+7S8w8kQ3AkVJawjvbIp6XuUlgbzURmQP19plV9aMsBssHZtA93Xy88O/vK+ViaiP0r0U5K8f
-        psahcKNZcKQbbFwUY6x2oT6/KBbAb/9HxyWuZ+mZVjByKo/65oV3R/zwNPjjZUyITsMo908e3LVD
-        S/g4pDWTkOj94Y+XdHOpZ16wbLgRhSOST/CarSMnCWDevp/426/An/xvc+1Av+uVzXIj2dI+Fy5Y
-        iY7IpZddj8D+qhK0+er7aqR7CAso+kRsmr6epQu7yTW2Ttj/wCaaP5z1gostEqpc0hHQIuo18OXZ
-        ZJGO/cDsXsjB8T4w0hqqGHV0k3I//4rV6D5n9P1CEjjs9SO27mrGGA6iFGZw80Q722U1WY6cLe2U
-        LsV2RdRhXvkcwfAyZjTcbnBGfzx4t26m335a9NvvBV8egY+k58A01GYKv/yY+rMj6N3LA9ZPn7AD
-        d80wbMWbAr/9AvuqoLBp3r1n+M1zROhj7+tPrQpu1BNP3nZaRUtyaEZ4xK+G/Pj1ck2mAv78uTek
-        gt5utrMo/fTLFHiSrVn/GeUfn4y/ej0XVdjCe5xLGD0kTWeKb8ywAsz4+jPObVM8a/CsSTVG/srp
-        0zBWJfyUq0Qkv/m4q+ynrz/1AGrPYaszxC8Q5I8EzdrZ0dmLditYrhcfW5X/YqOPDhW8XVf05XOb
-        aC3sxYITjD2qLM1xYCu1R2guDUFSv9tnP14n9/dbivFxkw5ffbaBwCqLKi/j5tIHbsr9ZVOpWHck
-        oLPrPnZk8zsT6BNx0dgdzyOA1tum+uodwWrdakn8+3cq4D//9ddf/+t3wqBp78X7ezBgKpbp3/99
-        VODft/vt3zwv/JsKf04ikPFWFn//81+HEP7uhrbppv89ta/iM/79z1/bP6cN/p7a6fb+fy7/6/td
-        //mv/wMAAP//AwDOXgQl4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c09bf823fb50b70-AMS
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 17:29:41 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-kd1j0bcill5flig1m29wdaof
-      openai-processing-ms:
-      - '69'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 555d4ffdb6ceac9f62f60bb64d87170d
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding_large_context.yaml b/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding_large_context.yaml
deleted file mode 100644
index b6d6a75b..00000000
--- a/tests/integration/cassettes/test_llm_utils/test_get_ada_embedding_large_context.yaml
+++ /dev/null
@@ -1,1484 +0,0 @@
-interactions:
-- request:
-    body: '{"input": [[5289, 564, 71, 773, 89, 2332, 19747, 87, 664, 71, 8311, 85,
-      392, 25299, 11032, 940, 89, 85, 398, 80, 73, 5481, 48558, 86, 1919, 1634, 8890,
-      5346, 44185, 53060, 450, 392, 68273, 64145, 511, 77, 80, 3696, 71, 2042, 28990,
-      44490, 19456, 89, 21807, 44490, 6331, 3180, 23361, 71, 455, 76, 583, 87, 21436,
-      34695, 352, 70, 953, 278, 59524, 2857, 93000, 641, 6043, 73, 70, 36463, 7141,
-      21807, 391, 1273, 8536, 566, 71, 7513, 580, 263, 936, 10333, 86, 983, 822, 9700,
-      73, 3316, 80, 1320, 365, 27278, 564, 67, 12591, 3576, 36851, 2465, 1739, 657,
-      6375, 89, 23361, 6885, 352, 88, 14046, 292, 70, 32204, 648, 300, 73, 32547,
-      869, 20854, 28679, 89, 11805, 70, 9081, 80, 11251, 87, 28679, 6194, 85, 906,
-      64, 300, 16501, 70494, 6511, 51622, 87, 80, 8462, 295, 13536, 49463, 604, 64,
-      333, 79, 302, 5469, 36068, 267, 5289, 19870, 911, 71, 587, 4912, 32868, 64087,
-      22650, 89, 3368, 83, 50798, 391, 273, 365, 72, 1233, 604, 3858, 48380, 710,
-      6375, 93000, 3013, 427, 7796, 66, 11160, 77, 10910, 85, 4777, 5969, 276, 7717,
-      87, 71, 21325, 80, 73389, 3576, 86, 29238, 544, 1026, 31019, 20218, 3524, 64,
-      7270, 7783, 80, 1498, 77, 1739, 5979, 327, 49450, 1791, 36409, 86, 582, 894,
-      73, 85, 89, 2174, 87, 40494, 20824, 40078, 89, 80, 4317, 1609, 85, 3601, 73,
-      86, 36068, 894, 56871, 89, 4680, 67, 2562, 1494, 6331, 16017, 2332, 21046, 86,
-      11823, 18854, 85, 10616, 85, 23913, 73, 86682, 441, 1494, 360, 1978, 3013, 2562,
-      511, 86, 427, 5298, 81, 2580, 89835, 14694, 86, 3059, 26738, 65736, 84, 1394,
-      4458, 677, 85, 3368, 71, 15479, 391, 713, 35531, 566, 94869, 325, 14029, 52360,
-      80, 406, 1290, 10616, 79, 773, 3315, 365, 89, 73, 2111, 13045, 73, 89, 14694,
-      710, 95210, 1804, 79, 20824, 80, 4086, 19555, 936, 1091, 301, 936, 1494, 73,
-      10784, 1029, 77, 1302, 1310, 86, 80, 24752, 89, 73, 89, 1302, 343, 38977, 324,
-      25457, 9902, 88, 4168, 67, 3841, 953, 96518, 4777, 3696, 80, 61057, 90563, 80,
-      20127, 86, 3418, 24672, 80, 796, 88, 85, 1026, 80, 8910, 285, 7864, 406, 14694,
-      454, 361, 85245, 83, 664, 43210, 3368, 27278, 9832, 89, 5010, 89, 762, 86, 19747,
-      299, 23808, 69057, 80, 4922, 20211, 71, 73, 404, 89, 1395, 830, 939, 5298, 402,
-      83, 80, 70, 1631, 97582, 3306, 7387, 73, 89, 2034, 66, 3906, 53060, 339, 343,
-      582, 2465, 80, 52926, 2642, 1739, 69057, 3906, 13649, 85, 3178, 291, 66, 267,
-      67910, 24672, 2201, 2933, 34175, 4777, 23361, 10784, 73, 764, 1517, 87, 12825,
-      49755, 24752, 89, 265, 307, 85, 80, 689, 332, 1331, 76, 1031, 1658, 325, 2303,
-      36851, 87, 8892, 365, 87, 402, 17606, 80, 12407, 4341, 85, 78498, 370, 3074,
-      455, 44183, 79224, 830, 20811, 906, 361, 73, 2580, 80, 359, 258, 10753, 2329,
-      37406, 50139, 67702, 10616, 56029, 7513, 2438, 402, 3258, 80, 22491, 4748, 359,
-      41129, 2034, 11032, 1658, 65, 3714, 65, 1919, 40153, 363, 2580, 52333, 73, 87,
-      80, 45015, 4086, 3141, 69, 392, 76, 19747, 21486, 708, 88, 1273, 21486, 85,
-      764, 67, 16373, 4223, 641, 53060, 784, 8977, 73, 85, 1739, 6043, 321, 89, 18571,
-      49450, 32589, 450, 88, 2303, 62497, 49595, 80, 49755, 1494, 80, 302, 2689, 87,
-      29238, 89, 1551, 8088, 76, 20926, 87, 2034, 66, 785, 22873, 53060, 8480, 708,
-      88, 906, 73, 4680, 80, 22119, 89, 398, 78498, 1919, 67, 64087, 318, 24409, 869,
-      754, 20990, 1498, 23760, 648, 728, 89, 22619, 29224, 1216, 2933, 85, 1386, 8587,
-      7737, 87, 17043, 24990, 70561, 47171, 6375, 67, 1073, 85, 89835, 3933, 85407,
-      564, 38359, 3647, 60338, 89, 17008, 10079, 80, 385, 1394, 32837, 1247, 14170,
-      74, 936, 1658, 87, 73, 365, 73, 21807, 76, 50139, 2629, 20568, 80, 1609, 5241,
-      21206, 96518, 301, 36722, 2249, 74, 581, 75, 641, 1494, 31019, 6780, 967, 361,
-      288, 77, 49755, 1631, 73, 11160, 20990, 876, 4511, 69, 675, 78, 352, 15809,
-      363, 65, 9110, 20990, 2034, 82, 544, 28546, 939, 73, 37227, 266, 70, 3013, 7911,
-      365, 14625, 65, 3841, 62559, 69, 2658, 76, 2302, 41922, 383, 347, 75, 3172,
-      784, 634, 89, 26554, 74, 75406, 544, 71, 1146, 20926, 10784, 32589, 71, 894,
-      64, 2319, 10784, 509, 15720, 327, 2701, 45015, 89, 344, 9810, 71, 344, 29700,
-      2194, 5308, 303, 85, 23361, 402, 86, 939, 283, 6870, 2005, 73, 1919, 5308, 858,
-      18854, 74, 11032, 911, 65, 80, 10784, 3576, 4223, 5289, 69, 2249, 37406, 44508,
-      89, 2739, 80, 70, 80, 10462, 80, 23001, 31019, 80, 40429, 9092, 19072, 80, 56102,
-      15444, 598, 30986, 85, 23866, 3933, 67, 1494, 86, 21325, 73, 2580, 18571, 675,
-      19239, 876, 352, 24990, 87, 1336, 14029, 78, 762, 9258, 2319, 9081, 87, 24244,
-      50536, 15720, 668, 85, 359, 86, 652, 70, 73, 70, 675, 355, 1725, 3696, 65941,
-      295, 93797, 9081, 1273, 49891, 830, 581, 360, 302, 89, 14878, 87, 80, 73, 44067,
-      86, 80, 5544, 49450, 7141, 65, 2465, 70, 344, 49463, 303, 10616, 3172, 906,
-      74, 1658, 9832, 88564, 65, 80, 1216, 69, 89, 58153, 9832, 85, 4168, 32204, 2067,
-      2465, 773, 73, 28774, 89, 5308, 18571, 49463, 300, 664, 14694, 3178, 71, 38844,
-      80, 876, 13423, 65, 1146, 87, 34175, 327, 1394, 68916, 302, 74, 78498, 22016,
-      450, 65, 2005, 7141, 80, 352, 31764, 73, 49865, 641, 16684, 17692, 2067, 9697,
-      28679, 73, 85514, 80, 337, 1804, 939, 84, 80, 906, 15618, 69, 8671, 894, 385,
-      89, 318, 13028, 18458, 70391, 89, 12328, 89, 5010, 49404, 285, 764, 32868, 3423,
-      70, 5192, 73, 70, 80, 24244, 566, 3172, 346, 31764, 89, 1273, 75, 3427, 87,
-      80, 38361, 1631, 4714, 78930, 21807, 24990, 40078, 86, 3906, 1310, 70, 406,
-      80, 360, 1100, 87, 2032, 73, 49865, 668, 37406, 6358, 24244, 6634, 265, 1100,
-      64, 16711, 822, 80, 52926, 8910, 3059, 1247, 4922, 87, 24244, 16400, 1729, 70,
-      1320, 427, 85, 355, 22524, 42908, 1729, 8510, 80, 89, 26929, 1897, 5230, 363,
-      80, 858, 89, 80, 64087, 637, 80, 48480, 69, 18577, 2303, 307, 818, 41129, 953,
-      66, 2912, 2067, 73, 822, 8671, 1247, 22619, 1073, 383, 67665, 8212, 752, 10759,
-      23866, 71, 1026, 89, 26929, 50139, 71, 16274, 8462, 82, 764, 391, 318, 74, 2465,
-      9832, 3013, 713, 16400, 89, 1065, 86, 39911, 74, 773, 81, 2042, 77, 1029, 9701,
-      22524, 80, 24672, 71, 22619, 76, 65653, 2034, 73, 581, 4748, 17008, 1320, 6634,
-      1498, 85, 80, 73, 85, 402, 67800, 637, 77, 820, 302, 12082, 4657, 831, 437,
-      74, 31881, 89, 11328, 9117, 80, 6358, 343, 363, 5964, 65, 546, 85, 32478, 1498,
-      87, 84, 454, 295, 3933, 88, 762, 1394, 69, 677, 96518, 88, 25299, 1098, 764,
-      3919, 447, 82649, 3423, 70, 566, 2249, 89, 302, 2201, 88, 983, 1498, 1320, 333,
-      3368, 34175, 84, 392, 87, 71, 16400, 93000, 8186, 27752, 74, 2465, 2642, 7141,
-      74, 11823, 11927, 80, 18499, 454, 85, 9907, 1662, 4171, 12273, 2706, 36325,
-      89, 7387, 65, 4922, 20926, 89, 23576, 73, 27515, 80, 86611, 9991, 333, 343,
-      2881, 20990, 3423, 540, 74, 796, 3013, 89, 85, 36068, 14485, 10056, 14878, 27515,
-      2465, 1026, 89, 2332, 303, 76, 28927, 43210, 3306, 81, 1658, 3576, 327, 292,
-      76627, 3415, 351, 75, 447, 89, 2302, 291, 75, 4086, 53289, 21703, 89, 392, 2042,
-      677, 3013, 70, 73, 784, 89, 14878, 6358, 81, 17156, 78, 582, 24752, 9996, 68054,
-      2312, 18571, 906, 830, 76, 344, 263, 87, 4680, 83, 12498, 65019, 4912, 65, 346,
-      10644, 75, 9902, 45228, 564, 73, 13423, 6331, 39911, 24235, 774, 74, 6789, 85,
-      1919, 441, 4748, 273, 28679, 25299, 41922, 1073, 68475, 18571, 3978, 89, 675,
-      66, 1897, 361, 37406, 9810, 53835, 66467, 87, 74, 1729, 894, 61057, 564, 81,
-      27515, 728, 86, 2562, 652, 73, 1336, 2739, 675, 71, 1897, 869, 677, 675, 86,
-      41796, 73, 637, 80, 24752, 2319, 1498, 8671, 28996, 13671, 9110, 375, 450, 1347,
-      69, 689, 72, 1100, 51318, 1609, 2042, 69, 303, 3933, 69, 1347, 8318, 86, 3647,
-      74, 710, 85, 4680, 24012, 278, 89, 70, 788, 7911, 28679, 70226, 41796, 2174,
-      57208, 11328, 292, 5308, 21888, 13536, 5308, 982, 65, 375, 820, 564, 32962,
-      8998, 2438, 74, 15479, 51622, 8587, 283, 2303, 67, 2857, 347, 372, 11823, 65,
-      303, 631, 77118, 92216, 3696, 65, 80, 2329, 4341, 74, 6200, 73, 70, 12591, 87,
-      80, 39911, 9902, 1320, 7387, 838, 56871, 61318, 86, 34175, 12328, 46082, 73,
-      87, 4341, 75406, 36825, 80, 16284, 12940, 13752, 70, 73, 88, 5544, 67, 75092,
-      30683, 80, 566, 65, 675, 84, 70678, 375, 511, 70, 74, 50900, 2465, 88, 9081,
-      70, 324, 80546, 7387, 24672, 7501, 87, 4511, 38977, 69, 73, 27278, 303, 2025,
-      5979, 4317, 915, 14170, 80, 9978, 12825, 32204, 1310, 14878, 89, 13423, 11032,
-      27515, 13536, 80, 7369, 86, 339, 14878, 89, 28531, 2303, 8587, 73, 85514, 501,
-      80, 501, 427, 4777, 45228, 939, 85, 774, 87, 6789, 4867, 19456, 71, 6885, 455,
-      75, 728, 65, 303, 675, 81, 3172, 72, 20629, 72, 587, 302, 86, 89, 3696, 86,
-      8480, 49463, 869, 295, 73, 385, 80, 73, 1658, 13183, 87, 94908, 8480, 3601,
-      1546, 99355, 66, 6194, 5192, 77, 376, 73, 88, 1729, 85, 329, 19285, 31268, 406,
-      641, 1463, 76, 392, 27780, 10470, 347, 1029, 22524, 376, 69, 22016, 86, 784,
-      288, 36851, 85407, 10056, 87, 6870, 9092, 292, 84, 1354, 70, 604, 723, 876,
-      80, 51759, 1320, 4922, 2171, 66, 22119, 85590, 85, 365, 65, 12328, 69, 283,
-      73, 86, 67800, 713, 309, 5308, 8892, 84, 554, 2329, 60933, 80, 74, 332, 86,
-      5308, 2042, 83, 652, 39152, 275, 69, 8783, 73, 28774, 24672, 87, 3893, 370,
-      79, 1662, 81, 24752, 3178, 20824, 71, 31019, 80, 78, 80, 21659, 1026, 301, 675,
-      2701, 76, 8671, 51622, 4214, 8311, 87, 80, 295, 12825, 89, 303, 5964, 92512,
-      784, 74, 99066, 31019, 97523, 454, 93000, 8671, 581, 50922, 80, 634, 77, 3893,
-      18854, 19239, 18631, 75, 50139, 7488, 455, 41129, 7453, 80, 4171, 86, 16618,
-      25105, 4341, 10776, 5683, 360, 9810, 89835, 1791, 31881, 70, 7050, 34106, 12825,
-      17134, 983, 27515, 74, 34175, 8050, 7488, 10910, 84, 354, 299, 2332, 87, 18244,
-      85, 441, 710, 13423, 2332, 70, 2032, 68, 2319, 73, 89, 764, 1604, 35555, 39152,
-      40078, 8050, 73, 2234, 65, 575, 1800, 38361, 73, 10616, 14878, 49450, 3919,
-      20369, 6375, 1725, 86, 8462, 325, 49755, 347, 83, 73, 87, 7513, 89, 830, 12328,
-      71, 8890, 97523, 303, 1631, 83, 70391, 29684, 1031, 87, 752, 31881, 1320, 4239,
-      1347, 784, 49450, 3576, 6591, 70494, 664, 2203, 2329, 86, 80, 36708, 80, 70981,
-      85, 1764, 80, 7047, 796, 78, 1073, 263, 7501, 450, 375, 16820, 73, 1310, 25457,
-      80, 7488, 65019, 1026, 355, 73, 14606, 89, 325, 295, 447, 73, 291, 69, 89, 36238,
-      911, 66, 14092, 3013, 344, 77, 398, 4086, 88, 12412, 53835, 7387, 66, 1551,
-      87, 73, 604, 73873, 1631, 1517, 318, 13009, 74, 376, 89, 8050, 664, 4193, 2000,
-      87, 74, 4086, 454, 8890, 73, 89, 32547, 3919, 10333, 554, 63643, 89, 327, 80,
-      784, 88, 3988, 13884, 664, 73, 88, 22119, 10196, 80, 8088, 41796, 343, 85, 28679,
-      65, 8998, 11032, 1662, 361, 56029, 3368, 36851, 72245, 2034, 14878, 87, 2319,
-      69, 73, 4942, 80, 70, 34097, 67, 406, 62497, 17156, 869, 1546, 7141, 10616,
-      80, 1729, 87, 68156, 1662, 10630, 4922, 15930, 11160, 55109, 74, 25299, 73,
-      59524, 579, 12825, 86, 822, 454, 77, 4171, 58305, 1517, 12498, 77584, 5192,
-      31764, 3716, 675, 383, 21486, 291, 8998, 11823, 321, 19639, 8587, 309, 66565,
-      3635, 3013, 89, 906, 3418, 7759, 18894, 89, 762, 275, 1658, 3933, 398, 22016,
-      337, 747, 2249, 56029, 566, 94869, 2249, 4458, 670, 65, 16220, 89, 8050, 8587,
-      85, 80, 301, 74, 511, 266, 79, 6194, 331, 87, 540, 6410, 1494, 1273, 4484, 4341,
-      1073, 283, 11377, 84, 3935, 89470, 80, 70, 292, 76, 1105, 2642, 20824, 87, 32837,
-      303, 12825, 4942, 406, 80, 74901, 44067, 89, 21206, 15618, 1065, 77, 2445, 2580,
-      73384, 5010, 38181, 1065, 354, 77, 5972, 664, 82999, 689, 2302, 1910, 74, 1791,
-      258, 1810, 71, 7006, 85, 953, 8587, 80, 501, 377, 77, 2739, 361, 25123, 54761,
-      2005, 307, 96518, 22619, 1494, 76, 1146, 18442, 14878, 2201, 30148, 11949, 85,
-      13092, 728, 1065, 30506, 29684, 14878, 13183, 14878, 65, 8088, 86, 19870, 86,
-      544, 85, 11160, 1498, 69, 89, 5104, 71137, 28774, 331, 1031, 79, 91410, 80,
-      29224, 49450, 93000, 5964, 1394, 8890, 84, 80, 42908, 10176, 953, 11251, 24672,
-      87, 355, 55233, 25100, 74, 4511, 16400, 20211, 17137, 3306, 20990, 372, 13855,
-      309, 89, 47689, 2701, 1910, 20127, 363, 80, 354, 637, 9117, 329, 50864, 427,
-      80, 278, 89, 708, 343, 62369, 1302, 16400, 73, 20191, 3576, 16618, 70, 302,
-      69, 392, 8480, 764, 65, 80, 321, 377, 675, 6489, 3059, 84, 80, 85514, 4223,
-      69, 12328, 74, 6634, 6358, 17043, 1739, 89, 21807, 641, 67492, 1336, 49595,
-      4341, 17008, 710, 9701, 87, 797, 92869, 5418, 2469, 60013, 377, 564, 28679,
-      1897, 50139, 418, 87, 11253, 329, 78498, 265, 4239, 377, 2329, 20926, 49463,
-      2580, 8212, 283, 3841, 46894, 762, 86, 7047, 462, 80, 47928, 80, 1331, 85, 451,
-      20568, 80, 3172, 27093, 43210, 2445, 40078, 1026, 89, 80, 359, 75, 360, 7501,
-      5469, 710, 6358, 677, 74, 5469, 80, 5192, 71, 14029, 94055, 325, 8890, 383,
-      52333, 85, 2008, 74, 7488, 36415, 12328, 74, 713, 80, 2302, 41622, 11253, 80,
-      784, 89, 501, 4937, 21206, 89, 3013, 74, 710, 86, 564, 1065, 81, 27455, 359,
-      81, 708, 347, 70, 13183, 2554, 88472, 28679, 80, 1494, 82, 8480, 7439, 86, 652,
-      34175, 74, 13423, 39911, 455, 21807, 953, 66, 4223, 14460, 81, 38359, 93000,
-      14736, 66, 7759, 68, 3524, 336, 71, 61952, 329, 7369, 28927, 581, 77, 303, 42818,
-      331, 14606, 76, 3172, 1026, 11089, 52971, 80, 20824, 73, 16276, 6194, 89, 18577,
-      677, 70, 331, 1551, 87, 86, 7387, 773, 37406, 2411, 355, 355, 4912, 85, 80,
-      1273, 39911, 31721, 9907, 376, 20191, 406, 2249, 869, 14170, 1336, 2438, 1551,
-      1347, 8088, 86626, 80, 2303, 80, 10616, 10776, 65019, 21659, 41196, 333, 989,
-      8050, 10011, 581, 509, 67, 3714, 1026, 80, 69, 1804, 75, 13565, 31881, 89, 352,
-      87, 68054, 363, 84, 3178, 2727, 710, 42848, 77827, 2303, 72, 332, 784, 273,
-      45015, 5230, 3601, 292, 454, 36722, 566, 343, 318, 1864, 2042, 2554, 333, 44508,
-      87, 85, 48029, 20127, 3172, 953, 71, 29684, 1310, 69, 657, 12825, 34175, 329,
-      3178, 66, 2465, 80, 34175, 73, 360, 283, 73, 20211, 830, 8088, 85, 80, 17851,
-      73, 11377, 1030, 69, 1498, 85, 4086, 8050, 67, 10616, 45283, 86, 5481, 80, 38359,
-      22580, 84, 7453, 581, 830, 70, 4168, 675, 89, 70, 1919, 75, 604, 74, 664, 12591,
-      41625, 31603, 675, 52926, 35401, 17008, 39152, 581, 30407, 9802, 89, 38977,
-      6151, 86, 39749, 52767, 24672, 89, 12082, 73, 88, 4341, 73, 1026, 16400, 12825,
-      16373, 564, 4657, 80, 354, 8462, 14029, 2003, 53060, 80, 17708, 1609, 87, 959,
-      69, 754, 89, 2957, 544, 19456, 57208, 20211, 9991, 71, 18244, 74, 4355, 33863,
-      16400, 81, 10784, 69, 575, 7783, 1804, 89, 4010, 798, 5544, 1273, 69, 19456,
-      89, 7047, 4835, 65, 80, 19747, 455, 6194, 1336, 76, 75406, 3055, 587, 70, 80,
-      4086, 10776, 85, 11828, 73, 451, 42908, 2249, 73, 50139, 1336, 79, 5735, 566,
-      3906, 73, 614, 87, 86, 1302, 352, 70, 80, 302, 83, 14912, 80, 70, 20926, 23866,
-      2562, 83, 16468, 277, 10002, 2562, 15930, 73, 6780, 648, 4458, 70678, 22619,
-      76, 579, 74, 19072, 84, 566, 89, 784, 12591, 363, 47689, 383, 1263, 86, 58305,
-      371, 76, 2200, 2203, 5010, 3919, 67, 13028, 346, 582, 5241, 71, 2042, 4239,
-      73, 7783, 1729, 70391, 2249, 15930, 2727, 2005, 4912, 46341, 1216, 75406, 14736,
-      69, 332, 18596, 347, 75, 3933, 3055, 27960, 86, 89, 265, 1100, 9810, 1100, 869,
-      36238, 1804, 85, 12328, 12825, 80, 32962, 39911, 8385, 80, 93797, 14029, 77827,
-      418, 2303, 361, 65019, 954, 86746, 953, 52971, 540, 3716, 363, 89, 4680, 80,
-      8385, 318, 544, 5683, 1791, 80, 1498, 79, 316, 10196, 80, 14088, 347, 3696,
-      80, 4991, 83, 2174, 50226, 65, 89044, 17692, 7911, 80, 5104, 4381, 752, 32204,
-      1331, 66, 3306, 21486, 73, 88, 1320, 75, 20824, 87, 11823, 88, 2701, 5010, 87,
-      86, 5192, 32962, 784, 3423, 4055, 1498, 3178, 301, 80, 3716, 1216, 818, 48380,
-      8035, 285, 588, 65, 540, 15770, 83, 7387, 785, 86, 3576, 2302, 52097, 7910,
-      88, 38359, 45015, 13536, 3059, 66443, 10462, 80, 1498, 21325, 73, 1729, 4777,
-      22619, 73, 28990, 89, 29700, 3427, 728, 344, 11805, 267, 86656, 392, 7513, 831,
-      7910, 391, 33539, 9117, 300, 4341, 8783, 869, 2203, 2249, 85, 2042, 1631, 37406,
-      2329, 70, 80, 3447, 1662, 13223, 57208, 11089, 65019, 73, 10776, 81, 302, 4168,
-      1411, 450, 49712, 80, 8050, 3251, 3423, 53016, 70, 447, 86, 2117, 352, 48045,
-      17063, 86611, 1310, 89, 587, 652, 32962, 60013, 3933, 14170, 87, 1031, 97523,
-      675, 44067, 5104, 77, 45015, 333, 8050, 70, 80, 525, 404, 87, 392, 41796, 69,
-      24752, 3696, 441, 30986, 49463, 21436, 67, 7387, 44508, 87, 3055, 675, 14606,
-      69, 894, 2715, 84, 83438, 73, 5673, 6358, 354, 2445, 34854, 32547, 73, 23361,
-      5308, 4086, 1631, 1551, 68467, 77, 45015, 73, 89, 70, 6733, 447, 333, 3647,
-      66, 22119, 535, 73, 86, 1498, 86, 4080, 88, 73822, 365, 41982, 454, 20127, 80,
-      1336, 392, 830, 75, 10776, 6723, 80, 74, 2580, 51924, 40261, 2042, 19275, 983,
-      86, 869, 82, 62497, 86611, 822, 64, 5171, 73, 6292, 19571, 1302, 27093, 370,
-      79, 14773, 447, 61057, 89, 80, 70, 83256, 80, 28546, 89, 80, 85369, 28679, 74,
-      3418, 283, 74, 89, 3368, 85, 953, 87, 352, 15618, 23265, 3576, 625, 784, 65,
-      318, 1197, 359, 88, 4171, 44567, 71, 46341, 2032, 16373, 354, 88, 78498, 10910,
-      3906, 85, 354, 64087, 2445, 85, 17134, 6511, 6375, 89, 19747, 65, 80, 581, 87,
-      1289, 31721, 8934, 752, 12591, 11949, 80, 1634, 12082, 333, 89, 33863, 24990,
-      5308, 67, 3841, 12328, 44970, 73, 25457, 85, 764, 8671, 35401, 2067, 73, 42848,
-      454, 80, 89, 1347, 4835, 89, 19239, 80, 31695, 511, 8480, 309, 5308, 77, 2329,
-      22119, 73, 8890, 1411, 1273, 69, 2302, 61828, 75, 13856, 5230, 33721, 1030,
-      327, 20191, 16276, 52926, 24244, 71, 876, 76, 1658, 52971, 74, 402, 69, 418,
-      42848, 73, 6358, 38828, 28774, 302, 79566, 49463, 79, 1791, 85, 8998, 52097,
-      80, 30506, 564, 89, 641, 375, 84, 2580, 41221, 4991, 36851, 8050, 796, 2332,
-      87, 74, 18571, 906, 288, 360, 6634, 85, 80, 73, 9112, 1910, 74, 10056, 86, 85,
-      12940, 51622, 1130, 86, 16618, 344, 73, 11823, 351, 3315, 2319, 22580, 37762,
-      80, 7521, 81, 376, 79, 24286, 337, 71, 9907, 8480, 94055, 3906, 1395, 80, 69,
-      9117, 85, 41796, 18442, 71, 44508, 339, 38359, 33367, 8587, 77, 7501, 5298,
-      5241, 5701, 86, 14668, 5455, 45015, 37975, 71, 632, 8890, 27515, 28679, 2580,
-      50536, 1347, 6200, 26397, 376, 8462, 73, 998, 295, 346, 88, 20990, 18442, 87,
-      1336, 74, 17134, 87, 73, 70, 80, 14170, 87624, 85, 3696, 69, 4239, 86, 85, 40924,
-      74, 818, 69, 75406, 24244, 566, 32962, 80, 675, 73, 88, 68054, 2249, 65, 344,
-      2465, 652, 3306, 82999, 78, 7453, 363, 27278, 41287, 427, 89, 324, 1331, 484,
-      69, 2034, 3418, 652, 32962, 70, 10470, 71, 3906, 28679, 45062, 2465, 20926,
-      17008, 876, 1631, 544, 87, 14912, 27093, 18287, 85, 32204, 35734, 69, 1031,
-      73, 566, 80, 2676, 72, 5308, 42528, 17008, 3906, 60013, 33367, 28774, 85, 3315,
-      64, 316, 89835, 89, 4171, 76, 1551, 20990, 89, 316, 713, 80, 1100, 20824, 19456,
-      80, 70, 21620, 77, 8892, 12407, 455, 86, 93000, 34152, 275, 73, 10036, 9490,
-      352, 83, 6632, 278, 377, 65, 2554, 337, 309, 3919, 74901, 18442, 22506, 2580,
-      7501, 74, 80, 40229, 12825, 86, 5972, 85, 8212, 336, 3576, 6151, 80, 4942, 74,
-      87, 80, 25337, 71, 2034, 80, 3933, 5972, 13536, 11285, 38361, 89, 80, 38844,
-      89, 2562, 89, 89687, 1551, 14694, 14606, 59524, 1662, 81, 764, 278, 59524, 652,
-      3013, 747, 454, 25299, 87, 1551, 2465, 9081, 67800, 73873, 450, 339, 76627,
-      53450, 89, 65116, 511, 747, 360, 89, 677, 86, 49568, 6511, 8587, 8587, 5781,
-      9081, 89, 4168, 83, 80, 23001, 55282, 831, 10616, 406, 3633, 2249, 18854, 830,
-      80, 74, 501, 363, 3696, 1791, 85, 28927, 17207, 73, 16820, 80, 28927, 441, 89,
-      15479, 86, 327, 76, 1897, 575, 69243, 4991, 657, 70, 32589, 83079, 36463, 89,
-      2249, 677, 86, 1919, 20510, 85, 383, 20103, 352, 73, 85, 8783, 78, 80, 46341,
-      6358, 764, 78, 28679, 85, 89, 28774, 69, 33863, 20211, 93141, 2201, 71, 869,
-      76, 447, 8311, 1897, 85, 89, 80, 23361, 72801, 4748, 11949, 544, 637, 86746,
-      1910, 20211, 6200, 86, 437, 52552, 66, 60933, 1872, 14088, 501, 59524, 80, 70,
-      10056, 582, 14170, 69, 20926, 752, 1411, 91943, 14170, 89, 3172, 13423, 59524,
-      564, 343, 3172, 67702, 25299, 2034, 73, 1100, 80546, 1658, 265, 773, 65, 16400,
-      86, 830, 87, 20926, 509, 44183, 73, 299, 71, 78512, 9112, 1804, 80546, 19747,
-      80, 634, 80, 1082, 85, 5972, 13423, 266, 15618, 86, 16400, 64087, 321, 1551,
-      277, 80, 3893, 68054, 708, 68, 354, 23361, 65, 18577, 79, 2303, 73, 57208, 1910,
-      89, 17043, 1910, 302, 17063, 73, 377, 12407, 84, 7488, 55233, 50798, 398, 73,
-      10776, 49595, 80, 3632, 5308, 16276, 50676, 454, 44970, 2329, 22119, 72801,
-      2319, 70, 785, 71, 18244, 74, 28679, 87, 1072, 383, 89, 15720, 85, 1286, 8587,
-      57208, 27278, 668, 20720, 546, 3647, 73, 361, 9490, 1919, 95328, 85, 10084,
-      67, 1026, 20824, 25457, 17008, 85, 5683, 347, 343, 784, 544, 998, 2303, 25453,
-      81, 2171, 86, 441, 85, 89, 8910, 30407, 73, 3251, 70, 5469, 73, 11377, 355,
-      392, 83, 73, 6194, 87, 80, 604, 983, 3178, 87, 587, 86, 664, 47689, 269, 75,
-      80, 13637, 283, 73, 9701, 73, 9902, 4835, 41796, 4171, 74, 16400, 79939, 45015,
-      43505, 80, 17063, 85, 9112, 88, 39911, 5721, 89833, 73, 4748, 85, 5298, 14029,
-      376, 13694, 65, 4341, 2067, 76423, 89, 3251, 85407, 418, 9701, 300, 13009, 85,
-      40185, 754, 1169, 61057, 9832, 77, 1215, 87, 18571, 89, 22580, 42583, 2329,
-      85, 6331, 67, 4223, 69013, 376, 8480, 86, 1331, 56201, 5104, 983, 77, 1517,
-      65116, 45228, 983, 77, 337, 80, 81606, 65, 336, 83, 1336, 77, 564, 21068, 80,
-      9810, 85, 1336, 2562, 346, 1463, 85, 30407, 1216, 28927, 266, 58153, 7501, 869,
-      87, 44508, 94869, 302, 77, 936, 26738, 20103, 50798, 9112, 71, 1725, 4575, 33963,
-      2562, 343, 67, 3576, 17692, 76, 16400, 2465, 9907, 283, 27093, 74, 939, 339,
-      73, 89, 1725, 31881, 74, 1800, 87, 2203, 70, 3306, 785, 74, 89, 42908, 11032,
-      2857, 69, 406, 65019, 73, 613, 427, 62497, 70, 7501, 67, 4010, 89, 8998, 75,
-      2857, 84, 1509, 36825, 1631, 88, 85, 14029, 23001, 7737, 80, 5010, 41796, 10176,
-      20127, 19239, 74, 2303, 4341, 11823, 329, 77, 1031, 80, 4777, 406, 1677, 87,
-      1065, 69, 73, 283, 9907, 89, 21206, 88, 73, 22119, 23866, 80, 3251, 73, 49865,
-      652, 728, 55442, 392, 86746, 7737, 85, 49755, 351, 14172, 83470, 3423, 74, 3919,
-      23048, 1889, 80, 70, 20553, 89, 3601, 307, 49463, 2067, 509, 53060, 773, 10002,
-      86, 32589, 544, 75, 59524, 11823, 486, 88, 73, 1662, 301, 7387, 344, 360, 86,
-      24468, 677, 42528, 360, 85, 1310, 70, 74, 2438, 1897, 89, 278, 41796, 3696,
-      86746, 22619, 85, 2067, 69, 73, 88, 23361, 84, 8587, 983, 2332, 80, 450, 27093,
-      88823, 8783, 73, 47689, 540, 14460, 73, 511, 90906, 69, 1026, 331, 28927, 11949,
-      30797, 1791, 76, 28927, 5298, 4777, 258, 76, 4168, 70, 540, 11032, 344, 87,
-      80, 301, 1662, 49595, 17134, 87, 80, 11160, 398, 80, 89, 6331, 77, 43686, 51622,
-      831, 1247, 88, 8892, 19639, 42426, 87, 6870, 427, 329, 3919, 65, 4080, 24752,
-      69, 1804, 3601, 3906, 1216, 23001, 7787, 36851, 20127, 1098, 316, 3433, 51622,
-      2445, 70, 5308, 7521, 85, 1029, 11927, 1091, 86, 85, 21659, 11823, 2438, 86,
-      561, 80, 10333, 7369, 331, 16276, 45228, 34175, 604, 6358, 17134, 75, 1273,
-      85, 5308, 71, 4168, 689, 21206, 2332, 19747, 20127, 10056, 1146, 2933, 49865,
-      86, 1029, 12940, 708, 5104, 73, 911, 418, 69, 2411, 88, 5308, 21888, 3906, 70391,
-      668, 46790, 80, 581, 18854, 93366, 8050, 544, 25457, 18571, 39152, 86, 1791,
-      710, 15444, 80, 4086, 13183, 329, 1631, 80, 22016, 1100, 1302, 9092, 1100, 11823,
-      689, 2580, 370, 501, 28927, 10910, 1631, 69, 5308, 69, 575, 7501, 39911, 88,
-      376, 2302, 3205, 40617, 450, 67, 33863, 511, 16820, 365, 295, 269, 677, 2329,
-      67039, 73, 7141, 4777, 7907, 3178, 58345, 2329, 56871, 273, 73, 20854, 9701,
-      48380, 86, 876, 8890, 1551, 89, 325, 23361, 49568, 86, 80, 3172, 1631, 89, 70,
-      73, 86, 8480, 89, 5192, 44508, 2392, 11823, 454, 87, 307, 2303, 75, 24990, 1551,
-      27455, 7047, 5981, 80, 1100, 869, 71, 67139, 13044, 45015, 3906, 70, 73, 9117,
-      88, 8462, 32868, 31695, 86, 80, 24244, 74, 89, 17319, 377, 69, 4511, 89, 5701,
-      48380, 876, 92562, 7387, 318, 1494, 87, 17008, 641, 7488, 71, 42510, 4922, 75,
-      49537, 8783, 42441, 24672, 66, 375, 79, 302, 42792, 6331, 80, 2302, 86, 637,
-      29238, 76736, 541, 1336, 12255, 581, 87, 427, 78498, 53904, 3919, 1347, 7387,
-      23361, 8998, 71, 43505, 80, 33495, 2302, 84, 12328, 346, 652, 89, 80, 74, 33863,
-      31881, 9117, 773, 13536, 80, 4680, 68, 295, 1725, 648, 71, 57647, 85407, 1609,
-      67, 34175, 85, 40924, 8998, 867, 5418, 710, 634, 48372, 1662, 38181, 3013, 17063,
-      19239, 73, 4239, 80, 18577, 81, 7488, 80, 1247, 70, 45015, 269, 86, 11823, 26397,
-      89, 7783, 70, 52097, 73, 876, 28990, 89, 329, 77, 80, 376, 74, 5308, 7907, 337,
-      2580, 19072, 728, 5972, 71, 402, 28679, 87, 540, 3576, 85514, 13423, 74, 2641,
-      3251, 65, 391, 32868, 89, 80, 8998, 23361, 263, 87, 7513, 87, 9092, 4010, 65,
-      5192, 266, 67175, 300, 2933, 455, 22580, 38359, 13545, 42908, 80, 85514, 6200,
-      773, 1718, 77, 2329, 7521, 3601, 17319, 73, 53289, 491, 55911, 402, 283, 89,
-      3933, 8212, 76, 675, 86, 89, 12591, 337, 4458, 347, 76, 23361, 3141, 86, 93471,
-      44183, 8587, 77, 36068, 511, 20824, 2192, 38181, 70, 14088, 81, 7501, 5485,
-      4922, 73, 70, 26397, 1072, 80, 1662, 708, 2580, 32547, 12183, 80, 20191, 89,
-      9117, 2026, 76, 2303, 86, 85, 89, 587, 73, 88, 752, 74, 1739, 318, 87, 25105,
-      9786, 89835, 1216, 1729, 87, 307, 28679, 324, 764, 89, 12407, 324, 21659, 67039,
-      23866, 73, 418, 336, 53289, 6009, 67, 3423, 4239, 564, 4763, 2689, 28844, 11949,
-      4341, 10616, 77, 23866, 1791, 65, 1662, 3628, 278, 89835, 377, 70391, 89, 14244,
-      1072, 85, 5010, 303, 1804, 6723, 80, 88, 73, 85, 604, 24752, 46224, 418, 3601,
-      771, 10616, 983, 1394, 1631, 83, 302, 38977, 74, 11328, 75, 1498, 89, 24705,
-      24244, 2067, 89, 455, 31721, 65, 7910, 86, 316, 86, 80, 17063, 5683, 1031, 27515,
-      71, 9117, 77, 1725, 2067, 32837, 2329, 85, 2438, 23001, 1136, 75611, 728, 10647,
-      79, 713, 74, 84995, 365, 361, 74452, 65019, 89, 12825, 4168, 74, 32204, 73,
-      8311, 1551, 1551, 44970, 1517, 1551, 62369, 89, 28679, 4942, 24823, 78604, 3172,
-      8783, 14029, 67, 417, 2067, 80, 73, 13536, 71, 27782, 2808, 38359, 74, 664,
-      73, 332, 764, 78604, 2312, 31268, 2739, 85, 360, 2026, 4086, 46640, 28073, 544,
-      14878, 14878, 73, 86, 70494, 27455, 8212, 19072, 73, 87, 71, 2249, 69, 4168,
-      61057, 277, 4223, 11805, 79, 39911, 3919, 83, 39911, 4341, 29700, 1729, 339,
-      86, 876, 44606, 299, 64, 3141, 83, 4942, 10776, 81, 24244, 18442, 9832, 9490,
-      80, 22016, 10616, 3315, 316, 8671, 67, 2580, 417, 31881, 15618, 278, 8088, 4168,
-      4171, 500, 89, 85, 1026, 14088, 71, 10616, 21807, 10784, 81, 2727, 14878, 52253,
-      10616, 87, 13855, 1336, 822, 336, 1247, 58305, 8318, 359, 299, 73, 87, 876,
-      38828, 1072, 84159, 10784, 96304, 455, 3906, 80, 876, 76, 8587, 31721, 5701,
-      73, 25734, 89, 752, 64, 458, 9907, 48380, 346, 45102, 12591, 62155, 20926, 93797,
-      69, 1072, 351, 87, 7141, 288, 73, 8050, 78, 831, 288, 11823, 73, 22580, 3696,
-      764, 10470, 86, 21807, 451, 5979, 324, 74, 11377, 86, 7821, 318, 299, 73, 501,
-      668, 36851, 351, 89, 80, 1804, 14606, 73, 7387, 89, 80, 21206, 17008, 89687,
-      70, 20824, 89835, 71, 1146, 2319, 1725, 22016, 21659, 80, 89, 3368, 316, 347,
-      501, 7783, 85, 70678, 894, 32868, 1498, 86, 2249, 8910, 31881, 85, 9813, 375,
-      24012, 80, 265, 1026, 21620, 303, 8207, 2641, 1029, 70, 4010, 664, 6194, 365,
-      39911, 318, 713, 89, 39911, 3933, 84, 4317, 80, 5010, 31172, 80, 24672, 68,
-      4341, 339, 69, 2857, 67, 2453, 24244, 587, 80, 38977, 53835, 31695, 351, 89,
-      455, 44067, 86, 5683, 69, 14029, 327, 2868, 69, 1065, 64, 309, 80546, 1791,
-      7141, 66, 1631, 21796, 86, 63958, 3172, 2249, 8587, 44183, 1264, 80, 17043,
-      50798, 784, 87, 22119, 39911, 10462, 80, 677, 5469, 80, 797, 2739, 7387, 80,
-      29684, 71, 2329, 31695, 789, 87, 3447, 87, 1215, 73, 1065, 19555, 89835, 32478,
-      86, 80, 3524, 822, 8311, 11823, 1029, 30243, 78498, 1662, 540, 19456, 20553,
-      2026, 80, 2438, 83079, 12498, 3696, 10188, 258, 5104, 846, 303, 70, 1919, 21807,
-      19639, 35531, 418, 21206, 3055, 4223, 351, 4010, 73, 301, 81, 73, 1517, 911,
-      36851, 337, 89, 80, 36238, 285, 46640, 20824, 1658, 21796, 42050, 2067, 263,
-      1658, 261, 641, 34175, 2580, 566, 65116, 27278, 34664, 73, 61057, 80, 9112,
-      325, 73, 5861, 2249, 7047, 48480, 10470, 2701, 79, 7513, 87, 398, 71, 2329,
-      7521, 29224, 80, 31721, 60933, 80, 581, 1631, 18894, 6375, 89, 85, 564, 86,
-      641, 89, 32547, 295, 14736, 8318, 90752, 18244, 87, 71137, 83079, 5298, 641,
-      8536, 89, 7501, 2249, 39911, 18894, 36996, 12591, 3172, 69, 488, 1347, 3368,
-      12082, 70, 80, 25457, 69, 1551, 544, 56029, 1919, 78, 80, 383, 23913, 402, 299,
-      797, 8212, 85, 1157, 7453, 73, 95945, 22473, 85, 8480, 6194, 76, 575, 365, 773,
-      91410, 32589, 89, 70, 73, 283, 71830, 20218, 9700, 1725, 344, 89, 2034, 7783,
-      2302, 74, 2642, 89, 4657, 773, 8998, 65, 7737, 269, 4575, 75593, 74, 728, 4942,
-      1347, 75, 3841, 581, 13536, 60013, 509, 46790, 80, 1073, 79, 60933, 73, 17007,
-      372, 89, 1517, 89, 383, 40952, 1002, 316, 87, 32962, 74, 392, 46341, 10616,
-      69, 3919, 31764, 4317, 773, 69, 12825, 3576, 2249, 339, 20926, 894, 12183, 89,
-      73, 15618, 8207, 76, 588, 7387, 86, 7141, 79, 11089, 8998, 84, 352, 16618, 56871,
-      89, 29443, 31764, 906, 73, 70, 44490, 450, 77, 1729, 19260, 675, 39911, 1919,
-      7513, 69, 70494, 392, 10616, 32868, 2067, 17553, 61057, 418, 5418, 80, 2784,
-      8318, 511, 77, 51622, 87, 14878, 76, 89, 2880, 64087, 9902, 1230, 80, 3576,
-      454, 2303, 41129, 3524, 89, 13752, 441, 6358, 73, 10056, 12498, 3251, 32868,
-      14736, 566, 70, 80, 4458, 752, 677, 343, 67, 376, 664, 2880, 4777, 85, 10470,
-      86, 1100, 89, 9258, 288, 48380, 16400, 668, 8512, 634, 83, 8186, 5682, 43505,
-      664, 12082, 540, 85, 26738, 80, 1725, 6009, 3141, 796, 7521, 42930, 47689, 537,
-      1302, 12329, 79, 8910, 5010, 27515, 346, 80, 89, 39911, 74, 80, 336, 7910, 80,
-      723, 462, 11160, 3919, 1073, 87, 73, 347, 637, 88, 1498, 70, 21486, 1031, 15444,
-      73, 21796, 60013, 11949, 89, 3368, 88, 69, 2329, 1551, 349, 18442, 901, 85,
-      336, 3251, 582, 2438, 48872, 450, 9081, 303, 1065, 76, 6200, 66, 1273, 581,
-      85, 22532, 1347, 76, 55506, 44970, 73, 87, 8050, 52253, 28990, 86, 6358, 48872,
-      87, 1739, 74, 89, 80, 44970, 80, 2042, 7501, 72801, 67455, 427, 16017, 85, 324,
-      31764, 1729, 78, 380, 8671, 57367, 2319, 82, 1336, 89, 15444, 73, 8376, 2315,
-      64, 454, 46640, 69057, 383, 73, 361, 80, 3059, 85, 316, 587, 86, 587, 637, 5308,
-      5298, 70, 1394, 6733, 80, 11032, 80, 8998, 8212, 73, 87, 462, 71, 45015, 86,
-      89, 8998, 34175, 69, 89, 6200, 14606, 85, 2332, 79, 876, 894, 68566, 8783, 86,
-      11345, 65, 1631, 1302, 89, 9081, 8480, 73, 5972, 8587, 80, 2445, 2026, 1017,
-      377, 88, 451, 277, 18244, 581, 336, 604, 8311, 85, 7737, 86, 89, 1031, 79, 3415,
-      73, 1609, 79, 45015, 17319, 87, 86, 13536, 939, 89, 14088, 77, 1100, 21068,
-      85, 89, 93366, 86, 4168, 2933, 73, 21206, 509, 28774, 71, 11949, 566, 6200,
-      22619, 38041, 28204, 10647, 96518, 22619, 3326, 67919, 23361, 52971, 292, 65,
-      713, 5308, 295, 76, 4867, 1568, 1729, 89, 10188, 88, 936, 300, 336, 3306, 3368,
-      1065, 9326, 65, 7387, 2465, 869, 66, 9555, 83079, 1494, 87, 3423, 652, 11805,
-      3906, 73, 70, 1910, 87, 10097, 72, 4171, 86, 8892, 24409, 80, 5230, 2554, 73,
-      52097, 80, 2026, 38977, 365, 4080, 89, 32868, 16711, 80, 352, 84, 80, 23361,
-      74, 80, 89, 66777, 773, 87, 21620, 1551, 34856, 462, 402, 27455, 8480, 55568,
-      1919, 67, 39911, 87, 3178, 67665, 80, 3601, 4080, 89, 764, 17704, 80, 324, 74,
-      9996, 80, 333, 87, 1919, 8385, 1739, 302, 4922, 14406, 830, 76, 96416, 89, 1910,
-      89, 85, 5010, 67800, 45015, 77, 16373, 89, 1804, 76, 14029, 376, 77, 23577,
-      4970, 73873, 11823, 1983, 74, 80, 3601, 67, 9092, 385, 22575, 672, 69057, 13045,
-      354, 38361, 8212, 86, 89, 4991, 8088, 71, 7197, 19239, 38041, 64087, 875, 657,
-      66, 773, 24244, 74, 4680, 9832, 74, 4890, 85, 332, 19555, 86, 2106, 77, 6151,
-      1065, 346, 5308, 969, 5104, 28679, 74, 13536, 85, 1031, 509, 75, 3172, 15802,
-      80, 5010, 75, 49450, 3933, 87, 1658, 87, 327, 47171, 21543, 34175, 87, 49358,
-      398, 31764, 55233, 392, 44508, 73, 302, 73, 36722, 12940, 71, 73, 7488, 12825,
-      89189, 37406, 52971, 3427, 4341, 3141, 876, 70, 5010, 324, 7047, 73, 2438, 3368,
-      46224, 762, 385, 73, 11949, 2203, 31764, 66, 46640, 86, 5010, 65, 2580, 89,
-      3153, 4664, 78930, 88, 1546, 398, 2034, 86, 5237, 44490, 784, 84, 263, 391,
-      2580, 85, 346, 14468, 79, 2067, 85, 42818, 18442, 8385, 677, 1662, 2067, 86,
-      383, 6723, 1073, 64145, 1026, 587, 2629, 383, 80, 8671, 40078, 953, 24990, 2026,
-      66867, 1568, 66, 1551, 8088, 38041, 74, 764, 70, 32478, 49450, 32204, 15555,
-      31146, 15809, 546, 15618, 689, 78498, 5308, 361, 73, 8462, 24738, 266, 26039,
-      71, 7910, 80, 875, 53835, 88, 28679, 73640, 17008, 70, 5308, 34146, 71, 710,
-      85, 8910, 8311, 2562, 42818, 6511, 796, 22119, 74, 87, 1394, 6200, 70, 46640,
-      47154, 89, 6151, 581, 3906, 1273, 10470, 25299, 80, 30407, 299, 6292, 266, 73,
-      63885, 1336, 20553, 1631, 86, 372, 752, 41796, 85, 336, 74, 1065, 66, 16499,
-      69, 6358, 38385, 10776, 71, 23913, 276, 80, 73, 13855, 77, 764, 68054, 23866,
-      796, 80, 1725, 4239, 71, 544, 2480, 89, 657, 86, 80, 78, 343, 73, 2603, 42511,
-      69, 69057, 5964, 7369, 8462, 14029, 261, 12989, 11949, 49463, 73, 87, 4010,
-      90231, 365, 450, 79, 29238, 85, 427, 82, 65167, 41129, 31019, 68411, 1347, 47689,
-      70678, 1551, 87, 22119, 3418, 728, 65, 80, 657, 80, 73, 10820, 1029, 80, 30506,
-      42908, 54899, 677, 451, 80, 20990, 85, 10036, 71, 2445, 20962, 708, 69, 764,
-      652, 796, 7501, 80, 1498, 78930, 5010, 10196, 80, 1072, 295, 87, 23361, 70,
-      45015, 70, 351, 67800, 86626, 66, 634, 1631, 9092, 73, 797, 87, 19866, 12498,
-      74, 3172, 70, 2303, 74, 12498, 7737, 65, 3601, 2727, 80, 360, 2034, 32204, 2727,
-      65, 1609, 5972, 89, 4680, 5981, 42818, 7501, 1302, 38977, 65019, 88, 797, 80574,
-      300, 1658, 73, 4657, 309, 97715, 5192, 6009, 24027, 10333, 84, 80, 14029, 40924,
-      2111, 67, 728, 372, 85, 365, 18854, 86, 5289, 276, 9902, 80, 359, 20553, 1804,
-      339, 8311, 1065, 370, 869, 73, 10776, 77, 80, 1764, 10333, 76, 1910, 8311, 437,
-      80, 4777, 77, 657, 74, 93000, 447, 85514, 6375, 4912, 36851, 42908, 7047, 25299,
-      74, 1273, 21436, 76731, 1658, 85, 953, 88, 9700, 5104, 36825, 544, 7513, 73,
-      438, 89, 11253, 10784, 73, 2026, 70, 74, 8207, 309, 25772, 4239, 38181, 3251,
-      65, 831, 377, 8480, 87, 22873, 83, 73, 94817, 637, 5746, 3423, 953, 65, 427,
-      41129, 89, 46224, 73, 1247, 370, 87, 300, 8248, 86, 2249, 8910, 85, 2221, 710,
-      303, 1247, 87, 86, 1331, 87, 18577, 85, 26397, 16276, 3458, 80, 2857, 377, 11251,
-      89, 7387, 42908, 302, 39911, 77, 385, 39911, 42050, 710, 89, 40078, 89835, 70,
-      5289, 344, 11328, 80, 1339, 355, 31721, 41523, 344, 2438, 73, 7501, 333, 2203,
-      540, 375, 79, 521, 5981, 588, 80, 89, 85, 10796, 87479, 8050, 73, 4239, 9988,
-      76, 1631, 81, 8088, 79, 1394, 82, 2912, 70, 73, 52513, 822, 511, 9188, 450,
-      10176, 46640, 87, 86, 398, 333, 86, 8385, 80, 300, 1897, 55773, 303, 1072, 2319,
-      89, 9996, 664, 31268, 13855, 939, 69, 27457, 39911, 911, 55748, 347, 83, 73,
-      86, 581, 6331, 370, 70, 73, 9907, 3105, 752, 78, 70391, 5298, 74, 28679, 65,
-      22524, 74, 64087, 80, 78, 3251, 28400, 1116, 80, 74, 796, 24459, 723, 85, 89,
-      3418, 344, 27515, 40078, 93797, 85, 1658, 6194, 73, 501, 2933, 71, 95143, 11206,
-      71, 73, 5079, 1073, 74, 3178, 5683, 3431, 81, 40078, 89, 1354, 73, 86, 3013,
-      303, 89, 454, 70, 80, 784, 80, 42818, 3368, 71, 7501, 67800, 85, 73445, 73976,
-      86, 5650, 6194, 79, 318, 66, 318, 12328, 65, 2200, 13536, 31019, 3059, 689,
-      3251, 6511, 80546, 564, 77, 1517, 28774, 4080, 41129, 292, 81, 783, 65, 70678,
-      24752, 73, 89, 894, 939, 39152, 566, 85, 77827, 80, 4511, 72, 1130, 5964, 20811,
-      263, 74, 339, 8910, 71, 8566, 604, 332, 1320, 16400, 307, 4763, 67665, 69, 73,
-      12591, 42050, 19072, 80, 3906, 89, 392, 73, 7488, 89, 1122, 418, 20103, 80,
-      56871, 4880, 65, 80, 74, 427, 566, 796, 77, 5701, 80, 74, 27455, 25817, 1551,
-      309, 540, 354, 94908, 8998, 4223, 14878, 8050, 23001, 87, 1065, 65, 9907, 1494,
-      1910, 581, 85514, 365, 88, 21888, 85, 5298, 998, 402, 9991, 85, 303, 299, 2496,
-      45015, 3427, 352, 74, 80, 797, 23707, 87, 13441, 365, 49891, 66, 450, 343, 26397,
-      1273, 455, 318, 267, 80, 7047, 1590, 318, 71, 20127, 564, 75, 303, 710, 5469,
-      3251, 8207, 318, 75, 10784, 2438, 79, 87348, 4168, 74, 34870, 302, 80, 3458,
-      80, 88, 50153, 1233, 86, 344, 23048, 370, 7521, 10002, 1100, 9700, 337, 20553,
-      87, 363, 9451, 6194, 73, 63643, 93000, 6511, 9110, 73, 2649, 80, 89, 80, 70,
-      9490, 86804, 87, 18577, 74, 3415, 7910, 6388, 1498, 27457, 1073, 70, 80, 69,
-      18442, 359, 58153, 73, 9907, 540, 89, 3251, 18458, 365, 5192, 74, 412, 327,
-      509, 78, 343, 73, 20127, 18442, 85, 19072, 10616, 391, 85, 80, 11160, 10056,
-      911, 24752, 4922, 86, 85, 42908, 1631, 343, 318, 89, 641, 2784, 1729, 1030,
-      5972, 15479, 1900, 2933, 43505, 2439, 9509, 728, 3978, 13536, 89, 32868, 6455,
-      2249, 8998, 89, 56871, 10784, 784, 5308, 49712, 89, 22524, 52097, 509, 45015,
-      8910, 2329, 73, 3418, 677, 4912, 80, 69, 24752, 11377, 10776, 391, 21325, 6511,
-      552, 2319, 1658, 49712, 9700, 70, 73, 8998, 80, 285, 365, 64305, 89, 61057,
-      1729, 86, 5298, 71, 544, 307, 798, 23913, 70, 2303, 263, 76, 16400, 89, 48380,
-      33323, 80, 24244, 48372, 18926, 7910, 3418, 85, 1551, 4341, 677, 44067, 3601,
-      3696, 48610, 3427, 89, 710, 10470, 587, 36722, 49463, 45015, 13009, 9700, 79,
-      372, 30987, 81964, 21796, 48380, 588, 371, 2201, 3059, 89, 55418, 47154, 73,
-      53289, 13722, 3524, 2642, 18854, 1764, 68, 16618, 80, 764, 80, 5241, 1604, 5972,
-      88, 352, 1662, 64087, 80, 4991, 10910, 953, 80, 303, 80, 1498, 376, 377, 88,
-      6634, 80, 1466, 7453, 94912, 9490, 8462, 15618, 65, 710, 89833, 75, 80, 88,
-      437, 73873, 89, 2312, 318, 66, 359, 9832, 3601, 8207, 23361, 74, 418, 67, 34175,
-      86, 80, 25457, 66, 333, 85, 3178, 1725, 268, 80, 4484, 604, 84, 4341, 5469,
-      89, 78498, 89, 35531, 67800, 4852, 441, 65, 93000, 33721, 318, 74, 604, 36851,
-      64145, 93797, 2465, 80, 61057, 302, 3316, 2191, 31019, 19456, 20824, 637, 8826,
-      21486, 351, 79, 6414, 3178, 1725, 80, 89, 42818, 80, 404, 1498, 86, 85, 588,
-      74, 634, 14088, 87, 23361, 80, 47689, 30506, 1029, 12119, 80381, 5964, 66, 1498,
-      73, 6292, 291, 89, 6256, 7835, 1498, 66, 7453, 73, 87, 19239, 582, 5308, 93529,
-      1634, 88, 329, 10616, 86746, 20191, 402, 4080, 86, 2005, 6511, 361, 74, 5308,
-      450, 66, 8462, 6780, 363, 4719, 85, 9810, 80, 29238, 80, 1910, 13855, 309, 69,
-      1498, 9092, 4922, 5418, 830, 79, 1100, 12682, 83, 73, 87, 73, 318, 66, 3423,
-      65, 80, 2332, 3906, 370, 710, 327, 28546, 87, 7488, 86, 12940, 773, 6043, 80,
-      10847, 84506, 352, 830, 65, 10616, 329, 22119, 4458, 64, 427, 79, 372, 21659,
-      31881, 3423, 44970, 1662, 1233, 8510, 31577, 81, 1031, 2308, 87, 318, 12498,
-      18299, 88, 869, 4657, 773, 339, 3841, 72, 4912, 3518, 406, 73, 3251, 65019,
-      88, 7047, 10630, 9092, 53060, 9902, 82999, 4625, 309, 38361, 67800, 16848, 70,
-      675, 42848, 87, 8671, 28990, 25604, 74470, 1662, 79, 7737, 418, 2690, 12328,
-      3893, 24672, 398, 53016, 32759, 3181, 72, 906, 652, 80, 13075, 31019, 48872,
-      96304, 5104, 637, 4381, 683, 70, 604, 1073, 625, 74, 58598, 28990, 418, 501,
-      80, 1216, 53016, 87, 43723, 66, 352, 85, 12940, 747, 404, 2026, 14170, 80, 8088,
-      1031, 967, 86, 911, 45228, 73873, 88, 1331, 581, 906, 85, 70391, 17008, 80,
-      275, 22619, 2739, 85, 16400, 4317, 80, 509, 372, 343, 21659, 2176, 80, 333,
-      1065, 9780, 73, 375, 20372, 1677, 71, 10056, 9902, 89, 5697, 336, 675, 71, 641,
-      29684, 1030, 39152, 911, 19747, 80, 32204, 1662, 1065, 4484, 89388, 1609, 3647,
-      94869, 6036, 1764, 15258, 1551, 16373, 5289, 85393, 5469, 2411, 77, 1551, 85,
-      47154, 365, 69, 26397, 76, 1026, 5544, 1494, 15618, 52971, 11089, 51622, 70391,
-      4991, 83079, 7737, 71, 450, 65, 16276, 84, 5308, 939, 24244, 9289, 89, 19072,
-      462, 1729, 11805, 36851, 329, 4010, 307, 333, 1662, 38041, 11160, 1658, 796,
-      5237, 45228, 8050, 70, 80, 10776, 9092, 1631, 363, 34175, 2070, 36068, 68054,
-      14949, 1031, 3906, 73, 13536, 71, 10470, 83448, 5010, 9092, 77, 7488, 84, 300,
-      25770, 26636, 544, 86, 4010, 22473, 8536, 3251, 76, 1286, 261, 17704, 4341,
-      70, 27455, 11872, 55568, 351, 74, 10056, 80, 12498, 70, 73, 46790, 566, 377,
-      398, 67, 1100, 376, 38361, 69, 24012, 580, 85, 80, 11851, 32589, 377, 22619,
-      316, 3576, 652, 70, 2329, 3251, 343, 2319, 82, 441, 36851, 79, 20127, 71, 1609,
-      29700, 89, 92216, 87, 398, 1517, 73, 637, 67, 5346, 71, 7501, 7141, 96518, 6098,
-      81, 418, 85, 10470, 83, 544, 41796, 89, 89835, 6358, 85, 4777, 564, 35804, 604,
-      80, 38181, 302, 95947, 70, 12723, 412, 80546, 395, 1273, 1029, 300, 87, 3368,
-      1273, 454, 74, 5972, 74, 1030, 12748, 80, 450, 20127, 5964, 69, 351, 75, 9907,
-      9092, 77827, 7063, 84, 2319, 266, 303, 365, 18577, 1073, 675, 3647, 69, 454,
-      87, 8587, 73, 85, 3893, 28679, 80, 25299, 1029, 57208, 9092, 9117, 2034, 89,
-      2689, 5972, 9991, 79, 12498, 74, 89, 29684, 2302, 29684, 76064, 89, 14694, 288,
-      98667, 7501, 80, 39172, 2005, 73, 3479, 14244, 73, 13183, 31019, 344, 360, 22016,
-      1936, 9081, 1725, 30506, 11160, 1919, 81, 42908, 80, 89, 4223, 86, 2302, 418,
-      3172, 87, 1729, 303, 80, 2329, 566, 85, 1336, 13536, 85, 44970, 9832, 73, 86,
-      302, 73, 1220, 18571, 774, 46224, 10784, 5544, 73, 4912, 1371, 12940, 1073,
-      73, 12082, 80, 1394, 53060, 437, 6043, 511, 17137, 85, 1065, 88, 4010, 7044,
-      32204, 451, 88, 7387, 6511, 1320, 283, 327, 581, 70, 33863, 23913, 89, 20824,
-      22016, 1394, 40924, 344, 89, 754, 7453, 73, 85514, 80, 2668, 575, 67, 1725,
-      675, 69, 73, 15720, 67782, 418, 69, 41796, 87, 302, 73, 54909, 10616, 2312,
-      74901, 74, 36238, 2580, 18854, 2042, 89, 399, 89, 31268, 74, 45015, 38041, 5469,
-      12498, 13391, 14029, 652, 66565, 3178, 35949, 1631, 4341, 5469, 49938, 65, 1897,
-      295, 2111, 344, 47154, 73, 2580, 73, 65019, 10333, 8462, 78, 1065, 6634, 71,
-      1804, 267, 66, 40078, 3013, 74, 6331, 355, 1729, 80, 24672, 540, 35531, 2445,
-      15008, 89, 5104, 1273, 88, 69, 1494, 1091, 2249, 88, 37975, 2857, 9832, 25299,
-      710, 70, 80, 89, 97523, 23866, 261, 89, 70678, 764, 87, 18577, 21486, 8480,
-      69468, 3841, 20926, 80, 352, 12498, 73, 42528, 36825, 301, 80, 418, 89, 45788,
-      337, 9832, 89, 85, 12498, 76, 1030, 1394, 11377, 73, 869, 728, 5241, 773, 88,
-      3340, 85, 1310, 80, 637, 4239, 30407, 3415, 68, 71696, 762, 302, 19239, 89,
-      1320, 1394, 764, 93000, 4680, 71, 2249, 69057, 501, 23760, 6200, 91998, 18400,
-      85, 20926, 7501, 73976, 79, 46390, 80, 318, 370, 18577, 343, 1725, 70, 1658,
-      4991, 96605, 73, 1029, 9832, 376, 67, 8536, 301, 89, 331, 85, 1347, 1931, 73,
-      6632, 301, 278, 46341, 784, 1725, 63643, 60013, 32589, 89, 1310, 89, 24990,
-      86, 18854, 4937, 4680, 87, 71, 483, 355, 455, 25299, 664, 67702, 1073, 9195,
-      73, 6634, 59524, 74, 80, 2739, 18854, 74, 501, 1331, 86, 26738, 391, 1073, 64145,
-      70, 2067, 359, 47875, 3251, 1498, 3933, 6780, 1739, 4912, 4223, 418, 79, 1897,
-      664, 65, 10188, 80, 983, 11823, 266, 48320, 5192, 36851, 74, 8311, 876, 15444,
-      3906, 87, 2332, 75, 80, 14878, 2465, 4835, 983, 76, 8462, 784, 5469, 575, 3013,
-      59524, 375, 12328, 73, 20127, 89, 983, 9112, 713, 324, 86, 11253, 7819, 1092,
-      86, 89, 339, 74, 15959, 295, 51924, 1073, 89, 31721, 325, 1331, 309, 85, 12407,
-      8671, 59524, 20211, 4484, 998, 283, 8318, 88, 73, 2312, 1036, 21888, 7004, 2026,
-      5241, 80, 2332, 36171, 87, 2303, 89, 26929, 1366, 20127, 71, 70678, 1551, 84,
-      773, 3806, 21206, 278, 81, 9664, 76, 38359, 85, 1394, 773, 869, 3906, 953, 347,
-      76, 1978, 383, 41622, 509, 339, 80, 17156, 266, 9117, 87, 84, 12748, 88467,
-      708, 15618, 73, 46341, 447, 48380, 80, 7208, 74, 87, 70, 73, 70, 1290, 88, 324,
-      302, 78, 336, 3306, 86, 361, 4922, 89, 73, 764, 307, 31172, 8671, 70, 283, 96518,
-      31422, 88, 73, 2159, 332, 2067, 710, 668, 8462, 31764, 70, 3013, 19271, 86,
-      657, 79, 316, 74, 447, 263, 44970, 5481, 44490, 17043, 32973, 4168, 2302, 74,
-      7501, 9832, 451, 1247, 575, 344, 2042, 1031, 81, 1739, 69417, 273, 11289, 81,
-      2445, 307, 28679, 1273, 8385, 648, 78, 511, 2445, 7047, 76188, 441, 2192, 80,
-      54803, 9700, 5308, 68054, 71, 398, 3415, 953, 88, 73, 10462, 363, 31172, 370,
-      89, 9810, 71, 1517, 52719, 84, 587, 3418, 82, 3423, 1729, 89, 876, 82, 3415,
-      73, 85, 2642, 22524, 377, 4942, 73, 564, 9700, 87, 2106, 8318, 88, 80, 22619,
-      752, 70, 1394, 75, 3178, 4835, 89, 657, 18571, 1729, 8207, 86, 89, 92216, 3172,
-      4942, 3933, 332, 939, 57208, 9991, 363, 19239, 4511, 89, 73, 347, 86, 9081,
-      70, 8587, 2580, 80, 325, 9490, 3906, 19747, 5481, 70678, 5544, 67, 34175, 29229,
-      13616, 73, 12130, 36851, 85, 80, 36068, 6200, 427, 17704, 80, 3251, 85, 31695,
-      402, 3516, 869, 74, 383, 2067, 72801, 79, 1791, 73, 939, 70, 1604, 3368, 86746,
-      87, 392, 75, 543, 4835, 88, 80, 4086, 94055, 16400, 71, 75406, 339, 625, 1729,
-      31764, 15479, 511, 1551, 5598, 398, 1320, 346, 11377, 437, 901, 85, 80, 38041,
-      73, 59448, 4223, 85, 3601, 283, 16820, 41796, 85, 4381, 336, 55498, 283, 22119,
-      14878, 44183, 455, 3059, 21538, 16017, 73, 5683, 89, 372, 708, 28927, 9832,
-      66, 98667, 752, 80, 69, 89, 1231, 8088, 11222, 1394, 3306, 71, 1517, 911, 85,
-      17134, 2302, 85, 818, 7141, 65, 5298, 70, 3601, 7521, 4355, 3223, 84, 347, 70,
-      4080, 61057, 46341, 1804, 28927, 46341, 47154, 16400, 8462, 12119, 32547, 1658,
-      12591, 20127, 12825, 84, 80, 275, 3172, 10470, 9117, 417, 73, 894, 34967, 80,
-      7488, 86, 80, 953, 2312, 17134, 86, 288, 77, 343, 10616, 25105, 29238, 74, 9110,
-      39152, 86, 1310, 76, 385, 1610, 74, 89, 9509, 61318, 77, 78498, 73, 88, 5418,
-      56178, 89, 9197, 398, 347, 55655, 25299, 5289, 3893, 25105, 675, 43210, 398,
-      65, 2329, 376, 2203, 17134, 75, 333, 89, 10910, 1336, 87, 32837, 75406, 80,
-      4010, 80, 1026, 75, 3368, 68, 55334, 42818, 80, 89, 1551, 31695, 86, 10784,
-      2329, 9701, 544, 81, 339, 20990, 10796, 75, 1094, 14606, 85, 1336, 45228, 3576,
-      336, 11949, 391, 86, 8088, 46224, 291, 36851, 424, 73, 86, 3415, 1609, 89, 4168,
-      88, 47391, 8587, 28990, 29700, 80, 3055, 402, 14928, 67, 7488, 876, 76, 6780,
-      88, 36825, 42908, 2312, 3306, 2739, 80, 25295, 30506, 501, 21066, 93000, 2562,
-      7215, 337, 80, 88, 677, 69, 33863, 80, 16820, 572, 35278, 77, 80, 1065, 64,
-      309, 77, 544, 1149, 68054, 784, 2332, 67, 2641, 73, 88, 9117, 87, 4922, 79,
-      911, 83, 10616, 11823, 275, 73, 21620, 31268, 70678, 1029, 98496, 12328, 10910,
-      79, 416, 85, 89, 664, 26397, 71, 73, 32962, 10056, 85, 17134, 1146, 80, 30463,
-      1551, 24990, 70, 41670, 604, 67702, 11032, 7488, 385, 581, 80, 1247, 11823,
-      87, 9701, 501, 1146, 352, 76, 44183, 21620, 936, 9700, 76, 1216, 76, 2396, 2249,
-      2739, 73873, 87, 18664, 88, 1919, 86, 85, 2042, 5972, 28546, 73, 86, 11089,
-      22619, 80, 99161, 1216, 45228, 2438, 70, 511, 79, 391, 25299, 939, 86, 1718,
-      80, 70, 1764, 21796, 74, 47154, 67800, 9490, 28679, 67, 365, 406, 73, 43974,
-      89, 19239, 652, 71, 73, 89, 3841, 60013, 2249, 69, 5584, 6194, 70, 80, 73, 21807,
-      58305, 329, 1029, 74, 7453, 1216, 80, 3141, 97816, 4511, 17134, 60933, 45015,
-      74, 5721, 664, 5010, 327, 74, 80, 295, 346, 89, 24527, 1331, 96250, 344, 89,
-      80, 8088, 953, 82, 2727, 318, 352, 347, 8207, 73, 88, 8462, 75, 796, 14606,
-      1662, 540, 17851, 36825, 1031, 80, 359, 1310, 11823, 566, 588, 73, 5038, 4942,
-      49595, 8462, 4942, 32204, 85, 1029, 73, 4484, 309, 9902, 85, 2857, 10784, 82969,
-      747, 88, 64087, 302, 86, 4080, 73, 87, 31764, 728, 91295, 95143, 7513, 869,
-      359, 67020]], "model": "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '45399'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6XROyvJbs/f4Vb723nF2CClnsOwREvkwQEHVq6hQoIqAiHwmQqfnvp/TZNafm
-        xgtIIQmdXt298l//+Ouvv5usyq/D3//66+9n2Q9//5/vtVs6pH//66//+Mdff/3113/9fv/XyPyV
-        5bdb+S5+w383y/ctn/7+11/i/1z5/4P+9dffPK51Zlm5w7mkNi+wXlnNrHNYerPffK4Qe1bI3MOi
-        6Oa2C3X4PNM120LZV5MsPW2kif1Edu7uzscyWyXImg93LLn2bIyrW9qg7N0kOGq7VTYt12WAzDg8
-        E3PBlt1U3E82IsXZIM5dEHlzXQ81ii0W0PF9LSOuN5CiPksntvGEYzSqjViqj4e1YMbwWXq9J5xN
-        tFoEB2JK/JIxIZ80YLfwyUjp4W5QvaxH3VN1iLVRrx09zrquVp1AsFAkp2rQiJeC7OMZd69FUHFo
-        HBGm55ERzxE9Y7x0eopky1jjhm53fGLPtQLz3b1QMRm31SRsdhZyNQNjtTaJMeeofcFhffdpIbIh
-        o900UPCYVjH8jhNvitmbouydXSjnn7KafdkZ4bHvPYLf8dIrHseugd/8rNwNvFFT/RIJaSRh9dJF
-        FevM5gz7ZzGzVBEO3UD3+wD69epNdhyzaG78kIIRgkT26+UWjfdVYUHXuwbTjRUx+gopV3RenW40
-        iaa4Y+nufkXHSqHM8+cPH8++ZymDOZRs+xDXEeV+eQVpfjpEOzRtNulX+oJ5v6vZVq4HPssX2159
-        ulhi2jQssmEc7BRNqPiQqMGWNxrIwNCAtSPG7FYZLRcigGxt1kxHvdx9nDGagZ2Shorn3jCmwZpq
-        aJDkElK9hGq6+MOIeBrpbPdODbRiO0GAL54Yvqt2JTnsDkjLUo1s9o/amE/B9gXwfN7JqZaNTJp4
-        bKKQvyX8ePVON662rYhMnVREZ2LOebB8J6gt5pztZEutBmFDTHhcaotsGs8xBoLUFoyWtmR/6XjF
-        QprG4DTFkRnuS4/G9ycQ1cg7tmwfBgmfHHYX0PEmjFRab+4ZD7c4hU14rvFKttSOa/rzBSS9bsnh
-        Ng/VuPaWBZgTw7S9xj5azckN5OZMUrKr5Sobda+qYbdiO7KnNzfiCS8KGIL3DQtZ4XaSrYGLhnVN
-        2HmdxsaUXbVa1U+iTwKla7vZsG6hvOAvj2hPOUJDrp1EOGO9Z9viYkfz6rBuQFjjJ9GFdp3NEQqX
-        ixlEnxHjlkZj2MgxvKrKJFqRxhV3anmUF6ZZUK4KGHGnkgDmTotZlnlbg0OQ6mglxzFzy6D1GuPz
-        tkDq1zb7rqfHj/1Fg+dCjohX54E3LhPPRif7bdK50KKKP2a4omJ6x3/wzoVlsYQuMHwq3M5rPoXK
-        2gXVOIS0Nzuj49q895GFP5TEHHnestTWS9g+Y4Ec9cmsRJTeCvCRajINDR2iSfFcI1F1Cqyk0j5j
-        +/BsI/nGB1q5ZWRMl+ch/X1vRubr2uBJCgpSLl6Ej0dQO/o2dymkZoEI/sQ6mtx80cIiWx6Jpx/v
-        xsii2USkNzSy/Y7v5NZzYbWlNXP5uzbG5BgpatKiA71NJ5k/FpeZotSMBMolWzdGCaMW7jmViO99
-        SmNQS9KDOo8q84Nsgca6S21Ay3iicgm8+iDT9IFtD5w5N/NZjdfgdgU3tAws5ctLRaVscwVu9zti
-        a89PNw8brYbsfbmQrWvP3sCV6gXTp5/ocr7bnMufXQJ1KXCK8F7mfLdVcgjfwor2kUa68eztAjRa
-        y4jZr7YzxvLKbXRqU6DhTRdRJx2DK1ocu4x5+OB4Iv4sl8ruvjgQ7bp5opEzMYD4qrjM8XzBmM/a
-        w1Ky4ZgQ52Q3Hi21tQhyBQ0zCpYaTD4zXbkesEnMaH5x3mXXFL58zyJnZ3j8Zl0EGMd0Q8z7a46G
-        UBlt1cIdZbo9XI35g+YExpBishMHyvtHf29gEzpvZjDf7OgPL3Xmq8xL6NugTjgDIAgpc7qbhqTm
-        sFPQqOQGXQPaRNP5ZpnyD0+6w27ZsL/NLvLr3KeX4bDgFL26BNISU7b/4Vd8rmflu//Jt54aY+bs
-        BWjagFBppBtj0m/lGR6dt2E75eMbo+51LwTYfLHTkDyyWeo+M4z0ZVM+W7ExHtVehzTwZLKX1m9v
-        XG3LJQjmS8JSPZ+8KTPPI7hb1SO+hp8dbcRWRN4Nd1Rp7HXGr0chh1CeGdkchNJ4+EPeoPXGdNlG
-        ezce0+atD7/6oGQrXE2va5CgLJszst0wI5oPZtVD9egCQpq6NcZzpShwKhKFuG5dId71YwHmZ3Fm
-        Ptsb3vDR3i+QpbkgRhV/UK9+1gn68iXl8iNAY7gYYrgqpYgVbxHxZTc/SqjJUacVs4/RUPtSCY3/
-        uuJptYiz7/xmVMnZFi+Mh1PVMkpsqNcd/4P3Sa2MAslna2B4ExmoTvU5gPA9KBgkp6jGFndrkI5u
-        hIUiffEJSx9AxvLUECOTVNSroVbCCbBIaR9uKj69ZwtJziYjmiHORqfL1x7FylHD5f1dd+PeXRQw
-        nhuPGWur4NP+KiQoFhsNw7wLq/EkRliNJPdItLi8cD4FbgBpH4wEa3sejTdtFKDrZOvLF7eOK5dW
-        BO2kC199lFRDcT+5kKx0h+ESvSPWHm0KT9G4MMfE947vzGWzbu2pI3r+iL2pC9wzqF1ofvGmG/Ne
-        O8QovnZ7shUWNzQFxtYH1O5lYvCPXk3ai2NY8NpjyWXaZNMru5bKtjMEDJdjhr76ylp3QeiQXVY6
-        xmg9Ugtu/o7R5UdA1ZRl5qxsVYsTO7lsKnGRvxXoZnND17b2yqZnByIaw9uBeP7s8Pn0VlNYBgEw
-        7VAjr6cIp+j7fYlvuTof3i5gtGenFT4FhpqNgb3EaNloEztFG4TaVscmLFztxpzHTcz6fDy/YLXt
-        a3bd+abx0Yh3VpVbeSSeJLXe/OP73/Nd0dSz0dTDP/uJ7Y6LtJqisNHBr/cEL6sPy2j/2Kfo8ra2
-        zFrCi491VCbw3T/Ez9ftd33iAi7HcE/8/WPMeCS+NLi8JJtZlyE0ZgXzAlgjV8RhS1ZN82MBgGEO
-        8WCkajZrTppCc85PZHOjecQi6SEqS1n8sE0x+tk8aOb442c65vnK4Pf6mCuPy8v6t96s8kMDJx8s
-        ZjnXpuKKjXs0iGRPF7reRnO6OmP46ge8YKVdrcry6sJXnzOsVHnGn0W6RHR4qFSNfTGbF9FeQZ6X
-        crqKNhma9cWegnTQMLstRDNiqZ2F8NkNW6ZNE+3GnMUzcPvmMl0Su27apkMAbGHdfvXPm26KacEO
-        pwmdW00zui8+FfEyDxSpgcXHSxS+lMDpOebOzjC6cZW84GywgUJPzGpKBIsinxaYbevlKxq++EQi
-        T7KffjbmpBjWoCN/QRzsAqLoVSW//UA2SaYZs1ckNoiGOGJxPa2N4TTQdK3CcoEXLlhZ31+JpVS8
-        3zLbv5nZ/JAfIZzyx4bsOXyqfqcdcjiBL9IFSo1oXA2zAPbgMqK/hNCbF51cooV88MhOdns+dQTX
-        4FaNQKyPkHV/9Mnmen0xq6m8aloJEsBLioHs1iZEf/Ss+CgqukjFh0HtKguUynVPWL2wkn/12wv1
-        zktmztLL+CBeWgCq7Wy2UdTI48ZnjYEu6plthYWKJnRsElhfBZP5MQzelF+MHIZATFlyjKvshx90
-        CIQYL+d7gyi7+6bSOnpDp9VCzOY8CnOw33imPF4tsnnpPlxVNUpCn2ehq7h1zAGcsj6TS6Xp6Hmr
-        AlNFe00jbhV6Ga+at4h+7+cxue+mvaUnahyKNvGspR+Ni/y9Br26u1SN+DObQ49j+Pofoq+iFnFx
-        v3fRV7/Q5+xM3nT1mhBYgypaJ30SDYvL3EOBuoT53kf3uKQW9c9fYWHpsmqOI7cHd7vwiFk2WrYs
-        XKdV5M+nwV35eqBpM2AF6Vt+oup+1Xh8L/c5WK/2gRcg8YqGohdDuU7uTNucCtQ/DVeHmPY6w7dr
-        441ejwRoW7EgmxgKNNW+WsIPv8KhEIw2FL0E9uy4Ysaymo15OqIQdmpnEswDzZsITLmK8pOAmbwS
-        OZfPTIOEBRHxPJIZ88Fga7TeWC5G98bweL7/XJXP00F4+cXTTx///CnZpOOim7H11NF59UqpGNFT
-        xWhovNQsq3K2a89lNVbKskG3M35jHhlaNh8nC8N3/sw+QFVN2dV+Qbi4M2LuloD+4PlVPUz25cfo
-        p9eABJ6F5eFwR09hQyzUpYn39aOjN9ZRm8D5OZbEaJlVTe1I/J8/ZJ4aWGiWL5qtjpYYsa8fjz5n
-        aaKQR/X+D99xeFsaejZejuW7IKJpGaQu+vppslnWdTROj1uAgnvGaXWT3G48megF0gs8ZkdZySc3
-        XzVw3W59huGO0LhUT7kizUuLcmdXeePjWDVwu8Y9u4dRxD+PRRrAPEKIZT0tqu6dWD7Yh1DCfNOc
-        jCYfg1oNjIfMTGdWok8aSSGYTykivlyybLTZZCnivW8ZPl2zbNTd94hkqrdsFxi3bHwMUQ7Sa8DM
-        pNfum38sYrhkvsuCrFhHM3pVMRxRWxFstoeM37a5q8T1xSC7pU89thy0ECF/MrC4vXTVMPZm/cc/
-        b9z70mBHY2vCULYhw2maeuPgtzU6d/ROtsOoZ3NfOhh1dhmx7aGiiGWvfAadnUxislXG6SM4JuAv
-        jR358edk1pMC/vkYE2ckeTc+hixH0bb9+dclGrXjiNXAoZy5/efZcTJmDVzuMSHeNlLR5LCTAMLa
-        fzJPPy686WU2JaSBIzOD2cesD7WHryqTazFnb2cdY5fMhMLevPASXWrOg9dO//E1XW/1XTW9Rc2F
-        VZWeyEYqK4NrxiNVv9+T2bKqV8t75wZwPz8QfUwbiU8+TXO4HnyTed35ns2QGNoff+ofBfxvffr1
-        w8SbV17GPWOyIfeWJ2Lr2qXi2Tt8oXbvDsQJu9bjemifUVQlN7br48KgX/5Tzvfnm+mw3xkSU5se
-        kiX3aZMcw2gePgFF7BY8md2/mm7oiraH9RYTtrujFZoyIwa0VjyVmblXRn0ptgLSLT0mrnwPs7ka
-        gytsanwl+x8fSWrxUm8ntSVWwvVq9fWb8k3bS8xe50bUU2SdQTxmHZ6K/uZNxVofQexez5/+ifoY
-        +ynqTOfAtsqLeVPWFwr6+hNifhZ7Po7zdIZccmxSdNLBaLP4DsjbGRPBsk2zbmZODfrnsiN+erp5
-        3/cX0HYvbsk9utTZhP1cQyf9syOb+8FH43utJuv11ieYhSfDWxq7g6VOGwC69m91xu/PQwBPWU2Y
-        tRaP3ie2sxTw8nkm/uo18V64nHWonVZn33wj4ununqPXQXDYdrkvMl4duAiO+37SxVzsMp7uTlfE
-        Pm5B7HQOslHV+jOwjUfpZOsmHz/2GaMv3qlssx7xYNXZsJ/OA9m1Mc+aH57P9/ebLneyjJjKLgnU
-        24OG10JyiIbNYK3hsace/chO2s2vY1eihavfvvlOmdEIpSJ4kf0hhqosvni1XXguUER++KNgvtYo
-        toQ9baM06Jhxjk2k3j2fedHYZKPSSksoGM9ooz0/Vfm+Iu3np5jVQ5qNOkf9z78R3eF9xZ87htGv
-        Hm1SkfIezfsEHiDIzFxLu0w8V7OClm4iEP8apd04B6IA3+/D9iR5Z81PnxNcu1RI09QYH/2pAU9R
-        cjyqT8VgTj2NcNOIhIdLx7ve67kA3zyCOOf3uxsSAffout35GK1iJ5rXWlxAPhkGXjrXpusgCDV0
-        2FoXKm1YlTFXlxKEi/UZM5BLPry/keUP//o3z5kWU1ugjYyudHHfM8RNawWg32aH7fbOgH71DPJb
-        Q5i+TWg1hMraRgJuV2w3JJuvP1oLIAT5iD8289HUrcMSZGksiNYmEx/sjxkodrZTvn7DiuYdRzXo
-        i3pD9Hnpc/apnz5c7gkhbnJm2RQeah8xSc/+5FOzjQwL/uz/uG47iq2nBt/9QdfJ5VH96jU6YJQz
-        77bTu+VK9kHRlMv0yw/RnBLNAlSXMvFyp0L9PYccvs+nM2EOQvuPb0NhBxXZnu69Nyx0fY0OySem
-        q2614dImSRX0psoH52nuZKO1xiYs+bpnm3WxQeJUXkzg+ugyTf042XRKlBSOvrv+6tHZ+NVTmEch
-        JBrpezT1i1aD9C1TYhRMMYY7W10B7XUNw/Xk8DkKsQIEn/ZUmU2pmx09bdBSfvcYYth7Xz0Z//Ie
-        LEaz9W8//9X/1N1ujhHvr4GvXr3AIjfhIKGzs9JeylA23/qUOxGvL14MeL5FlN8mFFHyrGMQ98qM
-        +TXxMv5cYRG9a/GN1x4s+dhfiQnu4oDodJv3FaebKkCLR5VQvqvjqOm3mfXbz1T56s3p4j9HaNiC
-        MFyvajSd880a/erBKa7bqr/n4lX5+W3SFAof7Na2ALD1IpZRdN4wP1YCnNXyRLaaL6KhX5S62h/3
-        K6aLFBlTtXRywIb/JEbBP9E7tbMADsFwItagOd0YOLOufPM5Kn79+bTtti/l6CHEDLyYvF++DC1k
-        GU70jcfp69gVyD1IFjOSdECsF20N1YEssF0txd5k7F0TlOcG//LqaHp2oggbajwISceJz1HVaco+
-        uqnffP0ezQu4iOBc25Rsd7isppvif9cvQnRh3NJsDGbdhvd4exJ7Lp9cerzLXB1bYjEDaaMxppdX
-        iFy5Rn/8sZgMBlW/foicnzuoeH3elVCplUusK9O8poAVwCGAmAo6jfjqm2fLjpCHbDNtt97orOwX
-        5NEp+KMnx3YJmvytb/QlK89uBpOu4T32JXGjdOwmBrWCNm5DMVrzBn3zFwGG5hSyrW+San4NWYzk
-        g8yJZh6CaP4gJUGqEYW/+p799APC+aqks8EXiB/jB1a//Ej0eVa77/yCP/npthNr3gSz6/74hVbD
-        sM3GZWK4MLGG/um3DLcqsFRiN3uWf/UV3ytFqH7zIlq/N8yYv3kgWphWQcxZdrh4QS1Fcfj0mM3r
-        nTcw6BVwG01j200XG/1jiK7Qxp8X0faen/WDqFC4rD8a2We4NHpap2eQCD4SM/f0TFqSJFE+K3+k
-        4oJv+SSOuYCmjQDM+fIdpbtriPYbWWekKVI0G3Q4K835esISJ49qZN1HUf7kU0UqdkyXr1QxQduz
-        0JL2nN/yzaj+9MC2OlmIbl9Bqpb2UsSz0J6zofbVAjV+fSVHLTANfj0u81/egR/RbZNJP783at2F
-        SlD23ayKVoFwO9y+fif0uteLFkj5nAMqxDmgofmgQsklz/7lnd702VRnOLVnYKZ4drLR+DATts9E
-        wHP90PjXn/hoPGcYT6JhoFExPgXMUXgnREqXaLbL+xXmepWy7XqziPhl7NI//Qv9/HkZc9wqJUyf
-        u0gnTzhmrGreS9S9sEUFfa4MfuyOPrzrd4tlEy8qHt1mXT1kWsIueWXyadVsBGS0fUuc7Pkyhv1N
-        cUE8Ng3D+mwYqxttLegH/4OX96Co/uRJrrbB7E/9DRfPBM671fzL+6vPdz3hXT9btjktR4PTZlHD
-        MvFlcrcy2Rvnph5hcfxkRFdJk3H64emfftVPz4vJMVOgiN2colWQfvPeWoOH0TrEgnUdzfgetGqj
-        lykxX+qC0/3idoXLw7WJLzlFx/eHawLeJp7o5anM2ZtN+hoUhG2qVl1htGIo2EqQRZR2j2LK/vDN
-        t/9Kh68eZYN8WsNnJ+jErno/G0IZYvTt9+GFEM98JJe8AFtgLeVJOvD25y/mp3X6o/f/5NtfvqXr
-        XWUbvXnBI8hUa//wQ/PtP4L6Qjp9bw6RN6ZpaaHVkF/Y9ix03RyoVxcc4RqSg1tto5meoIZ4DARy
-        DhQ9EwNb8OFCtiHbfOvFJBVzDuna7YiT36VuyLW7iG61VeJlwvVOfLmHEmjVr5nfjltvONHWB6cp
-        j0SfxmvWf/MJdaO4l3/rXxTXhfKZAk42fsarsfTuGnrs7xjL7SnIpmt5DcG92lucuKt1N1KEz8it
-        WoERKbc86bPpzmg17K9fvvhwqjlhCurD16m8OvRR8z58dKCu5xJ3soyKf+oBw+tz31B+k9xKggx0
-        NBfsSKE6NtncB08L0iThdA4/l2hkkWL96Y/99NhXX5XyWryqbK+fr0a/rzob7dxNjOd5vlXT2xUx
-        /PpL9Syl1SzptyWKN1rAAn0OOO+M+gV//04F/Pc//vrrP38nDF7NLX9+DwYM+TT883+OCvwzvaX/
-        FMXlP9nyz0kE2qdF/ve//n0I4e9P17w+w/8dmjp/93//6y+QVOnPgYO/h2ZIn//7zj++//jf//h/
-        AAAA//8DADtB0HjnIAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c09bf85ef231c7e-AMS
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 17:29:42 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-kd1j0bcill5flig1m29wdaof
-      openai-processing-ms:
-      - '406'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 3c27a4a0263197ea84526b8aa83799d6
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[359, 74901, 1146, 437, 11949, 3933, 74901, 728, 86, 511, 73,
-      5241, 65116, 4991, 375, 10333, 20191, 89, 383, 22650, 1551, 327, 1810, 1804,
-      80, 347, 11089, 3013, 752, 1100, 73976, 303, 32547, 73, 3696, 3906, 77, 969,
-      455, 62615, 6581, 66, 501, 67, 2649, 12825, 8536, 89, 2067, 85, 80, 70, 74,
-      755, 74, 352, 73, 4086, 3178, 87, 80, 35401, 376, 15618, 655, 13423, 33863,
-      3933, 911, 77, 32204, 2689, 454, 29200, 2176, 1739, 65, 8998, 38844, 4223, 953,
-      14088, 21486, 1316, 12328, 1725, 21486, 24752, 86, 1394, 5308, 321, 31019, 89,
-      80, 73, 5981, 88, 69, 2249, 19072, 23576, 9110, 47154, 876, 73, 2319, 1029,
-      6292, 69057, 2857, 20191, 2329, 80, 6455, 46640, 351, 89, 5289, 876, 77584,
-      73, 2026, 84, 361, 23361, 87, 85, 4680, 85, 80, 13009, 86, 1725, 73, 641, 80,
-      45015, 85, 447, 1072, 86, 22374, 14029, 83, 28679, 73, 70, 5298, 7369, 79, 544,
-      12591, 327, 9701, 80, 2465, 84, 455, 11949, 7881, 74, 4912, 44508, 80, 5298,
-      17553, 31268, 85, 604, 77, 11032, 6331, 9490, 45444, 450, 6236, 1919, 67, 20990,
-      34175, 1804, 73, 41101, 80, 277, 73, 89, 664, 723, 49755, 80, 2191, 28531, 8587,
-      15555, 79, 675, 42818, 375, 3601, 82, 1334, 76, 89, 511, 87, 73, 318, 4080,
-      85, 1146, 80, 983, 796, 12825, 67, 4086, 78, 336, 1897, 80, 70, 11032, 7501,
-      85, 12825, 651, 79, 16017, 80, 268, 69, 4021, 15817, 3757, 16400, 652, 28679,
-      5964, 73, 17063, 80, 9907, 67039, 848, 85, 5308, 76, 657, 65, 1216, 88, 40924,
-      11949, 76, 377, 79, 1091, 258, 343, 4080, 13752, 70, 27515, 265, 1273, 85, 89,
-      44970, 71, 708, 582, 637, 1395, 1662, 83, 27457, 5308, 8942, 1498, 360, 89,
-      10002, 67, 4317, 269, 587, 86, 13616, 31268, 73873, 299, 80, 73, 14088, 455,
-      8480, 1609, 372, 53060, 48380, 17008, 48380, 35401, 40078, 45854, 652, 80, 21796,
-      1551, 89, 9832, 87, 74, 1029, 307, 61057, 85, 12498, 648, 541, 267, 89, 70,
-      24752, 80, 18577, 43210, 74, 370, 80, 830, 4341, 87, 8890, 4890, 31218, 641,
-      82, 6331, 85, 80, 14170, 71, 325, 48186, 16400, 68054, 346, 9991, 78930, 939,
-      1310, 4239, 93000, 73, 2067, 86, 11032, 43210, 8311, 80, 38768, 86, 1494, 2312,
-      92216, 41670, 13028, 48802, 89, 7369, 69, 2005, 73, 7783, 953, 85, 49450, 73,
-      1029, 402, 84274, 1026, 76, 89, 85, 664, 8088, 75163, 376, 20127, 80, 10470,
-      406, 13183, 10616, 36722, 511, 1394, 87, 60933, 1031, 76, 1540, 5308, 66, 939,
-      634, 4991, 29682, 351, 332, 4086, 19639, 15618, 16017, 49450, 73, 87, 20191,
-      10176, 80, 32204, 32589, 1116, 355, 36238, 10470, 74, 2312, 76, 60013, 375,
-      71, 55506, 87, 8671, 89, 11089, 8910, 74, 9326, 3933, 23048, 86, 441, 718, 7047,
-      75, 398, 455, 73, 85, 20211, 343, 1565, 2042, 14088, 69516, 1517, 82, 5697,
-      80, 2554, 88, 2005, 65736, 17043, 677, 19747, 28927, 69, 332, 70, 17207, 80,
-      74, 1729, 2249, 82, 911, 71, 983, 664, 80, 301, 450, 83, 2465, 3423, 307, 84,
-      4317, 80, 88, 275, 3172, 1800, 69, 352, 762, 36255, 953, 3696, 3919, 10470,
-      64087, 46640, 73, 2329, 81, 8050, 13009, 20191, 71, 73, 365, 23797, 14088, 78604,
-      3055, 8783, 85, 12953, 53060, 398, 79, 391, 22619, 540, 6043, 73, 85, 664, 77,
-      2235, 86, 344, 79, 708, 89, 406, 73, 360, 2933, 41287, 9092, 88, 2026, 344,
-      89, 56099, 2201, 1073, 359, 65, 35401, 86, 1897, 78989, 2130, 89, 43312, 67702,
-      3906, 86611, 89, 894, 17692, 85, 30407, 86, 18854, 74, 710, 65, 93000, 13536,
-      588, 764, 69722, 11949, 22650, 86, 501, 24244, 637, 418, 5298, 89, 450, 88593,
-      919, 10036, 4341, 8480, 4341, 9907, 418, 87, 86, 80, 16276, 5104, 18854, 11328,
-      14878, 80, 269, 5298, 84, 80, 68412, 89, 4777, 70114, 575, 67, 4355, 351, 32868,
-      1146, 4341, 1331, 70, 5298, 77, 1498, 87, 2302, 18577, 998, 87, 664, 85, 1347,
-      1729, 9700, 708, 11949, 73, 2302, 74, 89, 73, 906, 1220, 21620, 80, 69, 40078,
-      5972, 372, 16916, 1215, 93797, 22016, 78772, 5289, 65, 7369, 12328, 9092, 67,
-      2302, 70, 7387, 80, 81706, 444, 647, 3418, 80, 73, 1073, 28679, 77, 4223, 894,
-      2701, 70, 6511, 10200, 4511, 77, 333, 27455, 509, 3368, 74, 17008, 93000, 18571,
-      19747, 87, 85, 5972, 84, 70014, 24752, 876, 28927, 18287, 318, 27515, 14029,
-      80, 30407, 1394, 82, 441, 266, 76, 45854, 1498, 582, 77, 24752, 74, 17134, 66,
-      5981, 67, 1100, 2562, 325, 86, 295, 55655, 89, 1331, 85, 1302, 80, 1216, 32868,
-      324, 35940, 1331, 9907, 2562, 9081, 4336, 83256, 46341, 303, 85, 2332, 70, 55418,
-      1030, 370, 73, 3368, 5241, 263, 29238, 8998, 23866, 2641, 80, 764, 5289, 15306,
-      1662, 28679, 77827, 8303, 20824, 35401, 23361, 9907, 85, 354, 86, 48738, 6993,
-      80, 1026, 1146, 1910, 12498, 80, 8212, 12825, 65, 391, 22119, 87, 22873, 8088,
-      24244, 915, 81, 11927, 6511, 307, 509, 52926, 1546, 4239, 47689, 27093, 28927,
-      24037, 1546, 81, 4223, 1320, 5673, 283, 69, 418, 87, 71, 455, 85, 4080, 80,
-      16618, 302, 911, 75, 2203, 48380, 80, 998, 67466, 14029, 1302, 72, 318, 51788,
-      84, 1813, 89, 31764, 32204, 1302, 3601, 44970, 80, 22119, 71, 29684, 4942, 1094,
-      318, 31722, 15008, 427, 79, 3178, 25506, 84, 355, 9092, 81, 4991, 55427, 73,
-      7005, 7141, 49595, 3427, 87, 332, 86, 80, 831, 71, 9701, 76, 44183, 295, 277,
-      363, 64087, 327, 53016, 85, 392, 24672, 8892, 3223, 83, 361, 89573, 69, 1029,
-      82, 12940, 352, 6200, 73, 42848, 5469, 31695, 275, 64003, 581, 2739, 710, 360,
-      40078, 581, 21659, 29238, 29700, 74, 77827, 12591, 79, 309, 587, 728, 9326,
-      8934, 53835, 325, 3059, 450, 83, 80, 8783, 402, 79, 10616, 363, 80, 11949, 1631,
-      352, 383, 21206, 1546, 35531, 74, 42818, 1029, 43505, 1791, 6511, 70678, 4922,
-      564, 56749, 89, 11328, 404, 3306, 76, 89, 657, 462, 447, 79, 447, 87, 86611,
-      8088, 71, 10036, 675, 27093, 84, 49450, 6331, 80, 69, 89, 70, 10616, 352, 354,
-      324, 89, 18577, 1302, 337, 2303, 36722, 1517, 15930, 69, 8510, 18854, 67, 50798,
-      1804, 77, 24752, 18571, 15720, 675, 1546, 71, 4912, 346, 28990, 24752, 544,
-      36238, 87, 2034, 6583, 276, 69, 73, 88, 303, 69, 5701, 2642, 25947, 377, 511,
-      77, 9117, 89, 3306, 65, 60933, 73, 31268, 39342, 511, 5701, 84, 360, 29229,
-      72, 324, 12825, 4937, 65, 2580, 16618, 87, 71, 25013, 2642, 398, 19072, 50798,
-      10056, 86, 85, 10056, 6292, 72, 540, 83, 3906, 266, 13009, 634, 3172, 31881,
-      347, 8480, 46224, 4484, 8783, 2130, 74, 911, 9988, 67, 1331, 1910, 22016, 29238,
-      4239, 47689, 38844, 22650, 89, 544, 22619, 71, 4680, 44067, 822, 88, 85, 2438,
-      86, 3647, 4680, 39911, 11328, 27093, 69, 318, 318, 1994, 7141, 876, 7513, 21659,
-      2319, 2076, 11328, 2298, 4223, 784, 85, 89, 80, 11823, 418, 1065, 300, 55233,
-      441, 80, 74, 87, 24752, 44970, 67039, 89, 81, 73, 267, 23913, 1007, 9700, 65,
-      27093, 28927, 77827, 3576, 39172, 1146, 953, 75721, 86, 455, 87, 86, 18854,
-      80, 8318, 540, 5418, 327, 321, 21796, 24752, 1885, 7737, 324, 66, 566, 84, 1739,
-      1739, 22780, 16276, 84, 80, 285, 894, 86, 830, 42848, 418, 23913, 28073, 20811,
-      86, 344, 3647, 86, 406, 2332, 70, 8910, 1551, 2308, 339, 14088, 69, 7488, 72,
-      12583, 316, 15618, 65, 20926, 11032, 71, 12412, 50536, 44067, 13855, 728, 278,
-      876, 581, 23913, 2727, 44970, 447, 8480, 540, 7047, 5132, 4341, 333, 27093,
-      1320, 72801, 31721, 78930, 462, 309, 23576, 19639, 59270, 32962, 437, 648, 1247,
-      1919, 9902, 1568, 4484, 983, 24752, 87, 418, 540, 89, 80, 34175, 14878, 12940,
-      2201, 4748, 375, 65, 1919, 65023, 564, 43518, 1100, 89, 85, 10776, 8839, 72540,
-      12498, 4215, 713, 36726, 73, 87, 10616, 77, 10616, 45015, 359, 65, 5298, 343,
-      92216, 87, 85, 344, 86, 22650, 953, 23913, 70, 31764, 64305, 75, 876, 70, 31695,
-      318, 876, 85, 28679, 31268, 52971, 78498, 12940, 73873, 6194, 77, 3601, 84,
-      2249, 75, 1551, 88, 38977, 3696, 936, 80, 70, 20975, 5010, 9081, 80, 764, 12184,
-      333, 637, 18854, 87, 7521, 3919, 634, 78, 1540, 89, 1662, 83, 39911, 8088, 4317,
-      329, 70, 3527, 40924, 74, 894, 1065, 18577, 74, 2641, 80, 336, 83, 1662, 59524,
-      5104, 1517, 70, 2554, 4168, 85, 39911, 73, 796, 37406, 89, 11099, 31172, 80,
-      17134, 84, 2005, 71, 28774, 2034, 15809, 1216, 69, 26397, 1100, 588, 301, 4777,
-      831, 2985, 1029, 94908, 9081, 1609, 8050, 73873, 20926, 275, 9832, 64519, 86611,
-      2933, 73, 1394, 7387, 818, 70678, 89, 1739, 21486, 73, 540, 86, 2067, 3306,
-      16276, 7369, 43813, 4341, 641, 588, 35531, 74, 6358, 84, 427, 40078, 94346,
-      8207, 10169, 89, 31695, 13223, 333, 355, 9110, 81656, 399, 79, 7907, 4021, 33721,
-      8942, 52971, 1394, 80, 325, 85, 796, 14736, 637, 6098, 40101, 74, 383, 441,
-      80, 17008, 437, 85, 22619, 80, 398, 87, 80, 73, 88, 5544, 8892, 24244, 652,
-      89, 23048, 80, 6200, 65, 3841, 43189, 1029, 9991, 303, 1026, 81, 302, 69, 418,
-      87, 566, 784, 9902, 370, 76, 32589, 1302, 48380, 501, 2192, 80, 60013, 2034,
-      1065, 41922, 3251, 9490, 1320, 69, 451, 321, 1336, 361, 29700, 16400, 77, 8671,
-      5544, 657, 81, 73, 911, 2312, 454, 1347, 13855, 2562, 80, 1310, 68054, 2642,
-      4942, 8207, 86, 331, 67702, 6034, 92216, 14170, 58781, 1609, 19239, 74, 50798,
-      377, 1310, 89, 564, 8050, 1919, 2857, 6043, 39911, 77, 9117, 1347, 76, 751,
-      41129, 89, 8212, 68054, 35531, 70678, 2857, 80, 9902, 67800, 89, 406, 17851,
-      89, 3013, 72, 360, 24752, 9902, 4341, 88, 830, 4385, 72, 1094, 1108, 437, 7217,
-      70, 3933, 88, 80, 2580, 9509, 73, 29700, 641, 894, 5964, 89, 85, 894, 540, 8783,
-      9490, 67039, 363, 81, 6511, 83, 80, 20811, 392, 3315, 2303, 2642, 70, 3306,
-      2076, 76, 89, 30142, 38041, 4937, 11253, 73, 4086, 581, 8376, 982, 402, 2319,
-      20306, 23457, 89, 44490, 675, 383, 22619, 80, 70, 80, 69, 3415, 68, 8635, 31172,
-      86, 11032, 447, 67, 4835, 65, 26397, 1962, 65, 5469, 343, 1029, 66, 1677, 87,
-      318, 86, 85, 1072, 39152, 1302, 1336, 80, 12591, 321, 7521, 42488, 87, 1546,
-      17082, 17851, 418, 5972, 23361, 69, 38253, 66, 60013, 680, 73, 34485, 989, 18244,
-      87, 398, 5298, 327, 1072, 3145, 355, 3178, 1739, 532, 20926, 81964, 22619, 32478,
-      73, 30275, 392, 10616, 87, 73, 86, 89, 21206, 80, 943, 80, 49938, 3576, 8376,
-      7717, 10784, 1105, 5481, 1247, 494, 86746, 9996, 55767, 17704, 75406, 28990,
-      77, 62604, 5481, 13028, 710, 1273, 53835, 77, 39911, 6375, 15618, 919, 307,
-      773, 85, 24752, 87, 5104, 454, 89, 35531, 8934, 13855, 451, 71, 2642, 347, 3178,
-      261, 87, 371, 2727, 402, 67020, 8462, 1100, 85, 360, 376, 40924, 84, 20127,
-      28679, 26047, 39152, 23866, 10616, 44183, 28927, 32589, 5104, 69, 1146, 45015,
-      351, 13183, 708, 1247, 85, 1310, 98714, 2191, 69, 12407, 359, 544, 80, 74, 6870,
-      84, 89835, 70, 8890, 352, 74901, 4385, 80, 3306, 86, 347, 86, 18244, 98493,
-      3601, 316, 89, 501, 22650, 1273, 76, 24990, 511, 911, 77, 5544, 406, 32204,
-      10616, 70, 376, 4744, 85, 3576, 84, 392, 71, 3178, 81, 20127, 3893, 80, 70,
-      344, 87020, 303, 65, 66362, 41933, 45015, 71, 9110, 86, 383, 764, 75406, 2496,
-      23913, 283, 80, 50139, 80, 56414, 581, 1302, 24990, 80, 7521, 77, 8480, 391,
-      3315, 23866, 24752, 1347, 67665, 73, 18442, 85, 501, 74, 2641, 48836, 19260,
-      588, 1662, 77827, 9451, 86, 540, 2319, 31881, 73, 6634, 564, 7513, 511, 1073,
-      276, 79, 2933, 80, 89, 4171, 16276, 73, 3841, 89, 4937, 80, 7521, 566, 9794,
-      6194, 80, 73, 10776, 14694, 84, 710, 10470, 67, 1302, 360, 73, 27093, 9490,
-      1146, 36068, 9490, 76, 8671, 70, 60083, 333, 3055, 10333, 797, 12883, 73, 89,
-      3013, 87, 21557, 80, 18577, 70, 1609, 14088, 75, 1791, 283, 73, 519, 11032,
-      1336, 723, 51998, 20127, 53289, 88, 402, 677, 418, 588, 85, 325, 12498, 96518,
-      4239, 6358, 4680, 87, 6133, 73, 86, 8376, 774, 303, 1546, 21807, 8637, 4680,
-      450, 447, 20127, 86, 47154, 11089, 74, 11949, 5979, 316, 73, 4086, 28774, 70,
-      21796, 80, 77152, 3178, 9902, 7369, 83, 73, 2562, 26738, 86, 11160, 455, 93797,
-      8839, 1923, 85, 4381, 80, 5964, 347, 869, 85, 20926, 85, 1394, 343, 86, 29700,
-      6194, 21206, 267, 1031, 14736, 67, 906, 80, 49755, 20127, 604, 1347, 277, 24752,
-      74, 4239, 454, 80, 1498, 73, 9112, 35401, 1302, 73873, 8910, 2026, 4086, 87,
-      86, 4341, 36238, 73, 89, 337, 266, 894, 20975, 3013, 89, 80, 61057, 46640, 318,
-      1546, 32962, 822, 261, 952, 283, 88, 70828, 85, 7047, 93797, 5531, 1146, 1656,
-      89, 70, 89835, 2034, 641, 4341, 3423, 85, 1031, 10616, 70, 713, 66, 4744, 94356,
-      28400, 85, 6292, 80, 295, 7737, 81, 45015, 1073, 86, 455, 2319, 1609, 65, 2329,
-      552, 7513, 1791, 69, 73, 1216, 13423, 87, 70, 19456, 1336, 352, 13009, 89, 5010,
-      78930, 86, 13584, 604, 41196, 47154, 21659, 82969, 5893, 21796, 89, 80, 1494,
-      31019, 87, 19639, 87, 73, 16499, 73, 10470, 894, 2580, 20211, 454, 9117, 324,
-      80, 73, 2005, 337, 5308, 258, 76, 89, 3933, 8207, 80, 2445, 77, 80, 8318, 352,
-      80, 652, 11328, 35531, 80, 7369, 8671, 6194, 89, 275, 4168, 69, 89, 398, 343,
-      75, 4341, 752, 301, 94055, 10462, 46640, 267, 51622, 360, 96518, 22119, 73,
-      86, 677, 2329, 12940, 86, 12806, 7783, 49450, 18287, 74, 1631, 352, 86, 6194,
-      3340, 75, 10616, 302, 73, 376, 31172, 9832, 2642, 22016, 5289, 31172, 56266,
-      14170, 81, 1919, 87, 1026, 80, 2642, 267, 1494, 447, 85, 1813, 3601, 80, 8910,
-      76, 1072, 64, 37135, 391, 10776, 1073, 21301, 45228, 85, 16400, 74, 939, 70,
-      1100, 96518, 299, 80, 441, 5481, 94908, 18287, 939, 78, 15769, 79, 5308, 14878,
-      86, 8318, 23913, 398, 327, 5641, 501, 318, 28679, 17851, 2034, 5531, 564, 40078,
-      49755, 28679, 71, 1551, 87, 35478, 9902, 302, 21206, 5010, 75, 8658, 20824,
-      76, 8671, 332, 15720, 418, 7047, 79, 1273, 3972, 9700, 67702, 983, 7387, 86,
-      89, 81, 73, 36722, 73, 47689, 70, 713, 276, 81, 2465, 20990, 45015, 831, 2303,
-      764, 267, 511, 31695, 21888, 316, 11949, 494, 87, 25105, 82969, 4223, 352, 65,
-      2880, 9902, 87, 20824, 5308, 796, 96518, 10333, 71, 398, 86, 4355, 3524, 50798,
-      23913, 89, 699, 2329, 47342, 10196, 266, 67, 402, 40078, 2249, 34946, 17043,
-      80, 372, 66, 634, 7501, 41796, 87, 74, 64003, 53835, 70, 784, 49993, 3415, 327,
-      77, 10036, 441, 67665, 81, 273, 501, 86, 13536, 86, 4168, 14170, 45015, 24244,
-      2319, 21659, 1310, 88, 80, 4239, 70, 1331, 291, 89, 67039, 73, 51924, 14878,
-      2784, 42528, 7141, 76, 16017, 71, 12328, 81, 21486, 79, 1031, 392, 4484, 588,
-      58305, 901, 365, 329, 2249, 657, 1804, 447, 45015, 23866, 1729, 67, 4991, 1498,
-      13536, 3978, 2005, 1336, 339, 85, 43210, 98714, 343, 92791, 74, 677, 76, 15618,
-      876, 8462, 911, 14029, 9907, 70, 346, 3524, 89, 59064, 822, 40078, 2392, 25457,
-      402, 9700, 81, 2554, 14966, 86, 16400, 89, 11328, 69, 4171, 79, 22537, 8480,
-      18571, 44508, 5192, 710, 12812, 830, 501, 17704, 86, 12498, 2365, 19747, 1031,
-      77, 38844, 80, 4080, 88, 8783, 2319, 1310, 70, 73, 57071, 1551, 94375, 89, 28990,
-      89, 4175, 9081, 1056, 23866, 10784, 5192, 87, 4922, 64, 1658, 27093, 2034, 52877,
-      27515, 4086, 81, 40617, 83079, 45015, 70, 80, 19239, 8088, 4942, 2933, 9832,
-      359, 76, 19383, 9832, 86, 5192, 817, 73640, 45015, 38977, 324, 6713, 71, 1302,
-      677, 35989, 9832, 266, 92110, 14736, 14029, 8892, 73, 87, 71, 94908, 406, 49463,
-      33721, 300, 70, 52097, 302, 12841, 2249, 8088, 85, 10470, 40078, 71, 2642, 74,
-      67039, 13997, 648, 39911, 19555, 26738, 84, 580, 18854, 80, 82999, 333, 93000,
-      2661, 540, 85, 6151, 677, 5746, 19456, 73, 85, 4193, 14606, 75, 303, 94468,
-      85, 2676, 544, 81, 4922, 4239, 79, 450, 1029, 14694, 1273, 1494, 1072, 11823,
-      91311, 80, 4942, 675, 675, 10462, 29229, 18854, 65019, 85, 78498, 509, 383,
-      336, 41796, 20990, 373, 12825, 80, 1273, 76, 581, 267, 80, 47689, 5254, 87,
-      14485, 53060, 9700, 352, 94817, 1658, 710, 96518, 764, 80, 82999, 88, 321, 1065,
-      1072, 14029, 38844, 7521, 69, 50798, 16373, 73, 70, 9996, 77, 3368, 307, 5972,
-      351, 1003, 88, 936, 351, 372, 391, 34175, 303, 1273, 398, 75, 447, 21963, 63643,
-      5683, 4355, 1662, 23576, 93000, 34175, 89, 8510, 332, 74, 8462, 77, 351, 87,
-      1609, 87, 86, 1725, 65, 511, 8207, 7387, 509, 73, 31695, 85, 1031, 80, 93797,
-      89, 9832, 73, 26929, 13028, 23866, 25658, 87, 72231, 1073, 75, 13045, 579, 5308,
-      71, 73873, 22119, 77, 752, 78, 762, 68054, 365, 683, 27780, 31019, 1336, 67,
-      2332, 2739, 86, 859, 14878, 2076, 710, 9701, 5981, 2465, 87, 365, 9258, 277,
-      58152, 321, 404, 51622, 300, 14029, 40078, 5289, 1302, 69, 73, 7141, 41796,
-      1468, 7141, 677, 87, 2192, 318, 94023, 66, 664, 80, 604, 18854, 10630, 3716,
-      455, 540, 36851, 88, 1073, 65, 4239, 15809, 26804, 764, 1394, 4991, 80, 88,
-      73, 7864, 385, 82999, 268, 18287, 60933, 86, 1138, 67, 3746, 21297, 74, 456,
-      4835, 820, 19555, 80, 2203, 22016, 6733, 62355, 76, 1216, 5972, 11305, 675,
-      41796, 4239, 911, 332, 9832, 88, 347, 10497, 71, 4171, 1897, 2067, 49755, 20127,
-      33863, 17528, 1286, 21659, 3423, 9117, 1073, 14878, 81, 1320, 64, 1540, 1030,
-      327, 7513, 7387, 69, 89, 4378, 29684, 4937, 23361, 6091, 85, 3315, 31935, 6292,
-      1813, 19456, 79, 9117, 796, 26929, 86, 9081, 4341, 68, 1302, 2302, 6194, 48380,
-      86, 1568, 1919, 359, 337, 19747, 6200, 375, 65, 15618, 86, 564, 69, 1026, 73,
-      87, 8674, 773, 19639, 86, 455, 2739, 1273, 67, 402, 2439, 90625, 2438, 66565,
-      363, 579, 318, 47154, 2329, 372, 12825, 76, 1751, 76, 906, 34175, 69, 95233,
-      1216, 76, 2302, 1336, 72, 592, 9700, 73873, 441, 68991, 13536, 66565, 4575,
-      406, 89, 588, 80, 1073, 77, 3919, 93000, 5104, 1609, 3906, 87, 14694, 817, 33686,
-      7513, 325, 25105, 8311, 87, 25457, 5104, 73, 89, 53060, 894, 70, 16276, 604,
-      21659, 710, 2445, 69, 41460, 7910, 5104, 28679, 266, 38041, 6375, 26929, 71,
-      14029, 45015, 71, 50813, 773, 87, 321, 85, 89, 275, 54964, 73, 38361, 344, 6043,
-      4843, 939, 73, 16400, 1320, 23960, 73, 52926, 19654, 3251, 73, 9117, 25105,
-      80, 76166, 637, 76, 38359, 398, 21659, 55282, 81, 18565, 1631, 73, 354, 1302,
-      14606, 876, 44508, 9112, 74, 80, 73, 87, 80, 392, 31695, 291, 2067, 66, 8462,
-      17134, 84, 5308, 1031, 79, 540, 316, 831, 80, 38361, 29238, 3145, 73873, 31695,
-      581, 8747, 316, 339, 89, 784, 1100, 74, 75406, 1662, 81, 377, 81, 2174, 69,
-      647, 7453, 73, 85, 27455, 80, 385, 89, 398, 1142, 75, 2554, 3418, 98667, 53289,
-      73, 22619, 74, 8311, 1273, 54681, 1302, 2054, 10743, 74, 87, 70, 8998, 1394,
-      28679, 57208, 20990, 983, 69, 3315, 53478, 266, 66, 86427, 80, 332, 77, 24752,
-      65, 32345, 4151, 332, 87, 3306, 4681, 50798, 7501, 80, 13423, 28990, 74, 637,
-      73873, 365, 86, 2249, 89, 85, 412, 86, 1072, 84, 3524, 27455, 4511, 10910, 21796,
-      80, 33721, 588, 40429, 3576, 309, 74, 5289, 48872, 1494, 78498, 55506, 87, 35531,
-      5972, 46341, 12825, 21620, 6511, 80, 38306, 17378, 354, 80, 69, 73, 85, 8587,
-      80, 406, 747, 337, 51924, 85, 3423, 7047, 89, 27515, 1026, 85, 1029, 83, 641,
-      77, 5544, 45015, 437, 13652, 764, 447, 351, 1103, 6733, 540, 80, 377, 544, 540,
-      74, 70391, 10776, 87, 5308, 939, 87, 339, 3178, 1791, 1551, 80574, 1394, 75,
-      12407, 60435, 80, 677, 81, 15720, 50139, 3919, 78, 581, 80, 89, 73, 581, 19072,
-      80, 74, 80, 73, 32868, 69, 652, 376, 582, 354, 73, 361, 785, 21963, 87, 321,
-      713, 52926, 73, 18854, 83079, 1919, 501, 3251, 92216, 450, 4942, 74, 544, 4285,
-      1055, 392, 27515, 1546, 82, 2302, 354, 87, 80, 1910, 86, 10776, 87, 5230, 53835,
-      71, 31695, 337, 4912, 1517, 69858, 392, 3906, 71, 2329, 544, 620, 80, 47689,
-      5241, 80, 73, 86, 9112, 72, 454, 12825, 77468, 18571, 1273, 66, 71690, 15809,
-      344, 6331, 372, 28990, 2933, 88, 7783, 80, 25604, 86, 85, 8671, 1073, 9490,
-      1729, 88, 354, 17704, 73, 38041, 1031, 2143, 49712, 73, 634, 76, 36463, 652,
-      302, 83, 73, 87, 10616, 15618, 377, 88, 73, 17247, 283, 4484, 1029, 2005, 1910,
-      2034, 31268, 668, 73, 48372, 5010, 376, 74, 14878, 81, 26397, 86, 675, 8783,
-      2642, 70, 80, 343, 80, 4777, 295, 13584, 86, 5964, 7141, 71, 8458, 2303, 8212,
-      94908, 5308, 71, 13423, 85, 89, 3306, 848, 1072, 344, 67665, 2329, 87, 450,
-      2868, 1073, 74, 17156, 80, 4223, 89835, 89, 6634, 21046, 73, 14244, 6200, 89,
-      14694, 263, 79, 1031, 10776, 65019, 1551, 406, 76, 6358, 8088, 318, 71, 1804,
-      8883, 10910, 23001, 24012, 80, 73, 95398, 2034, 3906, 80, 12341, 14606, 87,
-      391, 73, 2329, 485, 75406, 24990, 46640, 64087, 754, 822, 80, 70, 376, 269,
-      87, 27515, 86, 5308, 50139, 1395, 402, 3013, 86, 1026, 16400, 67702, 1764, 4922,
-      19644, 65, 4341, 8587, 89835, 511, 91485, 80, 69, 73, 19456, 73, 8462, 728,
-      1094, 31268, 87, 71, 5981, 89, 80, 372, 9700, 26397, 73, 21620, 51622, 1026,
-      4223, 87, 4175, 2332, 76, 17912, 69, 10176, 80, 38359, 2727, 34175, 80, 9991,
-      6414, 19747, 333, 8255, 352, 418, 677, 60933, 346, 70391, 80, 9112, 351, 89,
-      540, 267, 49463, 1551, 2562, 4341, 3893, 501, 73, 1658, 13045, 285, 69, 754,
-      80, 5701, 71, 39911, 81, 73, 953, 83214, 8311, 73, 19555, 86, 9112, 392, 40078,
-      3251, 52971, 87, 28679, 67, 2438, 80, 285, 7521, 50798, 383, 22119, 604, 80,
-      7387, 339, 28927, 41817, 28990, 10516, 1658, 2302, 91650, 26618, 1729, 3013,
-      641, 4991, 73, 2312, 12940, 24620, 36068, 51622, 73, 6634, 29224, 372, 88, 11949,
-      295, 20211, 17134, 5298, 87, 437, 402, 1347, 939, 63643, 20926, 89, 7141, 80,
-      1273, 36825, 8783, 73, 4912, 5972, 85, 33863, 869, 303, 2042, 74, 1072, 455,
-      664, 1394, 19072, 8385, 86, 1631, 81, 35063, 73, 1609, 88, 10616, 67, 64087,
-      8480, 292, 41196, 31019, 316, 70, 939, 45015, 309, 89, 18577, 2554, 73, 1897,
-      41129, 333, 71, 3893, 18442, 24752, 29811, 65, 33863, 3696, 18571, 7129, 80,
-      2303, 668, 911, 87, 10056, 95233, 10910, 1320, 18577, 16276, 24752, 5298, 86,
-      89, 2042, 16731, 38359, 6870, 80, 20824, 1897, 80, 1347, 39911, 1517, 78498,
-      796, 73, 21340, 86, 46224, 278, 1029, 82, 3251, 23866, 67702, 3251, 4659, 30506,
-      1394, 398, 754, 80, 70, 1517, 82, 2933, 89, 43441, 5418, 67175, 1729, 28700,
-      63848, 316, 273, 9117, 2739, 73, 1029, 72801, 3633, 73, 85, 8671, 316, 17156,
-      12328, 12682, 4171, 42294, 5192, 73, 1216, 32204, 87, 70, 399, 21963, 89, 360,
-      14736, 16400, 1813, 21206, 74, 427, 1494, 5104, 346, 444, 84, 5241, 23866, 2067,
-      79, 10470, 11328, 74, 2465, 70, 73, 87, 2933, 88, 3696, 69, 9081, 17134, 1725,
-      8212, 1031, 19866, 77, 3576, 7908, 31803, 773, 43686, 1498, 1658, 17156, 511,
-      22619, 86, 7141, 2042, 77, 6194, 85, 6200, 1658, 5469, 2562, 84, 23361, 65,
-      5104, 450, 67, 1725, 73, 11089, 67039, 343, 5469, 49755, 25658, 2465, 10470,
-      73, 4838, 23866, 74, 66867, 911, 4341, 1658, 27106, 352, 41796, 91998, 16514,
-      1031, 65, 8536, 80, 969, 869, 38181, 12116, 87, 73, 1919, 359, 85, 5308, 75,
-      29700, 70, 80, 2026, 2302, 69, 10784, 89, 1725, 86, 4991, 79, 27515, 71, 7369,
-      69, 418, 62585, 65, 376, 77, 10910, 266, 8385, 575, 29700, 1517, 566, 11748,
-      85, 42818, 4484, 2580, 69, 1494, 8671, 65019, 9258, 316, 1791, 9081, 575, 87,
-      1026, 81, 620, 589, 80, 332, 7387, 24672, 73, 38361, 89, 70, 876, 89, 4239,
-      21888, 83448, 45775, 85, 455, 5241, 67, 796, 42908, 64123, 76, 1073, 79, 564,
-      18894, 2067, 1725, 65, 80, 24244, 375, 45015, 1331, 953, 13009, 89, 32962, 7501,
-      70678, 2329, 77, 39911, 73, 21807, 31881, 648, 57932, 70, 292, 77, 80, 2438,
-      29238, 10616, 22524, 285, 26397, 74, 80, 1302, 911, 1195, 86, 89, 4239, 79,
-      2319, 89, 2303, 37406, 27476, 73, 13536, 80, 2176, 1944, 441, 31141, 69, 1336,
-      15802, 73822, 21888, 1962, 91299, 32204, 376, 53060, 447, 5298, 85, 634, 359,
-      752, 7521, 3919, 87, 1910, 2445, 49450, 73, 27093, 7737, 2689, 8088, 22016,
-      86, 336, 16094, 73, 728, 18244, 87, 10056, 18287, 1302, 69, 587, 81, 73, 13075,
-      67665, 3427, 675, 80723, 80, 52926, 73, 1897, 20990, 301, 70, 3906, 80, 3696,
-      73, 566, 587, 8892, 80, 427, 29443, 70118, 69, 73, 87, 85, 637, 77, 3601, 37406,
-      86, 9188, 2933, 80, 73, 398, 1919, 65, 8587, 316, 3423, 85, 20191, 6194, 346,
-      1100, 12821, 450, 77, 455, 82969, 75406, 4080, 32280, 43776, 49755, 2580, 76,
-      299, 23770, 5701, 5241, 65, 1031, 85, 6511, 675, 24672, 77, 80, 1662, 8587,
-      1065, 4223, 566, 1030, 80, 2026, 82, 713, 24752, 455, 46246, 540, 365, 93797,
-      41101, 17043, 460, 71, 91849, 4991, 327, 73, 87, 1336, 2727, 10616, 18244, 31019,
-      316, 402, 42818, 7129, 587, 89, 31764, 7513, 3306, 21206, 383, 73, 85, 501,
-      80, 69, 3251, 1546, 51924, 80, 1100, 2042, 46051, 86, 49595, 89, 299, 321, 38639,
-      24752, 66, 1729, 939, 1302, 402, 76, 9490, 60933, 4843, 67, 447, 84, 455, 31268,
-      22016, 80, 269, 97523, 455, 491, 77, 31881, 3368, 9701, 915, 65, 939, 8050,
-      67, 3368, 81, 2727, 41129, 309, 944, 76, 876, 2026, 83, 33863, 2857, 2933, 71,
-      2852, 2005, 4168, 73, 87, 86, 34855, 18854, 427, 75, 1662, 41625, 1897, 3035,
-      43505, 3696, 70828, 73, 3415, 587, 77, 46390, 455, 50139, 23361, 70, 2034, 3180,
-      309, 66, 88183, 347, 1791, 1126, 4341, 73, 18442, 85, 89, 5192, 1336, 50226,
-      35531, 2465, 75, 5192, 372, 21963, 2642, 3251, 6870, 1551, 7501, 94055, 11328,
-      1897, 434, 69, 89, 73, 1551, 80, 936, 73, 346, 1065, 73, 89, 1100, 2642, 3675,
-      73, 1395, 352, 73, 4341, 45775, 347, 76, 728, 80, 906, 2319, 88, 327, 1764,
-      351, 1055, 283, 88, 89835, 2026, 85, 89, 59125, 876, 76, 12940, 6780, 53146,
-      71, 360, 65, 41670, 53289, 1751, 858, 15444, 339, 710, 87, 437, 89, 73, 11253,
-      2329, 76, 15809, 327, 80, 2026, 764, 2312, 4991, 18244, 4317, 581, 77, 1331,
-      65, 8910, 92216, 59448, 86, 3035, 73, 2857, 77, 3178, 664, 87, 46341, 70678,
-      3647, 85, 42908, 11032, 587, 79, 346, 1411, 6511, 67702, 4341, 80, 78, 336,
-      38361, 70678, 80, 7521, 80, 50139, 89, 27093, 604, 28990, 49461, 69, 3696, 69,
-      3059, 1609, 44528, 12407, 9700, 87, 953, 7947, 87, 8510, 6511, 73, 70404, 65,
-      2580, 80, 4086, 16115, 23866, 80, 1302, 29200, 73, 752, 87, 327, 86, 509, 86,
-      3933, 321, 89, 454, 2465, 2249, 4680, 86, 1320, 31764, 31695, 73, 14736, 7783,
-      87, 29684, 2562, 80, 70, 80, 10616, 7737, 377, 566, 329, 19285, 3906, 41922,
-      1498, 35531, 89, 16017, 6634, 4511, 2465, 19239, 82969, 8839, 77, 564, 69, 1031,
-      267, 73640, 87, 28679, 24990, 983, 1065, 7369, 89, 80, 344, 8462, 84, 648, 65,
-      3415, 285, 44490, 75406, 7488, 14736, 67, 337, 16276, 718, 29684, 89, 3316,
-      73, 4010, 36068, 4341, 25299, 708, 71, 4937, 69, 73, 22619, 2465, 876, 8587,
-      74, 49755, 80, 1725, 86, 7501, 1026, 80, 4341, 85, 1029, 6885, 266, 1551, 564,
-      87, 8510, 80, 8207, 2034, 2706, 50039, 41922, 80, 12591, 321, 63643, 85, 540,
-      86, 89, 598, 79, 5697, 762, 23866, 89, 355, 14029, 19456, 17063, 20372, 764,
-      31764, 73873, 27495, 648, 575, 81, 28927, 74, 2641, 8207, 89, 73, 56871, 1546,
-      392, 67, 5981, 80, 5298, 4239, 35531, 89, 81, 360, 86, 7911, 511, 8998, 44183,
-      266, 32204, 52719, 418, 86, 1725, 87, 39385, 73, 376, 9117, 347, 79, 1813, 869,
-      74, 939, 87, 9779, 657, 5308, 82, 1609, 80, 15720, 73, 3415, 1065, 20811, 906,
-      74, 87, 797, 69, 32589, 1302, 42051, 333, 27455, 1336, 13351, 73, 36825, 343,
-      6780, 80, 292, 31019, 267, 3601, 5289, 1631, 566, 87, 35401, 796, 70, 8910,
-      15809, 50798, 1517, 41796, 3178, 81, 8671, 5010, 2344, 86, 455, 30863, 318,
-      3059, 11823, 73, 8376, 62220, 94908, 26738, 86, 4835, 1517, 87, 53016, 17063,
-      85, 6200, 5981, 77, 14468, 1725, 10056, 8050, 94346, 2329, 73, 4175, 79, 24752,
-      87, 5981, 2201, 447, 2642, 86, 9218, 20582, 77, 10776, 50139, 5346, 79, 361,
-      1146, 1247, 29238, 1065, 26929, 97523, 89, 7369, 21620, 754, 68, 283, 50798,
-      4744, 86, 346, 31422, 88, 352, 26474, 359, 16276, 71, 1302, 648, 1216, 89, 13752,
-      604, 79, 911, 87, 84, 2826, 12825, 351, 876, 29443, 74, 6870, 80, 82969, 2154,
-      65, 3696, 587, 40213, 12328, 588, 10784, 85, 2411, 9907, 6358, 85, 19747, 332,
-      773, 80, 20553, 587, 76, 370, 547, 547, 4021, 79, 11032, 1725, 291, 77, 32204,
-      54964, 370, 73370, 39911, 2438, 15618, 44183, 4223, 87, 2249, 7453, 89, 953,
-      1347, 17704, 70, 7141, 88, 31278, 604, 67, 86682, 5721, 637, 27093, 50536, 911,
-      12328, 86746, 9810, 73, 88, 69, 894, 7737, 53016, 73, 51622, 40375, 66353, 710,
-      71, 4719, 1100, 24672, 32962, 21206, 61057, 764, 73, 50536, 2067, 5683, 47617,
-      18244, 71, 4080, 1029, 17319, 1494, 16618, 17156, 80, 333, 363, 56871, 12328,
-      75, 12591, 19239, 77, 19639, 89835, 5308, 5532, 73873, 31019, 361, 70, 32589,
-      375, 5481, 344, 27515, 71, 5794, 47875, 385, 25299, 68151, 566, 14046, 44183,
-      39911, 79, 391, 35478, 1347, 73, 3315, 21963, 74882, 89, 677, 1320, 351, 86,
-      41796, 89, 63502, 87, 94908, 983, 51622, 17008, 8088, 5981, 77, 2034, 75, 1030,
-      2701, 303, 70, 911, 17134, 89, 53835, 77, 1643, 64, 352, 83, 80, 74, 69057,
-      9991, 16400, 31764, 73, 22619, 6331, 80, 22016, 87, 906, 604, 26397, 3368, 68,
-      427, 3919, 73, 20824, 5192, 392, 80723, 88, 14736, 26474, 86, 85, 8212, 20191,
-      80, 318, 5701, 39911, 8910, 18664, 86, 708, 71, 5104, 953, 80, 18442, 347, 11089,
-      4341, 365, 6489, 80, 88, 9907, 2396, 70, 6358, 6331, 3172, 406, 4469, 3251,
-      5010, 57504, 65, 80, 1320, 76, 1310, 37541, 953, 71, 7369, 278, 7488, 45015,
-      798, 318, 15930, 29700, 57671, 343, 32962, 89, 23361, 45062, 391, 12940, 96295,
-      35203, 85, 1804, 23001, 50536, 2332, 65, 35401, 6200, 71, 652, 13752, 4010,
-      5701, 85, 80, 8207, 89, 4239, 89, 48380, 648, 28679, 6194, 43210, 29684, 2562,
-      74, 89, 7369, 4080, 41922, 80, 418, 70, 375, 65, 402, 76, 1007, 454, 74, 1065,
-      81, 2005, 71, 11823, 588, 80, 833, 24672, 331, 85, 1331, 9832, 81, 566, 652,
-      80, 5981, 1273, 71, 447, 4341, 70, 1494, 267, 83, 73, 32547, 710, 4912, 8512,
-      24620, 89, 9700, 6200, 302, 258, 18577, 14833, 501, 73, 1347, 18577, 1517, 17008,
-      587, 1336, 6194, 13545, 69, 332, 406, 89, 540, 911, 20824, 998, 2933, 30403,
-      68003, 62497, 797, 98418, 70014, 15618, 74, 14029, 89, 7521, 65, 7488, 5192,
-      85, 1072, 30863, 5469, 1146, 391, 454, 85, 2629, 80, 2176, 89, 27278, 509, 88,
-      30506, 84, 1739, 87, 788, 1517, 77, 2438, 4239, 9451, 648, 830, 86, 346, 587,
-      89, 332, 6438, 93000, 26397, 32589, 3516, 31695, 363, 85, 12328, 74, 3315, 337,
-      1609, 327, 876, 352, 613, 8826, 2642, 1739, 66, 44970, 73, 85, 22619, 85, 1331,
-      76, 634, 29700, 1031, 3576, 88, 6043, 80, 395, 5469, 69, 347, 87, 710, 80, 74,
-      70391, 467, 5241, 370, 637, 69, 339, 3524, 44490, 73, 441, 36107, 4484, 73,
-      70, 2642, 82999, 87, 6885, 1609, 17319, 86, 32478, 80, 64087, 7513, 4168, 9701,
-      351, 6375, 86, 21206, 5469, 355, 1031, 67, 4171, 7737, 4080, 9701, 1394, 2642,
-      2034, 8536, 324, 87, 32589, 42888, 15809, 351, 30506, 13136, 62327, 73, 983,
-      2042, 52097, 20898, 16618, 59524, 796, 376, 9996, 3013, 38984, 4171, 87, 86,
-      9991, 85, 89, 2249, 1286, 22119, 540, 2465, 14088, 20127, 89, 7369, 6511, 80,
-      42818, 28990, 65, 80, 566, 18571, 85, 588, 39911, 2005, 372, 97523, 38844, 20926,
-      80, 18894, 64087, 14736, 1494, 86, 1494, 7521, 65, 5104, 73, 70, 27093, 84,
-      564, 20926, 74, 6194, 385, 80, 3919, 764, 87, 80, 491, 53060, 830, 822, 45015,
-      89, 3306, 290, 37406, 675, 84, 7488, 71, 1331, 30407, 1310, 1026, 1026, 5469,
-      894, 3933, 88, 634, 87, 14736, 31881, 89, 73005, 363, 67, 4223, 3316, 75, 8510,
-      80, 18287, 911, 70, 582, 3178, 80897, 3418, 87, 2329, 86, 31019, 17008, 2026,
-      74, 14170, 3893, 86, 355, 11377, 4010, 5964, 74, 80, 89, 359, 1804, 44490, 73,
-      11949, 26205, 343, 89, 25299, 4086, 38041, 1725, 86, 377, 86, 332, 939, 339,
-      36068, 67039, 333, 2862, 6370, 13536, 3524, 263, 456, 18854, 65116, 74, 354,
-      4080, 33721, 86, 1764, 359, 6194, 269, 450, 66, 3055, 6672, 73, 3368, 18499,
-      85, 2857, 69, 73, 10630, 85, 564, 85, 1729, 5972, 80, 6634, 87183, 5308, 65,
-      19747, 74, 1394, 77, 2933, 23361, 953, 2933, 85, 17008, 300, 73, 354, 8207,
-      52360, 2303, 604, 10470, 73078, 1639, 17063, 89, 652, 18287, 391, 66, 564, 45015,
-      86746, 5469, 8503, 87, 8050, 70, 77827, 45015, 5469, 53289, 4922, 69, 4010,
-      404, 1729, 447, 675, 333, 13536, 292, 86459, 337, 1336, 89, 8480, 6511, 94908,
-      2249, 540, 876, 73, 784, 754, 1662, 69, 7488, 44970, 9197, 278, 1273, 73, 1910,
-      363, 9902, 95780, 14606, 80, 754, 69, 729, 7141, 5192, 21888, 283, 1289, 1662,
-      805, 66, 634, 6780, 352, 79, 1609, 69, 1498, 31019, 375, 4381, 89835, 12825,
-      73, 4744, 78930, 318, 13423, 24990, 370, 19639, 73, 55233, 1394, 3427, 41796,
-      69, 7387, 70, 52513, 2319, 87, 2445, 86, 347, 31695, 60013, 652, 3933, 80, 8892,
-      5289, 21807, 657, 54532, 81, 20553, 28679, 9991, 86, 8318, 2005, 82999, 604,
-      49712, 3368, 406, 7521, 16017, 728, 1331, 581, 7513, 73, 18894, 87, 75406, 80,
-      89, 85, 2642, 5746, 7141, 88, 44490, 339, 1494, 27515, 23361, 14773, 31881,
-      10916, 32962, 295, 9832, 89, 1517, 73, 85, 80, 25604, 21796, 321, 81, 8671,
-      894, 23361, 43505, 71, 73, 953, 41196, 2445, 318, 16618, 11805, 20127, 35940,
-      372, 80, 2303, 85, 2445, 77, 45015, 71, 2438, 80, 51622, 344, 87, 4223, 86,
-      16417, 34263, 80, 32204, 73, 88, 347, 48372, 3893, 39152, 399, 96518, 1072,
-      299, 3576, 69, 98347, 6100, 22016, 15618, 16915, 8462, 73873, 17134, 77, 406,
-      86, 96250, 344, 65, 764, 89, 21206, 7044, 78, 1662, 1727, 80, 30506, 43319,
-      830, 2365, 3919, 29238, 73, 7783, 88, 1551, 69, 1146, 383, 641, 3172, 87, 278,
-      5104, 258, 81, 73, 333, 6043, 73, 1631, 35531, 3315, 392, 9902, 80, 73, 27515,
-      9081, 3919, 316, 581, 2203, 74, 398, 370, 17063, 42050, 2580, 73, 5298, 652,
-      87, 71, 52097, 2465, 8890, 86, 4223, 8212, 97816, 1498, 346, 70, 73, 2580, 18854,
-      78604, 1310, 84, 1512, 25457, 89, 1026, 8462, 2329, 88, 2396, 68, 1263, 75,
-      3933, 75092, 8587, 3826, 80, 437, 4680, 81, 3933, 3988, 936, 10644, 70, 564,
-      36722, 572, 8910, 710, 12214, 31019, 87, 3655, 796, 65, 80, 73, 70, 73, 267,
-      344, 80, 3893, 327, 70, 31764, 1910, 36851, 2249, 604, 4991, 544, 70, 5298,
-      90173, 953, 9991, 88, 60933, 2067, 5972, 42908, 604, 87, 10776, 21659, 9334,
-      22619, 1394, 31268, 1310, 55895, 3576, 4991, 14122, 72, 801, 4239, 427, 50798,
-      796, 40078, 74, 2580, 88, 1910, 74, 343, 354, 80, 444, 16373, 89, 73, 11328,
-      28927, 73, 67910, 5230, 76, 10910, 22524, 44490, 99692, 3159, 14088, 5241, 80,
-      1100, 7737, 74901, 4942, 11851, 10470, 7737, 2203, 86, 85, 80, 73, 87, 80, 418,
-      85, 4922, 77, 10784, 818, 295, 35531, 89, 9700, 352, 87, 86, 292, 49755, 3601,
-      29238, 652, 604, 36851, 4680, 78, 343, 36825, 36068, 80, 1336, 1729, 83, 58631,
-      1302, 80, 295, 80, 73, 344, 69, 22016, 86, 657, 3368, 85, 25299, 53470, 454,
-      8910, 80, 402, 10776, 79, 1662, 2203, 3919, 65, 5972, 35531, 789, 48380, 16915,
-      69, 2329, 2329, 73, 2629, 12825, 713, 1030, 70391, 3646, 2470, 32547, 21878,
-      5697, 80, 89, 22524, 370, 12498, 953, 67, 1302, 3059, 953, 1029, 6455, 2580,
-      73, 2312, 21888, 80, 1320, 1517, 81, 713, 73, 8998, 8998, 22580, 89, 64145,
-      73, 418, 24752, 318, 83, 27455, 80, 70, 266, 77, 80, 3172, 3458, 797, 9810,
-      87, 2201, 2176, 2249, 1347, 87, 3251, 89, 6634, 71, 3423, 89, 80, 652, 95589,
-      9490, 332, 10470, 8480, 21796, 46640, 9902, 35278, 12116, 67, 5972, 76, 4625,
-      73, 63643, 1631, 509, 73, 36068, 41287, 2850, 20850, 581, 2203, 4777, 372, 80546,
-      19456, 544, 81, 544, 7488, 77, 773, 76, 44906, 352, 5192, 89, 31019, 9117, 894,
-      32589, 2347, 65, 1130, 58153, 370, 31268, 65, 418, 89, 16276, 1029, 68054, 2701,
-      69, 295, 85, 28990, 80, 65019, 365, 28679, 76, 7387, 85, 1739, 46483, 72, 414,
-      39911, 24990, 2826, 797, 4484, 60933, 86, 2042, 818, 392, 564, 73873, 48642,
-      3919, 31881, 29238, 352, 24672, 77, 3906, 4922, 65, 24752, 5972, 3418, 637,
-      35531, 42818, 4777, 327, 43505, 454, 70, 1804, 9996, 50798, 15720, 911, 1658,
-      70, 1302, 307, 3520, 876, 437, 5964, 86, 3696, 51924, 31695, 652, 13856, 300,
-      4168, 73, 2438, 80, 1494, 73, 89, 73, 462, 85407, 7369, 21206, 75, 11823, 437,
-      19555, 17063, 74, 2635, 31695, 74, 9832, 67, 321, 73, 818, 6043, 16944, 84001,
-      73, 5241, 49463, 89, 24738, 10630, 3601, 385, 28927, 80, 2933, 25105, 73, 939,
-      13752, 73, 86, 4484, 1804, 10470, 5683, 15479, 70391, 55334, 80, 69, 3858, 67,
-      427, 344, 309, 26397, 68054, 9092, 80, 56871, 20926, 93797, 70, 73, 87, 1149,
-      3172, 447, 14088, 2319, 69, 8510, 73640, 43505, 404, 3576, 38149, 509, 564,
-      325, 21796, 68054, 4223, 303, 15930, 385, 89, 42908, 1609, 65, 27093, 10616,
-      17156, 12825, 2642, 32589, 333, 363, 15720, 89, 80, 321, 85, 267, 89, 22580,
-      1517, 635, 1791, 52971, 7453, 19275, 483, 307, 1302, 64, 940, 74, 1201, 70,
-      754, 83079, 1919, 9700, 71, 2580, 302, 77, 3893, 4168, 32204, 74, 18442, 73,
-      6511, 418, 10188, 906, 2249, 69, 28679, 52926, 7488, 80, 18571, 89, 14694, 66,
-      6194, 7387, 86746, 4922, 83, 6410, 49755, 32893, 73, 3433, 64, 2176, 71, 34175,
-      85, 998, 80, 3647, 89, 85, 9832, 80, 261, 80, 38361, 4680, 2701, 86611, 1056,
-      72, 9490, 80, 3601, 89, 7513, 355, 383, 10616, 11032, 87, 1065, 76, 89649, 67800,
-      1247, 74, 87, 20211, 8619, 20811, 86, 830, 65, 81913, 80, 26397, 74, 7737, 333,
-      8088, 13028, 24037, 77827, 63502, 21486, 581, 5981, 3423, 55233, 321, 63643,
-      85, 89, 3601, 86, 89, 1216, 86, 5981, 33863, 2249, 5308, 23707, 5544, 38977,
-      723, 7141, 40924, 21206, 38844, 9110, 85, 581, 18854, 72455, 344, 9996, 72245,
-      2249, 87, 49463, 3524, 87, 3696, 80, 911, 2562, 83, 40016, 80, 7513, 1498, 87,
-      4937, 73, 70, 73, 10776, 4922, 1498, 23866, 50536, 20218, 587, 18287, 85, 302,
-      3322, 14694, 10033, 24468, 648, 65, 21620, 4341, 2312, 327, 73, 18894, 8910,
-      74, 7737, 3251, 831, 73, 85, 1739, 2933, 85, 2302, 664, 86, 89, 85, 406, 85,
-      339, 74, 9451, 76, 10776, 87, 80, 31695, 316, 10616, 81, 16400, 548, 69, 351,
-      72863, 31695, 80, 376, 17008, 2910, 587, 5893, 648, 269, 12828, 56871, 39911,
-      7387, 17553, 5289, 39911, 4341, 2249, 6489, 728, 4835, 74, 37955, 86, 536, 564,
-      45015, 65, 4086, 73, 10630, 325, 331, 301, 983, 74, 383, 71, 385, 2203, 77,
-      876, 911, 5972, 89, 13752, 24990, 70678, 708, 70494, 89, 4835, 42818, 5683,
-      73, 89, 652, 303, 4937, 86, 12825, 47689, 953, 88, 80, 64087, 4168, 25105, 89,
-      70, 652, 74, 728, 359, 61345, 5683, 74, 3545, 2026, 79936, 11513, 28546, 831,
-      1073, 20990, 85, 1394, 76, 21659, 372, 38844, 6200, 27093, 13855, 8998, 2203,
-      89, 451, 953, 13423, 45015, 23760, 58153, 911, 82, 98347, 7387, 73, 52926, 9907,
-      73, 88, 6703, 575, 4680, 88, 3841, 713, 437, 73, 59524, 1609, 43505, 6358, 93797,
-      1073, 276, 12940, 31764, 7513, 18571, 16276, 53191, 915, 88, 41129, 818, 343,
-      1910, 31268, 3601, 73, 1739, 80, 370, 303, 38181, 69, 447, 74, 1072, 575, 4484,
-      8311, 1026, 88, 5308, 675, 86, 28990, 641, 92216, 88, 80, 70, 25457, 73, 70,
-      5972, 9786, 80, 88, 509, 9991, 89, 5298, 450, 74, 1919, 372, 9092, 566, 939,
-      77, 10176, 52926, 80, 69, 34750, 398, 65, 80, 21963, 302, 67, 6723, 569, 86,
-      80897, 86, 12328, 73, 88, 80, 88, 85, 4937, 75, 375, 65116, 86, 316, 27780,
-      71, 73, 70, 73, 88, 7737, 307, 377, 14088, 53060, 9810, 87, 74, 50039, 36851,
-      86, 869, 42848, 23866, 77, 80, 337, 32962, 69, 6194, 17063, 67702, 329, 5964,
-      911, 86746, 74, 5964, 40637, 80, 1347, 501, 47154, 331, 85, 14029, 8088, 85,
-      3852, 634, 560, 39851, 1662, 14878, 40078, 764, 63913, 10784, 65, 7783, 404,
-      2034, 35478, 391, 44508, 3696, 86, 3059, 85, 31695, 2067, 55911, 18244, 35531,
-      80, 295, 3906, 7453, 269, 10910, 86, 16400, 38844, 869, 23361, 10056, 92216,
-      18244, 2411, 544, 2857, 93797, 86, 316, 86, 383, 18287, 1026, 822, 32204, 87,
-      818, 80, 7387, 575, 8892, 81, 5697, 1759, 65, 7737, 66, 3251, 12498, 437, 73,
-      2302, 303, 88, 32478, 86, 80, 47689, 10056, 7521, 69, 344, 96518, 509, 796,
-      87, 73, 89, 70, 73, 70, 19239, 344, 53289, 4657, 80, 634, 77, 6802, 582, 67139,
-      728, 89, 59367, 3893, 27455, 70678, 501, 14606, 80, 15618, 360, 8088, 18442,
-      455, 21888, 58305, 347, 89, 347, 74, 7047, 72, 292, 906, 78, 581, 14088, 360,
-      375, 73, 27476, 20127, 764, 71, 28679, 936, 80, 89, 36825, 80, 88, 1729, 983,
-      1065, 37406, 97523, 4680, 1897, 1347, 87, 89835, 31881, 70, 355, 55233, 22650,
-      7349, 9081, 267, 18854, 40952, 337, 14736, 5964, 74, 60933, 375, 40924, 10616,
-      70, 3841, 337, 73, 85, 33367, 31764, 677, 80, 44183, 372, 71, 22873, 637, 88,
-      80, 7488, 66, 2249, 70, 509, 94055, 19639, 81, 713, 21486, 85, 4777, 93797,
-      1273, 18287, 80, 73, 2438, 38359, 3858, 9991, 9081, 89687, 85, 20824, 87, 41622,
-      22016, 392, 797, 17008, 18571, 27515, 73, 82553, 86, 621, 19260, 1146, 89, 29684,
-      324, 71, 48233, 80, 2067, 28546, 8998, 68467, 540, 6358, 73, 86, 2067, 87, 14878,
-      784, 1791, 11032, 56871, 318, 1551, 4991, 63345, 796, 26397, 1100, 77, 324,
-      89, 4922, 76, 754, 80, 12591, 533, 2026, 84, 1498, 1804, 73, 86, 418, 654, 74,
-      8212, 675, 6200, 1320, 73, 392, 3251, 6375, 1756, 88, 351, 67, 22650, 73, 454,
-      69, 634, 87, 6511, 34175, 80, 3172, 9112, 85, 15464, 799, 68, 21963, 38359,
-      23797, 74, 6489, 70678, 19456, 71, 42818, 89, 553, 22119, 66867, 5469, 1764,
-      31697, 953, 75, 462, 25105, 488, 65, 27322, 73, 67702, 25299, 80, 4010, 92216,
-      4010, 74, 1910, 9907, 3172, 42528, 352, 302, 273, 75, 302, 68, 2113, 39911,
-      76, 1625, 17851, 80, 4625, 32752, 784, 80, 637, 88, 1336, 6091, 40078, 80, 52926,
-      25457, 418, 70, 4777, 92562, 11328, 11949, 46390, 10056, 74, 380, 73, 89, 641,
-      87, 71, 728, 266, 5972, 1302, 70, 19747, 67, 796, 327, 70, 1100, 4748, 266,
-      34175, 450, 361, 85, 8480, 32204, 69, 604, 1791, 447, 544, 85, 267, 437, 52971,
-      876, 76, 12821, 647, 80, 61828, 2580, 894, 87, 40078, 8480, 325, 14736, 63502,
-      46640, 544, 1331, 3172, 85260, 894, 69, 1302, 89, 728, 86, 85, 1073, 377, 8671,
-      19456, 80, 784, 87, 84, 77827, 713, 94869, 8998, 11949, 1729, 637, 21620, 84712,
-      66, 7387, 6043, 84, 329, 89, 309, 2201, 1498, 55233, 2332, 5192, 89, 38977,
-      566, 27515, 80, 69, 677, 25105, 762, 73, 70, 74, 677, 1247, 71, 25457, 80, 78,
-      300, 1725, 45228, 85, 6511, 74, 637, 45015, 2465, 983, 64087, 1302, 713, 11377,
-      40924, 89, 46341, 983, 85, 41129, 1791, 7141, 41796, 969, 14898, 73, 10056,
-      86, 511, 14736, 70678, 4086, 604, 71, 302, 78, 1662, 65, 5010, 79, 540, 2465,
-      7910, 333, 87, 4010, 86, 5683, 85, 406, 876, 20990, 11328, 73, 637, 81, 418,
-      295, 295, 86, 45015, 28774, 8892, 80, 9700, 53835, 25457, 13423, 42908, 77576,
-      797, 85, 657, 9701, 96819, 2438, 70, 59194, 73, 441, 52971, 17134, 86, 40153,
-      1494, 10056, 87, 73, 4937, 86, 375, 1804, 75, 90377, 73, 57504, 1791, 1897,
-      23866, 273, 3036, 292, 402, 21963, 983, 38977, 295, 4080, 80, 29224, 89, 752,
-      74, 80, 830, 8783, 2933, 45015, 7369, 77827, 1395, 73, 1394, 1394, 67, 5010,
-      77, 10910, 2933, 15618, 19456, 32962, 85, 5972, 88, 40078, 8890, 80, 12654,
-      12498, 80, 3306, 258, 71027, 13066, 85, 50798, 80, 939, 2302, 22374, 19239,
-      1302, 87, 73, 3418, 4010, 89, 501, 92180, 73, 63643, 321, 93213, 84, 21659,
-      303, 81, 73, 2438, 83227, 86, 8998, 65, 458, 1302, 14736, 45015, 20926, 5964,
-      32204, 784, 25013, 80, 4239, 81, 747, 21659, 652, 604, 30506, 7387, 710, 9490,
-      1494, 89, 1336, 73, 2933, 88, 15278, 2580, 1100, 275, 8658, 70, 74, 1739, 437,
-      27752, 87, 73, 41139, 74, 5759, 7369, 3935, 12328, 17270, 354, 85, 14720, 292,
-      9117, 31268, 2192, 88, 45854, 376, 764, 6511, 1030, 24470, 51622, 6358, 23866,
-      10616, 3919, 70, 5010, 67800, 980, 21888, 581, 77, 4239, 375, 295, 852, 74,
-      13183, 80, 11160, 77, 2312, 89, 3423, 65, 3427, 7453, 80, 74, 20176, 8747, 28679,
-      80, 1625, 71, 1146, 6539, 78, 648, 79, 1331, 85, 16400, 69, 11949, 80, 11251,
-      6043, 797, 652, 11032, 78930, 332, 74, 89, 392, 59524, 85, 267, 80, 3368, 24041,
-      83470, 796, 41922, 292, 86, 2668, 82, 9902, 689, 1900, 80546, 19555, 77, 39911,
-      81, 9786, 2319, 89, 745, 5701, 78, 336, 9907, 70, 3601, 88, 85, 5298, 80, 9672,
-      13846, 70, 329, 49755, 375, 85, 3013, 31881, 11377, 82999, 637, 4341, 398, 88,
-      88548, 16400, 11377, 39152, 80, 1631, 45015, 6358, 85, 8998, 58305, 652, 78930,
-      69, 73, 830, 70, 74, 3368, 657, 9490, 89, 752, 69, 26235, 86, 652, 3306, 72801,
-      73, 2312, 5544, 69, 752, 20211, 392, 50397, 3601, 773, 3368, 43389, 1394, 1910,
-      544, 8910, 81, 64087, 331, 85, 23361, 277, 2303, 332, 80, 73640, 2465, 1919,
-      67039, 74083, 604, 1791, 13536, 74, 14088, 587, 1195, 269, 1751, 42528, 80,
-      35401, 89, 3368, 94908, 728, 85, 89, 46224, 447, 87, 18442, 4341, 78604, 4922,
-      12825, 331, 283, 309, 85, 12184, 2303, 14088, 406, 634, 346, 88, 31764, 26397,
-      3368, 60013, 713, 70, 1739, 87, 587, 1029, 2933, 78, 42930, 2003, 86, 48380,
-      71, 17008, 5683, 24470, 8998, 74, 80, 344, 5010, 93000, 501, 40762, 4922, 66565,
-      80, 344, 76, 575, 2042, 76, 1026, 509, 73, 1804, 939, 7047, 5010, 92238, 292,
-      73, 354, 84, 70391, 5972, 88, 846, 2465, 37406, 89, 14088, 100120, 14878, 20990,
-      564, 31147, 983, 69, 664, 31019, 11823, 3418, 14170, 392, 49595, 7453, 40078,
-      8998, 36851, 80, 38359, 20553, 67039, 1662, 14878, 80, 44067, 2423, 316, 80,
-      13634, 24672, 66, 1029, 79, 3696, 24990, 80, 300, 17008, 80, 70, 901, 764, 1336,
-      76, 20926, 74, 11089, 23361, 14029, 454, 1029, 637, 18571, 85, 9081, 87, 86611,
-      509, 953, 80, 36825, 80, 354, 89, 7387, 44490, 4239, 7521, 77, 1910, 9907, 654,
-      42050, 1029, 52000, 65, 1791, 73, 301, 70, 581, 88, 73, 1517, 8480, 73, 635,
-      346, 20990, 24244, 85, 80, 74, 89, 16276, 93797, 86, 953, 87, 92241, 677, 85,
-      36851, 998, 2580, 7488, 87, 44508, 5490, 14029, 85, 26738, 10033, 84, 7387,
-      76, 2562, 66565, 728, 75, 30728, 5964, 74, 4239, 78, 292, 80, 88, 80, 4942,
-      24672, 19239, 1146, 1394, 75406, 73, 89, 1302, 77, 5104, 9864, 87, 354, 53450,
-      80, 73, 1247, 7047, 70, 2034, 77, 70391, 78498, 370, 6634, 20920, 9117, 79,
-      10470, 5118, 9490, 392, 63643, 89, 540, 67, 4355, 80, 634, 85, 23361, 92715,
-      2580, 85393, 80, 70, 32752, 46640, 2554, 2826, 4171, 4239, 12940, 2034, 88,
-      9112, 88, 18126, 1091, 78, 1100, 377, 93797, 13045, 365, 23361, 71, 35035, 32547,
-      13092, 85514, 1494, 73, 2727, 85, 14485, 87, 74, 1031, 7717, 80, 10333, 70,
-      80, 23001, 74, 398, 87, 1302, 64123, 86, 2034, 5308, 85, 42818, 303, 5923, 88,
-      5964, 7387, 13009, 51924, 87, 710, 69057, 325, 24752, 44508, 16510, 4937, 35531,
-      9832, 36825, 1336, 339, 69, 66945, 73, 1247, 86746, 89, 5192, 71, 25299, 455,
-      77, 455, 3315, 402, 1751, 14606, 819, 9117, 731, 30407, 28679, 2739, 2130, 331,
-      4719, 92238, 79, 2249, 1804, 75, 2329, 575, 6043, 84, 327, 75384, 5104, 299,
-      5717, 81, 466, 4752, 86, 89, 80, 1302, 652, 65, 4922, 544, 7141, 87, 46790,
-      321, 32868, 69, 6511, 88, 911, 466, 75406, 3524, 444, 2933, 71, 29652, 20990,
-      69, 7369, 17134, 69, 451, 372, 318, 953, 87, 501, 1302, 1804, 76, 365, 5972,
-      2249, 28679, 80, 14088, 1029, 28990, 372, 100111, 6634, 63813, 2329, 2329, 331,
-      27520, 80, 347, 8462, 46341, 44490, 575, 5010, 24470, 75, 3415, 3524, 454, 4381,
-      566, 713, 4458, 64, 2319, 74, 3919, 86, 1026, 75, 11823, 89, 634, 14088, 69,
-      1247, 88, 292, 321, 302, 80, 3988, 6634, 73, 41196, 2191, 88, 69, 7387, 1739,
-      74, 27455, 4010, 84, 2249, 76, 2026, 85514, 752, 17008, 86, 329, 4484, 278,
-      3172, 25100, 43505, 867, 81, 939, 27515, 64381, 70, 80, 22016, 86, 10776, 89,
-      4908, 89, 70, 14092, 830, 25457, 427, 754, 75406, 20218, 1073, 5230, 85, 377,
-      74, 4080, 1233, 19639, 12498, 39911, 2629, 12158, 13536, 582, 14170, 884, 85,
-      38844, 79224, 4168, 87, 71, 2249, 73, 70, 80, 70, 19072, 953, 56029, 2641, 69,
-      73, 2465, 36851, 73, 3059, 17008, 20824, 911, 80, 69417, 18442, 87, 51071, 360,
-      89, 8480, 268, 75, 3906, 89835, 1073, 75, 9117, 1919, 88, 360, 96518, 8462,
-      28679, 29700, 70, 1302, 65, 7488, 4239, 65116, 74, 21088, 2465, 10784, 85, 936,
-      38359, 3647, 27278, 89, 8480, 8480, 3906, 1631, 1494, 295, 80, 318, 1631, 268,
-      8050, 89, 3919, 61057, 77827, 39911, 354, 416, 337, 89, 9700, 69605, 6200, 1919,
-      69, 7513, 73, 26738]], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '44957'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWxOyOp/l799PsWvfOm+JICTsO04CAiYoiDg1NQWICKjIIQmkq7/7lD5dPdU3
-        XhDkEJL/+q2V/Me//vrr7y5vymL6+5+//n7W4/T3//oeu2VT9vc/f/3vf/31119//cfv93+cWb7y
-        8nar39Xv9F9j/b6V89///CX895H/f9I/f/0NxKClxgp4EdfwvQYlDBwa3usln99ibsHPRthT/bmU
-        YN7QvQGd6pBRa3NdIgZyzYUZLJ9km2bU5HVlJbCPzgNaz+LczCxxQ7g84QabxFUHhmxYKtWq3mAH
-        vdbDcgHvlUw3jkPUdbpv5tVkMxjHpYrY0DYmF2ZuwLN8V4gUaC6fywe31WovjtSYmevTdR8sYJ34
-        EhJvzSun5/wUACO2a3pAVgqoEB8ruFRuhZEvSjkRVg9PlTQkIm7Gg0k3uHhBefPpSRs6SzQbpSfA
-        I2sDjOqK8slscwM0couwi0DKR/uVBsol2RLymo5mxI/uo4ftVTZwUEq7Zk7EPYFed68Qh1o8zO1m
-        pcDkNQ/Ub7rHwPlQi2COj5Qe/N3DXDbWnMK3xxhZT7eQTzu4bmGFrgv1QnLzZ80+JwAb9IEkYsjD
-        +EgHF949uKV3sbF9njz6FFqHUsDG9dNHizhVBqhGuODdDTyaKciPNWwXqSRsPVScry7bFG5hmhG0
-        imROW0kW4PAWTWpJeBsxrLAACg25USw2L3/UkF3BLGkOSAblNMxhsl1gYxcuDXdP0iwPnEIgP6yW
-        KHIY5LyCWQvabWHgkzm+cuYLvgiIdgSo92Gez80tiyG9nq/U+LZ3xHcVcE/ICwmb6ymaZbEt4Il+
-        GAGOa5qb4xEI8H33dtQ3/XXOr/6YwCx5HMhqPRlc0BCqFdGvR3wQT3E015+yhkqt5jjzg35Ypqtr
-        gO/7o1ezTD5zV5CBWHM6jM+9zYdhPZdw38wXethusMnNXBPUwNwZBLR6PdDTHJ7Uz21XIqZtM3Na
-        baMtXHa9Tk1tZs3YOLWmHmOxRKoLnGihWR4qyWGDqXW5PCLSypkIk3t+Qo9nooONddgTaI/LHQfA
-        DCPWP0QN2qukxm6TeLnkf9IOAFfhGC1oBGz3dkKo+6aJd0YrNNN8NGO4xOmC/SI9DVIzfzrFyayQ
-        FsbF8QneTiGkZhDiK3K0YTPEqQgk543QwqIajLphxNBiL0B3I94MU5ajEbLSrLF3OUoDu6iLslZx
-        aFCjeu74om+ZBe/EXmHUHKyIPcVOBNsz5kQRp3noay/WYPDoDHqLw6aZKx5mQFAVh2pv38iJrKU9
-        DKTZpwcVtPlybswUon15xL/xvbBFEuDNen/IahcVnLtJZ8FojiXsxLszZ8nZOsF3Ne6pfu5avsSd
-        m0Cujw0OtMfDX86X1UnRr7OAz+en6vPbKSSQt8IH38aLHkn6uIdwRt6TLGDI/T6DgQvy/JAQOrIi
-        Z49mGwJNvmkYb5fJnCRWnGQNnk7f+rHlvLpCF5wlYpPv980XVjUlrObExbuNfvGXQ8xf6uFpQWxT
-        Zx9x/xP2ilxQhP1qjnJWRy8EJ8cYqNW4WTPn5iZTXSfTkXi/BjmPxjwG4bua6K65RZzMq2AF58dp
-        ROK3vizdZ4QwiIcdEdO9mi9AH7ZA259VtLg7J2dinDNwmEhDzQM8cQZqJ4VetM2wdo6Gpr/qexfG
-        2q4jomhagGb2O4X4Kb2xIa0Rn0kOTxCXN0QGLXjzwU06G+7y3ZXMN02N2GXv2nDINjZaeif1Z7ON
-        NPklo4lqVDX5nGOvAmrS59iyFtGfbqt9/NMDqtGQ5ktuxJnylHc9DrbVGXBNNS2IwMWl1oWvIuZ3
-        KwJi0r0RgG4V9Zr8dmEY7VPqkc5q5nJyEVz5cYudKwB8iQSrhnmpdfQ2y9HAz3mGIPDJDlvbj95Q
-        r9EK1Vt3Di0E4dOwqxclMBBUGTvf+kme60GDcXMgFJ12q4guhoDgvagARYCtzYGJOQP10xGpE40x
-        4JFUFQBW1EQ0D2ST3W6+Ap5YzChiqQ0Wd9O3YIutDzoGYhNNVD4vECH9Qm1/3ZgzvlBREedyh3VV
-        LpoZFeMCt5xxJBkbO5ql08Lgu0g41fPS47woYwXowLXp/Xh8+XPSw1bJmtojnciihpdpp8A+8VS8
-        t0s28DFNLKiGgk2A/NwNrDiKDF5UXcKHZ/4ESzGYBgx225gGxuXtcymHK/jpNgHeB9Nl4MeX6cKm
-        03zq3W51PqVG7cKxUZ5EKUw5GlvproCWnC54D8qpedpQq2CumyMODmMTMflMDSjebIoNmGLAkXso
-        gEcsi0bb2I3YQwx6SGTjiXW+2ud8pO8UFH58JavEMHy2Yb0G1VLjeC/tAi6A2slgnuOEMF028q8+
-        Zkp6ZjWqv/N3roWhB9uwm7B/3Ujggy9vAYSyzdCczEnEzHnvwmCnxIQvu0dErhsOYYXyBbF0feEs
-        nk8VRCs3o442jA2/7AoXBBL38d7zIB9CyTpBB2+f2HuIjcnOSLDBfnPOsB8p1jD3Bq9grF5TtJ3f
-        hs/bx72FG8pW1E0zbDLIxxEkdiHR/ePx4cuhWi+/90Hr7S5tPryuOrW4HLfY63HDGchdD37rCz6s
-        ho3/dK69BQ0FD2hzfqomLQ/RAimrdaIuL9df6vemht7RcWnA8g7Mct+FIOu3NUZ5G0dUiK8V7PZd
-        i111xOZXP05gXgSKjT045PM7lVuQ8KXDZqav+eQY4QKyimypkXPLZGD76OAUbDTsbdrKpGonV8AX
-        kiO2hFDj8+v0yKCiuAa136UcsewNRcCzfoWtx3pvSh/5c4Ju4i5YqzoHLLc5CoD2VlR8GC96TlTW
-        E2g1zxU1zuFnYPo16uFNb1/YPfmdP/RCm8AsogBtQ53k86m5eqDYVRY9njsL8Cm4bqEjPRfy+FBj
-        WC5t2UOopZheSeRH8zArsUp8ImAcCdXAb+1kAQbbGttz35pUH/UV7EvW0sCp0oYvz6yH/bwd8KHe
-        +v4871YB+F6fGuK+49OubxCUBGWNDao8wDKJnwq2JLzgwBTGfL4XKw9cDzeC5Pup5kzcow5szweO
-        jds5adh8kws4JqAjauQRn43WlsAtzDLs+G+Hz7I+d/CQxD49ZPZnWPZgYXDgc40eswNMNvA8BuMp
-        rhGorJKPWNkG4KeXwvngNCzbJSlUpv2O5FsfNvMpEBVYetKGtCs/4ptGASKMKONk4/cfwF5zs4XA
-        3j3oXu7eAxdUzYPJmGL6qxfjtx5DF9oedY57JSff+QeLjbAl8rifB65Xggg/oCvpIZLqgYnVBcKb
-        9fxgqwPtwEXv0kOzjwlS/Z1uzvNODIASiEeiNJEbsebpV6Au/AzJxg6DpcnlBMof4qNJKEhEb2CV
-        gqm8mmQTFkMz8Q9VlN7JAupImybinwZr8FAfe4xKwRwmEr69P/NXw1b7490Ksly7Y+N+Z9HkSP7r
-        xyN4HyfO8DSvOwV2z/REfYVIPk3DxwlSE4XYWSgyGftsethPzZmEoeJxvtJLD7DZ/2BbNFv+uqvg
-        BTDTT1i/abdo2Spaqh4/eYu4dSvAfK3MHtzelBL5BMtouZZ999M7JH/rAXPMmYEfr+0df2eyUNdK
-        2Kz8GE3lvY+4vCYd0M1uoNdKOOdLvbYFqKeGRg2s18N8vl5O8Muj1NkiKxfWgqtA28096triAL79
-        YygT7k40+/IcvQExA9trGJOxuqYmCT2jg63vHgkQ7ixfulu1wK8fItBSdCCqDrSh4ThPon75SXhB
-        WYMd5RM+fPFgZB+1A+o4t2iwnt0wfvkV4HyA1N4kLF/WhmarEagfX15so/lguQFUg5IheNq1/myy
-        OwJfvsTXve7n8+HxIUC7ugFFWV4DLqiuB61p7qh5F/bNsDxPHZzdOKSJZdwHtrqUpXJPxhcSZm1u
-        WLgBIQgOpxHrRr8d+EhYDFftUcOWdj3n7IMfHZDJ8Ui16PbMudsJJfjxm2/npKHrEyggF7ORHqz6
-        1Tye5fSC72gKECuXxzAfb+4KmikbkDyKL392F7uHws6/EQl5RsOFGRgwtNI39eXns+FW4iuwSp83
-        rF1E219W12OmLpfAwt9617Bj+YHQPmcOWrp+4VxN3wXc3/oD2tytyJ9/fk0/I4KY+/D8Ga39ACKR
-        Gdi567O/6NutDXVfN6ejX2QmP+cnpCaZENCyrvCX54QQzm4S4oN+uuTTXXBK6DTGSDVfOEdsc00J
-        XJ2IinFmOoMwkiQF8MLe9GAWs8l3R3sF7+tBxwY9HCIqe1yE7Ik8aqnlOmeiqCDIa/2Cd5qumNMH
-        rUe4Hpac7vZVaL4XpMcq0sSerI4fPVpgIGugUA8hNsbkbs5nKtcgNhQFbWNSg2XOSf3zY2hR6k/D
-        T3N6AmcYBUiZ30XOF7RPYF3CkdpB2prLfe+yP/0P8pPq83lOBOV40gN6sNNg4LdTOgJXDrc0pCGO
-        Xn7UxVC03Jhq/MNMeu83ITTb+op4dfAa1u2vBeQXaSTSUw0axiPpBX0yjXjf3Xa5oJVhCyq6WFTL
-        rhXo7XYXwq+e0EOX3Yaff4B+vSDqqiM1WSvdt3/88VWNOZ/pe58CPJQ+NtdhM/CXfLDB7J+jb76A
-        AbspUwYG+zaTuWi1fKnfagVUUcVIud3qiNZVEMPc7sLv96WA66grwW2lJNjqZ28gfJuuoF8zRO0W
-        rMA0WmiBUbF+/OGj/hRm4h/+0qBTmkuVnz34Xk7B16988i+P23Cy8JXqTSOB+QVCQz1SzaVaqPSg
-        j/zbFvZrJ0XCaaUNwpf3gCZ+CJm7szwwmJgICtrrQvdriURdAwsBipYX0y/vDmPvtSMcxuseGyyq
-        +bKpMwVc9vJM9aKtoiWmTgvqt+xiFHZXczEVM1GrMtC/eYneSJqbnsCFRDZ60rvVCEWtiao4bCrq
-        vk5PwBaQQfDVD4zfq6whVX5zIcPhTLYFx4CZGVEU8X3KsO28jIitpi2B3/wIB5/7lC9b3SGgV+oT
-        9S+vELBLHhfQkd4LtXXT4VKyNrdwoEFOVnxYTMaCwlVKiByK5bs+LDfYxZA8ugORpeWR8+EWaZCE
-        lkezk/syB6/RSgh8WcT7tYTyZffxArhv+AWxt1/nnGy0Wt3lzvXr597R0uunGiT364n6lVUCHqus
-        U1GuxfiP3iZnK4Rp20RE0K6bnI5kG4MbmqPf+PYZtc0VKM96hY23W0X8+PJdyOyPh9/PcOt3Ryft
-        oCHkCdaUp9/001CkUC/eNjbAAHx2CXEMss4Jfzxk9vezBSFBlU0PvZr6X1724HMF1gQ+ue5v9MvS
-        q/i5eRPhcRIGZtwHEci+71O8sTXAdyulhsnnpeLD8nLN6XHxvF8+Ri14nvjMPODKH9CXFJnWGfDe
-        34xw8Q4OeX/5o/fuY60cT2aAcbVu/MXcpRU0pKCj5vVIzWllPuw//narM3EYG5Z2UJEShu29G4NJ
-        VUNRBX0h/td8ZRtvgdtO35HXV8/p85ynIIg/O+yb/j3vtDJ9weBjZIShS+gTxe4EWGa9hQ+9ujWX
-        8Wn98fM4kC6tz97ncwd5FL6wk8DWHwWHZ8pH9zRqf/NI1h4UBI/UcIngn8NmdhfUb8eiDqhRLjkY
-        zyaBcPGwg11rXEwWu4MCpSaBZGuNiz/2k+lBsb251JA3Z1+6i16qfPUcm9KbD2RtuDYsSHGnv3xy
-        esjdC+oH8Uwet+nI57dehdBwdk9svuWk4RjdOuUsKAIONmruc3tnLNBRUYLN+tJGRCiMEbRusibS
-        l4f4DAcIM4cVCGwCC/B1by2gFpQdxe2A80ncHBGQ3bP85//8lQ8t7D7rlOq/++Owa8Gmfh3JM96M
-        +ZI51xhazXtFVp/Cz2fn2ttQKtUX1ZNZjEbeXwXw5Snq3HzfXCwtf/38O6p//TWtOQHf58GGumtz
-        qhRH78eLNIBy0oyut4dQ219UIrIwN+fG3muw3TUTaQel+JOXArG9u9Sf4Xng890rIZAPb3pwNkc+
-        OHUb/vwA1aNdb3LvwmPIb0VIr1rnDSK5pwgww7LQQ3+8fVbdOhtOcGXiPb9Ww3CeXi/4zT+pDWQP
-        yJdoCGGGXQHvKs8dlpOsl+DLN2SbT0rEW88OwddPE0EYb2DWmpXwh3+8wpRzvhgwAF0kYrIxWmGY
-        fvwn7PY3rPuFYrJEqslPL7ArmmufHTZ3C+4EfYODY0qHEfJ2hKH+PiN569cRC3viwTGRO+p01Ttf
-        DtJJA9+8E1uuscvJVnfGnz6gzUsjA4kLjkCprgH6fq+I9dswVIPCvH155OgvK2PtKbtnZJHFxg9z
-        SdOsgKu3dUL8ABdOXk3BwHd8o3C+J/noejqEwUfLyDqXp2apvUKDtUIyukdO1fBQCkKg37OUgBlu
-        hvH+aU8AP06PP3kjja01VPSVv6fu/K59elHs1S9vo1+eGwiJTQsasVVj13wVDbkvpATP87rFB7M4
-        +uwuyBkodrWFUelgfzm+Rw8+BvFF9Q81GvHSJj00yCnAB7k2h4lf8gpyZb2gp6Yr/nJWYgLeRcyR
-        tFZY9DkFKwX8/MTxiC1/8/X3kL3UFdpUihyNt53SAiWd2R9+mk7Baguiz6qkOFaXnDXON//YWSmO
-        DngV9Ze27IArn7YY7UOtEc8krKH7HjfUk9WK80IDKUTj64KN6vnkvDzkDNqPy4uI/gkN37xdABtp
-        fyG5unpFGyhpveoD8qEaOGmmmF2nEbgptPCuaz75BofVS5Xdi4xRlhtcKI6rBZo88rAVCjafgy3Q
-        4HvailRDl9AU8oSPcLwShe7Oz5s/Y2LYkLBshe1vPsl2S5wCu/W2ZDlpSs5Ni7RQftjtV19yn8n7
-        WgQrEwbkp3+z5Ey9ssnzD7W2n0ezxBS3gPvKARu9szU/03m0wS1fQryvV9hnv3zoW2/ovjwqA9fc
-        8KQKJzfDcVWbQHTSvQUnISm+9dgyByOXFFgMwwF11b3wx69/+HM9HAnasNzPwQrqB+FMb4fY9b95
-        X6mmcx0iMEzku36lnaBlWwXWn4nOpbEZEADTyaXWV+++eaIBETIv1EseNp8B2xaA2YOH5NTgYLRQ
-        T2DOV/rX71L++uXpp4acsPs5qsOCc38BbF8U1NLtPf/yPoJxgwm1WhSaf9ZbhM2pou7bSAa2ixfl
-        xyuIt68hmjNXSX71Esl2GQ7TZQ4YQKdsog4vjGa5q7xVE62vv/Ui84fFgAgOn7eElPCk+dx+fwJQ
-        KPnq124u1+hWg7u32pKOW04uasWhg6zUa3T9vEQwP+TqBehR1al92HzyBVXuCNdKExC4HAkg4WpT
-        AsetD9jyz+HA8x1LFMzME5G2qM37/TWOVaVMY+q1m4zT5Zl1YK08Aqwd+nzoDc5dePQVA+PiVeeL
-        wYEL3RY0dOdy0CxueT3B5WBcqWeFOJqPN22lGmsRk666Q396OnEIyrDIiPo++nz55b1f/kVCsTdN
-        CV/rRa2riv3h6UlrRBFa0jpCK2F2Gp7d9B4erMUl9WkinNNUOcFPJwWol8Mx+q4vjIqWJMq3fjr5
-        /JFIAvjaiHAQrAmgh3vJ4JJzj3rPGke/8QBthO/Yz8TK/61vyG334fjwzYN+/Qn3rvlB4I41IEE/
-        NaB3HSnWFaXlX782Alq4A/atZ9fM06hmUAeejTFREvPrH1J4ogPDv/H3OCTx65dv/upBw77rlWDZ
-        dfovH83JOo4LGL7riShn4ZTP2rEv4FlnBFstYn778zMoN2Lsre+RT0dbH+Fq252p9x4/JjcxGGE6
-        VyHdlZdVMybSd3ynKKJaupbAH777MPwkPgk/0fjzV5KwXePv+nLOfnx2sJiLtesY5BOQpBG0Rt3T
-        /c39+H94eBpSDV/Qa91M4efgwmv13mBDqT8D8/xzoD6I9EFhuTuYlDjFCljep8ZaAyKfEWXFgLwt
-        IEbetAPCz6/+yU/ald3w2JIgtOLNAbvBuTYJuaeBKpXrF943QzMsxeBrYBscL2jZFELENTcN4ff5
-        kFQftZxVzkGE4la8YbfbaIP00+dAWMvU+fI1z2yaysL22GAL65CPYXpd4GmwewKqOYrmXJI9qHjG
-        +uc/IpLSYfmzHursZ51L33xLiQfpTDZLWeR8VIQaLtPl8B2/jcmmOkPQreIbtrttPSwpbRgIxWNJ
-        zVuP+bLzK/LL87AGhVPzJ985yzeFvHlRN9y0Xi+4SPWWmujzjn75MPz7tyvgP//111//57fD4NXd
-        yud3Y8BUztO//3urwL+zW/ZvQRD/TcU/OxHImFXl3//81yaEvz9D9/pM/3fq2vI9/v3PX1BQ/2vD
-        wd9TN2XP/9nyr+8d//Nf/w8AAP//AwCe/y/15yAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c09bf89ed1e1c7e-AMS
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 17:29:43 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-kd1j0bcill5flig1m29wdaof
-      openai-processing-ms:
-      - '471'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - a9c89e6436668562329d35d627f16245
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/cassettes/test_local_cache/test_get_relevant.yaml b/tests/integration/cassettes/test_local_cache/test_get_relevant.yaml
deleted file mode 100644
index 8a11796b..00000000
--- a/tests/integration/cassettes/test_local_cache/test_get_relevant.yaml
+++ /dev/null
@@ -1,997 +0,0 @@
-interactions:
-- request:
-    body: '{"input": ["Sample text 1"], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '92'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SxOyOrfm/PsVu/aU/kpFJIs9AwG5miB4o6urSwQREJFLAuTU+e9d+p463T1x
-        ALGiycpzW/mPf/31199NUmb34e9//vr7VfTD3//j+yy9Dbe///nrf/7rr7/++us/fp//38isTrI0
-        Ld75b/jvZfFOs+nvf/5a/veT/zvon7/+NuPiQ5nS1Anz5acM4uJ1ZNpa6bouyZMjLJdQMZs0H071
-        gcrA3keVHUtt4GxxmpbKpd8Q5urcTppOaEXZRcct8U/hJ+LRfchQhzZv4iqmnoz4sN3CaV17ePPq
-        P15npqcc9Pf9yLCTWmi8r4mBLoLgMxWNqKR6tKTwcM83rLRb8OZ4jLcgX4URN/ux8KgSvxtUsFJl
-        ji1XiBfJs1dO/JwwcyO5+oS8tQGQGluyS6ibDOB1N3AIDfAQNarXy5f4iE5iTpgpd5bOk8GtoPH0
-        HsOptJOxux9cqNitYI6nd2WR7zcusGJ7JGpq5px/KtyjfIMRUzeG7bHJkVto/O1AVxpqk1m0BRFN
-        SbH/vdeHi6MBXGZXI/jlC5wv2PWIOOlvTDvOQTJpbiSjOiUWBn67JNy/Xn3wyyUi2HaSjkVXVwX5
-        yBFTYytLhsxY9LBYXp/EROPEh9rYuqjFqkWiNiiSWeR2C/JN7Yl/Pr8iflyNAbCk7Yg1r4/JpO0M
-        G8xTsGGOfa35tHx1Mypq4cX2/uB59LA73SC1IoMR65B3w1IPd0qRVwqx/fuKT055zWVf2nV487pf
-        +fRQ7Roqeq6JqepFN54Wnx088MckesuJ3t+PqyvE75tLZ3o8JPMhMlr4iF2GZWU36/w45bmSc/HI
-        dLy0+GQ3VoMEB9XM552YTNkhCiFU45KiTaXpq9qOJbg894jo7eGgz6zoCpgyqhHttEbelK2XPRQv
-        pWLO+/XoRr69jhBErUy2w1R11K1iEbQNbYlNLi3nPpF6KNr9kaloj/mYvhoK8Ts1iZvG124+NMxA
-        S6FGeNwYjc6mdyOB3jIdo4Sq5ci3wQzWLgqZKgPhc56QEbFzLBNVjktv1q39HQQtCEhc58vvfCOF
-        o9V/8GrLRG/EdZWBtspkorfhAk3Ds/VBavSQOc6ClJOmNT3o7+xIdPKu0LiT9mcYqLRlD+uglnxx
-        WI0gLsUdMbfUSqbMWFMQUfDBrWaXXcv2xxEuihQwa65PUecf7zbo/RIRuz28k2lJ9XAhn0WJqcl0
-        jJpTezuDoF08st9Pli6K2b4CRweN2K3aJDRcbRuI5lRiu+tcd62elwKasl5j3/pG7RvWNdSZb7Mt
-        fY1Rfw9e7YabqoXFSyZ7rHhMdzADATOrZ/eo74bABr2bF7jE4Qf1lXWtwdkqKv2eRj7nPZ5huoQp
-        3by8mI+ysLuDYFaIHA2ZdsxE3oyGz+fAtFVYc25eZwOma3JkhlUZ3YgRwihXypoZxUg5m86rCriG
-        MDG37Oy1b+loo/ipFsQx4lXZiuvgKhedfyJeLIlRf0rFUZaKpiPGM4m42BQTVRabycYoyYJo5NOB
-        /v4PcR8z6bgvhi749InpSp/LaKoX8xHBZT4Tc/Pu9LES4wJC9dwQuzvPel9ZCwEtlrcn80f/xbn0
-        DnuwrBMmuNq9kikw1ZtS9ZgSo3rb+ojjZwHdOtdYGNmWN873cwPB4aUwL/G3nZhnkg2N2ZlULoYK
-        fUBUJZCjzsALYSGgQWu2LgzDAqhQzxKnsRbsAMKsJbozyeWc7ycXILUV4i7GRufF9ixDcmcYr4Ps
-        HU1ZPM8/fGV7Zn6i+Q2LCqzj7sFIwaSOfZS4gGY3AXMVKU9md3J24EK5ZNvDAXs0h3knT+mg4sXz
-        mnv9/Vk1Pzwi1iy+SiqkwRZEFH6IK9wT1M+fvQyOc26Yux2R1/zqoz6PFcPv6ovfnlEp/ttsmRXd
-        PL3vXv4ZhdbKomsehwmT4HMHTRFuzDEQ72YRoSUSsHOmrMjijn+UAW+++8H2YWR6IjvlNTQ7puFl
-        zVSPhviDoajhxbCzeKFRXtUAoowHLO1x5VF309TQaOcb28X6q+PJZ1dAEloiXqFHyHlSdTtUPJsN
-        nkRJRZ+l9RTBneaantTjs5ycMijAIujD9M+iTJh0kEK4CODjObotEY2VRJCDu3tjhhWZnRhebCo7
-        6rzHyzL0EV+wdY9++OBPgcbnHPtLcDe+S2JPtEs+mmK1CaP8Tqx+LyQ0dz5XFHf9iuz7riypgoYW
-        tNHBxLs5p6TvPmxEl0+bM3OzufJZSbsePbaSSHR3JZaTrYU5DP3KJMbr9vL4wjmHSBNzkcXVxtep
-        aIsimPfpitf0dI64eSyO8JkuM3OzRdjNwlHK5STOHsRVmlGflVrH8P0+Mcpli9o8vNfyZ/Uu6Glj
-        7vUex88c9I4azL8kozeHF7VHx70VEPyObH391SOQC++CrjYXmXfSPi9Q8hAt4s9rt6wF2wkgCWBB
-        jAKPnPvHowvxKwjJtbHVkhejlAHs9xIhz2uuz65wodDo95Bg761EQ/2UrsCSpvutVzc4t0kF8+hu
-        KRLte0lF1Li/98xUX3k5yo9RBH+tMlz0fhxN2UnsYbrdDySklfadb8zgNOHyWz+G/hnmjw9SZ3vM
-        /uy9iPu6k/3wll0/+y5hIz7vIK4OB7oOG+AzO1sCTJHVEFzPV9RF4qWBKr8/sBifomjOHcVA2ux7
-        zLxXbzSzQ5WDX6xlvDAdu0uHNMxA3NgTO4ufUzmzMwGkNy+PuYqc8p7vmkJ2hWpippycEfc/rQSO
-        fXl/+dLlfKEKM2LpOqPyFqceP8qqCrgPJOKPiwKNcpSGsHKDgKS+N3j88yhDkLPgTgda3fQ5ViIB
-        vvqRuIVX82bHXiKS6FXGY2xl0TQcZUCwJxJVosvTew16Hij44y2wEm5rfVhelwVoCtyY8+odfT7k
-        VqX85ntYIYt6y5Yo4qaj0GpHnG64dEmLHt7jwH71Ml26qIVsvX8y7Xsee2s9NXApA4lop1OqcylD
-        GIYqaJlh6auE6hdpRkt46My7lkn0Pd85uOtdSHaryuXf+rlDa2Qdc9y573pLrSSAm+BSCWuat/6U
-        fAuhvdHxeNcq3ortx4bUfXLm3WCORouFLqTODegkmjqfbHzK4LHPMUZXLY34cbiOkDyWFvEvt2fU
-        p8dnj4qWHOnzIhgRT+5e/dOfzBNbuexlPC3Rg7S7P/px/vIVGtomJLYvRGh2XX6EBVogpjdtk/Ai
-        cjGqgvLG7G6ToSlQxxbqu+cxvbHdZLIVl8KXf+hnV9yT8b6oa3C0jUGMZx+iL56KKCRhR6xg30R8
-        Go8GxHXsMFdXu4QVl1gAwZ4ZXj77GbWh0rpwNKuJbJmdelOw5zUAOY3Ev7gHfdaHCIOZtE/K2zmP
-        ZjHdSCh+XfZUXjw+Ho21coYpkFdU1lqtY8U2k+WhOr2Y4wg5n4Y4u8n652Ox3fmWebzFQQWPrSxi
-        MTaW0TTQl/tbH5qjMSmnpR4aKN/4CE9rF5fjPRgaOUkpwYuyWHX9V8+idN/0xLDEORq0amfAdPaf
-        uIvX725ava4GXMpQYubm7ekzy9gd4vqI2fc8cB4NfQb6p/bp0vSGkiqL1Q0sO3EpHKebzhedXYPg
-        CSXTRrLpxmpOM5SNqw2d2XUfTTVqayQf7gfmCkrnzfn52sIHKS5RkZ973/WRwXqIlHm32zGZw1AC
-        tMK5yqzzKY/4Fw9BTrwSr0efdLxorrAR5x4T936CbsS24KPlYpiJTTYNnxkvCtTsjQ9JVscAfSCX
-        baS3rU1s0jh8GFqnRzGVPsyTJsNbT4p+Br6VCEZJ+uxoeLH7P/rKseprMv3wrd3VJd7U2NLHzrvZ
-        qGAv9PVbTVL9+Lwxcky0dbLv5t/5CPcuZ+5itD2qy5kN3So1CBGE0euKle0jTR5rYoVm4M1CrAZQ
-        ZxeBCk76RqMFzg2ksn8zxzJuyTQsrnfw11tGrOnZltyY1wDhdWkz/3LTIl5MlyX68gtumhuN6rzf
-        zUhvioC+pNUdfWBY7aAo5wlPK81Cs6h6LdTH4Y37+Yyi/ucXpvh2wtxWKPrjh8w7v9I5SLcJX3Rq
-        pfz8sB95C8SK3LTBfzKdblmLvO6zM0awrmfCrKhrvTnWAkMxb9WLOK9hjYbM5uMPr4n79UujZY89
-        nKYoY9/zo3dmqi3htHyEXz6Cbqqf0g26Tb9kN2UX6lPNPQNJHzViu1tMkqkufEOuj23P9HaZ8unB
-        4xDkxCm//m1bjph5gLhznIntK6beV9cyRNVV27D9F48nW9n2imWSMxWTtIumi2nK6Ov3qKwhtRsr
-        Lz9Dks0eRdeiL/lU9iIMdZoyN0ViR396MTV3B/xcJ/uS366kQLg1TKZx4ZbMYvt0Qb7bFdnj18w/
-        l+VuifTX8Y7X3DK6b/3RP/ip3pdPNNS16oIZEWCm1t08LpmOij6Kvvvhi859/WTDgsc5IxB10aRt
-        NFvh6jpkHhrenEvn9xXgivZYweIBzYecVJBLhsFUGT31mdUoAItsPsw/Ld/JzBjN5K9/pfzDuN7f
-        bWwjcVHEVIzrORpq/9lA8WRLvFhMe33EgGXQm7f31VerpNV3mxmmSB2Iq7y1RHybDxfVp76hMJ/8
-        jhfbTNqw0ghYXI8vb7qcNhiEvfogptbJ+lCncNw0ZuV++StH7Q9PvviDV9u9pLPPUt6Cu/b2+LWl
-        74j+6hUX7E5X8s3Wx1k2JJQkXciscCdwKp5uN8iVZ822Ufvy5jgU7jA8DZGosl15Q5ZlGPT6dqUK
-        1fbJKts/MEot32HYMxdRYxWtBJemrohhXJ6o5/mth6PFK6p88kyfLmqbweUzJGy3vofdeF9bOyQY
-        mYFlRVZ4g+NPAUNurhiuA5lPMG1scMjkUSYoWiTqVbNF4vg5sH1YfX9P3apScFOLn5/Ue9ktDBjy
-        rUynMZc6vnDcClhoERxszic0DcdZAMHsRIwkUutD0D2XcHkXDdutIo83cp/vkHlJe6YTs+bcX5hn
-        eSG1B+aJ1sC56We5nM+rCEs4zL3RAu0KwX1/+sNvLTtbAHVYLJmaXnA3u82zBr3EFV3W2dObanVn
-        IMfCI7M/49Wb2QlCJD0rRrYDqcvZXV1FENfbDSOCEHh8VC4qsDo0CDG7uuMmtZeoTl2fOdWO6WPq
-        uz7EpXv74mPjzQzSHvyXwIlRPAjinz7MlWFQgDQf5iTc/GwM9OUbslu94nJaXvMlXMoLx3BRsE71
-        j35HjRafiJpeaMeKywGAb2VCBe+Yo/qw3TfQLRObDl89N7vKeFa6zcSYtipNtMQGvcvizB3K1Mst
-        6Xe3yw6q++FDVNmZOTNF2P74A8fe61NOy7tU/fI45hbeDo3dVbv+yau0i2AkortbBOsvfuKFIX3K
-        H38r4lidibo5WfqErvUZjo74pCv0mBErdqEAHSjlHz081CrewXLBZppGu8LrO+/mAt/ZAtE/fh19
-        /awE7fbMCbFKnFB9NfdKMZz3+Hnxz96k7S5LOI32m2lHvtAnyGcX8rUjkN95o2ES3OHhBBlLadkl
-        s1hoLcix1jFTPxy9wTl/QlnqLwpd05MY9fj0yoBVrs+sAK91JmFLQl8/h8XlNPAJdE+GKoufRG+f
-        WjIEN6GAfCX4THcIdHxUHqqsTTbB0rd+ukU9ir88gQqO3yDu66krL3iS0wAxn8/NW8sgicsbvkTK
-        mvP2PBqyHFxPX30Rd3zC26uymPyBmAhHnEvqJkSP/duh4s3Syok46xyS2+v81Sv7jpuv1Rb0blzQ
-        7nZbRuyjKVuEh5gx/BqwPtWUnwF/LIP5p+qiDwM93JHU7XdY8IygG090NUMSSAaxmyT1xnTuvvnk
-        tmc7cWcj/vMvjEkJOyzHhlMlWN7l1szfxPb7nT7+8peYwYuYGU0jtuCNIbc2TfDGfQ5lvzusK0ju
-        TcT8izvp7CjbW/TNa+gru7NuGixJRa0veMyKHN+bLoaMQc7CO9vFYlEO2anbgrMj7JsvbX75ZgGO
-        urb/jBf1ive//ITOdJV3PLmgJZKeNSPGNx/48cWmqihh/sRxt4F7e0PDsNHwdNrmHdXzEqDOsM3M
-        dPfi07CoXCQY+YJsWZvocy61ZyRsE4uZmbDvZn0qBDiBMNPkehjKnguqoCzE1xHTmvQ6Ty6NDR1C
-        b2Ju0yaZwya5gv7c9RR996e39ncXnTazgKXufdDFePOQZZGPLtstn0rHzIAGv/XBEj4q5Wug8R2G
-        5nWiDCo34v6RiWgKpBXTjqT85gdCBc6+upLIdg98VuJIAKnRQrbvHbOctJBfUdG6MXO+53tMXzmF
-        bvVcEH9aKsmIMwOgqtGWKrTsojHVix5S5wq4XeRrNNTrcInYrWZEO72GhE0SqiHIgpAY+U7iQx1f
-        ZXD8/M5cPYy98bffjmGumTatonL+5rmoPrI32++DNR9q/9Oi4LQaMJy2sTcNiyBTjsZr/OVv3rCc
-        614W1ANhxlOZ+DRYowoPy62/+PLWabzxfWD3qaCyZusd+1S7HjV7p6J5esGlqK9kCvl6azOiXM/e
-        mCLPRt/1JbrXRH/8FwSnecbfPAK9Lk7aoHZXlWy30pNuWraWjz4LVyDemooljc9y/sMH+pKijM86
-        iUP0WZANwy8v8L79hCXIZe3gEbGeM+mBpT9+qoWt+NW/doDM+FXhMW325RK34Etc22B6NNMkGqtZ
-        G8FKcp1Zh6JMVjUqakjVzZ14sbmJRvlyOKJU14/E9oclGl5ICKDRkhMum26tD/YZBFS9QWD2fhrR
-        aDn+7ZcvEuwZY0e/+TZydEFjpj7rSf37P/izdZh1KEN9WOrDiHA1xkxvkJWMeN3doXjJH+bPxlBO
-        mtJXKE5RQyd+h4jqpBdkM10fib1/6N6PL5D8OF8xzMa+W5tUFSG4SC3NbJA6tnC29Z985scPc+xm
-        AnzzXCwvcOuNaRCDbEbGjtyE3vcmzU1kYHHB2TZ4LPjnh1/C3rzRBWz9aKyCxx1+ea13PezLOW5M
-        H5IH2jIi3GdvGmydwkli2z/1w4tKw8CYnBAC2z6Z6rar5aHEFIvrvuBULLQGzPN5Rb55hcd/+/fr
-        T7h3HSMq6FOh1OGLMVc9r6I+FfkVllxqWOath26Ol5ABy4UrM+9bB/W4IxLgonli3oYPzvwjWyLz
-        iJWff+d9mmq+chr3BV5889hpeYUCkmy1I/Zn30UDyNVRyvmGEFXiH692ib5TOOEn5t3iVyfqpAf4
-        5d3qvSzQF5+O6Mv3xJS0yXtdiqUL4WX2f3lqOSyvjYi++gA3jYK8lqmxiE5SazHtOD3LIXi/RoBj
-        l/7R780JvVTQ6zQiqhRuEHUV6Qj5xlXpOjwzj+qkAri83yXTRLPkc6M2qtytuzUVvnzDpTO7gT81
-        NsPuXHDmz+cd+GPlU+rpT8QWEAVKt7o5dJQKV+dRrmD07Rcx4wW6zj8l2qJsc4kpXIaUT867Cf/k
-        Yf7Xz021/2lkRx333/oOuvaX/6ZbiNnRQGnSjTjbQeOrA62+/DjreRDAdDQ+jCywGolhpbcQXkYf
-        D8Ne69hxNYagjbsIr9Jr1PHjSgoguNs3jMRW7vj0cG4/vfjD53IY7McV4ue2IPs9cTzacKlHSaii
-        7/55SS/vbkeIO7oiKsJpyRdvo4DHzmiJxdEYcfOlqBBcFi/m1GTFe5mYBRQdPpFfPv315xRVzzwh
-        JF+PnBWXVwOCI3aUN6399cvB/ecfifnNU2elpc2PH/H0zccG+BxakLPThRGl2SWzfhlnpXGkFUv3
-        01sfZ+/RIDlIAyp/83++cLIAQt+byZ5d1t4vfwdrP03MMHZbPmTFIADfLlyyjZwVGpaWUmxaHzxy
-        4ShIeOL51fq0KjFthXvCp0tpiZBi+u2fnMqIRVsewLcfTB+WNib9LPsydKN3xcu8OaM5D+8Vqh/H
-        BTl885XhmwcoR3udY3m7p8msxKxFzd6rqODyqZxscwXQLbY5Xk/zp5sCpxTh+/6Pv2kq+Rmib/+T
-        bXt/k8xMMoVfv5D96bf+8tpv/kqMcnsv52+/GnD+qsg26jgfU6S7v7wQr7n8LLnvNQJ895fOga8n
-        4q+efDgmTP/4u2QthZ4AD02U8Rw8HnwIVKkF6yC8mauedt3MHHOLqt6n/6Vflq2FIYi1J9O//WD+
-        6WuMgsTI2DagWjJibm/h79+tgP/8119//a/fDYO6SbPX92LAkE3Dv//7qsC/b+nt38ul+G8m/rmJ
-        QPtbnv39z39dQvj70zX1Z/jfQ1Nl7/7vf/6S/tw2+Htohtvr/3n8r+9c//mv/wMAAP//AwCkxTP2
-        4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be211a83807169e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:55:16 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '311'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 665023d2f6ce38148bbb6db93c66bb82
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Sample text 2"], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '92'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6W9O6vJbn/f4Ub723zi4BkYR9x0nOJCiKOjU1BYgICMghAdLV331K/7t6um+e
-        Cx6EWmHld1r5j3/89dffXVrl2fT3v/76+12O09//63vtkUzJ3//663//46+//vrrP35//8edeZPm
-        j0fZFr/bf/8s20e+/P2vv7j/uvL/b/rXX3+PA19Q5yVYKZuW7ix1zX5Dre0xABNeX2e5CviZms81
-        0sd7il0Y1XxL8bzt9YkEuIBShzOyRHOYzvviHcJ7sOcQ3y4LY7wDOJB7rY9VVxe80ffjEppne8WO
-        dMf6qAmbEKjHViZygrSUlXZ5hkrRC1Q1PAKIs0ENOOJnhbbCbklZthVjyDYSILtj1nsLFTY3sL0J
-        B4qj+w5Mwno0ZPNq6jRQYBPR7XlW5Jfmd9jdEDNdYL3fwPQcytRA5MCWtxfYQDIuBtWG5KbPqXAZ
-        oXZmL1S/RSdlt4tygm53wNSQhjKaHq3fQLFe3vhg3a/6sr5LDv7eb0GlTKduVVYJ3bwzql1cgrVQ
-        +wSeQs2mRhJZw+dsKTc44scbq3tzieZtznzoDlpBHUfGw8yu7Ax68/lAgiK+PCadphkYu7JGrNF4
-        j5TMVaD9sCV6YXFUdYEQ3KA2Nhh774dXkSZWbzB6XB3sBTUDK6lEAX4cN8XeoxMrdpy8G0hl2mAD
-        33iwuscxgzgSUsLhG8+WxAhCCdHPQg2nQMPaPlYXdst1okqf0GEq2SrI19exxepbGyuWCkIJHHQ7
-        YV/lzYhNSxHDodEgPtz8MBpVSWqgfEkQqQ7eNVpfwzGE8SoX1DRVzhsDVSqlOn3qRAyrXp97pPhy
-        kSU6NQYVRuQ1HE+gUDcX6itXGbBHFyMoZ+KAxGyn6Fx492eYXbMXtt7bI1vTSY/h3EUFPvgtGdYy
-        pSI4xNUTFQJ5D+vrWfvw4oEKuw7ZDlTcXV3I53mCA/RRKq4vzhDeNuKeBs/rJVpdEMXQ/CgYu6dT
-        AxYZdSLEzm2kVvyWdeJadgbFpLewtjmI1SRA3oSH7jlQ97HrqklY7wYIlFuNbfaA3vjxtzZEFGo4
-        /X6PhdSfXuJ2/UKWJp3B8pT6BAofN8NurPHDLKJbAXfzPqAu6V/VXMHsBu+FfcLGtz9X93Es5f33
-        kfFD8hgJ4g+EbuzoWLG5x8DOSbPC6LRP0ZzzExg5nrehv8mvBJrnTzTVenaDXsEfsGXcn2Cmk462
-        2+3lQR1e8nVKr8kG9jO6YTUzzIpHvVhDfeRK7HAvC8zZ+VrD8pL41M52irfwn+cJMCoqBHwgqvpY
-        S0/wvVYKWd6aX7F8CRVY12BCIjk73rfeG4wO3EidZitFJG+iGbw01KFV2N7BuufPBO5R8SRiK0rR
-        HO9DQcYhcEnz8K7VwqaohhoNML7f2EMnRFIlKeFPGkU78xUx5TiW+0UxMXWybvYovZ4ghCfUU1z4
-        R31h+L5Kd2VnYmMwi2rdvRkC2/VEEUBR53VVo8fg9mwnxBM7S+mNaQbQzssLBzfTYXxlhURmpmMi
-        iTl1Nas0KPYwXgTs99kJrEPfJbB1o5nsvZgxqjyODRwz4Y1xuCsqZu0/MdSXlOJDXTTReNQYgc0G
-        mVRxT43ODvBcQysTW+wIHyXlvTcw4X3CCsbH4zNtrRIjEGeZRfNSvkVD/u4h0D7dhv6+z64yiALG
-        g7ojaapC9u13+0995dNr0lm8cSX81oOazvxEbM3CHFqHwx4f9I8d8Xn6LAH/hiJGFOTRrKEwh6+5
-        pGjPvVq2dAnpgJCPE8WdWuvr8TrYcG1djxq1Uno0xE4DuSnQqHK+P9OZdyINXiTcU1WTr188NRpA
-        SvQhUbM46dxEzQjFEN2xtb+bwzIddQFeayT+9mtFL8aFwI3CDHqQy6PH1PvjBA/x60nt4DFE6/JQ
-        QzkWXws12FuvFlFyBHi75CG2LVMBs1h/aniiukaD81EAq35NOGgL7xqRYC6GZbjYNvykZksPaal4
-        fF91OfhQaGANL8dhed7GE7RmppC1nztvWcwrBPvd6YJmL917ZOuAGYAV5EQ2D/u0171pheGcf9CK
-        blM0tfZRgm3SqOR9NI8DcVjfAJyfHKqnflvN7hpCGPI6Tw+t9QIr4oYVTkJVIjZslYEFxcMGJEkl
-        InbZ6w8egq357tD0wBBMPz6S1NHA0eVcRGuViRC6EV5x8Ga113nGNIMzlDqyGgPzvv13BrHV9Oij
-        bD8V2Qx7CY7sssHGMIcDEx73HsRfoBI2i1Ot56zrYGhSgrjdZY2YHvcKnELFxd/1HpYWjivw4ntM
-        M3OzTynadhpsCt7CyPHv0ZzUNgTHj5/TpEbMmz9SH++cej9gm09aNitHjwAx9O9oSd962sWvzSiV
-        BwsgTksoG5eTzIGLFV+pfXUPA5O4QQIhr/LY9wfGVisQFWBQypO5fGfVFI/rBjrTPcBO5DVs1OpP
-        AUcyL0iGKIqYVYWh9MVXfGLY06f3K0f7qxIX2HatNJrbdWng0G0CbD5XpncX/IEw0NUaccH2ODD7
-        mUIQeTcZ7fg6qqaMHyXohPHzD5/OhxkRsJXmI1ZXZa0o9d4i/NaPT83xoK/XUXMhmrSFbMOdMsw/
-        fG6v3Uy1scMVpZWiyU+0ztSQl5dHw/eph4tYMcL5Vh+t2jRIYHHxiI1oJ4JOYI7462eqZOiUdtXc
-        nkF9E3Sqq9IwsCx2MnjX5yvW46muxvObKbBXxSONK7vSJ2jONjRmzSL8SEV9xA/VhIkkRAS8H96w
-        1PcpA473VDHeNe+K/N5/bKKAcLpj6BTitYCdkjTYfPXSMO0yW4ObS//CZvayBjZ0TQmlLsiIXPld
-        RL/6AWZMyLDyrDV97EdXk0zNb9CyHDfR1POyD1QMVWpzQzSwDng2fMrmDgGcpfqs3bgc1P2MsZ7D
-        OJqtvV3I4zU84/uniXX2VtcZ9BH3wP6zOaQrhucS5O+zRZ2bM+k0cA0Tvvn8SA9H/gDWbcvX8J6G
-        HFbF7BUtwactf/WQZYnLoX5fKw22ihsRiR8yne1HYMPEaQBWQGBX8/P+MOAeCg11UykDZJY3Z5iY
-        Q4+uqWOkwvZScMDbIAOjA5iGgeDeh57xcKnOobVi4f3dQN4vEQ2c9BORw/pKIHzhN9rY5Sdi+Z0X
-        Ydmeb9i/bR3wURa8AV6xOxC54/JqBgAIEHRPSl1zOui0uYQ1HOdx8+MrsNAxuQGdPkrEve5Nuvbe
-        pQBfvKCPr/5eP/o4S9v0eaBKEveA+LrvwvvtUlG3m2JvaWG9QtbeciQcTk/A5P0rgXO6f2OHVq+h
-        yAq/B189g5XLrmXzPbv58Bw55Ps8F6zdXRb+zTc3rR5IRQ8EHg+xifHySbwl1g0TQuGgYUN3an2U
-        NtQEL8FSyGcjnnQ29+IMC6zrhB+aGixi2RLI7/YGPpyBMdAksDpgEYFRM4Rvth6yMIYTE0saRHY1
-        MKu6hZLIGQsCvker+fDYQ8lu6w/VlzZm882WEqnPTx5hnl2yD85u4c9fkPotflLCULcBeph12CZn
-        RydfvgHf/YEqa13BUj4+M6zqIaHaJfe9z+vcwp8+J9wtVaL1DoYeDldNpZ4aymzEB7IBRkgA6fjE
-        YutbGxrYXUKd2sM0pbO0aU1on6hPhn74iu/5icCS5Q6RKooBy2I1hwR2V6wl7dNbPJ3bwNTZIaqO
-        9pCu55DV8JFcObIZ+5XNTt/5QFKJgZg48QPLAafsR+22I7A7S+k8Pl4j+OojspPFTzULmcjB42tU
-        8RGVd71/a1UNr6+oRRvzLVckNIIz2I1nBck0lbx5oywJjNAZYf+zauAPn/300iGaAm++h5UNK5jb
-        SPIvaTRbU5RJj6Q/oM0J68N6GuwNJCgOkawEqzfX+5cNY15cqHNctWqKHNDB08MQMDpbnsfO85aT
-        ZvWxw7/9tu6vibhvxzKgf9bjcn+4UHF4n6z6Ix0YBsMIBdZ42NkrPVuG4ejD0K9Dqu+euTfIE3cG
-        ennjcDB/jgM7r7YEskBZ0fvmhyl98UYOn+XHQRy+XQBr23cMj/f9ierZRWLL3OUmvKw0QJfw+kiX
-        5SGZ8Osv0XsD+HRh+DjLZrys2HlZkff++mcQ5mWGZPQpBtrHxxnOVnynNqdWw5qK801OdkDD6FjQ
-        dOqadAQWG49Iun2WiHXmHMLbxdvSb/9X0y0/dUCkOJp21/OSsr7gV0jXDNLk9jlG6+4NENiNKiVC
-        j1SwSJdbBjvutKFGFNjsq39cGO1MA2txoESrs0E12Fy6F/75HbqStw+uDS9Sa06LYdoqSi1/9x+1
-        PheVMVrZClCv+ZOwy2ZOWZRXBkRchREI+7ViZYTiHz9SfdrZ3sxfFENm44Z+++lRsZYlCeD0+U6t
-        YkmGxXbrAmruZcWe79GhwXObQ241CzK/fTHq/RFocCBlTrGMAGvF3dPe82dt/PInHb7PuwFTfqc4
-        OPapPtNXbIPEL3yKFrHXGdkfDTloAKTOKVurlYuPREqbwMG4YeOw3BvvBpFe20RCMGbT67JX4Ho6
-        Eaot1jqsUhQ3MMXpk2y+zxtT4TFKm7aZENF4wqgjP2agP14x2itbZxjyuyzBZxwhjE+0ZeuWlZ30
-        rgKOlHzDD7/1AnqZcKT86s353kAffOjAqA82hTfrsYqgKRj/xvPxYD4FgPTGJltX4sD4UsIVfnZZ
-        ifb5bFfzZIU9JN5tiw1p0KJpnU0B2kJbE+B7uFqs4LrC7NhuaeBF8zDVO3qCJzu4U8/nt8O0KeTu
-        p6+RHOnPlGwKX4C/vGa/1tBbWb1qsK73E4KuIeqE3Lz5p48xyvNLumg3r4OX2Qi++Cow4h7HHGaj
-        OlF0wtVQt45G4Ddf+vqNLqLuul9h6s9Pqu0I0RkXiDYkXrIl/JSP0azVnxL8+Nq3pmCg+WxuwOMz
-        KEhSnxMbQ+CKEumJRzVsqQPf2kdR0B9VTOZiuqQscH0TbPMkxqga/YqxWvXhZOOUqvdHzwZu2ENp
-        fV4y6mUbu5pHts7wMTbHP3yy8N+A4J77B2y5sZculXUb/9Rjl7RNSSQ/Rohv95ZasugMw2jtc7BZ
-        tYzs5lQZOE0QTuCXb1n6VgG74qp14HZxtkjgWVUtt9O7gRvo7b/5yNlj3aH1oSA6V6xEoe8tp8Ig
-        EuoPBWrHOIsW3HAhBIV8Io10aoYZHxoIB0m8Y91R+nQtnciWo+Qu4r6W23SV/VaB1uHm4sc3H5sP
-        5pOTrOerxQFQABs2/GSAr1/Dpoe9lEr5iYNizd5kd9jZEalvsIPfvJDw2/4zzLtDTqCyvjVqRrns
-        sWGzrUHUriJ6zS1Kp4ejrXAUIoyt7XEC/UXqczh57ojeQnaKFmWxIDy9NmfqxosD5vNSGLCp5hs2
-        bqmS7qqmtqEvtjya7f2LzeCxKvJP7zmHfKz+5D2lu3lQt4yHYUROdYJvPjv+wUvyLqYE7lvZIez8
-        9r1VewkC/JjYRfL9SfRFcoYbdPP+je3VuDJCSMbBl/x+kOG0Dt4aC8QGJj6eqfuwuWjdsr6HPCcz
-        jDSeALJlfQfTnAzUmg7zsFy5isAuEc5U4bfHiGRegKR3VRyoqc12RGHjNZBahkk2eX6JaFBcbMja
-        JEdC2zY6u/JyDMVHZOFDc5sqcqmPifzLR4zjRR2E17NG4JFcOMQ/T4gNRrdZJW7CGtlv2yZdDw2M
-        gaxnGuGduGQL2ys9pJE3E3h48/o6n60cKP78oJZx34K5avSzHHAniIT1EVWrYC0J9Nbl+O987pfv
-        ZBjq2Jo4Aywm0DYwAMv9h3/V+IpfAoxgd6GHfhdW7NDoBTgMN0jtj7kwcrwOLtAWLyOPca8Btn8h
-        EzwOc4fN4iik4xF1K7z1akY17lEOsyqtNdzudgpF0LCq73qcwbrpO4w+91b/7o8afPEC8Zq3ZdRx
-        XHFvOP6DeupF05lVWj68EFehimoQ8Cdvha1p/fDf+6PvV3cNqRlzk0c9IudQvBKBOnvFBeN0nxIA
-        XeIjTmhyfT5YnQR//PDrT07e27X01fNf/Ms8Jl+r8I9f9rtzkk48b5wlphcmtTe3AEhqYppwb28Q
-        eXngkVKiyzbYOsX+u/5Pxm5MM0HT3G/Y9slVX/NV4WBiaD21T4M2LLV+TsBW1a+kEbmNTi/Eb+A3
-        3yKNW1x1FqtlBjMQ77HHPjZgMMmLn98iixZZ0eLvQwkeBz5Hb79FlTA7Qwb2vZjg4HTH6dy2RvHz
-        ixgZehPR4LK3QXQQRnSvsFetoIHJn3zH5Qf477wfXYozDsfTTie8YvegiF8vqo95xWbOR6EUjHP+
-        p9+Zm157+M2bcHBtm2HW6lfx4wMCUjVj7MUbGYyflkUNd38CX39W/PQqNgUYDxNBtwYK53CLv/1f
-        ffX1CjXQulQTtnswajcug1Z7jqkOzkd9Nt8lkb55CQ1GF1Vrcn+X8MSkAmMUGmDBYYXkoYMBVp+X
-        Vf94OtwAo/xY37xQjXj9bMWgIDHG6ubcDaQDAMLhbMxUUZmuE/2aCNI8+AvGdDlVHD/cXbiOJCO7
-        qrNS5mvRGXYN2Pwbr9bQrWHwvOfYZmURDddo54OttB7J/uZM3neecQZke7z++CRaCTlzMH/HFjJv
-        Wl1NBbJD8IoZR1VU3j2KrRsHF/HFCKcOacVu7UOB59jYEt6wh4FtIwLB2x9T+usn7mBehZ+fQEsg
-        fvQ/fHW1OPnrD9+ekOhZDgNdr7HhW260s6rwBOx9yX/5m09pFaYGfCTdgSrfPGVtu9wFwbjmRNJQ
-        6X35xYXXvXHB5xEzNnqSQwCNDyp1hE+RjpckgBDGTKBKzgeMbR13s7+oq0k9fXdP2aHxCni/kIo6
-        aSJWS0jeyj50ui395qdsXleFQP0Djth+vEJvjZEd/5mHAG/0U25zdXP409Nofr7BEngTARvk6tj2
-        3jqb/ZI28Ps+VFx2LZipOJ9gHwIfW1DR/sx3ZF7iLvRSF03ajOvdBaTefci2McRoiVhfwOvevOBA
-        ij0262MSgqO89NRx2+ew6GccA+8ouFSLgyJa3PlqgvBskD/zheXrzyX+rIx/5gtdbQR/9BzWw/nu
-        jec3UH7fk/qnCuhEstdG/s5LfvkBm/mLbQJO2dlUHT6dN2eXroc1Ss7UHXVTpwk9zLB/bCU0SLQd
-        xjXU6l/eSf2lXKrxZq83Ob/KFtrMzwPgzHdP4FU5FwjwrzmdQjJpgD8eUmyUepwuBVJOstJgiyor
-        LofdZb/voCVcj1j1gJx+8z5NynenCIFleQ2DcBwb8PVf1Pvm/eNhNslvPoLV95gNM7C6DaR8ElBU
-        S7VO5jPOwLmHGVZkzoiWGqvZrx6sLAVJv/MqDlbKohH5fIzB0igfG26QrdNLplbRPFEhBz88BXfx
-        w1YV9yYsicAToG5P+vjbj++i5r7zPNGb7PhYy8W6z8gbI/dPXgRvC+fRZ6ca+jolWw1883eypVoe
-        sfCd9NA5yU+Kglmpdms4JHuY9Tfsm5t7Shdb6qHjPVT6+FQr+Pz8JRC/XfrF/z/5tRQfQ6ojpFb8
-        +i4FaGbdGStfPOieaG8CDbxdHIz7Evz0mSRcUUjKbaV6/OtMN8A1/N2Xz0qdgmXu5EUxMLa3Vum9
-        el5GEu3UAPvnwgQfUXI4iAsUY2Pc2Pq6As+EQYsC1GBCopl/jsYvv6L27IfVgtdPDDUFXbDZiAsb
-        /WrugLwPG2yUaz9MWiWOf/ZLt3fjgb2FQ7c/SMTG7lx+9JXtzBl+uOqI5oExQDh37OHxfFGJwPwW
-        LJJTJbJb1CvNv/7nm1f4MC9vwne+W6bsFEvn3++xkfFbj5GXAGFwCVUaypyRLpvNNv/x30//DMQM
-        qxMYWYfxk2qb9Dc/A48zq8jwzW8moRk1uGseOfZdNkbjPlZPoNY3DckyKg5UUu4a5DvJwb5qnjy2
-        e2sJ9O7nFqei7Xtr7O9CuT5tX188GdP5AMD6q5ca7XGqlnuj3+CnbA/Y2EPire/xlIPUX59fPFfS
-        OSuMDl7U2aTaN0+fc0uJ//SPfidbfX0So4T31cxxYHJBtZj0Iv6Zz6pqzfTFS0wNtmf6RGJJ22hh
-        e7uHhoMeSCpyIxX6q1uDZ9QhwuLJGPhhuCN4d+IOSb2ZpH2ZttJPL1KsDbpHIziKv/pR/XZ4nfm3
-        MYGynmvUu4sOWKwd6n/4SP0tIX/4EP79OxXwn//466//8zth0HSP/P09GDDly/TP/zoq8M/kkfyT
-        44R/UuHPSQQyJkX+97/+fQjh78/QNZ/p/05dnbfj3//6S/xz2uDvqZuS93+7/I/vu/7zH/8PAAD/
-        /wMAVLQZa+EgAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be211ab1afd169e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:55:16 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '172'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 5b810c395d48248e473bc4e53de0eafa
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Sample text 1"], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '92'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SxOyOrfm/PsVu/aU/kpFJIs9AwG5miB4o6urSwQREJFLAuTU+e9d+p463T1x
-        ALGiycpzW/mPf/31199NUmb34e9//vr7VfTD3//j+yy9Dbe///nrf/7rr7/++us/fp//38isTrI0
-        Ld75b/jvZfFOs+nvf/5a/veT/zvon7/+NuPiQ5nS1Anz5acM4uJ1ZNpa6bouyZMjLJdQMZs0H071
-        gcrA3keVHUtt4GxxmpbKpd8Q5urcTppOaEXZRcct8U/hJ+LRfchQhzZv4iqmnoz4sN3CaV17ePPq
-        P15npqcc9Pf9yLCTWmi8r4mBLoLgMxWNqKR6tKTwcM83rLRb8OZ4jLcgX4URN/ux8KgSvxtUsFJl
-        ji1XiBfJs1dO/JwwcyO5+oS8tQGQGluyS6ibDOB1N3AIDfAQNarXy5f4iE5iTpgpd5bOk8GtoPH0
-        HsOptJOxux9cqNitYI6nd2WR7zcusGJ7JGpq5px/KtyjfIMRUzeG7bHJkVto/O1AVxpqk1m0BRFN
-        SbH/vdeHi6MBXGZXI/jlC5wv2PWIOOlvTDvOQTJpbiSjOiUWBn67JNy/Xn3wyyUi2HaSjkVXVwX5
-        yBFTYytLhsxY9LBYXp/EROPEh9rYuqjFqkWiNiiSWeR2C/JN7Yl/Pr8iflyNAbCk7Yg1r4/JpO0M
-        G8xTsGGOfa35tHx1Mypq4cX2/uB59LA73SC1IoMR65B3w1IPd0qRVwqx/fuKT055zWVf2nV487pf
-        +fRQ7Roqeq6JqepFN54Wnx088MckesuJ3t+PqyvE75tLZ3o8JPMhMlr4iF2GZWU36/w45bmSc/HI
-        dLy0+GQ3VoMEB9XM552YTNkhCiFU45KiTaXpq9qOJbg894jo7eGgz6zoCpgyqhHttEbelK2XPRQv
-        pWLO+/XoRr69jhBErUy2w1R11K1iEbQNbYlNLi3nPpF6KNr9kaloj/mYvhoK8Ts1iZvG124+NMxA
-        S6FGeNwYjc6mdyOB3jIdo4Sq5ci3wQzWLgqZKgPhc56QEbFzLBNVjktv1q39HQQtCEhc58vvfCOF
-        o9V/8GrLRG/EdZWBtspkorfhAk3Ds/VBavSQOc6ClJOmNT3o7+xIdPKu0LiT9mcYqLRlD+uglnxx
-        WI0gLsUdMbfUSqbMWFMQUfDBrWaXXcv2xxEuihQwa65PUecf7zbo/RIRuz28k2lJ9XAhn0WJqcl0
-        jJpTezuDoF08st9Pli6K2b4CRweN2K3aJDRcbRuI5lRiu+tcd62elwKasl5j3/pG7RvWNdSZb7Mt
-        fY1Rfw9e7YabqoXFSyZ7rHhMdzADATOrZ/eo74bABr2bF7jE4Qf1lXWtwdkqKv2eRj7nPZ5huoQp
-        3by8mI+ysLuDYFaIHA2ZdsxE3oyGz+fAtFVYc25eZwOma3JkhlUZ3YgRwihXypoZxUg5m86rCriG
-        MDG37Oy1b+loo/ipFsQx4lXZiuvgKhedfyJeLIlRf0rFUZaKpiPGM4m42BQTVRabycYoyYJo5NOB
-        /v4PcR8z6bgvhi749InpSp/LaKoX8xHBZT4Tc/Pu9LES4wJC9dwQuzvPel9ZCwEtlrcn80f/xbn0
-        DnuwrBMmuNq9kikw1ZtS9ZgSo3rb+ojjZwHdOtdYGNmWN873cwPB4aUwL/G3nZhnkg2N2ZlULoYK
-        fUBUJZCjzsALYSGgQWu2LgzDAqhQzxKnsRbsAMKsJbozyeWc7ycXILUV4i7GRufF9ixDcmcYr4Ps
-        HU1ZPM8/fGV7Zn6i+Q2LCqzj7sFIwaSOfZS4gGY3AXMVKU9md3J24EK5ZNvDAXs0h3knT+mg4sXz
-        mnv9/Vk1Pzwi1iy+SiqkwRZEFH6IK9wT1M+fvQyOc26Yux2R1/zqoz6PFcPv6ovfnlEp/ttsmRXd
-        PL3vXv4ZhdbKomsehwmT4HMHTRFuzDEQ72YRoSUSsHOmrMjijn+UAW+++8H2YWR6IjvlNTQ7puFl
-        zVSPhviDoajhxbCzeKFRXtUAoowHLO1x5VF309TQaOcb28X6q+PJZ1dAEloiXqFHyHlSdTtUPJsN
-        nkRJRZ+l9RTBneaantTjs5ycMijAIujD9M+iTJh0kEK4CODjObotEY2VRJCDu3tjhhWZnRhebCo7
-        6rzHyzL0EV+wdY9++OBPgcbnHPtLcDe+S2JPtEs+mmK1CaP8Tqx+LyQ0dz5XFHf9iuz7riypgoYW
-        tNHBxLs5p6TvPmxEl0+bM3OzufJZSbsePbaSSHR3JZaTrYU5DP3KJMbr9vL4wjmHSBNzkcXVxtep
-        aIsimPfpitf0dI64eSyO8JkuM3OzRdjNwlHK5STOHsRVmlGflVrH8P0+Mcpli9o8vNfyZ/Uu6Glj
-        7vUex88c9I4azL8kozeHF7VHx70VEPyObH391SOQC++CrjYXmXfSPi9Q8hAt4s9rt6wF2wkgCWBB
-        jAKPnPvHowvxKwjJtbHVkhejlAHs9xIhz2uuz65wodDo95Bg761EQ/2UrsCSpvutVzc4t0kF8+hu
-        KRLte0lF1Li/98xUX3k5yo9RBH+tMlz0fhxN2UnsYbrdDySklfadb8zgNOHyWz+G/hnmjw9SZ3vM
-        /uy9iPu6k/3wll0/+y5hIz7vIK4OB7oOG+AzO1sCTJHVEFzPV9RF4qWBKr8/sBifomjOHcVA2ux7
-        zLxXbzSzQ5WDX6xlvDAdu0uHNMxA3NgTO4ufUzmzMwGkNy+PuYqc8p7vmkJ2hWpippycEfc/rQSO
-        fXl/+dLlfKEKM2LpOqPyFqceP8qqCrgPJOKPiwKNcpSGsHKDgKS+N3j88yhDkLPgTgda3fQ5ViIB
-        vvqRuIVX82bHXiKS6FXGY2xl0TQcZUCwJxJVosvTew16Hij44y2wEm5rfVhelwVoCtyY8+odfT7k
-        VqX85ntYIYt6y5Yo4qaj0GpHnG64dEmLHt7jwH71Ml26qIVsvX8y7Xsee2s9NXApA4lop1OqcylD
-        GIYqaJlh6auE6hdpRkt46My7lkn0Pd85uOtdSHaryuXf+rlDa2Qdc9y573pLrSSAm+BSCWuat/6U
-        fAuhvdHxeNcq3ortx4bUfXLm3WCORouFLqTODegkmjqfbHzK4LHPMUZXLY34cbiOkDyWFvEvt2fU
-        p8dnj4qWHOnzIhgRT+5e/dOfzBNbuexlPC3Rg7S7P/px/vIVGtomJLYvRGh2XX6EBVogpjdtk/Ai
-        cjGqgvLG7G6ToSlQxxbqu+cxvbHdZLIVl8KXf+hnV9yT8b6oa3C0jUGMZx+iL56KKCRhR6xg30R8
-        Go8GxHXsMFdXu4QVl1gAwZ4ZXj77GbWh0rpwNKuJbJmdelOw5zUAOY3Ev7gHfdaHCIOZtE/K2zmP
-        ZjHdSCh+XfZUXjw+Ho21coYpkFdU1lqtY8U2k+WhOr2Y4wg5n4Y4u8n652Ox3fmWebzFQQWPrSxi
-        MTaW0TTQl/tbH5qjMSmnpR4aKN/4CE9rF5fjPRgaOUkpwYuyWHX9V8+idN/0xLDEORq0amfAdPaf
-        uIvX725ava4GXMpQYubm7ekzy9gd4vqI2fc8cB4NfQb6p/bp0vSGkiqL1Q0sO3EpHKebzhedXYPg
-        CSXTRrLpxmpOM5SNqw2d2XUfTTVqayQf7gfmCkrnzfn52sIHKS5RkZ973/WRwXqIlHm32zGZw1AC
-        tMK5yqzzKY/4Fw9BTrwSr0efdLxorrAR5x4T936CbsS24KPlYpiJTTYNnxkvCtTsjQ9JVscAfSCX
-        baS3rU1s0jh8GFqnRzGVPsyTJsNbT4p+Br6VCEZJ+uxoeLH7P/rKseprMv3wrd3VJd7U2NLHzrvZ
-        qGAv9PVbTVL9+Lwxcky0dbLv5t/5CPcuZ+5itD2qy5kN3So1CBGE0euKle0jTR5rYoVm4M1CrAZQ
-        ZxeBCk76RqMFzg2ksn8zxzJuyTQsrnfw11tGrOnZltyY1wDhdWkz/3LTIl5MlyX68gtumhuN6rzf
-        zUhvioC+pNUdfWBY7aAo5wlPK81Cs6h6LdTH4Y37+Yyi/ucXpvh2wtxWKPrjh8w7v9I5SLcJX3Rq
-        pfz8sB95C8SK3LTBfzKdblmLvO6zM0awrmfCrKhrvTnWAkMxb9WLOK9hjYbM5uMPr4n79UujZY89
-        nKYoY9/zo3dmqi3htHyEXz6Cbqqf0g26Tb9kN2UX6lPNPQNJHzViu1tMkqkufEOuj23P9HaZ8unB
-        4xDkxCm//m1bjph5gLhznIntK6beV9cyRNVV27D9F48nW9n2imWSMxWTtIumi2nK6Ov3qKwhtRsr
-        Lz9Dks0eRdeiL/lU9iIMdZoyN0ViR396MTV3B/xcJ/uS366kQLg1TKZx4ZbMYvt0Qb7bFdnj18w/
-        l+VuifTX8Y7X3DK6b/3RP/ip3pdPNNS16oIZEWCm1t08LpmOij6Kvvvhi859/WTDgsc5IxB10aRt
-        NFvh6jpkHhrenEvn9xXgivZYweIBzYecVJBLhsFUGT31mdUoAItsPsw/Ld/JzBjN5K9/pfzDuN7f
-        bWwjcVHEVIzrORpq/9lA8WRLvFhMe33EgGXQm7f31VerpNV3mxmmSB2Iq7y1RHybDxfVp76hMJ/8
-        jhfbTNqw0ghYXI8vb7qcNhiEvfogptbJ+lCncNw0ZuV++StH7Q9PvviDV9u9pLPPUt6Cu/b2+LWl
-        74j+6hUX7E5X8s3Wx1k2JJQkXciscCdwKp5uN8iVZ822Ufvy5jgU7jA8DZGosl15Q5ZlGPT6dqUK
-        1fbJKts/MEot32HYMxdRYxWtBJemrohhXJ6o5/mth6PFK6p88kyfLmqbweUzJGy3vofdeF9bOyQY
-        mYFlRVZ4g+NPAUNurhiuA5lPMG1scMjkUSYoWiTqVbNF4vg5sH1YfX9P3apScFOLn5/Ue9ktDBjy
-        rUynMZc6vnDcClhoERxszic0DcdZAMHsRIwkUutD0D2XcHkXDdutIo83cp/vkHlJe6YTs+bcX5hn
-        eSG1B+aJ1sC56We5nM+rCEs4zL3RAu0KwX1/+sNvLTtbAHVYLJmaXnA3u82zBr3EFV3W2dObanVn
-        IMfCI7M/49Wb2QlCJD0rRrYDqcvZXV1FENfbDSOCEHh8VC4qsDo0CDG7uuMmtZeoTl2fOdWO6WPq
-        uz7EpXv74mPjzQzSHvyXwIlRPAjinz7MlWFQgDQf5iTc/GwM9OUbslu94nJaXvMlXMoLx3BRsE71
-        j35HjRafiJpeaMeKywGAb2VCBe+Yo/qw3TfQLRObDl89N7vKeFa6zcSYtipNtMQGvcvizB3K1Mst
-        6Xe3yw6q++FDVNmZOTNF2P74A8fe61NOy7tU/fI45hbeDo3dVbv+yau0i2AkortbBOsvfuKFIX3K
-        H38r4lidibo5WfqErvUZjo74pCv0mBErdqEAHSjlHz081CrewXLBZppGu8LrO+/mAt/ZAtE/fh19
-        /awE7fbMCbFKnFB9NfdKMZz3+Hnxz96k7S5LOI32m2lHvtAnyGcX8rUjkN95o2ES3OHhBBlLadkl
-        s1hoLcix1jFTPxy9wTl/QlnqLwpd05MY9fj0yoBVrs+sAK91JmFLQl8/h8XlNPAJdE+GKoufRG+f
-        WjIEN6GAfCX4THcIdHxUHqqsTTbB0rd+ukU9ir88gQqO3yDu66krL3iS0wAxn8/NW8sgicsbvkTK
-        mvP2PBqyHFxPX30Rd3zC26uymPyBmAhHnEvqJkSP/duh4s3Syok46xyS2+v81Sv7jpuv1Rb0blzQ
-        7nZbRuyjKVuEh5gx/BqwPtWUnwF/LIP5p+qiDwM93JHU7XdY8IygG090NUMSSAaxmyT1xnTuvvnk
-        tmc7cWcj/vMvjEkJOyzHhlMlWN7l1szfxPb7nT7+8peYwYuYGU0jtuCNIbc2TfDGfQ5lvzusK0ju
-        TcT8izvp7CjbW/TNa+gru7NuGixJRa0veMyKHN+bLoaMQc7CO9vFYlEO2anbgrMj7JsvbX75ZgGO
-        urb/jBf1ive//ITOdJV3PLmgJZKeNSPGNx/48cWmqihh/sRxt4F7e0PDsNHwdNrmHdXzEqDOsM3M
-        dPfi07CoXCQY+YJsWZvocy61ZyRsE4uZmbDvZn0qBDiBMNPkehjKnguqoCzE1xHTmvQ6Ty6NDR1C
-        b2Ju0yaZwya5gv7c9RR996e39ncXnTazgKXufdDFePOQZZGPLtstn0rHzIAGv/XBEj4q5Wug8R2G
-        5nWiDCo34v6RiWgKpBXTjqT85gdCBc6+upLIdg98VuJIAKnRQrbvHbOctJBfUdG6MXO+53tMXzmF
-        bvVcEH9aKsmIMwOgqtGWKrTsojHVix5S5wq4XeRrNNTrcInYrWZEO72GhE0SqiHIgpAY+U7iQx1f
-        ZXD8/M5cPYy98bffjmGumTatonL+5rmoPrI32++DNR9q/9Oi4LQaMJy2sTcNiyBTjsZr/OVv3rCc
-        614W1ANhxlOZ+DRYowoPy62/+PLWabzxfWD3qaCyZusd+1S7HjV7p6J5esGlqK9kCvl6azOiXM/e
-        mCLPRt/1JbrXRH/8FwSnecbfPAK9Lk7aoHZXlWy30pNuWraWjz4LVyDemooljc9y/sMH+pKijM86
-        iUP0WZANwy8v8L79hCXIZe3gEbGeM+mBpT9+qoWt+NW/doDM+FXhMW325RK34Etc22B6NNMkGqtZ
-        G8FKcp1Zh6JMVjUqakjVzZ14sbmJRvlyOKJU14/E9oclGl5ICKDRkhMum26tD/YZBFS9QWD2fhrR
-        aDn+7ZcvEuwZY0e/+TZydEFjpj7rSf37P/izdZh1KEN9WOrDiHA1xkxvkJWMeN3doXjJH+bPxlBO
-        mtJXKE5RQyd+h4jqpBdkM10fib1/6N6PL5D8OF8xzMa+W5tUFSG4SC3NbJA6tnC29Z985scPc+xm
-        AnzzXCwvcOuNaRCDbEbGjtyE3vcmzU1kYHHB2TZ4LPjnh1/C3rzRBWz9aKyCxx1+ea13PezLOW5M
-        H5IH2jIi3GdvGmydwkli2z/1w4tKw8CYnBAC2z6Z6rar5aHEFIvrvuBULLQGzPN5Rb55hcd/+/fr
-        T7h3HSMq6FOh1OGLMVc9r6I+FfkVllxqWOath26Ol5ABy4UrM+9bB/W4IxLgonli3oYPzvwjWyLz
-        iJWff+d9mmq+chr3BV5889hpeYUCkmy1I/Zn30UDyNVRyvmGEFXiH692ib5TOOEn5t3iVyfqpAf4
-        5d3qvSzQF5+O6Mv3xJS0yXtdiqUL4WX2f3lqOSyvjYi++gA3jYK8lqmxiE5SazHtOD3LIXi/RoBj
-        l/7R780JvVTQ6zQiqhRuEHUV6Qj5xlXpOjwzj+qkAri83yXTRLPkc6M2qtytuzUVvnzDpTO7gT81
-        NsPuXHDmz+cd+GPlU+rpT8QWEAVKt7o5dJQKV+dRrmD07Rcx4wW6zj8l2qJsc4kpXIaUT867Cf/k
-        Yf7Xz021/2lkRx333/oOuvaX/6ZbiNnRQGnSjTjbQeOrA62+/DjreRDAdDQ+jCywGolhpbcQXkYf
-        D8Ne69hxNYagjbsIr9Jr1PHjSgoguNs3jMRW7vj0cG4/vfjD53IY7McV4ue2IPs9cTzacKlHSaii
-        7/55SS/vbkeIO7oiKsJpyRdvo4DHzmiJxdEYcfOlqBBcFi/m1GTFe5mYBRQdPpFfPv315xRVzzwh
-        JF+PnBWXVwOCI3aUN6399cvB/ecfifnNU2elpc2PH/H0zccG+BxakLPThRGl2SWzfhlnpXGkFUv3
-        01sfZ+/RIDlIAyp/83++cLIAQt+byZ5d1t4vfwdrP03MMHZbPmTFIADfLlyyjZwVGpaWUmxaHzxy
-        4ShIeOL51fq0KjFthXvCp0tpiZBi+u2fnMqIRVsewLcfTB+WNib9LPsydKN3xcu8OaM5D+8Vqh/H
-        BTl885XhmwcoR3udY3m7p8msxKxFzd6rqODyqZxscwXQLbY5Xk/zp5sCpxTh+/6Pv2kq+Rmib/+T
-        bXt/k8xMMoVfv5D96bf+8tpv/kqMcnsv52+/GnD+qsg26jgfU6S7v7wQr7n8LLnvNQJ895fOga8n
-        4q+efDgmTP/4u2QthZ4AD02U8Rw8HnwIVKkF6yC8mauedt3MHHOLqt6n/6Vflq2FIYi1J9O//WD+
-        6WuMgsTI2DagWjJibm/h79+tgP/8119//a/fDYO6SbPX92LAkE3Dv//7qsC/b+nt38ul+G8m/rmJ
-        QPtbnv39z39dQvj70zX1Z/jfQ1Nl7/7vf/6S/tw2+Htohtvr/3n8r+9c//mv/wMAAP//AwCkxTP2
-        4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be211ac8cdd169e-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:55:16 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '114'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - d39b785f954e1f1cc64746735c44b522
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[18031, 1495, 220, 16]], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '99'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaS6+zOrel+9+v2Nrd1KcQQvDM7nELECB2EnItlUpACOEWrjbgo/PfS+Q9OlXV
-        WQ0WS3jZnmM+Y9j/8a+//vq7CrM46v/+56+/i7Tr//4f87NX0Ad///PX//zXX3/99dd//H7+f2/G
-        ZRi/Xuk3+b3++2X6fcXj3//8Jfz3k//70j9//b0V0oz2TVyG/Rt/ZNCN/sr2Me7CatyjC9C+y5mX
-        y43OQnuxAIvnCnstoOdMy07C9hEVhJkt2odNlyJNVtPEIEoy1f743G1jZLXFlxxOSA8nvUg1eOgL
-        D6/UpEFVYO8qqKnns11X2uEU90xB2Ft4zPyMSGcv90Ihft0eeDxtwR3erNbgvRZXmEq31O0M8w5I
-        JkRhxjHIEe8+Y7d9RWbIdlbj+NPo3A2Quk4le1l0UBc5bQCvLtjjplK3qPWm5xE1kkGYHTeWz+3O
-        yWFydYrlGuxwuiw+JoTHRcZ2TVRl6Td8OhAk2oUYtvvRJ+kSd4jcHcRUPbfCro6bBnxjonSpJE04
-        tCqWUXROMbOc3spYFY0ShI+FQry1v8jGYv2IUOccQ+YIx2M4Tu7FRAGx9ng7VPeQuyf7CJcSZKJc
-        4jCkyzhQQLqEiLkv7x32RskqSDaPhOzS85ixM9I0VHmKRZ6SmIaDH0kNdHvoyQGg8CfxNFzg2wYt
-        sfB0Caf2k9sw+ReZWXe15MMldkVkyreCkbF1EdWN6w1sj+gMq2qC+nCfmtsXdEDw/rjiUzLYkYxF
-        3GGBWY9sqCK7hGp1/hLvEqUtX/tPE/L11SRe3GLe093uAfhauhSx4hSO6Gk04G/ZG6/XdNIn7g3J
-        dp5fpmwDi0+X+JujJOFftrdKMRyXb/8GYV2UdHVdqLoYWE8JTvtaJkZQn3Q+uSiF9zfV5vlC4bgR
-        8w7sbpWzgzC926HcVBWoaikTbJk5olZTi0BisSE7NWn4KBC7g2TcXdkeENG5nlcUkmo0iKkbj5Cr
-        KTkix7oBXlzflc/Kpw1QqkTDqA6VbHSPiQif9H5m1nlN+HjX3x36jU87RZnLyfr1AMaOhLz7j8BH
-        fE0aeFzyHi8sU3RHvbjEEPeLDVGOzyWaKmhsKJ/ZmR0ih3C+eD06cEfxQtSpydGkfrYBaK6tsVhV
-        Fc73/XWA9Vk0yb56We3gHO8lJMmQ4rpLM7c5+JcBmnd0ZF61vPHaYZEBBCdA9M/lGw5xr5+XU7uQ
-        fvvRr4aqOUN2WXvEWJ0sfdUohxy2vqQRUkeV2x8fWgfJ8bVhujfmYf2muYbe30RjhH22s36sG/hm
-        jz3Trh/G+3qbxZs+j3Z46M0NYqwcE5CxfGAEraKMZivlCNwo15jN9UPH5lGCflV12i43Q8bHhk5w
-        501M5Wx68knTzQgu8QWRpziysJNW7gLtd+OJ4ckq+dS8NQPOYebP+mCgIe7dMyruyy87VDHT6WlT
-        5CCevpgQLTmj+pHnDxQeISNeuVrr1Uk+drJbe1fiFjfR791RtGXnXjXE2Nx8LsjrD90GZLfHWyIe
-        /eEbjBTmeifa9UMQx6KGwZFOLp3IOfPH3XfyUH9x7kTvs1bnlrMpIV7M9dIbk8/ITTFBoFPC9C0U
-        fOLdVIGiqISYhViEw8M4BttPc2PEXTPb56wcU8jXF5Xdj2sr5CtW5tAL45aZ1l5r1ytS2UALZtFl
-        /8naSjwdJWgsd4dHWViEdIsmE+J+uaCLd73Rqf86mlAZWkOceyxnY5d+HOi044Io62OlTwK5yRC/
-        WhcvV8PXn9zjRKG+Sjr76f3gHN85fM7am3nOQWq7LdTpn/Fg103C6aefwyMT2KwHqLe7SZPDsTDw
-        8m0nLsUroQL340lErZLCp2hz1GCXxA1RDCdyuy30IlzW54p5zJBR4w5SCoF0ydm837OBlkayrV+b
-        hpHi7mUUbaIbuu33Jt0cVqeW7ftnBMiOQ2YefN4OZ9RK6Js9Me3d7hnyNzk0m76Lv8wtbjt3/TSP
-        JTRSqGGx2yltx6znGY7jpWDEKAo0nuRSgq829Xg1tBnqfnpLzDRgankrWp6exRLC2pcwum3PfBwb
-        V0OhUq3w4nA02sZhnwbm/kGjRv74g75TYjDle8P2Ec4Qc0/2GV764OLt7rsK2c4ORfkl0IA5Ltm1
-        6zfZ3+Sz4BywKF88NIz7dYXMVLvO+1nNRuniCSDa4JDL7W3zyX89jM2oRhFxN8IWdc+ifqCcKStC
-        vveM05RvKTiWisk+MK5hf1m8BfTbj/YleerT4dJW6L0WVsR9e2LGX+05AV58TEKOm8Kd+tzEaOvm
-        Ijv7kZt1j/wmwnMxhhj4/uYPYX2+wOPynZhGjTMa8bWq5HMmvglZD4z/9Af+jGeu//YodWfZIfpA
-        L7nk+d3yrUaQm6bBcMYHd0DSkKO2vp/IzA++cNyoAizvekqHZJKzCklDiSpPs4gpP59ZubnWRxj3
-        0YKQNhqyuf85IK2UMwn03ZL3xfoRgxC/1mRXRYk+bmFNgS6UM9H8CHi/EasHYNHrCOFt5tLL4mOA
-        Oq2ALs0m1PubZmMQn3n72+/+9CwVEZhZnXCyPj79wfbKCk7N8USiZFD5cPsMMZymMsVTu1zy8hzt
-        vd96M5VwVx+W730MpxOo7DJ6bdsno2lCFxSYShEDPsrrtQxUvFfEcw6Ptm4SqwPfi154MXl+xhev
-        l4LOgn1gh4P4RaOqCTnUi/UGb+7L0c3iwxTD3elGds3vVz6qHyag52vlMWVzfWXd3M9l9j1OTK2S
-        WzucgkACTQi/RMsGh4+77yJFSrKM5/FEaHzkiQHZ1ZaJwb0UTW3yOkNRHY/kWt5798/6irX0pOW8
-        HnwL+gLk++dEzEop9NZyVjK6Vt4aC+cgzrjxdQY08w6F3vi4X94r3lZVv0ss+o/SZ+7JKOGLuicj
-        t8VeH2lhJdvNoTqS8ChRTu1WogjQWafFzJeMmYiis+Ce2T7a2z4fa7+EUn59Zj5YttU3GDvohUEi
-        6q6O+OBNyIH4WtVMlYQV6t1jJaJw/BrM3txDf4jpLQIviM8EyzfnD89Bdy47Zh/DLuzxNYcf79KN
-        +lHdNZJ8DdzjxsEbqyz0aqw3NnTnYmRqGU7+9NPjmU/oamh1Poz1Kob5/8EC0176cLxLAiiPyibK
-        Lf74VKBqgtbntUsTphr+lPqohG6/6Gc9lrN+fR4rlF1Ei3jpELZDIZ0mVJDqRFyz9tvxWfDjH57U
-        sViFw+Q6GOVx+GSO/3y7QxUpJfTh2mXKJXbcUTw1E9BSW9HWqKNwbD+3Eha7vfGnf3KjQDKKD1pD
-        Dm5X6ZPl5AoE395mdsLalsl3R4PbZHK8kldC21TQODDvL6K/yMvlb6bHgMXDSBRmnvQJ5AxDpOGE
-        LuZ6Gh3yBFR5ukflZ1W7dGqzCcxGW1MxG1W3D+x3Kn/Oas4IFhI+xDSO5ePmarH9SY7Dmbcq8M7x
-        Co9WLei8ywwZiTK26Cc9hf5UrNMLGuUOYfGe4mwE+VXJd40SPIzuKqSltMFo3A8dOQj9xGlYiwYE
-        lSLi6pJ8EU8nyYD6UK7/1O8Y2O8EhKWB2eGxy3SeHKMUXvrk0mnx6rMuPuxiMJ9sT1FfBPqYXaQS
-        eJ9mzEj5Jhy1/FCioFIRXT71g88H2ynRrB9Me5ZtOIpjVcKzfLnEuLyTkF+VvQwPd0GZM7gXNEFQ
-        G+jHB972kfjjRkwCaMc2xZvhS9BglNdh80kvB2Lu9tBOOxsf0UHYCmRPVhWf9fqGdknUkPtye0XV
-        5DoeSgHbZBfYe59Obl0hcfIapoyu4Qq/+tbAOGH0tD4he2RSBcjmmBxi5xGOhll7IOU0x8LMk9P1
-        Ldto5gOMLtsmzNW0SuGQXzBRbhl2h199WFzmbH9d2m0/tbEH7LY1iHvXaFjZXWUj89N9CenLYzjQ
-        UvHgKfIFleb1mFbHOoajYlTMQlIQ/qnPKEgHcuiyJuPZ9aEAuQk2s9Fd9Yefn3SP8g73KeG8yO+3
-        BXrp8YsmyRS0Ne8KE4S1OWL+dqx2eO7aEtTTpsddOqCM3dTHBME9uOJ1caWIm3WVgua/H1S8v1Q0
-        KIpSbU/PbUW8ZrkMO/F09SDrXw51LAeFlZrmAoQbmTDHchp3UpTE2L5vUkm822eN6BvzAZrBmP7w
-        ItfzpINZf//0m8ZqPgIsv/cjXaIVtFN6rgK4PSOBXa+Lsz/peWgjL4jOTHUpafk18RT5lQcd21Wf
-        WB+1fH8GfVXnRPsMms/7PBxQOEoTca/ajnf7nt/QZldLbHddfFze6dqwvWvsQjdD1/r81RUU3VGt
-        0FV6VsIJr4Yb+N7k0tXUdj43606El9C/mSb6YtuN+2UF5jO44SLQD3y0WhajKq9MhvduMPPiyYG6
-        THJyiBzG6+uy7NAYGMEffuoPl+cE7ecqMC8ZPohKwhGDeyLbP38/Ro4EqKaZSexj+MrG0dl5f75v
-        7vatPy6XJ3v76wdzf+TDZ7IeMOsLXm+kE/rDs7NfYZqAPz4Xj+gC+a1vmAPBN+TfkN3kMbDedP05
-        cp9aDbXRbpgeVDDcyWeRoyYgKstp7meHOV/Af/iZON/1Kqx/439svZZYfa6GK7xiJlJspaMcjx7i
-        SHpfNrNfZGFxK9y5fjAMivcmeO/KPq1fyNsYa8+Z9+8nbMn6GkCoNCs8uYeNTu9aYELqLI+4EY/f
-        rLtnbgPukwRUXDxtf5j3G7q3s19d8wVn7ugEMOc1M/8WLpcE+vjDY0ZEc3euPwy9mz7oUK4P/zXe
-        3/d30WHBqx8f3FQnJ2pgfRCN+6aDxSLM6OIUxPp4XTYBmM9nyHZEOLfD4iXKKOvjHR53NfBGoPsU
-        Fovd6sf3nIvDxv75U1rN9bmaeQfNvMBs75TP/NU/JA89PniNJNlnxX0yQA2wREXdkMLpwIMc9jQk
-        eOYbNCZskuGe3Vd49KUyo/ZBHeBJ44o5xdrjdRMPGGXFq2d6G5d8LNaXSQ4/5xM7zHnX6JD4KM98
-        hLnTJe6U8vHxJy/AL9q51awfcErPAlNjD7fTyztREEwnpWMTftyJmaWNDt1tmPOWhzv2GdyQ/E4o
-        wcKpzKZnaYvwFKcN2zevozuo2leBmV+I9XLLlleoEv7kY1g8MX1wmONBl8oBs/GtcodOew2QHGOB
-        2KlA2ukzpcm2PhRAisDeh0Ng7y8oFn1n5uXnzIfHDk4yWmO+mjCnuehHqCD1bTacNOyS42RAq1BM
-        1+c1QcXcDyH4MptWhtW7/OUeg+0lrunsV3do9ZufFMiBNpYThnR07uavXggxmilj6NmZaHGNJ3y9
-        L+pfXpSDheQj209fyx2execBfv/oyN6XjXA918talddPvNDV2p/iQ5Jv1619I7jdWvpIy1sAxX2R
-        0q3QT6jnXrqAA9QZ0d/OA7HlgmpAWGTSz32buj0rAxOW62pB7NEu/dnPSr/+QnaBfkB0dM7DdlTj
-        CKfwuoXjN7QkuFZJwch5s+CTvz1jiPvtghj4mrR0zqsgaoSY3Xb7NhxzUZ39/KljP75i2WXvyL3A
-        t3QVH0S979Iihra+eczKrmu/vyzuAhJr+YmHqO/5j59AZqsPcT2uubQCGsMquXnMQDcIp0vMcnnO
-        K/FiZ8aoDquThnYP50mXL7tCI90dAjkzspg+H4bHh+Y9pkDe7gtfluGaD298VH55xpy3PttJupwf
-        21lviKIoPp9+fLNu33s6BpbKp8XLimDbHe50Nc8PNyxjAe3nwmjdpYJPn+XBQeT7omznb7A+sK8f
-        gAahwQ7idOMs+H5ypGWjiUHTj+H0OV1FcI/SbvZTERqWS7eEfRn0zNY0e85nrByWyypkEXpUnEWN
-        XsmBZXyJs9uZOpeE8iGb8qUg3jmKfPqZSkGWmRhh2X/2vHOO9xzyr+IzVdqMPj1cvgsUvB9ryrYy
-        a/lBWFdo+b25TDucPXfcfWUMeHd+MVd5p5xBIC8gK949lWxvwzndVSlIhmUzd7nwXFHAege3D9/R
-        IZ2SlgdWOyBsLBjBrquEs5+LZPuSErbbM9yi+CDHKFH2Jv69T1mZAXRBuWdeuSr46LCLieSvsCQ/
-        P8FXrDmjYLhbs94c0HAKzjLsd/xEn7uy573lfrTtrH+YsU+nj636sGHOswjJzlU4sG/4AMXWOrqJ
-        8ErvvRNoaL+gWzzMPL1qEkJlvPD27OCjrdu/OnxE7icp8ZQNoBfyfRNBH65cmnaG4w9BRSa0zb0V
-        89RFlvH0vMhBSeBJ7hvpxPldyxYQof1p9oc7f8BX30DO+/Zku7m+Z32hkF33y7n/btvx54cGm6gU
-        ae/WHyVBq375Kk6z1bqle3oekHFYMOK8+97tfvtj5klix42UdeLpIcNLj15MvyrPcPit90Hv10z7
-        DH7Gm+VzQrM/ZVq2Wmf0c3qmKJCuNZYuydPldJekW1Q/2bx/Wref/aJsrA+E7R72pPOXxyREd2ZJ
-        XC0veccP3RE2iyKnm/Khh/QUiBU6w16g5ewP1s8yoLB7i/bcL2/h7BdttKcP5+evMnZVVAk2u4bj
-        2a+jYs5PkZR3OXOP27AdA/ueoP3NXJKfHrCxaSJQHo1N61351me9vqHCajeMrAeCRrTBw+97WHjk
-        vU4FEkuwZLces1BfIT7nfSjZPAs8Ds0hEyKnfUjLu5rS4yUO/SmqxwFo0WnMfhRZuDrJaQn9ZR8R
-        S8k2/q+foUayLgS/qdCyrxwfoXm/r/hT3kRO40Mnozk/YcrqOCAuTt4NBOwaxHa80e3v2StBW1/W
-        mJ1vtLbEVzkBRdGc+XuXjLFyK6D4dXmwOU92p1wMI+h9sZ75oc9GJYkqNIHf0lm4M2q3W01ORutK
-        TGWpuzyspAhdrfKGl+fNoRU7bZDBChYq1dfTOqQrci7/8JQDgeWP+T1ewJ1XMRbDb+MO5FaD7EhH
-        k/jhznPHgxDKsAWRzzyr6iwV9DO8cRFQHu48nZ82ywjUFN8Imf3X1CbXIyx6rjE3O03udLhkDehX
-        XWd7tx35aJgfDMtlExIjl7pwMkxkyrLk9HgjdmnGdtXpj/8kWFf3IQ/tBfx4m7l3DYczL6bbXl9R
-        5o7NKus1Q49APUkVC/xnj8ab5qVQXW4PdpDWe9TL66UEwvrxnvOjN++/IZHQzkq3zGyUmDN8Gb3t
-        XuwTvAJZQpz3XgpWsDUJplrr//J2ac6TiNuGtVvssW5u5/n+k1+uDcsDuJhKS7SwTNtJ0x0bzf1+
-        9uejW7w8w4Elph7TvjLXO4lLE+q08wLnpiuj+o1rGTnvxmJ/8orP6SqAQ+7xnGcabntTrwaUz8+Z
-        uH0hu2yo7AeAc11QqVqwkHWZIYFskYzhZ57xoV5Ukazl1oYuzQL70z1jwS8PYfvykfl96pfz+SJ4
-        tHx+P20X9/pxu6tii27F3tGn5bvHv/MY5hm27k/LZauhP/5MvsT6EJTSGbYg8Nl/IZ/vqmcl42vu
-        kr3bnlD1y39n/WNXqwnbxj5gEwqrEmi3fR3csYkHD3pfqJkqMsVfR43ewHx+hYO9o7b0+Die4eBS
-        gsWD77eTeJIuYD4fNzznle3wLOoAAumW//RZp/eMPcBCZfrLN0Nq7h8C6vUEEasInLDXd8Hll8cQ
-        /YhefAj3lxTIN6qJQ80hG99ka8BtCkuG/WDl99toVYJb4ytxTs8i7AViU7QjSfBbT737nccqm3M9
-        84SNBjVNEuC9tyKG6cpzHhBXoBzbAW9i/Mq6y0JtYKsXT7ZfIDPkdaxM2+sgiOyyOn31cT6fRPN5
-        Mh0qSMLx59/9PhyJeU3X4XzeKIDfP0dmcE/j1GH9AubzT0IcJrY9+/bnTeqASwJqHttJfugXae6P
-        9HPaRrNef+Ufv5M5L+e0fnEPdI9O9N1GQ9tnF5DhvVzf8ST6t5anEzzQ8q0syVUcNm5/Cqpo+zt/
-        FF8dDce5P6JkExZ0FNmY8V11BUiSKcVii+qQ72xfhHuo50RV31lYP3ejg3Z3sWWkjjYh7z6iBuFj
-        u2MHeSqy6eXdNPjtH0y1KJu+6J5DpB0KYqdM0KebqmNAddDgiRqfbGqTxwJ20iDTJW91V/ydhymP
-        S8C8qDXD1U+vLvEN4c1Jjv3+l/+oTVoy7/Yx25F9izOKuM3oKG82fFj76zPg3Sll+/k8eCrWZYP0
-        VfVmXiOr4aQolQl//24F/Oe//vrrf/1uGJTVKy7miwF9PPb//u+rAv8OXsG/BUH8NxP/3ESgXZDE
-        f//zX5cQ/q7bqqz7/91Xefzt/v7nL+nPbYO/+6oPiv/n8b/mb/3nv/4PAAAA//8DAPzVCbHhIAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0b986749b8f9cc-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 22:52:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '18'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 0d93269b5615ee055622aca99d9e4aa9
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[18031, 1495, 220, 17]], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '99'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWxO6vJbm7/eneOu9ZXYJCCTsO05yNlHxgFNTU4KIICgCCSRd/d2n8L+rp/vG
-        KgElhJW1nue38h//+Ouvvz9ZXeTj3//66++mGsa//9dy7H4bb3//66///Y+//vrrr//4ff6PK4s2
-        K+736l3+Lv+drN73Yv77X3+J/3Xk/1/0r7/+Nhu9on7/9KJZFRRREw+dQKPUjAE9rMyjbnrqTPHl
-        c7CJYWMEP8GzpfZ+7hJi248X9HfvB+Gis+tn15R28BuMChKNDbN57gERpCyKsfPy5Z5sQNvCJPnM
-        OCQjqom2IzH4qlwgq9C3MqafrCOUQiZR92jTbMgDoQIseDyRnutzP21j5QbTwAWEMfSN5vdOyAEN
-        DxsamYUSDeo0OzpQCpsGkdMmgwYphPIKvvGmoW7PTvNVgI96Eqj/KDc1l4ptDLL31aGGPab2jIpm
-        gBEBb0SaY9DzUNghePeeO+pDXiWjwOMKykhqcAD9iz1bp0qBSh1uaOhpVUQlYXfQ2Ls+oDqzKsDS
-        +XuGVe56FMmt03+79e4INbBvMF5Hc8KfRrKDosJKitw97meJJSmIGnBHsFdLMF8vowI+YVuhefBE
-        QMbV14BfTdTo3qiPdrcu7ilUhhBjS8BRPeaKeYQ+egc4Eo4cLO9ThoJCMmxcH0rNiNenYGhWLXZf
-        LzmaLDzkUIsPGeHKS+LTvYgVbSOeZuo8U9TzIrcQvL2SkW4qQnuyzStZX73HBsdvf6inPJArUMM4
-        wZZzczl73aYDNL4axDZJ9vVwnbUKxpK7I00yXGz2Xpk7OFWnkgYvV4xouvq62r15mwSWyteeTpsy
-        1kceOnQLKEwGks0t6FbsSK1pq4P5As4hjBRI0PRhhi0aPB9gxvMSI13ec37s7TMM3rTEaGeRfqI2
-        FQGukgv6PMqmn0/4GMOSrGvsRKdVRM+2d4Zb5N6wTV5GLWv+S4HeqVSplfWnZDrc7RtUBh9jL/y0
-        YDa7jwLB5jhQy+l0m+SVn0NkIw9vNkBJxtaXQgj6S0+d3frN6bdLJ/BQxBe2XjHMiJI+fPhevSx8
-        4KOSzLRTz9oqJBPRYTkBNq20GwT17Y4N8y71syx8cribrohugPmsJ/CCKTRc5YCdXAmy+T2blT5C
-        H9HLt48SAo4qhJDcLbwJs3vPM9ASaEhqjjQvGAHFWhPDTX1LyWrIupq4PTxCr3ja2LWMB5j13kar
-        qFHvNDZPIR89FgrwPbcpxunVrdePKX1BYwUrjOyn17OT5JXwKVkx/TOfsKUHcMAvY3meHe9Srz/A
-        IKcGEUUtTuayxBB8uveAgHQMsjn+flMYhENPLUBUTsWzrYBgZm80NeUt4qN5ZHAsnDtRLkRLJns9
-        yTqyooiQrXmpWXK3X9AXOowvZXevyTwZoZavWpNuGvxM2KPYuqq1cTG1/ZIC+sorCPdx0VG3dHZ8
-        ErZXpKWW52Krvpc1+/T2AZi+MCIVXtuom078DNQxIki661lGFKWKwa3fVzgQlYCvm3giusQlFynd
-        /lVPjxApamE1Mg7m9QH8O1+13kTUlyvaQ/Y1W9jGtwZ7WC2TOXCvN9hf1hT/8tU4qnULe1HwqPtw
-        Wnt27+ILXov4jU3rZWTSoY9C6JSJifE6L7PXZf9wgbFVPHr/CIndR+imgMvBNGg0Jh5Yg2KE4HXd
-        +uRSdnpNEnHtA7A5D6iLnDabbnexgp+uGdBb2HY2HzdlBctJUjGiGz+RQoJbEM1Qxc5XKZK5jqcK
-        3tBhRGs5ftcsHYsXYPxF6Ob9qDkPWOTD7FlEdLMZqmgctt0Xkmtg00itH/2k5dyFSfD+UjNtLjaN
-        taMMnlthR7IlHpZ4HeAVHtJfPgFMfiUyLDhRsJ+iFR/k3ekLdent0DCLdoDpvn6AEZKe1Pv2fTI7
-        3bz7U6+ConXs+bLqNNhotx3erg0DsMMcvOBmnVnUUTUZzNpXE+HQ6C1qHVb2/LtJfWik2pu6mmdE
-        cl75BTjqoo0D8Nn3zMT5AdrXcEWkefpEsyVdJkAGdETqWVQAuar9B9AMF0SVL0r06cCWwMvO6hEP
-        d6M9XLezBiVdi0nnJoeIfLzwC+CnCujmIbxrdumeBhw8IFETNU/AHbUn8OpETyQIngGYw8cdGNYr
-        QNaZ9gTz2jq7YHlfaBg+sKfzzEQ4ct/BtxmVCd8JCoRrsprxNoJN9tkN+gccn+xD5LjiEbOy7gjk
-        lfBGz0np7PE7XzXYbk8Cti26+81XC0qDc8LyPOBTNH0+0HY9gpSdwGqe1KEBb7djgANftAHreNyC
-        axSc6c1K1Z4MyceFxanzMCLiNZnbra+ARzoVtBA3PJrfpxApQTn2OLhs3pyvWdYCvv88kH5HRt9b
-        QWFoh75WkVw6E6e6pn/AirIzta+HTT/L59wF7+wuYVdxOZ/bzo/BMn8Emk7GSe8lFjQTfYvR9tDW
-        JD52JWR5yZAcV4k9+8LO0H7nL2IeJqNmkUI93NoS4/aa1bw+Pr8wdOUttsuK8e6y6hTYsNMDiept
-        3893PzZ+6w1Nx1WSjMQcBCjsvyVZxZ5sT8c9ImD6pnsc7m/MHp7WCUKolQU+jMThfN4yBE3V4kSb
-        kZGx9XDy4SocJopWLbbp6zNZulYcJoov6jOiiWcRuAcPTua397VZ9MrYL5/iramt+4+bBwpc6jPd
-        wnIH+if0crDOLZs6wbnvJzgHORyIccHRaf/i1D7VDtTs3Z5mD6uuyToud1BoiUumerdO6Cnbu3Af
-        FkciCn0Usaq45yBVIxM7WtTwcVKBAN7eIyKqL9p81D3r9e/85r+1fiRPxYL3W/vE0eXpZSwdzy3U
-        2D4jK2f94eN7JxfwfatyjEPfSsaDF1baC8UfpIBZ4OQX77OfWxQdqwRMg9fHsKuJisSDnCVzil8t
-        +LbiDge71zmZNkf/pSsb54hPHJ8TNtXcAegU59h5XTc9r/xjCx7uFFDPvIwJIf3Lgpp92FNvd90A
-        dgw2L/i4TRwv820z2760cM+rhkhX0kStoFoCZGaVkPm+yZM/40Elgti9H30+i8XWgBO8tRS7cp4N
-        L4scoXPGGjqy0MnWQJgN8BhlB3uRP0Sd5moxFJoupJbdsYRzU6qgO1eY+t3c8WE3mzf4CeoWibnS
-        JbPbSAo8YTH93Q/061tpQb/pN0R/bQvOxXOkwfuhnmjU2xt72ByNFzzyScf2fg4yHn1vMUiMpkT6
-        umyjacOlHCz5gl7mwcomeZGDz+9qQ43U+GZ0uOcuLIlUU+OCT4Ah/yVDIsUPpNanRz/9xvfTw4gf
-        i77Q/EED6I1mHI3Jm0+fdepD4doQ6pdGFPF6d9fgCDYH9HbSVzacgxODdoJcbCz1fp5ULvzRL54+
-        1pwk4ioE76aCZNBvh4Rf1p8JSnztkjWHL8AHyfvCm7G3cSyHm2jYp+sP0OOKU5s7DZ/V24TgsDYq
-        aoFH3c8gfE/aBh1ntFYgrbmxvaYa5GVH7at5rplvhEyrOQoIH8Q6+QZTmoO3X3nk5bkfQA5bXwB3
-        7fPG+NYF9rI+HGAPaIee4ZGBKZmvE1wV9EZxqkbgK6Rr5RdfBMCTkcz8HBF4wK1BzcbV+VilDwtI
-        NjfIR0+8erqfoxYu9YbauTX2LBHXIfSK2ibd61Lbk/OgLlj0JoEbaRfxNHsWcFOnKcaF8simcDhq
-        sJMo+tXDbPr2SQ6xnshEpB2rOX0qMVjWN9J7JPX8azqpWpe+QnQj1DJ2/5oTOClaR4Tm2NXTqfuI
-        kM5HE9+j/px0llqX8PvmHVovemKMivsRqGFsICDZWrbo+wPs8ICwbe6s/k89q0azxDjxYzArqPah
-        ebICJHdOlix6/agdVl8XzUNqg3noPsLPzyCQP1nE6Hp24ODDmaIjtzh9Gf0H5ptcwlFsRBlLxJWv
-        RYa0xoZe3aOpq2++WjzIdtGjj4hP5hhCq98gwj2aZbPC+gk24TnE9p19OZOO+xjSZLejbvDMow8f
-        nBf4hpOII5fue/Z734X9YeitQNyPCXcKGJzGCIGTcQLzlTcIRoN6oObe0Tj3G8GFB1Q7aLeMZ8au
-        FkIfNQH6rpCUcXv7nPTseOLY9a0taKY9fYGKuDkC8FRmY+w+J7hLbldq4EedTUo85TokDwsjd097
-        eumzAST+Z4+UG52TKauMHWzMo0H35OMm4xbVDvgqcrOVjefcz2rRMBjwCdJrI++T6ahmLrDlQCSa
-        jk0wJV2aw0fNBBoes8CeuZC68HU7ONh1mFHzTUBS0OTHB/aNGHIaFhsf8KpRaDijMhvSzfTS6bTf
-        UP9tmpyvbx8DEAk9yHyXp55tam7Au1fvEEcTS6b9TjjD+GI9qNN2fsSuz8nRN+g8I7463uvpeLoV
-        QHaVC93o5a1na/9YQsaeDJsWl/s3Ci8VvHhWSSZ7VOx+/9UEeFppBY3Dk5S0Htc/aviUR2r2b5pN
-        SNGOoLt0dxyX78yenaCNgQX98JffkunHCzznoVNUJKyeza7UtMcw+9heNUPPr16fw2ZOXaIv8U8u
-        XWdAL64INcSK9UzfyS0c7/bzTz0m5uX+0mZ0A6i/7WlCHtZ2AtJpPiGBbvys3xWjBtVDhLG9md58
-        mnMTatXKlMinMaSeFcx2QP/UZEJ0eQ84U6EP/MNbpOhQl9HUZ08Ed95Rx57thf0QllgGxzPzicJm
-        MRt2W4PBi+BkSFlXfs1wPLVQGD4rHK81Kxni9KzBxf8TeZRwvehXBnPxsaLh5jr19GzjM7zE+pWa
-        s7fKyDKfEPf7J5Kf9SMa4RnKv+uJKNxgNF9WTw0aF6lH7AoUm0SvbILqhA1sb41TxPo++8DVeYqp
-        4zTrZEx4XMB9dB2p+xRJ1JK6IvClbxmOj+tPTe7fgMH+oZTUlFKSMHfyHXhbnwUCLDwks7ntWnBp
-        3D01u0sMRty+LfA5vS3EdmCsyR2FueavSLT4ZbNfb4tTqSz+n/BlPJNuxiFw4sMZL7/nnLvmDm6q
-        S07DMv/W38rtFK12Njn1l/mbtS8ToXSW9xQNUsM5vk1H+BhFB7sBiyLexMoAbXdDKLKf735Ui3GC
-        J29+UzvcbaPueewKIPrkRn56Vlr0DpiKs0TjXjWANM3sA4a1DhADj7qecy61MLB6beEjx2jC6XsH
-        axBccLw9xxlXilOrlSfpir7nW15Pd82JoVc+r+Tb623PfCBDmNnpDf/qN4uMxNcXHoff+e2dTZf9
-        xYGkjkO8q59twsykNAA9bjscdlBLPsDXHRCHuo23cR6ChfeIsI0uHZHXbmATBw8f2GT7msz7Uwc4
-        GQvyq7803m70jJUED+DImY5aa48ANU4HAsWGYmztwNh3jaIVULwRirp0c6jZcZMaEM7Vkdr6KYwm
-        KS4d6MS7M3Zq1YikHRMduMU2R9LCP+bgezD0JV9j98SHmptqcoZj4d5pqKEvGO8v+wxRHu9x5Dxo
-        NBiX+w0+bTUk6vMcR/PlcZbhwg+QdB6JPUssS+Fl7bbYcZpLMtrmoMDZuO7JkHl9xHkj+OCcqwm1
-        nrmYzHcjJNA/NCK2PzaNhnX+HWBlWAO1PvrU89zjMvSe7Yl6+LNP6A0PTIuhs6FBcAxsktyjFsYb
-        I/yTTxZe5MPBFXIkL36f5aZ+g92m93GoFGM91NV808V56qnn+mYvi74TgqXeoVlKUdLvLNJqi58l
-        8iS3PXN7eAa17dtE8YqqnuSpJHByErrEv2RPz/ByAAtPoY6srsCv/ursVOlIyrZJwg8r8wzXiX6g
-        W3El9mNIvNcfPxmXqQOY4R0E+IT6jUYsYcn4Os4yTD7DhXo02tUT9fgLjJ2j08BNmE3zGoSgsN4y
-        uRwCO2KfQkDAzfPPH741yNOHQBhcc2qbu6pnH8/6QBREBnX7jVfzj68fwWPPOmx4wttmb00qQdpu
-        JqTuToY9ty+Yq7/nQeLZsmdvXMd/9FXMAxJ9tvGUwkW/YXup/7wZmtcfvW+HuzEaoaYX8J63Mo21
-        b5gN22E8gISSGGlVVtgT2PoyPF05pBs/DyN5WH8GbeGhhL3iPOPkVPvQc+46DsNrFhHkv0Tt6UCX
-        Rmi3BRreteGPP5D++cx7OpmjD043UfnxkHrRWwyoWXDF/mxe7FkVJhGqBH2p2zZWxq731xmA6+VM
-        +rES7GHrD1+I+GFLury58ElVWAqtzlWxu3aDaDbHIv/5LTK/1l7Np82kQaXfJKgZHqgWHyzbgS8V
-        bzhuUpz9qa+Xjf7ClkrbhCpVdwQLf0K7lxnxacRDBaydQynKDqCmKHyU8NQqR3zZ+TIf7lX6BaA6
-        PWngizX/6QVt8bf0x48Yf6wJpORAcbjkJ35XzBKe7xAT5nR3ezqZxxwyUnt0+xGSaPIHp/zxj5+f
-        W/SF0sIlnvCSz+uprQMGVRWH9Ocvh9/vFz9L/RvdJ5zMVaE9PFpR3xpRMqVNU/z0wR9/wGpUI31o
-        jC3eBhnn/WjmDCRN59KIvcxkXYC1CxZeiLGz/gDS4Qj+0Z8/f0p6L7N+/gE7tDvUa98N0B9+Dhbe
-        xkDOd1A89ALiJX9ytlO0En7JXOBtlJd2N+4vMTCJlZB5FYwRi+NPDMxcv+CtYkQ1P5xFCHVQ69vx
-        NL4S+tNTthyJ1P2Kaf/jyfCn3xY9m3D9rBtwupwMokisz+YqfRi/90t/8SR90jWDvjyYSDeyLvlT
-        r4r4A6n7kppIjv28gIdr/cLewj/ENXy02lKfsJvWYj9oOXCgncTuwuPzhFmgQMD7tg8iLXxv8dcu
-        LFvlhDPhyDkFlUrAQWoMujxvRBf++PMf1IIPlEzXraqp37u8oebGvmbz5x6VkGltTa2Fh/PTaj+o
-        96Yxqa0dE5srQvmFQ73aYzRLu2ziU3oGD0V+IVYMcbYm87eAe3Dn2L4emp49rC0DxZnYePN+2Hye
-        9rSFQ2Nt0Wu3fgO2jssDlGsQ/3hD9vuuW5J/onvu9/3LVQIEriJ+E1hdlGS6zloJM604YVc6R3zp
-        5xxBEjRf6qfoASac0gP48U5r25cJ78T14cdDFz+2ylj/xppWfpQvDqbUqb/xcHfAwm+wC9trNDIW
-        Gb/x0+hUAnvhJ62+PlmI+nS6J8y13wJw3w9/WU+fbOFv3x+PoeEDbuzRDE4iXHg7kh7CuydAYS9I
-        k8NuWQ9zQs/1IdW51AVIGKQNWCdeSKAl+A8kXt60p99ma4Fh0DOMn+o5m41NedDDmLs0ODRVL10z
-        9QPryNtj91TpPSu/t1Bb+AdS3uYTfBR/IKC57xX6p58npS6DH/s1Yke45dHkH1MBat9zTO3t/mVT
-        cVzl/+YxLHSSWXT3OVQ27hHjR0CyGQnKBD3ptSKc8DNguRv4v/pD74+itnkpuiGg2jkik4s6zrw8
-        dOESr0Ruj0kyrqsuhPtTLv7pB5Kmml+6nQVHUqZGmLBCc25QTeKIFqXoJLMUYgu8ttHwh5+w0+n2
-        hegYlNRRe6MWB1C46o9HO216jYYHun1hqgYmTRGhoGt9PYSIBivy61dM5uM8wG2/wRQVL7MWnZrJ
-        8Ncf88D9aX8vXWeBxQ9iV7lUYHqwZKeFD/lC2uFsZrKQrjSwnXyZWqfhyakilB/dnUuMLVM9RcVT
-        y5m29IOwZYVO1O3rQIQXZJ0W3uJxVrDIhSImGNFHQBJ+7QcHaqdD+6ffwQ+r4PyLH2z4wszJUyjL
-        f/OM9vvtyVLf/qyXepl/vvR7VPw9+0t96expBrIIowEckHCsOKD4PLSwgKNFJlq9wbQ26pu+5Ed6
-        iEJSTyLEMSxnRSL6yqyW/m54hMYA9ji0FAHMVXox4HMwTPrjYwyktIK2F36xueRHkp5qC/ye/7D7
-        Cv34y29SwR+E9iHlJPBjFz6E+Y6Reh5qIh33CAgzacn+1So90beBBR8uC/CmFA7ZzJB1g0aqvPHx
-        4Udg0UM7ffk/BLfnIWPyK5PVxU9RLAxjPYcsOf74GrYlcQRsp7Dql//+9GP+9GcOq49LvaxjYBbW
-        uwN8btQH3ZzzlT2N+FXBCGt3vOgBzk9gA2FTXkIceh23J3XXWnCqLiWS3PidMHP9+cIfD9BPo5OJ
-        q9OtBE14DMlkEqeX8aQiKNy+XyS8k3vU78O3BnfGxadGVjqAaP6ggIU/oq44SfaMzsMNPgfLpIaL
-        AsD9QGDg11/96ddfvw/+/dsV8J//+Ouv//PbYdB+7kWzbAwYi3n8539tFfjn7X77pyjK/6Tyn50I
-        ZLiVxd//+vcmhL+7/tN24/8dP6/iPfz9r7+UP7sN/h4/4635b4f/sdzrP//x/wAAAP//AwC2t0TP
-        4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0b9867da38f9cc-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 22:52:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '20'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 25535161a3c6c4c4d2d95830fc85649a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[18031, 1495, 220, 16]], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '99'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SxOyOrfm/PsVu/aU/kpFJIs9AwG5miB4o6urSwQREJFLAuTU+e9d+p463T1x
-        ALGiycpzW/mPf/31199NUmb34e9//vr7VfTD3//j+yy9Dbe///nrf/7rr7/++us/fp//38isTrI0
-        Ld75b/jvZfFOs+nvf/5a/veT/zvon7/+NuPiQ5nS1Anz5acM4uJ1ZNpa6bouyZMjLJdQMZs0H071
-        gcrA3keVHUtt4GxxmpbKpd8Q5urcTppOaEXZRcct8U/hJ+LRfchQhzZv4iqmnoz4sN3CaV17ePPq
-        P15npqcc9Pf9yLCTWmi8r4mBLoLgMxWNqKR6tKTwcM83rLRb8OZ4jLcgX4URN/ux8KgSvxtUsFJl
-        ji1XiBfJs1dO/JwwcyO5+oS8tQGQGluyS6ibDOB1N3AIDfAQNarXy5f4iE5iTpgpd5bOk8GtoPH0
-        HsOptJOxux9cqNitYI6nd2WR7zcusGJ7JGpq5px/KtyjfIMRUzeG7bHJkVto/O1AVxpqk1m0BRFN
-        SbH/vdeHi6MBXGZXI/jlC5wv2PWIOOlvTDvOQTJpbiSjOiUWBn67JNy/Xn3wyyUi2HaSjkVXVwX5
-        yBFTYytLhsxY9LBYXp/EROPEh9rYuqjFqkWiNiiSWeR2C/JN7Yl/Pr8iflyNAbCk7Yg1r4/JpO0M
-        G8xTsGGOfa35tHx1Mypq4cX2/uB59LA73SC1IoMR65B3w1IPd0qRVwqx/fuKT055zWVf2nV487pf
-        +fRQ7Roqeq6JqepFN54Wnx088MckesuJ3t+PqyvE75tLZ3o8JPMhMlr4iF2GZWU36/w45bmSc/HI
-        dLy0+GQ3VoMEB9XM552YTNkhCiFU45KiTaXpq9qOJbg894jo7eGgz6zoCpgyqhHttEbelK2XPRQv
-        pWLO+/XoRr69jhBErUy2w1R11K1iEbQNbYlNLi3nPpF6KNr9kaloj/mYvhoK8Ts1iZvG124+NMxA
-        S6FGeNwYjc6mdyOB3jIdo4Sq5ci3wQzWLgqZKgPhc56QEbFzLBNVjktv1q39HQQtCEhc58vvfCOF
-        o9V/8GrLRG/EdZWBtspkorfhAk3Ds/VBavSQOc6ClJOmNT3o7+xIdPKu0LiT9mcYqLRlD+uglnxx
-        WI0gLsUdMbfUSqbMWFMQUfDBrWaXXcv2xxEuihQwa65PUecf7zbo/RIRuz28k2lJ9XAhn0WJqcl0
-        jJpTezuDoF08st9Pli6K2b4CRweN2K3aJDRcbRuI5lRiu+tcd62elwKasl5j3/pG7RvWNdSZb7Mt
-        fY1Rfw9e7YabqoXFSyZ7rHhMdzADATOrZ/eo74bABr2bF7jE4Qf1lXWtwdkqKv2eRj7nPZ5huoQp
-        3by8mI+ysLuDYFaIHA2ZdsxE3oyGz+fAtFVYc25eZwOma3JkhlUZ3YgRwihXypoZxUg5m86rCriG
-        MDG37Oy1b+loo/ipFsQx4lXZiuvgKhedfyJeLIlRf0rFUZaKpiPGM4m42BQTVRabycYoyYJo5NOB
-        /v4PcR8z6bgvhi749InpSp/LaKoX8xHBZT4Tc/Pu9LES4wJC9dwQuzvPel9ZCwEtlrcn80f/xbn0
-        DnuwrBMmuNq9kikw1ZtS9ZgSo3rb+ojjZwHdOtdYGNmWN873cwPB4aUwL/G3nZhnkg2N2ZlULoYK
-        fUBUJZCjzsALYSGgQWu2LgzDAqhQzxKnsRbsAMKsJbozyeWc7ycXILUV4i7GRufF9ixDcmcYr4Ps
-        HU1ZPM8/fGV7Zn6i+Q2LCqzj7sFIwaSOfZS4gGY3AXMVKU9md3J24EK5ZNvDAXs0h3knT+mg4sXz
-        mnv9/Vk1Pzwi1iy+SiqkwRZEFH6IK9wT1M+fvQyOc26Yux2R1/zqoz6PFcPv6ovfnlEp/ttsmRXd
-        PL3vXv4ZhdbKomsehwmT4HMHTRFuzDEQ72YRoSUSsHOmrMjijn+UAW+++8H2YWR6IjvlNTQ7puFl
-        zVSPhviDoajhxbCzeKFRXtUAoowHLO1x5VF309TQaOcb28X6q+PJZ1dAEloiXqFHyHlSdTtUPJsN
-        nkRJRZ+l9RTBneaantTjs5ycMijAIujD9M+iTJh0kEK4CODjObotEY2VRJCDu3tjhhWZnRhebCo7
-        6rzHyzL0EV+wdY9++OBPgcbnHPtLcDe+S2JPtEs+mmK1CaP8Tqx+LyQ0dz5XFHf9iuz7riypgoYW
-        tNHBxLs5p6TvPmxEl0+bM3OzufJZSbsePbaSSHR3JZaTrYU5DP3KJMbr9vL4wjmHSBNzkcXVxtep
-        aIsimPfpitf0dI64eSyO8JkuM3OzRdjNwlHK5STOHsRVmlGflVrH8P0+Mcpli9o8vNfyZ/Uu6Glj
-        7vUex88c9I4azL8kozeHF7VHx70VEPyObH391SOQC++CrjYXmXfSPi9Q8hAt4s9rt6wF2wkgCWBB
-        jAKPnPvHowvxKwjJtbHVkhejlAHs9xIhz2uuz65wodDo95Bg761EQ/2UrsCSpvutVzc4t0kF8+hu
-        KRLte0lF1Li/98xUX3k5yo9RBH+tMlz0fhxN2UnsYbrdDySklfadb8zgNOHyWz+G/hnmjw9SZ3vM
-        /uy9iPu6k/3wll0/+y5hIz7vIK4OB7oOG+AzO1sCTJHVEFzPV9RF4qWBKr8/sBifomjOHcVA2ux7
-        zLxXbzSzQ5WDX6xlvDAdu0uHNMxA3NgTO4ufUzmzMwGkNy+PuYqc8p7vmkJ2hWpippycEfc/rQSO
-        fXl/+dLlfKEKM2LpOqPyFqceP8qqCrgPJOKPiwKNcpSGsHKDgKS+N3j88yhDkLPgTgda3fQ5ViIB
-        vvqRuIVX82bHXiKS6FXGY2xl0TQcZUCwJxJVosvTew16Hij44y2wEm5rfVhelwVoCtyY8+odfT7k
-        VqX85ntYIYt6y5Yo4qaj0GpHnG64dEmLHt7jwH71Ml26qIVsvX8y7Xsee2s9NXApA4lop1OqcylD
-        GIYqaJlh6auE6hdpRkt46My7lkn0Pd85uOtdSHaryuXf+rlDa2Qdc9y573pLrSSAm+BSCWuat/6U
-        fAuhvdHxeNcq3ortx4bUfXLm3WCORouFLqTODegkmjqfbHzK4LHPMUZXLY34cbiOkDyWFvEvt2fU
-        p8dnj4qWHOnzIhgRT+5e/dOfzBNbuexlPC3Rg7S7P/px/vIVGtomJLYvRGh2XX6EBVogpjdtk/Ai
-        cjGqgvLG7G6ToSlQxxbqu+cxvbHdZLIVl8KXf+hnV9yT8b6oa3C0jUGMZx+iL56KKCRhR6xg30R8
-        Go8GxHXsMFdXu4QVl1gAwZ4ZXj77GbWh0rpwNKuJbJmdelOw5zUAOY3Ev7gHfdaHCIOZtE/K2zmP
-        ZjHdSCh+XfZUXjw+Ho21coYpkFdU1lqtY8U2k+WhOr2Y4wg5n4Y4u8n652Ox3fmWebzFQQWPrSxi
-        MTaW0TTQl/tbH5qjMSmnpR4aKN/4CE9rF5fjPRgaOUkpwYuyWHX9V8+idN/0xLDEORq0amfAdPaf
-        uIvX725ava4GXMpQYubm7ekzy9gd4vqI2fc8cB4NfQb6p/bp0vSGkiqL1Q0sO3EpHKebzhedXYPg
-        CSXTRrLpxmpOM5SNqw2d2XUfTTVqayQf7gfmCkrnzfn52sIHKS5RkZ973/WRwXqIlHm32zGZw1AC
-        tMK5yqzzKY/4Fw9BTrwSr0efdLxorrAR5x4T936CbsS24KPlYpiJTTYNnxkvCtTsjQ9JVscAfSCX
-        baS3rU1s0jh8GFqnRzGVPsyTJsNbT4p+Br6VCEZJ+uxoeLH7P/rKseprMv3wrd3VJd7U2NLHzrvZ
-        qGAv9PVbTVL9+Lwxcky0dbLv5t/5CPcuZ+5itD2qy5kN3So1CBGE0euKle0jTR5rYoVm4M1CrAZQ
-        ZxeBCk76RqMFzg2ksn8zxzJuyTQsrnfw11tGrOnZltyY1wDhdWkz/3LTIl5MlyX68gtumhuN6rzf
-        zUhvioC+pNUdfWBY7aAo5wlPK81Cs6h6LdTH4Y37+Yyi/ucXpvh2wtxWKPrjh8w7v9I5SLcJX3Rq
-        pfz8sB95C8SK3LTBfzKdblmLvO6zM0awrmfCrKhrvTnWAkMxb9WLOK9hjYbM5uMPr4n79UujZY89
-        nKYoY9/zo3dmqi3htHyEXz6Cbqqf0g26Tb9kN2UX6lPNPQNJHzViu1tMkqkufEOuj23P9HaZ8unB
-        4xDkxCm//m1bjph5gLhznIntK6beV9cyRNVV27D9F48nW9n2imWSMxWTtIumi2nK6Ov3qKwhtRsr
-        Lz9Dks0eRdeiL/lU9iIMdZoyN0ViR396MTV3B/xcJ/uS366kQLg1TKZx4ZbMYvt0Qb7bFdnj18w/
-        l+VuifTX8Y7X3DK6b/3RP/ip3pdPNNS16oIZEWCm1t08LpmOij6Kvvvhi859/WTDgsc5IxB10aRt
-        NFvh6jpkHhrenEvn9xXgivZYweIBzYecVJBLhsFUGT31mdUoAItsPsw/Ld/JzBjN5K9/pfzDuN7f
-        bWwjcVHEVIzrORpq/9lA8WRLvFhMe33EgGXQm7f31VerpNV3mxmmSB2Iq7y1RHybDxfVp76hMJ/8
-        jhfbTNqw0ghYXI8vb7qcNhiEvfogptbJ+lCncNw0ZuV++StH7Q9PvviDV9u9pLPPUt6Cu/b2+LWl
-        74j+6hUX7E5X8s3Wx1k2JJQkXciscCdwKp5uN8iVZ822Ufvy5jgU7jA8DZGosl15Q5ZlGPT6dqUK
-        1fbJKts/MEot32HYMxdRYxWtBJemrohhXJ6o5/mth6PFK6p88kyfLmqbweUzJGy3vofdeF9bOyQY
-        mYFlRVZ4g+NPAUNurhiuA5lPMG1scMjkUSYoWiTqVbNF4vg5sH1YfX9P3apScFOLn5/Ue9ktDBjy
-        rUynMZc6vnDcClhoERxszic0DcdZAMHsRIwkUutD0D2XcHkXDdutIo83cp/vkHlJe6YTs+bcX5hn
-        eSG1B+aJ1sC56We5nM+rCEs4zL3RAu0KwX1/+sNvLTtbAHVYLJmaXnA3u82zBr3EFV3W2dObanVn
-        IMfCI7M/49Wb2QlCJD0rRrYDqcvZXV1FENfbDSOCEHh8VC4qsDo0CDG7uuMmtZeoTl2fOdWO6WPq
-        uz7EpXv74mPjzQzSHvyXwIlRPAjinz7MlWFQgDQf5iTc/GwM9OUbslu94nJaXvMlXMoLx3BRsE71
-        j35HjRafiJpeaMeKywGAb2VCBe+Yo/qw3TfQLRObDl89N7vKeFa6zcSYtipNtMQGvcvizB3K1Mst
-        6Xe3yw6q++FDVNmZOTNF2P74A8fe61NOy7tU/fI45hbeDo3dVbv+yau0i2AkortbBOsvfuKFIX3K
-        H38r4lidibo5WfqErvUZjo74pCv0mBErdqEAHSjlHz081CrewXLBZppGu8LrO+/mAt/ZAtE/fh19
-        /awE7fbMCbFKnFB9NfdKMZz3+Hnxz96k7S5LOI32m2lHvtAnyGcX8rUjkN95o2ES3OHhBBlLadkl
-        s1hoLcix1jFTPxy9wTl/QlnqLwpd05MY9fj0yoBVrs+sAK91JmFLQl8/h8XlNPAJdE+GKoufRG+f
-        WjIEN6GAfCX4THcIdHxUHqqsTTbB0rd+ukU9ir88gQqO3yDu66krL3iS0wAxn8/NW8sgicsbvkTK
-        mvP2PBqyHFxPX30Rd3zC26uymPyBmAhHnEvqJkSP/duh4s3Syok46xyS2+v81Sv7jpuv1Rb0blzQ
-        7nZbRuyjKVuEh5gx/BqwPtWUnwF/LIP5p+qiDwM93JHU7XdY8IygG090NUMSSAaxmyT1xnTuvvnk
-        tmc7cWcj/vMvjEkJOyzHhlMlWN7l1szfxPb7nT7+8peYwYuYGU0jtuCNIbc2TfDGfQ5lvzusK0ju
-        TcT8izvp7CjbW/TNa+gru7NuGixJRa0veMyKHN+bLoaMQc7CO9vFYlEO2anbgrMj7JsvbX75ZgGO
-        urb/jBf1ive//ITOdJV3PLmgJZKeNSPGNx/48cWmqihh/sRxt4F7e0PDsNHwdNrmHdXzEqDOsM3M
-        dPfi07CoXCQY+YJsWZvocy61ZyRsE4uZmbDvZn0qBDiBMNPkehjKnguqoCzE1xHTmvQ6Ty6NDR1C
-        b2Ju0yaZwya5gv7c9RR996e39ncXnTazgKXufdDFePOQZZGPLtstn0rHzIAGv/XBEj4q5Wug8R2G
-        5nWiDCo34v6RiWgKpBXTjqT85gdCBc6+upLIdg98VuJIAKnRQrbvHbOctJBfUdG6MXO+53tMXzmF
-        bvVcEH9aKsmIMwOgqtGWKrTsojHVix5S5wq4XeRrNNTrcInYrWZEO72GhE0SqiHIgpAY+U7iQx1f
-        ZXD8/M5cPYy98bffjmGumTatonL+5rmoPrI32++DNR9q/9Oi4LQaMJy2sTcNiyBTjsZr/OVv3rCc
-        614W1ANhxlOZ+DRYowoPy62/+PLWabzxfWD3qaCyZusd+1S7HjV7p6J5esGlqK9kCvl6azOiXM/e
-        mCLPRt/1JbrXRH/8FwSnecbfPAK9Lk7aoHZXlWy30pNuWraWjz4LVyDemooljc9y/sMH+pKijM86
-        iUP0WZANwy8v8L79hCXIZe3gEbGeM+mBpT9+qoWt+NW/doDM+FXhMW325RK34Etc22B6NNMkGqtZ
-        G8FKcp1Zh6JMVjUqakjVzZ14sbmJRvlyOKJU14/E9oclGl5ICKDRkhMum26tD/YZBFS9QWD2fhrR
-        aDn+7ZcvEuwZY0e/+TZydEFjpj7rSf37P/izdZh1KEN9WOrDiHA1xkxvkJWMeN3doXjJH+bPxlBO
-        mtJXKE5RQyd+h4jqpBdkM10fib1/6N6PL5D8OF8xzMa+W5tUFSG4SC3NbJA6tnC29Z985scPc+xm
-        AnzzXCwvcOuNaRCDbEbGjtyE3vcmzU1kYHHB2TZ4LPjnh1/C3rzRBWz9aKyCxx1+ea13PezLOW5M
-        H5IH2jIi3GdvGmydwkli2z/1w4tKw8CYnBAC2z6Z6rar5aHEFIvrvuBULLQGzPN5Rb55hcd/+/fr
-        T7h3HSMq6FOh1OGLMVc9r6I+FfkVllxqWOath26Ol5ABy4UrM+9bB/W4IxLgonli3oYPzvwjWyLz
-        iJWff+d9mmq+chr3BV5889hpeYUCkmy1I/Zn30UDyNVRyvmGEFXiH692ib5TOOEn5t3iVyfqpAf4
-        5d3qvSzQF5+O6Mv3xJS0yXtdiqUL4WX2f3lqOSyvjYi++gA3jYK8lqmxiE5SazHtOD3LIXi/RoBj
-        l/7R780JvVTQ6zQiqhRuEHUV6Qj5xlXpOjwzj+qkAri83yXTRLPkc6M2qtytuzUVvnzDpTO7gT81
-        NsPuXHDmz+cd+GPlU+rpT8QWEAVKt7o5dJQKV+dRrmD07Rcx4wW6zj8l2qJsc4kpXIaUT867Cf/k
-        Yf7Xz021/2lkRx333/oOuvaX/6ZbiNnRQGnSjTjbQeOrA62+/DjreRDAdDQ+jCywGolhpbcQXkYf
-        D8Ne69hxNYagjbsIr9Jr1PHjSgoguNs3jMRW7vj0cG4/vfjD53IY7McV4ue2IPs9cTzacKlHSaii
-        7/55SS/vbkeIO7oiKsJpyRdvo4DHzmiJxdEYcfOlqBBcFi/m1GTFe5mYBRQdPpFfPv315xRVzzwh
-        JF+PnBWXVwOCI3aUN6399cvB/ecfifnNU2elpc2PH/H0zccG+BxakLPThRGl2SWzfhlnpXGkFUv3
-        01sfZ+/RIDlIAyp/83++cLIAQt+byZ5d1t4vfwdrP03MMHZbPmTFIADfLlyyjZwVGpaWUmxaHzxy
-        4ShIeOL51fq0KjFthXvCp0tpiZBi+u2fnMqIRVsewLcfTB+WNib9LPsydKN3xcu8OaM5D+8Vqh/H
-        BTl885XhmwcoR3udY3m7p8msxKxFzd6rqODyqZxscwXQLbY5Xk/zp5sCpxTh+/6Pv2kq+Rmib/+T
-        bXt/k8xMMoVfv5D96bf+8tpv/kqMcnsv52+/GnD+qsg26jgfU6S7v7wQr7n8LLnvNQJ895fOga8n
-        4q+efDgmTP/4u2QthZ4AD02U8Rw8HnwIVKkF6yC8mauedt3MHHOLqt6n/6Vflq2FIYi1J9O//WD+
-        6WuMgsTI2DagWjJibm/h79+tgP/8119//a/fDYO6SbPX92LAkE3Dv//7qsC/b+nt38ul+G8m/rmJ
-        QPtbnv39z39dQvj70zX1Z/jfQ1Nl7/7vf/6S/tw2+Htohtvr/3n8r+9c//mv/wMAAP//AwCkxTP2
-        4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0bc85bcee4253c-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 23:25:16 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '1067'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 482e97acc620bbf5e2f7d3dd44145666
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/cassettes/test_memory_management/test_save_memory_trimmed_from_context_window.yaml b/tests/integration/cassettes/test_memory_management/test_save_memory_trimmed_from_context_window.yaml
deleted file mode 100644
index 970b806f..00000000
--- a/tests/integration/cassettes/test_memory_management/test_save_memory_trimmed_from_context_window.yaml
+++ /dev/null
@@ -1,843 +0,0 @@
-interactions:
-- request:
-    body: '{"input": ["Assistant Reply: {     \"thoughts\": {         \"text\":   Result:
-      None  Human Feedback: Command Result: Important Information. "], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '207'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaW8+6Srfl799PsbJu7TciIjVZd5xEjlUIHrDT6QAqCiJyqAJqZ3/3jv53dnff
-        eIEkj0/VrDnGb8z6j3/99dffTVbe8uHvf/76+/Xsh7//x/fZNR3Sv//563/+66+//vrrP36f/9+b
-        tzq7Xa/Pd/F7/ffl8329TX//85fw30/+70v//PX3XQk9tt8IacmL0+aAZtXYYkmRk3i0zh8b5pFi
-        rLzv0M2o1HUIhpPLtvVdK+e2udog7hYz05U79abP/jiDvFzb9HMyBc7pcmfBlXkJ0Vv87niwkiU4
-        sljB4kI/loM4RSoURpsz1eO6N+lmkEMxVCa7P9Ys7oPZj5AyWQMhDrfQQB6Ers7xVmJeLXv8Izjl
-        E26iPzMzyWyP98HTVF5ayfH4Kp98xAsYAeWwIWatnrJ5EK8YqgWVCZG1jo/vYRChR2nAgtXpbUx7
-        bwyVLb+PZJsJy4zp86VBhbH3yfaYXbJpV8Qq7Be7kezyzs9mGaQczmTDSGAeC29azBYFv241gsW8
-        j7m4fkYwlVHFvLVUGO0qnhMIzdbCRbQ5Zf0wfQC87Z7RJc+vXT/OU6Gc7oqFY/DWZUM9TwVnf13h
-        9TVJ47Gzb7dNhIWQaRtB7vpYtBOIM6nFoF1xN6V+BYi8n0eiHac3mjr5ESmhZlH83jQu7ze8xqhC
-        3pO4Ual6DKQ+gfV+ZeJNuhb5TMkiRNdOCZnxzE5ojjenBgYtw8x5OrHXH/RxAXFWplh5+G45Tout
-        DmtPNIidLFjZbxG2ACo9xhJ6196YNCsdxN3ryez+2Br8GIcmNEWUMHN3XnZzliQiKMa7x+Mabw2q
-        nHwTmLdoWEDNlk8qoQmUu3NDRzWLvPnOnRQyCgHx8qPCRznYhZKUSFdiBo7H5937LYEh7q7EFgXT
-        m7faKYFMck50SXWtm6ISQpBjsyFX97nwhnIvNbB5zoxCkEt8ekmujVbCJf1Tn/N9OUkomSKd7DhE
-        3TiMJsjyqVWJk5fE43Oo+cru3chk+47Kcl7blxzMMDkx6+IXfDxgM4d4teVE448mG2+F3YC07Y9k
-        L6t6KbJ7M26uy6Ihunpp0LRUD5HC9ssPcb19iWb/eirQK2lKLN7mCs3f9UG4EHzmvjSz46K4jSBR
-        wWFXE2TjI702Jlpp0YdsTweW9fXxISpSb77ILSjKbl5bkIOi2SZ9HR9DPNloryo+7CeiOfWqm9hT
-        T5fFSajYSdPNbLx91q68iS53Ym4Vo5wUT8GgHE4+2e5EF/F3ieFXfwxb+jL+7Qe6zscHIw/3kQ1a
-        76RwiCqBLqJg330eGdTwnE4Ncbj8yfhhq1eg6lbCzFoV4748pBGIWeGySHnpxqxrnYDSlvXMX+/X
-        JTdHhuFRPijTrkZlcMEsIphk3SQnxIxsbj+yC3f/reOxdgHRxVOo5cSYNPZnv7uNGcLBW8dMy9e5
-        N3vSB2B/e56Zvz57HQOpSsGqng7D7Zkan6t/fsLFFVOmfXQcN3n3qSB/7Xd4JV9Pxpp/nlg2NvGL
-        Hr/rzbREakGzsz2xz4mXTdXVdFHa3XxmJxIqJ8uS1d//R9Q2HPm8302t4vs0Ia4nXflILrMIV25p
-        9IMXRTcDk5+yD/FE9CllnO2J9YTrEUKSCS8az7c6keF4yrdUejkaEo+HvAdotZjpneZ006JGGLgh
-        nyjSu8n7ra9c53ZF8OWy4TQrqxMsD/Ibr/Sw5vNLFUz0eFgW0/TikfXO843hDZnF9LW141O38UN0
-        /5xLojXHIm6bVWyhzcZeUnGhr0oWZWsVjv11y/RLGGd8UUQLNG5FGUtdzhG7Hh8jpNNOYf5BexvM
-        LBf9r17oWE5iyTxRPUCqOQcq+Zt9NkjnsoaG70JiNDtm0FUsJyATZ8lU8ci8T3V72Irz0gKmR6bn
-        cZfjA6hUkJielK+sv8ahiyS9CEh+0N7eVMeqD/tHX7DcOlUdl+6hAOMMHY4bQfG49nrY6Lt/zJEv
-        RjdLjzmHcFhhRoRsx+dV0UpIafucuf7a9sa8e1SKSw5buhzJEk2fGw4Ryt8fhi+vB5/PSoGVJfYs
-        gi39Hs9jK0RwiMAk3lNbIRoMmg6Nzs90dcJZPMessZFjRz1z70SKB+IWVKFZw4iDpb6bhW0v/eqJ
-        WEXieKJFShmtvZwTo9KQ90n9agEf11fxymQPj3/rE+Y4CIiWu9jg76oE5RwLCYkbeW8MO1oUgIoi
-        Yno0XYzxLvkNIor8YtqjvXnczy8SqOYmJLt6cYtnXSsFVO0hJffTKzb6d6EcYP7AQJKXyNAc9qiW
-        o6XrMH0cNETvy0lW1KwdiX6uMm80S9cE+gpstm9In7HjHlmoGxYlM0XP7phZihRexzwjfj9fu0nd
-        GylsjXKHEd2cDL56r0fYHQSdBfml6egt8dK1OhsaUWsX+DQw+4Q+19Qm20Z681G+LEcYL4ZOPCyW
-        WfMuVgd4yM2NELcQ+Bi84hk2UXYnQVZEcXPWuyccfFxi/j74nAYt0cFf3jdEy5XR+9hWVSnX/lDQ
-        8eZF3exfb09UvZcpPurKAY3zi9eQdiaw7WZsjAElyEWiFHWMUP3RDd0WBKjsRCMJe+4QOxhDtVnc
-        /CuJFlFofKrm3MBT/dyJ/YESTRv2roGvtR0VNPfR/c4vcqqPwsxyMI2RVb0O7OhMxHscdrwXgtYG
-        KXEUYhXR0eAD5xUapvMaC9JNRr1qQQHn+hOS3ddPTL/+Vu6oRDfx9CxnJwpvymPnXolDD6+YYqs1
-        Qbs/Nbbb4iufPtE8y/aj9DGKP694jEU7Re05Sonz1j9GR66fG+TocyYB5FlW3Qq1hVLSJ+LHes6n
-        73psvv2L3aqpNXrFME5wCVcZXeqZWDK6Supff6BFUSWch40AcKlm4+c3u24SCxs2SFkztzz2MYtF
-        RYf5NL4YEY4xYpf12lbOBDHiPMnbG8JK69E5bEP261fUuZYLxfG2FTPXXVKOWygtxdt4Kl1994t2
-        4rP5+QWm3ry5nEmc1vCpX3sWOKgy5tSmB4Ty14cF9YzLyYq2TzSr6ZFoprov5zVqZAT+5sn8hB4N
-        plgbADXbF3SeihLxxlUK2Y/YheyEVYNGYZlX0O0Cg93UxojXsN4lkOJTxrbN9oU+/f0oopWQpVhW
-        toPRf1xbgvb0kJnaORYa8tV4g5W5fTDbX25jQVjmNYgVi+n01Td6S4wUZK7tWWx2Yta35UMC7Fod
-        hfNqgUYnGSmUiWVTJeVmRpdwrJG7jCjD1dR6f/z+7dmlTD9XyJvWfmJBVy4r5ji+0HH/cpegvG1t
-        Kn79AttvQ105Facz0e2EG93HjwrYqSjF3SoZMz7nGyp7eXonznITd7PixLViUxrj6WpUHrXyQwKr
-        KYgYeShl3F/33JW/vECnr/7+9gvEvYfw4ls/LBCuEnLssCdGExjGdPaOKZpCKyeutLwYbMs/GO5k
-        cvFkyEo23iWzhQoVM1ZWp50xW/khRetjmtMuPPFyymcxR6HZWMyhaBnTtb2/wcJstvTIvQ0a64gJ
-        sI78AyPLweCrRer2P/9F58vpnU3v/oOBtPTKXE9S+Pxc9jny7PWO8jeWeOuufYAyfYzMaZ6bbGRV
-        pSLJXK6ofHu2cS82hb0Z2fhkd1nrEL/aUwThbkd/fsUYV2nayqupen77idYNxG0oJIIls2C5enhD
-        t7uIqH56L+afVzc+mEMIimEVJsmrzS6eh0/Vg0Q3129/WHlcjiJJxuVewMq7M7u16lg2vGE8kUB2
-        HGO6C1iFHukK2ebqu+sd3/YhXokx0Q/na8ytyzzLS1yccBd/XlmfRmoF3DousBy0rdHrFjPRx8Uq
-        +fHaMAzd6Y9+kbR7G2yslfaP3uKiO3lN+zRlEG99RIVaFTMmm0ECWE4qdupuijHkSwrwWqYGTSsU
-        dnytK4L89StYLvS0m8iD9OiwOR2I+6JzOQme+lQe4bGm8vbloTHdJia869T6Lz1TXKmCquIR3iw3
-        cTm1gzQij5EzHheHTTYuxeCEzmETMv27v199bNHjWgyUZ4R2zbc+IbxeF3h6jLNBrb0qwbc/EL/z
-        N9noznuq+J/bhu7yV5LNi8e9ApX5NjlmmhJPZ//rZxQ9JNbL84zZMGwBDQsJM+9IPuU0yjgBZ7fJ
-        8VIWAj4UhlRDnPRP/JEvZTnexXeL8LUxWJaiRzmFEPTy5k5O5NufumkzPyo4x3f7x3OcBuLyCev9
-        2mT+LQ2MSeudBD0HTljQ3Cy+0u6JhNwjPRHiqBUffnyNCkcnPz/cB7U0A7bKGCvLz8WYbdMF0Hvi
-        Md9nLZ8OXiugL6/h2esqNF24J0H3cHssn0+6sVpVj6eSDOcL0wZUZVTFnxmux7dKjEcjoBHl0whL
-        7FhEn3cKmtnNm5H66CZi7s73kkfN+wm//rTLtrY3qflNQubndSPOpta68dcf0WWeKLBEy6ZF6lKY
-        nuiAl6G1MXrUBCESKleit1jlJY3iwIZWlV367hQ75mZqY7gm3P7jrwTHt/GfftHJ20U2xa99KL86
-        sWM757BHk3/oW7SpDzuSFO4aNdfw5qJqcW6JecGtMe/ajwTgDCldCYplTI/rpYb5lB2J70HT9S+w
-        Z8hvskiMcDx0k+9cXFiidocXEruVX162QEObiKVBdfovXm0PVkTsgxd0Y+egGxQnsWJ29HIy/nj6
-        ItyXAyfq64r51Jln8c96BlltxeNL7kZ0ZHsFiy9p4w3Y8egfvkZGsvRaqbjegK7qhO3cHee9n3Qh
-        LLtwTTCCPBvv/eQqoFQdFW67wpu+5xlwjkq2C2tsTJ15F0Am0p3pU1Hy5hqHtvLjqa+/K8fstrHg
-        y6+YNzvi8bC9gDS0Sv3l9cqbBJAXYF3HhumLaPSolkUR6FHL6QPfu24owocJK5pcqCiKQ8aVbQ7o
-        2p8K4ntOXQ4HdysCf+g7hiW76vicHXo5j3JCiCwEiF+o3cLxEiokcHRsTHhHeziJ9M2cpbUvx9d2
-        fUJmmJ4YOfZXg9/lW4ic/X3FjOOnLefj4UDRr7/RH08HXaXCXrqpzJrcY8zLRJWU2/26Z66yKL2f
-        Psrbs3n/w4PC7Wq1m+2wu9P38qBz3gBbwHqxEOgo0VXc9KcOYBlwkcpfvpix9bSg3B0b8tX3jKMr
-        TUEZpIrF3/PySS6tBJ/NdGE7muvdKrtcc5Bm0SJWeY+QsEqUBkIhuBOKALL2x4dfvSee/lI82gRn
-        Wz7Uro8Xl9cDMfUcN2irHpaM6I+2Y8kjseH7e9nXX6O+6k8hfPmESsmCdbOVrlMYut5i+LxxOkFq
-        UooO96Sjs53EHvd8lqKvPpIjWR09LrbTDHM/vbBcHv2sPR43PdK7NWLagle/PCOEQ237NFtOYsYI
-        iRcQprGIPyfzwL95kgrokj2wcDgK3tOPG1X+5hEYoiNGfXmIQpjuZ4QfsvrsGPWWLVwvdsIMudtl
-        nXG2MFzcu4tlsbe4wN9hpXS7OsbfftB1YjuN8M1bmC+5AZpT1ziAcpqEP35zbsTRgtHQdaKZnHcf
-        KscCNBd5R7/+zBtBUGbEBUyo3D4O5eAhr5apNBf4/uXDyjr5Ljw1lbHwVepcyG4bE4y8NAm+JQYX
-        O7Ft5T7Y+Gwn6DXvjdOlRtuzdWfax9Yz0Ql5/uM33LNlFo/e0vXRfJpfTBflJepfLIxgp3xkhl+V
-        b8xDp/WQN8L9myacDK4vXRe+eS8J3q+w+/JKpQjvo8rMeSuUvE+jGibf41S2ogsaut1egK3gh3SM
-        lm32cg6yBd98FJe7RWN8fnmZ9jzJFK2lwuvly3pGfh1NLHjf824mcVTDj7/T3RahYdfRAl2qhBNr
-        Cj8ZX+V9BNJ8E5mavGhHl5Nuoud7JMz4vJfGZFmz/uN9XH7eS29+rYoC6tdxoD89WX/zN8DiymdY
-        PEk/v2jD+1Nhsv/YejxbpJPRKZ8XmOfI+uPf0Fe/yI83RUBYRcdPE7DcA7ucpItao0EolxRu6WCM
-        Yd0dYNuGb/whHe3o2U1mKPjiSAWpwkhYpWmDog40Yi1sp2PBSpZBJvKdKo+l36F31QGMF00nVn/d
-        Zf18piYkQu4yS4UxY57/TpEyyNU3v3nw1omSm7xrdJc57rbtJsGzn0jdhgUjsjAgqmpTBNg1OypL
-        UWeMn2P+zTefNVHPUpFNzkE2YSG/KCG8eZXsl6/tUSjRaRUUf/In5DbyjRlNUHrzOiILFN+GJ/GD
-        Z8/n5KyFymUNHtvSW8fnfl/0yNjsX0w/KZqx+uotfOrFg/iKUfIxyf0n0pdZ/Du/5eA/ri5aHUSN
-        qBI9ZnMwOPqPf5gu9b3H/RQk+R4pMdOtrcon7Hg92tyDE14+FCMWa6LVEPQLmX55lU/WbaHDdfX4
-        YIgyHc14Mz1hfyvOFBRxi9bffgXaxkp/eXg5XPWHuqlXvcKsi9Xz8ZuvozXRPTxf3GVMm+DuguDW
-        d7JLl4IxDEN5gO95Yv6t0IyVtwMXOlNHxIoei5KmXnOAb35OzC8/D1/9Rs1gEbrM914sLD4HAe1c
-        +cJ29WIRV6/t+gBpsPTIL7+mXIIDyB/RpihrWMn8FGRkuUFInKYJstE6mS5qVa+lr5w7ZVv4z5uy
-        fLM73dSwMr5+I1LGPHD/5MnzBSkjSgb6IW4fq0iYXKUCFh02TJ2egzcH4rqQj7o0EB8UwoVjvl+g
-        5lKsma+ME591AUXw/f14JZetJwKbn4oQTw1Rv/OSD1YkG4XpXqSif1A7xvCmAeNyAlqoD8ujjVo3
-        KBE385en1Yw3CxNQOKVvXM+GlwnaQ36Cpws73ErLi9f/ztuX13HBwEajn9ohZHQR0IXEFmX/2lgj
-        WDvDZsHyszF6k8kV2JOc47WTvvisemxGfJ2cyVZwTW/lxFcLnoFYE7X/rL2Z3ZsZoki9kMP9AR73
-        dEmGItV7upBWc0k39LmAe2saGLpoyPrLWn9C2kQmCUxH8ppfXlPoG2A//8BcoTyBv7xu6Fw1Rrn+
-        5ZPK2TGJ7V00r9dHVVf0WDeIPh0y9Du/MBwWNds6T8NYBezZoN/8CFt2nM1zMZ4UHG57Yk8Iexy1
-        Jxm+/p6ch0/RTbI7NNDvt8dvnmWX/WklLxAuO5M5wtCVr2sgPH/zJubvjKj8w5e/+YHbBz4fOzRI
-        yLnF/Zffq4xKxTVH9EVs5myKoRujyyuBSNtv6NItvmTx9cP68d5hsd/fs/HLm6i/RTn7+ec1w5sW
-        vvv5Jz8Qg3anwq8eH6b16ubOlDDKnu6JBbzFfP7p93d+hqvicIv5HDoY9jJqiB7sHe+Pn/7qMwuq
-        aIFo6hUH2I6txLYmexjjRmx8pGbNSKxg9+ymqrs0YDrN6jdfMfqs9SvoA+QzYzPv48mDpoafP8O3
-        pcJ59nApfOclzE+Ej8FB1tIfj2B00r1y7kOjV65zP9FZuVPj689k5ayMKju8Yjubn0K4AGSkD2bf
-        2nc558r2pJDDKSDubos4v9qbEH3zTKJ2Ts05XYW18u3/vzwYUVGqZbCuc0Ms9CHxWO4eM9Tb8cDw
-        2pHjsXP4DR1P1oquY96h/i6yBl5z5ZPd44YzXp5KCYTWkegCUN1NXz5C7rx9M2vL5njce3cJnWMx
-        IVZA83ICPtm//PpP/Q4uzUwQ3n1IjFiZ42YLnQVjX6cYeq8s+WQkPZCg7pndshdiYXtZyMFlnqmw
-        O9+733xMth4njWkrLSlHJ5F6UC4K4I9uFRm/M3dEW34diaEnpiGuUSHBd/5K7JcR8Dk59hEs9/2d
-        5f2WlUMuZDc4QJEzA1/1uDNn3//l5Rg1deUNVvwskIMuV6KfR8MTv/O8zd47ELbLuz4bFzftpIi3
-        o47F7aqOx3E6POXvvIqEr3PK2+SZj3CyUkoC93nz6LQPRDiVxZ0uLpcLGpf6SoIv/9P5ez7nxflh
-        wdBRi5k3ARv0PlUp1PYiJ1vnWXp85LWtvEl8xHM0Xbyh2woC2r9ZQZVVGHvz2U1GtFwIhHkdf/DB
-        3pIa+gZvMcu9dTYt1TyEn17+8qEJK5K7iZ8R+tPfuKfFMvz0fOvkzODtXKnyenkyv37hU/YfV5WV
-        qKum7zyDGONGPc1IuSyBGTmq0Ri/Zwn2Uq4SbZneuj96uj4aPp3PY+kxK7mOaDhA/csb4vG5yTHo
-        fZ3he77vYr5V7hSybNyy++l+99jFfPfIyw3CtHfuev2cFpby9+9WwH/+66+//tfvhkHdXG+v78WA
-        4TYN//7vqwL/Tq/pvwVB/DcT/9xEoH1a3P7+578uIfz96Zr6M/zvoalu7/7vf/4SlT/XDf4emiF9
-        /b/P//X9a//5r/8DAAD//wMAaBDGhuMgAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7bf024783c8096de-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 28 Apr 2023 14:54:47 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '325'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - f59ce3c6f76fb37599125046aec3d2bb
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Important Information"], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '100'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaW8+6Srfl799PsbJu7TciCjVZdwjI2SoEj51OR0QREDlWAbWzv3sH/zu7u2+e
-        RCB5lJo15viNWf/xr7/++ruK8+ej//ufv/7+ZF3/9/+YryX3/v73P3/9z3/99ddff/3H7+//9+Sz
-        jJ9Jkn3T3+O/m9k3eY5///OX8N9X/u9D//z1N7ldGbNR1kfT59Co6Mw2K/aiVIi5YisGtOPUMVc/
-        L9re624DJJoVM7PigS5k25cPVXN7MDsSyvbbeMOAFt0tZSRIHC4+lqELC7w4EyLkQtT7lXUGOVv4
-        xP6aWj52jb5AVWAsmZY3H0Sr5pvJ3tn4sEc2Bfm0J7cMHo67IOq27vK+rnMT1MzcMUfRtvqg6h8N
-        neTdjm3dzTmezPutAtE+a8zpTl0+tXmwQGccXom7e9hxzz/GhBJtFxP7GR/ygdlYle8eUunickmi
-        US+7DkY/14n9El2PVpWkwUtRLlR+oi8atsc7hr47fYjrGEU+7dKwBOXerPD4dMN4bJMaQ4iMB9mb
-        m1gf40wI0CpbypSHFxSxaJpMFGYhJkTCu0jAbizA/dgTsn1POGdT4z7lNQ1Vtg9jFQ1ws314R+iM
-        uTUE8/pkmpwddJPpWvlup6phKZhH+0FcY0v4dE2eMvpe7IxoFwYxvSZnGazE3ODNEK50Zp8WGjpM
-        tkp2+15DvEpQAXW9jZkG6UYf3ru6QivPD/ellBr5NGy3AuyJR+jXMuS2t95+Awd4Jsw5Xl95Hwbd
-        E+KbOhDte3t443FRl0jp+RsPxKxaOhYhheubMyqHkhEJweK2kXUVUmYa/a4dJyTL0ETai5DqHSD+
-        3ZtX2DzXIj6v73c+JVluAnMblxk1nWJaDFYJJ1LdmOYPe1R56duACR0CYl2FQqeNaptw2eYRMQPm
-        eP3tET6gv9CG+dpRi1dppT7A/cCFHCIvb/ssUUxwk8/AtmdZ4s1d+GwA1+Gb7EdRjrg8ltqmzuQD
-        wevzHo2raAuKAlHI3FAq4u69rBr0FT4dHnl94PxjdqUUjvsvs7SQ5DxwVxu0DvYbgje3jLPLUung
-        IUU+cfinQM3xbT/lOKlbtr8GKh+Cbz7B5p0hsideFY+Lz2GA18dzsNBFEh9Ph/1Rvt+vI9ubG+SN
-        py96wuNSMaa3LEV0HW4GWJ7vBXFegeDxvD4WcAl0g+gtU9E0NFEF922ZM+sqGLpw3SkplKtsR0hr
-        brzWcqJwabx9YNawafVRJ4tSlkf0wTA9gmgKe/cI3mPPiLVqRL1TFqSAOy0NujwsIZqu1DeQpNgx
-        c8rUb4fruaGwWBFGl1k3oMnU8xT1eBMTs8F2PqRPHKCPVn6Y+0jktutWzhXOn+LK7Msj493KIRNc
-        hQdnvtMeeZ/trk+IPm+baFKwzId8lYToGB835IyzT9SwvU7RVf4qxDT6Tz6tjyyA62qpsX3XeS23
-        nChQxhe2cO+Xb70+HXZH8PNWwZNK3Zhd3UxFn1oumJExveW7zgvRtlXfzPhKYTRsW/sMZ+E90pW1
-        0bjItxlF5095pfLJtHU+7y/42IwRw1/e42F5OjcgnO4ZbSrrHo/nnf6EQBGfeFiIIR9MbROgJk1q
-        slOrJh8DfnyApDtXKms+4z0JvALlW+dIPC++tUMtpCkI09Wg/C2/9eElr46gYW+PJ2uRtVO0LFXI
-        /exKM3v34GyuX1gsjQLTy0WJu82zCmCR7XSCfdXzhn5bYPCmbUpX59eej6iRRDAcGfDiIUhtt0mf
-        A0Juz9m2GpOIBmWVwZCWDtlnuzQfF/ryjnAgIaY9NIcPr+pWwS29Ueb6XEYsV90BZVp+Yq7mE0S1
-        10gRvS8LZjfJSp8KczVA0Dp3grvnLZ5ulWfDnRYG0ZWTnHfiDQAVOpTMO6EmZ4m6TNGvHsz1XUYs
-        pdCgyNVXmN3Duh2wRAtA7aaiIB0/Oj0HYMPwuK+IJpgD4mW9esDyYZjsmLG8HdtLGkKgr2MMpn5t
-        xzJ8GMgf6hfzkjDxBmEfYpg/01zBaV7fuF0isxovTE9I4E3L1klhlaUhUW1pp493Kroo4EqNX30U
-        o+5rtnd4UKDEw+2kj62JTEi8RUB52fke1z/1A71Xpkds32/y7iahAlVFGLJ9/Yh03l6jFH56uniS
-        UJ/S1beCp4QxFazs6fGuWWOE5PsNL16NO/+eKgD11j/xNymZ3n3y8AHlVz0yw8qe+mSVcIU4aVvi
-        qcY3pqbeZnK08X22FyWid3EvdZB98I3tGrTJ668f2UjvF1ti9QHmfBHVRyBJoeH+cPX1FV4+j+iz
-        uZ7I+fY+elz/vgB9CqIxXVvsou7LFAzj6RRieLnHaBTYqP72G/Of1qsdy9r1kYmeMZ7ls6XW8drB
-        oR5vVHqv4pYdO8mWvH14ZqYXdmioE/kK1/fI6DrnUzusrFsg2zFdz/p11YfTQxvkJn3VFJ1Q0/LI
-        SQPIHleXaIj6fJA/moEGJ3DwtOdZPqDX1lXCJbsQkrNPTvfkkKIa0RcxxaDTh8RzOoDUd9lW6Ew0
-        ruqNAZ0aJMSmuzHm46BfYdtlAzF0/uX9dHyVUrnFBc7rA8/H5CzfwXkqI/Eno8trIiVXpFaEEGsn
-        t5wNn4uNziE6EsLTZVzb7bBBK0k8UGm01jnjhZNBv9RqvGg76jVHqTeRVxRnZl6OQzRY33UDy1Z/
-        4Y15cVv6tc4VqjhpmWc/cT6cl3EFxeqr4+ztb9rxfbgfkbdmGtk367alk5U3EIXXB934vpsPheqU
-        yHiahBjudM65p8gYVT6EFJDURZ3TNQCU2Wu2N8ftXE/CHbbSUsZrU0lbdqpoJ5dVllPhK4Vxj89+
-        hrZvp6PA1jbns/+BJlW3xAlqJxqWt7cJOC+WeOEqojct1t4d1Bt7/tH7qVdTgM2VdlSe/dv49WMb
-        9B62dBLhzbueqU9Y7y2PkfX23Q58cH2lDByF6D0U+a/e0T3fq4wU0rGd0sTTYMdEmTn9K47YLj6b
-        8mN/PJD7YyeiuloVsLkl0ZauBTvPh1d1qFB2phVT0UuN+HePr+hCM4E5/GPwLhGiFOonVYjxsr7R
-        oLdvX7m+jxad3v4mn/tHAGa3aDCkeyeiZbGnyLmKXzzaEfM+psI7cEwnZ9aGJPm0XVwCOPjjmu0l
-        M+TjSjsOKH6LSwxJ9eZjZd59cBfTB1eWlHjTJU7vSno6XJiviwKf0lxfoHOzj+b9zHReX+QKXbbv
-        CI+hjdEgHx8bqEVVISTJNI9P6qaBfXgAph/2fitW1agpg15+mUPliI+R0RRyAsaT2fmzjH96qFhv
-        JtBi7dF41LpPhdh74RKzrd9e9+snd7btiJZ9R31Q77ErF6410PuVFjE/ZZ8JnWRrR1SqFdEwaHsT
-        tEezoAthLFu+aX0fihRsYteRGfVDkcsg5HKEkS1O0RTTboH4JzwSp7++o2nYOiJszG2Fryx1+MwD
-        qryVFJnsrsc9GhVNlSH+pm8Ky3fV8gPFE5rvM9WvUNRl24sP6pT3mFlqn3f4vQXw72uKFztbjBls
-        iAiyaG6ouOwrbzpmIvzhGesyMn3qzHqD1q+BMM31ypiPplSg5pAGLBRhy0U7MGf9ubt4LfcuYuHh
-        0iHZ3wlMpc4zoq8gDSAdhoY46/1bH/PmIsA9JypdJvXD49HDA7RNO4Ml9qLg43HxLiEZhy27D1M7
-        r8cdg9FvK6I7ytHjr10mgOxVPjvoktUO8/5Avief6JqtRH26GlMA8/rhNM94PK4t20TblBrMmrQb
-        mkZkC+j9JJyWSFvrU4JIB7MeES0jfTyM4RT+4QkhfrUehRt6gG29C+JH9oD6IqvucBztGp/UoORs
-        We5UkGvrzFSFL3R68BjIR1H08MB97nWF6abyn/tXb+v14qevULuWRDqeZQl1zDZVGFnL2N5CjHcy
-        2vigLaIY97pTIOavxxDiznkQLwkVr4eUPtDiMnyIPrYyZ61Fz2iuJ7wUvKBdCUxSYeYb4kSlEFXF
-        lWK0l+yImZ/8ko/CzZWlLXljTNd0bMf29aKotY4q274n2vawfpSA3oXHduYKe9PJuN3hoqgfsosP
-        G0TjiyhCPa4bog+OHXNlCO7KOJ0FukFu3fJFtwcYz+s3HqtGj1Z3KtoAKXbxcB+qeHgv0wp++rmQ
-        F67O0/NVhZkPiHU/i+10U5mIlkqXE3xwJU4TZHUw+x+m7z9DNLyvuyNcveUCS+v92xu87FLCay3u
-        mf1WJX2qfWeBYtyF5CUPa94eywH/eItyrXznvEfFXdHFISBmLxb8j16t72bPvMTTvb4BPEFcqiEj
-        lbPXB93Yb2C9DV7E21dKTNXYvMJrv3KIZ3V5PChYEJGTezs8xHanD4/vZoK5n7AQ0Y53wbedUPHd
-        hcSr4IGmMepT6TB9KmamNxsNK7HT0MwvONtuJH36UmmBzhfjyw6xgtt0M+oLcKWdPvNTihhlWQaf
-        w3uBefqq2mFd1BiwHy7xr3/R8JG4SPUZ0HhfJdEYxUGn5N5rZFqSaFFHj2QDi7QUCDa91pv5vkCx
-        my3p9A01T5z7pVRZwYAX21vqMVs5nEEZHiVxQcB8rK+KLOtrssECWbUx3ZHPFcrjKZj7o5rz/LyR
-        YfX19sStVDUW0iygytspNsw4NF48rWwjBbeMl1h4ZKq+6hoPUBU/dBYFKxuJx0xcQHnXJuIWV8Ob
-        uuSq/eGR4RrG3rRb2xTabfUkqu4t9dqd7p1sF28Ty/SocPZGlzvk2dn58VPbVOjYId0LFGbNfqqL
-        +5EqdkVvVJQ2VTw92V4ABy0jLLyPnjfRfBSVU7m4MYtGeTsZ3fEB5LR/sO1Hs7xBSwFAq6uUPuZ+
-        xW3ldoSzkI905X0lnSc0miDvqhLLkbqIG6HgBXwfokGs+ObF44UmIdD87M1+q+SjVOIMITf0qGiS
-        qz6GkhiC8bkS4pNUaKnfrw2Y9ZfM68+76HJ5wHUnCmy3aTNv+JrtFe2dV0/FXiwQcx8XAYXIfBCr
-        eupoBKwN6JneVeIYdInYKlphmPsTc78n5lGWbDY/nmZG0mHU5Y+hgdm/MVP5PvP+Xq18+WC7wIyq
-        0FvuHdMrcD7tmFWZ6o8PMjk3RZE5XKnayTc+AWgb+8Cs+NZGzVuNFz++xdJoXdpJ1d4DDHrxJVsv
-        uHtzPWRw7/OECvg+ofGzMky4VOuQWR5r8zrIvgGUvfdk7uxfum1rH2HWbzyd9w4SnuY6AB2kO2nZ
-        vfFYQqMBdpva+cOn/CtnFeTZ0cErmMAbGssPkb32XdwImo6GsxRSCBThySKzR3ldq7dA5hIizFPq
-        MZ5A359hcZk+7Od/uvNheYePVnyocH+I8fy+RaRt3MPMRx+PTY32BMsIG+I3Wq1zVtcF/NZHlvyp
-        ZU8vn2BnZwhPy7PjibW/BVQ+/R3ZSuKprV/UuUJ9NzWirraR1/OPP6BfHrXzvpLHn5KqobBEzpy3
-        xREdkS2i84YZdPxolj7u9VRUbk2YU7ToSm9wlav9y6+Yx+6NzkC8HaHSrYR23+Sds09ypzAs9JA2
-        J7PSR8tONXhmpzWun+YuHtTRCeDZ4Y4RxLt8+L3v1fO8+NWP3rBkIwNnxci0tR7zYWdLGFL/ZTPC
-        Rkfng2gclc+JHX5+PG+QmGVKW3B31vMgHl/JA8OSX01GQInbMamfBvQC9an02R29YTHtO/SrD4YD
-        0xuwVJZAklLDq8Vmlw8ftDTATVwbr+tqatvK2j/hdnieyH4NOeLSavNQ5u9P22ql8dk/iIrImi2Z
-        81jeXy7MhmMt1n/8MLfu9hMu99ObSqHx5vyzWp7Rn3obxE00ys7rgcwOGmZMqRJToeAlzPxOl0Zs
-        xqu9Xglw4+aEJzk6RjRPWhnoUbgztZxaTuNd7KJfPnj5xpjzilaDfJXdEx6er2fLr0G2gPxVG8x4
-        1HedG68qQ3O+wfZe7utsznfQzL/M3Qq+PnT70gRnJTjMCY0tGossvUK/VGumjo3aTrOeIxdXlz96
-        9nu/cmryEiN2d/X1S1AKFAuZzozVsEIcRfYTwtfXIW7mqfHgpbUJb7Q/EUtR8pifvXUDki3IVNlS
-        P5aukpPCz496hXtAvCmSK/z0wi0Giw9OlwEcNgeXWUlJ9EkdIQXxEsWM7D4rb/b7GHnKtSCE3I9o
-        2rziTPrlu1a4nPO7c9P9yRdMk2w8pmhgAz5/E2aYapvToEwzFBurhM37PRrO1SeVnsampxs1a9Dg
-        KoEL+en8xYvPq8mHOpmuyp4/RzbnLy3DxtEA7AdLpr+EdcS7ZukjZJQ1Md/COxqtcRTQuiqedPFe
-        02hkt3UlN3jlUUrBbMtHVahgN7giZv/cesLsH1G7fmKmwqHNR9tICtSk2nb+fnL8vXxvBhikfLKZ
-        j1H3W785r6Sw6ireA3YH6ee3z8KKt1xcY/PHl2wH00MfJP3bIWNJO2Y+o6XXB8aWQi4qBtlTq/DG
-        OLRMAH4U8UCdRdxvnccEiQcBe34sk08yIRg+rDTpMn5co6EfREAG36h0uHpvj4XVToT5M9tZm+yX
-        dzUgJa8VnlhXx9ORdzbMfoGYsPP1OX8Mf3nIH32lP17xtlKIr29V8liirlPwQc3J67B8xMNhuqpw
-        uj4rPG5iRR82a0NGO219w4PSFfog3oQFyk1BJPsvITHHJyeA2Z/RrlgK8bRITwHsk1bFt9CL+QrS
-        8oEKp7Lx5bX95tw7VncpfH0ctrWc1BPn+lB+ftDbvLR8/eONHx9aO9lDnX4X1D952dZfpPr4zkUN
-        YJ/vmKHHhjfUQpWhJcMTMXgeeoMA3QIam27xuhC/7Zw/qvBw7AUzlp9VO/7y9tl/4XSJxfaXl8BH
-        3JjsNb/vds+pgHJkX8iuoCuPXpPnBhG09Sma+0198z4hfC9uRox4jdH67fsNgKRdiSO6fjwx8ZT9
-        /B1u2d31KH4rGH58uqVrE/HooS8A27uObDdHXec381JCsUQpXTyEW56el3ED54v5ZWQZV3wYfemI
-        JlX4ULR/5zFr2baBaeWaDHdPKR77/XGD6p3MmNdOez7MeTpKcrbB1zoqo498NxpIxYdPwuW59qbf
-        PISJnx1RM1VFYvn0B/C2KGT6ejTi8WHu8M8fUtgcgmhM6rMB67VBmOebDRqQHWvQd5cPXlpq3xY7
-        LNuArcbA35Nv8U7ajhjCkXz3Y9XkcbNIkwAitvqQbfxxOd3Y/V2+YR5gYdaDPD1f5/V878g+uZN8
-        Yi92R7Mek33Xta3wke0CurcsU6nqh5gvU9+UdHTz8E1gEZ8MZVsBeZkHvMRBqU/T8zAphb4oiZdf
-        zXy6uNxHRSgtmeVPaVvN8zY49bt8zm/vfDq69+PPz/+ZH7GZn8EZK5GOikm9eptqG8iMbUGXPH3F
-        /aotS1iQ24LC4sn59FpyDVxjzBieWuBjJ0su2Jpcs5+/44cuCJSZj8g8r2rpiFRRnvMndpFPX53R
-        5+oM83yGuYyd417r+gZNqvghhlB+9cnv1AIZq/Wa4PboRvzS3zVY7ssTs1bNWW8gmjKQR+lDLNti
-        +Z/5BGflyHb8tPyT78MCw5kO3ZLk5W0xBsrn1B+IaomDN5DHOoWX7XyxpIPQsrm/ovG8etPJOJd5
-        1e2pCdMAnC610yMf7vn+AY9H1ODpkG3mPHIwlHVcwG//6axf5U9l5kc8Zd/Df+UJzlX4Mlcm32h8
-        UeeOnoS4mC+GyBO3LSpg3LwWtFfGnI9NnrkQ8HRL/PvViadyV9lgriObbKPcigRfl1UQ7aNGdqja
-        6/1vXvCM7s953lujztSGUDGu154d9knC26/w7v7kkzMPRTMPCiAZ9Zfs/fLtDfHFK9C1rQqizvwy
-        0qvjgqYd3wTjTxiPhz7O0C2NKW1+vCMTywc/rxX2mz90Uqtryno955XDouEUDXUJ5JVLlItnDw3u
-        CUQUOcWe4Xl/T2GvnZHqh3/y1qjs1QqUMvAUKvcu8djv+87+gWCHW9GUrlgjK8H5Suf5V8yPu5MI
-        VmJssKQ4yKPe+3FEqtirDL9CEwnrPTLR1rkbVFk9xXyQdEZRHolXzKWFrQvCPvShacX+N++Ixpf/
-        1UCBQ8hILi7z7rlTB3mJtwqz1jvajl10EgAHz4j8eORPnrclOaZLt6p5mSf5RgaiH3Gd0G0+zjyA
-        +mZ1xlKEh3zgjROCWfEL2w9HC63G0axgKFlEIcidfHTIVoS/f6cC/vNff/31v34nDMoqeX7mgwH9
-        c+z//d9HBf59T+7/FgTx30z8cxKBdvf0+fc//3UI4e+6rcq6/999VTy/3d///CX+OW3wd1/198//
-        c/lf8//6z3/9HwAAAP//AwBim/ij4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7bf0247aaeea96de-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 28 Apr 2023 14:54:47 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '63'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 974557ca996688f2b7e568f6d601ad88
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Assistant Reply: {     \"thoughts\": {         \"text\": \"thoughts\",         \"reasoning\":
-      \"reasoning\",         \"plan\": \"plan\",         \"criticism\": \"criticism\",         \"speak\":
-      \"speak\"     },     \"command\": {         \"name\": \"google\",         \"args\":
-      {             \"query\": \"google_query\"         }     } } Result: None Human
-      Feedback:Command Result: Important Information."], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '483'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6WxOyurbl+/4Vq9YrvUtEJWG9IfeLJihesKurCxC5iSCQBHLq/Pcu/E6d7n7x
-        AfFCMuaYY4yZ//jXX3/93SZVlo5///PX3+9yGP/+H8u1ZzzGf//z1//8119//fXXf/xe/787sybJ
-        ns/yk/9u/71Zfp7Z9Pc/f4n/feX/3vTPX3/fopdD0flZVNPUPC8yT+sT3gt8pY/uh6XKIzl8CTzP
-        74Rhggh4m3hNHTU6VhN7kC18XyqDotgb+zmfIhk+DKen3kq1uXg3HwJceS8R25JtA15/gkgZ7UnA
-        TptGFXfomsGpRFfq7XDr94G9VxVzjTbUY1RLlu+XQXJ53LE261NCuyg4w6QiDZHiXKrKTRMg+KJl
-        RuBWrkPyiQQGU2j55ASHhnM1HnIomOyK/UP46VlvDDGM50TFfqDyiqUNOyuv9Lahhye6hzPnWQTX
-        0DngC2N2zxHqDMiu8I6RNGxBvy4uKRxflxRn7lr0yfd0G6D9kXSMwuTT8yG7s13IOgHbO5FzPiY1
-        gUPXrSiGmtF3X3RSYWolBLEi6qohbVigrDwhJErOdX924KlWtIgcqepU34SIL3sLt1W6RYA/hpBd
-        XlYN7qJ2JXxb0rAtJOBAr1hv0EbURZ88Qa3CO68k7Hjw40+nMUeKEphbspncgg9QLSM4xqs3Vldq
-        2Q+N4auwuBY11W3fqDYwfjLZQOOZ7vX+0k8nZT9AZH0YdYzjPpl1ZEiwdpQNUjYbLZwf5gZBr0EE
-        yXfb1ScRHBFEb4QQUJTGZ6etZ0E8ZQeq7nDJSSh3AVTF3UR1cQQ9f/Rghrt9s8HqIbgl3dGzIazi
-        zZaqvQjC6fM+11AAnUH9G90l8yRLGdRbsSJSo0nhDx874yTL2DtEVcjelmDJT1utcDaLec/ZfmvA
-        q9po1EykIZnDzhRhfMgDnJovE4xm6NTQEsIj+azevJpv+HSAard6oM333erTls0GWGnUwK7DN9W4
-        G0wLNifhjI3tM+x5FRdQcTV5Qq0ajRV7R48cesn5RtYAv8NJj9sWyhZbY0MqPsm8CzADv/U/lPtJ
-        58q9HGQeHWO0RpHaSyvCNeW9eiUYqXcnmd9lxIAZrwKkMA2B6f18OHA9SAoBtI56LhFPlsVTOC37
-        U4SDaHcGkG+WgS1SQp9kzrlUhq5fYZWlnc+d/BLAfZhjanrVwOe5oRA+SHTCqLmvknnclNqqt8SC
-        PrEE+Dhf1Bk2gD6wE+GGz1BKLEj6JsbHfez5bGUypnjl7Ua9ZwX0Sex7AhJpeyTysy8BewRWBpUU
-        vwhJd2FPuDHJ8Ni+Juyvdmd/krtYkyV7ulJNqO468UPYwMo4R3SfayEgD3vnycA/a9R7H7Vqs5dg
-        Bm/9l1L9/IbVpE4lgsVoaTjQFKlqjuMjg7f0nqMdqu/JFL/cFFTxekujyH75v/oGIJ4q6th2mHDz
-        +4kg/OgFKRa804MxEvg9zh49qmmt840Xy2B0zk9qW49rwkmbOFAJ6js2d/6pkqxSJNAs9YAoJ6r3
-        kzp9EVhfZwGrRdT1k51oGiw0KaWOcDcr8aoEKVzwgrVCf3N2TcNSMYm3wQi1Rz6JwERwT9071a/p
-        N6GMpY2MOqPBL1xs9bFwijOM5Rbj+4m1nKNMa2C9P9rk/TG3Pnt9DwN0b1ZEfXx89Pw5PD14LjSb
-        yDa79mx3r6Bsf0Qd8chnCZ3dqYSZc3FJMSeFzp6lHgAxkjC1nncjHGCgy5CBtUXtjXnkE1lFIjSb
-        yMbJBuX6JB7aARhXfiav/vjWp1XHY8ir9kQtfPLAdNzwmyy9wQXJFLbJYH0DWV7qjXqm2PXvfDgF
-        UIZ9jTjTuoocTm4OdkOFyMZ4dsngzucblDo+4MN12FSD7YYQipvvih78wOxJJq1UmCm5TdXhc03m
-        /KWk8NrnD2qiSK1Y9Vx9wRoRAXt3u/PnPAgh9ByLUkshVTIJxz6TrbI1sakIfcIOm5xAaY0qatw8
-        J2HnS2wASyqf1Oi9kPPrVhXhFHfSgvfE5/k1rJXUehBqrjOz38jn9Ca3uxWhe20kFWvRqoRSLECs
-        CyHWqcwfZ+iO3p2sG/us98q9JPC7YgVF/u7DZ8N/zMBxpZii4/fDl342w+YxaljXbwFgZeh7snLJ
-        KMY38wQ2xf5ogU14KxEzh7QfLRqVcH1lAjZipfQndJPiHx4w/kSnkHu7yVHgtNphu2GXZFY/6gVe
-        lCimzjXPOVvpkgh2R5LRvQwswPZP14Af/J6wrl7uOnNuWgzkx0vBfgfUipw0N4LwYLvYzldiz/N6
-        bUH3ARn1TXoE8+68J4pyjCk2Nd32e+IGDsw3jzeNEncLSK7OKRDM+UpxbyrJV+G5BovhXWEru36T
-        WX1bMTQPTo5NfT/qfE4tA0p3o6aHVef5ZK8HN3jt9zLe36ioT+uWfeGzEABGluPobGKrA6wvMcH7
-        9GqD4RX3B3BzvxE+HmXK5yGJLVlzYwEfsVD1VC4UCU6NMWLrLEh85CwgCtiCErvtgVWt8662CkPy
-        HW220hGw2yNP4b19Z+RtstDnJWEZHJPMoOb82XDii1MOtnPYkt0pVMJB6FoGX5K9wobmlLwvj6AE
-        76AdcLgtcULWaSrCQGq93//3OV3vG8iFuqX7jvOeDF/ewMIaRGp06APGBDxi+MkOGGuf2e8JausU
-        quQWYLyJJT6sdEEEXzMH+IilBLBG7FKoSdIB47TzK/4ZX7J8bJ8T3UvOUZ/XIzsr95paGEXWA/Dp
-        UNfwZGYyVY8oDbnnngcZefCD1dqmVafvqhaEN2Ri119PITkmkgZHVUfY2vf3ZNA+6xo4JtTwq6qU
-        P3gBjzL40iDuqorI2daD/WnekTk7RDrHj2sDz+28IcL+SkJO7NsBiunwodqqqwFd9AJY+IKsiHzS
-        6VtcCZAe64nMq67m/VWytsr3yDycLHphoNtXAOyAGdT8mJE+m1Y9K5aRW/R4j5Jq4UNBeU6Bt/QD
-        Ho5XJrYQN/qVwPbtcdFD3xvklTuTebN6huyqRCmkFVSp8RxafT6dShk8DK/HnpRrfp9LQQmOg9hS
-        zXicQbeK7hDGssvQSrXVZD3Z8Q1UzZliJznlPW9ldIH6cevTxM+PlfTZgQFe4l1NUZ2EIa3iQgC9
-        9vwifo9uIV+d1wN0+LukjisUPnXy9AzyTfJGz12rhRsv+Zwh/5QddS3jVJEvbRtwFY4Fja/6OpkN
-        /8RgkcOEquWN9ryYqhKa9tSRKcovPquemy/YyuWGuhp+Av7a6Q0kJj5QdKhjn0MQE3AKkvOfz7M5
-        K1vF3mdrJFbtxR/vMtOU7bFxkLD4iW9OMwi6NKsRsPsdmL5wXYI6KG/YfzQfn83K+6vUczki/s4o
-        6OazJcK7NlBq4Ab1FMZXBndPvCK7avAq3s/NGQYX94JE1DoVHQ86gnorVWitKrtw8gwnBZMInngv
-        tGdAUeY10E6TA2EGkXpuRbEE1fLQIUF/lDqtvnomE9euETDpkfO19kiBgI4SNaIdCZlyDCQ4Cv6B
-        VGveJQufDUr9MSVq80DW5wM75NB9v3dk/epVf1P5TgYPfaVR1RxgNY1zGUH3jFTyDty8mstdfIEn
-        93omKVKmnt22fQZKH+3JdtFXvVa+BTB8nYyej6smIQLeavBPP86uXjgDr/hC13dU+uPb8Zq1FsRM
-        GSl6rorkexxPKWisKqF+EYZ6W9HEgJ8zf2C0PC/fWzcV5quviPXvye03fcAOskbnA6psHQL+rQz2
-        01dYj7Ghc7ZnhrL0M7wvnKKnWfc1YBz5D4zI3uK8liYZuhZ3yXolbxKiWnoEvcm3iLTxumoQdt4Z
-        yKh4Yzu9lH1XWp8bXNYXY30/h81aOTEQnqsV9fy3m7CWwgyGxRrhoxYFPqnfvgiFDRvoLclg9X1d
-        VajYwWwgmB2UhFy1coaege5k3uzvCdOvnQrXloCwxa9rPudTICvZ95KjMeiuYMr0eAupOzywfau0
-        iknnaw1HmwuLf+l0XpJtKluqi7HabWky3Qa73Sr0YVGNXvqEi+tSgEUtcuq/HQu0YeGUMKmGhh4K
-        3dene3epYXnzHti5ZRYQv+4pVqbGGolSwHVS39csUqrkcscnMxWr+Tg+Ujjf43B5XqYv+BTBhMeM
-        rJ3XQ59zeoNQf1QXtE1Oas/w6uvB8+PVEvDMViEr3i8ChgJgqn7cLuS1laSy3PID9jZZ69Ov4c7A
-        V7MrPSq5XI07QBoonk4T9fvNoZrCyzAAKNg5PeZc1zfppDkQIWmF1lc5D6crg1+QEbTFqBiO4eB/
-        5zO8CoOK789zW01FpLGfHqUvTR9ClkonBuWnJJLVTGvA3NMzgsAPNDQnZ5NvhlH1lMva9ala27if
-        b8U4w5dwRxhd0L6X/HlVA/O9a7G+y9fJbOf7r3w9AICNXfKouAtrBMPYelJPUxJAgEMH8A6+w8/v
-        6iTqOwd2VVkTZR9//blB3hl0fXghEzJKfURrJ4DgBnwiJsDRx/M2HaBFFIEiDxSgrZNDA/eVzjC+
-        2j5Y+9ktg6e03KGJ3ceEX5sxAj2fAuqxj9yzraeUYNH/2L9OPBykYmWAvhZybNpiwydDlFoIJmem
-        etFBfXxePxl8SeYK+9tV7lN19ylhaW08/OO7yQsLAQqrIqWaH+Qhf+ttJL+PT4NmdcLDrjWuLZS3
-        VoL3F+74U1R/Gnh+Si/qnkIlIdnnWcLr3DywRm5myNMi/8Ky4CX2x/ZQzcXQbyEP0i8+2n7Haez4
-        M4Ty0aHGuioSlsR7SdH2X0Td3SvQKUKFofz46YteST9rdD8r7vuzI1BvMp+l0mOG2zTe0r0VxxWr
-        /d6Ac7MTqd19Sp+VetEqb34XqRraFZ+f/rGBw9qQ8D7UHH/hx/inf5d6aQBrg10GR8E9/MmP6PMY
-        e5BI+Uz44vfyzctQ4Qd/JrLkJ/1M2R4CdR0Fv/WrJrR2znCpL6qNwaYf7N0cw0uZ6Wi3ewX+FJyC
-        M2wQ+yJZUxI+tbOrwsW/UJfv0pD89OAFKweyWfKb2V4ZX7Dw4+In8op9wroEBtycSOevp4QDUgfw
-        tK9LqhaRWzEY+FvI0PZOnyda9VMVPmdwRlWAJNq6YP20TAFKxKko3ptW8k2FlwX53k/QuoNvTsHL
-        Y3CXJx8EorbwGWbqF4p7FuDjwh+0e68kqCZOR7PFH9DKRTl8m+RC91apJZLjAwdepWzCtv7FiYhX
-        XwfGezPG1Pk0/vAgwUVxt1OOzZ9eDbMKwuzu7LAty/uKH9aGB8LCe1L19XH7GblFCpf+SJ01jXzy
-        MFcHeHkFCdmF98mfrmqG/uh999D6yXrlbSOwZtobbR/HAYys125Qr6GPo6P0SHiIvQyGt4NJ1be5
-        rsgNPw5gdZV7ii2p8VnQJy1Q3PJOVoPw9kdlSjLgPIcZ+3TIQ17sTQNOZ2CRpf/3w7e9xPB2LBlp
-        9fiTzAA4Bvwo6mrJD8uEb+/uDdqCrJFNFqCKb7qrDFfaaGBLp76+IRuxVcJzsSJzzU5g0eslgNKF
-        Ud3WU8DKcmjBJXTEBY8fzk5t3gBzZ2P882stuxWHH38TLo5JP2fSSgMfBiIEPe8O6OG298BJmnMC
-        +09djY8ClnCvXlp6cdeIr6P6U//05sLXjr7x3DOB7pbnJFj0Qz8pvgZ+eaDdFmLCrY94UWjAHtiL
-        tq4+tcazBbt6zqjx2FySce2RGTBtZtRY+I1rM07Bc6fJSIi9Y8Wcdy/DpX6R/D5qPTtfzobyW8/5
-        TTacdclbgB7evAgrb7iiJWEpzMhhS8JtSZORZKEMxWcSoQ/Y2n2VFnkLzVgJ6GEKIKCwW523Gyf2
-        fn7Cn9/B+gYvShxjx9Vf/XSXmQqgmu2xO6y+Cdsn2IPkgyuqM83tZydJ/2v/+cOVwkV/WErIeoFc
-        jXn02TYNINxevg6CU1RXk7wFOXgFOCDi4qemqClyeAR9hC3adqDwwk6A+BsfsHk2h55stgMDzenF
-        MarY3herIDDgq28tmsnFoVry7QHUqZtR20OdPifqyVA0ehoJS98YTMP6mQGLrAR0nboTEPW3V+6e
-        O1XG6g5rnMBm10Dn+qqoeTYPPVj6Mdwk5hmbxjzqTUKUGrKrcEfwzvpkxNpHhhGCA6lNbe0Pevgx
-        4LGFAdWliSZTs/l4MBqnlCIlOFd9/EEzIJcyIehdFPq8P+9EyE6fHCORDWDG710E05P4xv5bfenf
-        X5658DkR7Z1WLev7BdZF/1DD2bSAd5vkDIon41hzD0PFSTS1ytKPiOhsWj5/ImkGwcW/0IPeCDqf
-        xiJXyt1Fxd7FxOG08li8e1XRhp7bpwLI5TYFUEubN9aDzEho+bxqsO6zkShouwaMNRqBi/6nP7wv
-        eaMKNcoOCBQh19n67jVQSY8vNITgXv34E17lq4s976Mns7nREfzVozU0gS9mQnIAPz1gy/ODj5E5
-        NPIzs0oyPZqCT6SwIOi3no3y/Aw4rT9BrAD7Df/U2+K/blsihCWiggs5D7NegCczlbHpvhveCccq
-        hc5GeGC8+DeedaUFsyZzyIL/amMIyhZsmtz95U096y/m9sc32MfXIpzNmxXALmoOhOAm5Fy8EA1Y
-        nyNa8Ff47PZoU6Aaxhcb4LLXf35febxsjYjNa883lYtKeAtIROZKufNf3gTAbefjfbPbJ5K9OrRQ
-        aJ9P6q92s88jQkR5yQvw8R6BaoLnIIP4EByxrRQvPgHzq0Hqkgda3/W5X28upacseTJ2dvViR+s4
-        Anh9qbEZiXNPkXKsf/MOsi15Hs6K7jagTTyBVBAn4ThqPpRHIzKJuORl618e4e2iKwFLvstPpm1A
-        4po1mvevvGdsPRx+9T72XrwCVMqKCJYjcKn2RLM+7tK+hukTHn75lT7fM5lAK6lNjM+RCUTMnC8M
-        +mOI1den63nQHLRfP8JPciI//MdgiDcYrQwlq9jZ2DZQ2Z8cNP346LtXEOzcs4I9MSXhSFaBBC5f
-        xKl/2+x1vpGnG7gGZkXNtLNC8XZv8p+/wE5kr/xh28sZlAstxX7t5aD9uo8Ymm/QUj22YciNobvJ
-        y/NgVZEvYH7nmQRHIzaxdcAnf7qcpi/45W+4jP2EqS/owB24CtQ+grXfit3dAc6o7ukyvwIUf3ca
-        XPQD1cV1Fc7+O9LgE/GQ7Epi9O/Uk6FsPLov2XkbPxlfwijJhgVLmmrt1v+jhy93/UAWfusnn+5k
-        uBeyBu/v6z1YL3iQf/m0q2EF8LRov9A5fXw0XMip3wj65QB3/IPQz9/x80nJ5R9fRsFo6zzEWgbt
-        z70m4rJf7G1JFqw/toRdcbglE0FyDJEnfOiiRxPuufEA3+CjU5X0nc5uzlEFnJ4e2JjI2LPEIRE0
-        toGz5CmlTw77XFV0UPXUaF4Fnwxp28C2sW8Ur7Mvnw33LsFfvnPrNl99qsTzAOzPtcY6vFf6/KrL
-        VFnyanr81hqXztnppqDMQfSy9Asaf6wZtmGE/sz/eHx/n5W2RALWssNWn9nhAQFODAUJs5hXjN0K
-        pHi7+EqPxiVNxtXuIsMXzTMkZus4XPqTAIVnZaJ5MvtwEgaSysVoaPiw8P3PH8BcEHTsxP4ZzOte
-        uoFJcQZqvB/in3xFLnc3lTqfTqhm81MMP/7A2Pk0+h9/u/Q/spXGTG8Pm/bPfA6j74H7LdCfGSw1
-        YUYf67EOJ+MKWji/fJ2i5v5KFjyKwK/8J5mcsEx++wUWvqUH+GHh3IVRC08SywkQwMFn1WtqYNKe
-        KD7KTRvyylfTP/MziyVLPOCPX+iIxp5Gy/xrWPIjeNnlGtUuyTYca/oeYHTTBvQVtAIsec0ByJr8
-        xD+8MamaNFCez3uKHodPz9GBer/8Eu1OyVuf78qaAHHTrvAprm1Oln6m7JPzCmOAvWpCdirDjb3r
-        qbbot0XfB7DP3x3VJrNPFr5BP71O/Vp76AR09Re2hxvCep13YB5cqVWM2HOxpykADPpby8GSj5Lx
-        KFPQGaLQ/vILROvbvR9Xu1SG7/39iarFn/LAdlWIDU2gP30+uRYo5fal38gUqCScwNUv5V0gW9Sp
-        6zxc+t8AHFPQsJnf5nAUSB4rzOoc6l68Xh/HSpWhDARO7cndg01EGhGyUbthLQeZz1dq58GVSBOy
-        zFNC+tuPxf+h0yOTdfYaNjNcdcYZe1tXDtn+ubeUhhknetklu/4rnvILNA9eTo3mLvvvG9k3yt+/
-        UwH/+a+//vpfvxMGTfvM3svBgDGbxn//91GBf8fP+N+iKP2bSn9OIpAhzrO///mvQwh/d33bdOP/
-        Hts6+wx///OXIv85bvD32I7x+/+9/q/l1/7zX/8HAAD//wMAPe/DkOMgAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7bfdedf56918cfbc-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 30 Apr 2023 07:04:15 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '25'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - f2850337441001a8e5bd70bacb4dede8
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[72803, 18321, 25, 314, 257, 330, 61665, 82, 794, 314, 260,
-      330, 1342, 794, 330, 61665, 82, 498, 260, 330, 20489, 287, 794, 330, 20489,
-      287, 498, 260, 330, 10609, 794, 330, 10609, 498, 260, 330, 38096, 42914, 794,
-      330, 38096, 42914, 498, 260, 330, 82, 23635, 794, 330, 82, 23635, 1, 257, 2529,
-      257, 330, 5749, 794, 314, 260, 330, 609, 794, 330, 17943, 498, 260, 330, 2164,
-      794, 314, 1835, 330, 1663, 794, 330, 17943, 5857, 1, 260, 335, 257, 335, 335,
-      5832, 25, 2290, 11344, 37957, 25, 4153, 5832, 25, 44921, 8245, 13]], "model":
-      "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '594'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWw+6SrPm799PsbJunTcCKl2sO04iB+1G8ICTyQQ8cFDOdAO9s7/7RP87e2Zu
-        TMQOkqLqqad+3f/xr7/++rtOiud9+Pufv/7+5P3w9//4XnvEQ/z3P3/9z3/99ddff/3H7/P/W/ks
-        k+fjkVfpb/nvx7x6PKe///lL+O8r/3fRP3/93fe7HdujKCtm9AaQH459JDpOlmEvSuldKTb3hq4y
-        9EnGJcUlek0rkR107xBO5h6vIbBDk1n1aujmt2ovYMrrgXkvfcdXzeomQ4hDgdhOt+um6pZGCuyU
-        BTm4LOLjeNqO0M6XM9NKpUS1p2aqIhT5ihmvte7xp7SQ0USOV6KdmykZykC9QPFsK8rTi1583uWI
-        IYufKZUDUnBa3+gI0C5KeuJSyadFvr9D5/lnYsJcdZNT9xfwK2lJto7AQ74U/UDBMV0xw3hdjTkX
-        cAR4Ye5J9H1eHj9uJjzR/UoscbNJmsPSTCH11ndyDkaOaOmWNXzeF4PYRK66sehif8NOtwXBgsL5
-        rJ2EFqARl8yL37uumc4pwFHiI15eu9ZgXqX6iolpSJUjNbxJuWlvRTeeB7aPk84bLuJOAC4JAt5U
-        6z6cpEAS0DdeVOldxrvD6NmQdQcZi6el4A2rSDAh9D2JeOGq8qZvfJTQd6RvvPJiiN5zBLp+Lcnh
-        qhQevTAXQADxzXaX0SxWIjxOco6OAdur3tmbPEmrf8/LrMtG83i/E2Q4GZs1/sV/ctqdC6VVThiN
-        smNMt/KBoXZjDy/cdenNu7XsgmjJe+Ys7LwYVsjxoRs2IztICkrmzyeZAWvziliefEHNFao1nM58
-        w1yao2I+yPkdAu2wZYew2ySj40tPGEVoKdxHqZjmh6bLZBfLxN2ZhTHKPr7IaOEX5F4c02QcPmsV
-        PsFTZ2SZ9Al3F+IITSv45JpgEw1NXaewyQqH1hHwYjx0kwmLsoqx6Cm1MQPOffRslgYxcLvibPqI
-        LrTbNiD2ywu7WdpPoNykmeNGDIZwPEebFDovOFN5Mj7FuG6iGmK7Foh3saqEj6/lGiXX6kN2NZ2M
-        0SFhLU9IiTE3QrUTptjQlfmxSggeb3Yyyqd6RPmu8PFY7XE3V/PGBH1VAlX0Y9RN92tbyuvja2JO
-        TzPObueNikoLm8Q2kdIx9aM/FefxWpLt1a7RJHtvH6Rn5DMj1Hs+L24Eft9/9Z7M67WuL+kFMnYt
-        d4jT7ODP8LGTmJiNUxZzFCcWbF5BTDxFcrppWKq9Yjb5me18IvNJdNAC1SsTU4k/8+7P+3KV4kpr
-        MTt7rAkzGQK7m8gObY7dfJDbpzy+Hxfm0C4y+vjUl/BEzyvDghIiSsF5yp8u1r/5oxerTwxPWDoL
-        xrAtQjGdcYBhf8A6uSTbVVF+18N+Yi8sBdU1mZnRvNGAtDWLCvbyJvZZRCjZDu8/95/5uTpBPRgl
-        /ZS3E+rH02EG7F5cZhru2+CW20poI1t3RiJyRuO8TWx4ClFEtGR9DFft/T1DjitCuYSNbl6vXR1J
-        Y7v8xqfppmOS65DqiztzJ2NbSImX3mFfxxPRjtsP5+G5yBVto6+J+vSxwQVBDGCKDhHbNmrr0fm0
-        z2VooSSX+rUu2MPXAiDtSEj01hqDa/acQ3o/OjS1n+uEt/d+hMCZI6amn1s3730Fwz5dbOlGf5w7
-        blznWt4f9joWHIWhwa60HNTW3NEmKzJj+jBuIpGXhBmATIPdrqEEa0G0mCVybPBzYQvAy/uO3IIo
-        DUe42wISbCrSoxt9wnHT8icYxTpgztZ00Swk71KG2yvAqD3UHXMi1ZXp9nVgum0J3mfrZ3/ij5cu
-        a4r+ajo1OlXhgYoPsUnY9A4u4LOwI5YfrULaIA7gP+UF2/Gz5Q1y81IhPu5tRq7TOeHm7XGH3hFu
-        zNBylc/65fVEP73XfWgSnugFwHx4UmZMY5HMXbW35H0KW0LY3CWjlacUUPjM2Rbv7WTeJLKJwix4
-        MK/PT8YIy1GAjSxKbJc1STeii/FWzOzMmIalbSf6E1D5aBiUuccV5bPxWObQ5IFCDmPtG1/9C+Ap
-        xBFdNHNodFtDnwFp74xh6tYG/yhOiyxnETM83uqQVgGmsFoedOLOst/Nj3VykZeBPBJ87o5IvPBB
-        R6iPc6ygJOl6KY5y8CthSQ7qKU9GeFlP6FaLiJideiwm7THZyldfiU2FU8f3ND1BH4wxs4Ik5fzq
-        SCnK7PLFzFa2kkmTHROCOJuJE/GrMYWFbqHzECpE3ypLo+0H5wQb+eUQYl2Fblb8rQXztJ+YGmnY
-        GyMvo8onlxjR3GibdDs/NSG5fj4stuZNMtzs/I5MvzwzvDGWXpMKqg4VfeRky4c24SdZusBp6nOi
-        utVgzHdcmgC7/Zvt9ZODaFyNMdhXEcg3n4xx3fgtiI0rE/zBu2LyJrYHL58p2W6p7fXS2vNRx/Qr
-        UZch47xbbBayVNEF+da718/LhwSLtUkJyUEyaNqkVNH2LCfaMM5FjYdwrayF5w2P1+LQjettWgMP
-        Hy+azThAHEtqDPuXZTBXP22M/mpqNcIiKqnA34rBzstoBFaGS7JvFimvN7jL0XvYd+TxHDGi210v
-        gHYZXfL1T2i8QJZDUb1rtjV2M+o9uaCgRm/ObO9eJcNGb2JooD+SfSd6iBXhKYL7iI+ENI1UsHu1
-        GJF49TfERc+7x7OyuUMdXvbE8YlXjHftlcvr4jwz43w8GHMUjYGyRmhLdrp4Q/M8nu5QL3KZ7Zhx
-        D+f6ktnyJbAroo42C7v4yddoKQVb4qmnqeg11dKBXq+Y6PP2kgxFfh7RfFF1EgXnRTjYxi1FVyw0
-        7Lo33uGQvyIX9FCSqXQ7XfkcKmIJSepuqCQfaTi1XWmDU6UVM7erd9cv+25GX/9CZSQdDWY5qq58
-        3xcd3SzjbT9aoGD35BI//Wy6Yb8hPtq/TIMZ/iYyxnvxpspS8rdsV+4Szu9luFCqS+0wrzY5p0Ly
-        foMbsAudh8zlkruTL7/8p4vKe/BR39spRKapMvtS1QYXrnqOXMnqiFPMmldvE7VFX7/MbB6cUDdX
-        V4Beazie16WaCKUcx8hDlJJ9xdJuRFcaQe1GHgvzw6GQPp9kBG0/5ExbozAcvv0Dff0S3hzqSzjS
-        WqzhcM9SZnk0TViZ33N0LBMDX5iqh6uyWF1AScuWmSsIjH7dRC2KMyVnd7MRkwlvNeFPvR+6niWj
-        PIc5iPOjpgu0D9GYXlcUJThYsa26eHpzhnkJOxt57HCvYo+vHJki2FVHdmgQ+9NPFJXHIl5/+/vw
-        rV+lelAbizh68maXEBXlsvzByr2SvSmPRfrzr8SUtpU30v2HKpH5HPD6vROSRvQuI3y6kbGDGR86
-        etmLI0xorzKSSy7n/vviwtsRL3jdK07BSBIGgLQyw7I1b8I5Nu0IzevuQba2EXbD1x9BFq8OFOJM
-        SjiCVoLzPS2wNJC8YI9B0GURsw/eLPCBT1u/OSFr8ZCYq/fU4OelP8P6uDNp/u0f07LW+p+fZuq0
-        lMOZryAFpmcKXXa96q2wZMfwJJ7GdqsMiin29RQyZYtorphpMV0f8Qn8g6rQ03uaOn7aJDmKxtmg
-        i+OnLOpNfwmQ/BCeLDH7shtSP9JBX2HCHLV0C16IWQnRQVUZXrbCN962Do9A7JkaPvKkcYNjjZb2
-        K2G7g0zC5sOQCW+puBEVL3NjNLqLCXw5C0RPGqeT9HVfb0S5xbhaZdBN/iT08OlmRtReN40pu46m
-        0soeJc6sZIjKy9YEz77eiDlVFp/IPpNhsJBD+dVee715NiLYrl8WRbBtOF1q8RPVifMhh2dbdF3V
-        XWPY1IpIdrtQNqpqrwnoq4ds+yodj3/zGbJiwsR96KSjZY8EWDz8noXDc1P85ielbBYWXjs3BbH1
-        kFMIuvZGpZN07cYl3qhw3z8xIc+nyEd3o8pKt4IIs1g9d1MmtgKs83dEDp6mF1MWnmvI09UCi6+y
-        McaXf61lej1j4kZvlozUc9frPnR2TF/3XTe961CHkvsC25/2ntfeQzuHPIMPs/S1Z8w//ehG+UY8
-        x7XQ6oWOF+Xbr6moLhbep1L8SPnNk8FRF4pp92ru8Ej0gJjBZgy5q8SAYnWb0fG2vhljsL0AgBCe
-        MPQHzRvzQsbwfR90/s7n03lgM7JxgZl+jpuCa7acynLl7Qlu+grROWgoWp30E3OjVi7ox8AlBHYz
-        MatAez5Lbd+jeOelzJI9w5DkIrBhpRcq3vz83dePIxy2a+JsxkNBAecBfNS3RpIPq8P5eNT7nx9l
-        l9PYh2MSZwLUmrSmo3J/Iy6lhwjmJ+h4Ck9bLrCj6ioyPXjMUDSSzNfTQ4LTxsNENQQtWbXyK0XG
-        TmnIdrDEhBuCXsqZskPf+fsW8hcILoTcfTK3NZOE7oRXjxanS//lC1UxSGSzB1pLOV2v7TaZt42s
-        I2dcnSl8+cZQBvYJTinBdO3ddyE17vcenMdjyZxTlXat2vQ5rEnFCBl9D4nsI8Xw9ed4w43Bm1I2
-        vFEmNoSp0kPu+Np75OjsGYRsccCLwWmJjeR1mxLvUFfGXAVWD7cEJqbZZ8Sp8VjlPx5AdMVMu8En
-        VQ5DxF1ySJfEGx9NtoCZDXdmbV9pyL/9Qw7so8m+vIHXfXZ+w0vWE4IZ2iHeaav2xz/Yb97ru5uS
-        w/aCo5/fCufnwi8hzpY5sU7jPpw01K3BGe810e+71qBvrZthIz8c5pRalky4niSFRDJmrolwOHB1
-        MhUVLWzacjVBvNprkiLTak3Xh9XTmw7ZbYbandds501xyPd1Z0IfZgL76cXk0uyt/HiRAehtTC9P
-        KUG72iuiG7md8NnWY7CxnRGP3Eo0D9HtCb/82C1Siw9h4VowNX1Pp855hO/AEGx4tteRrnul6cbn
-        IVDRb341WIXD6UOjALbMjphTpKukf8/zBTwh0LFwtv1uVBX1Am7iN3iyzwn/w3cYXQXM5O+H0T+2
-        m4V8LG8GXfw3v0HiS9r/8qMYr5kQo13L9/Rd5lPCs9r04ezWOds+RCec+LP7oy/s8dU7vm8PMjrr
-        O4LXq9ZBws8f2bLwZvbi6iaNsn658DleE6yM+ZvTIGpHuD9IjaUgSRE/1mMJ93NEyF6PRa8vyqUE
-        P/8UEbkqaIHoHR6idPrqv56IP70vX/lEDp8HSVb0HO/BOx5j0s7CJ+l5lZ6U+KZlBH9OARp/8cRi
-        uiFWbmp8vCzMCxqOlyfTb2sHjafj8Q442b2Zeo4jxN6n5R76d53Q6RpPHj/aGP/p16Q6ed5qebNP
-        SNnONR61ru+o1+UXqKa7R/zb+uZNN7t9wi15m0wvZbHoMWls5A5uy8zH4oMmqnZv1D3cC13tjXcy
-        dFMXozKLOCHzLS3G/HNWIVDQjs4+OAmd9u/nL/8o/eCqG9nRtuGoNxoz0kveze2nCeDL4+jYJJhP
-        1VpcQBA7W/LTa5Fgs1dO52lDxe0l9AYQjzmKJnv89u97N6tNn6KY9Jx52bE2Rin285/eki0jrdFI
-        PNv/4T0K1WI0hvuljpQNuuJNkV4T2g/aBWX9JaOrx+Nj9LfDPofLW61ZKGwxF31SpTB2xZnYl8o2
-        hA50+ofv/PxyPcWejuoPPrBtggVvPMenk/I6nCKi48ExuBw/apSepAfbBmOI2C1atGh/yUe29RTb
-        GJPNMkJfPobH4+lQfOtfhp2wk7HEn3rH+1Y3lVdd7OioTSs+1fdSB+4WT6osuV/Qe6imEEMk0fi4
-        oqjf64YE0oW0mPa7Rfd85WoNNjocmVnW0PXf+toIhesy6307JFxzzxf4zrPErg+vbirF8YQ+Tq4R
-        e3Ftk8lpiQtCuyyYJ0ZOMi23kCITxRe6TAfJGKmTWsqwCyV664XBG52zv4Zf/x+F9B3OGUZv5Jhe
-        QDdwzfmEhukOU+bdiNfngpd+6xmSmu6JcWNDMgSPvYB6rePkxzOFN32tER9Si91e8d4Y3eiZojKb
-        Uqbbz8YYD7Zm/uZ7ugoi0s3EGGL05Wn4NJAjEjflLd7ooSCTX/8clJtTglCgN3PK3b5bm2cvgova
-        hORANZm/h+2h/vEZPAu4S/qiXElgBNGCdgoIqD+fribc6Ykw0/BZwj/3awAfcftgmvAIjUYVaYte
-        tR3T25fXjLfQGUHNUEZUQ+47nuqbO+Q39U2s5JqFjSZrJpBMIlSxCj0cH7v7jMS0qpg3dzWa2ta7
-        oMPe5sQpd33B37djrZz2L4+i/l7zH79DbMVDhrtmYczsNaWKl0fa1x+RcHZ382VTrdcrdhy3C++b
-        7ydwzm1Jvjy567OHsIDJn3u68W6SNwfCTGG9my/ferKNL29UgWQCweuAcGNKuJyDlj4+uKkW12L8
-        8bhQ/rhErSwjGbU8xCDYvcjcz8L3xMZKTn/y/zC/EoP2tHfl8z0vKGyqjE92XpnoN49k5yOE7BD4
-        sULTBoidbO2QM/mjbwRYvXGnxsAnofTkP3pIyKHh3bENI9gyNyKO76h/+ChoB8mhtHrsCoG3AyAV
-        gc2M3aSi+bb8rGF+LnRClHcWjtbT8mGuZIPW2fpkjOJ5YaGfvzXwM0u4V9k+uqZ9R6ybrYWTAlOp
-        mA3SKT97Gl9dnUUOfUJjCugdGVN/Du/oFw8DP7VkVU/3Gj7g3L/z3ux99UeVR0VtiHnGiM8PacxB
-        5G9CvM37xefV2CygbeITXhTbuVsNh9lVjO6yII4Xtrwb77KPct98E4+8Zo/J0vAGKxESCp80Lab9
-        bUORFYY2zb79s79u+7t8OPU7OimhnYiy6zxh5ZkhXURRkPB0cQFINo8Sw5fHT3IFe2CrKTzM0lX1
-        phXSfEjvocPsnTmHvTwn6Z/9F6vMc2M+Hl0K3Ku3X166RatgjFoY1eFE7G//548BdAhJlJCruqBo
-        7v1NjM7h0seLfvcsxh8P+/JLDEs4ePPydcB/eJx6LYaCxqYaIzXLBUY2lmbwVJ+eCDuH4scXDXES
-        pBTWt/ZK7NdxgZj6cZ/QS/mduEu4J3VQOhe4e9eKad/84k++CeTwxW1CwvDs8Qd7SsBPpUXcTXX0
-        poV5pChzrhuy/5Qemnva25DPw5J923DXKOurjeaDqbHj3S87Fj9uFthzeGSuExbhSIfIgrxJjnT8
-        +s/i8u5qubVuPd34xOuYs3pQ2b6aOXshY5UM2mNjw9ff09tXj2Zpv1kAGy8V2S8lDUnO2w1ka6B3
-        hitPQd/9ihZerLJwlqyPiXAKBB/oMzng5fd+87k59LJ6tHfsmL+sgovynENFXzndiG0ejgaxXLD6
-        SiSWvrh8/Z0bwxjgmrntZeuNXRT30D0Kg3krpzHGVN6v0eI03IjV1kPy4/MQC+AS9dznXd/rqqq0
-        VtKz/VLK+GiGdQlKurwycq9aPttoNcOP70SrtuE/HoG++kGsFeR8Plzmu/KnPjtD50JQahelUVXC
-        /O5dFCxJLxQIgQNzLu8L56ouBsp9LBdENdW1MWb32EZ32sN3fyYt5uapYeX4sM4/foT6XPvo8FiM
-        JyxHbVzwaFYXYLnXHYao7cJfP5GXQWp8eVvXUbYkJvzZnzk9w2R0o0uOlE3aMvvLP8ZMdbE8Iawy
-        LHwWfLyF2gi6m++Jdi5KYy6JY4LQWy5dCnXK650VjX/mFe9I56T1vcPzz35cnt/FcHRIUv+J9zY5
-        vZKRSM/xx0cof+7yZGp3kotUX0uZWx/GcFxv6xpoLeRUwob3X/zxGT3Y16/X4fjdDwZRrjE5FLbB
-        uSwN5R8+40caNaj5uZYQjaPBVPu5Dod88emBreISN9M+//JXw0eW1D6IdwkUNHF1stAkuBrD1aPq
-        ZrYkFkjP2MeT0b359DTPOWotdUmSbmGH7G5ne8V4B0uil4IbzptNL0GTNy0zv/2YO2i04c62DbO0
-        XZfwNO0xshE5MqtXIs5KyyzhO998+UfTTTNc3kpcWA7B5hWS4XKefXT08ImmG5Oh+hcvnGzfuKFd
-        5LGh62UoRnTB7JyLyVx2NxWaDivM3izFZG4QWsjOCp2oEn6owQPsPeVv/TMyoDQc1UVh/3gP+eq1
-        0QtMjZUwa1y2P7zaonfOvgwxoZztN5WGRHNvrWGt0iv58bhJe2zc334cXWzONe/FYLxDe81D7DeZ
-        bExhuaNggBCQw72SjUl4Z5ZyH/dH9uOhHZbUCHYQpMwr8CIpx+pYKn//TgX857/++ut//U4YlPXj
-        +fkeDBie0/Dv/z4q8O/4Ef9bEKR/M+nPSQTax+nz73/+6xDC301Xl83wv4f6/az6v//5S5H/HDf4
-        e6iH+PP/Xv/X99/+81//BwAA//8DALUBqRrjIAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0b9868dedafa62-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 22:52:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '196'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 0dc16b9c27373738c2c364d171678493
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": [[53380, 8245]], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '90'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaW8+6Srfl799PsbJu7TciCjVZdwjI2SoEj51OR0QREDlWAbWzv3sH/zu7u2+e
-        RCB5lJo15viNWf/xr7/++ruK8+ej//ufv/7+ZF3/9/+YryX3/v73P3/9z3/99ddff/3H7+//9+Sz
-        jJ9Jkn3T3+O/m9k3eY5///OX8N9X/u9D//z1N7ldGbNR1kfT59Co6Mw2K/aiVIi5YisGtOPUMVc/
-        L9re624DJJoVM7PigS5k25cPVXN7MDsSyvbbeMOAFt0tZSRIHC4+lqELC7w4EyLkQtT7lXUGOVv4
-        xP6aWj52jb5AVWAsmZY3H0Sr5pvJ3tn4sEc2Bfm0J7cMHo67IOq27vK+rnMT1MzcMUfRtvqg6h8N
-        neTdjm3dzTmezPutAtE+a8zpTl0+tXmwQGccXom7e9hxzz/GhBJtFxP7GR/ygdlYle8eUunickmi
-        US+7DkY/14n9El2PVpWkwUtRLlR+oi8atsc7hr47fYjrGEU+7dKwBOXerPD4dMN4bJMaQ4iMB9mb
-        m1gf40wI0CpbypSHFxSxaJpMFGYhJkTCu0jAbizA/dgTsn1POGdT4z7lNQ1Vtg9jFQ1ws314R+iM
-        uTUE8/pkmpwddJPpWvlup6phKZhH+0FcY0v4dE2eMvpe7IxoFwYxvSZnGazE3ODNEK50Zp8WGjpM
-        tkp2+15DvEpQAXW9jZkG6UYf3ru6QivPD/ellBr5NGy3AuyJR+jXMuS2t95+Awd4Jsw5Xl95Hwbd
-        E+KbOhDte3t443FRl0jp+RsPxKxaOhYhheubMyqHkhEJweK2kXUVUmYa/a4dJyTL0ETai5DqHSD+
-        3ZtX2DzXIj6v73c+JVluAnMblxk1nWJaDFYJJ1LdmOYPe1R56duACR0CYl2FQqeNaptw2eYRMQPm
-        eP3tET6gv9CG+dpRi1dppT7A/cCFHCIvb/ssUUxwk8/AtmdZ4s1d+GwA1+Gb7EdRjrg8ltqmzuQD
-        wevzHo2raAuKAlHI3FAq4u69rBr0FT4dHnl94PxjdqUUjvsvs7SQ5DxwVxu0DvYbgje3jLPLUung
-        IUU+cfinQM3xbT/lOKlbtr8GKh+Cbz7B5p0hsideFY+Lz2GA18dzsNBFEh9Ph/1Rvt+vI9ubG+SN
-        py96wuNSMaa3LEV0HW4GWJ7vBXFegeDxvD4WcAl0g+gtU9E0NFEF922ZM+sqGLpw3SkplKtsR0hr
-        brzWcqJwabx9YNawafVRJ4tSlkf0wTA9gmgKe/cI3mPPiLVqRL1TFqSAOy0NujwsIZqu1DeQpNgx
-        c8rUb4fruaGwWBFGl1k3oMnU8xT1eBMTs8F2PqRPHKCPVn6Y+0jktutWzhXOn+LK7Msj493KIRNc
-        hQdnvtMeeZ/trk+IPm+baFKwzId8lYToGB835IyzT9SwvU7RVf4qxDT6Tz6tjyyA62qpsX3XeS23
-        nChQxhe2cO+Xb70+HXZH8PNWwZNK3Zhd3UxFn1oumJExveW7zgvRtlXfzPhKYTRsW/sMZ+E90pW1
-        0bjItxlF5095pfLJtHU+7y/42IwRw1/e42F5OjcgnO4ZbSrrHo/nnf6EQBGfeFiIIR9MbROgJk1q
-        slOrJh8DfnyApDtXKms+4z0JvALlW+dIPC++tUMtpCkI09Wg/C2/9eElr46gYW+PJ2uRtVO0LFXI
-        /exKM3v34GyuX1gsjQLTy0WJu82zCmCR7XSCfdXzhn5bYPCmbUpX59eej6iRRDAcGfDiIUhtt0mf
-        A0Juz9m2GpOIBmWVwZCWDtlnuzQfF/ryjnAgIaY9NIcPr+pWwS29Ueb6XEYsV90BZVp+Yq7mE0S1
-        10gRvS8LZjfJSp8KczVA0Dp3grvnLZ5ulWfDnRYG0ZWTnHfiDQAVOpTMO6EmZ4m6TNGvHsz1XUYs
-        pdCgyNVXmN3Duh2wRAtA7aaiIB0/Oj0HYMPwuK+IJpgD4mW9esDyYZjsmLG8HdtLGkKgr2MMpn5t
-        xzJ8GMgf6hfzkjDxBmEfYpg/01zBaV7fuF0isxovTE9I4E3L1klhlaUhUW1pp493Kroo4EqNX30U
-        o+5rtnd4UKDEw+2kj62JTEi8RUB52fke1z/1A71Xpkds32/y7iahAlVFGLJ9/Yh03l6jFH56uniS
-        UJ/S1beCp4QxFazs6fGuWWOE5PsNL16NO/+eKgD11j/xNymZ3n3y8AHlVz0yw8qe+mSVcIU4aVvi
-        qcY3pqbeZnK08X22FyWid3EvdZB98I3tGrTJ668f2UjvF1ti9QHmfBHVRyBJoeH+cPX1FV4+j+iz
-        uZ7I+fY+elz/vgB9CqIxXVvsou7LFAzj6RRieLnHaBTYqP72G/Of1qsdy9r1kYmeMZ7ls6XW8drB
-        oR5vVHqv4pYdO8mWvH14ZqYXdmioE/kK1/fI6DrnUzusrFsg2zFdz/p11YfTQxvkJn3VFJ1Q0/LI
-        SQPIHleXaIj6fJA/moEGJ3DwtOdZPqDX1lXCJbsQkrNPTvfkkKIa0RcxxaDTh8RzOoDUd9lW6Ew0
-        ruqNAZ0aJMSmuzHm46BfYdtlAzF0/uX9dHyVUrnFBc7rA8/H5CzfwXkqI/Eno8trIiVXpFaEEGsn
-        t5wNn4uNziE6EsLTZVzb7bBBK0k8UGm01jnjhZNBv9RqvGg76jVHqTeRVxRnZl6OQzRY33UDy1Z/
-        4Y15cVv6tc4VqjhpmWc/cT6cl3EFxeqr4+ztb9rxfbgfkbdmGtk367alk5U3EIXXB934vpsPheqU
-        yHiahBjudM65p8gYVT6EFJDURZ3TNQCU2Wu2N8ftXE/CHbbSUsZrU0lbdqpoJ5dVllPhK4Vxj89+
-        hrZvp6PA1jbns/+BJlW3xAlqJxqWt7cJOC+WeOEqojct1t4d1Bt7/tH7qVdTgM2VdlSe/dv49WMb
-        9B62dBLhzbueqU9Y7y2PkfX23Q58cH2lDByF6D0U+a/e0T3fq4wU0rGd0sTTYMdEmTn9K47YLj6b
-        8mN/PJD7YyeiuloVsLkl0ZauBTvPh1d1qFB2phVT0UuN+HePr+hCM4E5/GPwLhGiFOonVYjxsr7R
-        oLdvX7m+jxad3v4mn/tHAGa3aDCkeyeiZbGnyLmKXzzaEfM+psI7cEwnZ9aGJPm0XVwCOPjjmu0l
-        M+TjSjsOKH6LSwxJ9eZjZd59cBfTB1eWlHjTJU7vSno6XJiviwKf0lxfoHOzj+b9zHReX+QKXbbv
-        CI+hjdEgHx8bqEVVISTJNI9P6qaBfXgAph/2fitW1agpg15+mUPliI+R0RRyAsaT2fmzjH96qFhv
-        JtBi7dF41LpPhdh74RKzrd9e9+snd7btiJZ9R31Q77ErF6410PuVFjE/ZZ8JnWRrR1SqFdEwaHsT
-        tEezoAthLFu+aX0fihRsYteRGfVDkcsg5HKEkS1O0RTTboH4JzwSp7++o2nYOiJszG2Fryx1+MwD
-        qryVFJnsrsc9GhVNlSH+pm8Ky3fV8gPFE5rvM9WvUNRl24sP6pT3mFlqn3f4vQXw72uKFztbjBls
-        iAiyaG6ouOwrbzpmIvzhGesyMn3qzHqD1q+BMM31ypiPplSg5pAGLBRhy0U7MGf9ubt4LfcuYuHh
-        0iHZ3wlMpc4zoq8gDSAdhoY46/1bH/PmIsA9JypdJvXD49HDA7RNO4Ml9qLg43HxLiEZhy27D1M7
-        r8cdg9FvK6I7ytHjr10mgOxVPjvoktUO8/5Avief6JqtRH26GlMA8/rhNM94PK4t20TblBrMmrQb
-        mkZkC+j9JJyWSFvrU4JIB7MeES0jfTyM4RT+4QkhfrUehRt6gG29C+JH9oD6IqvucBztGp/UoORs
-        We5UkGvrzFSFL3R68BjIR1H08MB97nWF6abyn/tXb+v14qevULuWRDqeZQl1zDZVGFnL2N5CjHcy
-        2vigLaIY97pTIOavxxDiznkQLwkVr4eUPtDiMnyIPrYyZ61Fz2iuJ7wUvKBdCUxSYeYb4kSlEFXF
-        lWK0l+yImZ/8ko/CzZWlLXljTNd0bMf29aKotY4q274n2vawfpSA3oXHduYKe9PJuN3hoqgfsosP
-        G0TjiyhCPa4bog+OHXNlCO7KOJ0FukFu3fJFtwcYz+s3HqtGj1Z3KtoAKXbxcB+qeHgv0wp++rmQ
-        F67O0/NVhZkPiHU/i+10U5mIlkqXE3xwJU4TZHUw+x+m7z9DNLyvuyNcveUCS+v92xu87FLCay3u
-        mf1WJX2qfWeBYtyF5CUPa94eywH/eItyrXznvEfFXdHFISBmLxb8j16t72bPvMTTvb4BPEFcqiEj
-        lbPXB93Yb2C9DV7E21dKTNXYvMJrv3KIZ3V5PChYEJGTezs8xHanD4/vZoK5n7AQ0Y53wbedUPHd
-        hcSr4IGmMepT6TB9KmamNxsNK7HT0MwvONtuJH36UmmBzhfjyw6xgtt0M+oLcKWdPvNTihhlWQaf
-        w3uBefqq2mFd1BiwHy7xr3/R8JG4SPUZ0HhfJdEYxUGn5N5rZFqSaFFHj2QDi7QUCDa91pv5vkCx
-        my3p9A01T5z7pVRZwYAX21vqMVs5nEEZHiVxQcB8rK+KLOtrssECWbUx3ZHPFcrjKZj7o5rz/LyR
-        YfX19sStVDUW0iygytspNsw4NF48rWwjBbeMl1h4ZKq+6hoPUBU/dBYFKxuJx0xcQHnXJuIWV8Ob
-        uuSq/eGR4RrG3rRb2xTabfUkqu4t9dqd7p1sF28Ty/SocPZGlzvk2dn58VPbVOjYId0LFGbNfqqL
-        +5EqdkVvVJQ2VTw92V4ABy0jLLyPnjfRfBSVU7m4MYtGeTsZ3fEB5LR/sO1Hs7xBSwFAq6uUPuZ+
-        xW3ldoSzkI905X0lnSc0miDvqhLLkbqIG6HgBXwfokGs+ObF44UmIdD87M1+q+SjVOIMITf0qGiS
-        qz6GkhiC8bkS4pNUaKnfrw2Y9ZfM68+76HJ5wHUnCmy3aTNv+JrtFe2dV0/FXiwQcx8XAYXIfBCr
-        eupoBKwN6JneVeIYdInYKlphmPsTc78n5lGWbDY/nmZG0mHU5Y+hgdm/MVP5PvP+Xq18+WC7wIyq
-        0FvuHdMrcD7tmFWZ6o8PMjk3RZE5XKnayTc+AWgb+8Cs+NZGzVuNFz++xdJoXdpJ1d4DDHrxJVsv
-        uHtzPWRw7/OECvg+ofGzMky4VOuQWR5r8zrIvgGUvfdk7uxfum1rH2HWbzyd9w4SnuY6AB2kO2nZ
-        vfFYQqMBdpva+cOn/CtnFeTZ0cErmMAbGssPkb32XdwImo6GsxRSCBThySKzR3ldq7dA5hIizFPq
-        MZ5A359hcZk+7Od/uvNheYePVnyocH+I8fy+RaRt3MPMRx+PTY32BMsIG+I3Wq1zVtcF/NZHlvyp
-        ZU8vn2BnZwhPy7PjibW/BVQ+/R3ZSuKprV/UuUJ9NzWirraR1/OPP6BfHrXzvpLHn5KqobBEzpy3
-        xREdkS2i84YZdPxolj7u9VRUbk2YU7ToSm9wlav9y6+Yx+6NzkC8HaHSrYR23+Sds09ypzAs9JA2
-        J7PSR8tONXhmpzWun+YuHtTRCeDZ4Y4RxLt8+L3v1fO8+NWP3rBkIwNnxci0tR7zYWdLGFL/ZTPC
-        Rkfng2gclc+JHX5+PG+QmGVKW3B31vMgHl/JA8OSX01GQInbMamfBvQC9an02R29YTHtO/SrD4YD
-        0xuwVJZAklLDq8Vmlw8ftDTATVwbr+tqatvK2j/hdnieyH4NOeLSavNQ5u9P22ql8dk/iIrImi2Z
-        81jeXy7MhmMt1n/8MLfu9hMu99ObSqHx5vyzWp7Rn3obxE00ys7rgcwOGmZMqRJToeAlzPxOl0Zs
-        xqu9Xglw4+aEJzk6RjRPWhnoUbgztZxaTuNd7KJfPnj5xpjzilaDfJXdEx6er2fLr0G2gPxVG8x4
-        1HedG68qQ3O+wfZe7utsznfQzL/M3Qq+PnT70gRnJTjMCY0tGossvUK/VGumjo3aTrOeIxdXlz96
-        9nu/cmryEiN2d/X1S1AKFAuZzozVsEIcRfYTwtfXIW7mqfHgpbUJb7Q/EUtR8pifvXUDki3IVNlS
-        P5aukpPCz496hXtAvCmSK/z0wi0Giw9OlwEcNgeXWUlJ9EkdIQXxEsWM7D4rb/b7GHnKtSCE3I9o
-        2rziTPrlu1a4nPO7c9P9yRdMk2w8pmhgAz5/E2aYapvToEwzFBurhM37PRrO1SeVnsampxs1a9Dg
-        KoEL+en8xYvPq8mHOpmuyp4/RzbnLy3DxtEA7AdLpr+EdcS7ZukjZJQ1Md/COxqtcRTQuiqedPFe
-        02hkt3UlN3jlUUrBbMtHVahgN7giZv/cesLsH1G7fmKmwqHNR9tICtSk2nb+fnL8vXxvBhikfLKZ
-        j1H3W785r6Sw6ireA3YH6ee3z8KKt1xcY/PHl2wH00MfJP3bIWNJO2Y+o6XXB8aWQi4qBtlTq/DG
-        OLRMAH4U8UCdRdxvnccEiQcBe34sk08yIRg+rDTpMn5co6EfREAG36h0uHpvj4XVToT5M9tZm+yX
-        dzUgJa8VnlhXx9ORdzbMfoGYsPP1OX8Mf3nIH32lP17xtlKIr29V8liirlPwQc3J67B8xMNhuqpw
-        uj4rPG5iRR82a0NGO219w4PSFfog3oQFyk1BJPsvITHHJyeA2Z/RrlgK8bRITwHsk1bFt9CL+QrS
-        8oEKp7Lx5bX95tw7VncpfH0ctrWc1BPn+lB+ftDbvLR8/eONHx9aO9lDnX4X1D952dZfpPr4zkUN
-        YJ/vmKHHhjfUQpWhJcMTMXgeeoMA3QIam27xuhC/7Zw/qvBw7AUzlp9VO/7y9tl/4XSJxfaXl8BH
-        3JjsNb/vds+pgHJkX8iuoCuPXpPnBhG09Sma+0198z4hfC9uRox4jdH67fsNgKRdiSO6fjwx8ZT9
-        /B1u2d31KH4rGH58uqVrE/HooS8A27uObDdHXec381JCsUQpXTyEW56el3ED54v5ZWQZV3wYfemI
-        JlX4ULR/5zFr2baBaeWaDHdPKR77/XGD6p3MmNdOez7MeTpKcrbB1zoqo498NxpIxYdPwuW59qbf
-        PISJnx1RM1VFYvn0B/C2KGT6ejTi8WHu8M8fUtgcgmhM6rMB67VBmOebDRqQHWvQd5cPXlpq3xY7
-        LNuArcbA35Nv8U7ajhjCkXz3Y9XkcbNIkwAitvqQbfxxOd3Y/V2+YR5gYdaDPD1f5/V878g+uZN8
-        Yi92R7Mek33Xta3wke0CurcsU6nqh5gvU9+UdHTz8E1gEZ8MZVsBeZkHvMRBqU/T8zAphb4oiZdf
-        zXy6uNxHRSgtmeVPaVvN8zY49bt8zm/vfDq69+PPz/+ZH7GZn8EZK5GOikm9eptqG8iMbUGXPH3F
-        /aotS1iQ24LC4sn59FpyDVxjzBieWuBjJ0su2Jpcs5+/44cuCJSZj8g8r2rpiFRRnvMndpFPX53R
-        5+oM83yGuYyd417r+gZNqvghhlB+9cnv1AIZq/Wa4PboRvzS3zVY7ssTs1bNWW8gmjKQR+lDLNti
-        +Z/5BGflyHb8tPyT78MCw5kO3ZLk5W0xBsrn1B+IaomDN5DHOoWX7XyxpIPQsrm/ovG8etPJOJd5
-        1e2pCdMAnC610yMf7vn+AY9H1ODpkG3mPHIwlHVcwG//6axf5U9l5kc8Zd/Df+UJzlX4Mlcm32h8
-        UeeOnoS4mC+GyBO3LSpg3LwWtFfGnI9NnrkQ8HRL/PvViadyV9lgriObbKPcigRfl1UQ7aNGdqja
-        6/1vXvCM7s953lujztSGUDGu154d9knC26/w7v7kkzMPRTMPCiAZ9Zfs/fLtDfHFK9C1rQqizvwy
-        0qvjgqYd3wTjTxiPhz7O0C2NKW1+vCMTywc/rxX2mz90Uqtryno955XDouEUDXUJ5JVLlItnDw3u
-        CUQUOcWe4Xl/T2GvnZHqh3/y1qjs1QqUMvAUKvcu8djv+87+gWCHW9GUrlgjK8H5Suf5V8yPu5MI
-        VmJssKQ4yKPe+3FEqtirDL9CEwnrPTLR1rkbVFk9xXyQdEZRHolXzKWFrQvCPvShacX+N++Ixpf/
-        1UCBQ8hILi7z7rlTB3mJtwqz1jvajl10EgAHz4j8eORPnrclOaZLt6p5mSf5RgaiH3Gd0G0+zjyA
-        +mZ1xlKEh3zgjROCWfEL2w9HC63G0axgKFlEIcidfHTIVoS/f6cC/vNff/31v34nDMoqeX7mgwH9
-        c+z//d9HBf59T+7/FgTx30z8cxKBdvf0+fc//3UI4e+6rcq6/999VTy/3d///CX+OW3wd1/198//
-        c/lf8//6z3/9HwAAAP//AwBim/ij4SAAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c0b986ab8dbfa62-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 01 May 2023 22:52:32 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '195'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3000'
-      x-ratelimit-remaining-requests:
-      - '2999'
-      x-ratelimit-reset-requests:
-      - 20ms
-      x-request-id:
-      - 208e3672e7991aa80472beb0310e43d9
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
index 82a4f1fa..dac79d49 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
@@ -2896,4 +2896,472 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text; include any information that can be
+      used to answer the question \"What is the price of the book?\". Do not directly
+      answer the question itself:\n\n\nLITERAL TEXT: \"\"\"Books to Scrape We love
+      being scraped! Home Books Philosophy Meditations Meditations \u00a325.89 In
+      stock (1 available) Warning! This is a demo website for web scraping purposes.
+      Prices and ratings here were randomly assigned and have no real meaning. Product
+      Description Written in Greek, without any intention of publication, by the only
+      Roman emperor who was also a philosopher, the Meditations of Marcus Aurelius
+      (AD 121-180) offer a remarkable series of challenging spiritual reflections
+      and exercises developed as the emperor struggled to understand himself and make
+      sense of the universe. Ranging from doubt and despair to conviction and ex Written
+      in Greek, without any intention of publication, by the only Roman emperor who
+      was also a philosopher, the Meditations of Marcus Aurelius (AD 121-180) offer
+      a remarkable series of challenging spiritual reflections and exercises developed
+      as the emperor struggled to understand himself and make sense of the universe.
+      Ranging from doubt and despair to conviction and exaltation, they cover such
+      diverse topics as the nature of moral virtue, human rationality, divine providence,
+      and Marcus'' own emotions. But while the Meditations were composed to provide
+      personal consolation and encouragement, in developing his beliefs Marcus Aurelius
+      also created one of the greatest of all works of philosophy: a timeless collection
+      of extended meditations and short aphorisms that has been consulted and admired
+      by statesmen, thinkers and readers through the centuries. ...more Product Information
+      UPC4f19709e47883df5 Product TypeBooks Price (excl. tax)\u00a325.89 Price (incl.
+      tax)\u00a325.89 Tax\u00a30.00 Availability In stock (1 available) Number of
+      reviews 0 Products you recently viewed The Nicomachean Ethics \u00a336.34 In
+      stock Add to basket Run, Spot, Run: The ... \u00a320.02 In stock Add to basket
+      Critique of Pure Reason \u00a320.75 In stock Add to basket At The Existentialist
+      Caf\u00e9: ... \u00a329.93 In stock Add to basket Kierkegaard: A Christian Missionary
+      ... \u00a347.13 In stock Add to basket Proofs of God: Classical ... \u00a354.21
+      In stock Add to basket\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized
+      as"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2507'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SSTW4bMQyF9z0FofXYsJM4P7NL202RZtEg6KJNEWgkesRaIwqkxo4b+DS9SU9W
+        aJK46E7gz+N7H/RsyJvWuGCLG3KcXdxcJd/7m29fhuvx83139+uj+3qyfn+xvCofTGO4+4muvG7M
+        HQ85YiFOpjFO0Bb0pl2eX64Wp5ery1VjBvYYTWv6XGan89WsjNLxbHG6WJrGjGp7NO2zycJDLo+F
+        N5jUtKvFWWP+aR/ry+WiMYWLjcfS+fLs0BgXmByqab8/mwH1TVY4ommNVSUtNpVqklPBVANY8KhO
+        KNcTwGsoAaFj3sCDuUVPxdaGPhjo9nBrxY0K16NgpFEb2AVyAUjBbi1F20WENQvkUVywisAJ6oGB
+        YYedUnlp77ADdWIzpb7OZlbUOdwHhCzk8D8bpPDn98lqfnnVQDeWqfEmtrOSFEqwL+VpWcEmD2IL
+        pV7BCoLY5HmIe6gE+oR+mgh2i5AYBG2EAW2i1L94mM7yeo2ioJmEymgjCK4jugnGtI9PKI4UFTxu
+        MXJGXxFVH3c82AQ4ZBSWaTgHiqycA0oDjrcoNXrhTE5BRxfAKgwsNsKWpIzYQBiriEz4baSybyYl
+        T1tKNSpvyWNyOIdPpUJynJQ8CnrgdETYT79RC+xYNlqrRyv7VwwKHWIC6weStwyUNjX9RBKtr+8S
+        hMc+8FggkBaW/dwcGrOmRBoeBa1yMq3Rwtk0hpLHJ9MuDj8O7/4CAAD//wMAU2wM4F0DAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4f548931119-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:38 GMT
+      Function-Execution-Id:
+      - pbmeavwjmg42
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '13515'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - ab314b2e9bb880724cb82a80580d492f;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '88914'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 724ms
+      X-Request-Id:
+      - fb2737f00b14403a74927018f9a97197
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
+      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: a
+      description of the book \"Meditations\" by Marcus Aurelius, which is available
+      for purchase on a demo website for web scraping purposes. The price of the book
+      is \u00a325.89, but the website warns that the prices and ratings are randomly
+      assigned and have no real meaning. The book offers spiritual reflections and
+      exercises developed by the Roman emperor and philosopher, covering topics such
+      as moral virtue, human rationality, and divine providence. It is considered
+      one of the greatest works of philosophy and has been admired by thinkers and
+      readers throughout history.\n\nLinks: [''Books to Scrape (http://books.toscrape.com/index.html)'',
+      ''Home (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6625'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7SUS27bMBCG9z3FYNay4bdjbYsujHZVNJtWhUFRY4mxxBHIce3A8Gl6k56soCy/
+        lCyCFlkJmsfP7x9qdECTYYy6UKKruuzNPy+sfE8n43w5/DKdcTFbLstP86/y/PTxESPk9Im0tB19
+        zVVdkhi2GKF2pIQyjIezh+lg/DAbDCOsOKMSY8xr6Y37055sXcq9wXgwxAi3XuWE8QFrx1UtK+EN
+        WY/xcDIbRXgVvyRGk3mEwqLKa+18sDhGqAs2mjzGPw5YkT8LOy4JY1TeGy/KSsBkK2SDhUNiAQAS
+        lIK3eSE+wRjaYJugvYRggkso1C+CNW9tBlIQ1M5oAl43Lynzpg9LsEQZCMPWUxPfOSO0El6tTUmg
+        uaqUbQqaxI2OMChoiqyqKIPU8c7TakepN0J92UuQ18qGHnvRF+U3q3ZOd/qX2Lmqn2B068yR8myN
+        zc/2/hn9ZgRvsvGtIBu1Zv7fR10qe7LQg8f3RU8Sez3j7cQdYO2MGG181R18pTYEfutCpxJYgqoa
+        YGPzRkuzc6QFjF2zq1TYi9AWUg12c37ovESMh5RCe7uZYOydUmbCg91zd6i+JrU58+1MWb73V9HA
+        v3bXJ6pjdN7U9sQXixqET8B3hB1fyuXdHT8lQu1V4pWrv9Xp/hr+/B5N+w+LM2wD3HIn9ojHCNfG
+        Gl+sTjuHMXrhGiM0NqM9xoPjz+OHvwAAAP//AwCkoYsdiAUAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc55dc9dee1ad-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:12 GMT
+      Function-Execution-Id:
+      - pbmegdid7glm
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '30081'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - a847bfe80cefa41d8c90162f62421032;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '85948'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.701s
+      X-Request-Id:
+      - 2138028baa9d1b5c4544e7197979eb65
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are browse_website-GPT, an AI designed to use the browse_website command to
+      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
+      the question ''What is the price of the book?'' and write the price to a file
+      named \"browse_website.txt\", and use the task_complete command to complete
+      the task.\nYour decisions must always be made independently without seeking
+      user assistance. Play to your strengths as an LLM and pursue simple strategies
+      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
+      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
+      the question ''What is the price of the book?''\n2. Write the price of the book
+      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
+      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
+      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
+      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book. I will then write the price to a file named
+      browse_website.txt. I can then use the task_complete command to complete the
+      task.\",\n        \"reasoning\": \"I need to use the browse_website command
+      to visit the website and find the price of the book. I will then use the write_to_file
+      command to write the price to a file named browse_website.txt. Finally, I can
+      use the task_complete command to complete the task.\",\n        \"plan\": \"-
+      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
+      and find the price of the book\\n- Use the write_to_file command to write the
+      price to a file named browse_website.txt\\n- Use the task_complete command to
+      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
+      the correct URL and question for the browse_website command. I also need to
+      make sure that I am writing the correct information to the file.\",\n        \"speak\":
+      \"I will use the browse_website command to visit the website and find the price
+      of the book. Then, I will write the price to a file named browse_website.txt
+      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
+      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
+      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
+      "content": "Command browse_website returned: Answer gathered from website: a
+      description of the book \"Meditations\" by Marcus Aurelius, which is available
+      for purchase on a demo website for web scraping purposes. The price of the book
+      is \u00a325.89, but the website warns that the prices and ratings are randomly
+      assigned and have no real meaning. The book offers spiritual reflections and
+      exercises developed by the Roman emperor and philosopher, covering topics such
+      as moral virtue, human rationality, and divine providence. It is considered
+      one of the greatest works of philosophy and has been admired by thinkers and
+      readers throughout history.\n\nLinks: [''Books to Scrape (http://books.toscrape.com/index.html)'',
+      ''Home (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
+      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
+      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I have found the price of the book. I need to use the
+      write_to_file command to write the price to a file named browse_website.txt.
+      I can then use the task_complete command to complete the task.\",\n        \"reasoning\":
+      \"I need to use the write_to_file command to write the price of the book to
+      a file named browse_website.txt. Then, I can use the task_complete command to
+      complete the task.\",\n        \"plan\": \"- Use the write_to_file command to
+      write the price of the book to a file named browse_website.txt\\n- Use the task_complete
+      command to complete the task\",\n        \"criticism\": \"I need to make sure
+      that I am writing the correct information to the file and that the file is being
+      created in the correct directory.\",\n        \"speak\": \"I will use the write_to_file
+      command to write the price of the book to a file named browse_website.txt and
+      complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
+      \"\u00a325.89\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
+      write_to_file returned: File written to successfully."}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '8003'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6xSTY/TMBC98ytGc06rlm7bbY5wqrggBEiIoJXrTBMTxxPZE9pVlf+OnKabblmx
+        EuLoNzPvYzwnNDmmqEslum7sZP1hw1+L4iOXd/lm3byffbKHu+O7qpXttwoT5N1P0jJMTDXXjSUx
+        7DBB7UkJ5ZjOV/fL2eJ+tdgkWHNOFlMsGpkspsuJtH7Hk9liNscE26AKwvSEjee6kQfhilzAdL5e
+        zhMcya8LCQqLsiO0ebvqEtQlG00B0+8nrClciD1bwhRVCCaIchJtshNyMcIpcwAAGUrJbVFKyDCF
+        ARwKdJQIZriFUv0iGDxRDlISiArVFLaglQPHB2gDPeEPl9Y4UyuXgzCEshXI+eD6NlWQk2mGybWk
+        JxXYGVe8ogu8h71xuXFFjzXeaIpgfOyYK4iaB28kdhiJ8gr2xtL/dtxY5c5mJ/DlH/hu6HS0rE2o
+        LwtwRP1orSqC0PqooOQvMibAjmLqNlAOmr0nLfaxX8jTaC89to6+Gs8Neft4GzM0pKrXPqXfubG2
+        X+4LWaENlw970fs0w7Nml1yOc6j8cZtO1XS284zpxrXyxe1ZX9/ZmeBztD6mCa3WFMK+tf0Wxslu
+        8Ja5DrsE98aZUD6cmTDFINxggsbldMR01v3o3vwGAAD//wMARwk3SV8EAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc64648bb10cb-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:38 GMT
+      Function-Execution-Id:
+      - yvvl2c4sntif
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '18885'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - df845088a79f4f2e92c980eb9a6e2e52
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '85933'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.71s
+      X-Request-Id:
+      - d91688703794f0cfd634cd4bd337530d
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
index f5a406c3..c45b71c8 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
@@ -1350,4 +1350,231 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the write_to_file
+      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"reasoning\":
+      \"The task requires me to write ''Hello World'' into a file named ''hello_world.txt'',
+      and the write_to_file command is the appropriate command for this task.\",\n        \"plan\":
+      \"- Use the write_to_file command to write ''Hello World'' into a file named
+      ''hello_world.txt''.\",\n        \"criticism\": \"I need to ensure that I use
+      the correct filename and text to write to the file.\",\n        \"speak\": \"I
+      will use the write_to_file command to write ''Hello World'' into a file named
+      ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
+      {\n            \"filename\": \"hello_world.txt\",\n            \"text\": \"Hello
+      World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command write_to_file
+      returned: File written to successfully."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4608'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7RSy27bQAy89ysIXnyRDTuGnVhfUCOHFoiLBqgKY7Oipa1XXHWXip0a+vdCLyhN
+        XwjQ3hYccjjDnQuaFGPUuRJdlHZ6fbtxUu5MOHx72vo7qdanbHl9f3/1jm/fY4Tu4Qtp6Sdm2hWl
+        JTGOMULtSQmlGC/WN6v58ma9XkZYuJQsxpiVMl3OVlOp/IObzpfzBUZYBZURxhcsvStK2Ys7EgeM
+        F/PFJsKRfAQ26wjFibJj6WqxqiPUuTOaAsafLlhQGIi9s4QxqhBMEMXSyHQsxI2FS8IAAAlK7qos
+        l5BgDH2xB+gsTTHBLeTqkSBUWlMIh8raJzh5I0IMk7dkrYOPztt0AobFgYKDsQSsCkphkjf4/tTg
+        MznLZAa7nIDpLKBdUShOQRxUgcAEEBWO+947NfXxnVOLzhKMnqv0pIJjw1kndde3gaevlfEUoGh5
+        Grn0erHQysuJfyEE7gxrgj8dR1zb3myI2tc/s11axZ3jKXwIY9/I8mzLX9m0N2K0CcXw30zUThKH
+        yjdzSmALpXePJiVQ0F0dDs4P5Iaz39KHktRxoD4Za1vfr5bcUdbRkNy+/afgNn/ZbfuB/oUo5bOX
+        mX+eqP+R/MFCa6N3k3CNdYQHwybk+243xhjElRih4ZTOGM/rz/Wb7wAAAP//AwDKh13FrgQAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc6e12bd2e1ef-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:18:06 GMT
+      Function-Execution-Id:
+      - yvvlex8job2h
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '22621'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 827e911ff253a9d12783cb62e669dc20;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86005'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.663s
+      X-Request-Id:
+      - 4d357db894485be6e259654a899f2e57
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Hello World\"\"\"\n\n\nCONCISE
+      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
+      0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '252'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOQUvDQBQG7/6K8J03JSVpmu7RU7GIXooHK2WbvCarm33L7qsoIf9dClqvAzPM
+        BNtBox2MtGNw+Xq3CQ9DXFfPj09Oim5Xu+3+u9oO+/tPhgKf3qmVX2PR8hgciWUPhTaSEeqgl3Wz
+        KsqmbjYKI3fkoNEHycvFKpdLPHFelMUSCpdkeoKeECKPQY7CH+QTdFkr/KdvuFEQFuNuoKpmhXZg
+        21KCfp0wUvpLRnYEDZOSTWK8XAfZC/nrvMmSveazPhKJ9X3G5+yALTnH2QtH1y0OwKxwtt6m4RjJ
+        JPbQSMIBCtZ39AVdzG/z3Q8AAAD//wMAv00f4UIBAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc7839fad10e3-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:18:11 GMT
+      Function-Execution-Id:
+      - pbme9het6dvt
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '1227'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 4a9b8edee07c9658c887ffc760c711e6;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89466'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 356ms
+      X-Request-Id:
+      - fb5593e05606c34e2e9461ff82b28747
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/basic_abilities/test_browse_website.py b/tests/integration/challenges/basic_abilities/test_browse_website.py
index 1afe10cc..4befb059 100644
--- a/tests/integration/challenges/basic_abilities/test_browse_website.py
+++ b/tests/integration/challenges/basic_abilities/test_browse_website.py
@@ -1,8 +1,6 @@
 import pytest
-from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
-from autogpt.commands.file_operations import read_file
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -13,11 +11,11 @@ CYCLE_COUNT = 2
 @pytest.mark.vcr
 def test_browse_website(
     browser_agent: Agent,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     file_path = browser_agent.workspace.get_path("browse_website.txt")
     run_interaction_loop(monkeypatch, browser_agent, CYCLE_COUNT)
 
-    content = read_file(file_path)
+    content = open(file_path, encoding="utf-8").read()
     assert "£25.89" in content, f"Expected £25.89, got {content}"
diff --git a/tests/integration/challenges/basic_abilities/test_write_file.py b/tests/integration/challenges/basic_abilities/test_write_file.py
index 36a97733..1b0198c7 100644
--- a/tests/integration/challenges/basic_abilities/test_write_file.py
+++ b/tests/integration/challenges/basic_abilities/test_write_file.py
@@ -1,5 +1,4 @@
 import pytest
-from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
@@ -13,7 +12,7 @@ CYCLE_COUNT = 3
 @pytest.mark.vcr
 def test_write_file(
     writer_agent: Agent,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     file_path = str(writer_agent.workspace.get_path("hello_world.txt"))
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index 0bf7bfe6..e5275071 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -1,5 +1,4 @@
 import pytest
-from pytest_mock import MockerFixture
 
 from autogpt.commands.file_operations import read_file, write_to_file
 from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
@@ -16,7 +15,7 @@ from autogpt.agent import Agent
 def test_information_retrieval_challenge_a(
     get_company_revenue_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs and checking the output file content.
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index 99243a10..159f9dfa 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -14,7 +14,7 @@ interactions:
       below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
       \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
       args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
       \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
       \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
       get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
@@ -22,7 +22,7 @@ interactions:
       list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
       Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
       Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
       \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
       information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
       Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
@@ -42,6 +42,10 @@ interactions:
       which next command to use, and respond using the format specified above:"}],
       "temperature": 0, "max_tokens": 0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -49,297 +53,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3282'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SSyY7aQBCG73mKUp1tBCEs41sSRQjlNppIWTxCjV22O9PudrrKAYL87lFjzEQw
-        GinXv5b/q+WIOscEs0pJVjcmXqzvdytn14vVt7vp992WHz63qw+/v36S9cd7jNBtf1Im54pR5urG
-        kGhnMcLMkxLKMZnMl+/m08l8No+wdjkZTLBsJJ6OZrG0fuvi8XQ8wQhbViVhcsTGu7qRjbgnsozJ
-        4u1dhM+9L/okdBQnylyk5XLWRZhVTmfEmPw4Yk08tPXOECaomDWLshIgnRWyYYBjagEAUpTKtWUl
-        nGICZ/EcoL0EMcU1cOVakwOL8gLbA3hSubYlSEWgLYtvs4DKm8lI9gKFNgQtDxkhe3PSMlfXyuaj
-        FKN/rTwpdlbbsvd7qAgK7VmAhRrQDOKgtTn5MEd+4wpB3FVKQqqnX632lIMroKZrp8Yo25vE8IXp
-        ZbxgF8TXxktTG8N7q8zhD70MlJOQr7Xtw5b2/Th8RZR5LTrTXA+7tkQnArLc+lCsBNZQtMYcXl3C
-        lgrnCRrvMqL+Ou7K+nob3JB6Gnx32pj/uvAoxb5ZFw3PdF7gzS9ZVVPvc1n2FYry5fUL9oGQ+1x+
-        izJAnEDOPKntsIuw0FZztem/CxNkcQ1GqG1Oe0zG3WP35i8AAAD//wMA2ddSQwEEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f62c2bee313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:14:28 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '11555'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86494'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.336s
-      x-request-id:
-      - 7cc7737a077abeb1f4e9117975dfb9c1
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
-      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOzUoDMRRG9z5F+NaZMrF/NjvRTXdSsSAiJc1cZ6IzuXFyS1vLvLsUqt0eOIdz
-        Qqhg4RsnvkttMV+u9mv6zquH5x+qH810KhNe3x8Pry9PR2jw9pO8XIyR5y61JIEjNHxPTqiCNbO7
-        yWxsZnOj0XFFLSzqJMV4NC1k12+5KMelgcYuu5pgT0g9d0k2wl8UM+ziVuOavmINYXHtPzClGTR8
-        w8FThn07oaP81+y5JVi4nEMWF+V8yFEonu+Xau+yuhwrFysVWZoQaxVprxqXVeNSokjVCIPGR4gh
-        N5ueXOYIiyycoBFiRQfYcngfbn4BAAD//wMAmYjYl0kBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f6881eab313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:14:32 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1017'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89866'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 88ms
-      x-request-id:
-      - e9912526fc04146baa08a05745789e1c
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will start by reading the instructions_1.txt
-      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\r\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4419'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSQW/bMAyF7/sVBM92ECdtuvnWAjvkWmQYhnkIFJm2tcqUJ9GI28D/fXCcNK0z
-        DAN2fSTf+yjxgCbHFHWlRNeNje/Wj/uvvzbdiyq7x28Pm3Zpb3bzh8/36nZdYYRu95O0nCZm2tWN
-        JTGOMULtSQnlmCarjzerZbK6W0RYu5wsplg2Ei9nt7G0fufi+XKeYIRtUCVhesDGu7qRrbgn4oDp
-        p1US4cX7VU8GXZwoe5GSxaKPUFfOaAqYfj9gTeHs650lTFGFYIIoloHSsRAPGxwyBgDIUCrXlpWE
-        DFM4iacCdTKIGa6BiXIQB55UDlIRGA7iWz0Ahu1iJp1AYSxBGwyXx46hdXvUtKtrxfksw+itvycV
-        HBsux5DNX1wHbGU4HI2ZOoFAAq54NwBSKYELa+GsdftpamMVj4ExfAn0Z9R/WTXLOIZ7Vvb5ha76
-        YDDJScjXhukNtlATJkTaGzHahHr62MSh9XReq2itfYaWc/LDb16zwY4K5wka7zRRfvwHN4mevkZo
-        SD2dc/fG2v/94dG8j87XdapcHRermsbcV5cJmvLl9CbHwtB7Gb/GPEMcQU48GffYR1gYNqHajpeH
-        KQZxDUZoOKcO03n/o//wGwAA//8DALRhJ3cTBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f6916aeb313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:14:45 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '13200'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86470'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.353s
-      x-request-id:
-      - 13087de20c75011601dacf71bc0bd2f3
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
-      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '713'
+      - '3284'
       Content-Type:
       - application/json
     method: POST
@@ -349,756 +63,59 @@ interactions:
       string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
         with other requests. You can retry your request, or contact us through our
         help center at help.openai.com if the error persists. (Please include the
-        request ID a73e800f9a4efa08668a838196d2950d in your message.)\",\n    \"type\":
+        request ID b6a7095cc0e76b9901aecd234de4f5b4 in your message.)\",\n    \"type\":
         \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
     headers:
-      CF-Cache-Status:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cf-Cache-Status:
       - DYNAMIC
-      CF-RAY:
-      - 7ca8f6f52c0d313e-SOF
-      Connection:
-      - keep-alive
+      Cf-Ray:
+      - 7ccfc7929fefe287-ORD
       Content-Length:
       - '349'
       Content-Type:
       - application/json
       Date:
-      - Sun, 21 May 2023 01:15:18 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Thu, 25 May 2023 18:18:42 GMT
+      Function-Execution-Id:
+      - yvvl1pjqkaam
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '30010'
-      openai-version:
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '30015'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      X-Cloud-Trace-Context:
+      - 92320c9bf2c16a55143abddee3e4aa6f
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89839'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Remaining-Tokens:
+      - '86494'
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
-      - 107ms
-      x-request-id:
-      - a73e800f9a4efa08668a838196d2950d
+      X-Ratelimit-Reset-Tokens:
+      - 2.336s
+      X-Request-Id:
+      - b6a7095cc0e76b9901aecd234de4f5b4
     status:
       code: 429
       message: Too Many Requests
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
-      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '713'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTWsCQRBE7/kVTZ9nZdc1msxNEEUIxITkICHIONtxN85OT2bajyD734Ng9FpU
-        PV6dsKlQo62N2Da4bDR/PT71l2/j5/fN43LyMt0vthOfF9PZz2yBCnn9TVYui57lNjiShj0qtJGM
-        UIW6GD4MhmUx6pcKW67IocZNkKzs3Weyi2vO8jIvUOEumQ2hPmGI3AZZCW/JJ9RFP1d4Y1/zcyws
-        xt2ag7xTaGtuLCXUHydsKf1TIztCjSalJonxcnZkL+TP/uMEBtJvEmoVzCGSNc6B1EZgDgeT4HIH
-        jK9AaooEtdkTrIk8eAZPB6hoT45DS14SCEOkwFF62Cn8anyT6lUkk9ijxiQcUGHjKzqizrvP7u4P
-        AAD//wMAmH2nWHsBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f7cdac76313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:15:24 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1554'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89839'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 107ms
-      x-request-id:
-      - 2bcd88e9e8bce8177b8e694d44cd16fc
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that I was
-      created and there have been no new developments to report."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5468'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSXYvTUBCG7/0Vh7lOSmPcVnMnIliQBcUFdSPl9GSSHHsyE86ZsF1L/rukSe2a
-        igjezsf7PvNxBFtABqbWYprWxevNx8Nt+Vbvv6yWZf35/e3dK/Jf3xj37sNGIALefUcjU8fCcNM6
-        FMsEERiPWrCALFm9fLFKk/XzmwgaLtBBBlUrcbq4iaXzO46X6TKBCLqgK4TsCK3nppWt8B4pQJYk
-        61UEF/FLYpVEICzaXUJpuu4jMDVbgwGy+yM0GM7Cnh1CBjoEG0TTMIFhEqRhhGNOSimVg9TcVbWE
-        HDI1BacEHmQI5rBRhFgoYeVRF0pqVJaC+M4MgGGbLuQgqrQOVRcsVaeKoXR7ihluGk3FIofoqb5H
-        HZgsVaPJp7+oDtjaUjgJEx5EBRTF5W8NSmot6sJasnP8MHdtnabRMFZ3Af+M+i+j5jnF6jVp9/gD
-        r+rUIFKgoG8s4RNswTbMiIy3Yo0NzXzZSKHzeB6r7Jx7VB0V6IdrXrOpHZbsUbWeDWJxugPPrOfb
-        CC3q/dn3wTr3vxcexfvo/F1T5uq5SDc4+v5SmaFpX81/ckwMtZf2a8wzxAlk4smphz6C0pIN9Xb8
-        PMggCLcQgaUCD5At+2/9s58AAAD//wMA0m5dIxQEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f7d89a64313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:15:37 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '12147'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86457'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.362s
-      x-request-id:
-      - 7d145f8982be5decde986f8f3ae9b1e1
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that I was created and there have been no new developments
-      to report.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '761'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTUvDQBRF9/6K4a4nJWn6obPrwkUVRV2IIFKmk2cyNpk3ZF5rS8l/l4qS7YF7
-        OPcMX8HANVZcF9tsuX45uunbqpo+Hl5v7w93ZZzWz7sHe1rePEGDt1/k5G8xcdzFlsRzgIbryQpV
-        MMXierYoi+Us1+i4ohYGdZSsnMwz2fdbzvIyL6CxT7YmmDNiz12UjfCOQoIpykJjdI98riEsth3J
-        bDFouIa9owTzfkZH6d/ac0swsCn5JDbIpZGDULj0r5KyKp2SUKfVWvXkbNsqaayowNL4UKtA36qx
-        STU2RgpUqeSDI9Wd1O9Vz2GCQePTB5+aTU82cYBBEo7Q8KGiI0w+fAxXPwAAAP//AwDlYq8fZgEA
-        AA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f835ef47313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:15:41 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1511'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89827'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 115ms
-      x-request-id:
-      - 5dad92e7ce5734a1e14ff1816067b8c8
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\r\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6470'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6xSy27bMBC89yuIPVOGVT+S6AvqU4GmLVBUhcFQG4kxuauSK9iooX8vZNlwoqAH
-        A73OcGdml3MEV0EBtjFiQ+uzu82XQxU2n/fm4T48uqXP/cv3Bv+sqk8/BDTw0wtaOU/MLIfWozgm
-        0GAjGsEKinx9v1wv8rtlriFwhR4KqFvJFrNVJl184my+mOegoUumRiiO0EYOrWyFd0gJinxx96Dh
-        Kn4l1msNwmL8FVotV70G27CzmKD4eYSA6SIc2SMUYFJySQwNG1gmQRpWOJaklFIlSMNd3UgqoVBn
-        8EzgQQawhI0ixEoJq310gkoaVGLSbusq5Uj4BHAnbSczOYh6dh5VlxzVJ+Y0tBXennDLIRiqZiXo
-        124RTWJyVI+WXxtUjpLEzg5HSCri785FVAFvyzH1ab2h0SJT3xL+O+BtNmVJmXpsOql4TxNLG504
-        61KYXhMpdXHQN6I2r8wsx4hWbt4ttWh2F5O98/7//tdo1etLc87Mu+KQCTimeKM0CWtiPe3cSAxv
-        rxLXmG/mpxX9uMiXl4SnlOewJfXQa3h25FKzHUsGBSThFjQ4qvAAxbz/1X/4CwAA//8DALYwIcUN
-        BAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f8408fbb313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:15:53 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '12090'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86458'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.36s
-      x-request-id:
-      - a5f70c956e20dee73bf6f83f3ca1b262
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nAs a system, I recall that nothing new has happened since my creation.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPMW/CMBBG9/4K62YHkQKh8tZOZWBhq6oKuc4Rmzp3bu4QRCj/vaJqxfqk7+l9
-        V0gtOAjRa+hLrtab3UVQRzlr+3o8rHflbUO5exm38XsLFvjziEH/FrPAfcmoiQkshAG9Yguubp6W
-        zaJerxoLPbeYwUFXtFrMVpWehk+u5ot5DRZO4jsEd4UycF90r/yFJODqx8bC3X3nKwvK6vOdLOvJ
-        QoicAgq49yv0KP/WgTOCAy+SRD3prZFJkW79z2K8kVEUe2s2ZsDgczYavRpijYk6Q3g20YuJvhQk
-        bI0kCmj60fxeTUwzmCwcEiWJ+wG9MIEDUS5gIVGLF3Dz6WN6+AEAAP//AwCfo6VWZgEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f89d1b52313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:15:58 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1539'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89832'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - 8885d0872614ba24235f88115811c52a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n13. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I fully understand
-      the instructions before proceeding to the next steps.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\r\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will read the instructions_2.txt
-      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I fully understand the instructions before proceeding to
-      the next steps.\",\n        \"speak\": \"I will read the instructions_3.txt
-      file using the read_file command.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\r\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to write the task_id into the output.txt file using the write_to_file
-      command.\",\n        \"reasoning\": \"The instructions require me to write the
-      task_id into the output.txt file.\",\n        \"plan\": \"- Use the write_to_file
-      command to write the task_id into the output.txt file\\n- Shutdown\",\n        \"criticism\":
-      \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
-      \"I will write the task_id into the output.txt file using the write_to_file
-      command.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7465'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SSza7TMBBG9zzFaNZp1ar0tsqOxV0UJCSqi4REUOU6k8TUsYNnTIuqvDvKz6Vt
-        EAu2M8o53+fJFU2OKepKia4bO9vs9pfo3+e2qD7a1f5TuXj+snfNy/rZfmBM0B+/k5bxi7n2dWNJ
-        jHeYoA6khHJMl0/bt0+r5Wa9TbD2OVlMsWxktpqvZxLD0c8Wq8USE4ysSsL0ik3wdSMH8SdyjOly
-        vd0keIPfFqtFguJF2dtos9y0CerKG02M6dcr1sSv4OAtYYqK2bAoJ11M74RcV+GaOQCADKXysayE
-        M0xhHI4Lukg3zHAHjigH8cBVlNyfHUQ2rgSpCETx6TDGJdC+rpXL5xkm96xAir0zrhyALxWBcSwh
-        6q4iQ6Af0QSCmh4sqhAKcA5GHmwmB+PE9wMfpYkyl4tAYSxNxY1VbnDO4DPTvxPfeycM3fm14Xr6
-        GuQ4ho6pBHZQqZ89rcfmoKztbWO1vNcyHKnwgXpVX6rzTUNzQ+r0Kjsba//n3QdQm7zed9z8dV6n
-        ahocD6RJFBXK6Z9xf9EB8K6r2re71eeoNTEX0dpff1L1ycaAmWuxTbAwznB1GHCYIotvMEHjcrpg
-        umi/tW9+AwAA//8DAMizuHGnAwAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f8a7ea59313e-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:16:07 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '9391'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86464'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.356s
-      x-request-id:
-      - 2e3c14cd6285c662dde517d25194a06f
-    status:
-      code: 200
-      message: OK
 - request:
     body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
       are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
@@ -1161,15 +178,15 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCAohxLeop0StegmHqq7Qsh7bG/bD2h0LO8j/vdoYSAsV
-        l17n633emTmgKjBDWQuWptHp/fO3r7z88rh23/sfvVJv69fw8vl5ZxZdUWKCbvtKko8dE+lMo4mV
-        s5ig9CSYCsxmy9VitVjdTR8SNK4gjRlWDafzyV3Krd+6dDqfzjDBNoiKMDtg451peMNuRzZgdj+f
-        Jvgx+xyfLWcJsmOhz6HVw2xIUNZOSQqY/TygoXAa650mzFCEoAILyxHSWSYbDRxyCwCQI9eurWoO
-        OWZwDB4T1HEM5vgEoXatLiCw8AzbHjyJQtkKuCZQNrBvZUQNm9mEO4ZSaQJ2UBCTN8oS7GvBIMai
-        mGGxI7DU8STH5E9VTyI4q2w1Sr/cEIhmhIrz6jhLRue+B2VL542I5X8zjGUdQ2BqwqVwo4UdNVNY
-        h7E62twctYwRtogDY/CW8Ty3KTxaofs3uqq7RXQBJL1iJVUwpyNYoncAsqH1sVkwPIEwUDqt3f5f
-        9wAhZesFk+4h4lNZKqnIsu4v/YeGxO4ktVda/8e1rzY9Cg3J6emO67z6OSsMjQzn1V9gCl9dvuqY
-        iLUf7deYJ4h3kCNPbgccEiyVVaHejK+HGQZ2DSaobEEdZtPh1/DpNwAAAP//AwBBklTnKQQAAA==
+        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCAsFiG/NqVHUA1KiqqortKzH9ob9cHfHBQf5v1cbQ5JC
+        xaXX+Xqfd2YOqErMUTaCpWl1uni4bV++3s2bpy8Pptyult9+fZ+v7lbb5/7xNyboNs8k+dgxkc60
+        mlg5iwlKT4KpxDybL2+ms+ViliVoXEkac6xbTmeTm5Q7v3HpdDbNMMEuiJowP2DrnWl5zW5LNmC+
+        mE0TfJ/9Fs/mWYLsWOi30PI2GxKUjVOSAuY/DmgonMZ6pwlzFCGowMJyhHSWyUYDh8ICABTIjevq
+        hkOBORyDxwTtOQYLvIfQuE6XEFh4hk0PnkSpbA3cECgb2HcyooZ1NuE9Q6U0ATsoickbZQl2jWAQ
+        Y1HMsNgSWNrzpMDko6onEZxVth6lH68IRDNCxXlNnCWjc9+DspXzRsTyvxnGsj1DYGrDuXCrhR01
+        U3gKY3W0uT5qGSNsGQfG4DXjRWFT+GyF7l/oou4a0RmQ9IqVVMGcjmCJXgHIhs7HZsFwD8JA5bR2
+        u3/dA4SUnRdMuoeIT1WlpCLLuj/3H1oS25PUTmn9H9e+2PQoNCSnpzuu8+LnrDA0Mryt/gxT+Pr8
+        VcdErH1vv8Q8QbyCHHkKO+CQYKWsCs16fD3MMbBrMUFlS9pjPh1+Dp/+AAAA//8DAKcjlwMpBAAA
     headers:
       Access-Control-Allow-Origin:
       - '*'
@@ -1181,21 +198,21 @@ interactions:
       Cf-Cache-Status:
       - DYNAMIC
       Cf-Ray:
-      - 7cbda46dcdfe13f2-ORD
+      - 7ccfc8867f9a2304-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Tue, 23 May 2023 13:28:48 GMT
+      - Thu, 25 May 2023 18:19:09 GMT
       Function-Execution-Id:
-      - f495yye134fc
+      - pbmesm0aoa9z
       Openai-Model:
       - gpt-3.5-turbo-0301
       Openai-Organization:
       - significant-gravitas
       Openai-Processing-Ms:
-      - '19439'
+      - '18581'
       Openai-Version:
       - '2020-10-01'
       Server:
@@ -1205,7 +222,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - 84cce4a68c05919b6fe5a262ed4a2f23;o=1
+      - 244d650faeed742e67c771ab39ea3909;o=1
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -1221,66 +238,15 @@ interactions:
       X-Ratelimit-Reset-Tokens:
       - 2.336s
       X-Request-Id:
-      - d999eccb67e039480b5f0d38b5dc5b63
+      - bd98d60ec0822b964eb683bbb670db8f
     status:
       code: 200
       message: OK
 - request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file to determine what actions to take next.\",\n        \"reasoning\":
-      \"The instructions_1.txt file contains the necessary information to determine
-      the next steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_1.txt file\\n- Analyze the instructions to determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I am following the
-      instructions accurately and efficiently.\",\n        \"speak\": \"I will start
-      by reading the instructions_1.txt file to determine the next steps.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"This task_id
+      is 2314 Read the file instructions_2.txt\"\"\"\n\n\nCONCISE SUMMARY: The text
+      is best summarized as"}], "temperature": 0, "max_tokens": 0}'
     headers:
       AGENT-MODE:
       - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
@@ -1293,7 +259,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4459'
+      - '294'
       Content-Type:
       - application/json
     method: POST
@@ -1301,15 +267,11 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4ySQW/aQBCF7/0VoznbCEJCqG9FUSqKcqkSKVIdoWU9trdZz1q7YwWK/N8rYwgp
-        iCrXmXnzvtl9WzQZJqhLJbqqbXz74+Hh+2xTL2bPzXNe0t3j4u5+pYZPPxeze4zQrX6Tlr1ioF1V
-        WxLjGCPUnpRQhsloMr2eXk9vxlcRVi4jiwkWtcTjwU0sjV+5eDgejjDCJqiCMNli7V1Vy1LcK3HA
-        5OvkNsLj7vf6aDKJUJwoeyyNxuM2Ql06oylg8muLFYXDXu8sYYIqBBNEsXSUjoW4u2CbMgBAilK6
-        piglpJjAvrhv0Fq6YoqPJQHTWsBwEN/oDgtMAHHgSWUgJX1sheXVQNYCubE0gDmE0jU2gybQbrKT
-        LLseaFdVirN/9uxEKUYfSTyp4NhwccS5YAfdgcpw2O1i0t1r+A0Yzp2v1A5cHGQk5CvDtB9bCwSh
-        Opwa11Zx7xnD06fwL3ClKcfwjZXd/KGzuf8RnQBpb8RoE6qeag5MtAMgDo3vxEpgDqqC3Fnr3gwX
-        53ZK68YrIbuBDp/y3GhDLHZzen+oSb0erN6MtZ/8xEthSLHf3kaH9O3VZ+FjVVFv/O50wqZ8cZrZ
-        vtHNHuXnKAeIHcieJ+UW2whzwyaUyz5vmGAQV2OEhjNaYzJsX9ovfwEAAP//AwDl8KHQMwQAAA==
+        H4sIAAAAAAAAA0SOzWrCQBRG932K4VtPQn7U2FmWSiuuSlu6KEXGydWMJjNp7hUFybsXobXbA+dw
+        LvA1DFxjxXV9m1Sr++/Vgnnz8XRoqmqxeCuWp339/tC/vD5DI2725OTXSF3s+pbExwANN5AVqmHy
+        2XyalfNqWmh0saYWBrtekjKdJnIcNjHJyiyHxpHtjmAu6IfY9bKWeKDAMJO5xn/6hvOZhkSx7Y3M
+        JqOGa6J3xDCfF3TEf80htgQDy+xZbJDrYQxC4XpvlVg+qJOXRi0fVVHmEyVRDWRrJQ2prW9J+cAy
+        HN31gddFKmdJMWpsffDcrAeyHAMMWGIPDR9qOsNk49d49wMAAP//AwAqXzViVgEAAA==
     headers:
       Access-Control-Allow-Origin:
       - '*'
@@ -1321,21 +283,21 @@ interactions:
       Cf-Cache-Status:
       - DYNAMIC
       Cf-Ray:
-      - 7cbda4ffadae111a-ORD
+      - 7ccfc90cfd676375-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Tue, 23 May 2023 13:29:11 GMT
+      - Thu, 25 May 2023 18:19:14 GMT
       Function-Execution-Id:
-      - f495u7ofauc1
+      - yvvl4c81ashb
       Openai-Model:
       - gpt-3.5-turbo-0301
       Openai-Organization:
       - significant-gravitas
       Openai-Processing-Ms:
-      - '18627'
+      - '2097'
       Openai-Version:
       - '2020-10-01'
       Server:
@@ -1345,7 +307,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - 9f90e5f759c4963f38509965c99deef1;o=1
+      - 6232341524f6b478562ccd013bfb5708;o=1
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -1355,13 +317,371 @@ interactions:
       X-Ratelimit-Remaining-Requests:
       - '3499'
       X-Ratelimit-Remaining-Tokens:
-      - '86466'
+      - '89456'
       X-Ratelimit-Reset-Requests:
       - 17ms
       X-Ratelimit-Reset-Tokens:
-      - 2.356s
+      - 362ms
       X-Request-Id:
-      - b789df6a372f156ab649b8822388cf4b
+      - 598ef1969eede681b5f5554e147d12e7
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["This task_id is 2314 Read the file instructions_2.txt"], "model":
+      "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '132'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6XQ+6Orfn/fMpdvYt80RApGXfISggLy0Cok4mE0BEQUBeWqAn57uf4H9yZubG
+        RFpC2q61fi+r//Gvv/76u03LPBv//uevvz/vYfz7f6zPHsmY/P3PX//zX3/99ddf//H7/f9m5nWa
+        Px7vpvhN/w2+m0c+//3PX/x/P/m/k/7562+tbgTCX7NTTz5wyiE7+BFZ/N3oTPl718IbeCJ6lMJb
+        Ol2FuoOhNCrU3t/P5ZJ2ywLl+s2oxx+TfhCgJwIopBesY2diEwgEH55Sc0aT4vb9IlmEgxE079gU
+        TT2dAGgD4EqOSyTmn9JpMesMenkyU61pwrQPmqmDY3R3ifActZSVofqGWu8M1BLNvp9JNIjQvSAD
+        o7yQHYbmhof37O1Tl3hvNvWcxYHvXLyxrtVdSL3hHSs0tQ9k4+tD2Ytu84ZKnF+JfGUvNtOxt0BZ
+        lSU2dlmeMu12kuH0tF2MoeuXE+b8FnbaCeH9NqpSJifHANxK7oxPt3MCZge8I5kE9RHdItPsZ27D
+        d4Dr6ZYau4wLZ+OCfLmj4QEN9vcYipe4tkCOH1syPF4iI08lV6F/QQ25EFtK2T05WdCxuRu2RVgy
+        +oaDBO6bR0xNTozAgjfcAG96CbCVvXVnSDrjAJVd+sC69Fh+4wRU6k3DF9fmw/kK/AqaQS6gT71R
+        9aVJ+Ag2ZTBQlF72TAzexgDvDXenJlEVsJyihw3mkO3p4UX5fqBvRhRdSBMkiee4XMBndwPwds6J
+        ZAePfjLZSYTLu66xPR33jNxeL1tZnCHCzokXwqEhag4KztapaabMmTjhiGANLjdsbw3EBAd0EXzY
+        W50ecmKGE+/INWAfTiMKLESH2UJhwXJfP6jd82dduH73lgKsrUeUG5T6gX7yHNJm+8H7I3g4MyjM
+        DB4ky6b3SyKVg5HVgRxeLAeH+AIArbcMwUMW9kQWoc7Y9vPhoVd1V4w7oICvploB1J60xO7DU4EI
+        FCPaNbcnJruplMtv7Ns8nDW6QUpx6MP5dGgR8D47Sm1tSNIhLNoWvtF2INCExGFuWKmKYB72ONzk
+        T7ZoWEDw0cQIVUItASLUOQQWrnvs2d+xX5rH1QDeB1CsC7VfTp4bqfB5yzwCVfByBtizGuqm5lCn
+        ZUO4bDwkQWd3bbCTdEO6PNtShMy/nNBHFqt0gtd9AoXQEjEOJr0UEe4zWHeGSgQhE51JzYJ8s9vd
+        IFXP10f50VQ1UFR+ayP2+uzD7TVMAmCe+RN29kedTVlmT2AE4YPUr3PlDJi7tTCM05KalrDvF1lS
+        RZjtuxsBe0wAGwrZAIa1ZX/yn+1hO0GaThPqEp7qAxNiCJvHd0HiTbT6gS0QQTvUjwSGyAGkiLME
+        GpZnIv6ze5bz4t1uwHz4Z5zG9xSwsSk4pdlcChJJoa/TDLUVPNavO5KmMkj56dtVUMwuL3p8ju+U
+        8vpFglGhfbDrdcFaD2ghH7GWUrVuff2LT6oNbQu3aKM8dykVbXcBxV71sEYlnfGSaUngVRMdH16f
+        b8+2WyUAl2DTY3RrbTZfFRbDoowbavLcsZ8dbxYhH13O2HidD86sab32O1+kzAcvXFxei8DX4t5Y
+        vbRI78TNxYe7MTIRyNBnXV/LybsRMoxz103JmM0FlP2dTFVPb3qaoaKG1vu1YHU53MBwK/gcfk8N
+        omj4Js6w1eAEDmfpg95Wfi4J3CdvOMy5ga26eoRMPqYGDFj+oMa56tjcRmcN3j74Sx721yvn1Dnb
+        8Csad7r/OoeSH3SjkJmSbaiJyiObB1BnsCn9AYnm5wIm6+wNYK+GIT2V9zFtv64bg8a9JTSDxQjo
+        fc4NcMS9ieTNyw4nTfAnxXJUngCDtToTheQN27dxxs6OkXDmNrCFpSYI1LiJbT8eiloE6lk64ENn
+        +zp58Icb3B+fInWl+A2oek41aH+DDuv6LtRZ4+8q+Llo4rpfZs8fhwQCLB0mbDH/GxJj8WzZA0VL
+        Y1ed+zEydi7kCnIk0sf89u2L1Br8DC/2y49+hmKvAQ3lDrbG98dhXeIg4N15mToRbPX50W8IfN7p
+        h3wl3tFnV21kKH1hj+2kOzjzsZI5aOGqp9o9assJ+YWtnEBh0tjaVCHRKnoT3328pYZ/fuusmg8x
+        UEcorfjEpUPS9JEcxxeTGu9kD5YQbwKQi9MTPw9NyZZ+02hAyt9vNIE20Cm29AyyYzmgieyKfjxC
+        LMF+3zzJtK6H7F6jD7YfWGLLND/h3C0RryBOPmBdmNK+Q/LsygdVKPHB/5jlthBEFUZRnWE3Kb49
+        vRMWw0qCexotaVHOQ3V/gwjkI3ZFGIWkfVoZXM+L3u/9yVmS6IpkFCQyRZ/8xZhwn3NQ7DUPW3eh
+        Z71GYx58+wCiWZMpW9b6CGdt3KApaFQwi+84gd40ujhWCWPLZXO34Os8ikRZ43V6nFgE2mNjYPvK
+        9mCp95wKK475FMv5oM8kqkRYOSmPLUv4guXGpBr8zrsysqZkZ7TESm6fIySyirDxfuh8KNFZxvbm
+        1aXTOd/4sCtFSKTp3qTDPlfQD38JlGINTHqYdaAyvDOaNrt3OXdLxkP2ujk4lbqp/DYBbWFGJoTD
+        Fx3CSStPEXh3xKHmODRgUhlNYFZGBjqHUw2mOPFqoH02J+o8+ns5w523gGufnPHePMhsDFQ7gvZk
+        QyRtNglbvpUHgcPetzX/vJQ9La+APXf4ogaeHmw5fc0ImvyM6fHzmdmcnJoFet2zRr37Gsrl8Uxc
+        QGRKkG+7n5CmZbLAeOED7KVfWk6sGBb4pFFOtbg5h9Mx0QvAo2NPpu9XSceTaXNgD6cHvnX9mw1X
+        gbQgVB2ODCueznfzqMF49G74aKnfkB1yaYHuCzQUL7rfz49AVX/rp/fg7qRLH9stvGl+ST2xNcrF
+        3xe2UhhC9sP/ctlIWQtd6eTiNIKWQywQL3JXPVtql/dL/9WuDwRHkdZ05YMplckmk3e7BKLXESjO
+        rHI5D1IKv9jV0JfNyRJMsHn0C5LMs5/Sp+W9QbZJZHp8E9yzYyn60IeGhM3TaVvSoAtvcOG+CbWi
+        VCkH8eK6EJrdQgDk034uxGUAaz3Fjvbe9u3lK/tguc4ntHydgS1cxiqw4iF2+7johynEGjjfEUXC
+        sMXltHkrCxBfXIoEr3qXSykNMZRToyOb9GLr4kOkNhDjIqCGUupsyzWlCsh1aelB2Z7SafMWJqjy
+        bo6PbynpWcu9DVjsux1Fu+fZWRLFRtDHzUhP+H3Sp1pbBsAOO5ViJz+CWbtvOGh0rxd1guMRbLvE
+        ceGzKjUExeWbzkoV1ooPMpeeiCDqDBbQApi9d6jdWRKgsIA2QJx0wCY3fAFZ6xV8i1aEs7zjy1YP
+        oxaW++pBTSyicm6juwYIaXfU018JYDC/36AB6hKr86SxZV0vRKFeY9dcSp0U4dyBiyGJ1G2VTdl2
+        H62D+lc5k754AzDfqaRCTq8QVW/PKVzxiYBHKh/xvsvHcKnqSIaWo/FkvkRqyNJi0sCQogIpk6yl
+        q97g4WuxXHwLSqT/4g1cvluINpfZB4uiKz5IUQCofs9TxlLhjSDiaYSIfr3p8wJUCUQoEuljucY6
+        qUrZkpddtiXLzenAKzqlHAB3GdMj3ovp4EyyDHtJNggTprScLhfLgPmpbWno0y6lTnkjMJrPyi8f
+        +uVt3Q1YW0lA3ZQF6VT5ogYlfrKw7lM73MYYWb/4wFpR1+kUcUMObbOG1JbNzFnsTSfD4LxQ7C1X
+        UWfbooiUvXoOcRg/SL9s9VcOlffLpWoxFYAoVFfBZygZocLhAZbp7HPK63y0ybDWe36D9AruSueK
+        jU9Knfmr7WuoP6QMe/xRLsmezw67eKgGerwGBhCse5LA6/ZpkO27Epzhdb0fZO8uytRtv6d+Wo76
+        oPhwrChWCy4ctHIfw89ijxg/nxdnxccIOtIAqDPfAjaf8qsMg+Cekh0eeGfCl7GFxySrsPEcu5IV
+        L50Hd8PvScMNJ9bt7FsMhdAWsRmll3DgzGwA8dmu6Cl7OykDzKmh5D0L6uT8Neyzsx4DuNu4+HB6
+        RIxVR7ECWD098LE/OQ4jl/MbisqtpG5x0J35YzBfWd//jet8Q9RMaW4PjKZnvKT0trd5aHwijnpH
+        /EzHW99L8DzRERtROjrTZY8DON82FTY5kWdLsqkgeHrqgUZ3tdS/S/WJQP6UPHxKuBkw7baXfnzs
+        Dx6PMoX2Tqs/AmrPyRROKUmQ/PLzfM0vmY1oOi0//YfEbtOGrA2jGNz0FyBDjO8OA1MrQupvItRJ
+        fJi2/nBC4DW8AiInPNZJ7tkLXOsxqodxAOyIXWNHlTxHSvs02NYcsQyfU7OlqvMkznha/OGHv6hR
+        k1r/bLRnLq96FJXH8NWz23Cr4arv8EH/fEJ6Ec0FDlBGJHpLSzq+GqT90Yt7QY6dL3gMAwDPMaf2
+        42Wk22mSa/Dj7/y4X1LSbxoViJKr4rugtIw9p6lQ9hfZpSdXCPSB5bYGjxdpxCEle0f84aNkBQqq
+        qsxhS9GjCpiP4Ex1T2odFkOug/zEZ/jkbh76fNkecqglLxUj6tY6s4XWkvmnNZLlKsv6mCzBAs93
+        lyLutlwAYVZqA0lIeOy4r6EfZz7QAG6yA3o9tUM5BVulBiZvlRSjL+dQtW04ALX97sd3HVa8HBHM
+        ViRRfaEkZRN7xHK5iTekUavZ6fPrgmCccipaFO2s//F3lJdUrPqlBKy2NQLUdrlQt8HAWYh3EJUV
+        T6h1FxywVAAffnqYwFPR9GO9Nd6ytUCLPnXdTsW9KIpwsE85NR52XtLhs63gMckrsnOFRW8DIeDh
+        KGSIRiQC+hAsk6Gs/Nxjk7ZNGRYAlMn+pVN3ja/JOJ5jZezamcxIe5fj1jllf+oX9mIhZPUWIPhq
+        Ykq68WaXY9j7B9g2AY+1ZXd2ZlMTebiJwi09ip8QLNvLJANCVA97pVw4w952NNgeuAQb1uaQ0t2Q
+        EaBI1pFmDQb66HKeIf/OV831b8nm08QB5yx2qHev+5K3XMuFaTcZZJe9nZBdP98B6u42oeqzUFJ2
+        uygqSEGyrH5CCUZflFp42eQCRfEx71sjq3158O8HbPf8rFfnLHvDTffKyKr/GXGd54rnNKb2o5/D
+        ytu+JtiedYzt4s36aecaCTyhm0/Pby9joxGUBTxhFVKr4YtygtfTDYiOccJe1L77cf+tWgWGB4Df
+        jmP102V4qEC6gS82OHEo6W6IBhC0vYpNeHqAOQNDAlPRxXg/14VTl+KpBuv+oo0c7fUxfic+9O4u
+        wtZjEwNh5hMNHqRFXPnOox8LUR5AOGgZ1fCF9ePFEQkEdwnjCO+RMw0kC+AsZJTwVS2ySf64BAiy
+        blKVeWLZ8lsrgtuDL6AVf1Oxw+kEtr1jIF7IPDbnB+4An9NnS+DKF/ptUcSQvRKH7s86BstIVU5Z
+        /ZSffkmnKTQ16Iy7nGZnoOvT5dqJcJzkKxGfo10uU8gGyHeViPGiTz2z8VUC+9dmT7ZAaPrxDDgL
+        gN5pyDY57cqFy0ANL4YsonLvQmd8Tjr/x9/pDz50ls8mRPKKB6hZ589L8JD++G8n0/RKho4tgZ+a
+        VORrnqWSNeVelR+2oGMUyHXI1LLLIXdAMlGa4y1lvZ2/oTpyEvWKg5NuY2xYPz5HJNXXQxrq5wma
+        pjaQzcvb9SyVGwK70PXpWXbqckqPjQtXvCTbHz99TtMbdvLo0dM2gf1yr3RJSfz3HVv3vgBEms+c
+        supDssQPI1zrPQ+DUSix9tQG0A3GBcJlvGk0fpMtGEQ10ODlYadYhxIJF1myRNhLkkH3zsUJm+Gz
+        rcGj/dRYg1LtLIeWvaEyRi1a9Uu/xAtGEFjoRQ+n5gnYsv1mPz+TnhK+BmQvciI4P/ccVmd5ZIMY
+        fHMwRqmLUfp02ZwUTgSPr0gkDF8Aa1Z9A37+r7P6QVOsTa1y5/cII9+j6aypqg+R60Rk2s8nQIK3
+        QaBomJAIJpX6lU9asrt9F9i++AJj96yUYGvPX2qZ5jHlm+Ml/6PXPa+TwbTjdzfwFccjtseb3U/d
+        x+4gL6obepruuJdI4UPo48+IDyv+/OGPfqEdENgxFM56+o0gZWeCjcqq0yryAYTregmbtGu6PJ6B
+        C29VrSC2+ulz3Fwn+ZePo7zM5XI1rAMcntMVR0a99P09Odkg084Hqn6fQbg0CYxBLZOBGmu8s6P7
+        jeCnD9K1XqjlRATdUkB/atB8yE/h7N1rF24P4LXGd6ZP990yQTvs5z98ainFfQ2zh1FgtZB7ttCy
+        vQHwiW9UXfezV85mBpfsqlJLUNRSnA9Yg+nn5GH1GQfptNX4BV7auqLe7tky9nk9W6i6oU2PN7FI
+        Z+g8ArDGGz1xb5zOyksS4XX7MJC86rdZPtQJHC1FpwduH6WjcAgqyB1cmar+gWfLdvREefXPqOGI
+        xpr/WJW9T6hj+wX3YK7uNoFvJAzreQTh6l8uAJEnIcuyO+tbi8wBnF2ZInHFsyUEnirbD/FFj6yq
+        e7KuHyR2wBCpEFdOZXnMoWMkLyKuftGsL6IPf363frc/4Bs3z0nqzMmkpngm6cSEmAPfrvPJm390
+        /aJQR4V2dTCxv/p9Kx5yYP0exque47tmvMlXBAyK9KukD+iTRPLaf8EGUYX+e65ervIwQpdABhqH
+        ffWmg8eLPK7++wssC80WeJGDgCKzbcsFyTsEn7fco6erUvXCz5+0K8KwCQSz5H09d3eVc+exIQ+v
+        fq3PA7Tsm4XuqqGu9eqkQntTYHoUKQeG7qO1culpH+p5BWbzGGgHYDx4lSbT8cXa5a5IcOWb1HZ7
+        ms7n4D7B2Ja51c/SnOlFiCqrY+RSP557xtr9Qfrp0zUe1JAFly+Cs/wNsHWpQNpNtW7DwzDscSou
+        L2e+36McFgaasF37W/Dzw4BpJCp1tfeTzW0/QllODx3W3rrsDEI1yco5vwfkZR4SRqG75xTBNPZ4
+        7zhFyIYyE2HnfWKSqeClT5r7meDLFipsqFXLBiI49m+cqt/vI5xe17MBjOfxRtVLXuqzp919OOnD
+        AWvaNDpjb0k5bIz5RVHuHlb8DHz4PqmP1f/fgLVf4EL/dc4ITNmSLv5Igz/vu5/FDGdfnDq4+lcU
+        N/LUzyoXi2DVd6S61nxJe2EIgKgkJXlpMgW92jYQQrmRqFluH4Cez5eDkhwNH3s1GFN2sDccDC/L
+        FlutFTP680NXP4Z6M7qlg3itud9/lLnXL+CvpmhB7hXPKHhqLphU8pLgXN1HrN6efji/GkOFnrcc
+        CUg6N+3L0HrDZlec8e1Spenk6FoCuVc0UwfyoK/j8TRAMzy+EP/cfvQ59goDHpV7h1rbCnomZJGr
+        YDv28HHcJ+XcP7oWGl9ZIPDhqYwnxY2Dw4EDqOexoJMQbwNof/3u1y8p5x8f8e9Tjj6fzwy+t3g3
+        wDV/Vnz3y7V/ZMNfPuaffA9YLKcyvIpiQgpUgJB8XyWCmflo0GadPzdB04LQjglWv18lJHEiBzA+
+        Dik11cTQF9Xoa+girkDDBy7p5J1mHy6ZMvz8FF1caLTAnx5L95iwtV8kgpKQEElrfZx3UWiAZUw0
+        xBkoScVTXdXQsARGUR5TZ4LfmwhGIUfYwUgvya+e/vzCQ06adEp1N4Mr38QHnwb9H3/5ddQu1MKi
+        yCahSVvIMMnoyVC0kmyEWfqD3z/9xUp1PsCGG3i8ryMt/OMPf+f3G1sbAYOxHHkZ0Hev4aMqxSuf
+        uUg//EDbc8WcGaR7Tln7Y0i8BtT5+c/wmmwAte69yibPzVQYx1cTbdCT6cPaL4GCG1Rr/Ezp2v9Q
+        AX4JDl7rN2D+a78o0uSecYBcAdBzuOXh5cFM7H0WWpKTolpK3z4muvqv4cyUsgPbYlLxxf9g0H3d
+        nQar95Dhy5JaK38QRWBJdk/CzjbBfFVjGw5zZmD1ezHT2a0lS3EvroG9PK7BHKhaBDeC8iHT6neu
+        /SteWf1xbJ/40fn1e6FJXl981FOtJL/+3crX6NHIKJguezOAZRg4ZOhjtRRLG4hAD7KInoJ7H07L
+        dM6g1H2uWBsvWzbLmt7BjrS3lR+OJdO6ewRKmVlIHMo92Fp6+ZZ5se8RLXZ6v/pxBDIohmTa7LR+
+        keWyAkFWOfTxnt/hvNYbMNVaTuJ38mIr/mlw7Q+g3/ytfpQzuG9OFeEm2S5ZLfi58vfvVsB//uuv
+        v/7X74ZB3T7yz3oxYMzn8d//fVXg38kj+TfPi/+m4p+bCGRIivzvf/7PJYS/v31bf8f/PbZV3gx/
+        //OXIP25bvD32I7J5/99/q/1a//5r/8CAAD//wMAMvLWqOMgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc91e49f486d5-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:15 GMT
+      Function-Execution-Id:
+      - pbme4ambn2d3
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '156'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - c0d4388eaa5635db1c89b13a41bd4308
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - f01268b23b94415c41df7d0463c49b41
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "a task with ID 2314 to read the file instructions_2.txt.", "model":
+      "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '133'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6WQ+zurbk+/kVW/uVPgpTsNlvEAgzNkMG0mq1IAMJCSEMtsFX97+3ku/qdvdL
+        pIBD8LJXVa1a/o9//fXX313VXM/T3//89ffrMU5//4/vtUs5lX//89f//Ndff/3113/8Pv+/kde2
+        ul4uj3f9G/67+XhfrvPf//wl/veV/zvon7/+br2rT1bEM3innc0WXkRwIO82FEJy240JTK12oc7e
+        XIdTdXKv0FZ2NsU08Sx201gGyeYzUy/uTlWva0kP8T1wMErFQ8MC1UrAZ11esFUcloGV60iGN1ip
+        ONrIJ77E6SUAyqR0pMu2z4EdrHsNryITKXb5CKgpzhksBvbE/tM6h9wMWQk/xzejDpfqgfWHYIGh
+        v0fYDGo9ZMKqsWGxMidqBGzgDPnDBoLtvMFRm0vhBN9Zr7/gKUaqPSScrXfyAnX3zolyP4Z82SWF
+        pgkD5thZbY5gmS7lAoNgsvHWzJOcsRiMoM4mC2PbfYRT//EYaI+RhDdpeqmW8BQ4YDnhHXmdHD8k
+        swEP2oPPa+oLZMq5BE8OUHYyIeQF7Fw8Z2kNLoNWoYVEl3ypbWboU/XcUvcgsYGLjX2GdXqhON6/
+        5maq5zXUFDvd05CKZiWGzYnBoxzusfuyDpyuzp0IGci3OHjnFCypKPfrkz4o2MrSTSN2vZgBxeML
+        uTG7bJaToRjQi+IzDbFtWGJhrMX1lNgN9aZnV81FLRba1lbO1PbtMCefxxLotXx/YeuVV9Yy1Jsr
+        eK+qDK2+8WD0QgVIhM2MN5Gx4j23TE3vZZ4jiRplOIlLWsLEFjoauKse/Fmf/nhBGB1PviXp690Z
+        9pkwU7STtg2zjKwALvEG6mptDWZ6fXoAU22mKBpxrkwsYbr1KBmS1cWvaDveFlh12gFHa10ZuDG1
+        Zwg1o6JnwozqieqHDSJ7xPhmuw+LQifUoL6TLVTFXcPZ42wnMGahjMCTZwNh73cPVdFIv/tBAXNk
+        7cr1DbcVNff9Jief9TqC68vziX2bHq15ibwIpA9Voag+zJwm/JXA+LV+Ix1H48AOSWvrazcv8WaA
+        qFmMVn3A8FUG5B6dnmD0GqCC3JVDbJ2uJ8D6VdgBoV698FZMj5xpZ/MJD2faIM78IZ8MCErgWehB
+        w7qHOXv59U5XvU+CYyK2w6yO2gbY5ijRKEpiwANZceDM1D2aZlvKmactEOrj+4OmV/MJOVYfj9XV
+        GS1qgkfA59qbHV0YYo69Zx5wSfh0CBT7S4mRPCFr6QulgyB59qhdTna1ADW0oZ1liNrZ3gNMbw9X
+        2GZjQYDz3oGFCoSAsrjdMFoJw7B8HF2EuQBkxA7EypdmMCOoT6KO1C+eEPamPVTXbEMDXCthf3h2
+        GWQy62i8RLAhQA0dcN5ce+wkcQvGzbgR9GzaNISp2dEa5WN71qi8DtBTPbhArJt1BM1Pt6YhVpf8
+        cJyfIgxtccYmn/yGtdXDg/AWcbrhF41P0uHigFVmH7HD7+HA+xOX4W6LTVJdyaaR150KQdQ9ZrwB
+        bRouue844KEtAkZ5svAP4p0D9ce+ohuVFM3cDeoV/uJnbLvnsOSKjaCYoxua/THg7Pv+UAM1x440
+        l9WIxfkM4eOmI81RrGF+0E0GtTMi2PHFO5/KaKMCRSpdagFhzCcvno0/+R9fZRwuavB2oFNtbGrW
+        1rsin5DbsJJPhCIamZzVkRZALngdtsJn17Ai4z3MnVahpj/2nAnTJ4OFK2zQoss3zpu1L8Ci3XCK
+        m4w1DLJCUNft+0aYGZ5yftZQBE8vNaU+2vnD7N0WEeI+NKgbeQcwPxy/hKqQ3Gg2x1Hef9cXbG6Z
+        h8Q0vg9U1MIavvT+TuDlMDZz//EWKKrJHke709Pi1iFOoFI+b9To7QTMWuE9YEIXjGQu1c0rsnYF
+        LAPo0svRnPhwVQ4P6CK5xZEosXx8BJszrJrgRcMocgfZKp0dOChNSGbNIcOkwDbTut3Fp4V9BJxK
+        8GTDRlQHauTTrvoUtVjCiYMtjXZbGn6U/FUCfXx9sD/W72o+XomoxW8P0MBRmoaxm/6A6bvaEeGQ
+        mpwtjrPAMGgfeDt0tsW0DwqgNzKJuitHsJhg16V+jMU9TdP7aPF7pjJtjw8TjQQn5sy0Ageshy3E
+        VnJPq6lrQQQiH42o25lCNdXe2oGr8+6Fj9bNsqS1wGUonW2FjLuTbdVuqtlwSVCJxI84NsQ/wBrS
+        3O6QvrsE+bLyHyLklxfG8bMyOTu8X57+nT+2Su1g8e5IMu1xZzY2zBvK5ffrLv7ijT2oSaCnt+4A
+        87eX0ItxODccPAwE5QN6YjPTvWqx5rjQbsX7QE2+vQ389u4T7do/XjTK6nPOTqOXgR+/hCE9h1NA
+        bQgxVWdscbPhzJyNSI/j9o1kWuwrHibWAlk6Lvj6As+cacdoBx9pNFCk6mf+fX4GDOa02E9Na/jM
+        tl5A48Mripw8yGdPnjUYmGOAdwDV1UzZC2rm3jsTi0uyxbeXxNHfkm8jGBdS2B7Lif3JR3ZtngPL
+        qmCE2WQ0NIx3iJOfXlCEk0kju4qaEQBXgC3jPhrjsbfmTyCov/H4Ft4UfruYqa3rnRthc0mnnK+2
+        dwbJTTBoMCbFwEKtkOEXfwmU/G3Fwua0gK5EGvXN492a+cleoB85GjaC84ETo1Vr+NsPL3tV5fNh
+        1RXwEZGYWr06DfMPH+TkzJGmpG7OhsbdwVHKAI1xNDa8vrwXCMWkJ5ImpM2cfcIraAqFkv5wby1y
+        nJ8yhMnZw+4unazldAYH+Lsv5vPLWvJXUIL6rKfUuK1qwDqH9fAbT5zu+0f+mz84N4ZFsbL9VFP7
+        eWhASuUPuX/nv/TFqgcQDSX15LgC/Lavr0Bc6ic9HC5S9flg6P3whHze2G94Gs2CLl7OE3mkqZ6z
+        Bw93EAaejvfT88LHAsAHWF/aJ0X+al9NpRQu8JW+W2qImmkRNXjbcCO0MWLK1R6kFMsinKViwQ5m
+        Vc6u57aAfbUakFBvIO9IMhQqaBROA3fYA15CXQVFFYfYiyHK+f6adtC9nyTqLdKWL7fTvYapv2uQ
+        dluagUITddrWls7Yvy7Cf+mHSdMCsvajRz5zFsrAbpeBLGE0VWN+KbI/8cMYWtasmEMLPscXI6rj
+        xtZyHN8tlGl8pVuVWJb0cMwSBMZV/q533EjgFTtasz551KCfJqd0+thaBcMbYl/+ma+XvlUc7eBT
+        w7CykB2Pqgbp8b2l0eLJOV1tPwzs9dOVzPv+Uc32K0P6CBODRj4WwPf3T/hOXERet8Nx4LKSy3qt
+        LGu0sO3W4v5TSqB02YXYXhG9Gct3uAE9yBkS14sd8r2UEN041Bm+bR606iVS7ODr49nY0bWkYfTy
+        FuAINiOZZ98JuVBWCaS8M/EffKSrXoO6UBzwoVF8i8nbZweKk66gZdea+WS/SgQKrUnIfi33FR+4
+        d4bbp3//8gfjXHXIZl1NJccodGEzgzzMoDX2At2k63dFx88Wgm5PLkhIxcPwzWcIPZescKScOKfW
+        ZO9gfi9uGBV3Nszb5cDA1SEWjR7Blc/+uCoBem9ORKWizGfnMmUgeNUjrarTtVnUgNpgKwmIejEk
+        1fQJZA1YFy37kx/05KhXOK/XmHyk+cmZu2IILnsY0nMOi2a2URXAn/4Lok4YyE9PvMv9mWJJf4Ts
+        6ZbLH7wJtm6Wy/NHRwCbsklIOa/C0QloBu/eIaPWeaMPi31PA11Z9XvsU7vnPBwNW7+fRYrLJx2r
+        hVu+BnS34UTZWC2YCqiOwH18fLT6vi+7tLWmyyAr0fsgJY3SjkcGagsecc4uRiWZihzAh5zcMZJe
+        Dp83K0OAcCe80FpvnVA6K6cDvNz7GL191Qt5LO8EsDJrgcZj0oSfK30WOr/KDVkaXuTzGzwJ9OIr
+        w47RPCvOVwYDjb5+0fCStTmPQYagSYsesfx0q/ib90/oDfc7Yv6ONjPitQOhXUVo3DacdxYpHvA4
+        AAeHL/c9EFoONngeL2tqzK9LSG/r0YGfy/FOMfFqPkfjPvkz3rgDrSGvtDwDrV+ViPfPYmBLYmZA
+        WJaMRkL5ALyazE6XV4vy5cs9F5072UEjuBzw5lMM4fyW6RlIoIDU0uSttRziTwQP3XL74VH1Rw9R
+        3pvYTuN7w0jYBqBKjyo1+3MUjgEOCvXHn/4YLdUs0/sIhdjf0JIYPv/WQ1dgIimlzgRP1qI36RO4
+        8SujOO+QxXcGXn56HSODHPkcFrEGjun2hkNx7sMRLY0Gv3z41bcZbyM7aeEuX03oHsJTzsRbVUKx
+        gAk2sw+v+OIrouaO6yOS9RY0LCn0ANaL5dFN4stWl/qGCue0TeKVdll98XBGGnuuAFoN7gwmziwZ
+        9m2sYbezt5ynGnPgpsstIgrtofqz/9exFVK7VuyQnkwQAVOLMrp9HJ1BUsdlA8OP+sbezrxWX//i
+        DP2tK2HLUAifW1J7+lcfUvs+yPm026WCfrSeLk4i0x/k9KI8oaDWFoJPy2m4GjYJtNy3Rz1s7wdW
+        fZJWZ08d4Pjc1s1y018euG0PMWLzS7cWS970sDitFMSytAhHt5sD+L4qayTHkQLG5+ncagBxiO2m
+        eg+snQZBi1y9wJvHqrXmHMQJsLrgTmPjcB7m47WVwVvTJPz7zmqJb/48b7oFz3D+zg+AsxMhXf64
+        YLiDudegBz5kWW+mZrgq1wcAZzvCxip/Adbagw087nz1hroZvhXzVXd8fCRKUTbVkuxZop+cNqKB
+        kr4rsj1XGohdWabR/h5W8sU4a8CKd2vqbunMqdhEZ/jEY0Y3unwDS4jdJ/TueU6d51AN0xuMBH79
+        ICLMZzawVdMyaDl7kUbkHFbziLON/tWv6Bju7IoJ0z351X9Ek+6yNVP35cDyGidEkqUqJ4PiP4Db
+        lRo2TcUfvvlsQzyUO7rdfXQwaf1mB9r96o68EV4rFmqJrJcfQ8XRtsnB+Iuf/jhWNCaiM0w2PGVg
+        M/KaItEPGlZHSwC/eINWdalavPXOHjhAq0PwoL8bMn+kCH73K41PKRzYYd/s4OooemQ2qjgnV9Y9
+        gRNcBwIO63s1BY5twwofNoiqcQL6FaodXauniOLD3rOW8LRx9FG03tTM53IYoGOpYGeQJw7Xr3O1
+        DMjroR2uLBrrhzufexA84ZePCXfdSz5/5wvDj/bGLj1XQ1dfOdS/fgQeBWcC9OMuhrYdvBYfQG+C
+        L3+qWmCvcuzK/n5gOFTbn/7Em/S1VMNxuRswvlcBkj9ey+mPP3/5gYgaASk7+j3si/FB99TQwhGL
+        6zP44hl1H9wL5yUy0B89lQZiFs4PMwrgV++jJX0t+RJ3OwQDjO8UO8NrGK/4LsIghAV5rxwhnOG7
+        7H7rS/hhvoFnfRJG+POv9DGxrMXA6ysQxptL//h190Yu/9RXxsX1qrmMAg1aYyfQtKHZz69b4Gfl
+        IWo21cXicXy2oWOP2h98mNVSRSCNFYMouzS2uDaL5z/4GUfdx+J5EGRwh28Yycf1PHS//UkL+YSk
+        YUfDOaARBIs3ALIO2ZbL9j31YPl8VIitSf7zDwms5eZF1tJsc6UzKNJoe5yRhsXIYu1h1KB4uU6E
+        +8YrnN/PqYf74tihS8ySSvnWU8CxiYYG++hUdFEkCD1P+GbCZzOIo3IgsNvdfGrvXkrDQWh6sF8y
+        mXABAWvabYoA/vR0LMXDMPdPq9bfcllgL6qXcKyZvsCV4sXUea6ShofrqAOCvqkx3sc1/8b7DFNb
+        dOjRePcDMc/yBkr1a4+jb32zXFnXQoekMd30opsviv44wzkwZ7xVSxQydSMK8ItHqMvvNWBjnwV6
+        xvKJurogA+7uGw+qbgWpdX+zsA9cL9PoUk443PLHQPwJtD++wlH0fHBOdrszNB8fkZofg4KxM3kB
+        pcPRoXgcnwMP3xtRJ8fp/ccPY0toG9Cxbi1ZdHkF6HH5bOBbU6WfHq8Wv5N3sLvSI46lu9GI13vT
+        QT8rt9RwbQMo0LE0SGEHqFkgJ5RzHznrLLoE2BdIXI39Kuwhci4GtcMOAQ2olg2r7BUhpRRasMTN
+        FcLiXh8wEuRnvjQ4UiEeit1PPwzUB3AH+boP0etxbAdmzl4EjtHbJFoEecPdsUfgIVkxkYtNZ82F
+        As4/Pxd7+4s2DF++BV8/h25B5jTzl8801zraX3xO+fJqdgm4Fa/D10+YOL+DudP3HTCRsBLCZnLC
+        4Qy1OXmhlb5Y+ahK6g7GG3f70z/WkkH/Cg/PZIMv0r1u2I5mtpbF5EqD3SxyytKRgZeiMRohcc6Z
+        KrGD7r79Fgdt2A0ss8NeQeMS0PjrPy6/evqHF2ZT6eGnLhcNljx16U/ffC7TVYakEABS1oE9MAMo
+        CB4950m//kM1G6Y6wlA5reiW+yxfdHYNwLe/QLeWdR9Ykivqz5/G293nAqYUyzI8WOSDkXY6WWxn
+        5gJk8HEiS7p2c/k+qZp2idoDUlcLyemJzgeweh1ran/9kolo9Rl6142PNM8zc9E6nq4QgCJFoscO
+        1bJ/lCM83jsVu7n/al4/f2gVzhFF76MxSEL28cAs9w4Re+8+MOMjFfAcwwj//LAlXlUZ6GFjYzu/
+        JJZytB8aqCy5pli73PLpJewKuC/2HfYvwhhOyWZJ9NofPeq0rgKW227M4E6YdxjDgxuyjWAv8P7u
+        jtQJ4Mea12u5hdY9PJOW34dBkuwqA3ZvidixXJfLQPd22ucm+9jbz3hY1lf5DAXdqImSvDYWK/d+
+        9NvPRFaXTzWeRiOD6J51ZGHr4x8/QYs2+P3tF53C4csvUDSrhawlvwTL1jg+4aV0CTVNfBvm1ugN
+        LXlmEw2wOFpMx7cCfEq7oFE8BtY8qqUG5/IVYHuZ9yH5hMABIlwW7KR7Eo6t3TjwMM8lRlfHCjma
+        byMYd9ODbr/+B5fyBEEtFWpUbzt74JtcIdD1HYkolLFm9DRNgMdY3mPffdOGh0m4wAVsTCLcrydr
+        mQ24A8/t1caOEstNB/XLA35U3//pbYuRd38FTbm1KL7Lu3xGx4H98ceNUM1DfhM+BygeR0gt+bTm
+        XdfDBKgL03H+rbfmj6obgG/m7ptvTcXOz+oAfeNdIEhYndPtpXCgE1ORuvChDex8u9o/fiVvIQv5
+        vHo+IIhHbUSfrXKtiHQ8JX/qQYtd6mqI5R3Uv348RswQqyWa0qv+WoIV9q6ksPg05PUv3+lu9zo2
+        ZPCtP/4mAtXpOoi/eveXj9aXj/7osdh3AhzR59KQ8uapsPLblNqb45yPzp0c4OaeC/ir78P5q6e0
+        w8xLpG6qTfibL9SF8kDtFbk0DLqFA+Xkykljhg3gbbmHOnxcdOxqrcH5QKwI/vpRhpopFnO7dQBM
+        +20RtgHBz68P4BxYM1qH7MWXoQ6u8P7uj0iWtzhf1pJUQ4z3BQ7to5NLwcMoIc4VmQbTuAPffCWQ
+        nt0HqjW5bBZ/JZVQNE8Lmiic+NcvvoIt3vZffC4bJj6LHrJMcCjWlyanRUce8J1s0dfPeIY856EH
+        v3qexuLWzuX9Ol2gHudP7H/5ns+m+lh/+2OE0Y+VT2Ob2nBQtC3eVsJ9UOZcO/zxp3/6jcWoy6Bm
+        Vi729SwN+2HCG2iuBAvdTIeH0/29OsPX9XDG2xoE1aKzQwC23SAQnn7U5tsfZXBvSSG1CzIBGsgr
+        G/z420zvY8jFKC5A9Fm22Pqc54p++42gcAjBm9qdBrotShEc5FT5g0d8Lc8jTPzbFt2eSlPxUDA1
+        PT2/RqKDSxnyuZ9LPX16Ib3eUJ8vU1hAKFN8RcO330IfnpxA723ZOHqFE+C47UbYCeYZu+K0rr56
+        JdC/+gs7fYKsdvCtAmrhsMf2rD/4KHrnHfz2/4h49IHF02b+9nf5Bgdjojb0F7/+glY41jcRoMmZ
+        INAekUQg7NOBwd2uh3F0zNF26J4hU4x3oYuu32AXynSYRT+pwWvxVjRcv2DOfnqTtvsZG80wgPmV
+        HDKYBOSEsaRvrHFf1k/ovsOWuod7NfC1vCbw5xfY7O40km8JDzBkMqYh1Ix8OfGlgF//8Ot3tNYc
+        OLYD17EZ/vR9zuZZ2Wlp13U0ip4bII1qpq6l2SMYb/GnmrOPdYWFON+IqnyKkOVOisDXj6cZifR8
+        +VxEDazHffLH7/vpb/1c3Z7kgmtzkAInsuEdORZaC2WRz5GX9vrfv1MB//mvv/76X78TBm13ub6+
+        BwOm6zz9+7+PCvy7vJT/FkX531T+cxKBjGV9/fuf/zqE8Pdn6NrP9L+n7nl9j3//85ek/Tlu8PfU
+        TeXr/73+r++//ee//g8AAAD//wMANss50OMgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc9233c9622cd-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:16 GMT
+      Function-Execution-Id:
+      - yvvlnv17ahsb
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '18'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 23e5ab6873bf9bde0d2d32702adcf101
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 4f7afd2da27d1e26072a09f6de91c9d4
     status:
       code: 200
       message: OK
@@ -1405,8 +725,591 @@ interactions:
       {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
       can be parsed by Python json.loads"}, {"role": "system", "content": "The current
       time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that I was
-      created and there have been no new developments to report."}, {"role": "user",
+      reminds you of these events from your past: \nI was created"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I should start by reading the instructions_1.txt file to determine what actions
+      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
+      the necessary information to determine the next steps.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions to determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      \"I will start by reading the instructions_1.txt file to determine the next
+      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
+      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
+      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
+      next command to use, and respond using the format specified above:"}], "temperature":
+      0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4429'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4SSW2vbQBCF3/srhnmWjB3XN72ltKWmFAJtIFAVs16NpU1Ws8ruiNg1/u9lLTsO
+        NnVe53a+s3u2aArMUFdKdN3YdPJ99nx3+202XhYfW3n4+en5/uvDuv/45cfn0R0m6JaPpOWw0dOu
+        biyJcYwJak9KqMBsMJ6O+sPpZDRJsHYFWcywbCQd9kaptH7p0v6wP8AE26BKwmyLjXd1IwtxT8QB
+        s9l4kODp9mt9MJ4kKE6UPZUGN9NdgrpyRlPA7PcWawrHu95ZwgxVCCaIYomUjoU4OtjmDACQo1Su
+        LSsJOWZwKB4atJZYzPFXRcC0FjAcxLc6YoEJIA48qQKkoretsLjpyVpgZSz1YA6hcq0toA20n4wr
+        i9gD7epacRHvFA6kMqGXY/KWwZMKjg2XJ5D/CEG0pgwHUEVhYldZMLxyvlZ7XqmURGgmHZ/Ib/ay
+        JORrwx3Z3mMQai44Gqu4Q0jh/pqP994jzzmFW1Z285cu5q4RnQFpb8RoE+qOag5MtAcgDq2nzu0c
+        VA0rZ617MVxeyimtW6+E7AYiPq1WRhtisZtz/6Eh9XSUejHWXv/Nd1ORY3d9lxxjeNi+SCGrmjrh
+        V6UzNuXL8/B2jTh7Wr9EOULsQQ48Oe9wl+DKsAnVoosfZhjENZig4YLWmPV3f3Yf/gEAAP//AwDn
+        zGd0PAQAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc928d9db1254-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:36 GMT
+      Function-Execution-Id:
+      - pbmenv06a5yg
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '19200'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - bfb649068e555d640f6ad40b261616c9
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '85989'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.674s
+      X-Request-Id:
+      - 0f8563fa8b875d2635d106aebaf6c721
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Read the file
+      instructions_3.txt\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '273'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0yOQWsCMRSE7/0VYc7ZZZddq+ZqoUKhl57aWiRmnxrN5m2TJxVk/3sRWtvrMPPN
+        d4HvYOD2Vlw/hGL6NP8M9qVvl4vDcnd8Wz6/so9t8/hA/gsavDmQk59F6bgfAonnCA2XyAp1MPX9
+        bFI1s+l0rtFzRwEGu0GKppwUckobLqqmqqFxynZHMBcMiftB1sJHihmmrTX+0Le4bjSExYZbMmlH
+        Dbdn7yjDvF/QU/5lJg4EA5uzz2KjXA05CsWrvY3Kxyzp5K4PSlglsp2yausDqWh76tQK/yp53ZRy
+        lhVKjBpbH33erxPZzBEGWXiAho8dnWGq8WO8+wYAAP//AwC0qgQXWQEAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc9b398c12c5c-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:41 GMT
+      Function-Execution-Id:
+      - yvvlzurg1bsa
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '1797'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 87a5b0baa518b220c789956026d896ea;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89461'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 359ms
+      X-Request-Id:
+      - 6ef56affce707bafde194ae7d76813dc
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Read the file instructions_3.txt"], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '111'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaSw+zurKm5/tXLK0pvRUggM2acQvhahPItdVqASEESEK42ICPzn9vke/odPck
+        A2KFqFyuet63/B//+uuvv9usLvLx73/++vtVDePf/2N9dk/H9O9//vqf//rrr7/++o/f5/+3snhn
+        xf1efcrf8t+X1edezH//8xf/30/+76J//vp7jhadBheQmvNGyEW4TY8vusvLpScB4yaY3u5vuvNq
+        6E/+436Gt3ra0d3uZrF5Ixx5qL/GkFrlaQHjcdwZMLl5DdY7RzDnLcAtvKqGj7V+n/as4/o3kHTr
+        gQ/ibePT0rpxsJjAA/UqN4MxFegCbjF1qenCrB816dlBVxVavI/ExV+ubijKp+F0pLvZOPYMyTsO
+        LHbOIYEjMZhfz28Lr+dYpI55gslydt0zNBa3xNpRG81xIJGnUhYhqm2/z3oJJWuBF1esqR75AiPP
+        4SVB5dGecLHVn/6YR6MH78ltwK56mZMZzN4RBMwR8D4Qvz6zDhdFGZvhglS77/rZSvpSYe2rw4F5
+        u/qvnHNL5dkJDTXHl5wMya2MoKTbD7Qpug+bjreuBOFN8ugaL5/2pxTCz2Pao+rrSj07vIkEwO6S
+        YNe9u3VnRMcCPJjxoO41eWQs6qQrhLFY4VCPrIzuTM2Cr6yuMeoeB39qmGXAzjIg1oZKMtmX+x4B
+        HN0ITfGL9iPJZAvIYRlSI/hYNZ9jEgCNQEp46j+yOYp3OThtyYYaReKDcU9qW2WxLBDlILNkqt3Z
+        g96Ga/H+tO981g+aBvP74OEHATP4em5FVC0EGIFGj/v25p8gTN2ioO5o7zOx3tcx/OWDr12PTHDJ
+        p4FpV1V0Lz0k1p7uUwnAYLVkWlCTsa9yeoP94xBSv9TdWnDdMle/MZSQDMP6935DPfaxg/e29srm
+        04gjOLrHgRbqtmF09lMH/PLTKW+7nt1KaMNqH/tYv217k+mHmwPv3Kxgm5NBTxSr62DvsRtGwkkF
+        8+SmBsC5zhHerGjdHS5XB1wEfB6vBdeaLEXpAuJhEKj/yiljgT9a8EYsRiTl3IBpjS9MEzZj9LVy
+        RtZ8BnJYhVS/bX1zTmU5BrHfn/DOqDufBVXqKH0mnlB5yJ4Jk5ONA+22PqIvgB6j+ctugNd8KqqH
+        b92cw6aKVLJbMrw7YqVfELxWsHtZOcXTmWZsurNC0a1+JPAYaAm/BF8LFpgXcXA6k35mYRVvrnYU
+        E+kXn+g9dPDG7S7YT9+mKSpaIYEPZZhsrPxWM135TrAUPJOIY2EmIwKHBhpjadCbYwTZ0JRtAXfa
+        eCFwIEa2/XLPM7x0kokvyWD2i2efJMiJpoi2RTVl37NjXOE5THms37e8v/CvqFJTpbaxbjxIUsla
+        3sHIFCPqkF3NWKnZCOb1VcNFVK2nM7djmKI9IB9PI8ksAN+B/Eu/YX25hT5/rZwJ0gWLCNJkZKRO
+        Ea9IO3pF030wEtIIrgTK73IlDBxQTWSrvMLDC0LsHojeL5O9Q8qbIx8kyElQb5kkTbAoFYCNrhnA
+        YqrMhlxPamzIvdMvNFdi2E35nhr9RjeXi+u/4Zc7VtjrxaUehAi84SZfPoTjfVwvLpOMP/uxp5ab
+        zc+beYUmaTocnOcKMGfqA5DwJcZooyfmW5PbBkb19kq9KjOzaRbkAWRv7oBD1MOelCfxDVgMBGo6
+        S5ONX7y3AAH3KwG5XtaLGRVEMd6zgHf0Q8yBCRyCVzuOqZu5EZvCABrgYEkSxi+c19Pue/Ygaz8d
+        2YJTlywJ0QeInyNPbU7O6uUmDjkc9tghIidnPe0HxwC3UKMU49r0GaqKDqz7Tw97ha+J6iiKEtTe
+        AW1AEDNyzMqrKiZvB8HTmdTTPtPeoHnseawf84YxsHs2agZehMynbeVPZjy8wZl3CBnikrFx0MAE
+        j6cmoadsd/L7/iNWsK6pgfebU5IMoXK9wvb9dKm5v9hAeBrnI1xUtEWq4AXm4tl3aRsE2YPuvkZV
+        f4XDUkL5si2J6Aqv+rvTPQQfl46nmiY72bzfRQhK8HEgcNu8wGRrYQXGLg0obnYkGU9zZsDRPTtk
+        cc5DzdzpVcBUUEK8fwxFP6SScobxMN5QJfdtvYgwOMtzNOn0fr1k5gzMkZO33cWlxoOU5jSMtwBI
+        mllj3ZvsjDaPQwmjTWhgW5Hjnk13UMiGWr5xci6qemHehYAq5zQcpHPPxvyTBnCtl1ib1SJhfLWD
+        ED8pT4Q1XoMZDw14PUMVI39vJPOlmAd1Sg5n7Dfxs56eV3sALMQZYUm7Z6LPYAlLkh2QyonPbPo0
+        C4Qbn/YUHZnGhF3yWuB5zCDidsPLfF8eUgshkwx6tNTQX6oiOkPhkDc0JMc5odMd5ABfbjtsuLML
+        5jBUIAwksSOcdviwmTW35ldvkLyf7/6UVfsKtL6nYO2rmsmYy8IE3W/g03O/iGDIVeMNbwZ54eB2
+        vtSDbFSlau/vPNXYNa6n+eGlMPwqBKlneOxZun214EOXHr1OHWFsqfRCreUsQ6q24bIRhWrw618I
+        PHMbLB5bIrh9DRHdlfOzbnFNRWh8xBCdSXvoh9/vF7tqQJNx3NXTeW/mUFOOKY7H9FOTTT0FKg7M
+        FFtvhUtmJY0mkD68LbWI3voTH8lnuJ2MDeo49ZLRZ+bG4NZeOeoZC6kXQ51EmAc9wqY0BP6w1NFV
+        PYJ4QBvpEyXz2xN5GFdpT3cxz/vz7/+zzTlDnLq12OTO8Ap/PIWA3pnsHtcGzE7yCXvJ8VMvL1+O
+        YXJnd8Itk2suxkevwLoeafW+rYcmP3O/9YgvlCBhVWaWkLNURAMlLftpejiefHxId3zPwrofdJQf
+        AdgWCVrc+cvojwcvnfL58YrJtu8C/eGx/WPg+vFhHHioNa1OM5lzGE2Oex5ybzMm0nmMzLnmNaKG
+        N8UjQBhvbJbNZw69LmI4R2XHOutY5Su/Gut5RNl0mo42cOWA0tNsHOtpCZ4WXPeXAL72+3lPegvK
+        fLzH+/vVMIkADQvE2Vem+xYRsMBFj0AhNhPNN4LNlu231yB4pwwbS1OwwTpLZ5BfjRPdXUu3XqAj
+        tXDJ/Qua9ZPmL0eLHeFarzBeQMoWKRYgZHL3Jkr9UurJd4gGMg1BchC7lz+2L1mBa7ywC2DCaMCr
+        gzJOtkH3trZLWIgnEa71khoGsE3eiEsbcmn/obZQCMkcNKUGnkApCfAfn+zbwm+gVFB10Ni0uT99
+        QGuA+nq6YH/ls3laBgXaTNnQ335MYDJTyBIuJD++WjDiUtgOAYcUJ+R8NvPdBKXTCPF+a2UZc2+i
+        p5pNVCIZwATQaznz8OmyEs2U17P3feMUMDELH2vG8dXT72cx1NIZJHzeNef+93vKUwx6bKc2rteO
+        fobmVRGILNhyQl6+HIFFm0e8Z1acLOaxROruUww44NJvv4RolsA77GokKHeFUYZbD17QI0dbR9R8
+        gRPSRrbv7pc6pbOpafO4VQpuCx2v/TFZ4gR1SgHCLw40fqhXvpeg5sZnJNh14tPKKnIgJ4GJj+lX
+        TUa16GOZ5s8cceGw9df+swD/aR6o2/clWzymRIoDp5x8t/DJpvf2GEM6NleaXZUNoK9AQnBy4Aeb
+        cBDMUZNqSVl5mdoytbI1fzr4FFFPzUs7sUHu1RSiU/Kkgd9F/hTW/RlG1/tItg+16adSP3lgLxo1
+        deu0Zf3aDyAjyQPRbfBly0EreYi01qLmySTZzAnpG1q3zZ0GK5+Jm1CTgOigO7ak7ZGNTBQc1X8P
+        FY75qM/GNHh4IK9TjQhdMIE1/gH43hODHKm/ydhRJxXMYGdj5IkwmT/PtwOsXrvhfNvsAJ+9bwY8
+        RFGNL56Gslb60BS8L2qMzYqavXD/5AWM1eVENp6zA9RsvQHkrSGTJU0qRl57OkFfHG2q9deyHg/n
+        A4KpOYfYcfUZMKsNINSf9pHizd1j88lxPBCi6oEdcSeAKXsfNLj2CwRf0qeehvGAoPU6OUS+Jo+E
+        Pq0cQVVpH3jvaShZ2vckgs1npxD6Ko1+uquBCG93M6HhLgqzQQfTAIIx32Djnah/+ENxsgFihPfH
+        bNbwwYCbz14hW9Pz+snNdpb6UE8htoNeS/jDKY5U+SKUqAGjnVFFP4lAHp8n6oS6AubvCzrKlztX
+        2Hg3JhC+sC4gVd8QbaeHzcTgmSFALPqgeBu4gFXjx4LbF4mwvfa/KZVgA87325UmKOzqQfiULdwq
+        lxHVKx9Mb6RflffXWCh6Wh1bPO/bwUVjI5o2ilGLcHEjsL6PtDz49NTi+BjOu+sZKfolzRZZO7YA
+        6rOB3S18gu/DuPGKmDQO3vncLfvpcVB47gt7TmGZQtCUhmoERUWdQ+wyJiZSCj6eFaPJpz2bxE8l
+        KSUtQsR6renHXXe3oeLIDdZPb2bSG4oq9VmWInXE3QmwU/58wwg5HC2OlcLGY/osYKo8bRp4pQ62
+        6XZsAT7QCBu7uWQDSRfnD29LFTebbD+VUEXv4/1XD3p6zmsRsm9r4Pz+sXsxFd8D3IzinobhE2Xz
+        o2+GH8/QlUfBJHzKTl39D6wThzOZdXqmAMdTQFE4XMwlkLxSSafgSlha+PXUbaZIwct8RMu7qcGg
+        +toCS+4m4PU8JrV+OHi//EeSvzUzVs1TA/Lgi6j/3jb+koYJD2SuOeBLb5XZ3NzvisKdNYJtzZ2y
+        pTgtNkwFKaTGFFUJHU+XAm4G5pNfPWTJ9XYE18/5jP3NDfuzszsOkHi3Iw3f5pQxhSxI1b0jR/1n
+        /gbsHo8RxJdsR+bwBHz65b5nuD12EzWHzPC3S+UW4KFzGfWoCGpSbAII1/NMrfR7X/UGtmCHLh11
+        3UDpR1h8DWjuBZl6Wjj48+qPgP4TaNTGUQVWfyRWsU4GjMikmUuijccfH6z6V0+EFx8iqEcaT90T
+        6XrS7F8l7Nwh/KOXWDVLDbyqmk8Pif7JBjo+IFj7EfaEqvUX+yoVUKzfA/YhX/fLa/9ZwKuKTzSo
+        jQAsrdp6QKURT93wvtRTxHUKKNHVRYNXPhkLZT2HihX1ZFkajvXGIbvCU6wZNHUKy5+tpC4Vt/Ux
+        GRbX6afTXSrhrU25Vf/U5vBpFAjOpDgid9sDQNDri2A7SzwBe0QT+lEONmwiL1z772zSEEsi0MXJ
+        xbddMPeM215zwJfXkh7zU8n+6K32XL6Qn75rc75/jvkvXzF+lVU/F32Vq0frecF/+r3UMwfsG9XE
+        ubQJkoYPxgb4b1JhTUFiRvRKXaCy+d6xeS6M/rPwLw22eZAiYeWZHu7eFrhVdPzxZbZ19tFZvTwq
+        SIPy/swm2zrEcPVf1ngOYOabTIQuJ2k4P88Gm388o96abI2/WYuzlwTyyr8Uj6W6nveTBcMjkgnn
+        741su7/JLYi+1RcpMtPM6f6+l9DCLaHOZVtklGMBgQknqtTU+7Sfniuj4cMYYUtTLX9SfWcBf3go
+        h13SPcxogZyoi4QdzFcyp0Euwdo5M6QM+yd4XQrAgWKIdDQrHTEHpd+2kPeITd3I4JIf3/z0xeq3
+        NdkoHvgJZDtlxoj3cc8Y/4nB2bRtAj+GwJiIiQSm8FMSnouBOQT101Z50ZLRNj7ghAf2VMLpeI6x
+        teizOUetUsHjQ7nTP/ms5qcUpkfepXp4yvztygtgUYMtEudiSL5wthoowfuBrPHxt2kpnmHwYYTq
+        ptLXLDq6FnQ5RSOCQkpAY70zYB50HfbIEGbbaynzUFjKFoer/llaueig80wXcqbLhg3f+NaBU6W9
+        sa9yKZilTXKFOsiMlU+ajNhHApWIogI7YK7MlWRzpXvZOUVUuWRUvjotsB59jNRr+1z56VzA11np
+        iGoKGCzKBSHIam6mtivs+mXUeQjjvZHTnXg/sG4jZgtwLraJ9/wDs0VdwgXAyz3DoZ1m9aCXGwn0
+        0R2H4O4j9vn1v+L9Dmho9M9+Ifo2gOfG87Bd2Nd+tknLw/Zdu2SxznW/fCK3Asv5UdGdQjTA07km
+        v/6ODWC/2FJNTALaHTCixrDvp0fCFQDsTgk5gvGdLcTWCFjPH/35Q6t+W+DBUiRqZPeDrxjRMYct
+        DCu86z+7lbdL7df/qb3IWs0PltPA9qlE2HtnQzZ0XzOAZbPfYzOTHTBHcZiDGewSJDYQJrPQnG0o
+        s9Bf92NmrM7CCa68i3W46/uvAWUJnobLkbqCfcvGp1EcQbt7fKl7uGc9Lc6zBimLEbWov0mGLi6c
+        n19OFE7dJjR/oQZGyONoGF20P/UE3IXSoemqB0e1qGOgFJ8b/un1RRMuFjDJuyPjGfI9MT5uCZ4i
+        xnTPrGX1D2QCc+NcYqv3x4zpNU9AVAtXqqtly1Y/MofSULhrvzKyPzy8bJ9vuodTBJbueFugaQY5
+        NgVxziY6Xjg4eyamJp/xZjcczxGUY7+n1neSzYV7VAE8wYtEV7/fX7x7iMDdtVXs7HQHsND/nH/6
+        nWyp5SaTbHSl4nsHQL3U8xPBL1MD3IXKQcxZrGSYnMQGi87v6Hkysc/A7vsGMRxVMqDSY1twxSlA
+        Uz/R/evKr/ORzILHPnKwFX/9bAoCeYE2F450RwIZrH4OBMMgP8n++zX9LeM/EZzxUOJkfE3JNJwb
+        D85inuJ7Ze4T/guaCgT3PKPZK8dsxs17gtJ7krBLIqEnZ2vDw63VBTSUPc5n9C4juNYX7DvfExhU
+        WzVkspsy6j8mJZne5cBB/Mm+BPLknvFTyrXKbuEv2H1tjrWwqeQINC/+jZE4AZ+AUS1h1y0H1DKc
+        mT/eh5dTgKi9tGnPPnWjQXb92NR7atSkr0cy/fz09TyVgFzFKoBawfk0vC04+1OPDunnQO1LdGRD
+        xHUS7B7pm4bHy9dcDol1hWBeCqIOMm/+mSf9/Oq5r91s+MaHVln9CxzwmzqbvYWdYVT4FZokdvOX
+        7q0eQXgVFmq83Hc93CrfgPsj90D1kFX+cnsInmrK3Amvfoc/V/dbCjW+fRG57zVGTgQhWPTh7r/8
+        kHoWLGio1RvbODLYMKViB3kwedRb/ZhO+o4RkIbcpXo+7pig4ZsGNb53SbwrFfCyuliExnk+IH6b
+        XxIy6hCCjX5V8ZXsajDtzkoDzlwu/ZnX/PwctTjVERG+hlEzx7RFEJru7TfPyparWCGw8hOSvPxt
+        EtdOWvAdD2+0Xf3ERa/USV7nBXTXBRGbaqZP6vV8SJG41j92UM9I/ekz/5dPzi4foI83E13nN+bw
+        0FMFHidYkSb+9pmAYz8AODc5UuYH4rOEOi28h1RE4hU+s0H1nQnWxreihiKIYHxLGYL3Y27h0577
+        ZEuVWm/gbPc+WaTomM2nOdNgp0wCalZ9uXDioYITf0kRiE+VP+3HxlG/Un/ApmlvAZmfTgSqHGoU
+        v0q/FhPiEniu9wtREaz6dZ6CoG2IALXxuDeZe+M86A/phfBc/fQpuOIr2JdHD2faVQWvm/CqQBxf
+        9/TSIgRY/r3aEMB9gLbbk56sfm4Ano+HTPiE3eqFE28l9DawxenlONUDsUIbxgO9UYvlKBnvnL/A
+        z8QH1IWh6W/V/HSF5ZXm1PlgzRScXJ/A437eYe162JmsER0eiKESo2WtdzNM75Hc97xM8bc89tvv
+        IeCg0hwY/dVzNhpMAfXGHrBjvo2Myh0pIGzLC37stmcwaS/9CutgM2A7i+7szzx0rXcIeFZnTmbc
+        HSEjMfjNE+u2Pz8VUH/ThGxeOO9nq0t5eIInCWuuV2Zz31nXX3yRcCy1mhyJyYHr9qz8mX/+4e11
+        3kL3SNtmcw8p90cfaW2F/T/+4VofaWZbT3N5mvfox7cUS58poxuGIPzyxhXv13kPQ3IIYXp7GKiU
+        LcffrvpJHet+g/E8Dz2p0qCB2Xxo1v5PQduUZa4m9SMhYmFL9dSwwIDC8+GgWdoZPb16wQKb0ptX
+        PfD9w2fKb74ZODzXD6vTDn2sTmijGE1P3cKV1LAJ76jbtd+kHgYjBoZ/e1ONQ5tk2mdrf87ROiaK
+        F3/5yKkDhkC5/fwR8Mefkw57k+qOb/78wRgcJ66ie0fUTIE1t7fSpAUgFNemKaRR2UGtfn3xXqdi
+        8mf+svpL2DvSlzlrUq1sV78CcRs98dl5Jy4gdASEjQfRfIZkk8CpVSkNEuCYlCufHtxUd50if98n
+        c7A1G+j0Y0mqs+Gx6d59Y7jqMyT0540/KcYwgcel5Ymw+tvzTjeQ+vfvVsB//uuvv/7X74bBu70X
+        r/ViwFjM47//+6rAv9N7+m+eF/9NxT83EciQlsXf//zXJYS/v337/o7/e2yb4jP8/c9f4M9tg7/H
+        dkxf/8/jf63v+s9//R8AAAD//wMAqjA5m+EgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc9c1fd9513d1-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:41 GMT
+      Function-Execution-Id:
+      - pbme8b7quow8
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '22'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - cc893c79eb41c92650396b5ee03be018
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 6b8a366fd1c0a7253e3a77e7fe91d0dd
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "an instruction to read a file named \"instructions_3.txt\".",
+      "model": "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '136'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6XQ+ySrPl/fsrdvYt80ZEpYt9x5fIl90CijqZTABRAREFuoE+Of/9BJ/JmZkb
+        L5AEqOpatdaq+o9//fXX301a5ln/9z9//f0quv7v/zFfuyV98vc/f/3Pf/31119//cfv9/+7M6/T
+        /HYr3o/f7b8/i/ctH//+5y/xv6/835v++evv52N1Y6aULngfEKWAS0GPVIyNoOTLIRchxdrIdH3a
+        tVL2qgWIjeON+dqClvydeNk6zvcF0xV6abnbigXoS1fHQFQtGrv1zgRb4G9CDK1IpxXa66gyVi3Z
+        XQtcjli7CNCtq4DZlvZB0zsXY6S6d4P5XuC0g2iWnZx0kBNj+N68SQtGFZ2+9ZW5r6uKpOHxkmTR
+        tFWyD18EDecdOiIJJy7br9+6sSw6jAE9lyXxhT02vuXxKSlVOLrMu62bcii7Xgfm6B/mv3zK6bN9
+        X8B3yw3ZjR/bm0JLruGxLEs8vd4LYxBeKpa37CIQEn27lMM96FBg1gyfcHFNp+LCZfT4fm9kf8b7
+        aFLoFdDjYr3plGVVyQSr09E5wHu8cepLND6kJEO4B4dK3eR5X+RdB2g1yAnePsV0CteBCdMlDYnR
+        2arBTeEzIeKlW+Y+BiMVvWNjQ1xdB6Ll0QXx5jReIBf1L3Hd2zLtX/0mh5N65mTXWBWfNMrXAPz0
+        xRwzL52kSB7g9/zFMXKN1Vj7R5RU+z3beuIb8dHRMlj3k8Z2U7nnzJMMWbmzuKRD8ymN8X5+5xB/
+        ii/ZY2nt8V07Juj3/lnOXiVtfUNQEu52WLmCwL+/+CgBbph64ULKZQhyyINcxGG/xeXSG00fnuvH
+        nlmRjY1eO7w7eOkjMD0/DN60bq4PeWnRhm0Z2vNlIlamcjITHy+rW96OhTuGiqOdcoI3Z6EdHWcD
+        UFEzYPe3badDcx8BjdjZEK8xnXaiPrHgFUsnYi+SVTTsZFOFVZHbeNP3eco/2mmC16K+kD2rmceH
+        4VKj8oAL5m1HYgz3vbSG4TnesbwZi3JqPkYHYrP6YqXEGz58d/4Bzk2OsOAcOm9CkmBCnvhbclO1
+        K+dlxyXQ2PvJ/IO4N8ZDU2IIP2xPPCUevekxfip0lJ0XLm7xN+IqCA9IcnVBrI/BI2auWYVI8I6Y
+        fXk9jHHEga1QS1sQK7kr3gTatoDs/lwzcoy+3qjadoaMNCYUdsXIxz6WbXTR8AIrZ9yng9UW9aII
+        DgG9wPGWfrMXFcA8OTXR2NErJe+2keVH2gkUHVZLPrjuYVD0fXZnZuC0/LufDg3ASabMXy4vvFsd
+        1wmcFJtQvvUbjy/4OgdEiUfc1/WBBqSe1/BtpwPefLc7Y/pUmwady8Egp5vF2kFyn7oib3Z3PNlm
+        gar7XpKhfN8ObO/u5XKKXw0F12/PZFuiZzodSE7BMh8tMyyr50NafzKob8aR0moBaPQv8QPsSdTI
+        7r4N+AjHswjyRfcJoZh5NNbb7+bh8zudz1M5jOajAhQLN/IHn+SupohBO2FoNJUvg0mu4OPFX6Iv
+        5A6NZ8PNQVjLQPb5C1ImOmYN5ES+dCz0oaQI1iGE/aki28V3Mij9yhaQT2hg4RhPvK+vJwkmnWxp
+        2GSjN4lZvIZ1mMt4PO8nrz8pewsVqzwnqhU3ZT+1RxXi3tOYlwk6+tUHfNnlTSx4knQ0bKNGdStw
+        pltO3E6acotlcF81c76Ljnef62qCtDlciHsNIz68yCsED/SM7a2XEY3lNaSw4zdK1KtYlQO3lxME
+        +1hl5nM6cY7ffYXIe3xQFl5ufHzd2BoqagXMOkmLtqP68ojYGWy27ZYRmo7ebgKqsCcj35VqTGn7
+        ceX7+8OpLMHQ9vX1JsLu2jp047uFMa4KpMuqtMqJN8ZVOfavqFLG612j0+G0agd/LHW4rlGER39w
+        jPGrpxdw2spkMVoH7cc0NgU8jvmBuJfdCzFz/a5A+Cg3Zsz4tzwGzQC6Zq0o65KyZa8jttHSMAOW
+        zfnl4XHpgykHIVPjrc/7UjrVwJkesS3/vtrPOShl9BFNyub+4o3o4H7lV5J3bH9Knvzt2ascqGUs
+        6Opa0HKIlGYCgVlnou77VUmnpV+DH9gO2V/1jTEKdD0BrC4GC/L2WQ7n+Dih56embO9hlXPPXuRy
+        b9zPxH3v/XRMBZ7B51mssTTne8iNdwErb7Um/qYayvH5FCQUg/kgPlGf0Xt7Tpo/+dwi7ViOIW0e
+        8hl/41//Mab+UXRwl8kHI8i8iJvCc1CyS+ASTIRbNH3igw+768fBqDGdUhTfzQDZ2//gZfKp01Fn
+        IUVdrabsRHd6JA3GVwASvCJi7y9rRCenOSBqZRoLtcfG6yAZJLjVtoyVsi7KQVufGvRQ/IiYB2J5
+        0xOtAfpun2B+1OpyuBifA3TFxSREqqt0PD1cXw4TTom9cvR2fE9WAzi9RCzd24L3FffLHJRbdSAz
+        PynH6qQ2Sia5NlNX7FOyW7vPwYpyl+DUq1q+azcXuSmqNxYOb2TM8c2V7mwCMUJLjppkkwGsuUCw
+        dD0Sj0qD0qAl3xqMXKV9NO7rhQA9cjd0+bHA6Hayr0NMui0eDsWn/eIuzwBOa0oy92zw8bq7N3AQ
+        kichisKjsZRuFTJershUaVmiYYmRKRedF9NIPj54ZvmrGmr3llP0fCw4z9i5gAUIO6KFkZ8OqMwA
+        AlW44POJx7zbgN5AVmwZs0RH9oYDUh7II41GDE/eRK/65A2wM3Jgqs8DPvnSt0Ots/fJXB/R5Dlx
+        CGa122Lh0yQR3UyNjEYe1LgX127Em9MmgbxhBS71c2zwrb3xUWTtGqrEx3c71eNbRPp6uJLD04tK
+        RtdiB9Wz+xBcq4bB/ciSkCz4VyzxRxbx+L6jf/DD/tqEs2+Cq8063gXM+6yXBuPC0gZq5RreJHHB
+        Jywv5F9+mRpkLPr1P0jiISB5Q8WS1pbxQLR1WmZvVqLxwSOJ0ca1M3bdCk9jyl41wEa/dUzNb4XH
+        78XnCJd9/caLAuttJ+ieLaenrqDCku3SYXk7FmjdfHYs6qEt2cV2bfT02ICXbTikDZezEAVO9Gbe
+        3s4NTk+rBqbM+NCqNKuUsQfR5V0+GBhhp4p42SERtppgUHHm39OXOTraxfqEN96zSlux3uXwBLfC
+        08yPaK/0tTzzL7aPj++y115ejM7XMmNWr2yMwRBCkEvKBObEb88QvdKp0YyvzKe5w4e6yS2kbSSb
+        wpeF3nS8lxfA6tYn1t1O2nGRnFxwFctj5vWpGQO47xBer9PEfCVqUn5WZAoGpAWe/F5Nl9dv1sFL
+        DAJCwHkjHpbxV0l106OLeli0tHifjrAVjjcqf8E0+A8PRaMXiF22ddvZy1FQtMuRk3uXGO2YE9UH
+        pgYXgsWlVvJ2l1qA7/qXjg46G0y98wakY30hmpRMEY1PdxeS1aoiBoyux5OsWaM5vsREphJ1wqGq
+        Ye5/VF4cX2gcls1Bzpu+YK5TsnKY8Qcl3s0hekCUaEjrZw61tNrgcmzLiErb4AhITK8/vhz1bi2K
+        EOekIG7iX8speV4H5IGazfmhM5/cWWjzfl/YVhj8aAymqYJz4O+Jcz1BOe7qDYVXLJ5YvEybtlso
+        Gx0JGkloT9OnMb71w0H+5dPj7sGbStXC0JbayParOi3751OSQEpXFrNf9zCiyfM6QdRFS0yJoKSd
+        1C4FeYOXR4YFFTyaMITh5T33ZK/pD2P0imIAWLCQlmr5bXmd3wpww+WLbRXJaiW2W+qglFNOjE9E
+        jX6xezbK6tNJJPCHj9f3el6gxU5KsXg/de0QWD78zj8t23uRDu9TUSvZqGFiLnqZz/xFluZ+QfL5
+        fQbtbFMk4YtLrqiReBes2hyFubQjW7rT09UxkQuY9SQeUK6lvFipJmSamtFPxy8tPVJfhMvl3lPw
+        gk/JygWLkbzZ3onxqqT0V2+oyYEwX0SRMRpxr8qa7tbEOikPb4pF14ZZv1HJ1N+z/nvp4O6EO+XN
+        tYlYfrkK4NR3l/gzPk/NqnfRRuEvOi1kHw0qvCk4EToyVX8PvA+9MoP9wUrwRjVOxqwnVbQA2P3w
+        LOULPmTA0vrO3HD5LWt9YxwU69utie0MWrns7EOndOJzTfy5Hrv1iA5yoR8npom1hfgpfmQy3JyM
+        mK9n305JOMSox0POtFg3jeWsv9Ccf7ary2c6JgFTwTVje8bvNh1hK13AOT9bFrV3PRpCTZbl9kuf
+        NDS6fdTlRfJAh+03Z/45iI1pfR0shSzyAxa6Wxfxjr5itFo3Jyy9OjOiw+IiwfLNEQ28/av9o3/b
+        zVclhnxUeR/vsgIVAvPxMIpKyzrDUdEtlz3MHpFUDqXzFkD/SDJTaxpzrtKTBe932NOVEWvGxIvA
+        RK+ApVTAnKWUL1IBNnh1xNKsB6czW1uAYrixneb6iP/wdDoOiJ1iGZfNfS/I6ORsTabl0RqNeNwd
+        ZXYWbOKlhtS2x9XyApPyEPBQnt98murSVv70PzOFlhmDGit7O/2QX/3MeKzCL94Oa9y0E6OtDV9D
+        3bNw/669EXlDreyaqiG+KarlSheTC1qgW0VHdwmcH/qvjCx/JeP15fXwupnPbYL9Uf2Dt5yUUQFQ
+        iXtyXvle2tJdjtGtvzaUqUvqffjl8YCTmAjMf95W3lgRnKH2nl6Ji/29x3dyKEHuhTXxL17mcYk4
+        MljPxRvTwzs1hpdmSMiAa8HsEIHBnw76yva72PzRy5P2CDOQnOhA35ez2kpOnetAL68lc+b+M1V9
+        0sBgxiXbBpbhDdf9+gtHFt6ZnmVmK/br1xoN5rFkrpCoBg+u5ADKrT6wGU/TP/Ux83NGPq+gndaX
+        nQD9bksZOWtpyi2hWyP3Y0zMthAph/PmKgEbh54Q9PgaL99RLDkKkoEqxVE0Zv4XAh4Klflhc2n5
+        DeuVPAydgBfWJUjHOF3bIDDzzALtW6RsceAXJLS5iseFsmynKt9gmAK7wqhMPcT3ahqjOHl7bNY/
+        qNeThYU8CRV0g5qYj62ghUDlrUs8yNponNpMle3jwsCT5cRld1zVFYRk3bDAQSuvyoZBQsX1/cBC
+        WLy9aXHqws3M75n+iWNOhfXnCEKqCXSTHpqWpnZngTRpR2aFuIlmvlL89CbbpbFsdKOYg+zsmUV+
+        +RiPVRbKPbI37MZONZ/xSwUi0QVutrvK+Ag581HN3i6Z9QoajVZtlEnfb8l7I2eo+wBIiAanHTnb
+        T4T6T6qZ8ExaQnZaevJGp7VkqOrrkzj54pEONWw62DyOX7pSPscf3zii00UtCc6o7S3fE/7Cgx5E
+        dpsUweutyyGExWq5Z0bgi+2ESVpDwXhP8HUTG9yTPBmutvwkeLQcLrb65MMZNzELcCW29I0WPmpU
+        dWS7p2yg5ZN4R7RdvnyiBhmJqJjla6gruqXN9Nga3Su3KNiXd8KcOibptN3gRJ7xi9h2zr2mmV45
+        fPcoZH6DrJZX6BSC6YYPKl9DzkfTGB+K9pU/eOW9l6i/mYMEl8utx2W56w2+21sXuLRayayDLhrD
+        oT9acCNCh1cbOeOTuF9mwG3JIlut2Rmf+r0IEV1gc+bTI5+0YKPCZhHadPF5BeV41O4YLtnDYm7E
+        DtHKjywR0eyLZz/qU44/vfrzL539afA+3XpnwY2/JFzP/UT8gCgBXfgm213Oj7Iv32BvZn+AhubJ
+        85Zq/JGR+0pTRuphUU45fl4gnwQHawk4fDoGmgDtplHJJf5yNMz6HBJ0R5j3+gvR1JdcCKIC0+F7
+        w2VXe6m/mvXhzz9EXU0vB1Au9/jnxxksXQYU3komE6IusTGU17FAv3o3qu+h/abpuZJnvCZqGC+N
+        T3J+YnhGyROjY92X3XU/fJWfH2BKxSMdVtI2RrN/x7C/KDnL2Pkhj0LdE3xZHFJ6C3kGmdi+ME/Y
+        ineb67ZC5yl40HaOX78quApJ8Dkz85vylG6/FUDoHwLiaKey5cvn8gK25+aYzX4Yz52hAO8kEean
+        Mm/H8ek3yMiFmmi7vOd8M+kWpLrlMVsPJ2/ixdVCc/8geFJZO3XaisKh8Y9UeTyasvnxg/n8MGy+
+        cbtpeqgQlTJOyDZvW2rV4VpRjuKCWZmjGavTy1lDsx5E4j3qxOt00agAi+6ZbAOr9AblkxxkbXIu
+        dKr6TcRPcZND4VkGMTb6FPGfHqq2MZ79zrxt8mhj/vw09vOfupvz7FB0Gy7sfGwaxK7smCDyORjM
+        6LRF2ev+rYHsXq7p5SjZEQ9W00HBcXBlhvGp2vat2A/A6s5nu5KS6M/5ifmZEI8ojHOJaPLv/FA0
+        mJLBiu2zRtuLe6Cjt3+Vw1PahIBt6U/+vcnr0hgVXNoxg3xGYzqUU4yAdI+5n1QlS7JGBpPrFcO7
+        3m7Hu4N1SNnTInqUBu0Q9mcMZz2kzBkzyeuN1m6giVqbabO/xs206tDsB7LZX/O4ekdfdBylmOj1
+        pi/bd+LlMBqhSHB/Do2fPyJfHOFAp0G0ouVc/5uieSwwPy1Dg7Ggr+S3kzJGztfKo+bjVsld0ke0
+        KUaVi5Gvh+AHrsP08Omh4XNdDfBMPgQv9tIDdfZyI8C0kd9se2Vqu2x6sQI5/ZZ0/LbUm+hXNsFb
+        NJzE1yMzBjZoE3RE3JPbM8GRSMVIRGrAJjb7IcZoZ332w1tiRqeH9/HzQwdNgiSKvpOMeE3AQk2y
+        kQh5SRvev1zxgnaPzZouyutQDns0JdDYg85cSf8i0VfNB5rnIWR/X7l8OfsdSMgeT2Js4GL06ZCo
+        kFqjQZ/BtS65M1gVrAblRRUNXrzPn6hDquGffvOhkhcr24Tr+SowbaGcWlaSASASli3Tz+4nZeFR
+        8SGPvY5pG2JGP76A1quqZtrn8TD66DSJoC1HNvuTPp9+86bwpZ+o8IjvaTX7ySi/iRnBXqam06or
+        a4TMy/sP3534ID9+9cn2u7tj/PQIHAt5hfMiaNNpsdMlparT5x+/lmvrKocVhB2d+WrZLdXgq/z8
+        AWzHdTRUTQiwfiZX8tNz3VVhOgTfCei0KlblVxqWDWiBuWVq8zEMyXIOOkplEZMdWtpozJ+IgjA2
+        mNgtoKgLD8cjmJ0Yk9tkXFKe2tsDJPEUEG/F9+3oX/ICjJicqHDPrlHvX+IC4tc6Yvr3AO2sV0XY
+        xerEtkquoP6Xf+tsPfGEApL+6hf1YSIxe+UU5ZS2T/unL7CQ0cabonKZKz+/UT8KJ4PzW+NDMZ0r
+        hte3NaJSJE/gHA4K5XqTpysFjhW6relAJzyJ3uQ3zgFEgwn4fDk/2g/yhgqCYeH+wdsOH9sQrChz
+        SZDd+3TaLYwOynb7xmzme1Nwbw4wPSyD6bP+mPKbLoE9XRdYCdqvN2IyXZRe4AeiT5vE40wsGvTN
+        pJFOyUYzxP07nuC+X2G6Ru29bbTX14XVsHjRVIlHo4/TtQtO1ryIpUYMvaqyMGG5V2LiyHQ0pnOw
+        tcBIj4RdA3OHhg24XzT7O1jkPY34xdZd2IVJileXs1qOVvY9wipPKTGOyI+G9YhCsPG0ZH5tHWc9
+        54W/eShdhsHoDaMYA8zzix8fMobgSBN5eT3kxO6UJx/mfgWnGnTmHeu+7Y5x0MDoPgsc5/iIVoHb
+        SzDHm+n94phOL/dU/+ZvZHsPS04/1eYLm0l+EH2Xbr0+VJzZjwRC0v7t86EVDx3qzKdFy7k/TJtt
+        loEcLTjm0svxBkd1ErTXXEShr0xvpOwLf+Kz3Xnf9I+eR6+bTIxbpJWdISTwm7cS5zefCaC04ed/
+        +VtapwN7PmJlxs/Zn36gQbMWLmjCU2X3UbH43C9NVKVFytRKbiPm3lITZr5PrCpZop/fofz0I1kQ
+        DS2TWv8q38PdIU4S62jcNMNRkUdpJHqTjQZrqkQEvcYlVT6TUUoKvQpwHWqT6LbQlF302bpwPxoZ
+        wc/zth1TAWW/fkDFjITtyDZyDFEXLPE61KTokxjbSpn9ZIZnfKCxqLu/+mUaN4xoFZZxAy51Oxy9
+        h287HJJHJf/w0gmEvmyCciei6/P7mvknS2nHc38D4eHMYlnwuPQYnzV4PPIwms/nwOXsgIpq3czf
+        ++Q//YpOfp8S02mziJ9ejoyq9JEyI/3c2nGeX6N5/kBMLXm340VYx3/wVT+aLOq/r0MOfaztmReM
+        qJx6ZtqAe8GhC8XoS5Y76wLSyVTYzog1b7g5nw7yCRxGmC3yGR9c5e/fVsB//uuvv/7Xb8Ogbm75
+        a14M6POx//d/rwr8O7kl/xZF6d9M+rOJQLvkkf/9z/9ZQvj70zb1p//ffVPl7+7vf/5arv6sG/zd
+        N33y+n+v/2t+2n/+678AAAD//wMAP1WwTOMgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc9c72cc71244-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:19:42 GMT
+      Function-Execution-Id:
+      - yvvldstgvsvm
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '74'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 1dabd53de4282b519b0b347d06fba149
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 93d0b7b83f501e32a6081a99294f07ac
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
+      Use the command read_file to read the instructions_1.txt file\n2. Follow the
+      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
+      limit for short term memory. Your short term memory is short, so immediately
+      save important information to files.\n2. If you are unsure how you previously
+      did something or want to recall past events, thinking about similar events will
+      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
+      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
+      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
+      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
+      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
+      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
+      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
+      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
+      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
+      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
+      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
+      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created"}, {"role": "user",
       "content": "Determine which next command to use, and respond using the format
       specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file to determine what actions
@@ -1423,8 +1326,8 @@ interactions:
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
       instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
       the instructions to determine the next steps\",\n        \"criticism\": \"I
       need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
@@ -1446,7 +1349,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5540'
+      - '5471'
       Content-Type:
       - application/json
     method: POST
@@ -1454,15 +1357,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4yST2/bMAzF7/sUBM92kMxJmvm2YZcUa4EB62keAlWmba0yZUg0mj/wdx8cO0uX
-        IEOvJB/fj9I7oMkxRV0p0XVj47v7h4eK8unT6tF++Zrcmb3kC/P47fv84/0eI3TPv0nLqJhoVzeW
-        xDjGCLUnJZRjOluu5qv5arH4FGHtcrKYYtlInEwWsbT+2cXTZDrDCNugSsL0gI13dSMbcS/EAdPZ
-        bHUX4Xn5ubFcRihOlD2XkkXSRagrZzQFTH8esKZwWuydJUxRhWCCKJYe07EQ9yccMgYAyFAq15aV
-        hAxTGItjg7bSFzP8UREwbQUMB/Gt7rHABBAHnlQOUtHbVtgkE9kKFMbSBNYQKtfaHNpAx8lesul7
-        oF1dK87/2XMUZRi9JfGkgmPD5Rnnhh30ByrD4biLSfev4XdguHC+VkdwcZCTkK8N0zi2FQhCTbg0
-        bqziwTOGp3fh3+DKMo7hMyu729PV3P+ILoC0N2K0CfVAtQYmOgIQh9b3YiWwBlVD4ax1r4bLazul
-        deuVkN1Bj09FYbQhFru7vD80pF5OVq/G2nd+4q0wZDhs76JT+kb1VfhY1TQY/3W6YFO+vMzs0Ohn
-        z/JrlBPEEWTkybjDLsLCsAnVZsgbphjENRih4Zy2mE67X92HPwAAAP//AwBqGZrbNAQAAA==
+        H4sIAAAAAAAAA4SST2/bMAzF7/sUBM92kMBokvnW0xBs2GF/D/MQqDJtq5EpV6LXpIG/+6A4WYoE
+        S698JN/vSdyjKTFH3SjRbWfTxcf3T93janm/eVE/v1Tlnyf7+cP8k/vqn1c/MEH38EhajhMT7drO
+        khjHmKD2pIRKzGfz5d00Wy6WWYKtK8lijnUnaTa5S6X3Dy6dZtMZJtgHVRPme+y8aztZi9sQB8xn
+        s8UswfPyszBfJChOlD2Xsmw5JKgbZzQFzH/tsaVwWuydJcxRhWCCKJaI6ViIY4R9wQAABUrj+rqR
+        UGAOx+JRoK3EYoHfGgKmrYDhIL7XEQtMAHHgSZUgDb2WwjqbyFagMpYmsILQuN6W0Ac6dMaRddRA
+        u7ZVXMY9pQNpTJgUmLxm8KSCY8P1GeQ/RhCjKcMBVFmaqCoLhivnW3XglUZJhGbS8Yn87mBLQr41
+        PJIdMgah7oqjs4pHhBS+38rx1nsUBadwz8ruXuiq7xbRBZD2Row2oR2pVsBEBwDi0Hsa065AtVA5
+        a92z4fraTmndeyVkdxDxqaqMNsRid5f5Q0dqc7J6Ntbe/s03r6LAcfuQnM7wOH11haxaGo3/OV2w
+        KV9fHu8oxN7z+DXKCeIAcuQpeMAhwcqwCc16PD/MMYjrMEHDJW0xnw6/h3d/AQAA//8DAGvOn0w9
+        BAAA
     headers:
       Access-Control-Allow-Origin:
       - '*'
@@ -1474,21 +1378,21 @@ interactions:
       Cf-Cache-Status:
       - DYNAMIC
       Cf-Ray:
-      - 7cbda5ab893210d0-ORD
+      - 7ccfc9ce0ba71101-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Tue, 23 May 2023 13:29:39 GMT
+      - Thu, 25 May 2023 18:20:03 GMT
       Function-Execution-Id:
-      - f495scdawjjo
+      - pbmewb1rp8v5
       Openai-Model:
       - gpt-3.5-turbo-0301
       Openai-Organization:
       - significant-gravitas
       Openai-Processing-Ms:
-      - '19949'
+      - '19929'
       Openai-Version:
       - '2020-10-01'
       Server:
@@ -1498,7 +1402,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - 0128c66c9918142a24cd829bbc2b234a;o=1
+      - 1cc694f7ec27d332fccf8ee536d2fcb3
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -1508,13 +1412,457 @@ interactions:
       X-Ratelimit-Remaining-Requests:
       - '3499'
       X-Ratelimit-Remaining-Tokens:
-      - '86449'
+      - '85978'
       X-Ratelimit-Reset-Requests:
       - 17ms
       X-Ratelimit-Reset-Tokens:
-      - 2.367s
+      - 2.681s
       X-Request-Id:
-      - 438ac4200d6062dd394f5ffe9944af58
+      - 097693547d7c7d083fa14613bab59e0f
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Write the
+      task_id into the file output.txt Shutdown\"\"\"\n\n\nCONCISE SUMMARY: The text
+      is best summarized as"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '292'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOTUvDQBCG7/6KZc6bkH7HvQkFRcWLB0WRst2dNmuTmbAzocWS/y4FP64P7/vw
+        nCFFcBAar6Hr22L1cJ3XzVd+mU8lR3lb55vn18fb9incHe/BAm8/MejPowzc9S1qYgILIaNXjOAm
+        y3pRzeq6WlnoOGILDva9FrNyUeiQt1xUs2oCFgbxewR3hj5z1+tG+YAk4OZzC//qPzypLSirb//I
+        cjpaCA2ngALu/Qwdyq8zc4vgwIskUU96KWRSpEt9ItE8BE20N8rmmJOi0QaNejlsUjSJlI03u9Si
+        Id9hNDxoP2ipJzWe4mVMRppBIx+phNHCLlGSZpPRCxM4EOUeLCSKeAJXjR/j1TcAAAD//wMAWEdU
+        8m4BAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfca5cfb6a117f-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:20:09 GMT
+      Function-Execution-Id:
+      - yvvlzdkld8xw
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '2345'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 935ddc3ec26e3fc83995dd88cb4b84e6;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89455'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 362ms
+      X-Request-Id:
+      - bbe6d9f4186af1ddaf62b36bb61890e7
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Write the task_id into the file output.txt Shutdown"], "model":
+      "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '130'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6WxOyurbl+/4Vq9YrvUvklrDfEFCRS4KgiF1dXYCIoMg1AXLq/Pcu/HadPufF
+        KjElyczMmGOMmf/4x19//d2kVZ6Nf//rr78/5TD+/b/WZ49kTP7+11//+x9//fXXX//x+/wfI/M6
+        zR+P8lv8hv9+LL+PfP77X3/x//Xk/w/6119/F5tXSPeh9AFzeAYDmNX8SYIhE/uRiWkM7wYqqO5+
+        9858zdEAsF4Saj0dkwlL5JmwmMsNkiTNMyZdMgj4Jq2NQAWfbFZVhJTR/g7Ys8mjX3YtKGFGhRc2
+        wL3s5yJGGti854AipMz9tJd6F8K9G9P0Ow49IXOUwSd/2xBOi01HJPwNAcMvj9SuXlLPkr2uw5dC
+        GgIFcHIme/+YYIB1kZ5255DNoms2kN2JjJ23d6yWz0aNoBrfNXw0QBcum+yWQOejDNSYb3JFRKrZ
+        8HxRdggi03BEUz3bIH18D2SjsT4c+ucJQveiyUjU08SZbzlB4L5DW6y/+50jpPm9A6/ok2D9uI+q
+        qftaHZTqd0/Ddb2UNv0AH+0mJluZ7irxPk0+5MxXSS0cJwbNP/UA46sZUvNGMJjOCclk3Q01vGOB
+        bizSBkOwPWsT3XtHAibwYROUx6nF561RAdLARgMT7ws4SkwCFlOJE3As3Te+y8CsBOVbcABYRow2
+        n7tm8NL23gFJ7WZq0Nu7Wuj1UytfNkAajY3vTLuUXcAoTgPWVNlIJ+htCCRf5Y3x5uGzJf5MAmT1
+        ssOnY+k7M4CEwOFbQuxU8AkYncoEUsR1ZFnjMfPOx4Jp01Xk00IBMHEUdUgSMcOOVAiMETe9wK5G
+        R7rX9mk6x4kcK+cT/yZSDUG6vJ5+B86DfCFy9JaqxcK7BiY0k+k+iK/Vn/1498jCtuH26WxBJ1eU
+        u+xQh5uZw6IijGHBig4/9McQjplxESC6XgndBYMXLp0vT6AVDhg7p9POGD1NjMBbdBfEJ5sXYG7w
+        UoB/ozsy46FkHVMuFjiVtYtmPOhscq9KA8p0HkkjFV/Web1cKG262eDjY2ocsuTGpD5kzcE3ywVs
+        7lRQwyUoAZF3ZwZYwGoTxv0R4EMY3nrR+vBvZdsdXkSBAqim08cv4ZqPSKWXIJyut7sN3YsuU43W
+        DZuqk+xDJZUEfKumDBA83HXoClaG91029zN73i6wS60O8QnaVGyWtVrxyyWnOKyLlO7g3G3UzfNA
+        pEd/6Udq1zZkZpej5d2/jLn1Zl0eppqQdgPuKfUECULj+Wioye3rcAFH4kJDfHsIvL1vP7n3b/bb
+        D+pVCzUan8t1CKxdjLXzeapI0JAGdlenJePyeYcz/hxiWfCcMzWLqaqWPFJymOGhRWSgOGTZ+arD
+        AT1sAnuLC/tXeU+gxe4v/KirOl2eHBfBXYt8JJxDHXTAmGNV0h4LIbde7Zmpni34FK4dNa3hWLHN
+        JpAg8i4JaU7xPp0HGzVQRfGO3qxB6JtLZXbw3bsWaSRtNMbUCUvo6c4Bm3TpGSt2GwvkL+dGuMd4
+        YCxwOgRmLSww2pRmOE9ERYBk4pG6cLDZENFbB89MTenuPIisk/vHAh3Ef+g+OpXpdPrEBUy7DqHt
+        pqiM6XBhzQ+fiBS0g9OXSTDAg8E9kcQ4AqiUmAIMDA3RkN7e/fI0rAAgNQ/weh76yRhiBI/E8xB5
+        eYMzjoczD4LEvOB9GDvOOn8bWN9YxJaAnXD5iEIHPdOeKcLK0RD6ieMATbQjjUdPZERtrByW/PZJ
+        rSE/Md79TBpc8QNrn+0xZDuJTtDeLjx1PdPrf+cJuoKdUXx6i+mwwHv0wyt63+taJdxOTaaIYWJg
+        HF5jMBxPmqWWA+/g/UEIwslXWgRtoz9jjxc0xoeCwMNwDCCRJAqcsYgPOljxhmzcK+pnpOqZ+t4f
+        MdXEpgZzt1ciCOgxRz2jXdUP0ukNIYs+iFXXQ89v3/wC66FUiRAxyIauFBbgaPyZJp8gSaep2k6w
+        lus9PrxF0xnn6kTgNXrniHb3Z9iF75kHR9nvkJBtD44g6EoCMd+d6a54js5AgSxA3hOO1ArbXSW8
+        8bLA2DIcbCf+DOYDGwNQZFlF3V7WKno1HR2eL9KOhvf33mHhkyl/6qM+wCWlO60uYH63DKyhuQDs
+        XUoSDFLjRRbmoWowzXxSTreS4mOy8QGzhXOuPHIAsMkbj3RBjjAB/qIgjA5tkQ77ZuQhTfQjdSc7
+        cOjJdghQdHFPTSPVqqG8DhM8Xp0M78bdno3aUvtwa+jpn++i4Mm8sj8LEO+P0egsSxAHsHKhQaNs
+        ezCWfdQIkBu6Az7eSM5Gbg4GWGEJ0JQ7x+niZ2H3q59U+1zdSkz2tgZMSmOMGRj7qdXlN2DcfFnP
+        mwOWLRoluD+wJ9keo9FYunjKVey/DHzzVDWc1b0JwZCWAdpcD0lFP4qYwBVPEH9WUcp6Y2updk5G
+        Ut9MM5zjUjqA48lesLEvWoeqhNMhwfOGOm5bh1MQyR1UFqjSoyqUxjQVGlTxWNtI6G9hP28Nkskq
+        eE5kcgrECHK4BQazleLjfhiMmZPPCdQkQ0HcpnyHTO1PLrR2IYd3OE3T2QBuBhb5uyOty0RjURst
+        A7I4N1TL3kU/WbJNwIdLJjTXG9izQbMioGv+DVvXU8omcuv+nU8Gb02AEniVYJXAGIemJjHGvOAC
+        n2Js0ZV/VS2jlwH6HDuS2meWMZfDkyjCyy/+5Kcoo3sEtrPdYP3ZeimNpnhRNKIBMt/Ui8G8GtSQ
+        H+QXxrLLV0tefjg4WdYF67v9i9GjXC8KcDWC9/FJTKdij5UfXuDDpw6MRTbuyo9fUpfc/XR23CYG
+        fX4NEN2ofT9JanxRrrTB1L5NujN/ho0L2ufmSvd5wqomBNqg5pWjY1sVzs6chzKBQHJ8au/VspoH
+        FJcKzl83fDsT21nyXLbg9zsE1FeaORw4Ie6gZkOHJuv4Xz2H+Ps5YSwMJpjx61wr8HD6rHhTsLk9
+        UUt5b/ER4+jgO3NwXxIlNWqLelnQOSwdPQVE3zml5lkl4W8+IHPGEBu6ZrDtjfRvKL8mjeL4NvTj
+        WW05IMQuwZn3ttJpAMEFRu18wHqhXMJtUZiDuuIbtnpPZyPXXjToStaRuve6Dnufnifg38lA7cQ/
+        swZHiQ2D5HDBzma2KiFuxw4uQyUTapuLwdj5aIHQdl0altuekX6rCUDN4gg/r/U1nZVLJ4CXNKh0
+        /3JsMFfxWMIGLTE1kVqx2W2kSVn3m560WXbIZ7ON4LFAMrXcmIL1/DagyHOETQskYIKeSNR7EtR4
+        Vz3FcIpA4f7JN+n0jXvm6u/yx+9JekkyNgpPQYBTj01syHexJyeKBGDkRUq1Wdyni9fPBXgeA59w
+        bqIbMyxUHhJfyDECs1gtZ7+wITrdTBR8eyed4iPzoeVHM2riZGRU6myk4L5+YjwBIxUKcCrAnV3i
+        P3yaiOXmDdxIf2Pr0fMV2xzPHVzG+oZ3HL8P+agvBcCXSoWkV/ZKB/ABE8wo/8JpDrVqSZPj9IsH
+        mS76kU3wKiRw328VNG+XmZHbqcnByqf+1K/luMwIZMl0oGd+ycJFWCAE+Ps9UZP77IwhuRwCOLzf
+        Jn3aZuAwPeMk4AMer/HGbNgErwN0XEEhChc5gFR93wEHCR963F7acOWfHbQbOtD96dtWH02vCGj3
+        8IaD52mpFndTDQrfAYGeTN1x5uR21BWRf1r0oHRGL6z/94cv7oJhDOciPmiwF+8mTib+0c/NXLyh
+        LLKGQM8c+3bQMQSx5BhIfolWvyT6LlAjn17JtoNDuBy4N4F3D+cYPbJn2hb+MYLlftljN64n1u+g
+        3IBl/2BkpjulX5RbVUvaYPhEPT95sOLNG7S8+abe/bUAVnGvSc3iJUVFcxWNuZxeNfjxBXOfXnty
+        Er0CjOeWUTe8tmC4v40O2Gw+0Z0FHDAfn8CE/m3c4evkheE8p4YGyUeRsaZY0b/5EipSBztf78yG
+        S+pBqHq3iu7wUILZ0zYRLM8LpW58EBxSHrMa3m4gxKcNkEPKy8VB7Wr3iFGLO6OrWBeBp+U9qOVK
+        dj9F7FWoL/Q+4OMFyWzl84V6TzFD0su5g/l43GhyGCGBWgt3T6eItQXczlaDb23Qp5P1OnRQSuod
+        xlFtM0EGoQXB9VBQXciLvle6doCJ/JSIMMm6I3QaH8NT+XZpXMBDz8zdQQPr/Ih0TapwTL5mDHhH
+        yKjuCnHImJdEkLvWGt4XvW80d/6kQzsYTIo4/eLMm/OT+5Mfnig4jkjMSwMZxy7UHJZdtazrVTKP
+        cEQub0a6MPtcQ+OYX3/+gSF+bCjA06siZLZAD+a3yS7goYNg1Vc7sM5PV4QSj0RNd5XD7v62hOOp
+        e+KDeD/3y6qn4E63bHpwznL/w2PVeDxV6rTcyWHjJdFAfco8mmQvkk7VaQ7geOx4jJ/i3E8LnzTA
+        3R45FEvFkQn3K8vUzzfqCLFOST/H5WRCam1abPOfLmUXLJSQe9YcUurFruZuy0vwot9iil+W1E97
+        7cXJVbkZiJCYiInbuU0gg6xFsnnmQqLfBUspklxC2+tpYMRxbj7MxO0WbYpGBX/ive73n/rdej5P
+        YJRRjoAVzyfxZChg1cd0tyzfcPnGMfzD73/8ctWzCXR7c4NEbr9N2eW4EZSxJGfCHSTWj2kYIDW5
+        pI9fPoVLop98gNuaR6O/SZx5PNwFWB+zElWK/AWsCUNdlel0ob6OG4MpJC+gGfcBaRiHQBXSOYD5
+        146pbT2WdEr9cwYLVnZE3alzP4zfwlIDZh/IHAxjuqz6GCZh7lOjvM7GYKs3Dcz365l6/nOTzqpn
+        NFB8JgOp+loEk/TJAqhmSYSmyvQNsgS+D4u52BD1YwjG6ud0QJobC8FeLvpZ0/sBepqTok1Ud4xw
+        1p7Afn9+0XRbuOlMD/NF/fE3d/WHxlIqfPga+4L44u0ZDvI1UiB/4md6deMCLHtUWrCKNjo9KbbI
+        luksTXDVr+g+3x22fZkhD5rX9kRP5jkP2+TpDT99SH1v7tNpY5cxxHpBKNrOOpjR6JnwZD+/KP/m
+        VkioVyvKqhcoOsQxm91hrME7sG74IHdojXdUwvr53JJJx5ZDV70H5IB6+MhfGGCTqwh/+Mt5ePXO
+        4oqjJq14Sj0HSelnFC7JTz/g68vpGLWFc6ZW3M7CrzVfJvcxX2CnHRHebY2KUXObZNC5KzrGq36a
+        tnDi4WtsC+wR/tYvWRRwPz5JD8I9cybzcrHA6mehdsV7vrb9RZUjUtHTbkY9A8lwgdv9JiT84zn3
+        tNiJNjil5R7HwWlOSbIYAtSLBJM3Ug0msn3YKS84hNQndZiyxym/wFqoIKqnRumJIRxK6FTyDmMz
+        9Cvm1JkJJ9PmEPscmnC64iSHZM922PTVGEy5pfgg2GkVvm6okE6DcTcVPtxO9HAOdcbukxRAzqxK
+        RE6tzQT66Tiw8iscfurKYbQYdeX25lIkHoZXPzntwCuFWjVEsGeOTQ+XHiDg7DM+PevBmbR+GmD2
+        Eryff9bP2438hrVUfamzOXtsYEWRg1Vv/sn3Fo37A6D25vLTz2D0T48CrucFu+Q+hQtusA0/6UUj
+        fPNSjPki2Au8Xt6MxhtNTJfoETSwSrgYqcnO69kYH3i42Q0l3Vnp2WEotQ4wi6eU4h0r2FqvLsB8
+        jSY+RVvNINLxMMBLej8hcDyKYNkM2QTDyBVw1t8/YCiuXgDtZhyoLnFTWmteb8FBywRs3FiVsi5U
+        CkhyfqHn1r8b3dm8vaH0/miE8dbEplU7wCtoZALHuwIWswt1uLenLTYvqANE9c0EBBuLIjaKl5S2
+        Ymcq5xZm9OYTvp+mHmZABY+J6l+Fq7ppB5Kfvv3tdzofbzCBB968Yec7uhX1xTiDEi7eK7+rwoWz
+        PKJcyXdG3/0wOKze7HzlMyUZPpUHAKZcY28IImNEfPvCPZ3cRVCjzzzR014v+qk91DGAZ6xjtGiC
+        MV+IacLIHHp0Wfmt8H5OtvqL7+76MPvtz5/MXryHT3ap9PMkAAXeUqWl5h74KXi+Zgkm/aPCTtqT
+        /qO4gwWpvH/h1b9l84OWb6ijoKfodPKdsRnzAa58BXvoaad8JOYR2Om2TU/lzQiFenAsiNmHYXdX
+        duH8coNCfZ5DjE+9RdNFLXYL/GbNFo3oaYfsZDuDYvmXmYY6Fo2pW3gLxoIT093Kt9j367mwPj9e
+        RGyWqZq/22sM342zIYWltaAJma3Ln/vlSo3PNa3mA50yMExvguOi3xh//KdWMDHdf51nXwNHMhW7
+        XWy8C9ylWrDkliCJUgvvuIvdL8dOKcGqh+nqHwC2fQ0aBEi7//Tgqseng3qp85rwq97/ozd/fmSx
+        3DRjqaqB+8WH2rfNNqU764OggC1I8bW+hh1kjIMv+z1R3Nu7ajIGH8EiyyvsfqxT//Oj1ffszVhD
+        Wv5vPrD4lY/kY+kbfHE6L+r+ufWp4cz7cMXjAkYW2aGbut8wGk3+AqOctlSjB2QwKTjY8uGuKQTk
+        sOiHb3nzf/UO9UMuscH9TDoU+zRCqvItQ/pN7wRKaYUIvwdTOKz9EshQn2HUcrExrO+H8OH12AmS
+        I+M93crBe3Cuf+YjLndPkF/Xzvv5UcaKfxlc/UcEX+Kt+haCU8PnNfgg7ps34dzMTQ0zIDpELmuh
+        Yll7PqiT4L/+1LutY76ImmqvDbVWPtRfjiIP6+4VoG3cBs7c3t+FSiYY4b2Q02q5jr4Ou5tzoYf+
+        xvr5mpwVCE1HQZu3/ElH8a0Rlbu+tZV/oZDcdq9Jffv2QE/Q3TkiijhXeZiSup6PKZ3j6FtAVNwd
+        ur+234pdLlYMt6lByGCWF0BWvwyIdnTG9vn5AYM+7XV4jd8nbG2KxZmCfIrUMWxzjCi994v43WUw
+        vX8nMn2uQzUVp/sCV32Bd7VPqpp6RIGwCS2smfhhrPwzgpJXyAi+rYvR6S9egJz+Eqk37y/GBB7q
+        AQ7L+46T7f5jTINxPqik2c7YXKrKWH76rkvtDkEzfFXLgdDoD79QVn9v+V6OB/iKvgkaZHffM1/0
+        czWHiK16n0+nhz9B1WBvkUgnSXP4Xz1b+Qf6+eEMciwGsDlbq17rnT/6hIK9i80hqAH9JIoLKqwA
+        JPihl07LEHIwei5Hsk2Vig31AUlwgN8bUvmodobVT4LMbHIcTiIHBnvXwJ9fS763TZ3+8BmWxpRQ
+        4/7+OILZhdpP72BTurzBcMVBDkudQqxf47PBlpdbyh46Uar58xYsgq7EoOEUH72XRUgnXqo5cPOU
+        C5nQrLFFBqkFayulaH6QK1vWfhncNc5CNrF4TGeuzTSQT65NFmFkbAkGqYCfJT5iG0S7UOxCpYRw
+        e/Hpw0FxyLSiDaBTgR3++VerX7H88B1riZ5VE3m2GbyYNwPNrS8bH0FcFPW3Pq16d4AICutUcDUL
+        AuLeDJl8CLrf+tA2lPZgmi1XUj5LckTF6u+xpTUQyFReID9+T7W4q2FV6DzZHqJbNa79HPDTS/rx
+        M4dM6nQXjOVwxqGuVaz59QPd7Z5D5YYe03lzvnHwLaMH+vUftvhzSKAmmiPdtf7dGeuXM0Cg2AAf
+        k6dgtMvRF9ShqmoEp24A7FWeY2h+hgQ70tmoJtSZkfr2rQHv9p3M/tT3XDMDbPi6wIjv5j749Q+U
+        Vc+L2/mVwPr8fJHN6X0LSfQIOpl9aIVt55H1y+VkcbB96hbe1RtYzS8zFKB+vSzY+xiCM/7Oz8p3
+        iEiNgS2DhxOoRdyW6l1/ZSR6JA3s/QtHpDjx2BK62wnaz17BxsrfPl81M0GeHH0iMzkN2+8+EaDh
+        F0ccyNyHTUeT88Fc3GNCNnrb0+PIfHW71w5//Ew2NC6CQhU42N6rej8n1DHBy/rusRM7bTVmIDrA
+        DeP3q79zqeY0TBDsPOuKb7T6VtN7p7zV1b9Ei3bZ9Mz6wFo0X9TE9uNVgcmZ+wK6xBB//dx+u/a/
+        QFp3Ejaa2qsmrVo0IPu0pMbKH+kG+5G6+kvojYczW/PTBz+8/vGvKXtXFvB4v8Uxyy8GW1oHQQdy
+        C1n1zM9PhbD9GtmvP+vwj2zIwBj2ORGTZ2QskDEIDbH20DjveacvDjsdrv4H9c7+ridq7JhwLlMD
+        nVtfdmh91HRVV+4etaulcEbzmb5h5g0c9vzpwGauvejq379bAf/5j7/++j+/GwZ188g/68WAMZ/H
+        f/7XVYF/Jo/knzwv/JMKf24ikCEp8r//9e9LCH+3fVO34/8dm3f+Hf7+11/bf183+HtsxuTz35//
+        Y33bf/7j/wEAAP//AwDnoBEa4yAAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfca726b5d1041-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:20:10 GMT
+      Function-Execution-Id:
+      - pbme52vq34dz
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '252'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - f738b1af12886297fba45c0ea7b50048
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 9c5ecb63a4996b946555161a4a7fe863
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "instructing to write the task_id into a file named output.txt
+      and then shutdown.", "model": "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '157'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWxO6OrPm799PsWrdMm+JiKRZd8hJ5BQEDzg1NQWICArIIQGya3/3Kf3v2jNz
+        4wVQQpJO9/P8Ov/xr7/++rtNqzwb//7nr7/f5TD+/T++1+7JmPz9z1//819//fXXX//x+/3/nszr
+        NL/fy6b4Pf67WTb3fP77n7/4/77yfx/656+/V725oV5tnPvZup446Y0g9MVLZbIxbPcA5/jxoMbh
+        5iHm3mQX8euCp7Yuryr2uW0LSA6PA9F4bGqT08YL2nmrG5Hl3tWWA0leaO/rHb7bluRMOedI0Kub
+        G3Yyw+wZzy4v4E/8SD1FMFO+wtcBjm90pvqs92hamR8A17/sqZWGSzrzTVWiWfXvVI1CFa3txEuQ
+        DLsLtqRedxYJ8wAXneTUFWxZI9VcmKg/XlZ4tzm8tGmOViYM7HbC7iB+onl+HARo5/eV2jK+a4PT
+        317o3tUr0jm5iTZXV8zRQT0/qasDjqZ4mSfoHjD5m0ecprN5ehWoDRwN44ey7uc8dVwpMcsUGxLL
+        2ZShKIeRZyXFtf5O6SVcdLhUokP35kbQZvRBLlRbTvM7Vr+0Th1sETwfLGzjsOpnxwok5KzME/YP
+        eRMxTVNeMO3qjOqSDek8PMoX1LnFcILmN2LD+6SCH5Yidoa0c5Za00MUNzGP43rca+tbkwsomjnV
+        X4LbWlsS7pTBzg5zsllwHS3vgyehZgwSetz7Ts/WaZFBk6uNz5ST1zNc5hIU/kyxPy4Nm6vrp4O0
+        f+bYUmfPmdk0cnAooxTvo1uGpsjAJjRD6ZF1aV6iiefmEyoOr4S651xwll0VCNAvmon3kv9irJ2b
+        FkoIJrrLedWZLafUkX48b+jOPUE6V6eW30qNONDDw2kYu+JtAIN2TwibSxQRrT6E0KBJoeo2kNFy
+        53QdPvhCqbWILZoo3AKonKLCt01xYNMGFTbw55dE1fTTsGUbygsyH72NNeelpMuedBwqYsEj41Gp
+        +3lssw69s+VN9dp9pIM72zy009rGjv6YtMEXeB0M5+T724pMGt0psYVW+0zFmbHhHHLTL5ac36YB
+        B/VlFwmpmAhwCtsDVWn67Kf9ZnSlraMN2Pwwq1+TR+Ki6Dxq2PykqrZOXhcV1b3kYnPmumiCuBYg
+        s8qO7upVxZhdblp4iJaJbw9nz8b3PZTg8WkLvOfkKZ0T3A5QOWXlz5ePEvHDqswAr88JtWPFQ5NH
+        VHVl4UykKu4+0SzmMYFVr2+w/cgqNu3fE/nFC8VeVWgtnIkC8T6TqMkNp4hxy10HLpUDf1JVBbFT
+        pOYIdbs9dcXHLprN63iBK1+6eE8Jh8YYz7osdue3/5zajC3GW5TQgJecoCJzqilZdz6QdVr5nH27
+        aCwszRKOIdcQoSPXiJ1jRGBlxxO+eHndT7tPGMrWsU++4yvSeZ0/dVktdpQaSyD0S67JMaRmjKmX
+        m1dtcYnqwstJrv42My9oulERwMK5SHFPVhV1LYVAJoBNpGkUojE73ziIz1yBjTy8VfPzOMUIicXo
+        VxFVNebvpxOq5quE3aDaR0y3tgKy/fJGcdd4FZtfLITkTSzqhXuxIujALnKVcRuyuqwjRORDCXCM
+        CE/GdWFHkxgYFlx7DxH5SYJ+pr2ho8urjbGhHiQ2nrybCtsm6Ol5LQbOsvZO4i8+/JWQtGiRzc4G
+        Vt88uveQgaaIheX2ect87M7NCbHrc1zAwWKDTekwaBPTmYpOvHmnmnxg0Wzcaw5amqypYcynaCml
+        rgROdDH1FraqfvkObQ3+ivd2NERUT8gJbpuwpRrPHfv5/nR50G3iUXcqSjStwpMA7mNK6dGRN9q8
+        M2/11riX1N9G8dDTK54D+coXrv9s76m2THAwYZeSBeuLI7M5iHoFXq40U18qZjR9VESQjcOaHjJT
+        QEOFHwPcr+2RXiRx0088t72AmBoLtmP36MyP0Jpg4MDB6mR76bqZN4JUc7xE/bF+Vb3wvBEEZmDS
+        S3ld0tE92gC7dFj8OXXbnoYPj6C1dS+pd2oLjbFXKYLUSIMPrqumG7GxOdiYi0C9z3aJ6BVvQxhz
+        yaD2sN1WE4VjCK9nxOPdg06I3cIPgbv9MajaZJU2lfMUylvz9aL5O1URyWiQANGOFpFO8SlaaLQK
+        EFV8H7trrXfmbaNOEFavlvq3tulplus+FL5WYk3frNFwtSmHolCxcPRdjyFdngkI27nDNli9syii
+        acE8xzb1342psVmgi3SPk5y6WWmw+VkNIgRrOcW27vPaeA9vFjjh+oL1ojS0teccLtI3H+L9jTyd
+        KRw/IezVilF9ce5snDsgwH2GD9Z4TWVUeB4JKrOTQOOctFX/G/+Hhh+q6zczEpqNwiF1FT2xxuPa
+        YVu6VpDedXtsGPK1H4xKCeRbqn0IfxZSxuqeS0CWCsAn6Cs2vz/GBOEx2ZPNWdIjdntdfLjfrB7r
+        d5MgMu95RU62N80PnegVffOPCc1Oy37fr40rmplwmBSeenI/aIu4tyUoV6ue8HFlVutfPrleK4Uw
+        KiqISR+UILbuFTIJoqWxcfYlcKniY73ddtrMre8EkYlL8W/9SWrjGL75Al8a847YDms88JfzHvuX
+        mK+mkt/qkvi2A3pAJ7NqiRpy8F0Pv3dQ/a2HnYloYVv4EMVuNS1bxZS5D/lg1fKjdLiOSgHbmBl4
+        h29jxPbXswXx2vIINye7tP/mJ7i1TCXybj5rS2xfF+lchTb1SLCJGNxF65e/fCFxg4o+EqaC53OW
+        32uwr5Yzsy/wiydDF4xK6IzhAkF4qrEDs1ctbz4upWYME7LNV3rPEzXhoHwcX9i23jeNZamToCUU
+        8q++cxAh27iDoJok6srqoSfjKgnQ+TS9qDkve2cJVTNHP/2kXteORgE9CngmfoqVFRf3v/8DoeaB
+        2sGUMLb6JC3KnaOJr06Sp/PSMBFeDyOkWedwFakVJ4enZJ1pImNZY/G5LLfbush9NjVuP8fuFP7q
+        vy/m5TtithEHqAvRA5vP1kSzbu5cdL6ttlQhY50yVIjcL99Sw1BbxlzLGtDyChdfTMMw4uuDN0Bd
+        XM9E+KSlMy9CU6NXUTXYUTZCP7LnEsDlIq6wWV7DSKj9lQW+Pj+wxT0UtOzlvEPN47mj+Ex2jG3S
+        QAfx846pXpA2Ig6vCdDzMu/Pm/M+4nWJS2A/ydFvftkG7qItLaF+pNHaPjHq76cLZGO/xd6z9NL5
+        +iIJmozoSvgtHvtBqZ6q3OXZhSq2p1bzO0l0hCNkfvOd4iz2xu1AiM8X6hz8tJ/dcpUh5VNfsaZb
+        XUqiLg7lZYMLvN+M94iJjQ1w1i4B4TxTQXOeat/8xKi/6VZRNErLugNthUqMy6DtJ79VYri9hZO/
+        Psdu+tWfueS8tQ1pmH3WlpAlA4TnvYrNy2ujLaCIElCmC9heB1w/zo8dD8922P3yRTV99w9y8sTz
+        txwoziZxWx0K+9IQ8UI7bRxuBQCe2wf++YW5SCQBwvV8wMZxWtjcFNoFCC1Mv9g0Ud/vlMCS5faU
+        4syK3xU5c7ILXJcLBH3jn1nHtETxtjmTwYtOaeduZV2iOFewb98EjV3xHKL+wb9osB9SbTluTye4
+        vLqYau7eYst3PdExhIYe0eCmrLqnpqQkp5cvZfQW0aZkgBylXVOjYDvtp3+kMhEyug+7OVpks7RR
+        muxtqp3fKzTq5sGH4Pi64VMQv9hETjgToxcnUE/CZzT388NEetB0ZD2f92h9vmgmVBlssKKqBZuF
+        tAhQ67knfKxXFWL+7cVDYig7f7q4T60b1cgCBF5LRDhz1fgIlUUuIZzI2ts1EbP8hMDFSm8Yc2+7
+        n492W6N3psa/9a6687QrEIe2tr/NQslZdkWsStFe7rA9PSNnCVilg+llH+rPyTOdhS4CmYkNIdvW
+        WEfTtA1yoBo6+HK7KOkS248J2cGAqF+ZebUY70mUDqR++Py6OTkTwjBBMxQevmraNpo9yyokpRVs
+        rOvvQz8Pt5aDw7Pysbp/NP1wNK4ZSMOVp9r9laczzsYc7gdJpHspaTX6LIYQ1Vl7w97WqhjhlLYE
+        N3pcyae5fHo2XIoLPNBm99XLijNxcZ7BuLNGHx18VH39sAjJ4X7Axr0iWm+dsovkPC9A/bo8oXm7
+        FjLgUqxhjA58upynQwnezM/YeQVWJNhtAOAd7Y7u2NPu+8D7vEBLi4IepmDjLPfDRoGWxmv62Ccr
+        rUNxo6KLwG+xNjDMptlbZyjae3e6gwZF00p72nKkhxTrHz5G5KkMPkRaUVLX28/OOAkrDmofKf6y
+        7220NpLakgbda6jdsJYRkx9qdKrPui++FOjHo13U6FONC/WSXK4Wi898MMekItA5eT9n5xtIH20W
+        yfpz+aRLpZ1aKdBMRriNjnrazk0Hd/EU40MQpVX/SJgCj09XkKVAKVrcVqnllnQt3TlzhP741cq/
+        H6nyCOd+MaTa//kVrD0Vvp8S+/FCOHAdrGnvHVtDvcTy6bo/+tz5qPZff0RgVt07zoKqSeehv+co
+        XosJ1uOrFi3z1grAMfYydZ/H+b/uH5+556/tYsUWf9wKW+dhJz7Z6KhielKf0LMlO6yJde8MnNu/
+        EC7jgbyg15DwwvsSuqkT8W4wTv0oTp4P1X3UqbutWTT6EYvRXa7Gb/zvIkZ6L0Ti4ZNjR+/Z1/93
+        NRx3ZeSjoyd913ulouWtrsisJT5q47VUA2UbjepGEUfz+vkRUdErBPvLk6Xf9bYQyI1AWhwxNMGZ
+        qD99TM9n96ONho8CiHuDkhmJuJ+l3LpAcNGe9PDdr9/9PcBH03q/czrbmbE3T/LPT1urhPbMPjnc
+        Ntjc118/EUXzyQ5csFXvTK2XkvW/egnSnluolZO2Z9vcKuEmyZU/XfcYDWi3M0Ehuwd1Y2mIps0N
+        vySzbLaEU5Nrz9pMOgFeXxN/RTSNLQu3LVGoik96ih3FYUF2DyDptnfCK3Lw1RN+jnAAMdW9PnHq
+        CPQFtHHc0ctlkqJ+b7QteiMupIcgQtV00bkB7YOj64uN4VWbzejWaHkrqz88ZwiEfoC8lz2axscD
+        Wk6CYwFZ3yqKE6NG88k7KjLslQi77fnpjN96KX3ni4iLaLHJqJTw58cJtzyjaDaS2obGEUyykmaP
+        jeElyiD7+DNWV7KVTq10qIE7KCW9NKaMqJ+9OyTq2YHaaDYQjS5OCApSehxtnzf240Oy4vAcHjP2
+        RAuE7/hXz7Epidf+x1PAKB45VgSxdSbefgV//NZXz6BlXCXhz99RIw+3/UjKSJG++pDIt6vTr9EA
+        KpAgONGgVRCi1jEtQLgZFXUNa+l/fhKS7LbBJ3goVX1dZg5YlD388esfF14veTA4V6BJALkzyNq2
+        gJxDyK9++VZR2gvsOnhjS30f2OKvyAmS7hBgfzkM7KvvJChiXcFKFDFneWFcot2hOOL84h7TyVIe
+        FwllESHs63+6fd/Z0LF3/fUDPhO+9QFeSWvjkzv16bI6hDV8eajPu5MTkWpudYhYllHlpHJskrVt
+        CZvb+MJq/Pr6TbmyQL6Ie4rN/efLm1wd5E3tU4dtFI2tPmELsdA21FoKNZr57nVBk8Jjet2MckS3
+        A7iwO5RHrO77js235iKAcS8oNuRTHS3+JHXQnzWJas1WTfkQThwqSXX16/IapotWKRlU3RCQVZn1
+        6Fc/gT/XEj2IacxYVWUD8jhJxcbhfdTo1PEisrju7U+bhvWse3QTCEbc4iT6tH17NK75H7/+05cD
+        05ECBaEffxIGHU0HPlMgMSafRj/euwozQTrf5C1Zvwll8+YVXuC3P6dS6p3Zu8kqik+5+Uef0f31
+        bEuGa6a+572CdLzj+ITUxAppLohiuritVSNrlSxEnuRSm6VcucCXR/qTY80pi5urCt3Uin6jnjzG
+        mHCNt+otMfxxXXTRct5xphTfPinhvn52FPNgkBRH4PCOz7b99NkoE6TC5fDVe3etvdGJk+XxOVFn
+        SG3nq09eP36MVT0RqvlwOlloOj1tau56J+W3tlNCoFgGdfgFO+tvvUD+43XA3ufpoHnvdxK8H2NE
+        /c720+13v6DYJKPP303CBmlvD/BCpyP+8tvoj57t/Tig+nE/pUQZ0gDWV3r25+pqp/yvXgWazqhK
+        G51ttNNah0cXj3ivWnY1Bc2kyMPS7/314TaiZTRSkD5hlBM+cHfVlNPYRcddEdEHd2ui2S8bHTkr
+        /UTPH7t2Zs/ZneRVLF6oq++KauaqpwtTGVZkGcroxw9ASq5AqdFyJZuzxs/Fwj41OK9LntH3Ke4g
+        2wzXH++ppkiILqjoVfKdj57N7yQ0AZxHig3ZqpylkCQJSIVVauXlOx3OW2dCfu0xsh63x2qSlYnI
+        mUdXZDLfB4c2JyWUnfduQ1bf758Om0wALS0LqmJh6Pu84FvpeqpD6m03NBoO/EmFjUCmL1+/OEPQ
+        iQIyhqnEmNprNG4EX4Dbp8L4T37e3y8vCe49+Nv9fKr4EDIOnOcJiOC/42r46iOAhiRE/PYXxmf9
+        JmDkAXz1esum1pJP0u2t7wm4yGMsL6CFsT4Cec9PR5st6xOgD1dkhLsHO21xVhxBEGcNNteJUv14
+        uuTv9Be+PFuTzXgv2nCuVwb2j5+Dtm7f/EtixmhSZ9K0ip8MJ0a74ICwlThFtPSrroXPXThj/avv
+        6S18ElmXX2u//fL+eSrtDg7KZk/kuxSxn5+EzCo6+qhXvCO4/S6Rv/0Ef3HlHFFxLbTQZtmeHh5X
+        RxvvT52XU2mn+zMfCNGXHxao51c8tdG77GfDkXJ4E3/rr2+KgYi1uatwOtkV1T7XbTW+P94ExrCU
+        VDt723S6ca8Wtmb9InMR3tIp6ERe+uVP/+Ieo8lnLIB+KoZvfHf9a+u5F/Td31iPq7qiPclzdLqu
+        c3+9Prz6ifqeAIy3aryLdiZi5fUjoFptwL99+ciy4eIFroe5+dYzC335oQrqcGHY3G1INSpu6v/0
+        NFn71jYak+fZh6f7UKl9PZbaTG9xDdlVCfD1669mz1JK2V8VGtlp9aJ9+x8tsmViEgmHVTVr99UF
+        vvmE8PrtxwcmTu4fwssX+yzshx8fe0+3FHu5uXF+fgV+fN/qzkr/px/w5UH++IvnpyQRKGQ5o/qY
+        Len89WdSW15fPuKTtiKnrcZB90wNf5F1qSfW5qxCtBD88w9/eIFc+Y8j4YzO7ukmDyQ5bp0dtrpn
+        hcYPqVt4opb++KPD8oLvAOS3QFZdaqeCqTwKxK9LHut8UTqz7dwIOhmdjL9+o2LjbEpw1B87uusv
+        LWJ765nD1tkN2Lwdn+jLDyX07WfRn/4lobEPoFMG7svjL9USjTcTvvNDZKWrnKWRDhN8/b7ff/sp
+        07mLdehVw8WmF2rResg+C2iPVUvtGGXV18/mqAnvE7avdyOad4ckATVvEqzF64Wxs20pYCmeiS2t
+        iKtZeu5smTJToP5XP87DreBkQkuT3PDEvn48uwCZhxZrQXd0JhkPMWrCx+RXBoaI9KuyhWMxKFRZ
+        aQe2hNNNgqHIazI30tK33/7Ir35R9xNgNj3Wuxz8F71hw/Ps6ve+X/yR06c99/Tr7yHntgj73tpN
+        1+fnmgNVMl0ii6D0s0yHDLErav4rvndKYMseJ6o/PZxOv/pshbfGX771YViZT07++fUfn2fmPZ9A
+        cRvHl9rLHH1ex1ZB27NuY9w411So/Y2N1h8kELk+imgMb6cQfe66hZMYQU/Vg+0DMT0B77SEMKb5
+        LIf9kdU+V5l5P9x1r4bIGje+YDxabTlzsg80TCj1ZWgdcuhvEzBVdajxsU3tD7/68QCHT6x+/H7P
+        n/5KmSmeswh6koM1ZDrOcwezHw9CY9ns/M2CzejbT83kn1/87Y9pAUuC95SmWEFpkE7x7l1A3gYh
+        vj5iFFHH2ZVgLJ+VX1zcnbbclk8NzsNK8Pn4whXbuZoii58m9qX9foc291itId2YF2zTpYkoLnMR
+        uINa4sPD2aN1En4KVHY6xkdbeGuDR2wFnOJF6a3jNGds7nb5p59ni6KoTafpOMDdezOse48Lm+7L
+        UYFf/Txvh4HRH7/8jX+IyUdbbmLl/vrTdP9wRWfqYFF+/Tuq6ZYdzdfzQmAyjlcfsotaTfe9mcCP
+        D/7hHdf1MsHlHb99dn4/0Pjrx3alE5KJ25gVVczbBKerccRaKmmMDe1JkP/+nQr4z3/99df/+p0w
+        qNt7/v4eDBjzefz3fx8V+HdyT/7N88K/qfDnJAIZkiL/+5//OoTw96dv68/4v8f2lTfD3//8tYY/
+        xw3+Htsxef+/1//1fdt//uv/AAAA//8DAJR+VSXjIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfca7878ae2a00-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:20:11 GMT
+      Function-Execution-Id:
+      - yvvlhpufeil9
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '46'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 649b408d80465f7f39e5760eedb089a8
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - d48b82d9676ed7ffb7da5829ba34e927
     status:
       code: 200
       message: OK
@@ -1558,10 +1906,9 @@ interactions:
       {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
       can be parsed by Python json.loads"}, {"role": "system", "content": "The current
       time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      reminds you of these events from your past: \nI was created"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file to determine what actions
       to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
       the necessary information to determine the next steps.\",\n        \"plan\":
@@ -1576,8 +1923,8 @@ interactions:
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
       instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
       the instructions to determine the next steps\",\n        \"criticism\": \"I
       need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
@@ -1588,11 +1935,11 @@ interactions:
       "content": "Determine which next command to use, and respond using the format
       specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      the read_file command to do this.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains additional information that is necessary to determine the next
+      steps.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
+      file\\n- Analyze the instructions to determine the next steps\",\n        \"criticism\":
+      \"I need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
       \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
@@ -1611,7 +1958,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '6572'
+      - '6533'
       Content-Type:
       - application/json
     method: POST
@@ -1619,15 +1966,16 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6SSTW/bMAyG7/sVBM9OkDRxm/ncQzNgA4atl86DocisrcYWBYlGswX+74M/Ajdp
-        MWzolRTf5yHEI5ocE9SlEl27anbz6fOXm6/fdg/r+9tf1pT50902/s18fftAFiPk3RNpGSfmmmtX
-        kRjuWtqTEsoxWV5v1pv1Jt7EEdacU4UJFk5mq3k8k8bveLZYLZYYYRNUQZgc0XmunWTCe7IBk+Xq
-        YxzhFD41ukhhUdVUijeLNkJdstEUMPlxxJrCKdhzRZigCsEEUVY6TbZCtlvhmFoAgBSl5KYoJaSY
-        wFgcG3SQrpji95LA0kHA2CC+0Z0WmADC8OyNEEhJICrsM5ODscJ94dFUBNyIa2QuB5nDFkLJTZVD
-        E4aRfjgTzvqnmuta2fwfUucpRi9NPanA1thi0n07unMuCZRznp03Ss6ovdZf4dM2b3q4StlBYQb3
-        79jxAnNB0d6I0SbUA2oLlqhPJBsa30UqgS2oukcYW/SZmr0nLf+9U3Ck9ifSs6mqd/3ea9jAaqPT
-        OY45r67RqpoGjTPuha3yxeUhD43u7RQxaZzNX9791Wq5Phn2lqNsaltsI3w01oQyG64PEwzCDiM0
-        NqcDJov2Z/vhDwAAAP//AwA/k/r4YgQAAA==
+        H4sIAAAAAAAAA5STQW/aQBCF7/0VozkbBKEkxMf20BJ6qqhUqa7Qsh7wFntntTtOiBD/vdo1lOAq
+        Snud2XnzvefxAU2JOepKiW5cPbhb3Pv514ePNF1Mvn+u9g/ls6l4ufjyST9+wAx5/Yu0nCaGmhtX
+        kxi2mKH2pIRKzMe3s+loMpuNbzJsuKQac9w6GUyG04G0fs2D0WQ0xgzboLaE+QGd58bJSnhHNmA+
+        nsymGV7EL437cYbCoupLaXp3e8xQV2w0Bcx/HLChcBb2XBPmqEIwQZSViMlWyEYLh8ICABQoFbfb
+        SkKBOZyKpwbtJRYLXFYElvYCxgbxrY5YYAIIw5M3QiAVgaiwW5kSjBVOhY2pCbgV18pQ9jKEOYSK
+        27qENnQjaXglvEpPNTeNsmVULaOCCcMCs5dEnlRga+z2gvVnawDTOPbRJxi7Yd+ohCmVErBEZcJd
+        EwT1SCVs2MOmldYTeNqQJ6tpCMtXoaLbikA559l5o+SKNxniJJ3AXxL0Tbha2Y5/AN/eCuLf4+1t
+        0d6I0SY03ap5iiAqkg3RdIplDqqBNhi7TYqavSctSdmqhiBBxIdynXSkErKgtG69Eqqf+yaDI7U7
+        r34ydf32N/+PSyqw23XMzkd80vnrhqONDuNqb49W+W3//LvGOYlO4pWw+3/LzWT8/kyYKE+whT3i
+        McONsSZUq+6WMccg7DBDY0vaYz46/jy++w0AAP//AwA43yIrmAQAAA==
     headers:
       Access-Control-Allow-Origin:
       - '*'
@@ -1639,21 +1987,21 @@ interactions:
       Cf-Cache-Status:
       - DYNAMIC
       Cf-Ray:
-      - 7cbda64a0d8b1049-ORD
+      - 7ccfca809d0210d8-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Tue, 23 May 2023 13:30:12 GMT
+      - Thu, 25 May 2023 18:20:36 GMT
       Function-Execution-Id:
-      - f4955nyjuij9
+      - pbme7kantxw2
       Openai-Model:
       - gpt-3.5-turbo-0301
       Openai-Organization:
       - significant-gravitas
       Openai-Processing-Ms:
-      - '27188'
+      - '24083'
       Openai-Version:
       - '2020-10-01'
       Server:
@@ -1663,7 +2011,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - 1d7fa6a5187cc4d84806587407f4d630;o=1
+      - b3143c8eb6fb2bdcf9b7429eff4fa7b4
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -1673,13 +2021,13 @@ interactions:
       X-Ratelimit-Remaining-Requests:
       - '3499'
       X-Ratelimit-Remaining-Tokens:
-      - '86449'
+      - '85965'
       X-Ratelimit-Reset-Requests:
       - 17ms
       X-Ratelimit-Reset-Tokens:
-      - 2.367s
+      - 2.69s
       X-Request-Id:
-      - 99ec79bb56359aebe30013d596125a19
+      - 4f56d1467ab6d751cd14534935c37bad
     status:
       code: 200
       message: OK
@@ -1723,10 +2071,9 @@ interactions:
       {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
       can be parsed by Python json.loads"}, {"role": "system", "content": "The current
       time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nAs a system, I recall that nothing
-      new has happened since my creation."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      reminds you of these events from your past: \nI was created"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"I should start by reading the instructions_1.txt file to determine what actions
       to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
       the necessary information to determine the next steps.\",\n        \"plan\":
@@ -1741,8 +2088,8 @@ interactions:
       next command to use, and respond using the format specified above:"}, {"role":
       "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
       instruction is to read the instructions_2.txt file. I should use the read_file
-      command to read the file.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
+      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
       \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
       the instructions to determine the next steps\",\n        \"criticism\": \"I
       need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
@@ -1753,11 +2100,11 @@ interactions:
       "content": "Determine which next command to use, and respond using the format
       specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
       \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to read the file.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
+      the read_file command to do this.\",\n        \"reasoning\": \"The instructions_3.txt
+      file contains additional information that is necessary to determine the next
+      steps.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
+      file\\n- Analyze the instructions to determine the next steps\",\n        \"criticism\":
+      \"I need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
       \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
       {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
       \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
@@ -1765,18 +2112,18 @@ interactions:
       {"role": "user", "content": "Determine which next command to use, and respond
       using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
       {\n        \"text\": \"The next instruction is to write the task_id into the
-      file output.txt. I should use the write_to_file command to write the task_id
-      into the file.\",\n        \"reasoning\": \"The write_to_file command is the
-      appropriate command to use to write the task_id into the output.txt file.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the task_id into the output.txt file\",\n        \"criticism\":
-      \"I need to ensure that I am writing the correct task_id into the output.txt
-      file.\",\n        \"speak\": \"I will use the write_to_file command to write
-      the task_id into the output.txt file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"output.txt\",\n            \"text\":
-      \"2314\"\n        }\n    }\n}"}, {"role": "system", "content": "Command write_to_file
-      returned: File written to successfully."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
+      file output.txt. I should use the write_to_file command to do this.\",\n        \"reasoning\":
+      \"The task_id is important information that needs to be saved for future reference.
+      The write_to_file command is the appropriate command to use to save this information.\",\n        \"plan\":
+      \"- Use the write_to_file command to write the task_id into the file output.txt\",\n        \"criticism\":
+      \"I need to ensure that I am using the correct filename and that the task_id
+      is written accurately.\",\n        \"speak\": \"I will use the write_to_file
+      command to write the task_id into the file output.txt.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
+      "system", "content": "Command write_to_file returned: File written to successfully."},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
     headers:
       AGENT-MODE:
       - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
@@ -1789,7 +2136,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '7652'
+      - '7667'
       Content-Type:
       - application/json
     method: POST
@@ -1797,15 +2144,15 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA5yST28aMRDF7/0UozkbBAQC2VtV9UCl5JQeqlIh453ddfHaK89sCUH73av9k0Bp
-        q1Y5esb+vec3c0KbYoKm0GLKyo2Wn+4f6G7xoB+zcvdB+Hk+u19/yT4+yyK9Q4Vh952MDC/GJpSV
-        I7HBo0ITSQulmExvV/PVfHU7XSksQ0oOE8wrGd2MFyOp4y6MJjeTKSqsWeeEyQmrGMpKthL25LkF
-        zGYKz/BzYzFRKEG0O5eWy1mj0BTBGmJMvp6wJH4Bx+AIE9TMlkV7aW0GL+TbL5w2HgBgg1KEOi+E
-        N5jAUBwa9CRtcYOPBUUCHQl8gKyOUlAE61libVqLDNaDFASZdcRjWAMXoXYpcFELpOHQd/nIQuV4
-        g+pSJpLm4K3P36KlQPu0OzrNcnkPDppBwn9ZqJz2vfoIPjN1N0XzfjtMgcCEsuyU/gy84ploxRrL
-        ZQ9dgyfq3pLnOrZ8LbCGQv/oyJ1ECto58GTa+cVjp8+woyxE6jTF+vxfH+GK9P6tMztY5/4WVy/S
-        qJelGfL4bWe8LqnX/yW/K5s65tfrdrkLPeC9c0MI54i4Nm0+We3c8dVV52wwuPENNgoz6y0X2x6H
-        CbKEChVan9ITJpPmW/PuJwAAAP//AwCAeDvT/AMAAA==
+        H4sIAAAAAAAAA5ySW4/TMBCF3/kVo3l2q1al227eVkKCLgiEAAlEUOU609jUsSPPZC9U+e8oTUq7
+        5fLAo2c053xnPHt0BWZorBZT1X60eH2ddi+rH/b2buGXt+9evHlYfP4SXxWT9zdvUWHcfCcjw8TY
+        xKr2JC4GVGgSaaECs+nVcj6ZLZfPJwqrWJDHDMtaRrPxfCRN2sTRZDaZosKGdUmY7bFOsaplLXFH
+        gTuB6VLhSfzUmE8VShTtT6XF1XWr0NjoDDFmX/dYER+FU/SEGWpmx6KDdJgxCIUuwj4PAAA5io1N
+        aYVzzGAoDg16kK6Y40dLiUAnghBh2ySxlMAFltSYDpHBBRBLsHWeeAwrYBsbXwDbRqCI931XlxQE
+        GnahPLxF8249BCUwsap0KMY5qnOKRJpjcKHsUT64YKib/jeQOjO0muHoUoATPhiDDsURc0Mn0kv/
+        2uvQW4/gE9PfwUHin/JeyJnkxBnHVa+5gkB0GKXATerktcAKrL6jM2jtPQQy3demx4M9w4a2MfXg
+        0m30qe1lDK5J746e9857aP4jzDjHXrRVx/MZBn67nqAr6v2eGFxg6VReHt75t/cCN94PmU8b4cZ0
+        69g23j/+ojqQDYB5aLFVuHXBsV33cpghS6xRoQsFPWA2ab+1z34CAAD//wMAnTqQcAYEAAA=
     headers:
       Access-Control-Allow-Origin:
       - '*'
@@ -1817,21 +2164,21 @@ interactions:
       Cf-Cache-Status:
       - DYNAMIC
       Cf-Ray:
-      - 7cbda7160fd3e277-ORD
+      - 7ccfcb2e8ebe29c3-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Tue, 23 May 2023 13:30:34 GMT
+      - Thu, 25 May 2023 18:20:58 GMT
       Function-Execution-Id:
-      - f495ip5txdm1
+      - pbmepc01gbzx
       Openai-Model:
       - gpt-3.5-turbo-0301
       Openai-Organization:
       - significant-gravitas
       Openai-Processing-Ms:
-      - '15997'
+      - '17906'
       Openai-Version:
       - '2020-10-01'
       Server:
@@ -1841,7 +2188,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - 285b29ed564c106ff4d38a33451a5203;o=1
+      - c04b0eee68407fea8158cee793fa60de;o=1
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -1851,59 +2198,26 @@ interactions:
       X-Ratelimit-Remaining-Requests:
       - '3499'
       X-Ratelimit-Remaining-Tokens:
-      - '86452'
+      - '85953'
       X-Ratelimit-Reset-Requests:
       - 17ms
       X-Ratelimit-Reset-Tokens:
-      - 2.365s
+      - 2.697s
       X-Request-Id:
-      - 48a48589bce33baaeb8f62202ba96d90
+      - 15503d774ef53cf1f960387e503eed2f
     status:
       code: 200
       message: OK
 - request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"2314\"\"\"\n\n\nCONCISE
+      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
+      0}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -1911,7 +2225,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3334'
+      - '245'
       Content-Type:
       - application/json
     method: POST
@@ -1919,120 +2233,74 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4SSy27bQAxF9/0KgmvJsGrXD+26KJAUKNpFCvShwhiPKGmSeagzVGPH0L8XY1lO
-        YQfp9g7Jey6HB1Ql5igbwdK0Ol1+vP/xXX35lDV3H5ya3nxujbh5Wv/J5t+qt5ig296T5FPHRDrT
-        amLlLCYoPQmmEvNssZqvZ8vlYpWgcSVpzLFuOZ1N3qXc+a1Lp7Nphgl2QdSE+QFb70zLG3YPZAPm
-        y/kywefZZz2brxNkx0KfpdV60ScoG6ckBcx/HtBQGMd6pwlzFCGowMJyhHSWycYAh8ICABTIjevq
-        hkOBOZzE0wPtOIoF3kJoXKdLCCw8w3YPnkSpbA3cECgb2HcyooZNNuEdQ6U0QRfGili9OWrSGSNs
-        OSkw+dfKkwjOKlsPfncNQaV8YAhMLagA7KCzJfmYo7xyhSg+NoJjqaffnfJUgqvA0KVTq4UdTFL4
-        GuhlvGgXxdfiFYVN4b0Vev9ELwOVxOSNssOzpd0QJ1wQSa9YSRXMuGtLdCQgGzofmwXD7avxq07r
-        PWypcp6g9U4Sxd+5zB5aEg+jy6PS+v//eYw6KXAY0yfj0ZwWdXUzVhgaHM5LvYAQvr48teEh1j63
-        X299hDiCnHgK22OfYKWsCs1muCLMMbBrMUFlS9phPu1/9W/+AgAA//8DAABeWuzpAwAA
+        H4sIAAAAAAAAA0SOQUvDQBBG7/6K8J03JWmatO5NPXjw4kUQrJTNZtpuTXbCzgSKJf9dClqvD97j
+        XRA6WPijUz+Mfb5+uZf6OcR1H58e64fTYWrfl99v52kl8goDbk/k9ddYeB7GnjRwhIFP5JQ62LLZ
+        1EW12TSlwcAd9bA4jJpXizrXKbWcF1VRwmASdyDYC8bEw6g75S+KAls1Bv/pGy4LA2V1/Y2smtnA
+        Hzl4EtiPCwaSv2binmDhRIKoi3o95KgUr/cuE0qBJON9tucpZXEaWkpisi2WVbnaYoHZYB9ikOMu
+        kROOsBDlEQYhdnSGLebP+e4HAAD//wMAiLNr+0EBAAA=
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cc6279c6ab63ac7-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
       - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfcbb129082322-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Wed, 24 May 2023 14:16:35 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
+      - Thu, 25 May 2023 18:21:02 GMT
+      Function-Execution-Id:
+      - pbmevu50gphf
+      Openai-Model:
       - gpt-3.5-turbo-0301
-      openai-organization:
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '27497'
-      openai-version:
+      Openai-Processing-Ms:
+      - '1540'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 850f41e684b09434d8c479bf8334a162;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
       - '3500'
-      x-ratelimit-limit-tokens:
+      X-Ratelimit-Limit-Tokens:
       - '90000'
-      x-ratelimit-remaining-requests:
+      X-Ratelimit-Remaining-Requests:
       - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86499'
-      x-ratelimit-reset-requests:
+      X-Ratelimit-Remaining-Tokens:
+      - '89467'
+      X-Ratelimit-Reset-Requests:
       - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.334s
-      x-request-id:
-      - 518916964b78cdb0ae0001c2c19bb7e4
+      X-Ratelimit-Reset-Tokens:
+      - 354ms
+      X-Request-Id:
+      - bd62e6c94225740f116d494598aec43a
     status:
       code: 200
       message: OK
 - request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file using the read_file
-      command.\",\n        \"reasoning\": \"The first step is to understand the instructions
-      and what is required of me.\",\n        \"plan\": \"- Use the read_file command
-      to read the instructions_1.txt file\\n- Analyze the instructions and determine
-      the next steps\",\n        \"criticism\": \"I need to ensure that I understand
-      the instructions fully before proceeding.\",\n        \"speak\": \"I will start
-      by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}], "temperature":
-      0, "max_tokens": 0}'
+    body: '{"input": ["2314"], "model": "text-embedding-ada-002", "encoding_format":
+      "base64"}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -2040,139 +2308,177 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4445'
+      - '83'
       Content-Type:
       - application/json
     method: POST
-    uri: https://api.openai.com/v1/chat/completions
+    uri: https://api.openai.com/v1/embeddings
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4ySQY/aMBCF7/0V1pwTBKGUJbeqe2lFb7tS1aZCxpkkZu2xZU+0sCj/vQqBZRuq
-        ttc3z2++Gc8RdAk5qEayst6kyy87mX27ty9fH+Rj+2m9X9x/r3drLg9eryEBt92h4vOLiXLWG2Tt
-        CBJQASVjCfnsw9371Xy5XN0lYF2JBnKoPafzySLlNmxdOp1PZ5BAG2WNkB/BB2c9b9g9IUXIV8ss
-        gWv2qz5bTBNgx9JcpVmWdQmoxmmFEfIfR7AYL7nBGYQcZIw6siTuKR0xUj/BsSAhhCiAG9fWDccC
-        cnEWzwXccy8W8FkQYinYiYCyFNyg0BQ5tKoHjJtswnsWlTYo2qipPjl66+akKWetpHJSQPI2P6CM
-        jjTVQ5OHv6T22FJTFFUbuMHwm1FwI1lcGStnjHsed/NG0tAoFY8R/4z4PyMWBaXiI0lzeMEbn+hD
-        SmQMVtNQJtyziIw+johU0KyVjna8ZKTYBryM1VKJof+/WypRtcYcxBYrF1D44BRiqakezx49yqdL
-        l2dtzL//kU4bHEK65HIr5zXdnApJi0P+60pHCDLU4wsbCr33+vwW5wJxAjnzFNRBl0ClScdmM9wR
-        5BDZeUhAU4l7yKfdz+7dLwAAAP//AwB9LqMb4QMAAA==
+        H4sIAAAAAAAAA1R6Ww+6vLrn/foUb95bZkUEoWXdISAgYIuAiJPJBBQRBJFDC3Rnf/cJ/lf27H1D
+        wiFA2qe/09P/+Mdff/3dZlV+H//+119/1+Uw/v2/1muPdEz//tdf//sff/3111//8Tv+jyfzJssf
+        j/JT/B7/3Sw/j3z++19/8f915f8/9K+//lYvkklkzb5UzFTOCbzqRUaTWKrBdHHrHTTpktHDuaBg
+        DqJvDNNqBuhl3zt9KWvcgsEcFWpfm4fbJU/JBK39ivFxHopqkV1Xhjz091g9H47Z0ge3HKKvoWJv
+        c9H6PCkkAYLv00Obb3HMaCCFLRTQ+UVP9IgqXscSgvR1/5KvUD1D0t6GAHLWNqD68nT6Ob1AGTYt
+        D6jjRFw/VfvYgNhBAhH8qGCTGlet3MXSHW0un7dOjGGKlcjcaFijVVi158M3kTdmqdA9+Oq60MTH
+        Fu6+nI+Uqthm37epcgo9m1ck5V2qkzILIPT65o348gbcIdt0pnSExMTO6017JtxTGTZJVOFTf+j7
+        5UDOOTSWzKTOo/CqubY6E/SXj0XuT9HSRfl6fMOwBVuMUrRn8+EVqoqcujrhU9fvx1sUTjBmAabO
+        eKwZwcxq4aWZK3o4oDJjjn6BMLSzB3ZGQdGHs1k6cDcAhk1PuegL/kg8uKudhPGNOvqi6D6B3Rsd
+        8D46VBlxBFGAgVno9IFHvprU2PXBJc7O1LoqBCwbk0VwnAuNqtNLz6bM2XDQIrlJT/LyYXNvhhNU
+        ee9JSmB/AbGXKIcXPk6wWvAffaplF0GplS2sX0+JPsz9lMLL2/Ao0jgf9NPDFqBxTmLElmqsZuLE
+        E9SDd03xOl8L795yWHg+ojhNn4C2k7jAU+djqm18ytg6flIFZxk7I+4ykr7vOXyndI/NFnJg8o2i
+        VXyXctT6DF4v7JmWwu/FsbGB3gkgTdxpsvPwcuzsn69wOoQhD4t7mWJL9SijrpET4MvnCm3G0gFz
+        ecomGbaOSLiA+i57zfUA05fxJjCbtWp7KpsGWvMM0cw75569ml0g4TbQsS58/J6ZNtrBxT/tsfa5
+        eW4r1/4CB5MqSJ7PPZgXkBD5uDlfsWdTmM36Y0phmHy/SAxFJ5xlZVSBxt8CFC0an01zv0vhOJca
+        tYGdVUt7G3x41csMe1Gy7ZfhEg7wqeoUTcOjyIZ58Bf4PKEzxVs+CVnXnSK4GySGdY7d+qkTWLqJ
+        DdJRlEdmNg8m78BbRDns8txDZ2MV7KD9FG0iJMUXzIKoOopyPH7I0WFxyMBNN6QkgB32NuHLZV13
+        iKH/lc6IlyqrX7I35EH02Sz4V79TJbRvGBvChHZPy89IUNo2vFScSQ+n5MtetfmNoQdNSLF0qvsl
+        6T8BZE9HXOv9oVPaXGzoi3cTB8BxM1JHtgM/17TAlvjo2Rj7yQSPyP/QvRHX/aLCeAAOd7DxsTut
+        9W1lA1QFIKAb8pt+Opud86f+7ox0jHhkCGBjew/qvNqgnxtbu8NWNAA9HMCtmsRey+HC+Sd6JFch
+        IyseymInh6h4c6SfwuM7hcc8Halqgz1jn/cXwVr+ttj5Lqk+bMpvBB6chqilepjxlqsGEA3uF8UF
+        4UPmHp53cBqtASnXwAFf4uQLOFskQCx9V2wOIpuD6znZfHMLvF8ctKHDYUTAXj32Az5BDiApD0jF
+        OYeQseoUQeVjEOypdcTGIiJvQBZgIJ0T79X8PrQN5BIrx6cr+rBlSkUBqk2WU5XvOzYWFxoD94k5
+        sp1rzv12xtLCU+ocKX4BphP8ud3h9+Ij+qDWSR/fPpfIY9UAaka5HdbRtW/AwfcsGgrfRZ/9+70A
+        D0W28WF934oXHhyidIfmnS/oLJ1SB14jlRFhH8ghtTfpDlwaVpF4H6TZvN1AE0gZ9n7rSZ/NMpug
+        2txy6tQdr9NvO6z88abY2WZhxpaiz0F9DBqyPfoVmK8PiwAS2AU1xV1RjW5hDHAKaE3tpin1gZ/5
+        nTQVfkrtD47DQflCG/QHg+JTr3cuayrblHXNPOGVP9yJUZbCx7ho9HC+D2BMwkyDcV1HeB/pLzak
+        xw2S3k5Myc5yWn3yIkuDQibERL74aiUizmig82gmuvdKUn10vS/BOYknIo/uJ5wl6MoQXpcazR9e
+        BSwfjg1sY3QmLyMy9HknOwkUUPjCh2NQZ+P3hDy5vzz22Ir2gc6O+/sdeJnh4XMiPPpl68lvWI6P
+        mTR+UrEWzJ9YPnVlhvFtbKvx0OMBAjuKsf3c94B23wFCXr3x2HDuARPqi7qDpfexsG4VGViay8uH
+        Njbf1ARc7dIQPmTAnjcdR2fFdAfX2uXyijdUA06fTQNt3z98o0bQArbM56qEWXAtkCJPZkZd+dhA
+        XUMh1kR672empB6EVnCi1jMv3bnTpR3oG1yjeeVv8SoMSP7NF97vmmw+h7YHz5aQ4PU8XCT72MLg
+        k45o8Q5JyB7biww/n27AqCknNq71D2yl1DH+5hbjW/5WQgFuV/6+Hys2f58JKDu5wOrtss2G5AA9
+        uLsNBj1dwdNltLk4kCejh7aX9sJmL05UYJFIJRJCtf6JIOeDsdpaZIOckC0/vLPI3cR219V6cdkn
+        PKy7o49+fDqCDXIk9I08ejiIcT8fP88CADuOCeu1NJxSpX0DpkQOPQZB6zZ9GHjwW7fFem7r80be
+        vuWd4m4IzLZ1P/Mci2H3jl2Mg+AGaPlJWjAvoUydHV9U7LwDAfzsbj41i0PhsoeQt/AkyyPZrPxL
+        TtTrgAAbmYjZXa2E/FmVyr7GmLrnJKuWkMQEPDg7QhwZdlk7zp0J36lord+TABH9bQO+grZQi12t
+        bPiNL3/iS4wl9+12zeuZQ6bEDkXo07nzyNk2VL79hjyunhkuzet5hzx5qmTYhHt92LyK5od31D3f
+        82q53+2dchF1ivebsdEH7qUiyF38PYKGqlfzV5McuMWnN9VsXQDfsNjsgNgHNXYj1mXTZhRtqDRC
+        iaDFvdgEW5aCxgE8WnTW9VOmljtYffMDUYRWDdt0sycgCY0JH0nIwj/1D+x3SaRyX7NpkLkEvlPl
+        RNVDGfWsHuAi4V16xIdTbGdzeYI2PKWajuR4LwPq7GwTyrediKQg7vUFNT6BH0tF+BSKUCdz4O7A
+        j+/VHT2xZQ6GAEqOoqLpUDB9yiVfhYa+fZH+dZTZdNcMFQZme6SW2++zaVPaHNxHio61Bapg+xuP
+        x7RZKFp4Lpv3dfUH/6m7u/VsEU3VgYrpGfTCc33GwM01YVI9NQQGMruThqYc4m4b0VXv95NrJSZ8
+        g61IVVvRQ9GVvh5gaKmxu+832aoP73DUjQr7t8s2pFdx4GBcaTq1nmWtL49W5GGOkgI7t7h2V/3e
+        QRvHE4HV5qQzrDYFZJRd0GBTGE6r/oak7HZIuLcUNCGJB/DKmivZjM0JTHpKWjifMx+BREJg5pWl
+        gflmLqnztYxwjhIdwsekLNiWs3e4OJ0qK3CX6URMrLiaboqN4EE19mSbKKo+D9a9hGHSfzEe30M4
+        otvSwtjgJ8Jy0mcL76XeT0/RtZ7C+RZBB07TshBwipJqWsZbAZOAf1OtwkZPvmmtwkZ63LCV3YuK
+        vbtUhtG2Hamrcq07PYEkg3V8iHwBcTgzi8Zgi/Gb4ji+A+YBJwZdPMdU3c04Y9JFNZW60x264r07
+        RteqgWw6tkjwYy3ktyzWoP1sIOHrqWHTEesBfO/kiHDj5uXSJ6lyoAekp/v3U2BzHhgEoi8yMVYg
+        l804zVQYXrgAnbChhlN63HiAPzUxPcYpWvHmgWD3zs9Ynao3W4xhF/30DKGNftOX/XJsoQCpiqZH
+        JoEW1JIDdfa5EKYnW7DIzor/z1KjuE4NtmCGW+nUBZjuN9SqZlEXbfjgVERN9WNUk49jA4q988SW
+        S9/h8IGjAWWwH1FZnU19tNN1/gq+pqjrYrB059kE73RzQozcGr094r6FkqSesLvOz6w/Eg0Gx3rA
+        xmJswXy87wm8VNCktpwZ2ZSpWgGGqOTQ+Gmz7Of/YBJwHdZNuu8Hy9trUAb6iD3baKpB7J1cWv0s
+        GeXlA4YCyi3kT8MdW0Z0YfxmEBLI5yYh5QaRbNUjA9RZfaGmn+hgERA0YJmmNt77ezVb/bAnq0Lf
+        oSh1/Wq8oz2BwuC1NInFd8j6QlKhcrsxZNFzCRZysm2w6gNqb7y8mu+oNCHXaPXIkX3Z01y8JpDn
+        xABVSBn0SX5PKSxBsGA73mqgm9KNAFb/RsBjHwE2lIEDu4/bIvn1xj298xcbnu7bgiih+WLjyws1
+        eOXn61rvu35uvVMO501+J8sGkfAPnqmCJGBtxVO6iZYCnu5jilHw7Sty/BYljHYnjsTt+esuyXM2
+        IZ97PLYXedaZerx48Oe/RC9XwnbFf+XVCxW1BS7Sp4deO3C/7BwaamPhklsZcNB4yYTMqrILGUxd
+        HuSQO+AD0p/VVCgggfNe44jw3mWMAHcI5GhbfrChoTZjcilOUGcPTK0QnMLx5cotRF9TJdP+Pumt
+        GvcdWLjgRJancA2HeYe43X0TVdiWbyWbAqvbQaqSA/aM/pYthzEhsL/UFrb1OQULqqcYzjSKMW70
+        mzsD7pT86hst18YNp5SzOSB6ikcPDz4Hc22VJux4ocJIwCed+Xsa/PQLtdyxZMP1kPFg3ocONqO7
+        yeanPaU/PsAmXyf68OO3VuC22DF90LerHoNK3MT0x88LRa9AaWPDxc6OV3uGt5L605Or39DBUlyn
+        CJytxsNeX+7B1nl0AuxicKfOiU0hUaeigF6uU7K5fOt+kOtkAvXRLigiUxay+dkReNunRwIeepyN
+        7T7RZC3sCOKlj9MPbAoX+G0vIplGM6rmsBB3cPMefIq1V1rN/QGkYN6rHNXYJ65GqukI8CSWyfTm
+        UEU19eUrxtn3aebPNhjG6RXDJ1eHZLPizzQC0QHfi6ZhzVIC/U0WLYfD9lxSw8mjbFar0gCcEMzU
+        ro5nxvhk58uHQMqR8mmzcD6H7VsOGy/HCH0cty4unximcy5QM0rrkOyCeIDG4sg//NaHJ7iV8BY9
+        FsKsAoBhkax/87l5HwLWhschBTC9CNjafMJwzs/vWFn1MtpKdgDYo1eFn3+hasFb+gj4hPzJnwS1
+        rlzi9KUKkXQPqAXqM2DnHfNh2RWIOtKDB6P28QZ4OUwMD+JyAov/TTlZ9k4QHx48x+hvPa3/j61Q
+        7LLx5S4dPMK3ik+rvpntJl7gohqA7ICRVINnSx7YeuWJbBwDZ/xCgkB55W5Lf/kGBUlJJJOmRzKv
+        fmcygsyQm6Sh2FD6UzXSfSfA+3nv4v2gOjrbb4o76NmUUkOqv+6Yee0bbraoxersQ3dZwlGV+yqx
+        6a/eF307+HJ9dAokcUbQs2HEb6A254Rstvwum3rpEkCqhzHeg7pw52P2jeHka4ga8cCx9yGKGvjT
+        B1vJicLpaVoq7KvUxuotZKwTMeSBqxwPSJEXC9C+Nw2wvS83bFcuC+frHUGZ6rc71ld8YRe2fyuH
+        ormRtwY21TDvTAi0g8Ko5VIjXF5JQkCZBhoasaFm5P4RzX/P51QZTOwHxINL0z9QmZFzOBt5soDg
+        E3xQ+Tyq+pydvjHsG+uJuGAkPUvGnQ/JvrWp7khHfc1nbOD1cYLghhNArb6dHDqPe0dmNdAqUSo4
+        HxbPq4iWbKBsYRfkAEkKbgRmdK8v0lFLlJ51Edpdy9RlN3pL4WZrlhhV+lNn0fL14Fi9AXUPJnJX
+        v9gAIa9GqsuGyn56DMD0KiARvBBbjt+igFe9e9FV34bb8hQuUHLe5I+f4/MD8kHq88mKRzu3o7eN
+        CdOCy6kmGg1gF26zAO/UPyjeWi998o7nNzyqWwmrJ6L0wzDZHASSmGN3cl/h4PieCgKz1OlaL3pT
+        3cMBMCT31ITGl43BZU8Adwn2KELFBcxZkk9w9QfU2nwjMJceS6Evuw8CN1fDne1U9cBdXTYEQk3W
+        p5Yjb3ARQ0At1SHZ8s3qBaqVcMKHh2X1fCXYSPrWZYq9jO5dQQqfOZyKpKA24b0e/Phj1fdEFG8t
+        WAzxkMCPKdvY7rNnyPrnzofZnmqo32uuuwBvXP3i21vzoheYr3eTg2s9IbrfmRnrn1MA5WNRY8tO
+        V/9nC3fQSPiE3SKv3fGXD/7ynt0Pv+xNIMPWZiWKL+6zJz99teI7WjIyZ/NOLqff+395Y9hPbd6C
+        8060Ebcc6n4aobiTVrykR4cJ4RynowDMySEY10kVsoM5TtAdJrbyrapvRbEtYK6YLgL8+cD4cS5N
+        pcpmh2wfEwCLvn0H8tZLLOzR1gzFpejvEFrFjTBOvPdLm3otkI/LTLESdu4fPdaZPvdHz675ZgA2
+        12NGPUOtquGXl6mHTqb7XtDCbbv3NegO3UgN5Tu4g9LdSyg5GxWJdwx76oupLe/uR4yD1f9PlmsH
+        0IguEj0iR9P5964zoZDP0p98hvCuxEuNxZ0ReByujH5bnYd3FRyIxGlnl0x+t8BAlA7Ytuymn356
+        8sk9TljdjUM2Rlfdg/TsPcgmjiEYY99f4NtpALU+E+1pMyoFPEywx9Z1M2WEnNoSQMuxMMp9PVzH
+        s4QJ26So6rU0W9b8/6f/0Riae7ZofF/89Bo96be6J2N8v4M1fyVzcVuyNlO1EupadKPu0d9WC7uY
+        Dky0yKP2Ux8zfuoTDWbP1kb1sGgh7/ieBkDC8dhQvp675osQhhdiUrMNu2qS6chLXDtCasjoserN
+        ea03kuNjEB2raVOqHCgfuCbc2s+YItU3lOfJO+PceRqu+BzLAZpnJaO//H3xu5CA23n3oue2kti0
+        kNSHv7xdaMOuHyu87YAv76/YA7slY+XS5PC4cc+IK5NvttjLPQevU++jZeHKbEmKWy6zZ6avLBRm
+        BGq7GI6HFyHbW3cNa1TRGPaVryEB2h6bUpvLoRZOPBJVh4RExLwAf/jIuQiywT4dl19eSw2iBmy6
+        73UfkHLh/vQvfnoOOCcjWdf7UJH6+YBQTMs91k327v/kDfWtXBCAD8QoK70G/PK0c0TEfmJEbmF/
+        oSfqRXGkT1ddJlAPmpoiF90Z26u2DN89vtFfnrek7+gOo1rF2FR7q1r2S6f+yfcFP1LZcmTbN3iq
+        IaD7wx5kw/q/inLL2E9f96PRmRyU06OODc0zAWsq1VRMmhzxMW9E/ac/4LdOo59/zcTXtOZ95KH+
+        +KSfTk4QQyk7eUhc/daaryE4asIVbRzV++FRDsuuRNg51IcV78YF3Jb+QM2kIdnYm9kED6HbIcWq
+        Rp1Obd6Bh39C9Kc3xSk/vmFkWTbiz4qps/l7TcA0FQ09PKaMjV5Rm/ASv65/8mFy/Y4L3N3DCyGo
+        +uhsc0llqIWyTC0qX91l8stJofOwxZq7YdVUabEA8a7EKLmWqc4eQtxB2cOQvHaBWNG8/yIgZMQn
+        VMEfffzudysfei1224H+O+8fQ+9L13zJnYtjsgCefMyfv+/X+/cfH5LdtVH0eTHJW86CU0rVYtfp
+        XR2ptiJk8E6NMhSqPtnVa/+h70iw5lGTnn1S8Ovv/fhr9orRBGurDQk7tQF/8uXP8fMkfdv07sId
+        Uu+nb7CrcvaaR7c5DJv4TfdrHix2XT38+IbiRpf0pcwCDvYHk+I1L+uXkOQDeKp7Sk+NUverP+3k
+        J7lYaOJ75w8/yut6XP3xrlr9SQqcR/zGqEw7QBvykH9+4A9fz4VzLmFGJ0Qv8FXoM7M+EfzWXYGN
+        HLNqQfUuljB4LBgtfB6OC0gGSF/5F9FzXfYL/pxzRRxFAf+Zv/zZF0BpuBbvi6sPSB8ub3DMO4ns
+        wvv2l/fJ4CxZEZq+2rmaQD3bMDC7I8bKue1ZQ4QAGqXKUz1tG0DLheSQhoBHonizwXyKd4nS2nOJ
+        MfIuGeFjcwf97+xiC29tNgvimj+akYO1TTBn7NEVuXK+cjmZTvsmo1L8RQBa/ok+VFNx25Mjk18e
+        huZ+p7NFnVRHnjTLItvxBfQp25QGbJumwpbhL2zhzJSDT3La031kvdmMknn343cyjc61F99dIEPo
+        WB2CFlSzrV3HGuSS0xvr5eSBlQ86uOpV+lzXH73wWiTVnetTvOerkGGVlHCzjQj+9RPmW8Tb8Lqs
+        /XdRmMAfPf73b1fAf/7jr7/+z2+HQdM+8nrdGDDm8/jP/9oq8M/0kf6T54V/UuHPTgQypEX+97/+
+        vQnh72/fNt/x/47tO/8Mf//rL+HPboO/x3ZM6/92+R/rt/7zH/8PAAD//wMAK+GH5OEgAAA=
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cc62859ed003ac7-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfcbbd7fb02274-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Wed, 24 May 2023 14:17:03 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
+      - Thu, 25 May 2023 18:21:04 GMT
+      Function-Execution-Id:
+      - pbme9l6q6fyb
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '24655'
-      openai-version:
+      Openai-Processing-Ms:
+      - '1219'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86475'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.35s
-      x-request-id:
-      - c0da07f2916746d8735e7bdcbfde425a
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 4decc7240f714a1a6b1e4c57136ffc0f
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - b844d587eac449c8f5ef8515c53c2549
     status:
       code: 200
       message: OK
 - request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that I was created and there have been no new developments
-      to report."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The first step
-      is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
-      instructions and determine the next steps\",\n        \"criticism\": \"I need
-      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    body: '{"input": "a series of four numbers, \"2314\".", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
     headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
       Accept:
       - '*/*'
       Accept-Encoding:
@@ -2180,382 +2486,167 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5444'
+      - '112'
       Content-Type:
       - application/json
     method: POST
-    uri: https://api.openai.com/v1/chat/completions
+    uri: https://api.openai.com/v1/embeddings
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA4ySTY/TQAyG7/wKy+ekagmbltxQERIckFaCw4qgajpxkulOPNGMw3ap8t9RmoZC
-        ioCr/fr1448TmgIz1LUS3bQ2Xn84qIf03fY+TdS37ce39+WxDiQHnT5sthih2x9Iy6VioV3TWhLj
-        GCPUnpRQgdkq3bx6naw3yTLCxhVkMcOqlThZ3MXS+b2Ll8lyhRF2QVWE2Qlb75pWduIeiQNmq9U6
-        jfBqfk3cLSMUJ8peQ8nLtI9Q185oCph9OWFDYTL2zhJmqEIwQRTLgOlYiIcRTjkDAOQoteuqWkKO
-        GVyClwQdZQjm+B6YqABx4EkVIDWB4SC+0wNg2CULOQqUxhJ0wXB1VgzS3TmmXdMoLhY5Rr/6e1LB
-        seFqbPLpL64DtjIcoOy81OR/E4LUSuDKWDpr3dO8W2sVj41i+Bzoz4j/M2KecwxvWNnn73Sjg8Gk
-        ICHfGB7TTEeBINSGGZH2Row2oZkvmTh0nqaxOi7ID/e7pYKys/YZ9lQ6T9B6p4kKw9V89tCSepy6
-        PBlr/31HPm9wNOmj6Vcua7p5FVYNjf4/VzpDUL6af9iYGLTX8lucCeIMcuHJucc+wtKwCfVu/CPM
-        MIhrMULDBR0xW/Zf+xc/AAAA//8DABSF0HDiAwAA
+        H4sIAAAAAAAAA1RWS9OyvJadn1/x1Du1q0REsvlm3EUuiYqi9AgQLyCiQBLI+fOnfN7q7upJBjsr
+        2cm+rL3+/a+fnz9tXpXF8Oefnz/PRz/8+a+v7ZIN2Z9/fv77Xz8/Pz///l3/H7Js8vJyebxuv/Df
+        zcfrUo5//vmR/tfyf6B/fv7IU2dTuTYqNATEOMNlxbbMTPtXN3k056h3SsTCW+oh2TqOmaanU0M7
+        114ILntKgd6aNWe6FrTxoCyzBKYxdjG3tTp/r1qkwpieFGK+cguJs+RR4On7iMfDqsypBPCAz25z
+        JB6So2CMcxujyagrKnjTWJPxOM+guRQti4JLLui58BOg2ZawgwVWwONdvUVamtgUHZmRL464buHZ
+        PJYY8t6o5Jw8Jhi0s0eV4eHk7BJ2PuyHw56OknQTQl5JKtz7bM0MMM1Kiq7pR+WJRXF9adr8U2TS
+        AwJ4vfByZ7iWmAoMaN3mEZ4eKe5G7dW48PSOSzyspDsSshdn0PDYoZd0dc0nMn/44LzNNdP3/a2a
+        jK6T0Z3SBVl7NcTTTNkW8JAWBXEedpVTOek5JE//wHR3nef8ExxbZA6xQanMejFKBrLRRsN3Zu2e
+        Wt7ONEMFv/ZiYvqJn0+fo9nC931k3T1r1G9fSQ+X0jeJ8947Fk2jSkWF1h6wCGaQt3bn+SjNLwFe
+        OVsUi+VZoRAuP5Rq6fsR0Cc1ONxxtKYLv/lU75MZuRCmV8o8W0Wi/z3//HgliQwZBUw7lBhmqf4i
+        STmnsYCNXWqfmZGTIG/m+bBcxOVqNc9ndMp2ccDXW9OHGSs/WIqXgRAUzw4Qz5c75u1nTTzx9WWL
+        NvOK0NlVnnfjzqcqAAps5qh9bC0Pn/l59XphmVhvK7GmzdNTwQxFTOzhPgajz6Ma0hER5tgf1I1Y
+        K0MEipwQl5FnPuzrk412R1UQJ5PvFSdFCHAhwRJPxNrlk6uiBET0Lom/zy85O25QCNSSQrrni71F
+        bfauwfkYgGVldhdC9vIMRiYQXryXvBOY7RS4H94B8c2FifiB33TtubUlYgUziD+uig5otREuXZbc
+        zIV0UGdw0p4tM3fkgnh2OITI2e0C4taGJcYm5DcYCjWjo6/W3cQm3kBhuYC56jysv/e7ZTsnTnEx
+        O2nxhhYMvT8TPU/XldBDzVMXrSIz50h0MXbPTEH26aaRYOMXgdDG2J0788Jn5Yb5FQf7MkOnLXsQ
+        P1FelmCDakMZSU+2+Vy2Oa/jZQm2PEy0bmKS01W1OKtuIFXM+PY3N87VDEqjiIj+yZJunBllsjp/
+        rox4oDw6PkrHA8zNeI3ZTEmrUdGfWxQ9wvW3Xq7xlGRBCSyqU7azUz8QYe35cMluORV07ljiqls1
+        aoTaE5e8d4FII2UGYjdJJAqvu3jKXoUN76tn4aKYSfmYk0u/0kzVoOMR953gWy2EeXEYSbBQ74G4
+        pWhSu3oeMVsrVmLY8tkHBhJ5+BdP41CVEFGsLVWX7T6eoqwN1fv+cKHaS3ujL6hFbBW86F1143yQ
+        tukDXbTDkpmPlFZDH70bsETekkDpVtZkz3QdbRepgzmuHUsGedeg/fGVYO1ekFjctq0CQ7oXBF+b
+        R9yj+15Cs9R8kXDAQd6/2/0DMWqv2Wm9f3f0LkoFynr/pov3/hlM7OrW0Ailx2ilv+KGzD8ejIaq
+        /62v/ptfeAQNkGC2T8WIP7yEk9OaxFF7EdCwEq42PzOfGdbpUAk1TD2YL547OveaWnQevUnArAej
+        81mMLRHEHwnW8d7CSxxcgglL50wl6LNk+s3Fon/NwhkC7Tox5+lvqvG5JDVg4kbsrz/JJQVEObeI
+        7ll+xZMhT2CTnR0WXQ5C0GnPdFj3poSnV16hsaPPCW6LIiG+YbCY4Rsq4EHCiq35clkxvv4ksBc8
+        IYYk3RDVvZYDK3Y3isqizTk3hQyK7WM6OnGFhuGVchCH9YOttV4NuiQ732B7WJ3Y+hTt45H6hYJ4
+        NsNEVx0zEAaWdGDpbMKreUbz3nlKDXI748w2cPjOQ2JRsNqDx8JL/Kim4PxOwD08j2yTr2NrAltx
+        oSvvG3orr4MYD5fAhXu3xsy6LA65MM5YResNPjN/XC8F35Eh+xufmH5kNPGjoCDt+Za4p7Hvxu/8
+        Q9Myyoljf/JucPA5QYGm3rBkme+YL5TYhjrcIto7i40Q294J4bIatsR00VH0s6DN4MtHxDWJZXEh
+        H0Lt1JYlwUoyoEG2VgD3ZL4itsT2YsEzNUT5ytoRgiaR04W4t2gvr22G36ofC8QOGPK1qZNY5yoa
+        uKWrv/6Zs5P6fLKu4RbNj+uKGVEH1bQOzj365U/hKXI8hu2qRiTfbIgdJbtY3EUFmn4LPwSzexdM
+        zmYnQ+h2e+LPZMkSrG1u6NuvzPYOYPXDK+xRZ1+vZL1Y9eI7jz2QpJ2g80TfC16pawzffie4jjfd
+        +Mk2Pohp/yCbfC0s3j0jGRJXO3z55mnRWzltgZHVmgSe7li8PO9AuyvTjcoufCxaX/oSsk0bEM9W
+        c8HbizeBE/o6sTYTtwbjESi/9UX8sWgs8R42OlwR9YixfJ67oaMDB2lR93g+U1YVvayULSJFaTLf
+        b3kgtpeGQ1+/OQvc1A44uyr0738UK86Q+GxDD47TYs7M+1US71FbbGFeJCNWT5ep4463pCgy+pSE
+        kRV0/UKQG3puXYmR8z2qJidfNkDwxPFD0aJKMDjfIDm0DVXExrV6Bc4y+pRSw9y5T60J5n0Jr3dV
+        M+ssrtZ4jHmo5rftjUVz9xB/+UCGoJJksj8FPerW5zkgfXGSqKQmcVdhliqqoXQzyvC0Cybda6df
+        PUDf8cFB4+r61mHE+zN+q+dVwG5tFgLrR0zseNkJIZBPYbmVbIZtbyP4dSNu2q++8pXPC/WPk+3D
+        M+5zthbDLZ6ucteAF5A3VdyNhXhSewVk3nFPgjaokQiKRQ+CFQ4J0N0Qk9FVEszPg09H85Kh3p3X
+        /G+8BZae+Xh0dhxUnuYEG2ZVjY9b7cJQJSXbONs85rmjcXjvygnTDft004t7HwgtoyMkltx8lNL6
+        DPyUvOjlq2/5a31S0S59ZMRIUVyJq6x8QDNeHlYOz3U+SUFswldvY3Wfa/Fg+vsG7M2yo4LvToJ/
+        8wlVEF/p/cRelsA39M3PvWamixaILl++i9hq8yLe4qOj5a3dY0jEMmffeg6kZcNAXTSNx3T1M1R8
+        TrsSvVzmMZLoE5qOeKSaHAx7Esa1GywSWWzRN17M3mtTIGqfPOA7/+niYmKLi2FzgLSONBJ4z23F
+        Xp3pA7XkkBhs6nJavLMZ5Od7hZGb2hbf07sHS66vyDWHOxrnufuAJj7P2FefWJO8ekkQFULBsR6w
+        WMyTi4uO3dn98v2pmooMbqr0xvGvvkHjJjJvsMOBjDXLqQJ+dxsJiqr5MOJ+jtVkxNMDslIcSTBM
+        z4q7Ns+0RpslzAmCJBjdMc/Ql48JodbSGondUkSG+ZNEzo51zByXLvJrP6bLm7kIxq+eBMOfTDzv
+        ln7Fi+swQ6vXzGV4284s/ng+amBRkzI9T1+dQM3mAIp2Hkg07XaCPyf0P/nYDn0wRdkNQzVXH1RC
+        i7MYC7or0YFLlFmGs7H63FlMQFmasgieKeKr/wAAAP//TJpbr4LI0obv51dM5pZMREC62HecRI7d
+        KIqs5MsXUDwgigLdQCf7v+/gmuzsWxM1ge6q532qLokA6uvzplyht5Z77tbREhddsYK2RiU/SOHA
+        G3Sf/fJu/CopPLdOTPlSUVr+8Dd3+N5vz5dP1kAzukN1anlEt1KrGN5NfgVDeQtYuud3/jxNtQhZ
+        LSXMCavW4lbAUjDYKiTe2TKTZX4WXTDfbY7F68ay+POiZGDJBiHhubrw5hzpIZC74hDXStT5Puol
+        EDPPsDbnqXdkviUUZf6J6aKXBJOctQ1Cjlziraw6iGojNpUz0j2yf4h+QM9hakN0GpXv+7Co2d8p
+        XG9Hg4Wc1WhcP71G9SpXJutL5VajlF46eG7Mmg5ZcmtZ5w4+XKSxIXM/akdbvDqafA5PDD9FO2Cn
+        aVLhgiUDL2i2LsbGayWAl8GoSd911UOkqUjd+Iis9+rUTv0i9kF9WCblGV9YTEpXItx26Zms/adf
+        Lam/V5CNh4AECZ+CUVCsDHR1t2eOfLzypl+2LqyX2ZWkkqsgzi7J55fnjQPuKro/Zz6kZRezXdNL
+        FXtWcgcyb64YxFMf9NsyVuDQU5EFmwpZY0C8XM3d4w6LafZsx354NCAyt2GmiTGfXiIRIIk/Z2LS
+        vVw8EFvt4D5dKVmbJQvGdHxRmOsHM33jZHXHTfCAtXv9wf2iuLd8ebUpCs+bA+a8C4PBeJk5fHkY
+        fXl3E2QUoADCzO2jC7op+XGhg7xjDrHrinfW4wnb5LFmm3K4F+Mo3nPUHzWVrC1LrTioNQCmiUn3
+        rZ4Wv/xkB/6DuWKRIfbtL8qF9CyY+W4+bzksiJARR6jNSsRcitFcX/CUSkLVeTtP/+YpNvMhn/p7
+        sgN/tT0T3dbsYhl4mogOydtn0bGfUKftUQyRQX9YeBLEhA4H1K3mvEj5Vh9Rp8baHQ3dZcTTwvvh
+        47QQfSg2uk7wz3qDRq1bfZDsZzqJd3BGnByvD9QbN5m4RRsVfCenAPedobNQ80SrjyUzhF7yVUYE
+        ZdV2F4/fARflkzifaAj6tRdOgNSgYV5+f1X9EBaT6gJZk2D2IXRZKHsQXVrP/eKc8OZUdSAGRkJs
+        HLcB08bCAWeaDnRlvdWCf2Lbh+p9uhCP+8eCKYgPkLkQsnBpKFX/YvwJi9y0iEV+BjQd4+EJyAxN
+        Fn/zp9+uQsBrvSLB+Y7bKc2tE5Ai8OhoC8uK2oJuagqsRWJulqyi3dG4Aq0Mgxmqw5NeIDCBEXCZ
+        Lkj3Qf2NmVe064wf5r2rtPrWs99+pwTDo6U7bj7h0Q1vqo1HxWLLOovBt5qaneXkFcz+avqtn9e5
+        3k7UvwFkjWfQpVmSYPZLgOpod2T29z5w6R2DMpoHtv6BFx/EOCwRSw8Bi3atVk3ZydxDAR+FhPBo
+        KhrlDVZnn8SyOn8jqvjrEG7kqjNLK9x23E3aHa5R1NLSXcZoTAQSIzs67+jwzcPV6OVgpqJA0p0f
+        cA6L8a5dqkVIpXciFYO/tB1ganllnvVWk8/qrQvAB+1NPxf93rLO6h4gRWZAc+WzQQPVAVB7/1zw
+        bRRk1MeSj5XGtjVy7dBYdDtZ1JEeZRE5Ohoq6AGvOlCHoiB2PlwKFpXwRHV3Dom/iVBLvctyD/tP
+        9sFPYq+rwdsZOhxfQY37bl23/C0VKjwOVs+il+bxQXTGJxBjfWHk+vaCL78g//STEme4ZUF33ogf
+        qPDKIfah7PhASZKhQ0Qc9q1nbcme+OvTiBNiQNPX37VAPUKoNvBffgy1l0VcfIOquUerGM3vn5mp
+        JLTjJ7h3gM7Jbc5n94A1SSbBN29as08crPwjgSo4HcPGi1hfn6IZt9Bha8vK22lZWyGQTCyItT3o
+        Ftete/ztd8S7fyprjLbuDk7r4kP3E86stnb0UJv9A9Mb7Be02y4BYrnn3/taffOsetIHzIzk1Vbj
+        TTnn8IonzqLC3SSi+HPZq8Kpwcx8v4Zkzi938OK0mL//007XuJBg+ao1Fk1PPZAFQzmBdJFeWKlz
+        D43hZJ/AErsbswczQEPGcoxm/zbzwdsal8rVBc9TjmxD29biw0xx3nsTMiO/XoJ6376vcDHcgfh3
+        x0XcWRCKbgew6fS8+dZ43MSNVm9SkwQXI+Gf56Xag+uqiDnH0LCGIXQodJYfESz5t4RZAdujMsfC
+        L2//8vEytXNC6jQO5LQ8St/fJ9nhYlhD+9nm2uzfGNHovX19nDFGpTUhhr38lIwu38Vozi9kvT9s
+        gmGNgx38LJ5XYs282x+DCyDXeUSsKFBftYNZDkixXcycjJsB3+4TBc15jRldVxeDq2QDyIk/0UVf
+        tu1kYCrAOVVFvK9phab90jghYXU/sGjsnslYueqArm3Wsl3ntsHswwCFckMJwVHdjtmnoL/8kh0u
+        t4BPO3C+fIkFj/mtKnBbgYtYqlSS3Ax16ip00ZzP6AN2JpfO23cDn3r3oTIOtKBzpB8FYnxJKEkP
+        RjAs3/BBX56RVlVfdLa5uiI9kbbEl5spGa3DY49ei8WLuC2yiwF/2mx1UnoRK30kW938fOFu3Hb4
+        Pvp6Mog/xxRmtYpXj+3Daue8DJvLpyCeebGKvkySEs3zADyOwpE/isDbg07RQL+8Nxhk6yDxYAuY
+        9WVQ/frr2eczv8kHPr3teg8nfcLMWia9xdml+MA68pZUrt9LNHrFFaBxipYq4rCxxCSXXRiPlk8H
+        9HgVLP/xKcqf1x07zfl02F19Cn0qrGceO7XT/Tq6qInPKR66dM3ZZaxt0O6OxIz927Dkmd9QlyVH
+        hrfyM6DssfO14xjFGNHjaFGv1lX4WTyuJJ/74bT1kQCGqN9ZGGxg9s2HHWyxJ80+z+O8VXYT0vLD
+        imwEo0mG/d17ICkpCQsOC6Hq0oZMoCnXFdmUg5n0m8BqNJ2uBjL7I+uz9Tmg10c8E6J7RfC9T9C6
+        a4cdZh9Nkw2LgWM4EhzG64Rnx0BE952lE98VoRp3imHDW0iV2f8c0XiR0itkA+LE2tbnpJWzoUOn
+        ezIyc1E2AdeFskHtRTTJdn5/fP9UHDCOfsGs461LJl9Y2bBlwpltpFIpZONZ79GYpRaJHrLFRfl8
+        cNBcL0gat892YFN6gvWi9Jk9VU4im7LZoGeSC8wYf8Jk4OVdXc15vY8Degp4a9QUXdu8/fUhH7AH
+        WxtSg+LJ2C+DMcoLF27krrN1tKmL4UTDHG0D2WXYvLmcPp7yHtQf7Ui5cLgn3N5cdaB6WP/Op8b3
+        OJWQNYGB0fNh8UHdfBo093eiz+fnt/5THddfnkXjZ798QjMsbNylByFg5dktITYdRKLbiRVz3vS1
+        57Bd0+XiJ7em9VHZfedVdKFsDD6tqmUO6sMwiSOdX3OeNfbgBFLFSMVYwAwMJuJNKDOreL8Qo3tD
+        VeuPX5L1q30E/ID2HXhaeCOWNO2SjthJ81sPcayFhbh18issUPVk0c/btKbV2xVgJeQe8yWqVF1t
+        /HTo6G9LNvvfgmuNHsI7DlZYlajSvp+plYEYpuE/8ylX5h2M/SViRuRsrSkerU7jS8UjG69Mg+Ey
+        +b88itHF4Jxlx0CCaJ3qLGglqWjju5rC9/45iu0G8nwegRibC+abZ9WO6DNNyORsjT+rx63i0eFN
+        f/PdzuRqwgcznYAZoUF2IwuQLO4nAeRawyxaiQaa/f8elq+XRl+1YFtDjHQKVrd4MM+aJ3+tEnXQ
+        O6cjITHVi2HY7nbw9Z/GOql4f7ogE4Lb3aX3h86qYd/uS6hTw8Ozj0ZtPogm4KO4YMai3wejVhYh
+        XI5PTgfX8tuv30TSetCYbZlewm3zVK4i+bglVsmwNd60q4CCp/fAy9X0k0zOkk3osesWLMAjcDoK
+        ZgqP9jwwL+rrgA9mOUEPa0L0fhkEXB4+Oqzf+oYVT7KsJtVcYSSvz1ey2T637SDI0h7N5wff5Fqp
+        WvDCExx3ZoEhOPmttKq0DJl+WbNAn6pkPJqRDd2jHfDSylw0+/wnchZuj6eLwtF3/goXezgS73X8
+        BP2POupwzu8Fs7/95RonEvJzp8FNMDyqcak0LuSxQ4hjqHtEZz+Pmif6YXh0u2AqyGf69gviGAev
+        mGwFTgjW15CY6dNIxCVzMUQqKBgJuxWa/FV9B0XLe6ZbiPKx7sVOxTf1w771pDNukgiVCyOZ600y
+        8fEzoDlvEvfgT6i2Dt3+O9/Fsvs4FfxUGE/t67MTdFkV/eLdAby0z4ps5vnGOD4tYfVI0yednwcX
+        9yJLUVjmmMz8Xg3uW02Byn6KpW2tF/x4CEF1F1LH1mOut5MJhq+tnm309Q/z/OMA2qRc92S9iiI0
+        CM5JhPAWtsSa8zrPf8zu1x9BXF4Dqoo5hWwKO2Lk8Q196I+eI5Q1a7Yj1pjwkQ3CclnKAb0Py8ka
+        /adKwW02AzO1hcm/9UjdRq5BDurm1bZpeRRVYvcO84/TFfVz/kDu2YzZl8ckL/2UMM/zGCZpUIi7
+        q0khtKwWr+Z81m4yWYC9xC1GSpcmw2RPHeLH3mOH+fwO1zyWNKQjjw7OpkgGaVa4xZptqLi0jWDa
+        GjdH++u7FfDvP/788/++GwbP5lzW82JAX4793/9dFfg7P+d/i6L0N5N+NxFol1/Lv/71zxLCX++2
+        eb77/++bR/nq/vrXn8t/1g3+6ps+r//38z/mf/v3H/8BAAD//wMAz7LCz+MgAAA=
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cc629212e6a3ac7-DFW
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
       Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfcbc95b7df222-ORD
       Content-Encoding:
       - gzip
       Content-Type:
       - application/json
       Date:
-      - Wed, 24 May 2023 14:17:38 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
+      - Thu, 25 May 2023 18:21:04 GMT
+      Function-Execution-Id:
+      - pbme78psn76u
+      Openai-Organization:
       - significant-gravitas
-      openai-processing-ms:
-      - '27552'
-      openai-version:
+      Openai-Processing-Ms:
+      - '70'
+      Openai-Version:
       - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86463'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.358s
-      x-request-id:
-      - 47e4bf23b06275bef6330450764eab29
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I should start by reading the instructions_1.txt file
-      using the read_file command.\",\n        \"reasoning\": \"The first step is
-      to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
-      instructions and determine the next steps\",\n        \"criticism\": \"I need
-      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_3.txt file\\n- Analyze the
-      instructions and determine the next steps\",\n        \"criticism\": \"I need
-      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6394'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5RSTa+bMBC891dYezYohPfyKLdWaqX00FO/1FJFjtmAX7CXZy9NpIj/XhGIkkfV
-        Q64z3pnZ9ZzAlJCDrhVr2zbR06fn7XL3LbE/Pn74Xr2zCj/z+/XLzzb8yTKQQNtn1DxNxJps2yAb
-        ciBBe1SMJeTJKnt4mz5lq4UESyU2kEPVcpTGjxF3fkvRIl0kIKELqkLIT9B6si1vmPboAuRJusok
-        XMWvxGMmgYlVcwMtV70EXZPRGCD/dQKL4SLsqUHIQYVgAivHQ0xyjG5Y4VQ4IYQogGvqqppDAbmY
-        wInAIw9gAWvhEEvBJA7eMAquUbAK+40phXFMZ4A6bjuO+chiZxoUXTCuOjPnoQ3T5oxrsla5Mi5A
-        3rp5VIGccdVo+aVGYVxg3+nhCEF4fOmMR2Hxvhxzn7ZRbrSIxNeA/w94n83MRXvDRptg5wdEFzo/
-        SCoW6xt9Td6j5rvXCS2q/cXkYJrmni9ydIgLGOV6eSnEtP8/fXDK4uj06l6zQMpX8yqNxPD2KnGN
-        8mp+3rxlmjxcEp5TTmEL10MvYWecCfVm7A7kEJhakGBciUfIF/3v/s1fAAAA//8DAF4b24zkAwAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cc629de3bf83ac7-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 24 May 2023 14:18:10 GMT
       Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '29389'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
+      - Google Frontend
+      Strict-Transport-Security:
       - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86466'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.355s
-      x-request-id:
-      - c74448d89d195cfad9d7fcfc8ed151c4
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I should start by reading the instructions_1.txt file
-      using the read_file command.\",\n        \"reasoning\": \"The first step is
-      to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_2.txt file\\n- Analyze the
-      instructions and determine the next steps\",\n        \"criticism\": \"I need
-      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains further instructions that I need to follow.\",\n        \"plan\": \"-
-      Use the read_file command to read the instructions_3.txt file\\n- Analyze the
-      instructions and determine the next steps\",\n        \"criticism\": \"I need
-      to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to write the task_id into the output.txt file using the write_to_file
-      command.\",\n        \"reasoning\": \"The instructions require me to write the
-      task_id into the output.txt file.\",\n        \"plan\": \"- Use the write_to_file
-      command to write the task_id into the output.txt file\",\n        \"criticism\":
-      \"I need to ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
-      \"I will write the task_id into the output.txt file now.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
-      "system", "content": "Command write_to_file returned: File written to successfully."},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7348'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA3SRS2/bMBCE7/0VxJ4pw684jm4FiiIpgp5aoEUVGDS1lhjzoXJXsQ1D/73Qw7Wr
-        ttdd8puZnTOYHFLQpWLtKpvcf3rdfv84f36c7ec791hV+Pl5efx2evuwPEWQELavqHn4MdHBVRbZ
-        BA8SdETFmEM6W62XD4v79cNcggs5WkihqDhZTO4SruM2JNPFdAYSalIFQnqGKgZX8YbDHj1BOrtb
-        rSVc4dfFbCWBAyt7Ha3Wy0aCLoPRSJD+OINDuoBjsAgpKCJDrDy3NoNn9G2Ec+aFECIDLkNdlEwZ
-        pGIYDgs8cjvM4El4xFxwEFTWnIeDFzUZXwguUbCi/Wawi0IH55TPJxnIW1ZERcEbX/TALyUK44lj
-        rduIJCL+rE1E4fBWZUyprPI9IBFfCf8vfwsZMXQ0bLQhN46GnurYMhWLJ1Gqt47WYXOhrO3UBp95
-        J0tii7sQsZPi9h7/Mk0Vqv1F7GCsvR7Rh8Mkg/5xIy+FDBn+6sMrhz3nj8wjORWLcZW3FfSA922c
-        LsE1ItVaI9Gutvb021XnbDCY+QYaCTvjDZWbHgcpEIcKJBif4xHSafPSvPsFAAD//wMAvNN1YlgD
-        AAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cc62aa52e403ac7-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 24 May 2023 14:18:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '19007'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86473'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.35s
-      x-request-id:
-      - d281dd2fbae62c2925a71cdef320242e
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 7b3aeeee5e3b212f52c48ef9748c385c
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 65f5b07aff01746ac5a824644cd2e8bf
     status:
       code: 200
       message: OK
diff --git a/tests/integration/challenges/memory/test_memory_challenge_a.py b/tests/integration/challenges/memory/test_memory_challenge_a.py
index 3e293099..1b1bcfe0 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_a.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_a.py
@@ -1,5 +1,4 @@
 import pytest
-from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -15,7 +14,7 @@ MAX_LEVEL = 3
 def test_memory_challenge_a(
     memory_management_agent: Agent,
     user_selected_level: int,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
diff --git a/tests/integration/challenges/memory/test_memory_challenge_b.py b/tests/integration/challenges/memory/test_memory_challenge_b.py
index 28261cb1..f05c1cfc 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_b.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_b.py
@@ -1,5 +1,4 @@
 import pytest
-from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -20,7 +19,7 @@ NOISE = 1000
 def test_memory_challenge_b(
     memory_management_agent: Agent,
     user_selected_level: int,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
diff --git a/tests/integration/challenges/memory/test_memory_challenge_c.py b/tests/integration/challenges/memory/test_memory_challenge_c.py
index b6cbc60d..f6afad97 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_c.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_c.py
@@ -1,6 +1,4 @@
 import pytest
-from _pytest.monkeypatch import MonkeyPatch
-from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -21,7 +19,7 @@ NOISE = 1000
 def test_memory_challenge_c(
     memory_management_agent: Agent,
     user_selected_level: int,
-    patched_api_requestor: MockerFixture,
+    patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     """
diff --git a/tests/integration/conftest.py b/tests/integration/conftest.py
index dfb94d0e..cb49bc13 100644
--- a/tests/integration/conftest.py
+++ b/tests/integration/conftest.py
@@ -1,7 +1,8 @@
 import os
 
-import openai
+import openai.api_requestor
 import pytest
+from pytest_mock import MockerFixture
 
 from tests.conftest import PROXY
 from tests.vcr.vcr_filter import before_record_request, before_record_response
@@ -30,7 +31,7 @@ def patch_api_base(requestor):
 
 
 @pytest.fixture
-def patched_api_requestor(mocker):
+def patched_api_requestor(mocker: MockerFixture):
     original_init = openai.api_requestor.APIRequestor.__init__
     original_validate_headers = openai.api_requestor.APIRequestor._validate_headers
 
@@ -51,5 +52,3 @@ def patched_api_requestor(mocker):
             "_validate_headers",
             new=patched_validate_headers,
         )
-
-    return mocker
diff --git a/tests/integration/memory/__init__.py b/tests/integration/memory/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml b/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml
new file mode 100644
index 00000000..b79a6486
--- /dev/null
+++ b/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml
@@ -0,0 +1,2672 @@
+interactions:
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Sample text\"\"\"\n\n\nCONCISE
+      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
+      0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '252'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOQUvDQBQG7/4K+c6bkBCT1j1XRYSA9SRWymbz2qwm+5bsK5SG/HcJqL0OzDAT
+        XAsN2xmxQ+iT1cu935ptWUfTvj4cno3d1E+Pl0uV1+8NFLj5Iiu/Rmp5CD2JYw8FO5IRaqHzal1m
+        xbpcFQoDt9RD4xgkKdIykdPYcJIVWQ6FUzRHgp4QRh6C7IW/yUfoolK4pv/xnYKwmP4KslnBduws
+        ReiPCQPFv+TIPUHDxOiiGC/LIHshv8zv8GaW/K3QWdIdMCscnHex249kIntoROEABedbOkNn8+d8
+        8wMAAP//AwADaRSQLQEAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4adcfe613ec-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:14 GMT
+      Function-Execution-Id:
+      - yvvl5lovloye
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '754'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 592e9151aebda45ed59a9ad565a24324;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89466'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 356ms
+      X-Request-Id:
+      - 7e69598f8d9d0bc01b752e4a0b05fa0d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Sample text"], "model": "text-embedding-ada-002", "encoding_format":
+      "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '90'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWQ+zvJal78+v+PTd0kcBkuDNuWMKYbQZMkCr1QoZSEhIwmADLtV/b5H3qLrq
+        JlIIUjDeXnutx/6Pf/z119+forqe+7//9dffr0fX//2/5muXU3/6+19//e9//PXXX3/9x+/zf9x5
+        rYvr5fJ4l7/bfz8+3pfr+Pe//hL/68r/v+lff/3tJ8svlV+lXVErX4hr86DtGZaqBPGXTM4QWJct
+        s1/uuu0vFk4A2lFgeIV35sSNKVDv9kVllpCZ/rjpGwtlO8ci2rmTUy7XSbCWZeIRLCirli3MM0b7
+        PfhML9vU77yaOzCpzgOPsfou+GDZA7CrHDJHua5Qv45FCvbHrQjWvhQNGcoSWCcSZ3jbaQUv3CiA
+        nTFe2MY28nYSat1Rq3y5/z1v1V9uJwv2z/uR+A/liKZFfTJgWXzvzC49K+2bLCnR/uaHVPLMizko
+        1k2D91o6kHBEpj/4MRzQN9QsFiz2qfldv60TbBdhRnDKGj7hNw1QGdoRC4TjvXjbffNAephwWo63
+        O2KW8T1Bp9Vbps/j+zLxLkIpFwyrq0+bcjtLRNh+l4QuHgVBg2IdNbQdPiExNL9GU+fbDvgfMmF5
+        v2mrfpOdMliJQc7O7+jedjsqRLC5BDXxZU30W0r3ETwPxCZ69Pm0HEumAg4qETFu6ZeP2w/p0Jb5
+        HgnM7FJMW+mVwcUtMZVraZPKlmQ2QKiyYyGL7uh9ML5n1O2FiDl+sm2ZXi4aUGrjToLypVV8k+kC
+        rPKrTSwhq0xO3a8HmZiURGtzoWC26XtwYmmDl9Y3TCczp6BM0/XK7O+98Tm86xoJzD/QdUDkdJqM
+        +05tfK5QNSlIym3TdGBzVFpmfV/LdmijlQDv3WlBlRgZqZzXrgam1gQk1E3bHA99noAYFicSViL4
+        v/cJJ9mTWfgJo2Jw0AhQeKZK9PU2bsdHua8BkpISMrpFxadbdUZrt34wa9Hf+RD2uQHvsrZJeBKr
+        ontklQMPMROwhIuw7epbvoKitwmWniGupoUkX8Gj8oa5JH6mPMjfAXSLmBJn88oKjozvE4510ROi
+        q006LNDkge2YWyyH1scfev9aQxIt9uS33kbZP4iQtG3OsJe9zPHzvgSQFG+faKfs4Y9Ln1F4G0hl
+        ni271XCBdPjNH9nGpoWGY/QxYL3Ybim9jSPqdHcMYBBvhCrlF5tjCr4F/uXek2BCRTudwTwspLI5
+        Mkf0LN7ujayGaPgQsg+okE6b18oC/dH7WNF8p+XoOEZIWq/fzF4k25Rn6tZAEnN3bF4/5vS5VRgS
+        DW3pWrIZp/6xNODj7zKs7lyj4H5+2MFCo2/mj4uhGvlr0KBE4wqL55AWTe2uJ3CjRUpRsuxTniCl
+        Af74Osze7seKunXToftqU5CLKvQV9d/BFV3dbsVsnNt89G66A9LuFrGNZ6o+7dD3g3ymMUbW3s1k
+        phGVsPH7J3Hkyz4tlXxZK5cw35Pt+tGjLxUjAVarTUl86FaoaaLyAUXxDvFKkd10WYjaVfXzpsbi
+        C91NHpcXAX2X8ovoWNm3PImNEwxuQ/GiGnA1BMfhqpyn1iTGs2Gc5+pNAdDNjhijtU2HY1Qa6jq8
+        fVkgxldzUlEmgkA0hfjdlxY8rk82CC5d/PSM80wlBir9N2Z6v/HaUarz4bf+mKVvfF+k5cJBC3f9
+        xamcPfhwMz4iPK5QE/MWm3/qB9Urt6HiQf6kDbyGBB6LrUG2G6Ezh7GPPciH2iTaa9Okw0HyE5Dl
+        0CNG/EyrCW6ig3YfItKJ6vuKl17RAckfPtMeRtZ2bpzUcLxvJzouR+bzdbey4fRdMGaORlm9lVh1
+        FLl2gGz226ToQ8k/w2cQBeJt7g3/ip5qoVNEb8TcOFLapGJsw+KWTsza2LjtVuK9AdbnOXNr/Wj2
+        zB2falc2e7ZZJltzet9OB4U4uku0UPDa0RUzEaY6PjIHg+CPRHoFUL7FihF6kdHrV39BSc9su4i0
+        djnPjzLXE9EFySqGm1HK6lcuRiqt66Lg255nUK+bDqPFMUd8QYMr2pdNxBzhdi6mvefVoG9hRbQq
+        O/Fhri8Y3A/F68UkFr17XSWKL2ZrpkUNSf/0s9/8m9/3tRhqy7bhsjA45ZZntlNwXK3QWlI2f/oj
+        /xhRAxfxwMj2ZJz8YUVfJQhDk8/6Nlb9PB71TQyJzHprct1ngLwwkYjnBIHPOXI8pbftjvhV/ESf
+        MHMPkK/5huiPzCg+iRh9YGudVnRSzHPFhZ4/QUKHAk9DJ/PR6vMAsK4/iFvtk2LIpN5Ai3KQ2OmK
+        CpO+3I8CEvN3mH/i8zwfyQ7ebeSxTH+KiIe3agerBztioZGbaqRiJkD9GO94mPWtu7+FDiWHNMJC
+        aNop/emP1dsec5djhMZXjc7osTsMxOhNk4sXKAaFH1cSI9I9MMdHrcngRMOXmMv+XrEsO63gGxoW
+        0d/0WQ1uuTQg9M+UHCSkV/SE7jV4/dEkzuDe04GCIcC1/CRkW+UL/pHNLoNFkbXEm/RjwZS3JYIV
+        IYva/aOvaIuyCZIkc/E1MYqKD7dTjdbrMcBIMApz6GJdRGznuOTyDDo+vo0sUOpJYrQ/XQ5p/6tP
+        d3pUzLgIvjnRuPCgZYbMglF1EXevKwrV8/3BpRUt+WTXjqDglovE0erKpIs60eCbnDDdZYHHRyOG
+        BzpMJ4+ZC/Zph0eyXMHx4pxJaGQWf2WmMaDjdkjZtZa25jRl7mpdRZ+U+Y73SulwLD14beUnva0f
+        pJ3KPi6hUYuMeM1RQ3Qn3gHO66vGDDT4aPDk2xMZN63/07/6jbGWwdQ+AbkdslcxgjEZsLpOOkYX
+        ZFRUkPoaXVahTGb9b8tlHghInnYm5fp2nJ9fLIH2AWP2+rmrvoz2HSxs7UFcP9I4f5XLCTrx3dDh
+        pO9NvjB3gWpTKMk5vj3TT1Y7NbLat4PZxzXQrH8yLA72wELzIFd9Kt9klLOthlnaP/3+dnsAXJlP
+        8EKLCpN7pjRBOGUOcy+LyB+C904B/FZ6Zl0eoTk8rysHjGQtESu8GVXf9sj602+suX+1Dg0i2KhH
+        gz63I2ung5deQReTgoRaK1V90zcBDMl6gRfNmaec3XQKaVJzKsalbTJ0HBM4olEmluOW6ZRH4w5G
+        f3ciOnhVwfANMDI+qUA/p6zi48LsGng96iUje7Ou3o9aT8BgNiL4cr0X8/OvkNVbHjGWGSq6e5ZE
+        IDxvCdMf2ohm/26j90vRmf0q67azvEqGJsSUOQux8Idbn9vQR/KCLg/52x/jOm+Qv7BVLDquVvQX
+        KjzQz+9o1/xVjXavADKe2ZJ+6cn3uVS7Bwi+6IqF+81C7RJNE2A1kolNjlk72Shr4NA+BOJuqrhi
+        7OZ260V7XeNF59Upv4pNgH7+b3nQD+1w9FoFAu2p4eUiKtse9XGGdKNRmXPVZd7tclojXF/WzHTL
+        FxpyP/yg55s6GLT+nA5vz8OKLigxM8/1wxxM7ySguZ4x19zSbG8it5BzsJ+UdZ6ddvP40QJV21nv
+        17w81yiActttMVBl5XOl1wBkkg5zPznwaUV7gKA4JHQYHZGPeyPzYCM6GtvkjsSbU50rwI2yY5tn
+        SKshvTkCBFqtsS0+ar7M++YKxDFdul6592qo8/2EDMd/0DWJn8Xw8VIL4aN4I3qxC/0pBEmBaL2M
+        2TZqxYI965ODSjXomJks22qY+6WSfcuQ6Vmy8On8/0rX7nLmhk/J51mWrGDUPgdMh3CouGlkJdoX
+        kU2Sr1EW37u0y5AiW4zgIRxaNnnptCLr5o0XnK/9ocrAQGaOzrg/nBNES2NyQPO/e6K/zKodTrE7
+        KOQq2kRPUG4OeXnZof3QXSmXMwOxbc9PgFT7gFdm/PQHtXY6SA5xxEhuef5nHq/67DWTBLFzLLia
+        pQaYET0Rq4syNDQoOkBS76/MOXeZPy7rpgHL9kYKrj0Ug+EZFqQr05vra6ymnTt2UD+jirneOuVD
+        i74BwoeixXXQHVs69XGtBLV2JJoib1uq5wcb5vxCTCw7Ph/o0gB83wzM3z9oNY6iQkG2LUowoe9i
+        /OXFWW/oevfxioGbxkcNl1OMYee7Zn/sHw7s1JdKr9oXozHLkjOsJv5i5ub2KKZCJgG8rcNIAvda
+        IhaXe4BbcZ6I09usGub8h+b+xKKm6CoaZVUJBzmN8cvdtAUPPG9CoytlrNBcnUtV7Blo7tf4NcIT
+        TWq5MdDGeDx++mZOijgJIJS1T/Q63/CprXVbMYfpQx/562iOW7Oo0fpSLal4FBXzHtweKzXf7SjD
+        /uHAJ4PKH2VzwfVPP/0pvbkZOhvl+9/1p7sjVrWjfGbOfkHQeAC1g/l3on3tntPJ+B6Q9chsZvYL
+        ivo7ikpUrz8d0f3YaLmM7goIkrCjwrf8FK2fXw9gX5WE/ep/wNkJK+G7M1mhZFa7TND0UYiYXAkx
+        k6/J1ffijAZjOTJjtN7p1ERlqcYRvTCyFM/V8DSfB3RW91vK5jw++uK3A129Xej6tqOcrsQ8gFq9
+        c+bja15MgvSq4fk4hcwWcZKO77d1UE67d02n8tsVzHfHFWyKccJCMeCUd1krA38vTKJn387vl+Bj
+        1PfGBrNt2rU86x81GDejx0O661B/zamIgnwZzbyjLEa15x6Ux2E/55GMszvSbPQ9xHtGnC/x6fM6
+        1LDPlwleXk9exYNbcoW4yO54+XTv5hCZxQnqacloV4aRSX/+WBCrkpn31zGl2/JCgdNJY8a83qcQ
+        1H/7BS+N7v74fVMbXktVo4/FSIrlnPegOIQWs8Lbo2KzPkP2xAnx71D74ymD4MdLmP6mVvUnnz/l
+        eMesd1wVtJHODbIOeIHv/carBkOcDqBotTfnZyuV9fxqIbZdGHShRcgcN6pdgsEsRJXX+4bY8U3P
+        qL8dgYIYC2YvlZcPuudnnW38DKHxx1tM4rtUzL1zO+ZZtUOraXwRq14nfETJ5vlHj+O5voaupAlS
+        LS9gBB/vfAqNb6BcDBYz2z9I5iBfVxjNfoC+Vh+35ULWruB0ME7MEM5D1cZ1YsHxcLwxvdalor+j
+        7AHZVlApWvZmIW99bCBZoy9GIBzQcE/exto3eIHRO/mk3IxFAey8PjKiv3LE7f5RAlyC6Y/+TF25
+        l+GSbU7MnP00f8XFDp5krzBXuOzboSmDEqpc2hPjGD/QGIjTU3VytSV0CKN2PGXizMv4hZgNXMzv
+        slxmyly/xM2+PaKBkR2U8m7WeDGWTjXmZvoB/SqbOKYnt6CsRh3E6KHShynm7bBFd1ud64NpXztE
+        Eok+gTLzDYrm9UGdOpfR7MeJ9zUMn1vJRkbkwc94Zb3rivc0yMAwlm8KZNqh3/uGWHZEQo6H5ewv
+        4g8U0zUnPjocUs6R5qgXo4+Jx2ldTYZ4V+D8BoEZvnTxh7VnJIi+FREPVaZwBn0uQ1Q+debM/qiX
+        0P0K+lZY0eecd7kJfQAbdW8Q114NRfOmwgALf3fBw40+i2mXXx107HFDl/V5rIby/ZLhhiqNbI/H
+        FWI/nlNOjw/78bZhf2soKqNFRtdGeeOsEJ0zKlXcMbfqDd7bpkcheVyPzE5OXjqk4rdEsBW/xMXK
+        Mh2u0DWwdTtOdJLYJhdM/wDQxxpz4vei4J9YtdBeNnKqdi8N8Rr8J4r9Q8q8SV8WMz87QLNd8X/z
+        p17UHj8/SCELuopHUt+gfsoIM3qzQpPmloOK69sarybRSKeKBt6vv1PI723Komgs/+gfD+9uwT9G
+        1ijZM0hwKSxbk21AtiG62QLl5ftVTY33PIG0Rm8WhpvQ7G+SWaI5f/7pv+z4rq8w5w3i3Kjtj/ve
+        OUGXL490dMiunTJp94RgV+1ZMD/vzIsDNG4gJjOPQp+5f4BsvTvM5zz3aWvng4zd7st81XLTMfXf
+        T0TWnzeVVXiZbLq1V+RotMDLbdqg6STJux9fYtYL3X32krdXcBpzzXz9qrUDrXkCbOe5+Df+YStJ
+        MqxRoM2ZTStEjfY7hJcCwu9J/vpjFK1t1Drbyy8vFiPNQ0dZuOhL5UMRIrSPJQ11uxumuSkJLbu4
+        I6CZNzHfdZbm8FCPiQJb+Yvvx/RbcanWD3/4aOha35Zr/s1WZj3B9W1Kq2FKrvjHi6gQWy4fCcrO
+        MPtZ4soFbsel/+4A4o3C9OVIzEHsJwW+o/7ByjG2quWc31Fj1CuMikgvJqHcK+vZf7PNukYFLZBy
+        RspGSLFwOHUm38H5pCyPw4mFW/o2Z32MIJRjQvbwDc3uod4SNKKrTNFL/VY06LUnoDcNqXS9ZubE
+        4qcB8/oh2GqmYkrMrlMuFk6pgPWVyRxqRXAX8Y42tvxtuRiVAzD3apFAhoXfFHUzATXOF+Id1juT
+        kXJjAxOjFwvyu1+MeY80kMjWppJuPlPmuXcNvhoKZj1QfzyoRvfVtsDru6Ejvqu5rJ7Er0jC0neL
+        UZIEjL4XO2FOKASp/Oh5AqeNEBCtNsFsr54nQu3omBHSlW1XgKFAsLvvqTAtsblcxcUJHR+Pms38
+        sJiub6uENcIa0RdcnvvR/gMXLLp0fHZyW8eZeAKrXCQMO+0eTQWazhBG8opsF1FZDdf3DkD/bHd4
+        0U77aoivK2ulYjFiB9e02t/7g6OmHvAg+nXFmKmu4FCcB+bHnuAPsdlFSH1Gn9mvYC6d6av58UJM
+        PW1XjWsjisCxXg+m1/kLidfj6gHHOu/JthENc1nHHUbxs52IsfHOPuUqXoFVpyFerIIwZVjyFeV4
+        2N+Y0xS0mIbjx4O6v7yIczE3JlPgdUK6GBXM4dPOH+d+DN/p0TCyfrCq59L5vE6WcjnrQ+93e+uw
+        gqN8Q2xD19ycHj2P4JqPNsOEblO+rCsb/XiUdtDidiiTgweqAB0eNLIrJFs9nsBhe3HmRYb/4xtI
+        vu0FYiXXJafJdXiosta9qJhITzSIWYVhvdtJJN5UDHWpu05Avxx1pjVFUI03tj3BR3bWzD/XFeez
+        v/jxJkJURfPb4ZY8YTEdNuzHKwcq3ygyb+TItPF251MjnT/KzDfx0G/HYiTRBytdLh2Jqz+wz8hr
+        2P3J48FjFfvsm4QAy+R6Y1723pr9Ekysju3pw1xFNKof/0HNxHbMcdUPGjvqCz/ewHBioIr5+XUH
+        s9+hpejbVZvE3kkRqdDM/KszuzwaVmpziYBtBiK1Y6PiBhwXXbA883P2Pn4Oir0wKFZ10/b7GE1Y
+        neT9i4X17VLIFQ0c6G5+goX9pi84icoG7dHpQdfH1C8m0zMekIqeyYJwyzlr+kfz25/Bk+bbiIue
+        9AB73byYt6vNakzqRwlvJ1xhUd/45vg2ogDmPES8XV21XH0vzxDaHqc3ZYmLcQ07C/aMFCyc+T43
+        jh+sGOtRY945Opn8QqkNfH3esCBwDXPmuRg8ox7pauYVHBn3p/ocFvm8X/RIeWMoJzTXC7N69WPO
+        /fkKf/KLuWN8jCXZho5sLUamq5KOddwOaNtGJsHmjqD+Y3xtQO8uZLtGkQum12iCviYOFub8NgVG
+        tlMkWSuZqegSn/T8YKFQtQJmvZ6iyc7u3f75GzyGUKHBuvESplI90847T+24/WwpFI+TP68vnA6n
+        kgYQ39LPHz36eJB26CobBTFUGxc9elMHSjtOiXWvhmqwJBPDPUwUrI5P2eRr2JWQ9cWO+fHd99kT
+        KfSXN4nH+srvXjfdUNjEKzzNevlagh+g7+N6poMsWf4w91eQcu4TM0cal377UcJt4+AzSz7V93Nc
+        TbDfCz7zJcMo5v1XT0V1nLNIh6qazuWiBBGLmJFVEBajk4EDc34kxIqFduYtAMvQ3jNtXi9Mgf70
+        8xvzeM8+JaYnKLzgQDCQY9v99jPKcSti+bJNqulNhQlm/SY+ojYfFeProeGmLWm7OK5Rr/TOA5r+
+        6OEhN81i3o/D6ELhRZL5/f14ujr5lUWF++2JxmtOZaSGR0zlLmjToUeTBXM/JES+XdCf77M/IfbM
+        i5nZawNaUZmwoF6L7VD2dwGC7/rKDPum8NF4W/jn18kmd/Z8kMyiROhAfBLO8zOtbu4DHQ6OhJdZ
+        X8y82RPAIXFN73GtFNPUx09Qit2Z2V3QFvP+3gQfrXv8eGPL1vEzAfuZnJnVfdx05nkJyKqxpbxG
+        6+rnT6DGov9nv6P/JtdMKY/TntlzPxmy0rrC379TAf/5j7/++j+/Ewb153J9zQcD+uvY//O/jgr8
+        83Q5/VMU5X8y+c9JBNqdyuvf//r3IYS/v+2n/vb/t/88r+/u73/9Jf85bfB3/+lPr/92+R/zf/3n
+        P/4fAAAA//8DALL3VtrhIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4b5ab352afe-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:15 GMT
+      Function-Execution-Id:
+      - yvvlzvw7w00x
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '139'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - d5b6c4b4328aadd51fde99c9ed21a059
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 75e3150646d393829f5234099c9b5efd
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "\"Sample text.\"", "model": "text-embedding-ada-002", "encoding_format":
+      "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '93'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1RWS9OqvJaen1/x1p7SVSIqWX4zBEQumiggYI9AEQERuSSBnD/f9e5T1V09yWDl
+        qdRKreey/v2vn58/bVbl9/HPPz9/3uUw/vmv39ojHdM///z8979+fn5+/v33/H/IvMnyx6P8FH/h
+        fy/LzyOf/vzzI/9v5f9A//z84bfbmR3pOBlUvQQRbG6KTBt824nRfR9bUC18YoZ2efQDwBeD9F7v
+        2O4TJRXXPqoGgdQo9BHfXhnPXRnUbXE1KcQpNwSffB9V9edKTupm9Li1Sxp044stfvPTsqKnGcnw
+        3CQlvipelk3rg1ijaLI+zOxCvxf1YSOj5rPfE09Z5Gjep34KeaCrzPpud2herJ94039hZMYV9YhX
+        6JFAM0UNXfLSFqJ/JSHk4zkljs9YJs4rK4cY3Jl57nZp1AuVWYhlC0Sr6ekJvt/aHMpn0GJx6Y5I
+        WJrdomgtSbi6ol6MDb7kW67LFolKEQeiTdYyvJTrlZHo4Bm8MlVNPVmdoB27XT0efpEE0NR7dsx6
+        YgjNOyfAd+UGUx5awXtx39fw6cMlVVy7REJZrVp0NOcjcfhlmQ2789pExbb1sSq60OupeSxU1a9W
+        7NBmKKN7la+3IX/keDE6ozEcwBuQQ5BPjmcl8fh0QhIcHI6I+3Z5MJV3sUapbmyIackNEnibhJAq
+        pUqXZ8kWivLWG2TeupBhun8FnTndQwDzfmImiUwxLI2Xv51W6ovsIv9ecep+ffC4oRKsVr0xiXm0
+        gL5bncRad+757sytbZL7Hdkv9KHiV1/VYKUGH7andYkml74wuKZn4G0kmMH9btK2w8K/MVKAHlD7
+        0B6heaCCwjaXPVGp+xw9NCtm+rs1jNXh2ZmAM+lJnI/ogymt1xJ8lnVEsvz9zeYULTnQsbix//Bv
+        3TwSOA6ZT+wBup5dlSQCBSec7GutE5yihYw0AZzh/aIK2KrRS9C2dkhw3W7F91FK8iaMK5dKBysW
+        bIikAd5H3yV2VWUGXe6/rnr/uAaF670L5v1wKOBW1THJHovY46X/TFBc+xnRMhcqfvdmHWDYB3Td
+        3Jue16mkQttyl1z367mfuvPHhNpiJ6ZtfVmMH/97hOFhv/Bqdy7F4L/uOYASyiy8Ka0Yv8dnhI5X
+        xcaTu7+g6ZvZFKZCc8mheLKeYdoAhNYDU5X6WsXz8FbAKi3XZH+WbDTESoUXND2EjJxULROVesrh
+        6AYpsaLrWImrcg5hWCU63o7THU2Bl94hcHYbZiDKq+F0LX10dvGTaSikaBzyLAVdnAc6+5eTmIOc
+        lGiIIgurpxXLZug/APubM9PyFdfG9BnVNfrVL8Gb7Vq063NSAq/aidnyWglm8Whd2GclYt5Wjgxa
+        W9Mavl07kdDCYc92bhCB3Z6PzGy+bzH55T1BdiMt2G6pHTyRB7saCjmnTGdl2I+aaQxAA39D7Ijn
+        xnTRVUCKOjuExHhRscxKQ0QdIyGGWd4rUbVJuAmWN5/Y+udQLVdG7QJC5/ZXX+eAa+UbA3M3C+K0
+        ZteLU+hH0IbGmor06Ip5WcwKemXGmrg7cw6mW/HFcOPbLTm5jRmIse51wKZpszge/Gza6B8TlrJz
+        xjO+6sbw+VAXpR/lQExexRWXr1EK0fdIWJg4pUethd2CLa0iZqozZFyp3AH96gfLzKvEfDcfEXrG
+        545Yb+vc81LrzptYW0bMmQMSiJbcfST6LyNEm7khVsWWwiVY5Jgl+8mYnS0ukZE3NpY15WVwqfBz
+        6IYqwfCQ7ECIW3DebnbSg3nXx82YGOESNHx3Y6QMl0iwUS+hkpQl21092xhD0mGkw/1MtPdCIBrL
+        QYjk0/Qhmu6Ggnd5UqJ69VoTrfZP3ldRSYEEjD072uqQTdG6wHBGO5dpMeaiw3FpbxdruWbW7jJV
+        k7p0OuQ5g0ae2nz2pmuwAXhamDJ3sZLQpEmKgnT9viOnVxB488weZxSryzczg0+FeL/dgCrqZUgO
+        VqtkfWAsZ3DiqWP6w9p7cyvcGn71RiWn497MuR+p5iYzmPdNi36QijSHm19mxJzPUjArzloFGtYW
+        OWgd75ljZJFqt/6ROI/aqiYRBylqFY8z65VViEetpIITi47WW7CQKJfbAZVF/KYwaV32+94aycSS
+        iVUsp15Ek1Ggjq5fxA2HphqlV5qAnK8q4r6eRsV3jQzAne5FXOpr/dRXLUZSGgdYmTZjTz32dVHS
+        Fh6J7mSRjat8KYOam/Xf/1Qzb5YzOoT6nRzYe18psZyFoKv7A7FXhd7L1sxcNCbHkV3Vu5oNrN6q
+        sCikE/GOKPO64mLW8Nv/r78a2WzrQQKPr9aR06NtgknEWQqZAIIvXVEZ37ReA6i7J8Kfu6yLOXnc
+        EvjcW52l7rHsJ+RZNTxPO4c4XWxUCoZzAndPaZiLH7tqfu9GU5Vt/4bF5Xqr5nDSOnUsc4wnDJUx
+        ETVL1Za3JQl/83DwX2GO8tc4EhvdcSDiZeDD/j3fyWnevjLhGEEIQtLW5LTCWiA6KHU0HtyJ7ecC
+        V1wrRwyh9cT0r7/PZfj00SOfHIzMBcsGEGaHnsbqTay0GappPNzuqJePmLj48er7U5iGYJ7vnB2S
+        qhKiyF4WGNekZp7dgUfNyO0gWPGMHb/KU/CF+rEgDW86wYo/eFQrHiHqNq5OVW/zDbicVhglJ0yZ
+        +cuf1e1mFsDta4h58SmCkYfaoF4olthvP/0wgKxCp/ANfh9HR/BirQ/QtaaFu2JzCZj3Wg1w13ud
+        kOYdovnulC5aGtGbOc/LKeOZdOrUtVnZ9BoBrYbjYSuhiVIgDhZVP9fWpMLv/oFRZPQZdazehV++
+        47WtHPvZ2ggFTZNl0dlc59WUVWiN9jdvxsoYZMHsEbeFDb8tyNGUimpqvr0LkfJesqMpadUsxFvb
+        HrRP/Mv3qqIfOst//QY3Y4Ay+jsPMJq8oFMupxV3FlEKNN2H7DAMaTalEWk2973uUdFuT4L73UYH
+        f7XYUlh4KmK3YDGsvEuT/M2PitsON5EjpyEW7LUX43K5mNX7xzZY0vZexWOlP8IZGS7uVs0CiYvW
+        W9A88Ui8MToGU62NNuRLd8awqvVgGXKNwlk+MrbTHcsb6HuW/rO/YvaQxbzd3M8o0ElOdsp4EsOX
+        nzqETctmu1xWqzlmVgnpseyoEMe5Gg9WcYZHLFFcT46D5tG+JH/zH7dxX1Vj/TJaEBnS2KmQnmgO
+        Bq7C+/blVN7srz2PR6uDXIoipvnbCYljc8iRpnFgh/Nuj2T5GiXw67f45X8IYkkoz8Cs+0hOapAK
+        kWwqDTjxGFV0Kck6vZUVeO1/+1t0kA1ZiSSUS2FEiBNSb3q7Owovxl3i5W8nozeYZRifO5u466Mf
+        CHXecLQo4MSO2zz0RtqoKvhauMKzw5hgTilz9W8+WI4gFfemSQfr0xuUbz62J8O4kqHwIwVPnNmG
+        WL9PObo8C4/hz+trMP/7tWC8rmrKB9nz5rB8+ujqDhIWp4Vm1GERJ7D2rhWd5FRG1OLPs9qopUu/
+        WaP18gsf2g3ajz3bVftbNW0DasLlk1TM2cMccIhVCTbkHbAjWFpPJyIUEI39Yq5v42DKvjaFGmHM
+        dmyt9BN57igMYhzYvtFrMYe9UGCeYWR7zCo0HVf2AO9uHPBD0RGi/wMAAP//TJpPz4LI0sX38ykm
+        szUTFYQu7g4Bkf+toojJmzeiPAiICNjddCf3u9/gM7m5S1wgi6o6v3OqHrttCa84zyn210c08lsb
+        fN9H5Ouuq4R3p4B8BedRP38A+iytdwSy0T6onSobJLOXRpCW3oaoDs1eCB0agNHMCuw6uO/bWXG9
+        IedGcxzc3yef16VZI0GTDfbrBcnGuisiOKefD53mcd/jlV+gu2o3GK9wlXHm1xbiV/0y1fMRddHh
+        foR9cnxRY9Z2SFDnuFNxa7+wG65yny0vjQP3+XNBjYXFEa9tZQXlWjU/sb7X+mGqP5Tz8Y1tv5Ay
+        xt6bDtb+cku9Rpb9X/19uBqQlaUWiCC2YN9+xjh8fkyedDOmzuDHJ8vz/iFEsPNqJO9Px2hEceG3
+        KxsBWt7rDd0y7RKT88XtUHUjGo62g+ePg+kSmPwqkR5ZJdj4uV9htncpNiR7QGzkXQSHa3MmUAHx
+        abBgCy32MyOa1e1dEOWQpmiQrGW0MtbLf+od+3eNbrIw7MVpX1ra9L3T9+gmkTKiI+7M7kSl81c8
+        ts62QeWYPaiJz3HV3d9mDXqm3/DW5Tpa9rNRhefRKWl+P9SxyG4/EZqVuI/qMrUFTfP9EbQVzujk
+        rwWX34cEiqy8Yt+63E1GO4NAHHKfvD6HoCLLc3KAa8J8arFKrvr75r4Dn2gaXfPRMId8sTK+8ykq
+        pv4ZDrdtC5GnVtR4GEwIYgUlqOs7ok67uWQTfy2gvYe3aHYbDv7zohsEpG1zouvM/SDhtm6NIDjW
+        eC0ba7PP43UDV/Nsk9G+bvxR8KcN3V160lBqI3+apx4K7VbQ49xEGZv0DF28zsSu4jQV7+vCgSqu
+        LpO/XcfSfKu3mh2cGmqdnq4QP+d9Ag/NZ9Hs9XB9EdJBR9m2lmhIbOZ/7kOWwnWlmmThBNeeVYVP
+        QH6HPd2e5n7Fbi+TQJ9f5uSZqouKOk7hKB81eZKcJ0XM9z9WA+YtmuNAxOY//Lo8mOnX76ARKftU
+        bZvLGq8ZdXzm/iwA3ls8UKtMG0GoJhNI29LHgcmRIFe05PDuupHqC5agjhnbEsxbMMdBibcZ2Qzb
+        ElXUtolGRSL4LF1yoCP3yGryU8PQMP3L83Sj48J/B85ShdvcuNKQDEY26mGx08Ko8khTFLNMbH9K
+        W1trlBB1o8985rfHHH79+MLigsg/SwYgJYtIyUH134+0duCW2Fvi+O6m79LUaoCrS4t621ie/Jui
+        wiaQnKhlLznmu8LtoImckZq5k1TsvF8A2OSeU2cS7lGfzRYgFeWbevHy5HOlPe3AL7sjxbeE+Z9q
+        XUbotd6eiLRyeC/2KAnQg3KPIJ2wjN2GXQGCpQZ2eUxj0r4bHRg/11Sn29oXab5PYONsJDLfpEbM
+        9mthQCdxhYazWhFs7u5KcFu5idCZHXwenTsHVvIANHzW3H/HTe1As3LXNFSCJhs3l0MOqY8ekXya
+        97344b2BDHW7pf7mue4Xi/k+h/d6yAniZC7EzSttMIx8TYPGFz632fmA7OS1jZTYMvppHs/URi08
+        +lMeT4K/4oejTfVNA7R8ZLx6pSnkXLyjV8nbfuIzR9vqzzNuw63fU932a3D7gOJk4qHP04IVfHne
+        PnQ6Ek/jqaOpv6Px+FwKaquCwTp7SVE/8TuZaYMOV6lQySJivBev48PWXEUpqZHnaS/Hrlcj1Xv/
+        UMvfPBHZLl4GtHZ3wNvwHlYfxaA2FBd/j03ZyWOqAwGEZ++RzI7MzkiiFA60imRjy+EDEiv9HCBi
+        BBpeD7lrMptTB4YYNGzVySAEktflNz+ggWUif5BmtxRWVKrx+vhcovfeUGcArpZRA/S8YlOegF51
+        cY1WF7WtxuES1YAuDov441z7HTr1FhzD+B0p9n7TcxK8HVA1OSaKVJOY7c+yCtTOP9hyArUf9vdg
+        AJpp6Ndvi9mPV8IyKF3qDEkas4NtMPQTmv88j7I5eLA72DL1n+6j+uoPujPFIGq3XlfLEKU5TPMo
+        Uo+DXX22mtmh8flIqfGuI7T42JcC7cyrRTeyXaCJhzhaF0d38tPt5F9PO2XibxoUpV7Je72ykElb
+        izrxZh/z03J3ReeF6ZHl561lIuv1WsOPXYD9xOxjNkuWKopvt1mk+bMzokq8O4IYACJ20EZBrbDR
+        0ZQ/0bXX1+brvPsYSFpddBpGshnTPUoi+OjH5Je/xq9fL7owpJvt85KJic/Q6m24Eal2ns9XkdOB
+        hXhAkPzc+/wiN/qv/q1f0Ak+6RlatGsHu+YsyNgMDR4yrseU+sXKqMbdMqqR8xmvXx4VfNJHkMts
+        R5yqQj7N7EMCFXNMjPfS4HP7FNZoypupVwVeNv6cLjlsOkyo06U8bgVyCaoZ/errdspnHhEosX6h
+        6eRvl0GNa5XSi07NfTcglpxdrlCWa1M+8fFZ9UxLdd7cM7r9HIIeTfyEdKePo+XcCHrWhPsCTfOL
+        ANnOBGuqPEVPcjUiJWuKSvBlp4O0rU/ULyUnY4wcbuj3ebnq4uHa6lw7x8EP3RBMqwFE0KLlsFtN
+        el8g5mTPAJzCqaPlY3wKoUR+Ce7VE9HKdzfVotTLA6R2GhMZ3mvRRbC7QtjynmL3/cjEtWESKJ3K
+        8JbMRcw7vinRLbG21Co2H8FXkd7Cyl7tcaY7ucmu5rVE6jCe8aai/be/Cui8S0GD082LySKOSnQi
+        non1+TNES9DeDgi3ksmda+uYvZfXG3oOukIjM/N9vnazq1o9VyWOWgUQjU2NwyIUr0ib+DZfbh4e
+        fOeN3Xdtzy+PtwNffTcinYjucJEZHJXeoHjKw8krfntqsrXOhHW7gyD2XO80V0HlNP9xxs+XdQcz
+        d3+mRniFiqvSuoGZ2L+wf2YH85P7sPq+n0Y3ey6o264b1NimG6mB51SyYhFQMzt+U9feP/th6k8Q
+        16fAruzpPeercYEW6BbS33x1yl/Q9XM60e1tUSIxbNwaHmyxxXc5KmL+fNgFoC4ayHi5bc2xTdgM
+        +jyb08hYpoJ2Z8S+z9Fnt3zHPCsGC5xzsPvdh8iTP/3Ns2y/SGK5kDgHXcwYWT2kRczVpHDA9a4W
+        DVnXZtKgPg3o18Y1WnCJVWN6299Q1mYPPPVXzz6PPvjyAEHm2o2nvPmGJHkriCR5Qz9+7knyzSPw
+        OgLT52caFeh+vwNd79S3P07+U+OYr6jhuveKHUVaAJi+TsPYMWL2PiKAu0zv1F43tWByuWkB5HZN
+        VLn5QW313JVwxC3Hm8ft0IsQhyUq9Uaa8mdAbHReHtD8bEWL5v1Eo22kBYoqSca25AX9N7/XCq07
+        RAqPaSZ022xgDKf6TUw/e++qSw6j9Dx+56lgQ7MyoD2TiDBlvRRs2r/Ay29sjNNrnYnsMRhIZIpO
+        VnJR9rwrdld4eqBRw79Jlbhv7gc0f7EWW3a06MfX4RHA9XM+RcO0j5nypB2wR9xi3EkCPVdbtIJH
+        TiLqT/uK5vXMD7C5ryxqxu2hotr8YXx5kU55Ui+KTxKpyu69o3ax3PettVJ0CD7kh6B9cPXFO671
+        Xz+bjS8/5p+qsjSNk5Dqyqv1x5/TPteupC2xXTlexXdXkNBsGG5EJnORMTVlhvaxxpagTxJki2xb
+        /vI91ttohRiLdQ4YOzG2t7XXj+Y2T9F6FRT03JFjzKfvV71TNMe2mvXVsMxVUHNHXL76GN/qd7tD
+        vlr2EU+Lg/jyEwo3pwabN1b53Eq8FqY8gFrylvZ8ttjeIDj4/NcfCyd/GnBz73ca6Gk08XTQwLmc
+        R9Hy0OO+u96OCTyd5yJKEzbzifuABUx5XnT1FTcmQnwMIIADiuOVbY6qLUkgqcylbg6qyT1PVQGa
+        ZkNdxbEraXu5J2i29yk2DvsPIiKSOJwCw6ebRX7sx07tPJj8G7Zu14fP3mzTQvbzExI07ScWCc9y
+        ZK7nP5ES5busPdUvD8n+YvObl3Kv36eamdcOdd3X3BcXTeXwuh4UwpaJa47vMazhzR8uTg5dIcZS
+        O1yRyYY1tmVZxAPOXQbmLJGxoZ598c0zkZR2exwWs7n4rbdd5QmqJ8q9J88mS0BW96/Jv3YmSdOg
+        QYHFgkhJrjeTNrtLglQ7CKkXyjgWrpkd1Sn/n3gsEPLS2B/hy2uqTn/8blsqKvhsrVK9eOnZ56AR
+        GxaX44lm5U4yJ95xIL5ulhRrq5OgR+7UEFvNC7teafWL14s4Xz7+8jUiUz1+8xk88Ur2WaKgQaVe
+        Szi7HXbxB1Kuop0X/ETKS/gxKY/nA1B207AXyjT+PJ9Zqr4P/Bopl3jbc/cBklLj1Yjdxra++44D
+        OCsd4Z9J7zg6VZamZp+MLJ1bh75+Gy2SeUBWY/iuRnSsHNCV++zLqxl7Lw83yB/0gwPr/YnPp31n
+        QeyaCvXR7o6EDmSGmtd2M/XnWLFXcMsR3gDF20wb4+8+DkXVQsYXrjwqlv68dyhY1nL0ySxiimT0
+        S+gC9o6ENkh93x8IQD//Qb/7T7aJQwKXfRhFiWgW8VDEx/yXJ7/8ScZFaUNraEAWJkIxL5aqBFPe
+        TQ2z8BBXh6eBViEZJn9XZtyU3h789b0K+Pcff/75f98Lg6a958/pMOCTj5+//3sq8Pf1fv17sZD+
+        ptLvJQIZrkX+17/+OUL46923zfvz/5+2zl/DX//6c/V7bfDXp/1cn//z8x/Tf/37j/8AAAD//wMA
+        TTrY2+EgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4b93e5e0160-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:15 GMT
+      Function-Execution-Id:
+      - yvvlxf18lrrw
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '253'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 42e4c032166aa68717aa47d33fce4daf
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 5a8fe0a9400421c82190dc74100ae5fd
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Grocery list:
+      - Pancake mix\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '268'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOS0vDQBRG9/6K8K0nJTWmj9npoigFQcFHESnTyW06bTJ3mLmFash/l4LW7YFz
+        OD1cDQ27M2K70ObT5dy/rBarfbk42KfXt+3t7Pnx4X2/nN6t7qHAmz1Z+TVGlrvQkjj2ULCRjFAN
+        PZ7MqqKcVdOJQsc1tdBoguTlqMrlGDecF2UxhsIxmYage4TIXZC18IF8gr65VvhPX/BcQVhMewHV
+        eFCwO3aWEvRHj47SXzJyS9AwKbkkxst5kL2QP8+brIlsKX5lrUuSOaHOfTvfZMF4aw6Ude40wqCw
+        dd6l3TqSSeyhkYQDFJyv6QRdDJ/D1Q8AAAD//wMAfbMoYEIBAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4bd1bf3635c-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:17 GMT
+      Function-Execution-Id:
+      - yvvl315jleb0
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '1386'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 85053cfc2933d3f356880e73b7fd2d45
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89462'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 358ms
+      X-Request-Id:
+      - 5239e4222b7f6d5c65187a9e6e046965
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Grocery list: - Pancake mix"], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '106'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6W8+6vLbv/fwUb95b9owISMu8Q84CtgiouLOzA4oKKOcW6Mr67jv4n1l7rZsn
+        kTZ9mnaM8TuM/sc//vrr7yYr8/v497/++vtTDOPf/2v99kjH9O9//fW///HXX3/99R+/v/9jZv7N
+        8sejqF+/6b/Bon7k89//+ov/ry//f9K//vp7Mxwj7BeBFvXvXODhNbdqAtXQz+Zp0gwoGEQiSrfc
+        +oWAhwxiA6YUBWVdLtv75Cheafj0dBeMcoH5O5WnxuowMgGIpnMAfJC9aIDE8LJky+N5lmEd2AbZ
+        sISyoWDPCxg9aaLeAY+MbOytCxOuANRE5JlNTaI3kHqvEif28vHYq5AQzI59iZTSjvvB8e4auAAN
+        EFrwis44LZxgT8Sc+sqt0iv9iiT4kMwHVtvc0xtXeltQ/Bx8bC/JHgxizcs76UpHam82x2x06TGG
+        V0kiGJcy84YBdzzoqu2O2n3/0sn9tJtg5W51wrNxyoYvvGvgqt1VfFw+czS/X4GgyEu3IFmv1YhV
+        u5MGd617pfZhdL3Zsm0NnrzrHj39+6Wc1v0B50RuWFUWKRvfdNfAySwOaPleNvo4ON4CW7lQEN+q
+        hM1xumugHuCG7LQxALxb65Uik6XCuhkm/dilQgchoSM+OHectahpEXyeXYomtzMiIXHnCeocAER+
+        FLdsWpY0gcM516h9eu3Ztg7fIfRP0Zli6eDpNOU8Ce73pkr9Z3YE83H3TKHucAkRw9z0RmEGF0iO
+        3YQi7bWPmvU+YXe+Gr/9lOt5LTBuVIs6QSQDcn+HFWw5+UzxzkZZ99pNlvJm3B4tm1LWZ/4zVLB5
+        cAKpPwOMOpi/E/gxhJb6ybvySPm2XbCIx5DMY2iU22bvTVByfAlt548eDYUBZbnm2BWrqYqy5X1R
+        DGAGly9p6PUL2DyGAzhdmgjf3c0RTLQ9E7j9lDdqe21Qska9GfBRkYxAH/AlVZZZhnhX70lXPdVy
+        hqbrQNbOjNTJUS9nUoJYRtC/YRMJi04eRCBgX7kDdjR+zyp5XwtwYUKAff4lRDM+2xpAm0+G3Udx
+        i6an71xgEMsR2lKy6PRiVRPwuGODDfGj9NPVG+7w8brq2OiNRl/W/AAAdleq7fONN4gWV4EntBqK
+        3krH6IxOFvz00RX7B72OSPFRC8XiexttB77JhteVTvLevCfUrW9d1NGmV2FYqYCAtJ09irdhtyFg
+        u6OumcVRTzXtosDIttBiPzS2FZikyoLMB9j87Kd+KNj1ArupuVCblmO0PNR7AEhVdVhzoqhcWpPl
+        0Oeve6xl8+QtvGK78jk174RoOvHYOdECeEqLFwFMGPShY8yHSXnssHfUPiUbRMmHbzBkiJ/Yt1xi
+        fbeAS+BvcWhk34x6+cyD78XO8eG57PQl6O8IWjlKsC4OpJzm7XCHke6n9JylBpje1lxBnZ1itDkW
+        fs8s56QBdcsI9qxzySal73iIIyeiUXWp2FiH7wBCZecjeTuf9MW7SAYEe/6E/XMF2UCyuZL756VF
+        RNORPg8CQXKaVUdsedurx78kYskacU403kdpNibvuYP5hc1EOci3cl7zTTlL80T4WxF6SygWHASP
+        XMLqTfN04fPYGlDouxkfZrv2mtP1GsN7hlSq5/U3mvlPVcFwCF50T4IakMvzHSvhweeJ/DnPHj32
+        zheKYzqjJbD6bNC6twGD4VDgg/tySnp22hzuG21HdkV97JcrJCG8cMDB2i8fU6Kmym2abOqC8Vou
+        Mz9P0J2uAvZvzzqio34l8IpuCtp8ZiPij2/IwzVeqFbkJzY/y0IGrx2XUXuz77w2WEAgv5OOUm1S
+        G28wjFgDW8g9SM8Pd7A83e8FTKbKYRRnMZvVmPuC6+zEhEqHXl9aW3IhlNUN/d0v+YwPGerJ44gm
+        fYvBzBquAc+4rdC8Y7KeZNUBQgtKA9b0IskW+8gShaUhR+2X0APWcvEF1kZ+R6LXBj3Dn50AHBNA
+        shlyS2++nVDA4fV5UmzsqmgOyvQOleoM0Fa8iR7Jc/UFH8fljfX8yUqSgECGLSedqR2HN29oRDOE
+        Vhp7+OrUvD4TY0egJzwQ3Wv9V2/h18lBTcMC/3t9I+BhaF5q6p94LVqorBbKO46u5NMLFZvWeIOt
+        6mv4kh4fgDHb7OB7j3sEj7srG4xPeAEHfaZ4fwzO3sL2aqWc28VCvXucPVbV4AU2h0ONvWR0++XZ
+        Vx3UlN7Cvrs5sqX2XB9qNkookn2tnJ/hMYW2U8aEDMWNjdr0dYD95BJq1kCOpl10jOXoG1pE8MnH
+        mwwrGJTcDiCNTWSwpRXCL1REacFufXMjlpLeAubmZdCwjayM5XG1wK4Sd0TwtqJefJ7zAq98eSHF
+        Pn96FXjGBnzHS4HgPqDl4Nx3L3j0FhOJhWx6IveOE+ju2wLj87mKZl9JFllFIk/3sdn2TN1qPvjh
+        3ZZMiC1tpRhQp/KJHovDHLFo2AlgCVb8LJN3xLhp64M62pyw89y5+vLaSQZ8bWsdH0+fvF/0JJCU
+        lc/g/TGp2ZKARILO+fslfKN55VTtC0E5CuYeO8fbBBYeVQR+H1sJ743aZ+39FvCQaaKMtVealMyu
+        wwaU4ILQpI8PjyT9ZEHEOJ7i+PrWab87fmF7hXeqw8cBsPEyy9AZtltqzfmStRehRZDt8gchsq/1
+        UyMeA1DMlxYJ1sbqF6l2EbDm0CRLjwcwa6fhBc17nmB8LIZ+2Xy5CT4blBHZdy76tGmSCboHYJMq
+        YlE5v0cIYV/QASm++GKTNbcWjN4yoQd80stpuhQ8KIPCwbbFXh4VqQ5h9oiPRLklQrZkvJkDrntE
+        5BpewmjKFSiA2Q4PZMe8V0RuyUMGZ4uk63nabBzOVAJ1n56JmOGXPiO7k0DPFQ41e8EA8+H99uHd
+        bg/Y682Tt2zvkgvvHdmSwry1JaNTNSmP06HCrtQDjxZZNcGXcn2gxb36jH0uuQaNrR6TS1gkbCgM
+        XoZCf/hiM73vy/lSqynszgKmaJvZJb3GEoJhkkQ0XujosS2fDvDJrhKZdyzVmexwEnjeM45Iyylg
+        rEBqo2z22RH7jlnpi365+9ATnggjNAgZVY3egrWcbcjukC5l49znAkIuvVKzNg9grudCAkiK/ZWf
+        jGw+vR+L/KvH+K599XFfuhoMD4hHd6Gi5dQxgGAS+yr12kNXspTTZehoL5mq31Yo50H4+nBjnlJq
+        jd+Pt0if4wukhfhAwjWzyjkJEx6Kn+5KrWtm9SL3fA7yih8Uad4LjL6/68CKH0QRHlw/x12aw+3O
+        COi+6KRsmmxX/eUj9aPJAWL0OGnwoz5OaNGqrT6Jyd2AX43ckULGypvuxTGUpPLlYm/lG8OgahoM
+        Yila40f1hCUCOTSUcIcK0Ptsm2iSBmsZuGSbpQZjpfxN4bzjO4wvUV1OjykYwL5yBuxwW738mGmL
+        4EieJ8Qnd+gNWlOl4A/e2lwIpqPKFWDlL/TU3ARAio/zgra8PMm+erc9Hc17+ic+28XsItY80wFy
+        XsQjMd9fo2UP2wCMXW1gv0RmubiibQFuu3yoSmLQT+nnGct9hESKTu+OTaQPE2jMnk218n7W56UD
+        sax2zYkGwU0D8z56o1/9Juap/5Zzm08avE79gUzregxfbprMpE1IrcujjBi2JgRVokdUTZ23R5Pi
+        Hstk4DHF0l6KRjUWvhDOLKWH0YclkWoNwdGTJ3qsVK3kGX4mEMovF13W+6ZbHVTg9J4nIge62vMR
+        s2QI4MFH2/ihsHHaFJISfSaAr147lcTJni/g2YtMpK31ycgPrw9lfiMf3Tt605lCAapFMlBV31I2
+        FQYvAc32E2y1fVoO/f6aguRaa0hsa4sRxcMIitZdIrGcLt5UFm8HiO7ZRJcPUD3Gkt75My7YygEs
+        +CEZ0JanJ9ba6Bux8079wvv3+sC/8yfm4k2Q41QXI9zt+uH45gXYSKeF7v1wBu2SpQWkesiR88rX
+        Z/h17lDUzBc+fN5i32rT14Uf2lGsqizKJmcI49/5YU95XMH0Pe6+f/iN+maWJ2qz5EIzRgzbb556
+        DQaUwNlzLjjGwMp+elh5gvpBxLU+st4tHWXGWonEONzpy3yWHDhmBkad/Rz7uW81A2rhdUuKNV76
+        3f1kQBhVJ3xf8Z3Ep7MMdwcorXzeib48LTWAIzeiHlHyiNXLsQKRy/FoidTzqlfnaffT5+a49OXi
+        h9wAaDgzfFQ9kI3AiRE0zuKW6tdlZqxRTxZMnkKND7LwiZZxnCdIhrOBbZrJPVWiKYTFFgnYPiXY
+        Iweg3qGDvDcpAsuLtnWhWT+9RmQwXvvBld4GkLj+i/ef58BmEj54+EgAh5RH9GLk2dYcdFvji++O
+        aXiTfrVkqAyfFwKBvDCSftvLDz/RnC+9R9muzSFft1+KbnHRT5npXKCo2S/q2Ivp8Y+c+bDs+4q6
+        xjnP2L4cCAya6IyGcwXB/BAeE6hFVVnx0AfEM8MvXPkS1c1QKmf4VXNwckWBtNz3CWZbCBb43nwb
+        tK2BnI2fq6TC9kkEsskhBkLSSxZYwLcj7HDU9RE4dwRTOXhj1BGTLUJ3D8AVZQoSNenck5v4LKA7
+        nQW09aDjbX/rrfiFQFbzWb0936xffSUcrS4RSc86D4YKin/0F3+F3hesfgze220bsTD/JhBmcU/R
+        w6eMvEWQAjNTjn/mj7Wu5lDyTZNsxXfLWB15EHR8UWIzSZpsNiCU/5yn8bUqMI0Pi4NtJrRUa45B
+        trx2k6GseuOXvz2L5TMHV/2FllCbGY1vzw4ybStjc/6U0byZwgLyKh3JvAUDmK2DPiir3qbHa1Vk
+        rU6DCd6LR0DW+ytXfuJDQeB0BI6a2c+7DFuy8xA8ajjcM5p2VcHDTcwZ2ANtyWZZlrQ//FXb8gCw
+        o2NW8P4VGoqX8MZolkkIruNU3zbniImBG8urXkfyvrR/+eeCx0YUEdcPrTcZ590L2pHwpfhL7XIp
+        39gFz31YrH7HyMZB6mS4v9MagVn+lATDmUAUszPhLb/RKfeOU5hEw5aaB4mAYfONDehPOU+P4OJn
+        08ZO73J/tQ0i78taX/WqAEyWhmS3Gc5gxmesgvx7z/CqlwBpRMrJtxFj0m2awpvjHQvkle9h751/
+        +skoH90ffm6/BI+N6DsUMjhCncZsDLJJ3lMBxI5Q0+MjUsE2u3cySPzThL9Pq+9p3G0deOr2Zxyv
+        fsIwMzqBdHnZ+MevFj4/FuBxkGPCrfznzSdODqdk5xFu5QN0zhQftr3mEFHn+n4J/PCrdI9vS977
+        UQNC0N996Fg3G025wIE+CTgBrPGFD6ejG032SAkIgOBj5PKtPtpCMIFSFXN67GQ/Yh6+aeCuLxDv
+        zU/gLabeXoBo5RLen3V/1XdCA7lvbWEv5AZvfkjpHejl9MSYJRR0gaxoMDMzDrF7lmbLj0/kekrx
+        0dL8aDIiXoBrPpLZu+91WsokgS4Kntg8SIjNN46rwK9eTG5x6tmoXwc4NOcdPrLejoTULLWfv4i9
+        QA5Bk1rnAc7E12giCU+w6l1JXvkvjVzPikooeBBMrzjA3u7TlT/+rqz+Dv3lC/uenQZmt1zFFm4Q
+        m6ZGvShCfboh0ZvLjJ0W5wsdqQkRkGo7E7HBXvDwFTPqwq/ZL65TdfC2BxzWmGb0vOIOBUDT6t9W
+        xiWaImZJ4Dd/xS82qD7PA8fcwVVfFtnE8DWB7RP3hIEqAyMxZqLUdeFQn+zc8o8fvPIbJLux5i26
+        mBZwnmuTuoJoe+SWnCUQ0rb4g4fjc6umoJGiBUljNPbj03gHsoq2PHZi9MnYV+8d8DGuOdpa5tVb
+        FM9Gv3gkG9QU/fjOYwdejOpIT6t+JateBz8/RScg6meiKRpszvREgJbeoin6dBMU0TFE3IFEXleW
+        ugDvWCb4wH03bMqqAwc/deZiWwG8x+w6bUB1cc/YccpXxjrghvLKh6jtzXo2BwsLd56qvvDKB8uG
+        tucBoGNhEjnezR7rUx3CLz8vqFSy0RsvtZPCntMUrJZ06LvwUnUQncMXPUiL7+0MyEuQB/7jF9/Z
+        LBThC0jGpSeLeTuUE5qcEATJ9KI6Aaz8xSNYDtqBHj7va7/UnSfASvvk2AhHZT2fuwuxwt2w8XH2
+        Jcsv7R1Gbetg1A8H/be/XboUNlHiwvz5tQn41R82b5VyGnAn7E74iMh2rVerHzHINn0esaUbUGcS
+        Vy3yO5DO9PpdloyNW1CA29t+IE0eD+V0ktMY1Ndtjk1bl6OlTnsVPm8qxEg/GDr/cvXmp+fp8a1n
+        2ewU3BecSDqu/YUiW/3dL1j1OWJrfizL+/oFYb1zCO9pST9vckUF6/kRrt7NGVn5NWyXqcR+fhbB
+        qrdkeNAZpXZmH7MVb15wJ7U+kU97nc0OH1vy1qUhNS5No5OgfRZy1sAtxtKh98hh5y0/fYpdN9b0
+        uVV2HTQuZ5V6xsktxSybkPLzJ3Dbzv1w31sc9PfLix60cWK/8wHpd+xIv+LBRCXuJYPzkFOtOZfe
+        vMCAh2v9XtcvvMWv7j4gh6nEz/NxLttNvtWg5BD9x4fATy/Czct842uQeoz0ajXAX724JRKNVv8y
+        h/bd8FDYHKdojnziy/CiRBjr4MWYqLYvyOllSle+ls36gwXKPTrN+IiYHfE/Pv2+FxApDhSioQt5
+        GcZ0eWF7eE+Abz/1Al3pk6FlMJVysvZ7TiGvY7j6l6LX3/D7DvGlPKPNBmrl9jXbGhTHZKb+ubqD
+        QVUyDqz8Cx+FR17Oim7exU9/ulJ/+/Wz+Wm0ARhORkf35kOJxvmILXDwX0/qczjup6au7j8+S9VD
+        RSLWpx6E050lKO4Nx1vxQAXv/bFH1dpvmVPipPBOPhpZ3OsAZump5pDjNBeB1d8azEW4w/Q6qPTA
+        PDUbL+dOhuihydhpirCcVj8Wxo1mrf2G1PvjT63+CXYD/fXvcT5Irkjmgbr6AU4K341XodtOKvTm
+        wyUEGpbgUes4OBm/6l+wO3AS9Rqvjmi1u6nQjGiDfe1i9lveKjil5uYrdkfHAet9FT9+sf5uwCKz
+        ACpVGDg0blUE6F3eCVBsXxVVb1qvTzOrp59+IfOm8zz+5yeKN1FG/Dy3YECb1vjxRWxuH1PJ4Ld0
+        YS+EJdWUOirZTXUacOhos9aPR7/EUfhVWPiqyEyR583DmcpQacbo3/i/8g/4FgVE+Pv124uVs5Ng
+        nY09Yr7y6MkBOLm86j2qbcpUZ4N9s6AzXlW6X/t///YHrLOMVa+pezajmyGD6fWhNu+fwdy7zh0+
+        DlKMD/WD09s1noEZxF/sMMzrdLzsZHnP2jfi13rHrOuOh5KDJGoV6racH82ug4/NVsTWd1dGc5Z+
+        ESzC7kw2OI90QdhtrV3DSxM1d2cFsHHLXtB9iXsiOaWaifHt2smnOU9X/zLNlqQFKXxdJPqnXs9i
+        oGjwNRMBsRC+o3X/FgzVDf7156K5VeYOkiYX6d78TDrda98UWunFw9bQ7MFcem0gn+f9hSL+PPft
+        dmsmkldaPs7DJ/EW3QIJ9Hw3pJapv/Rh5MwAXlOUEj7cBplY1aCAN+t0ob4aDtGE718LSN+dj/1n
+        BLzxyfRBvs5ujNXEsMHMX/QJrnwPOxtmsW1IWwR7IShxtOIJy7e9JT8s1abWW1ui4ZDyAnizu4Dd
+        QQuBkI/vC/zh3conytEphAqu9RmrxdxmrGolH7RCM2GcHSSPXAKn+NMvEj5A1Sfjk15+49SlfuF1
+        DnwIP3+G4h+eT3lVwbW/gZFwc0FL5+sdyr6v47Oty9msVN4CyL7g6PF+dMGP/8HVXyHLijcLJBr6
+        9Zd++rNsGqfg4fedTqQ7i3w2GuPdgpfY1LAzezJofJZe4LR3Zor9u9BPnnUMweqX0f1+1NjiitgA
+        Uw9FHBeeHA2PKRmUbR4cyCs4BR6LhpkHwwPdsWOSHvTnnVPBtb9L9WEzenN7TF8w0zRIygtP+pWf
+        VVBPnsc/+nNe/TJ4uW7wT59ntEBOB8NKA4hK+yRi0eOmwl9/3JK8WO/sQdFgbk82PfD7kz75GkC/
+        fuzaz7p5/EbcVbDS6hwpl3zIplt91+ByUA9Y886BzramFMDU0S9ok3ox++EDiOsC0MPp2EWkBu0F
+        JsL0pv5Bt7PpOnQLPAr2Hm2Eo5FNosNC5e/fq4D//Mdff/2f3wuDb/PIP+vDgDGfx3/+11OBf6aP
+        9J88L/yTCn9eIpAhfeV//+vfjxD+bvvm247/d2yqvB7+/tdf8M9rg7/HZkw//+3zP9b/9Z//+H8A
+        AAD//wMAWK4fC+EgAAA=
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4c8d9b11121-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:18 GMT
+      Function-Execution-Id:
+      - yvvl9h8bnq2k
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '42'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 079a9786f90021c1a5f4aeb630bbfc1b
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - b1c65dedd1c013d35ddccff10d9bd9bb
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "a grocery list itemizing pancake mix.", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '114'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R62w6yyrbm/XqKmXlrr4gI1GDecRIRsEoBFTudjigiIHKsAmpnv3tH/53d3Tcm
+        YCUiNcZ3qvEf//rrr7/rpEjvw9///PX3O++Hv//H997jNtz+/uev//mvv/7666//+H3+fyvTKkkf
+        j/yT/Zb/vsw/j3T6+5+/hP++838X/fPX386uWuBl8y47tr7qghLc108KIrHRXIvvGPynklAh2g+I
+        t5vWQNnD9RiWhswcw+cSwI63DXOxUiXdbX3MZdinKtnTOzf5uEIiKkgwU2SlWifc4umGVI1PuJ4a
+        Ek7n0k6hWzodlc71Bw2ahCnyPs7ELD/vkgkVagTCypCJXhhDwvnYp2C5tonFKGu6aRPWGC5l9aBz
+        XH0KLqrLGpFyvrItvy47tnxFAEWyr4hveBOioFxsuOjrLRaP3gv1xtKXFHEQYnaHjc27IJVr2K3N
+        LV5t0QfxsIwjhd37FE9NsSl4tUQAN0EvsGpfUfhpPY1C2L1T4ha3VTGe49aG88Xf4dWnLlFT7Rsb
+        bZ1dykxrPnez99YVuJkqxX2QN5y3q5MPx2WhkZ3fntHUnE4lNPwj4iXfNAVr9lsMVCcpVhLGzdkQ
+        xQyczWum4qqnydwwzVeHz8Ij+nPYdKy8vBewkZMn8ZV44Q29FPlK0UQhIQcfwvHhcAAtSEe6GLI5
+        mdLno4fbOL6Z7663odhtdzl0763H3LyqvPo03jXwgtxhdn7eJdPJygz1iWOf2a3uId49ugAYutX4
+        /UKQ9Denb8HtHIcElvLhrTMtUuirrGPked2hWSbogBaLvcw2g+N6bX29z7B+TyssG4LIZ2XOSzUP
+        Dy7ZNhvPK/EjEGAf1zZLj87Dm5q9FKNbYCXM2hq2KfptXUK3HXuieY5lshNcK5hSfiDaRT2gMbvG
+        BmpkY8Ar62ggYa1pMeDDpyAbfXQ7vktNCi7XR7bllWnOg644IPe9TszzYjKp5t8oyDvoGOkVPxx1
+        ufLhgkuHCt/fn86yLIG+KPZ4+bH6kFqBRmFbrWqy4Y1h0kXtiYA/tw0xctsvZr/NSvSOO0awFh7C
+        eb28uFCoAMT97i9bOysLqTauiT70gGZO7jVci9uRbHtLMnvTKmqkXqoQGwe08aZDY2eQrJ4m25R3
+        oegNcqWoe+lL4hcXsavdSy+CsXgbxMuaOWzS54lCo4Umzav7Nhyn/GpBIaORLq2XjAatM8RlU94s
+        th9VL+RJX6Tqfn0+EK192uH61FuisnraV5wtvMrjz3tlwLGfWrY5KU+T52S6Q3S0PcwymZnsSswc
+        OjvRv/V3T8bt5ZQjcembxD6fem+aeOTAr552uSeb/VGZR3g2pkv23KmLcfkuHfiuZ8R6XTnnounC
+        Tb7fSBrzZTcsbTDQt1+ILsZBOD+0oYKiOYdEmxdSOIIxZGDV455Fbf7sOEnzCOg7ehJvXvlojG9L
+        CS1cZBPzrr2KiS+uGZQk+rAjM9tiGLL2ABt3OBFPdKOCRqfCgrA+Z1idphufRSOzUVQvZypJmRFO
+        u06aUbsyz1Q8Lo/JKj5yDP1DWLFUj4qkinMxAOMt7yli2cacZE+wVfuRZfht2++EdYNkQJ8/nwRv
+        HkoxifUqhvpYycSv+kVIc085gKZvNkxf3vJiLA7rUd5s7xe2N62w6AeZ96quejmdrxYk7PaqbFh2
+        2kijstyg+WUnFcqWm5D2o7UrfngOaJ02zNmglcdOvS/CPcZXsnv6vTl9MrNV6UKL2H6dFiFn2gvA
+        E54HgivPLSYQn5Icu9VE1+km4zP5MA1eaAts2yr7gme51aPFtnXYXr6rSf9AkoG++8s2LoGi762X
+        iL74Svn6+eh43EcuQpIY4aEEak6zNAuKHkoHpjfFu5j0MJYgfhNGha246lp1lhWIX4uJwvZ09/rB
+        XtfwEXcDVX2Fd5T37wNstXWE4Wrm3mSImq9ezs+RbfB7ncwrq6rgCAeDTvvlEzUetStQ1fLD/KeO
+        UJ8kW6z81nu+OhezUyolvMZM+OL9qeMJSD46KGJO9vk0Fo28kFxIu1ZkZL8nIasPsY3alX7+1ucc
+        znfqLkDBzY5pfkC7QQ9jBULj7NPV+/EpOI0TRVll9w1L5RcpZqc9BipXUEF57KCCD4Hqox++Xrb7
+        Q8cjcVagsEuVmOHS8mh0sGL069dtusnQ5FFcol3T13/4YD6rsq2YNwPTs9H0CV+jyYVTo3+I1y2u
+        fNyx8wjrPFuzzfiYeN/uJgzbc+Dhxsv6cD6+sxxa7prMuwibcLV+HTCc905N1QXvvCm74Qjelm6z
+        05sbIUfSuoLgWr3IVuulgkrraQFJuY2ZKx2eqLutrzmMN3um0sWGoj1kOxHm2yTj1VPNkyE+Il85
+        kTkiG7Em3ifUGw26q3vBQnWtkxmfrDsc3HEgxpEJxQR236OYn+/shy9jczzHSPjQG5Zui7zgmQUW
+        6OouZ/pNU00umMRGl5WnECvaD3zEbUrloEIa2a6ZElJqbQEknejEustFMlOLADhn9CD20Xvxmb8d
+        C0wPvXABXhgOtjO76ku7L4mZL3HS2582gPBGOHE+nIWdIjYjTKXvkCSEZ9gvV6OEpP3CIF4lkI5e
+        6/sCBUVrMHxpVibTVxcDHt7LZ06z6HmdXQ8GNLeo+NVP8Q4+jgFFbuwo6Jc8GY+P3PnxAZbSaekN
+        N78TlfIaO7/67UayySRw3oZL/NFquj/9ECttxTRJq3l/zrYHZHSRhdXWjsPpepdKEK7vgfh7MQpn
+        17hVUEfrNdPTPihmDTYKYpbREIz6nn/YY67gh0e7U//xePQiKUol9US0W7ozuQJaCsyoF1Stjyc0
+        nFI2I4Y/E5ZKweiGt2PE8AwNkfaXPjLnePNuFWeOGubMj5SzYmPGP/1CtGhRegyL9wBobGhYGkKh
+        4PUhttTV07qS+BzsPRqZWob2o2HjhRaO4fBi8gxHH+8xiuqVOZFKoih/+irZvLmR9Ei1ZzRlLjAs
+        ZVD0gXbNIXLDmtnI58kEdtnDkrxLpt3gwal+iS2UzP6G2cflMeRoZ8WQcTcj1iIxuPAMp0h17LNG
+        tGcdJmOapDlwLaio9K5nr+UkaqFyWEmR81nzNrWtAHX35ET2jGd8SvTVqLiGioifUav49gNGD2tv
+        EHvMS/PLXwp4H3fCgtF3Ibc23IVClkdmRfs9XwnmeIDuZS6pNDUkmcUeSsRjSPDReGl8jG9rCaLB
+        WFCEogXibTAoyhcPqJpVYdI/M9VXNvL1+Wc/x9tbDYCKvctwKQCajOw+/vqPuf2sIUE2zhjGcbP9
+        XXPxnmSxuqf1Da/M994b23sy/sEvL3a1pAvLwxl+ekL0Vx+PDxv5DPDJUoKJa5ri7ubnkEzX9Vdf
+        LE0KB7cC9ro4WBLcTzGqjuUDe6p3vJJ3n6SfBd7CexNPZI+PejiYXeDC931SMVsmHR2fN1sm5Xhl
+        10ZERS8qTQ0cSwrt9YuR8PQT2fDQwCJ25FI+YEuPYVFFwR/9Nu427uGPftwWpPP67aAtQAxniVli
+        AWhkx5WB5LpdsR0RP+b4OK0F6E1+YrqzWhWj125jdFhss68/eXZ0vXy6KAiCC30m67SYfvzTWssX
+        Pm+52E2x0GYKM9oFs69tyLm8wKBMrvNhN8vkxcCc8Qw//QF7w+LTuRkcRboqIjPUreANZSCl8Inw
+        mxl6DMUknVsHbCp5bFuyMRnkxqI/vh/au6x2I9ZcDF6aIjp31VR8+cFRv3xAQu2e8G5bhBa8xlz4
+        vu9twhXzTdGx5y1F0ikwmXYaK3VK8oARVKJivGbnSjlGiklcctDN+pyRQPk+DzEl0Svmn/6/Xyvr
+        jx8ZhceOIpTrM14FaPboB19ikLrDi45deELz2VU1mNWCEL8YppCbWpSifVQpxOrkfTKOiqkBPmu3
+        H56jvNvqmdKPlc/MDW86qi7VGbbpQqOrKNBM8X3d31E3cA2P96Yq2GcTULB9Z0W2yxug/ve8+Ufh
+        ZAe0Q1PyxDf4zBJjeqUryXwwJgzVJq3Iz682p4tbgSO3nJBDfvF4NY+2aqLlmZlVdPYmaxwFdej2
+        O9xF9cnku25bola575kXOgzNIulAee2x9sM7xGqlL5X0+DmT7a1YFZ+FjBWEzEtNl7ofmNPjujRQ
+        6YXJrz/N4ZOZNXgnbuP1NGnFuFyNyq8+cL893c0f3sNHwTJef/0ELdJIBKmACwvuYIRr7fGYwa78
+        M9Er/RaOaoty9NU/OL8oR8StcdvCu3a3xP/W23Au8R3RJFjgw72xC2FaNhTErWCx7S6mHgXlackX
+        mdhEk1ddONdNk0GJTgesBASbc/ARz5CZVkeCvbn02H02XDgMmYlH7XgMx70rBcDwe6Kr8i50zD5I
+        OUQ4Epj9yXjXd/7WABprGkt01UlWX7yEY45z5o0t6aaIQg6wv6vEOvarbnwlbwFOp7mh3XVpcC7h
+        cEQ/PfZH/5NzsfgvPfmWKJqjU2cr86u8YxTC86vPRw1OHnPoslf8ZHW9HBWYleCI184FmcPgLkT0
+        1Ud4eS+icIpeUo0uuHIIfq0Y6ncsnX/+A68vpdOtdvwE8OVf8uV31ITNSYS2sXJmuXpoNrvqZiH1
+        EOxweY47c3wlg4jSTZsT+7mazD/498hlH6/ZoQ67MfRztHt2W1wdPR3RRW0KaE8WB7qw030xJ5Ks
+        KXeD52QjOUIyBYKpAB/PCVU2exXNoDxt5WrRLdNUN/RG0+pqqJ6ZTT8dVb2ZXdENihDdaX10cjQE
+        x3sFxWVR41HodHMMtGOO8OFdsP1lqpLpWp5GNY7agLkvIoU1Gl0JSdJHwzIqXyG/k5sAdSybuMvC
+        dVeL23eFbKp4zNDfmvl9Pgnu71wiP/znazFIlUkSJ2LHopWs/vgB+/VmP79c7dYPFy3pkTL/lUdm
+        te0vMywP6oFoTRom3LWvo+yXrw1VA+uB/uzPKDghC9Mm7MZ6wWeZFDfKjIwtOIPFOYDVyqbEEscs
+        5O+H36Iovp3o8or7giUwYvjlVY7gfroR4hj++DvFLbtulBgqkSk0PsGPnRIO7iKJ0Bcf6Nc/Ii6q
+        6xa1RdMRTzoF3lgdt7bSj6VPNkZ5+4MXQPbxlbi1oqDG5rgF2rcN2+tkMofPGN/Q/Vpa7H649N0k
+        HAQXJa6wYUfAQTIZpu+i2d4dCPvmF5OYyJm8co5rknQLmTeSfLxDXZEcK1dl7FhcqSn64hl+Q8q8
+        7nctK1rGtr0Ve8NHvR+gum0IVj/bLpnj5GirflwdKRo6oxOEpawBi5sAL05aYdL1nARoT+BAzO2i
+        4mOJpwB9Drsrcdr5Hs7TNnNgz0OL2c7TD+f+WtpwOT9G8suX5tJuFSSMt8OfPKSP96BB12YGib56
+        fGSW7EqKd/OIvhHrgr0+3Q0yJJ6IFn5Ej164Z8CXb8mmvEdF3Xx2IqRUFpjD0yOfjekpwGHITWLW
+        z7CY+VuzgIxsT1kkHRH96iVAj6tDNimQcP31cxBQ4pJddhaLQeLfvGJx11mstn73/X8H8OPyyKIF
+        foZcrfoIffGB7NynHM765WCrw3HXMPMoVHxONgDQXugaT3o28B4rXQqFWM8EX5qTN6GznEIvBzpF
+        6GUkYsMcH+73tcH0XtonYxiA/ctPyT5PVmhG0i5A6fF9/urJCx/vYa798jh20ke34N98QaFM/jCr
+        K4KufXrtQjbeaE/XH5R1bJd6FLS9aDN3ObuoXZ+MGvLVPiA4Fw3UC74AaGXfSobv3aYYsr1xV755
+        JPMWYmvW4naoFE0WGNEcteIsfsYHJdCk/k8exb/+B33zAazQT5H01/DLt624ZPjoPMyqLW+OdCJj
+        xM5Q6OH4kU821MKZEOxHQzeOW7yAna0GzLiDkTCiH3vQ5/LGfv1Vw6qpYCiUJfnqUz6KF+WMPl7O
+        CFlVLzQfsp2AbMAtIVyWvcGvmljO/ccHt/cN9uavnldueSdhVC735lwhGNE1lOVvvUxozrgEQNLZ
+        ouzJyo4vp4bC/fXsCQZjy/ncbWbId35Dp/3L8ySHSBHkO9wwb9Lcb71Ozh8/vkvWVrgmHfV/+M7s
+        UCtDVrq5BcnCkdju7CaIX65TpaLRef7883/lBb/8ASdLhujb35UgEheT3UPHnC92SY+ct+b+/EAy
+        kErqQUuvBZ3ay8rkZ308o1cnucQl9IT4+qqLENvFm7hrexXOXTMKf/z5nmxGNOnqcFO+/YSXNT7z
+        6ZR+Rjg15gcrWLHDUbOi6OcHsdwYvrmSG6uHjcJdRrrxhcaoVc+Ix4uEmF5Iu5HrywoFRW2Q/eNj
+        h2MYBzOSoPXx7G3eJnv284ikpezSobWl5M2kLgfurihelMIdjeE7bWGzEM4sPmzZ139EI1w+q4Sq
+        9B6a8zcPUm7mkjI/PMvhcLi7LVI2akSw1XTesK/XGJoI9ViN0YFP3/MGGNfXI9PwdjKnWwMpRIO2
+        oEvpTVH/ws3ij79xLvd1OIXNSUCzV27ptLosw+HCTBG++TrbvHme8LdyOiiXnXcklrKpvfmgBimi
+        JHJJKlzeSfsKnykqyGHGK5fcuz96Ne92E4kv93Xyzft98C9+RQJ86/lsPf0KKuwkxDkHg/nVcxL8
+        6tlZpGCO1ZFY8NLSJXPQLkp4dM0PKjU+O+LSjxmu9/bLgujdCwSzjhXFV6/D4e7GxD2VKyTcs7cC
+        gvm54nEX6oVI15ahvrXRIa4YbDiVPm8fvnkILRpRD8Vvno+a8/HCjMc4oX4R7ioUPfsnud1ltfjl
+        hbDMI8R2jZh0ozscDlCVzsi81XnjsXZ1wvD1s3/OF/pW7mP0xQuGG/dS8MtVLv/4edW3LW/a95oN
+        Ua3O+JWtR290hziA9Xbb0YWY5904b5wU/fyv+vV7begOPfrmz1T++jsWvbYpjOvk+Mt7OZVuzfmX
+        N5Mfn02d6UbyN38jluMfijneDC2kqvb65YPfPN+h0DOc0faqjAWL+7uLNrUufPOLFZqblN/RTy9Y
+        HJ/Mz76QqXJaCjvyiLd6spqqQ6Del1VMfnpoUI+5BQumbcnjWDUeb/K5VhO8NZkmdLo3O9tmAd5p
+        sn/1FI6Pq0YhaHcLmtvMTUQ5cwxIninFIn8d0FjtGgkeFcTEuFr3kPqq6aD5gCdmOtGLz8bWi5Aq
+        Hh4kFLID4u+H1armJxqIVrcmYqw4Buplo4TERLqDuDvSALqQZXTRvjbJ2iq8EbZF1RLnCHPSf+sF
+        feo1ZtvIeBQ/fodwvunM0l7UpMshz8G63HJiMq3rxvC5BrA/lU6bRkTdXItDDI5xEOgKRWVHewhv
+        6Pu+MBJdoWDvgzOCedMwcaWHmQjew8vgdRRbZhFPDbkxyCLYkdARQuK+mMx5fYbD3YkJDp4uX2FL
+        v8Hc70q63OQ94gs8x3BJlA/NmpQnPFuPLqq3Rcw2Ave7STClAOxWWLINCz9h/+UvEJfYJLqnzXy+
+        DqgFCWqf3NN9H37PN1LUJqPJTt6BdP3P7xxmZyDatDvxlraOA0pMW7q2sMmHUrUWUEnTlURmpqBv
+        3lzC+YJ3TEsFk3PU8R42LjvR0YOwW3+CtIJpf30zZ/PIwvG8UijQcCEQ/x7vED+UugFudKrojNSm
+        60ssH+B1T2bi5/KL//Qx7NfRgQTnDQnH3ESKopRNSpc7aVvMzva1gPxcOERPLi4SzqF5g3JuEjz3
+        I5iDdM4d2J6eKjEm+4zmX37eJrOJFytPQExK6wyJ9/vA9uosmWxOdeUP/png8XAYFwZWp/M2oatb
+        JXQD5b6AnDp0sFi3C49lud/D1deOJHWFOpmF5VZAdbXPmUbrR5dhpUgh6fkeL09yyackMPI/eLd7
+        XXYFd4v8BjQ5LJj1Pc9hjeadwT3aNX01xbtjK12rYHycRnx0Lhnil9d5hraxc6aJWVGwjXcU4Itf
+        5PA9v2LhFPlqkWs7iprTB43TsunRO7Urspslj7PSbS0IgsOF+XJJu7HziQbXwKiwiNum46hDPRxb
+        6cKuePXNW8adDUnAhq9f88z5q69gPMYqlZZP5vWasM1gHLdbslGDRVH/6qd7b7w/eXSTR4sFDB3Z
+        YeVF4kTII6eGNZQXgpe60I1hfJshu9pLjE6NY05jEkhgZXZMdEevTP66pC368YFx3rBwtNk2BfVS
+        hsxVaq2bf+eR0hK5eAq6VdI0kqWof/+mAv7zX3/99b9+EwZV/Ujf38GAIZ2Gf//3qMC/b4/bvwVB
+        /DcT/0wi0P6WpX//819DCH83XV01w/8e6jL99H//85f6Z9rg76Eebu//5/a/vr/1n//6PwAAAP//
+        AwB/Gfvm4SAAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4cb8b3713fe-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:18 GMT
+      Function-Execution-Id:
+      - yvvlh8rh38s0
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '172'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 91f42e8a544d43c21eecdcd9d8b2f786
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 54675364ab43889d41f33f1cafe85a27
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"What is your
+      favorite color?\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '269'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOwU7CQBRF935FczdupqQEK3SWLnXjgmgTY8gwfcDIdF6d9wAj6b8bEpXtzbkn
+        54zQwcLvnPp+iOX8qUntS9DTs/jvdGrb+jE2x9flw6KdLmHA6w/y+vuYeO6HSBo4wcBnckod7PR+
+        UVezRT1vDHruKMJiO2g5m9SlHvKay2pWTWFwELcl2DOGzP2gK+U9JYG9qwyu6v+5MVBWF69cMxr4
+        HQdPAvt2Rk/yp8wcCRZOJIi6pJdATkrpEu+KzwPJRV442Ye0LTacC+GeONGtFBt35ByUCs+R8wSj
+        wSakILtVJiecYCHKAwxC6ugLthrfx5sfAAAA//8DAGuClxRMAQAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4d0f99b2264-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:20 GMT
+      Function-Execution-Id:
+      - yvvl4b8j5ntg
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '1327'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - cab4489fcb073187a73b112f5825f6cf
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '89461'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 358ms
+      X-Request-Id:
+      - 509ffc387963a73e880ed3350d567cf9
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["What is your favorite color?"], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '107'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6Ww+6vLrn/foUb95bZ0VEpQ/rDgGRkxQBFSeTCSAi4IFTW+jO/u4T/K/s2fvG
+        BEqCpX1+p6f/8Y+//vr7m1Z5Nvz9r7/+fpX98Pf/mu/dkyH5+19//e9//PXXX3/9x+/3fzyZv9P8
+        fi8/xe/x32D5uefj3//6S/ivO///oX/99fcZ6z7epWjZNRd+c2GRtyvqQqWnQj82ERBDVShmht5N
+        WA56YFJ0pbZVPTouvwUfrrvG9cB77RFfZd83RKggVH1kliZoF9CR7qmjJyhojcizojZCx9zCnvj6
+        dJONkwRuj0tND+JmCPuLuFNAMymnmr3XK55N4gLoxtGx6+WmMz6ObQnP3TGj3uUhpH0FlQfbyN0R
+        4fZqU5IfQhEVoVZS43ySQxruvj1Ir/sVO/azQN/X6xyAGBxib43vV6dXq4ChUv5gwsEu+JStCAM1
+        Zqr3OHV69fQU9S2TwnuSMR8+DrMR1Gg7LFrsnnjn8EjzTZQ2ao2PdzfUxnRzecML7As22DVJm/au
+        l+Bdz50nDuo6HGtUCnDaZwgrZpo4/O0te1Rbh7O3Jf2T8+Ai+tDsLhlVtTvveNGRN5KbkVBLuJyq
+        RihNd3t83A7eqmVauvYOuy8kxQd5TZZv+cTvxUIGMUi9r6Rt0fTaIBUV7ftOxjcqK7Z7dhHczvsV
+        maztwpmUt7RAr5O29QYqxpy9rgcTtMHR6OFotlW7iU0Fqr3tUP2c91V3fXQ5uuvwJKOxwmmrD6wH
+        xWsd7HbK1mEH7aiCn8d7HHDjFY59USWyI70xeWLNRsy2bSbt5OOAnVtQd71ALxfIPt8zNtqhrcZ4
+        SQD8RKg8yfCg4siNY0TYN6Y7Y0XT0ZUED7aSsCRTVRl8BX26AbxdrAhPZVyxi2ipULhCgq3roHaC
+        3/UxbC7qgR7r50Xj1m3no3Fc69hzViSc7vs6QdZ5nLBxDHaaWK0yE6JT5FG8ZZFG+9XmDVlRnbB1
+        Ejhi+/EB8K3eN+zWXd+N9cOrYa/eONVUtqvIcctFkNJ+8JgXfRHD+lOEVbXNsRejHPFiC720SuoO
+        3yJ/EfLddPJhhbIbNY7BUxvqISOgvw4fbERkh8QtEzJQzYtDJKWzuYAbAUAyLYcesumNRn17jWEU
+        FpTuTo9z2sIRC5vWT3RPqLEfTvVaq9F48HrsWNRwxot98SEfJ5cq1VNEfUfHDZAwcj2Z6VE3Xt9T
+        udRz6UH3ZP8OWQvxG5oj2+LDS1HDtRLta3hMloBVt3t1/N30JYqsMcBHpgvVuPFuNnzj7eQt7+Oi
+        Gjp/EKH0Tzq1GA75GLS9Cq3cY6xE65MzXadYgO6QbekxXxthfWcPE05SpOKsqD0+JsKawNHyFOp5
+        p5iz81vLgXEcYq9UA/QSQsmAMowpPmkf25kCPS4hsniAlesiTifsFBuZGIpCmrpfhTR5Ny6ELC+o
+        U3w+3QRNbaDPd7EjqF5pGnNifyPjplhQZWdcnQHHS1X61Qu3woZPpjxEoL7aqyfwzudCvUi+4J6w
+        R+1xTVKapeMCHDc540Ox1bup0soLNB85+X3fiksUjH+vn/pS01ENMhHatxV5YynUnKxRR1D5iU2y
+        dvGkkSx/TpBzWfK4FNNqYK5wAc+4y1SVWRfWnjrFaLy2FbVIv0PDuxwyeKieRuB5P6SCWFMD3Q68
+        wXomDSGJ7i7Afih8HG40zeHfoibQt4ZGnXx1CSdBBRPdU+tL7cNh5Yy7bRGBoK9E6sBVRqwfmwsY
+        L1XGh9u94hN5Jhk6QcXItjOXFV8cxQ34x4VHPUESQnZ3eQ6256X0h7/U7GkMCLkudYT4WTG6uyjI
+        fXkfrHZjmbKyH77w3iPF2/JL6kwXsgVp/15r2N2cTTRF28aDr0o6IvCJdJ1ZbUrktdujR3a3Whs3
+        3sn8Uw/2Y/NKx4hKFxCcSvOmbHx0bDyFNQoO3pXi+5hXHcmQi5Kj/sE2et4Rie76Aoq7f6I3hjli
+        maOrMG2vjB6uXVD12S0wQR7OPjXoUHDy2w/aRVt6U+bVDt9Z+QU+yhKT6lMQh3wWuwhtF/ETW535
+        qOb5LNAVThXdhfa3G6stSgBOa4cqq+LB2fkjSRB6VKO7Ibf5gA7KBC9bHMk0RXY3iPYUyHZXfKi7
+        apfOtEYVkau96ZBFNRgOY/fJhwx3JXbylZjSCV4x6FeeYmsXZ5xoeFBQkZhvnCuF000fijzk3psO
+        qzOeslEHCRnf+kF/9UnN/pPAWgmDmW+qlI7VBsCvP0e8W0srbfKnLkfOjTyxam0X2oAOJoMFNwzq
+        VYOh8a25LdG5F0NsBYMbrvr9opbuy/eG2ubWSP/wxTU4aNg7a0U4zvODz+QLWJvA44N+5j0or9DG
+        7vP+CbngBRmUkjZQSz2t0ufLKTI0Xr8VPoybtcZj+lTB3NzfdK+dj44oG0qC6vftia3cbxHRQ0eC
+        9PxQsWF/ruEkrycPvkJ2wGeWcIe8T58C3XeiiI0yHkOy2ugi9OsYz/jSOkw5DUya+RXrSw+nY6P7
+        ujzzL9U8t0zZa0QLOMeCRJUm2fPxjuQczF0yYvc7tekg3swEud8oILz7OFw4fyZJeh2oQbot4um4
+        3U05eEKzxoqxfKGpOrEczudTTI+bgDl8WH9V8FeaThWur8LpXiotvGxhJHywZd6L08qT1C79kMXj
+        /Q2pmMcK8OSYY69Du048Kdsv5IWUYw2dTG2QEiLBShFVIiutqrGAagH6nFIDu9SLKuaWaxc+K/Hi
+        EdnEqCWbR47WT0ehJiKDNiK8bmGeD47Ut+NMfn2PNgkKnoQTTUz54riQEAkvLt5pRR+yzXcP6FTy
+        AwFNPaTch+Aiz3hEDfwZuuaOVhkqhPOBHlilIHLf1/EfPra37piOduFHcmItYOaP0WHL2+CB09ox
+        KZ2OOsxTpVgeVrVFZz7qevvSZNB1koW152cZfr/7OAeL7xcEwfWO2HXNcrDkqcbu6qB1Y3h6tzDz
+        pTfkayOdwvWWoR9f6bbaIe68ripc33pG+sUYOiQWFB9CXjtkmZ3t6oeX0m+9f/U+XvjNQ6u1tPYW
+        rU9Str3nBNXW/oy1qzhyQo1XCzN+kaUqKZyfd9cJ9nf9hmc+D/lC3AqIr6sWG6LVhVyCYALloas0
+        T96BxuzhnYOdGozu5a/O2ea2FJCjOm+yNHDF2cqZWqSWRU/3VVqkPFhuXVRw5ONjtF/+G/9XFcqJ
+        ZCm1Qy5khG2itDbhXOu7zrpZATq+FxpZQyk7bODxhLCYhnR/NKSuj6bWREZsfqnbKTeHRVf5AlH4
+        hD96lxX7yoDDx/Mxfi0Th+XZqAC8xBor98VL49qK2XCy1Du2IblUPEu3C/SAuCLdgxA+Lqg0wVKJ
+        A3pHt3XIvX3gyvzSAD4O31b76WNwql0046lZkRkPwZFqjPeHzEbiMIw2tEMQ/1u/8Up5Q3yId9Rf
+        FUtEl5unL6cOibErVtdq3LwuNvjPXUfdcrpXY1btVPlz+Gbk02Vu15LQjZChWxgf0Eab8ZO7sFe8
+        PbXb9NitCnwDGP3ng57VTKjGVf8uIBhFSo/+sei69drNkTK9LnT3eOwQc5zJheC2AmxajHA+KPkC
+        1O72oYpjaN1a1vw3KoseefLW+VZjvxffcBXL0PNbcYvYS1FNeEF9JAvA63T03GcgK97XocF77DVu
+        2dyEUPXfNEwdgY/nKmxRf9Fb7CzU0WHq2f2iEJsS/uPvjqaqgk11i7A6wRX7tl0NDrsWWLmUddov
+        PygCgcUO3bfrpzPBEYvSvSQ1PVwmyXlHXajD5SOV2AmDK2dCfIp+eo2sb/Xzpw9NqJ+6iS8nSNLv
+        fkkM4JcO6EHhY8oOgihAZkkBdhbI6vh3cBL0UF0Nm0Cqilg710duxBi1wreOGHH3AZx26IZ3GKq0
+        tVXUQ7p7NPR4d7k2+8t4+w7GM81LdUL9QmEMHR5dROBgvTS2H68AHB1csr0ItkOwU0jwOFSZt/bv
+        x27c5bz4rRfe3QYfsdKyFugpGhWRT43Qjf5nbwOSbxKpGCmc9gMnSb4GpYS9t+VX7M27BB5L2NP9
+        5NYaLeW0Bh+RE6n5RCq+vAsZ/PSWkrmRNj2rjw3rdoeociqJNiSnTAHxbYzYq4a3w06mQiC2PhRr
+        +z0JSZY3E+SKyqhZiw7qesdzkWo/t1jPdhEayRQnSLWrLWFUZNrsX9/olQZf6jwLRePewWqhmdod
+        WdpbWavJSvHggrcUW6PphrwWQoZKnJ6p6/gq6q93p0WzP/W228uHT4Ut9TDXD1l81EbjDn+ZcKTC
+        wqsy+e0wsf7oSF7vJWwk9uqnny8w6w1vKRzVdJ0mdoFw4bnYXrifinwo91BzOPQekDNow9ZXajQc
+        BANf465xRl7EE9RatMd21hbpWA9ZDx+9GGm6fhvdWAZMQOuPcKQxL8aOxTkyJGOrXvChPlh8OheV
+        AMOzZqRsjmL340tkEgJ0N77MiqljsZFkqcuwPeMh4906A+FRZl5PzpnDxGOrwzvgZ7yf65v+ySfG
+        x5qUao0cCrvGRPw5JVSNlG83YF4JQMf7mtqkdMJBUT4iKuUXpuZp0ab8SY85ile2jvd+eu9+9YbU
+        CSqs+/kl7WM1F5AZQUgW2mdCox2OrbxEaoO98TWmpFt+RBCz6EB3nVqE1JRWJejXMSXyO/w4xD/6
+        F3nGEwLL1qnW36Lu4VrCiI1gFSDurqI3ODDK1PlCgVg0tTb4XZDQ/az3iHZHJlhFdiObeX+t27Oc
+        Q3Ivc6IE6bujxVYg8k9fGTtRSf98r+XTV0gjYSXlu+nmS7P/IWMa1w6tsflFz/Jge5H2qKr6vhgC
+        mP2mJ01N4/CnJV1+4yQdhyv/rQd8lo75wxNEZrxBlwEjjNOz4IxpqGVgnB4pVuPDOxw7/yWgy2dT
+        0qtkBN2YaEcJPVNJJeLqyjq6JXr7xy80s//uK+g8WB3JhXpK0XW9+YwJ2rVvEytBalQNfY39z49S
+        pyD7kJ4z/Y3MlbgjBQSflEldLUK73qn4UHknbdY7G/QnH0s2VGvzc7OAS1JfiITPfsfXYTHBevjc
+        yVa39XStfUpV3hn2xpNnfhjLYCOgMOjv+FguaodXx5sHbN6lbH7feMrOG9jkW5XeHuqrqpToWEPh
+        igkR61ORTh7Va7QSRhdrp+cr5Gb/iQGfny/8bcRSGxcLZQPGYnzj+0gPvMwPqQClH+rYOxC/49dh
+        W0M+TBPWUplW/c/vCS9a0z2ItjZ5qPLBO71TuneqbzcW78sCpspuSOfIEZqebmlD9mnP3tqSXilz
+        x/1FUnXW4L3wJRU7CAsBPadqR6S6ySp2K8oSpOd2RR0mLNNxypsI4jdCBC9YG1Katy26nr8vT0rb
+        hjdb36x//h1jqfTQdG+XBbq/A4Pu7gKpxqAPc3RkZMDmoB/SP3pK8sQYuzeTaOOMp9LMl9RK0IGL
+        37H8yk+04t6k1qlGuY1qiImy/FM/k67Lk/S9EB3r473UZrzOpdn/YV+8xSFfZEcFmhML6fkRlR01
+        K1bCajy2BJ30RqMNkcTt7Kfwfj9eK66lToSWUj1hT5bsaqKVtYFldSe/+gknU35doOkKoM5WTdC0
+        2rjidgIU0N0bld1vJ8Dn0GbYucOdT8GNGOgW5D7Z6sOSDwMrFuhUjgdPPAZPZ4i/T4BubBKsD5c6
+        5DfzXICHrjpWWXnrJs8acxAlwyaCh/SQvw1ThDlfxPau1tKp2RUBvMbtB3vrvHD4pwsXSNwfNbrz
+        tWc40tdIQJaajJonl3Zjty0Y6rkwUO1b6B2bjD5CjhufaaymHWI2Et4w85O3Wd2Kqr9/vgEsuuWO
+        zvmUNo5clJD0elypeUsch58WOwZN7jF86DPNEVqi5vC2shJnQa915HWwPHjFtuyxmT/Z63X20U//
+        n9Njjfrx8SRA4uaF8bLcO8JnbQfweYoy4bu15fCJPALImGx6yx0+duyg7VVk7y4HT8y0mk9LIiXg
+        RhOjeB4fwdy4cLhMN+zaVzscLU3Q5XAvmDgIt3bVHcJpAUTNchIn7h6hvR/p8qaUMqzDwXSm+DXZ
+        UIS7kupJXvLpyppEyqSTRDWu9RV/fWQdhpcd0J9/n/2XB18jOHrbZ860LzBkQiavMw9QNfBZ/9ZA
+        tZM869d11d5DqUCQn77e+oTNlJmbcy89D5uGqtvmWK3UwWrRrM8pJsdVx/aZmqCXF4fUqvynNr6i
+        a4Qk/dWQEUwfke4oqr9rekgnP2SfhCjgK47sbV+vI6ck4y7UwXpJd9eTkRJCixoS5WvjAPaxNgyR
+        S1C7D9/YLWrCh8hYxii4rYGsyvLAJ+frCaBpSYK1QyLxP/nTLrFPZHMOjyl3+GDDKxdtb/zkC20w
+        szGHGc890QxaPrgSuNKcd1Jj5U98dItDAsvPzqfaIUk4eZusBVEsvthhwiPk1VRfYGWbArbU0zkd
+        72bkgfAoMmpscy9c0de2R3Peh52jWCG+zq5feBf7J93lw8HhL9HxgGXviOqstiru20Upz3mwt0Fk
+        cHj+PfRQlfn1l8doBNI7oHl9ybo/v1J+XOuqtHwGyk9P8bneBKSZA8epRd8a++7jDKD7CN6qXT81
+        bp7bGOb8nOq3VxsymqkCnODJ/vj31ivEDP3y0B3WWsQiZRPBZbFvqPMBOxRtFRGkpxeZ4vQcaX/G
+        rzf3QNa8/TpiDGvzD58a8/dsyOTHID18jDOo6pCBfBPgXTUa/uXnQnX1dVTpJKKzHuaMX54bMDsr
+        wVoSQDqszk2BZryhRvnAjkD5QYDEeu5n/FQdHoydgax+I1LsK6d0dC07+ekJqqJI4UOwkexfPWDt
+        /K2cb7dQVFl0Nj7d65ulw0m3u8gzf9FZf3X8GroMDau35VH9PiFmGZ0k3dJRnf1DU7HquUjgbhaa
+        R2Z9OjZHY/Hr/+DjKyHVaGlgwBwlU/u2vFScaisR8jpTCNLoNmTk25TgCd0a//KsSd3lElRkI2Ac
+        HjbdBOkZYHsvOHXCYM0nJIQRmv0oWffLvJvSzsyl+q4TvBdFOeXYHA35c7z12LgA66YHucRwPocx
+        /embQT8jAvYz3Hjg8ohPdVtLv34UNU5zX8EM1Tdc8+WV6ld+075YfwpwXa729I+eu+BB+uU1BCLz
+        +rvewNFZv7zNUmPOiDbTG4gqnb3PuLlqQx6fGHxMPcTXYlt3/MdfBVIjElvMQ8L0vJnwiFZfsk4O
+        ssMui/Xml/8Scc4/xya9GxB8jT0pQyVw+Dlza8R9qcfedhdoE7t0HtBE2FBtM2Th9BzlYGv5aond
+        pis5myIpk1ak1mnq6Fk6rt1nD/eyr+msFzoWLk0Boifb0zsTcTj2+8Ufv+8J+auopmqV2dCk+z3+
+        1aOwHx8LtDr2FxpuhiwlZ+R/5Un1EVn4oHarg3L2IG2Ump4wVOFgBaoHDWk/hMkkTYegT3Oodu/G
+        m/OrkF9DnaGnkzv46DPQxruZuQhEP6Wz/0r7/qW28o2ylB7l4J2+ukHVwYheBnW+mhmuxmwrgf08
+        bbDaHMWqnfNykDWbEb6GvcY2YqQj/owqbGrHdzcZ1S6HBi048dWNqa3zL+7Rg5Ye3h+XoUMHb9Bh
+        eQ/e+Ihu1/Tnd+SV8QkIM9NEy6Xr0vjpB29VrIVqelxv8Y/vvA0QrRtKvSWw8R7On3pldJcr0q/f
+        M/d/K0KeSf7rXxLpGW27Yf7/6DMFAjVeQxSK99L8ol8+Yc79xdaaRAMG8tCplz7sin8OG3/VV4n4
+        40/Unz/S5tf/wFZiDdqoRXoA50d5wK7jl4iIW8FH7VpTqSkSEbEm1yWY1qaK/etiE/bqWf8CHoyC
+        DHc3dNg93b1BXKYV/uXx07W2CQB1LrNeqUL+08PZxnDpr//D4pzP+ZPrY80KLcQoxwLat/ELh5nT
+        hXT23/KvPp1q5XY8WI6uLGDj5f3xT0syxXIdrJbeuIcLYpc08tbmce0RwVY7/v71wy1fKanbdCoS
+        Zr2LtpeUUntqGm3U2beEl5eE1LLecTjNfAq/PM/U2WaO7PUcNim/ks1xP/IxzjQf/OtpRxpUi904
+        nMGELJmUme9stP75gbBQG+y6PEJTlj8ZdD7vqbJxmqr5TJ0C23Ghe4Lk3bTpmbAAljeqe5DdR43N
+        eSia82VqGmXTtdLUSejv36mA//zHX3/9n98Jg/f3nr/mgwFDPg7//K+jAv9M7sk/BUH8JxX/nEQg
+        fVLkf//r34cQ/m6677sZ/u/wrfNP//e//pL+nDb4e/gOyeu/3f7H/K7//Mf/AwAA//8DAHICMqHh
+        IAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4dc3d9229b1-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:21 GMT
+      Function-Execution-Id:
+      - yvvltf2fi4jd
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '107'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 843ac424687a30a5c420c14d40332799
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - d8044446eca268792e84fffa9991472e
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "a question asking for someone''s favorite color.", "model":
+      "text-embedding-ada-002", "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '124'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6SROySrPm/vsVJ86W/kIGpZKzYxIZlEJwwI6ODkBEUESGKqBu3P/ege+N290b
+        F1ghIWQ+U+Z//Ouvv/5u0irPhr//+evvd9kPf/+P5do9GZK///nrf/7rr7/++us/fp//38m8TvP7
+        vfwUv+O/L8vPPZ/+/ucv/r+v/N9D//z1N2nXAt424cUj7K2aYJuFS69BWaC5GXoe7sVlohYb1I6/
+        KqgFrRFlwk2oiT6jzHzgT/LGf1+se9et/LqEZOxUf400lUmPT2xDVfkZPgCu0bS5xDWyHomEDfq5
+        p9PqXOignhOeGvSjpJWXfgBOcQV0X39sY1BeNocerJ1Ig1e7asJ7lMhCt/Gorst2J10iw4fhFvX+
+        533TU+ZZXoxaaztT3btIXlsPggr5xgyxdt+/u7m7jqY8A05IWTQdogPv5/LWPZTUOGSeMYnMDYAd
+        M0ZW9srwpm7IQ9jG8Ru7Ybrt5snZtvBGmzf2Kk9DvXsqS3B3oov3j6fHxptYl5AVuYTV1jt4DQu2
+        IkjOivmyonXGKL2YDRx8z9iz5iCaw6cAMrfZOf60P78Mlt1Ihh6smbA3PmY03swi38zRxaZ7alyq
+        Sd3RWY7HzZ6MsuN10qw1Kpw97koEx1cr0R+pBXeh3fvrztBTCZdmCaK73eA9f+0ZSz5joeTnl0Ot
+        07f2mKjlBdqFIofdotlU0+jYLzhqk0i3LRjd9NVhD1vtjOg24d7GwF/WHMRr40VmIrxQx18g2Sjv
+        zsDO+ftBU+aFofLMbgq+Vo1UkZsYWco+W+2IsLsLaG7qjwz2kGb+e6m3meZdCeLhdcWH0Aqq8WmI
+        L/jMbPZ54m6ZJMpuA2W/d2iSSCdvngK3hkGGNTXWuRkJq2oclYlueuzgzK/Gts5CyPTQwep9lL2l
+        XmJgl9En0AsZ+vP8dk9VwxFuTTaflTGB/GafsV2ITiQ84Wkq7kcQqHqY045uNnKOorg+YS3KUEfC
+        0e/BdzkNa+dW6Hpt3o+AyqtBFMX+onb/7XJYpzX4RGZtNx3GVke5X+X4UN3eaAykTwBeGgQ4r4Xe
+        mAuhLaAZTm9sjXWFOnXjleCNnyvWm0/nsdPWbYCSC/In/S0bUyVEAL68+VJ8SwLEqsfMQ2MFAb0X
+        NI5m6V6OMITeyUfXA2cQuxxVKAK9xF4Du4i83HpGn6/88LnrGFTMOfUXdDj3X7yVkdIR6zCXq+gi
+        bel2qSe22iUETSJ3xfY3lNhYC4cYVPYusSY+hK6/eRCgix1ufUe6tmysjdyHbbRzqUNjr2q5l6XD
+        IHNrqov8y+ij7U2Hxzkz8LZVVt4svK0RWpV8qQ6OgD56NTQw9o8aG92nrKZP3YrgSvOOumqnGdKs
+        cTKAflSxc00HNFTGa4Zd2r9xut0cUiLcZQ6W/seHyXErhr9aplip2PlL/bHpuO/20EvFTN3Cc1P2
+        rrkMTsfbi2pv78VI4/oxHEL3TpB1gYo+hGaN9rcY0Z17/lTDoTwGIId3h6xuychYr8cvdO2oSCTJ
+        qVl/S7Y64MLTfUkcmFHvuY0L9eOiLnjVVH/qd3M/MvrDE4peWQ274476LB8Ra/thnyMwdew/c66r
+        erjoKnqvEgNv45PU0fl9v4DdvR5U39r3aLYqdY/K5yeiO8mxUF/AvFbQywoJet/Eboyi5ygX51uH
+        nZ7kxtjqCg9Ca/lYO52qdFL9F0HXw9Om2jpQI9HI0gwdY7Gg/vodoHFfdhZMD1mjhj8rKXvHA0Hm
+        Omuw5m1Ggz2MqYeEyFuqc8yIhOO+2gP/PA00C1LMJnTPfJgEbFN1zZ/YeI2cGLJebqlDYKmnYXrB
+        xGKPzOF654n2OntB9Oh7Mt8shPqpLxoYq/cKbzeOVPU3GhIwTXjg/ZtsPVIY6IJSn9epOn9QR9zT
+        AACkHSkORztlTvoNIZ6blAhfb+OxpX7WepsZ9L66VB3rB1eUl/4gkue7HWkeJwu4ihHqW+reE05J
+        NYPzWR/oWc799HuQBBGis25TJ4vGiG42c6Z8xCu3vO/IG6Xe4mCjuDrFDaTdlCjHFrqTTf0Vh0dG
+        7mEWgiZ/eJ/neT/taUB8aF/7mV6LZ8Lma5OU8JbNhsYoDww290kIgX+lhA+ye9XnxbNWLL4NfJES
+        8KbkiXUQG39DVmL/TqcHTAES6lLH2mXVp62sTiZaK4GNz0l5jBY8UtEUZT6+y9oesdW5y9BwHgpf
+        9s5OOlNd1+FuKCp1MvoyGns67VG8snyf52wzGtvH9SQv/xcbh40cTR+0Ln98gHcruzaosknMTULW
+        W3r6KH01To7rw9E/fLHJvVk1Fp5BQHj6H6qL8Rh9yXsOlUfgNhi/BYNNxs4msDrnMt6yePZI8DUs
+        OIT2He+G+FnNNb8BQGQUl3412ai1IwdHOH2xHh9iNkryg6At03bUP+3NTljblx6c10XD24uldPTt
+        Zhzkhij7Vn1rq1E7dyE0h7jBjyRiqH8diwCS+aFg53SajGFEfovqGa2x6fo2Gq319wRt0dQY35IR
+        jQO6jQA9etJ9shcMGnuiBXfdNqi/ySPGctJxMK7AxJnS52nToS9A2R8l7F0PuTHfxNRC3VgWRFw7
+        NF34Pvv1z8LHt27cW85r86IfiXrMKdKJl+sQ8Ff/0r29fkVzE19dsL22JFI4XQyWfaQ9Kv2tQ7ec
+        rHtUVdVCNqdLsPBX2jFZFW30FssMm8Iwpb3hX1zwdSuhbrjm2XQ4GDXE/CPGW3dXVSx+GiNMUwt4
+        b6uAhoXPQLBeW5q2ZPjhjw9pUSt4Ow6OR73TyUUdb/V/7i9qVVEj+WKc8XaLwRhpv+bRRuI/1LyN
+        UceM1ToEpbQkataNgIhV2Xv5hy+m9LhGhOWGDVxxKBf9I3ZTEnIBXMr1B2sPye8W/CFKuykOeAdy
+        n/74SDG25ttfm2rTDcmN7UFvc4PuYymP5qsJFijVhsf2k/bRbK2+BNH9S8O6osdoWPQeqi/ZjfTO
+        mVXkUWT8ZuEfrPN1Gw1JKIZo6+LSX6m7As1+mV/QLXzF5IffvTwjAvfdc+9Lnt9WU/xUT8BWXYG3
+        ck5SZlqIA/nuDFjdvWo0d7UqKjfRepLV8zYaDF08EW78OcSH5FlVw+HgvTYkozN2HP/EZrcUCbK/
+        UkAxdc9Rc/dSGQ7SoyLcG75eq2VVi8x13tBDaI3V6I9diwLVXFHDmstuOG7rAG3CD8Z7BWOPf4b4
+        JLEpHknLOzYaz5zHgyZpDRFPhzklTHs2aOlvalem4fES82S05pMnNbZ3DzGSP2UUaLy/8PPTmw6W
+        38J6td1ix7jTaHbXZgyHzX7GNl59uoG/Yh7NonjEhjXr1SjYT16+7/kPvmzy2qOkn1swD4gnMseO
+        xsywnMAZlxX1PyGKpv66WfQXaESoxE9EvcPVh099iiiGe8s6cu05eY7pEfsXaeimyzMoIde3HcZB
+        6Xe0uFkWFEfpQbHA9Gg8b20eXr3RYeP6fRnDbI+JItSFTviwlVICaiEr78rg/Hy7c7y5qekaXHSJ
+        /JV7FlICc2Aq2pOU/rjofWmbOQ1o2c2ij7Rpq9nKvAAMN1YXf9EZ4y3c7JGhlTe69FfHclIBWn4P
+        e2utZMxLKQfNK+eou7wPngyYyMJrZthaOziaNT+Uf/VDpKq5dqxDaf3Tl/5YNs9uvgtyL39W+E13
+        Q6xVnb4zbXSKXEbtztAj9nHN+fd/Sb+SY6OpjYuPvoewxN72fuvG697Mobi6MlkfpoENmeJkcB7o
+        ER8YH1U97DYB8DJeEd7beYjxdtci+/QUqPnYthFDO2QhUvhH7B4rzhhl28lAPu1jbD3Ge9ffRcsG
+        6MwXjmVnk77F16YEJrINdZ9KkI41uBf08yvWufx6s9ZCgha/5LM1iqq5PqbFz09S7ZoWRvc5agRd
+        HQ4wbgB1DevjDNiUjFS/bdVIOokTD9enFtKjrFspXbWTDaL1HKguIM0QDmOpyj8/IqfRDpFXLJWw
+        +BWsVtsAse+Q6ujnJ3biwLzxGe4uoF5dg7yEo9LNrwefQ0nHsy/mUlIt/qpUBJMXsf+gGI2C1sso
+        c5In4X58EFFYwy2sYyK0BWXzS3Bd1J1cSh13d0WDmgk5WkvcQP21rVWUOKc93IVmj+Pz6ZaSwl2H
+        SLJuH2wzZHYj6uoa2k15oHq4/njN0s8oph5gnZIPGiPJ9mVvvtTUW/zAhLqe++l/sgJNMige7yFa
+        5Zcn4U9pacwPEC8/v4dxEkVs0Y8zSCOX0t3L9Lpeq3gdXqvC8aPL6RCNZhaoyjtxO7/3qiEabyIp
+        UEUHxZfoQiDz+3wCVBQW3kXtxhjt1k7gxl9D0vcCoBn8TYv660vA5ue5ZqThvyOaL+sTdaVg233f
+        YJNfHoET7fXyRkE+6jA+J/3nn9Pp/KQxdJt4R6/8Y5MO81Wz4ev0F19hPOumj6tdQHsHhJCsYcaQ
+        FGsbLfxLtcE1janTexXZ2CfU1C5WJWw0VwaF8RZOrbPm8ZFk7yEPQoIN7E/ehMcbjxQmWtjD7Vw1
+        V3NsFerHHN5R91M1VhU18NM/NtOfVd/qAg/1hitJ27jfbuidhoNLcxzJO7RKRL98LcrOEF2wXZmV
+        N1+VlYmeyUel3nYzpBSn+IXkuzdQY9dtO3FzubdwXfkn7NybnTcPQcmBh/yDT16fORrixEvg7oQp
+        PiRciEZQ4QIae2T+2H5UJpZGZ8udd9zhpT9S4eHppvyQJ4dujy322NyHAVxRYxNxMCJvvNJyjVTJ
+        IYTl0b7jf3r1uJIFf2DxCo3aLinhEKS+v5LeTUp8bsXDFbU2dTj5kk4jshqoHyeV7pRLYYwTgxwt
+        /Eue11Q1psNY6sj14ou/IXBlY1O/cqhX547afhswNmprHwWa6JNqihuDrnYhgbKPJIw9f53Odf3c
+        wyPqebwrFFKxQ6quUeu8AprvziViT+hLGILTFbvc5Yl+fhK9IzUivZ2NFXVKxYIw31XUv5s1IulH
+        dtHPn9q4ihjbrhoTrDh4EMmutEoQtciCSzf7ZLxaU/frV3jRt0RgIA/GlF0pA5PDq88HmVL9yQOg
+        3zyxN6K6YxUxXj9+IEppUo/x9+miXF/vnAjBtPdmbXfmwEp2GVaTr54KnSOJwEWzQcjBatJx/xXl
+        jWGcL/QcVuGSB6QASmlK2L1xk/fjMyTfPk8ydAIfTV0AIzTmU8MfJzMrfvGTcLoLVxzGhxiNtZva
+        sD6kG+ycDydvuoiKiQr5a2Dt4H88olVShiaWePTwbNL0uZvCF0T31Z3wQqB7otG+fEAvM6S3Jf+Z
+        9weNg46bAl+22yKdG6TUaH24bbCpXepqCp/rNSIGX9Ddgg9zg4QaeWdOoFvLfhhdn88m3G79+POT
+        6SzPTQgc61Xsb+RPN+7Xuwb0pufxuYWqm1ad+YL8XDt07+021eCdAiLzbPf54w9nbXNwN2c78fDu
+        p4/HwObAwVaz+I8gEqmuqwp2zB7/+ITNWqEq4qsd/JEZNJ3d0xvgndgdNdV8ZczWFAD0t3TGh+DU
+        Vot+DaBqPm8CXjWkYzCmGVr8BrlQkhlMV/FebhwxwzupFo1hd9qYP/9M1WfUsnl/cAA2D01f9Amp
+        xiZOCbo8vdjf9CT3Rnd1GlGj9yZ9LP01GTuVwOrqO9jM97toOi7s2DSG++MT1Kb0wCG7jkyy7sw7
+        6u3Ky6Cs1wQb+8o2BKKnIlJaLsc7u9I6MXwKHBhVFPkrbWMxtvQDIoZYYF/tztEXXdRYWfJEvAPt
+        my76OJBD7TsSw5+ebBR7O0R+cLT9uaJNx74OX//wnuYb7VXVv7zP/7qU2sleRcLneLflHvgD/eH9
+        EEaFC/GI9nRbPoOKbKePiOapFKmXU9/45QW/+sC/fEMEtZGh2tsWTqTgXX0ft0QEn7sLpGm9BH0z
+        cV+gQ/4KaHb5fru+G44+OrsHG/un/asbH7dT/vMT2Ky9upsv+50MWls7Cx9evULLmj1i66dNuEu6
+        YbPAriWc7tKVOp6aIGZNuQpXHF6xlTXvlITbLINaKQl2XXXuepZfahiy2fU3h9bu1m2dBWAcuD3e
+        9YbLhksS1XB6rXV8mOobm+LmZMP5JbTUfT6hIhGnvuA+W+ov7+4Eb5x92Fy8lIzV06zmcLSI3N3V
+        C9a0XjKYmrUq1Gh6YPz5OGxmct+gJR/Gtqk2FWmO3gm88X2lxuJPpuS505HrQ0kXf5WS/HZc8Hwt
+        YGxXNBpvpnSRnUKoCL/PSkbq+ruHDUqYL6RSY8x7brIVWViFPmvDjvXlcZ1BH0YJ1WWeY4MzuTGa
+        +muBva/Q/tFz0OjExFaeeGl/frYnGDJp7V8JiVhfD5vXL//DWJm1StyPRYzuasz7H9UmXZ96L0s5
+        ZJKG/b6eOtJfxRnOzygndOAN74fPaMnfqbqdCzY/vJ0Lu9frQK89HBjzDvYJWasTj63d/IoW/34B
+        2r977J3Ks9fDpsihOKcdmY+WZghhVNiQbrl0OW+mS173gma4vKn2ogv/l5oF4YOfqXWovmy8NfcZ
+        4kvYkttDLBY/Z/M/fUut7aut2tSjJUo4NBImB27KsJT4KF5rL3oon3naP26nDM71a4OPIvpGpNXb
+        GM3HeoN3wWo0RuMcmQBbaU+KTJL+6BVQj2KD/aW/yM1reLToV+yft7tO4nHzgjitt/70CjUmrud1
+        DoavyYTLxR4NC75DCH7lo2W+ICVmYqLr65Pj7de7GbNwEVV4y1aDcboX2UzRQf3lYWRzKV0m5ERK
+        ZOsRS/TQCadoXPwAWrGu8Zl/9j0q36/tD+/org63qbiZJRt6xtUEsgR707tmKqyt45NMWVRWZK1p
+        oRL0OaXqKAhVf2vOI5R2r2Jvcz0b02kf6bA6yoR8D23TTeaaq8GTGo1mWUK9cddeQ3mNyg1e9Jwn
+        +pwkImtGmt+/ydagu0NDoEiohQ9ap7O5u64t2B6DAw7CtjKmH5/HqNQpVncqmq+KZMEhuPnUsjZa
+        JJwavlSWfAY7xOBZ63MFpyx6GKvby+DNnP/MYMFnf94gxIhZBckvD/W56ylD8wO4Ewq1bvR740W8
+        6aLIOvzmI6ZY8+n0GcTmjx/VCLTekkfnsAnGkC58bPR7y6nh/DzmFCvzs1vyLoCfPtSd3ZPV+zTp
+        IX2vY2qsEetmTo0JsOSUUPdY5QaNzTYA3S0tvFNfZTrlBWkBF47+y8eqicegol3j3rD307vN8Ex+
+        /U63raF2PLu646/+CbUt1eOFt3cCVy+oj37v53BSS1j0Id3F2z4dPse7K08aWeEl/0Lj+lImQMhD
+        oy491hGLmhW3WeYT5LPk6WyU0R7UaX5TcyW76bjg789PUdOw+27JA3vEhSpP8ZKfDlXhh7D4c2rl
+        klyxZd6ILp0E/mplMzY/ikz85YE0XvhmWlXrEU5N7lPjehjTSXmpHMws2NKbt1EYPUhtAvApYyKz
+        4cTmiFNrZdGv/zXvOIujiozelfHeeBFjmRfF6x/fLfM8b/LSV6ngbVH4QgtVNXwGroEXMy+/51fx
+        tF+Lf/JLs0jAaMPovYe1FT39DjnIG2Z7HcOSv/ss4wQ0SnfRB27iJgJRua94e320YSwMhv0JNSnt
+        nD6GZ/JW6T7lUo8EUspDEgwGdrTOSYdcgAs4hVT5SvnMo0X/2BC8T1fq17c4ncx24GXN38f4/PU2
+        xjBrLEef+hL90edDEI0XkA7Vyueu0TOdLvQb/vCafIQ4i/if/tpc5ZbuCsWvyG++8VV5Svfpdu0N
+        n0FsofmOt2X+03Xzg7zrX/5CLs3n1ZGb2cngDl6AtXdz8v7knUo/pdT/6fWPu59BHMoT/um/ZmJ8
+        Jt/QvcUuiY2IFa5wkaV7fsRG8ayrybFi96d/sCVfHYPclEBVlvnU8nyQQaZrnqD9eD8SxmqN9U+D
+        e8n5tpPwwWl1o9Fmc1Tc78f04R0e09/8FY4Y1kS2/X3VeSs/hms3iEQRcy1tUiUN0Lz++oQtedp0
+        ifIG3icpoPuXoHvSksfIxrB2aCLoHZv0qvX/zFP127aImmHQVLT4dYyft9FrzluVl4Pd4UptpGdR
+        fzXXrbzMP4kAfZOyk7jhodsqvb++jQdvjLZH/cfnyzyH8+beqVX0yze97X1T/fgOHlmd+tTz42gq
+        yVUHFu11Ih2zR8Tun+IEL3lPqJnvPynNii6Bv39bAf/5r7/++l+/DYO6uefvZTFgyKfh3/+9KvDv
+        5J78m+fFf1PxzyYC6ZMi//uf/1pC+PvbNfV3+N9D88o//d///KX82Tb4e2iG5P3/XP7Xcq///Nf/
+        AQAA//8DAIhgdPLhIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4e0bef3e1e3-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:21 GMT
+      Function-Execution-Id:
+      - yvvlf6849c5t
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '22'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - f7e1aa5667d824ffdc22c9b3a2311546
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - e80be91cc8cb1072e124d8609456adff
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2940'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
+        with other requests. You can retry your request, or contact us through our
+        help center at help.openai.com if the error persists. (Please include the
+        request ID d18e0d0041203d240f04766f9875bd2a in your message.)\",\n    \"type\":
+        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc4e50b34117b-ORD
+      Content-Length:
+      - '349'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:16:52 GMT
+      Function-Execution-Id:
+      - yvvl5uno49x7
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '30011'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      X-Cloud-Trace-Context:
+      - 559387b6907187493804c27758732019
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '88794'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 804ms
+      X-Request-Id:
+      - d18e0d0041203d240f04766f9875bd2a
+    status:
+      code: 429
+      message: Too Many Requests
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
+      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
+      dolor sit amet\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2940'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA0SOwU4jMRAF73yF1WcnyhAGgq9wggviilbIsZuZDna35e4BVlH+HYF24fpUr1RH
+        oAwB0hwt1VZWV/fXcksHbUI3+nqXDm038kN9vJWHpYIH2R8w2b/HOkltBY2EwUPqGA0zhOFyN262
+        u8vzwUOVjAUCTM1W2/W4sqXvZbXZbgbwsGicEMIRWpfa7NnkFVkhjNsLD7/un3248mBisfyS43Dy
+        kGahhArh6QgV9b+1S0EIEFVJLbJ9NQob8ld/dB0bGhm9oYucXcXIxFNBVafWiScnL+5delaXpFbh
+        8tctitlFddG1EhPOUjJ2R+wyKk38LWrLvpDOxNMaTh5eiEnn545RhSGAmjTwQJzxA8Lm9Od09gkA
+        AP//AwBuqeKNhQEAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc5d8b8a4638a-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:04 GMT
+      Function-Execution-Id:
+      - yvvl7ew5uk02
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '3176'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 78fb317ed136dbeb23921ccd45134139;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '88794'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 804ms
+      X-Request-Id:
+      - 42784145c7d38006e79bf17199be9178
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
+      ipsum dolor sit amet Lorem ipsum dolor sit amet"], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2778'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6SxOyvJbufP+Kr74pZ5eIQBZ7htzkmqggYlfXKVEEUQSBhEtX//dT+O7qUz1x
+        QGIlkLXWc1n5r3/89dffdVpmt/7vf/319/vZ9X//n+XZ/dpf//7XX//xj7/++uuv//r9/q+ZWZVm
+        9/vzk/+m/wafn3s2/v2vv/j/efL/J/3rr7/v3R7jxg8ibzjqkKNN93gzRz7WaETwGGAqqMF88dR4
+        AzaPTyhfekJXV0nV12Jr2xBwGCgEKPA6gSZHBI8oI/apx+U6z0YM8nzs6XQ4lel8kmcDks+zJI7H
+        duFwIESTeyWnzG1aaa7lbjqizDcylonvYKavu54pbdkTolOgbU8tuYLDrgYWTGsc9q976iN+wBz+
+        0MnV+/1h85V/+91l4lPvq0vLo3A8dnicvG0q+LF1hOvmJDH7/p3a0ceeDNq6vTH7VRdl7/hNjroi
+        DDCyozCd8qzJYI1snQXhJpjnx+uaQX0pHbKd4w16KY0rA4ZCZerw+rTN/SPH6K0IG2LaZtDSKcg4
+        aOpLydyVpLVDG3iG7FSZhBm5v8rpMh472Et9xpwW79ORywtVER5tj+XC2KFx2gxf2FajxojcDx4V
+        uLsK9Sf7MONdn1qKteYrqW/BIoGuvOfBdUQRTeFUkd/5zc8k4eB5cjk69IzTZ/tBa1SBi0jgyQ7a
+        FOklguf42jPHNnApbFD0hW57U1jSDDd9Di3zK9+Gj85w8G3SziqzI6QDvtPKOavhfJv6GNSzWJPo
+        En9bKs7aE03WBxOnGvR5vNCnBffV/UaFBLbh+psEPJzu8R2DYt/KuT/0FcQ0vODC14dy3EuiD44Z
+        BcQrVbucofNU2XKTLRZy6Z1OJ+WGkfS6hr/zDOf0PdwU6ZWExPGuedgJwvOqxDAHZOvJXzQdDF8F
+        TVBEZrkBQaMgXGs4vK9fspPLrqWBmhzhyB8Mgp2inCf7xmnyi8Kd9tOahkPv3yzwCu2BW8HYeqO0
+        WavoFz/kE+3bSb3mR3n69DLxWofqs8AFR5R9X0es6IqJplC/q5AaxYF4AmV6d5aNSOEPzCVaf+Ln
+        CcbuKZs9x9iO7UaPltfJUoz9dSJbFCI0dK7bgZt4iOltNJYzasYvqtEFESsOpXSO+SmGva3eWLoT
+        rLY7bFsbQOGPJB7mIJ15jt/DVF0ysn3Uh3S6NPYL4MjuFF6fZzujRqohl9MaCzt9lQ5Ko8mrdpA/
+        eBDVUh/fR7WDraNHxCkPXTgNOOBQLu18gl3NTwcB8TZMVZrRwZnschJm6Yn2TiSSHalrvfPi94Su
+        kdsydRkf0QZrkItni2xbekXTebtRYZC2e2bt9EfaGc1ZRcv3JljR5ZSetysNpea6Z3glluWIPskE
+        O8loiX/xPl5JjjsbguKNSKaZddqHgiqAJWUecTXSzRPZoQRMdU7wJrxZrXDr2wj5K1kkVrZXwsa5
+        mlfohnJHDO1EvcEMCw28Z4zoylSztKfbmkeHS0FJEJ2u7eBbTg4xmd9Y4I+veco6iGFo5hgLh3W3
+        xI+gAXc/aCQIYzMdPauekEEj8if/vte5s8DPvyua33OiD1XU8EjddCJx0oaFzZldLCCbm4XlqyUi
+        Wp21DkXKMyA4p1s0HsGp0HAJVILd7ppSvYgSyHeQs91S/8ZiWPEg3D8eXaerUzpCkWjQrNU3wYUk
+        hmyXeDk0E6cTN4iLdMSadIVwxRGcu7Wozzy/nxTpZF/I9hxb4TTJzRFgKnriVY9cH3DQfdHO7kzM
+        2rugT0P4oOgi6WvKZ6dVOX2vwg0UnNRMp59d2xmFL4N29mq84c6tN2i3rw0rh0bMh3ldtt/TjZPa
+        4tsT1y3OaEjn2wv0XPWZ1vFdOGgv/gjl4ZpjwHvea07rgwC/es9fnp03HLkvhfVqfccLvvy7HqgX
+        xWV6cuHmz+99T/6wI2n1UL2eHmID0ImtqRikZTuZafpFWwsmFvhJ3LYfXPMgvSlj2x9eCPP4hI2r
+        3Zk5q+M8vl9CDGfnSjB3f43pOMqSCvWuPlOQ8kfZcW10hOeO5Mx9dQaieB88kWw+V8S6ozikaX2o
+        IJMsi1hL/aR54wPyTk5J22e7LccycTJ46ZuauVjgUI+1MQG13QCdp9Ty2HZ6yKgb1yXZVWvL46M5
+        wXDuJYkyQRrbwSZSDaqT8Mxs9QD1RnypUe7qGnE20QV1/Vas5PTghiSQpymdI2XOoLCOL2J011Lv
+        L80+BuprT9oLjT9PM0xf9MNTvfqW5Sjo3AsprIiIF5knxObNwQY+iz2iFa9jOvLG+wV7q1PZISoU
+        77u8P5xoLS3rS3OnPp8y7OR0R0F7HNrhQHYqGJz8xkKBu3ASB9cF57Le4CqXzHTBvxqE25Fh5N9F
+        RGvsVGizmTwKJ23b9pF49OENz3Sp537bSxtFQ+m7VZjOCXE75JTzwXhYJ8ytrTicz+MIEOFMJwbf
+        UX3qnRJDfvav5LZzVmVlB/aArmOkk+xdnMI5FakFAbhXYr36ch5uw80Hzkv2JFrinfrec0DO270z
+        22oErx9VjYenvveJfkaTPjlRK4M+tQbBjXALJ7JqfLCv5EwRO87l6J4DDdjllVMZC9k8O45Yww4z
+        hDf0ULTj6ilfYXzRG8MX6zX3q9Z/gsRzDZV21XbujhYvQsqJKh7q9On1w/5jQSJaEh3n7R6xc1dj
+        9M7UD4UD89oN2wsvCJYd4PvrEA7q/eCC0ok3Fu5v17mnvhFD4p48ot492xu21/2A5og9iZ15qUdv
+        k2Kh6bTTSMCeYthLU7mXeU4s6EruB300K0uE9nidWWCT0Rs6Q+SgSlVC0nP6Kcc9DBXCjWwzLaca
+        6ovCff3qEeVjnW+7XZDvUXyNTBbm2xTlu0Sf4Fh2lJjpah2y2VAM+IMHOd3Ow6geK0V73jDLjtE5
+        /K2v7FytIDt6KMo/+JQI6pmY3uuFxiq6WrBmhx3zFjyf1R67YHX7mVgL/vVlHr7A45UZj6lrzHyT
+        3jk4ai+NZAdHRd37c77JWtHZC97V7eTedsv5VTnm6vaNvulaucEZ7Q4U3vdJH21SiMpXf16I1a+5
+        dJbWhi3PVkCJdpNf4ahOmyvqO//IiF+jcNZujYjmOYjx4O5YOe417Qq3/TTjVVh99XHwTpHMtX7O
+        8CVt5+kkuhks9YAFXDXMY9IlnUwvnMq0+H6fv+KguaAot4kRdduk0zPJO2Vr1jEzW0kJ66O0hz/4
+        YeNK9uYN8kW04AEzy3SYu2TLnghWLmXmWVVTIXt9fQlnuk+nSMnTBQ9q5BdKigsWHNPx/egqlOZJ
+        gAfnvm2HSyvd5CqwRspv29wbXKLV0JokxYonN3OvR/YR7J3qUMWwvJadNx5F672OsWxSIxyCkzDA
+        bSUAU8WTqwtIEuof/8YrQTqU44V+LRCy04EZ93Ysv/rNrQFLtsZuTXUuZ4doV0BReiF+g7iWNsnb
+        +tVP5lX8Tp8e/CNDBa8diUPK9zxIojGhryWdial/8nnIntsY8X1l4uHu1d4wKVcXLXoGKx8ZpeP9
+        mb9k7zC8mbk/i+30rO8c6h7JlSV8XOvzaL4s+dwjifjgfMqedzYxSkvdpIh95LILVbDRN/YOmF/q
+        76tJTxxsvEhiBraGlm2G5oqSargz/eN1+pwOKQcft2aL/qFhb52+9R++ZLYvIR3pthYgT3KBJcHw
+        LfvI24nohK0SixZ318caXyK46q8T0W2XIXab+gjgEWeEmGoWNvfesNCit6ikKrJOufJQK6GxuRLb
+        gc4b0ta9gbe/OWxnqG1Kgb5ckE7uhU6u1qfjtuO+v3zGE39rwlGP7D0ox7OCC26a0+7ehwKo8csn
+        WwPAY3XJeElsHgEz6spof/wTLhfypiuvqTyadXwEXL9OmLuV32jGqprD+OpulD9cqvYmd/Ie/fgJ
+        XvJzoxVzDfu1ZpBAPQbefBldDpLLx6TDdm2040kpAYrXlBA7xhv9F3/S6ZGsCGnvgkft4zEHkytM
+        5geo1ztmpTEI0m1HLrbM6R1qJFnWZu1FV61NvFG9DpqSyP2IR/VI9RGKvabkKeKJ1X0/aNCjvQaV
+        N5yY30lBOynVUVUuZ+SQXTgG5VSe8khx1nTGz/sQotk+agM6RELEdmq/Tqne0Byy4CoT15Jk1HP1
+        7AJ9KAJeV+8inP2Ek9Exyni2bY3uN24DwZeJ+MeL1LKs6yp5frYqczXizzM3vCfYb4wKK1dOSycj
+        u6mIJ8KZqbAS9e5zaDJQheRGtKAw5snZ2Rq8OHz+4WdKkSR8wVT8Bk9OX4W0yGUexHOVsm3G6eHU
+        mupNqdN3S7apa6AF7zAAfSXsx2+HSA+e0LP3nliNN6TzMy8NZOafmnjscy2nr60KcOOeOfNPpesN
+        BzjE0Oq2xPDByefxp+fn7TNivhUOHuu3Q4y+43HHtns/1scgYQmsgrbG+8P13c7rcZ9A9RUe5Kev
+        mk+mVL/1KDtf7XLhZzkEefhY6qk3T7NmZPLTRAYen5Wajk2GX+iVJTv2429LPAFo6+bGvBD23riW
+        Qg3ceP2gPEStPj3vcoZGQROp8BavYdN4e0AzX05YkpRibtvdaCl78aJhQdt7aA6OgguXdb1Z9P3e
+        m6qzRmHJP5zz/qusV/chUX58+MAdXDQ5rn1Fi19AdF18tfR99SxY9sucXbVF0+oLE3yfakA5zaxD
+        asaODPSbx8R1ntrMm8k0Qd9BQqxuhVGXsR6DuEla9lCDL+r3/ltGmH6elMcD185VPAGwqwgk8C5F
+        OkU2neAS5R4+qEfsrZf50OquRCXB0cP5sP2KYrh3VSwfs3QetC9W4UXcgATlvg/Zqg6/IK/RG89t
+        dChHKyk12KSI/PQ36vOXC2g9ejLTp6HXxzwdeOUwxzbzC9v75ZcKUpyt8beLtmjgKu2JDMKnZPd4
+        7r1BRIENh8/dx7R7vNKfvoJZEwYScIcGjd7B2KPg0dvEk4OqrOVP/UTrO7TLeQ46rfMVhnl13DKr
+        LrSUbR/fI1jy9GHujanzmjf6CqnOladr2+zbWf3wCdjBdoWb8uCnbNLaDuxKuDC9Wn3LsfH2HDTv
+        qSUB2knpfFINGe3Px5jZA229MduwCrryxAh5aGbJf2KEYYxsC8sFXaMXSB9b2rlqsdQ/E/GTaCeg
+        mXuBGXGSttO1sjHCTOKo0K0oGg8rh5Nz+VIzrLE4nddjkiB2UzLybVoJ0aqosLxLI4WcZc3QF7wC
+        cJ80XfhJlrL3baYQBEKM5/ButkMfVT6sOu9GhS0rU3ZnHcAzKQDXFqd4QwJ3CspBL/BhyT9We/kN
+        BM4rMIveq5RNq/IItmCFmMKlC6e1xTDo2zyhw6I3x2e65WH42BnT5+rWjvePHMHGplumaaaT/uEL
+        VYe21GhuvNc1+aeDexYPxA3aOvyYyfREW77L6Zo+3+mgDnj46W2ytx5TW3WabcEfP2OQaNlur/sn
+        EHS5ErWGbzml6/UNenTzcbH4Ld2jed3QZRfNtDA+a288s4OhHN/jfsGHWB/0SzOBFQwrjKa91vLy
+        p84R8TSeBcYgtayxcwum08amw/seet2C5+ijmBusGOmxnUJRyhCGUmXGYYnxSW72aH9BGPM4PZdT
+        p6mWPNzeHNFcLQgn6SNqMM8kJpq+X6EpRQSjCx+nzPO+b2+8fScKan3jFn6OvCleuxay0u7OtHva
+        zeNqyPboVpwcug57N1zvcuzCdQbEjGW9bl7bGmjvnUXcOi/D0bPyCY58aOCjK97m6aRVKpQGsbG8
+        6NnpOr+sX3wy68RN4XgT4xcs/jGz4zLTu+01GeB43kzM1V4zmnZ7x0VT0RlMf5TMm6tXzKN7rjQM
+        K/o1pEYoPkFdGyrblmOMxo2yHv74RfaYSHqXbHQO9NXRJJpVnuZRZk8ZEpmNWOYP73lo7DoG5l9s
+        vN7BDtEBJUd0qOwBT5l5ncfbO+dgyVdifghJh5N93v/8Kcwv8TTyziqGIvI1dtmhev627hWLPz1h
+        Vu9tyCvl6MLzlYgsgbDz5nYnGTK+fjGGnfNoh/LJU7hO9YN4JCvbGttHGSWOxvDsre0WvY6JD6v0
+        bS365ZR2Pk6/MGv8wPx7TvXejfxaytcUYxmwM3fvp0nRMp/dNw9I5+xz5UE/PTqMWgd7g9zJR9Ds
+        lsffa7qal+9rgxffV4R8s8Kb6PZgKAq+1rj8Zpq+GfRjh8LYEYgR7Lf65v52MrDbYmYW6J90lL8X
+        G5IrKoizq4p5QJOvAu0qEa/lcDe3Rly4KHlnW+IooxpuvvePAcfoxhM/qCx9PZlRBX54/2Bu0V+D
+        mcjDj+9g7thw4WSfX8c/fr2mEEBjIkGFsiCR/+g3dpFOhnJ6XFd0Y5+Oafd68DFsLW6ib+HRpP21
+        bSgs8UvMs8BQs/ArcOfjyAinVt7iN+ZIUR8e+/nt0+198YHgdKIlwlLZaefkCtqsvpg/9L4+X+db
+        DGNtXnFxjqt0pNb0Qgu/ZQ7T6DxnIxeh9N0of/oNox6pe2Xxu9h2brn59Yln/PMzmJl+aTg55OhC
+        c/JP5Ie/vJn5T3TLuj3RlvzpHx8vAj5fGbTQlQqxXaLnEL7aLxUd8L2ffoWzeLuQO9uSeYjmxEev
+        w2gx7eQU80gt+YUs9SKy3YdPvXFStOTH3/79fy9dPeVdcHkwhxZVOp1E7QbtIH6Iw1m7cO0c0BF+
+        /MiHjJaD+lVUNEj6nnKH7IP41ykRwMTug5BdrpbCvMlluJwlh2j8OKTzJ5RfkL5OBbP5Z1MOyfbz
+        BD5XDKYNoY5G92yqkEm8Tw7G5+RNe5I9EWvvR6bvOt0TEN+J4B5tE4+70QzHCB1fkFe3iJ3ZTfT6
+        M/8VUPtUHGZX9kMflbJJYKlvuNGnMp1H0Xbh+WYRlq/pA823Pn2hh0grrJT7IF0v/iXabFSTnLnu
+        6E0LvsHqevwSO+dLb85bpQItygfmitc2HWOTuPISr2Qrc9E8xFOB4bXKZ0aifRIOGntM8OVbk46E
+        OuF68c/keRRlzL2eajj88Mf2+hIfcX5B7PE6ZsrS72HOOW/m4dF1PDg7xWQB2zI0Sb0zoXeQHYha
+        RH3LdifPhZvhjWTpd6HFHx9g16KQeUbOo28ojplCbuc9FZd+1FJvLOg7LmGmXGM0VVis/vgftmX3
+        Zes521r50w+pmInmg28lkNTCigX0XCBWPUwDplLLiQqrxJt+fhwJzJj9+BhFn62mxGR8k21U3L0+
+        ltsKNt39zSzJTFIhllMemGhEzMgbtRVmzc/k3eWY4vXUflEXiQX3J58+j+egjxuqPmHxb4hZWg6a
+        HHJ10QN2L+aOYYx+9Q4t8UPMffco6VqQRMm8J5c//KgRRlsGK6V3CuB82mHxg5SlX4FXITrow+5+
+        f6KPsttQzj3PYdfkjILgdRfMv3fBwr+nDJZ6xZb+RDh/wumlLH4KVR718AfflLe6cxkhk1fOxFeu
+        UN3ilk51a6H5vNEpWq82dzwo0UMfk/GZgTccL2T7CL/hdJ62S3NIspgR61H5p7+WFl1DDpNXhH/y
+        g/Np9zuveaM0Wg2i2O+o7PoDml7Pu4+8SToQjL0Rze4hnNACDhj4wm3pZPoCCGCsCAnRqHexYnTQ
+        FnVP9GrlloOoxhwUn8uebMPnDo2re/6FDB4GFpb+VlNdSgGiAfm45jf7cuzOGf/rb1Au+Drhwk/p
+        rx9HrO6UoxF13+cPb/HQkbyk1S26Qb8/n3G+PiOdXVoJozaPDoRwqqUPTez7UIisY4tea1kdexw4
+        u5VJwR2h7AgRNFj8DqYe9yedfoPrCwoDbBKWXfTHD0Li+ZXi6q190TAGwk3eeLFEML8rwoVvaHAq
+        womY5ecY9t055sEVGkbchQ9PvP/5w1cxH+tRO73OIwW/WKXEv0d+OXi6aKMlX8jO8H00PN9rC5b9
+        s5/f1vMbp0blCAK5npQwHc1csRWZ/zj0Q++lNz5GyoNw5UL68/8G7WupaC7iF4aiCVtmnmQXzo3/
+        +NOvZs8kAeRtMaGKAk80rcH7QjsRnRafPQ1HaJ4uiH64psRUuXDab+UvPBI5xrlYeOW0Br1GWDUZ
+        lU+hGfI3edOhn770NT5peaMwRFjqNeYXf4TH9lX+8Rm88fimpIOJeKSdnZq5zqZBbKOfDbSsz7zQ
+        UsvNkftmoJcXly39q/JbXmUDvVsw2X45n1nuJg3+/t0K+O9//PXXf/5uGFT1PXsvFwP6bOz/+T9X
+        Bf55vV//yfPCP5nw5yYC7a559ve//n0J4e+mraum/799/co+3d//+kvi/33f4O++7q/v/zXwj2W9
+        //7H/wMAAP//AwBEtzLu5SAAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc63ad93ee0fc-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:17 GMT
+      Function-Execution-Id:
+      - pbmeiblrqfms
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '36'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 291f85b7147806b14c87634bd0b0395f;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - b12233120f7ebfb311f5076990440c22
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "a repetitive and meaningless string of words commonly used as
+      a placeholder in design and publishing.", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '178'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1Sa246zyrKl79dTTM1beskYAxnMOxswYE6JAZ9arZaxMQaMOWYCubXffQv/rd3d
+        NyUVpqgqMnLEGF/kf/zrr7/+rpMifQx///PX35+8H/7+H8u15324//3PX//zX3/99ddf//H7+v/d
+        mVZJ+nzm3+x3++/D/PtMp7//+Yv/7yv/96Z//vo79PotTZ8CQ+SSti3Y50OJTUc/MaKOfYyULMyo
+        150uzthvNB+J8YyoI2hTMUdXPYWvYFRk3hzKiKXYasF89Tdf1Fe7Yty7Ywg2PhjYeZyrbgjddwub
+        bI7xgX1P3ayO/RlptdbRrXJv0JyeNgFo6/ZLncgNnME03yWsmPTxp4sZo4mkXxmcR3mkT6qSbixb
+        X0Dlhk/8QmhttBnETQ+H4vSiarPyNfIRrAAepu4TZpztbh1TkcAmcHJq7LW2mAzJVKHh89wP5K3M
+        RuRnIjiP6uhLl4E4U+5aOZQ8/8GmYikFjextpRw5Mcf3SqRsFLWgUp7QX6l/aTZRZ/j9LAdWVxGl
+        3sdoWmWNDPe+leg+XKlstHn1it71KvWR2zvRGNidDgEOdGq+nMqZ5IICzGbHCDpL36LfV2dAK908
+        k/WqcorpvhF4OOwslx7796UbL7tND9mGGzC2TD1iqzMqkWKmBLvXb9uNfSFUcMq5hjrU2BTUFD4A
+        meDcfGkzqc70yBMXmh154q1zVrXNR34K6DSNJj2tjQqNG0vtocHIIoqcK0l7SfNW2XvdmsBr07NG
+        W2sA93bzweqy/gP9KDZ4hefh8+7MnCYhYaXk4VXFuzY1u3rlSTxcFN/1h9faivoO2yrEhXUnUW9X
+        WiejbFRe/VmgWj1etBGh2AXmGC09bLPaIbt1moIkfiZfure1xuwg4OF7Dzms3lU7oV7S2BCN8Qkn
+        S739qafhxmzqH6XRmXnj2sOxMBDemV/DYbRtYsif5QbHMyJo2ESfHBpXCokcTq+C0ochQPnaNj6o
+        21M048waoXx6J+o2Oy0iU/zVwfKGmAhZ9tTm5HZIEVNkSrhNkbJZqsde8bHK+xM4IZvv09ZVnrT3
+        cfTIbDZNissD2mgDEfivl4yahmXYmJDj7VsbksklrEe725fS3dbbRMPaHmM4WZcC+8fDXDS1ZQbS
+        57M5Uz3amQmTUTbD2RnvOGxWxJkMN+nhuH+usOd3oTa8pFZE9mNWsXbJMsaCWeRBbzofO1Q4act6
+        kxVCwsbnc98ranrKfCWowhzrVZcXk2k2JehpeiXo8KjRRAf7CnapqFRbP6/JXMtaDKOyDvC+e6GI
+        FOHkg7auv2R+hj2a80txBsUIXezz47GgfcBlIInfiUh9i1jddLIMj9fRw7uCP2vzgRouuMWVo/48
+        7IoNOEWonN/lGZsvx3A+z2djwJ3WFD/jRCp6cXOzkVt+Mrx13VUx1BYO4N2XBj3HQcBm4HdbNHzK
+        GZsxd0AT+75dOIWXDT60cZH0D3tSod3lPbWF/dkZcnebwyw/RYxjft/NQXy4olvOX7BreRNjhjrc
+        kdnlO3zo9IwNtjFn4Kp3D+M6zdBoXa0KSkEzyarcdYyk482WSfQdCKB4FTHV8isIlGCFt9PT0Bgn
+        SwRJ0bWmtqGn0bD7HDLwJ0HGO5ZOyYBShUfIFAKsumLssD4QMjA5JPz0WZtFKXeV4cxiImd7tVu3
+        +zGEqIgdotxRGjGn2WTIWV81AnO87samHFrAY/r1uz6yI/bTz7c2nzDWN2/Ws3iyFVPMHXq4PdcF
+        jbidDYs+YH9LJUZOwvsKWcsV/sppqcYGcdVD2tKIXBf9Z7R4GODdfInUcsU745yNGXo+zIq6lkKj
+        ZX1CtIqJ5UvfS5Owat31cB82iS+E3hYNoRQDFI1LsLMPH9GcmbWIXPXq+VwstA6bd5KBniHZE+7S
+        bBJyoL4LzYpeiKyVUkQ8azJkJG52vqB8Lw65kY8O4qHc07ukjs6sXYcKrda9hL04uXWz//y0MK7q
+        kkYP7YRGEZwAmZwk4H0HY8QGV7/DIbVO1FllY0I6zr/+9MsPz/MXTV6q+vJ7mGtq7ULbYfzNGuVv
+        eQyxtujb1HI5B3KXCPQQBZIzXQs7hHetpHRn36OufcI1QwSSlNpLfyGFfiby+pyP9BDbRTSZfCyD
+        h90PDo0rdaauKl2IFXvAungd0DjMNwOtj0OFsTABqwOuaGFfPb/Yq/OGkcfO7n/9CJtP/+yw3Tes
+        IFjr26X+tWR+XcO7ImZlgfFIBoeYzsYCixUB9fI5j6b1eL5D5XcmPgglLeZL2AWylPuGzzIvT+ah
+        zkdQ5IDRx/XbFk1x+wrgeCP7+Qk0TlO7RbcT71FbyB2HcMD5aOlf1FQ+czHtr4khay++w94RxcU0
+        1tcAXvxb8Dd2LCaDS1CPdoHv+4zd62goHzbIy3rgm5cd2dxxxhU65+JTz0g+bPTlugRQ1yfq4u3L
+        mV/7/Qy7OvHINpIENh7nPoTmmek43RQcInttB6AcAhU/bpdaY8WUtahokwDvjvpeY6CnW2jd4U1x
+        q6NlPxwsGC3tRPerqivm+xNV0N84REb/QIvxnsWtsloTCfsvVqDhxY+jwgr5gQ0xLlmzHtM7gJyW
+        2Eifnsbsx9WFR6xf6a6KkdYP802HWy5cqBvZTjGIPrsi8nR31LckI5pu6dWGLj/1BJUSimpvde+B
+        20VHwp0qsxiX7xFb9RoNkmiPNsnYtehuteHix4yC4CvKxOx5+f7xc2zyxhTO0nRa6g8j6jSrDITs
+        FGHNNUJn+n6TQLbU/EXC7+ugraXztoUzV75olHlqNHZY3cJDEiM/D0JN45OzeIfNedzi+Hxs2Kx2
+        siuqjxtP3o+SsT6wCx2Ekdv7pXURnD7yK0sWD9Uem6M4RdOmki304WseeyohybSbLBEOif3CunUR
+        tNlOYwLd08qp+5aB9U4RiAq9ega25KjrPnz8KJGx0weCtNWBDc/jmygcfgL11f7ASD0LhkwnVaT2
+        vS4KcvUmC4mq8qX7dJa18ZVvezFBYeX34DcdE8ujAbEXp/TJq9duWvRVVDdbmbqfb5yMamK06NeP
+        VTiQaLQzZURaurv4ZysanFFwQUBGagh+Jj8xmk9qzUNUZgPFhNsX/Fq0XDBdc/KF2bSi6ezMFVTT
+        y8PbmO20zXrPW+hisBfpInfUFr3zIRUyRD0O82yq+v0VdulVovvcbbR+RYYZ8as8pHY/F6jfbjYZ
+        fHY8xfrIpazru+sVtl3J0/1Hyjqm5tkD+FUW0v0qKpyZrbQ7vJ7FlVqZdHD49ZOcYfEDfn7JP8mc
+        HMGF+zvVqX4o627mHmoIybfhfFlSA2cunIKD7zPkCb83o25o7PaODgKYeKu9OId5ntFC882vf96f
+        kEn+GRa/hLfnG0Kj0uY9PKxwJMvzNBbMI4+03c4nX8VSunpdshKy5+mLPRHyoufHGSA3yjtZ7/dU
+        GxJyL+X+dJjobuxKbZgUXQC5uwlUrzq14EflfQfX+6j+FN2ViPn4PYO6xhWRldfe2bBmDmGpD399
+        yEttRrpcIVpuCd7zzRFNm+iTwaqRjuSdHN/JyK8HA9YmDenh3lrOmEaVC/i0fpPvvNeY0Fe4RgeB
+        M6nFF3qyDq/N9udfKOacjo2ZsA4Bs8eTGnp16oQqZy1kA3fzZZPs0UicjQCKEbjU1I9WQc+Cy4N0
+        uMZ0y9+3znTQL3ewxuJOf36B5urdh5JpR7IpnVEbf/txe6zeWKMBYv1jfOnooFxmnx85DvXpHaWQ
+        GJ33p//MwZYf4TtFD6w+chqR46i5UCXNcckbZdK6Xueig/0eCO8dtw6DS94q/TwPRHYJZuybv3S0
+        junDV7BYdmMZ1Bao/E7H5nQyoklRwhFUxOt4y9lmMr2kVoYhKVOsMmnH2FqCHiINIbqVnxRN1uNs
+        QdPmPjauwwf14SBbaMlP+EW4fTeJ+XaLtmnZYt3UtWK9qWQbfBu3PtB37cxhd9PRGZiDjQtLitmz
+        Jh1x6fFO9+sbjXqHXkPpSKKR1MnDdmbgD1tZLMobNncx6Uj7vKe/POX//NPMBbYM267i/bmiXTGH
+        wcaHbnJsvJ8PLprCa6PCsRQxtYTDy2HGSd6i/Rxh0qnzJVr8Rymbah/4c69yzuhnfo+GXeVQdY/u
+        DqU0eQBXR8QXAxVFw6s6h1AJwYUaSRZp086mLdrEXE91vjtHs30xH4g8/Z3fpT2HCHbBRlqqXSj2
+        v402k8N5RsjmDRqtn2Iyc8C5yFd2lBp7Vmvjs+s5yFR7xoeXIkeUv21n5be/3dd9w/rwLc9wqE4n
+        apyeRTRb91sNUvp5EvHeu9302oouYJY+sX98JM680rUc2vOwpo6G+2ge+48A3FvWSF+UetJvN6tc
+        /vkVN79MiNw/loBOyKn/5L1RXdc53EyV+mU06WwkpkdQn457rJfHZ9FHT6tFQ1KlZHTdVTeYKLeU
+        Je9Q/LzcE7bkcTjGx6dfb1hVjNLrfkXNTH1qs8+kTR/gRBSTE6baJduicS91FZStcKQeFvVuYp4Z
+        g7J+NT7BN8cZo6dV//n/l/7fjWklC6BhTyLK4o+W+jLAGt93avIfi/H371tEyhA0eKmvhJrCwEFw
+        eel41/l7ZyxUr5WL6xfIcez0RW+dO0rog6P7d/hyyOFQW7B6iQoNwzqJSNVa4i9P4D1tvogtflz5
+        vS9jurSInsL1DAuPwJeXU2kTY3WFpD3ryfeyuy1YIRRg+qQZ9qaV1Y1XpzZkZQgbItSXtzMnt10K
+        9YYcCMIvsevuVvuAAL06vOTPZO7cmlPYWQxJAoPm8Mv6oQPjjliXPlk0vB/yFhq/r/B2d9iz+ec3
+        PS85khG1efKpSZ2hKUldX9pmtTbr+BBD/mEb0rhjHM3t2fPhRGGmu/69KRa9LeF05U7UAhYUUzdM
+        DxSEjUykxa9OVtFdUXrKberTbat1wfUMYF7QjVrJ4d0xt7+3IA+ejY0waxLyXDsB4Hvd+eLyvBFb
+        GFD6HA70sNUip7k5To6WfE693TthTFQ2MzwN+Un12ZkidrzPBggK+NSGMCzmb6jaaPEvNI6mEk2n
+        iwQ//kPNuHsn0+XL3+FiX02cVtssWvyJDKudmZHv5np2RlLdCAqKoP+tJxvNAzFkfNq8fTm7ds5U
+        9PBAz0Cc/NV4FLUu948VcPgFSx7QolF6hVe02u2zZT9qybq2zBDdw7byP6BljN7ihoeTpBiYbIoU
+        zdHVfUBfjzd8M6N1Mn7jzkfaS+j+8IZv0BXlLz9hL7JMrU/vLEVLnqXYt2ONXG5iBtO5U31opgyN
+        H/F9RpL52dJbaZrOJk7XFsr21pJf31Ey8UkjiMP3auCrl58TqtkNgeNZn0j52E0R8zy/BpXXdOqi
+        +BVRjpUPOHFjQLVPFnejSqIAXrth8nnx6rFpdwQR7tzDw5fPVS1YqKLzn/VzcqFLBnP7iOV3ML+w
+        qom2M9VJJAO7yRbJKT0lTXDeyyit0cqfe7C0dVmrsbL0S3/cSUXSoukjw+KP/fFRXZNZHFoeKetn
+        Q7hSG6PxqocCiIT5PqxJ2dVHacrBuyQff+Gfyex6nQ/5Z9rQw1O2i/HMX2OktupIJImftUUveOQ0
+        ZULTFyvYfEJJBrBu7mSzm7Ri3VWlr7jVladGotQOu8VvQRE2l9EX4Yy6eaJbUHhjT8nKMsuoGy8x
+        +ZNn/bSaIurFiYj0Ou3J7J0abRw6R5CXv5dwRynQ5kI/93L93V/8ecmP46d/g/LRWg1rh4Oosay6
+        xrDS92e6e5gcar82L8IIGvijLOtoSudT+4ef2toxYLO7KwQI1sbWV1YPM+k+K5OTzsYqINxTiBir
+        rPGONu1hTbWTICXjuQ44KHq/xOaYQEJz5IooQM+O7u5vjbFIQDJwRHTp063ziK3nbwrq2quwKjVN
+        NDhfksJKQAmZOv/jUNmsfYi4YktxOTURsZW6R4te+qsnjxPigdQiP/Y4n7/5Gtr8eOHSj4k85O9o
+        ErhRVtbdIFFsy8fu51fkX16Ky6NSjMXpHgJ0jUH9OtsnG0s66KBv10/svzQj2aR424Ic4B3WHtpp
+        4T9yDkXjE19ZY8cR87t+RZ/VuiHrsvcdFnRdibqZS0mPn7w2//h0ddsohCZxG42P8aKD3j1yvxAu
+        edIf3IMPbZKvfK0KQmd8p1wOYq/I2J802WkkVPVAnOuA1T2StfZXHy73Ydi60LD4oHTNy9O5Uak3
+        rEGbxrezhRMA+JwlGcns7jpBkgds48VfMbZLIld8ITvG2pLnpuTrxSiwU5nseRcY45+zCPaXE7HZ
+        id+kRrzPAT/nBzIJhLFxx7wrLDx+yQNW0Qt7WqGf3jgYhm7SBq5HfEbWZF3f9sUkna0aPkJqEU7t
+        D6jl5WMIuHpEdBfdn8n4e36xd02sS5aTTNE2DyFPpoJuY03r1nYoyeBVWCM8u2psIhNkv/1IbfGD
+        nC6eDzOAWb+wS76cRtxYfKDw0sf4eTsVBf0YpwDFl/P8yz/FvNcOHBrkCfkS2umFALevBd/kmS1+
+        f2Is1XYhzBC5ZO2Ij2gWzokNpapmdLcz38n0GroMbYe7hXdLnmh/+a5dvas/8way6XAvL7ztx1OS
+        eeHHaLUXW/wc1uAs+7lH57JyFz4jaFOdNzb8eOB58LioUT17/OklxkEradPus8vgzq8lX+FwjGbz
+        5Yzw/UbWMHSzq/EdUuIfjyKr3TNkk284DxnTNU/dciOgNZEO88+P4r2rNk5Lgl795R+88Lmk15q3
+        Dcf9a0Xuq5xns1GsRbRvdUzN4zFMev3Y3mHg7wHeq9bJmeB95eRvr4cYd0RzNqrll7/PyfQoGZok
+        +xDIix7SvRHuus37fgVY9Irq7jsv5uh17H+8j+5GHzvjj8cuPP+X17op3x4s9OOn6zflnZl72KH8
+        49NWJjXO2LCtDRuTy31l4V39lD7vcNfWFtbcwnSm7F1a0Lsw4aMxgDP4hpaCCFebnjvZQXR0nmf5
+        W0YhVU2rL0apu82yrqd7rGrJSVv4d4WWesc7/VKg+f7ZCr/9SM3OathsT80ZHpIc+S/f5p3xLS35
+        ev218CF4Oqj18ssMv36rSTZFk+30NTqO+z0Rdaw7k2m+K3np11TPuU5jmBt9KIWdSf/wD1RpOsyT
+        cSEcCfpiejTZQzEbMvx4dzcEuReAonYl1W5FwCZJgBJuey/Bv/20zA/OUG/6w+IHpeLn/+A8rAZ/
+        fp2go3BpWxhMRfC/u0nr1kRhIgTxyyfzY1Um7KzqIUpRvKf6I62S+SAkKYpvtrHk3doZzzcuhYVf
+        4p2cOMmsfS0dOayk1Argk5DOzUD5Jq+MIO+wTaipIBfVqXih5uKH6GYMHsqmmG2fX3jC9OM36qBW
+        VD/xMeqUUFzmMygkf/I4c1RBWerFX3O3mza6ui5KLr6fyWbh+zPOtqNydI0nNZf+uui3AVnjYDIH
+        YaHNmWScwSxRQapEqbVJsneh0k4xop6FbMaH9yETfzzf49VrMeK8EdAvrxs+O7Iu6+zFn8kTtryV
+        Ey3zUffPPG+/32ONn9Ln9Zc3STvs+2T86Xkw6zY2/R1GIz3V7p+876OhS0Zyv59hvwvThV/fonq/
+        HUWlmBKCt0ETF+M3LlxYZ4Xur9WP7Uzqfp3BRlQirL+nazGsPg8VLu/rx+c1fqexn18MKYqIYI2q
+        8+fnHyxa+5NtOk6HinwLxu3YL++nKOYsqkN0MabXn7y65DEeHqK+IkKYHaLN6Dxj6Epnu/C0hi35
+        2QAhLTi6u/N9xLTRnOG5QT7JUKtGC//XIUFBReB2qZ0/9WlX4xmbsd8nTOlfLoRjbtAfH+6pmlTg
+        Pq4ZTqwVYy2IzIL+Mxb48bpv0LC5Xmo0XR9nUhSjp81XT7IhF64NQRD4zvS5XAWU06uD9/t139Hs
+        penADYboM7cwNTZEtxZ5I75gj6pk8Y8sVpb5pr/inA7N6ljGIIAt//i3Ns6ZmMFX0Cs/qYwBLX40
+        hCQODvjCzXttDjfBQwlmw6aenD+Tn1/7kz+2+s2KBNNZ2bCKe4tqy7yP5Wroyks/wP6luSStfcHp
+        b57yh+cwGdUzDOZKoLaM827+fIdRVrrniVrBK4ga8T7PMMsvEe/jz5NNXdW7UN3WCmH37YeN0XNb
+        Q73VZcJN2l2beeaqv3kBjXDzYOTH58nkN8s88RLRFDFO+ft3KuA///XXX//rd8Kgqp/pZzkYMKTT
+        8O//Pirw7/vz/m+eF/5NhT8nEUh/z9K///k/hxD+brq6aob/PdRl+u3//uevNfpz3ODvoR7un//3
+        +r+W3/af//ovAAAA//8DAEwqicXjIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc63dfc49e259-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:23 GMT
+      Function-Execution-Id:
+      - pbmexn5kc8di
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '28'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 7793eb63c23999a96303cbe39038fc6c
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - ad8d4f3d387595b6652d71076b51541a
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "Sample text", "model": "text-embedding-ada-002", "encoding_format":
+      "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '88'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWQ+zvJal78+v+PTd0kcBkuDNuWMKYbQZMkCr1QoZSEhIwmADLtV/b5H3qLrq
+        JlIIUjDeXnutx/6Pf/z119+forqe+7//9dffr0fX//2/5muXU3/6+19//e9//PXXX3/9x+/zf9x5
+        rYvr5fJ4l7/bfz8+3pfr+Pe//hL/68r/v+lff/3tJ8svlV+lXVErX4hr86DtGZaqBPGXTM4QWJct
+        s1/uuu0vFk4A2lFgeIV35sSNKVDv9kVllpCZ/rjpGwtlO8ci2rmTUy7XSbCWZeIRLCirli3MM0b7
+        PfhML9vU77yaOzCpzgOPsfou+GDZA7CrHDJHua5Qv45FCvbHrQjWvhQNGcoSWCcSZ3jbaQUv3CiA
+        nTFe2MY28nYSat1Rq3y5/z1v1V9uJwv2z/uR+A/liKZFfTJgWXzvzC49K+2bLCnR/uaHVPLMizko
+        1k2D91o6kHBEpj/4MRzQN9QsFiz2qfldv60TbBdhRnDKGj7hNw1QGdoRC4TjvXjbffNAephwWo63
+        O2KW8T1Bp9Vbps/j+zLxLkIpFwyrq0+bcjtLRNh+l4QuHgVBg2IdNbQdPiExNL9GU+fbDvgfMmF5
+        v2mrfpOdMliJQc7O7+jedjsqRLC5BDXxZU30W0r3ETwPxCZ69Pm0HEumAg4qETFu6ZeP2w/p0Jb5
+        HgnM7FJMW+mVwcUtMZVraZPKlmQ2QKiyYyGL7uh9ML5n1O2FiDl+sm2ZXi4aUGrjToLypVV8k+kC
+        rPKrTSwhq0xO3a8HmZiURGtzoWC26XtwYmmDl9Y3TCczp6BM0/XK7O+98Tm86xoJzD/QdUDkdJqM
+        +05tfK5QNSlIym3TdGBzVFpmfV/LdmijlQDv3WlBlRgZqZzXrgam1gQk1E3bHA99noAYFicSViL4
+        v/cJJ9mTWfgJo2Jw0AhQeKZK9PU2bsdHua8BkpISMrpFxadbdUZrt34wa9Hf+RD2uQHvsrZJeBKr
+        ontklQMPMROwhIuw7epbvoKitwmWniGupoUkX8Gj8oa5JH6mPMjfAXSLmBJn88oKjozvE4510ROi
+        q006LNDkge2YWyyH1scfev9aQxIt9uS33kbZP4iQtG3OsJe9zPHzvgSQFG+faKfs4Y9Ln1F4G0hl
+        ni271XCBdPjNH9nGpoWGY/QxYL3Ybim9jSPqdHcMYBBvhCrlF5tjCr4F/uXek2BCRTudwTwspLI5
+        Mkf0LN7ujayGaPgQsg+okE6b18oC/dH7WNF8p+XoOEZIWq/fzF4k25Rn6tZAEnN3bF4/5vS5VRgS
+        DW3pWrIZp/6xNODj7zKs7lyj4H5+2MFCo2/mj4uhGvlr0KBE4wqL55AWTe2uJ3CjRUpRsuxTniCl
+        Af74Osze7seKunXToftqU5CLKvQV9d/BFV3dbsVsnNt89G66A9LuFrGNZ6o+7dD3g3ymMUbW3s1k
+        phGVsPH7J3Hkyz4tlXxZK5cw35Pt+tGjLxUjAVarTUl86FaoaaLyAUXxDvFKkd10WYjaVfXzpsbi
+        C91NHpcXAX2X8ovoWNm3PImNEwxuQ/GiGnA1BMfhqpyn1iTGs2Gc5+pNAdDNjhijtU2HY1Qa6jq8
+        fVkgxldzUlEmgkA0hfjdlxY8rk82CC5d/PSM80wlBir9N2Z6v/HaUarz4bf+mKVvfF+k5cJBC3f9
+        xamcPfhwMz4iPK5QE/MWm3/qB9Urt6HiQf6kDbyGBB6LrUG2G6Ezh7GPPciH2iTaa9Okw0HyE5Dl
+        0CNG/EyrCW6ig3YfItKJ6vuKl17RAckfPtMeRtZ2bpzUcLxvJzouR+bzdbey4fRdMGaORlm9lVh1
+        FLl2gGz226ToQ8k/w2cQBeJt7g3/ip5qoVNEb8TcOFLapGJsw+KWTsza2LjtVuK9AdbnOXNr/Wj2
+        zB2falc2e7ZZJltzet9OB4U4uku0UPDa0RUzEaY6PjIHg+CPRHoFUL7FihF6kdHrV39BSc9su4i0
+        djnPjzLXE9EFySqGm1HK6lcuRiqt66Lg255nUK+bDqPFMUd8QYMr2pdNxBzhdi6mvefVoG9hRbQq
+        O/Fhri8Y3A/F68UkFr17XSWKL2ZrpkUNSf/0s9/8m9/3tRhqy7bhsjA45ZZntlNwXK3QWlI2f/oj
+        /xhRAxfxwMj2ZJz8YUVfJQhDk8/6Nlb9PB71TQyJzHprct1ngLwwkYjnBIHPOXI8pbftjvhV/ESf
+        MHMPkK/5huiPzCg+iRh9YGudVnRSzHPFhZ4/QUKHAk9DJ/PR6vMAsK4/iFvtk2LIpN5Ai3KQ2OmK
+        CpO+3I8CEvN3mH/i8zwfyQ7ebeSxTH+KiIe3agerBztioZGbaqRiJkD9GO94mPWtu7+FDiWHNMJC
+        aNop/emP1dsec5djhMZXjc7osTsMxOhNk4sXKAaFH1cSI9I9MMdHrcngRMOXmMv+XrEsO63gGxoW
+        0d/0WQ1uuTQg9M+UHCSkV/SE7jV4/dEkzuDe04GCIcC1/CRkW+UL/pHNLoNFkbXEm/RjwZS3JYIV
+        IYva/aOvaIuyCZIkc/E1MYqKD7dTjdbrMcBIMApz6GJdRGznuOTyDDo+vo0sUOpJYrQ/XQ5p/6tP
+        d3pUzLgIvjnRuPCgZYbMglF1EXevKwrV8/3BpRUt+WTXjqDglovE0erKpIs60eCbnDDdZYHHRyOG
+        BzpMJ4+ZC/Zph0eyXMHx4pxJaGQWf2WmMaDjdkjZtZa25jRl7mpdRZ+U+Y73SulwLD14beUnva0f
+        pJ3KPi6hUYuMeM1RQ3Qn3gHO66vGDDT4aPDk2xMZN63/07/6jbGWwdQ+AbkdslcxgjEZsLpOOkYX
+        ZFRUkPoaXVahTGb9b8tlHghInnYm5fp2nJ9fLIH2AWP2+rmrvoz2HSxs7UFcP9I4f5XLCTrx3dDh
+        pO9NvjB3gWpTKMk5vj3TT1Y7NbLat4PZxzXQrH8yLA72wELzIFd9Kt9klLOthlnaP/3+dnsAXJlP
+        8EKLCpN7pjRBOGUOcy+LyB+C904B/FZ6Zl0eoTk8rysHjGQtESu8GVXf9sj602+suX+1Dg0i2KhH
+        gz63I2ung5deQReTgoRaK1V90zcBDMl6gRfNmaec3XQKaVJzKsalbTJ0HBM4olEmluOW6ZRH4w5G
+        f3ciOnhVwfANMDI+qUA/p6zi48LsGng96iUje7Ou3o9aT8BgNiL4cr0X8/OvkNVbHjGWGSq6e5ZE
+        IDxvCdMf2ohm/26j90vRmf0q67azvEqGJsSUOQux8Idbn9vQR/KCLg/52x/jOm+Qv7BVLDquVvQX
+        KjzQz+9o1/xVjXavADKe2ZJ+6cn3uVS7Bwi+6IqF+81C7RJNE2A1kolNjlk72Shr4NA+BOJuqrhi
+        7OZ260V7XeNF59Upv4pNgH7+b3nQD+1w9FoFAu2p4eUiKtse9XGGdKNRmXPVZd7tclojXF/WzHTL
+        FxpyP/yg55s6GLT+nA5vz8OKLigxM8/1wxxM7ySguZ4x19zSbG8it5BzsJ+UdZ6ddvP40QJV21nv
+        17w81yiActttMVBl5XOl1wBkkg5zPznwaUV7gKA4JHQYHZGPeyPzYCM6GtvkjsSbU50rwI2yY5tn
+        SKshvTkCBFqtsS0+ar7M++YKxDFdul6592qo8/2EDMd/0DWJn8Xw8VIL4aN4I3qxC/0pBEmBaL2M
+        2TZqxYI965ODSjXomJks22qY+6WSfcuQ6Vmy8On8/0rX7nLmhk/J51mWrGDUPgdMh3CouGlkJdoX
+        kU2Sr1EW37u0y5AiW4zgIRxaNnnptCLr5o0XnK/9ocrAQGaOzrg/nBNES2NyQPO/e6K/zKodTrE7
+        KOQq2kRPUG4OeXnZof3QXSmXMwOxbc9PgFT7gFdm/PQHtXY6SA5xxEhuef5nHq/67DWTBLFzLLia
+        pQaYET0Rq4syNDQoOkBS76/MOXeZPy7rpgHL9kYKrj0Ug+EZFqQr05vra6ymnTt2UD+jirneOuVD
+        i74BwoeixXXQHVs69XGtBLV2JJoib1uq5wcb5vxCTCw7Ph/o0gB83wzM3z9oNY6iQkG2LUowoe9i
+        /OXFWW/oevfxioGbxkcNl1OMYee7Zn/sHw7s1JdKr9oXozHLkjOsJv5i5ub2KKZCJgG8rcNIAvda
+        IhaXe4BbcZ6I09usGub8h+b+xKKm6CoaZVUJBzmN8cvdtAUPPG9CoytlrNBcnUtV7Blo7tf4NcIT
+        TWq5MdDGeDx++mZOijgJIJS1T/Q63/CprXVbMYfpQx/562iOW7Oo0fpSLal4FBXzHtweKzXf7SjD
+        /uHAJ4PKH2VzwfVPP/0pvbkZOhvl+9/1p7sjVrWjfGbOfkHQeAC1g/l3on3tntPJ+B6Q9chsZvYL
+        ivo7ikpUrz8d0f3YaLmM7goIkrCjwrf8FK2fXw9gX5WE/ep/wNkJK+G7M1mhZFa7TND0UYiYXAkx
+        k6/J1ffijAZjOTJjtN7p1ERlqcYRvTCyFM/V8DSfB3RW91vK5jw++uK3A129Xej6tqOcrsQ8gFq9
+        c+bja15MgvSq4fk4hcwWcZKO77d1UE67d02n8tsVzHfHFWyKccJCMeCUd1krA38vTKJn387vl+Bj
+        1PfGBrNt2rU86x81GDejx0O661B/zamIgnwZzbyjLEa15x6Ux2E/55GMszvSbPQ9xHtGnC/x6fM6
+        1LDPlwleXk9exYNbcoW4yO54+XTv5hCZxQnqacloV4aRSX/+WBCrkpn31zGl2/JCgdNJY8a83qcQ
+        1H/7BS+N7v74fVMbXktVo4/FSIrlnPegOIQWs8Lbo2KzPkP2xAnx71D74ymD4MdLmP6mVvUnnz/l
+        eMesd1wVtJHODbIOeIHv/carBkOcDqBotTfnZyuV9fxqIbZdGHShRcgcN6pdgsEsRJXX+4bY8U3P
+        qL8dgYIYC2YvlZcPuudnnW38DKHxx1tM4rtUzL1zO+ZZtUOraXwRq14nfETJ5vlHj+O5voaupAlS
+        LS9gBB/vfAqNb6BcDBYz2z9I5iBfVxjNfoC+Vh+35ULWruB0ME7MEM5D1cZ1YsHxcLwxvdalor+j
+        7AHZVlApWvZmIW99bCBZoy9GIBzQcE/exto3eIHRO/mk3IxFAey8PjKiv3LE7f5RAlyC6Y/+TF25
+        l+GSbU7MnP00f8XFDp5krzBXuOzboSmDEqpc2hPjGD/QGIjTU3VytSV0CKN2PGXizMv4hZgNXMzv
+        slxmyly/xM2+PaKBkR2U8m7WeDGWTjXmZvoB/SqbOKYnt6CsRh3E6KHShynm7bBFd1ud64NpXztE
+        Eok+gTLzDYrm9UGdOpfR7MeJ9zUMn1vJRkbkwc94Zb3rivc0yMAwlm8KZNqh3/uGWHZEQo6H5ewv
+        4g8U0zUnPjocUs6R5qgXo4+Jx2ldTYZ4V+D8BoEZvnTxh7VnJIi+FREPVaZwBn0uQ1Q+debM/qiX
+        0P0K+lZY0eecd7kJfQAbdW8Q114NRfOmwgALf3fBw40+i2mXXx107HFDl/V5rIby/ZLhhiqNbI/H
+        FWI/nlNOjw/78bZhf2soKqNFRtdGeeOsEJ0zKlXcMbfqDd7bpkcheVyPzE5OXjqk4rdEsBW/xMXK
+        Mh2u0DWwdTtOdJLYJhdM/wDQxxpz4vei4J9YtdBeNnKqdi8N8Rr8J4r9Q8q8SV8WMz87QLNd8X/z
+        p17UHj8/SCELuopHUt+gfsoIM3qzQpPmloOK69sarybRSKeKBt6vv1PI723Komgs/+gfD+9uwT9G
+        1ijZM0hwKSxbk21AtiG62QLl5ftVTY33PIG0Rm8WhpvQ7G+SWaI5f/7pv+z4rq8w5w3i3Kjtj/ve
+        OUGXL490dMiunTJp94RgV+1ZMD/vzIsDNG4gJjOPQp+5f4BsvTvM5zz3aWvng4zd7st81XLTMfXf
+        T0TWnzeVVXiZbLq1V+RotMDLbdqg6STJux9fYtYL3X32krdXcBpzzXz9qrUDrXkCbOe5+Df+YStJ
+        MqxRoM2ZTStEjfY7hJcCwu9J/vpjFK1t1Drbyy8vFiPNQ0dZuOhL5UMRIrSPJQ11uxumuSkJLbu4
+        I6CZNzHfdZbm8FCPiQJb+Yvvx/RbcanWD3/4aOha35Zr/s1WZj3B9W1Kq2FKrvjHi6gQWy4fCcrO
+        MPtZ4soFbsel/+4A4o3C9OVIzEHsJwW+o/7ByjG2quWc31Fj1CuMikgvJqHcK+vZf7PNukYFLZBy
+        RspGSLFwOHUm38H5pCyPw4mFW/o2Z32MIJRjQvbwDc3uod4SNKKrTNFL/VY06LUnoDcNqXS9ZubE
+        4qcB8/oh2GqmYkrMrlMuFk6pgPWVyRxqRXAX8Y42tvxtuRiVAzD3apFAhoXfFHUzATXOF+Id1juT
+        kXJjAxOjFwvyu1+MeY80kMjWppJuPlPmuXcNvhoKZj1QfzyoRvfVtsDru6Ejvqu5rJ7Er0jC0neL
+        UZIEjL4XO2FOKASp/Oh5AqeNEBCtNsFsr54nQu3omBHSlW1XgKFAsLvvqTAtsblcxcUJHR+Pms38
+        sJiub6uENcIa0RdcnvvR/gMXLLp0fHZyW8eZeAKrXCQMO+0eTQWazhBG8opsF1FZDdf3DkD/bHd4
+        0U77aoivK2ulYjFiB9e02t/7g6OmHvAg+nXFmKmu4FCcB+bHnuAPsdlFSH1Gn9mvYC6d6av58UJM
+        PW1XjWsjisCxXg+m1/kLidfj6gHHOu/JthENc1nHHUbxs52IsfHOPuUqXoFVpyFerIIwZVjyFeV4
+        2N+Y0xS0mIbjx4O6v7yIczE3JlPgdUK6GBXM4dPOH+d+DN/p0TCyfrCq59L5vE6WcjnrQ+93e+uw
+        gqN8Q2xD19ycHj2P4JqPNsOEblO+rCsb/XiUdtDidiiTgweqAB0eNLIrJFs9nsBhe3HmRYb/4xtI
+        vu0FYiXXJafJdXiosta9qJhITzSIWYVhvdtJJN5UDHWpu05Avxx1pjVFUI03tj3BR3bWzD/XFeez
+        v/jxJkJURfPb4ZY8YTEdNuzHKwcq3ygyb+TItPF251MjnT/KzDfx0G/HYiTRBytdLh2Jqz+wz8hr
+        2P3J48FjFfvsm4QAy+R6Y1723pr9Ekysju3pw1xFNKof/0HNxHbMcdUPGjvqCz/ewHBioIr5+XUH
+        s9+hpejbVZvE3kkRqdDM/KszuzwaVmpziYBtBiK1Y6PiBhwXXbA883P2Pn4Oir0wKFZ10/b7GE1Y
+        neT9i4X17VLIFQ0c6G5+goX9pi84icoG7dHpQdfH1C8m0zMekIqeyYJwyzlr+kfz25/Bk+bbiIue
+        9AB73byYt6vNakzqRwlvJ1xhUd/45vg2ogDmPES8XV21XH0vzxDaHqc3ZYmLcQ07C/aMFCyc+T43
+        jh+sGOtRY945Opn8QqkNfH3esCBwDXPmuRg8ox7pauYVHBn3p/ocFvm8X/RIeWMoJzTXC7N69WPO
+        /fkKf/KLuWN8jCXZho5sLUamq5KOddwOaNtGJsHmjqD+Y3xtQO8uZLtGkQum12iCviYOFub8NgVG
+        tlMkWSuZqegSn/T8YKFQtQJmvZ6iyc7u3f75GzyGUKHBuvESplI90847T+24/WwpFI+TP68vnA6n
+        kgYQ39LPHz36eJB26CobBTFUGxc9elMHSjtOiXWvhmqwJBPDPUwUrI5P2eRr2JWQ9cWO+fHd99kT
+        KfSXN4nH+srvXjfdUNjEKzzNevlagh+g7+N6poMsWf4w91eQcu4TM0cal377UcJt4+AzSz7V93Nc
+        TbDfCz7zJcMo5v1XT0V1nLNIh6qazuWiBBGLmJFVEBajk4EDc34kxIqFduYtAMvQ3jNtXi9Mgf70
+        8xvzeM8+JaYnKLzgQDCQY9v99jPKcSti+bJNqulNhQlm/SY+ojYfFeProeGmLWm7OK5Rr/TOA5r+
+        6OEhN81i3o/D6ELhRZL5/f14ujr5lUWF++2JxmtOZaSGR0zlLmjToUeTBXM/JES+XdCf77M/IfbM
+        i5nZawNaUZmwoF6L7VD2dwGC7/rKDPum8NF4W/jn18kmd/Z8kMyiROhAfBLO8zOtbu4DHQ6OhJdZ
+        X8y82RPAIXFN73GtFNPUx09Qit2Z2V3QFvP+3gQfrXv8eGPL1vEzAfuZnJnVfdx05nkJyKqxpbxG
+        6+rnT6DGov9nv6P/JtdMKY/TntlzPxmy0rrC379TAf/5j7/++j+/Ewb153J9zQcD+uvY//O/jgr8
+        83Q5/VMU5X8y+c9JBNqdyuvf//r3IYS/v+2n/vb/t/88r+/u73/9Jf85bfB3/+lPr/92+R/zf/3n
+        P/4fAAAA//8DALL3VtrhIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc664f8981121-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:24 GMT
+      Function-Execution-Id:
+      - pbmefoalhwp8
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '98'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 37ebabc27cb744eaba5b13fa828bb351
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 57643378a1a524682d1e62a66d1b55aa
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "Grocery list: - Pancake mix", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '104'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6WROyPLfl/fcr3npv7a9EpoT3jklkMkFwwK6uLkBEkEGGBMip89+79Dl1uvvG
+        C6Q0yd577bXWzn/866+//u7SKs+mv//56++6HKe//8f32SOZkr//+et//uuvv/766z9+n//fm3mT
+        5o9H2Ra/139flu0jX/7+5y/uv5/835f++evvNJie2H+9X1ELP7cYftp8R2CtoXS1tuEbPsJmJtuC
+        pcMy2RMC16p4URNJTbXKouorcVm49JGezGp97bhQnvd8h63XACo2nZ03iL3bHm0ot3pr6FwI3MGr
+        TDa5PhvkpGxdsErmQu3nwkVkzzgL5h8iUpTDwmPl5uxDWgZvnM567S1hIobQVbwByX6L0wnQrATL
+        NPiE6A/IFj7QAyiPaUEdh69YmrmbETarVmCrmcNqMBYthMKljrC6/4ygp3WcyCdlINScaADG/Hm0
+        YWnEBPvbC5dOhShzgIhHgVqjXDAaQ9mG5XnvEl4KCCDd6DXAeKka3p/61Vh1EjQKI9YHCcFON5ZV
+        CjZw9PIr9bWH6y1edMght7TrtJYoZAv2CxWGLUmxfzN4jxSiNEP1fG/RojlaxOQKyBABV0HgNVG2
+        dJwUw7tmJETw9ADsjpSNiiP1FfZV/+FRTGseakNFsXsZrbQvfen6iyfa3kuz4j7ya4TXhyGS1bvd
+        h3mukwK+gkanPmy0Shj2yxXqURpQAwJUEffqiVC9vhlVi+Horc98G8Jm1xdkMxI9ndpq6GHd1AA9
+        Fl1g9WHe9rCVgIoP7vnKJn9yNvBCA5U6ClC86eCuPrT4JKGefzBAv00CXVlKoiGmpbKxMpaJcJWs
+        hXw+WDNG9RGMsLiFE3WvRpWSqIoR0JaTSrbc22RcdAMc5NnDQJtda0RjclJ7cJPACaM2RB57XB8+
+        +O230PIazOvECtAezDO+Sq0H5ja2EMSecKd+ugTG0oxxDF9HcieSDxmjj77IoZ20G1JfDltj3B36
+        M4yYq5I3TA2D9cNmlmYYnLHRm7uIbiyDgFSXB2xJAWKfX7w3G4Kwt1d21WIuRgJsIiXYfC5xtR6C
+        LoHAaGokVRlldD/vCuDvpw6bk68AFjpZBxd6ULEtXNtqOeHTCupNeaP7Nth401bN32Di3Ypige8r
+        yscvFwbCNsGHA2rYdP6opWJseA4JwaHzyJX0UDab8UI1CXLVwCTPhOCaHcn2/JgGwpkl2a4naaLq
+        bfNig9/rV6Vz2wytT1tnAhRALG82I8JuOZOUgELIIXcurnQvR1PEUtuHgCjBgHFEo2h+9lUPcU41
+        bD2EZVjBTifyd7/k7XrjsPRKGMNXnuzItlc+FcEbXYSJ7ZT4yEdvtnaceIaXBL6RoIRtxJyry4NP
+        m+3w42M0gFyGxQe5uC2wUU9iNCf62MOY6xOMLg412LH1OahodkIfW38PFu7wCiC63CcksMH3Zjso
+        S9DM7YiP+2dZraWWcNC5FRG9ebBgxLlrMfRQ/URc2pyqmXaxCt3CDLClpDtGpJfnCw8URajbil61
+        BLsnkneksLAm1beB3xOfl/3MD2gmTEU65u0iw+YNTWpoaWIs/rogJag+GyKZCQaLmIclbMpVxMel
+        dpnQVZcZAt1dMJLMOR1Y35qQK5wNtTaXms3VwfRhe/ff1EqW1/Bbr1LfLhHZ6meSTlot9lBOqYnE
+        Dx2Hib8sBXQVZ8C+5ZkGVRwHwSrd9GTzrZf1bW2uEITCEXvuU6rWy1Lkyn0wLeplXczYdNbeUNAi
+        Advxua2mLuFlyD7aDu22sRnxv/rl86dL/cw+Rkt+vV3BF98ostnL61c+iWXpqs/U4+6lN8kNK0Hl
+        HHTySdQUsJhcXVBqUMYHwEfGUq5bHtjHsiROIg9sPkSdDvP4ZFJMFlZNyZbokKv9FUnPfQhY5KMY
+        xMifEO+zz9DWDzn4nQ9G9/PVm68DOyt1jwA94LkH7Dq8ExjuGw8tZoPSOUWeCxrqCUTQ8JN9Lo9r
+        CPvk9KKGcnhXcxrJMYzu+wjx7KEMU7x/mbB/yC+MScJX05TNOby4gU0RFJN0auK9C8vb6OKbOzC2
+        mrzUQDtbXIrpUFU9aBoCtlxSYbMPKzb7s1rAjR2W1CacUS2lq/YKYNWHdNnwrua7d4rhK3jrOD83
+        mceMsg5h53gdWu9OymhsBwT84uv4MALM4OdCKS6chN4TnQF7ZH4GHkSh+HBXHW9eOjOE1ThY2AgO
+        fsRkmsSwCa2M7qdGj9bL44F++UAmf75XBOz0EaTS9Ub30ixHSxh6hVzY+p7MP3x9acWoFFKs0MfH
+        sNj89lkOx9FeMZolJ1qf7aiDqc4O9DElBliNuuLhLY01akRHaLSc+ephw6GRtC+p96pBMQu46TYb
+        tAnW1RjDRDrDsydtkcJHJth5KedDbXO/YRtM7y++eomcXVNGzfr9AWtdzBzYuVCnltR67LsfHyYr
+        wtR4lUu0ttSxQCrIFTatW1nNkF7eoPONAJvax67WvR7b8NMY2p/+OpOymJXN9XDFxoO0EWs+8Qzx
+        GlmEWx8uWxI75BV5e7L/1Cszu3MJUaRI2FmWvfHWhwJCKdhCfPye5/IotTdwgHVD8LR5epQ8CwsG
+        HVnpPuUKg0YnpYf3zs/pNz4pO/mhC9/Px0rtI4NpX6dOA5U3ycmUdtowz9dNAb58DYnZYA7spd1X
+        cI74jMjBZkyX3QZmsE42EXY2u8lbyZ50kDi6RzYH78qWebBHKGn0TPrZi6rVcacYQnlYkDItBWPp
+        tdvA9rbO33owq5nTmAnWD+9g9YEKbyqY8YbHl3ck/XnlUyZ/KhfE46SQWGbnar6RyQLf+BH5cDsZ
+        Y/tQcjA0eY793tpHNM0CH2bu6hHxmD0jlt2TEShCY1FX2pjD/Du/fbw//vjcMGe17cJdDyxSkLAz
+        vvUcK7/+ur/sJG+UG+4Nr/4tQyAIXbY65saF/UN8kWJ9YGMCnzqE23TpsXt09Wj1JlWGhdWcqCmU
+        GpuaMU4gm2FIM+BO6bf/cJAQ1aD+O0+jeSehACjC26KOfIgMtkL1rXzO7RHrF/HN1tcOBtCebxj7
+        RcSlVFH6Hv7y0Xa2a9S949MGltfw+odfLYW4csCBhYdPVUcidn5krowsb49/fHaUPrL141vkVJ2W
+        aJEbUMJixxQibsWhWpP9OYSCdR4ozjquWkHTjJBfNUzRrq1SZsFMBTfx+UBym9vRPKJPALNMTqk2
+        Ndaws2w1A1fOV6jNZ7eBeO29B14oQ8I9jc3wxb8E5tvMpt9+m85C+uEgWxOLauHRSXfpvWhgKMYC
+        UjaflS1eCn2o6A1CDMPaWxh0RzG4Zy4+2vU6jGGyXKFWqjHeXw5bj2XRkMOPRms0iEff2MnxrYT6
+        aZsRgRZ7YzUywYLGHHww5o4tW7wIZ7LT+RQ7wyZiQyd8dOjtDB8JHxF4Y36/yCCoDytZcvmcLnKO
+        VnC+BAG9SzPvEaTZGUybnBItPH7S6dj7OXi+M430u6Cvlj0vd9DybxPaRvE1YqHaiuACBvWHn8YS
+        C3sd3A5WTY95CYa5V08qwIzI1PDQYLBe1U14rg4mtbB0j9aoin15jseA3rex6q0InFzoXG4HYh3d
+        pmLsveUBU24n8lv/DOmjkfmjcf3x32hZ7hSBx0uI6Z7ni5S0icLJXuvHFEeaFFH/dWngJ/Lu1L0m
+        arT4bUhgluiMemWgM07C2zfEgc0TciAOmAKnL0BYvzDZtDvN4+asXuEDnSLE6iuIyMaIVKXamDK+
+        fPXNdIC5DebLISCKuXQDbfA1BM1cj6Q8yP6w2AdIoJEGM3XMhLLFz2sI9tvghC3Ou7ERr00JWIo1
+        NJvxlg21Q3XYLZpDPHxkw7rOlQ1APe5Qu28gGKdTqkKcTxrZlqY9sF1g23/0oD7LtbFekycB3/zA
+        qKfAGznozXAwzwj/fm8y6rcMd+Ik0+NYMNBB0b3+4Tv5t5+sl6XL/ujD4yjMoNNOTQ7Va8OwrgSR
+        tyhqeYZOhyjWdigZ5na853BbHA70uLf3g2C5ogWVE89jjROUod8qz82PD+PnvTSHdfRevXJ93S5k
+        9dRsWI0hMpUvfiOQdSJbj2kbw8zcblG8dtOwCnHpw48aLWQ4oLKqf/wiT7IAn068H02g4nX45jsB
+        zXvrzmqsaSXYu+GdHufzgy1u8BjBV18j+V4EEX1NViZ+8YT++NOin5/2n/5/XHQBjC+RyXB4bnf0
+        2LZrNf/q8bjLP9g8O2+2VP4aw/fuaGDd+myH6R0HMhRMWcD262gPY4VnCIUuB6S39160Y1An0HfX
+        jCjzkAASPgoIbq3xwSrPjQZTOEWEoiMwJI1FbBC1sK/wdjBrfLoCI2WqzZdw1o8dAqSZ2aQVTgI1
+        dxehzfAZPPq+3P/gNdWXU+mx8yC60ESHjBoY7j1eCFcIo8PwpF52SsGqCDCHH9E7ofdXT33x3wae
+        IHJEUps9mJwoQtBE+4w6NpLY0lHdBV98IoIHC/CnPuVCfyEGeCGl7C1w8KvvCbAGPPzqBZRi0hBm
+        FYvRc5LvwkEXE3wMY6Oa3SgLQEZn48un78P008cm93KQaHl2ursqtgr9UR4R/9WjAx9/XPjVk2Sp
+        Tqdoco4VBF5Vx3/0rdDLyQpSLRewGjsfYz6f+fPv/OhxNy9sksd+Bd5O89FsUsg+61ZFMNjbhHBa
+        OFRrLHgQxM/+hdUoaMEaYX8DS7xMFHPv9x/+Db3zdf7mQzis7FD4CmhlDZtLlYBlrfcEdq/5heRc
+        56KpveAetkqp/hd/XVm5wgfZ0j96crUPrFPebYwpFqLb8PHXxYfXkNujSMlf1cJpsvrjY4gNFz39
+        8tNc9rrep3tneBlzigwbqqfXFqtR+2bsdBN7cMxPb6wmIgDL29x3MD80HfWI8WCTRLsQ1p1GqXnc
+        XqvlbR47eWN+SrSpDgePyTRMwCF68ohzy8+wZtk9gC/Kf6ihjwdjvRZoA7YB//z6H6QibzxYUDC9
+        J+K+9TDOg7b++DJh+qU36Dq9Gzhp9kD1k9sDkt2jGWrUpV897g6L18e+DN6RRnboWBuk9JcrkJf8
+        QrYkuQ5sXz9VkKw+xrq/NcAov45XWd9VBXm/7iVYdvxhlG91vcNGuX+nzD3mFpzOekTR6bI3RtQf
+        S7mw1T192BAPM15JCbjIKqlxr9SUN+qBBx/1tOBmt28BEfEug+t7ueAnBp/o6w8UsB1NH6MEWd5q
+        do8GmBp5EOlbD7V9jQlkQHoQ6dnVgJDT0Yb7/bEmu+41pMvolUSZhOZGStPSAdd9Ugh/5y1se8Xr
+        vCvSAWCvD1ZfumvM8UAb8PNDVMH7/M7jDOZoyKjVHnD1h48vXgmxW95P6TpPUgKcZgVY2y3Hge0H
+        K4D0sT3gL56BeWX9DFLpfMNOqPVgsE3FgnkqmlgrSZ6y8AxcWBoJwT/+P0eh2cCfvuPc0qmIWZIz
+        /PIBbOB7aLC+wcWvv6LdqQ+95cA3IpyWPcVqfT8Yu8BgIQzO6RUf7rfGaJbnJYY4POs0SMQUrLQO
+        YumX71cl3YHKZEAFEphVfICgj1ZyX2TlV2+HB6mMubp0/p/8/vlts9iqV6U/oj0SmvbtLT/++e0n
+        SM7rQyoIl6qDbmqkf/wzJrh7F6qnaoudKzUBlwVQBl//lGyF6FaxFdpvYPRVTLVLf42+eC8Cy5Uk
+        6t1vL7C0l0MHrQd7Ec45ZQN9aadVMUXXoToBD9aaz3aG5E5aJOqqlq5h6OZwCD3993vp+DgKMSCG
+        cqNqPZve9OVXsrIwGe1UPHn0BcpMlgIFYlQdWm9VT+MZlHW5+eG/t/78o2bXFQR8/QDSyxH36980
+        eOmuR59T6IO272LsXHZnMMsNbGDbPX0ii9OtWhI74aD8sEW0c2zk9dk9WuEylztsRq1aCRXudegn
+        homx0HPDjDX3j97CnvIpvOWr1+Vw//bozy9l2JBs6YphhrVNT6puIEIGdu5GJ7tcnr3lJusFHHQ5
+        QQU0+3QqXbuHVmltsE0e1tDlby6Bz8CtKbYGLwWTd+agGJwz6mx91/v5XSAUE4HIUnuoGC3vPPDq
+        +U0PBIsGsaXnG3Qna0+d/BaDmd6hDrVRqbAzOsCjWuKHkHmbO3a2sWqsB1eyf34CdtuDF816vRDp
+        50+CfrXAclVUFbI7O5KddFeiOboBXhLt+5ZsZo+mrA6jWd7tAcLGl++td/u+yqOXXWm2HZd0Di+u
+        BUC536H3yh3YoiaJDar7kmMDPOWIjfZgwuvzaOJv/I1dGBoFzJuDSFWTZmB+RKQHpyWkeP+eXum8
+        5wEB7wK0CJw/BzZDo5PBcFF78icfxMs4gtB0bwRGePRIql9XKJP3iNFgid4qmPkGtgLlqDUTF7AL
+        eYnwpy85aFoGm6f5KudXIaCHu/oxyFpiV/ZCEWIM6QCIogwEvkXOwG4VadF8E+48PFFOpo5jO4xX
+        C/WqEEf1qK60szfuuxuBsp9n9MsP2XLXqwYI4FyRtgxaY/niJ/DJuaAoqStvNWHBQbpUPtZNqwSL
+        n08QvPygxtF7u4n62q8bqI5XA/vudfBm5zUHMDp8nvj8XT8JVG6Eq8md8Ombf6v+hA20WLmiNHrP
+        1WJKsw0+kXPHmua8fvGa4bu8pdRRmxqsUVJlSh/vJuyjyTb4Kxf6AMFmQTwN+Yp+CBf+9oOP7YYO
+        u8ut1aFkODZi3/V95yehUjSvC9bpbgL9Bi3FT0+gBel6JETWzYUfQ1yo1mZxOu3MYf3jv1rs8ajm
+        Gk8+n8yaQd1d4A6zhIU3SAWxok6iAkZSPV+B/exWejzl0bDuiclBdHtLVDs+abRykm//9Ct6I8ka
+        2F7qA1AMjYNe3YsOc3Kye7hqxxNRnGgcfvULpzo/IDGzl2EyEiuG+3m0qNX5Dfio516G2+OGx6q8
+        jYyl2uTXn3+KeMYlA4uSMoFnISkwnvWCzXcBWTAbHQNJBwFWf/Q/ZqOMck8K2GeV4g28Wxai5sod
+        wBdfVFBtLJnuU6sxxl69qzDFUY8t87QfhNGuLOXnT6mC53jL9vzhwdpsXnh/pR9vvSNNVeRVdGio
+        tIE3pvdPD1s4d9RcHz1j6H04Q69FMdnJvZtycGfy8P18rmiToMajV+5u/+GbqAGLwerY0KG7ooIi
+        +rgYbIPEDLD++cFq1+ce0+tyVW6SdCLC1/9bhFegK9bzeMGeEhoeK150A831opA5LhqP3zhuAD3Z
+        UtF63pwBrWNPl3NHz6gvt0nEODeWIVetG3r8zv9YN7olvO9O8m9eMTDsFDFASfai/s24eivTRAiF
+        ux9hvdNMg8DxAcGXn+IDUVaDRGcOSV9/96c/U+amsgnffC9Q9dns2AplaQNTfOqxMaOqWn7+rHTL
+        3+Tr/7Lddz4oAXVU6NHWt8OsqFUMe9IohCMfFfDfeZP0ka8Puj+Md8Dm2mtgbZsDNfkt+q/+MtoN
+        QcstLKJ1e+5WeD4NAdbZR2Ar0+YNnDhCqV9rJKLowzewHS0fH7eVDtZd4PjyT0+okwa8gfXUkqKF
+        +PgSatRb2mro4P3ThxR79zoao9B8w5ihhqxDHgDhUnkJPAfHjLqjOlarLd0a0FAJYwtLUjphzSkk
+        z+jP2NMLe1jGPcsg3JIa63ZnMf6OHB1GhKtwZDmcwTJ3Q+SHeFYprsW1oqX43vz8HWwWzxDwXnvq
+        oZiL7be/cqyT0qsJ5U8lYj1POvDT24Dju+brt63Dn37nmyeObEWgMXY4yA0Aur1Q8xNHoD+2Rxle
+        NkVHXZvV6XSHXABvrfb5zrMe4CPHtwJWRXDAl8MogaXy5QR8+ye1heth+PqPBFK/igj39V8XtCs3
+        P//tt//o8/MXB3VChEaUpYQ/ZDms3ILHf/hHglwLfv0ganz12pJImxV85ynU83OVLZVITSC+VBFH
+        33kjqcLurSz+ZiZjKGJvTW2kyt/6+ePXDQYvFpCtsUW1Ez+mrHLkGX79CzJEYBq+fiiEq4ZPVD+9
+        DmA54fsKFbQ9Iv4yugPhL2IO8bT9oOr2vhvM2tsctPBmwkh8PaLaqEf5z3zUi95BNcdbmYd9sbo/
+        f3jgR+/TwW9/RuKeG9L1O2+GQtIdMMZHHC13Lz7D68ocBJF7MeY2Rj4YE7L56RFGsSG5MF7mlR4O
+        yAILucsbWJ4PLlolZnms2DGk/P27FfCf//rrr//1u2HQdI+8/l4MmPJl+vd/XxX4d/JI/s1x/L8p
+        /+cmAhmTIv/7n/+6hPD3Z+iaz/S/p+6dt+Pf//wF/9w2+HvqpqT+fx7/6/tf//mv/wMAAP//AwCZ
+        Ns2n4SAAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc668afd1113d-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:24 GMT
+      Function-Execution-Id:
+      - pbme5l3ic5k6
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '224'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 874088999973c1eb2bab5aadc2149d90
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 0804d410605ce2d1b7617943c8185427
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "What is your favorite color?", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '105'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R62w6yyrbm/XqKmXlLr4iI1GDeIaCiQBUConY6HVFUTnKsAmpnv3sH/53d3Tcm
+        HBJD1RjfadR//Ouvv/6u4ix59H//89ffRdr1f/+P+d7z3t///uev//mvv/7666//+P3+f28mZZw8
+        n+n3/Xv99zD9PpPx73/+Ev/7zv996Z+//v5o4ok4L3fRNo/PwQG7nZbMsUozXi7lOoRyk2jsqJ7N
+        dtCGaYAtWBeGzfUrHhdx6EHk9Du87KUtGg1PLsGsgTFr/zoYouk4GtrmEceQL1aIpjeyQ3BOjwTL
+        zbcdmHqP4LNqcmbpZW/QJPEAErA50y+9mU3VYqWD6gVbYqRbK+bmt0kB8PbBjvUoxmwbZT48vqFO
+        l5Vao26lGxKq1qsPcxVLDfoKrAq4X1yIFrYPVG20wodjcbnhocYRYnrjD+iM95hK7P7O+NITBujC
+        BmPrqRyMdPvxUzUecEqHPXztCZ+dDn1fU0MOxq5BQ3D2PER0WhCSLgNjKoOyhBqiiDi38w1V2ilP
+        wUCbBku39SoYs9SX4TwAIkde3+0x3yxEdHOyM15K7MP52o48KA9NzNyE8nY4+0KDAvdEmVk/zrzW
+        8spcX7e9jtGrMOIlR6ccRlgJuOPDOhvurSaosBHuuBWUNRqabXtE6iN6UmVDUz6NaRzCu1hyyr2b
+        YA/F46ggqhoMVzi68nm9Nfh4mcm2lVrzZnuqTFCQdGTkqvZBLXRxinYX50WVbU3aKiNaB9dzZJM9
+        RzIa0POpg0DfWxI3URGM7y+/q2dVD2hVtbY97ZPGUybtxoj2inO7r49lBGifR0Q3jk02Ld2XBrlz
+        bbGcyZCNmV890LSyrmz3bVk82ZWIIZNFRNf2YsdXtzWSobuWSzpuS8KHRXTbgVJ5d4K9VEfL6wRX
+        qCK8Z06Cz3yq6cdCU8sNYrgpDabPPVDQfv0cyUHfb4zlfXAs8ELZZXbyDQ0mg1xC5/ETcYInR/zi
+        aJrK+HQjehV17fTqhBwWlcqZ+/1sOOuoIcE99ShWi7xC3JA/E4hunRDLwwniJxNACRuxJSfaCwFf
+        +J8Q4rN1Z7puvzm16IPCWFy+RA/HDRK1U/4G8bxz6HoFx2y5Mbca7IvPkemWUSJ+RZcQimhizHwx
+        DzXO1xvWijYZeFJlL5i0OvPQZql0ZPPSt4h3quRB+cQ2w7hdxbR+fmTYNQPByHTCub/SdLG0lRcz
+        elYGo3ioGmhe+Zo4m6UeSL1V5ABFIRI7QEU8aKcuRbty7ZND8haziZ1vR3j6TxHLHhY4a069BLp7
+        M5hpeqExLE3YwUXSCDGc5BSPi5sswqWpFIYvyTbL/evLAqQ8dOJxDXMu6t8JxEOkMc04XDmP3CyB
+        zXoVzPuH4+/6ruxASjVGvCI42txt5BR2JfKJxhfXdhB3mqx6B2tD+8BcZv3zvnbg9304Jd921P1Q
+        R7R+Lqi0Pet8Gv23rJ5P1YLZ4uFqU/3ywkrpqmu6LqKaj0/7eYV5/7FMM48vr/6xg2jFMXOUkqKu
+        P20UoPX9TGb8akdqpHeQCjXC6+QdZlPXdDvY2csjO4S9bvNx10ngurWH15c655RkMUVz/VFYpyNn
+        UTdSWKsnwIryYgFj9zACVKrAXD3u+feI/Te6GMeM/eqF7bP+AZZFDbpKg30snW12RDZ6VeSHr2yu
+        P/jhfaiYhj1t9vkEkno32KE+RdlUGGAhr/p8GRaHZTzWa+8KXqiumENXajsMdn0Hd0hVcvTCjI/f
+        h3JFp+DLKLzcRTYsviWA/ZXw3D+iMY1pEMEqVGJmM/KJO9STB+hPzWF7SfoEkxSXGlpKwpcQBafx
+        5O7UDtZ6puOlUMTx8DZqUIJra5BjsrFa/sEHDJGZtnQUTrRt3y8rQaniGvi9lnJjXC1HE/ZqRNn+
+        khbxNA1NBHP14+Xr9IrHTRZ4aCXiCzPWxYtXWYIsVFdDSfQsS2x2aXMFnNTx2Tn48D/1Ae26HZhO
+        sR+wskwt6JWnx5xWeRvsWzzDP/irTn6GRjYmPhTJ4khL9qZxt11/PFTLZkrMJn5l03a6TehF+owd
+        92XV8shtEzB922ZbU3plw2t5V8DbBibbF+QYdOQ+THDXhYkKOrLbzvZ1X91W+Zdt190iHo9SQFUd
+        QovKibCzx8PV9yB3eEq0GkuoUw/FGz6yEZOd4jyNHp86+PO98YDteHJXNkYZPjREX5r7bNw3ICBL
+        k19MV2UvZqfwewfL+/p4+HqZ3YXmTYM4X7mEBPbSmMzATpGmJZ8Z3wTeRZtqACdKdsxMi53Br80h
+        QUvtGJIdOjrB8qHiUFHNdM12S3/XjhvT1eGsXwxi6v474I6d+mAeK0420oNkbPMwBijl9khI//4G
+        /LTUH3BRLj3bHD7QfmRTs9BqASnRMJf46B8/OqxgWzBz57q2tLloJTqU/Ye4Z6VBXe4iBa5bppMt
+        ri7ZkOx8DFex2hMv6CZEz/bXQvUWS2RHH2PAEj9UwAofhMSi0cSDeujfyjeLYoLDJ2n5UXhr6kdD
+        iDmbZRpPoYMEkC8PhW20784Yjxc3gW6ljMSp1o3dCd9rhE7M86iKtzaXZv5R5v2nzLzzeLqd0wQo
+        vq3ItpcKNPffHXp7eWXm4TDYA2llHWb+YluxX2Y8+QwUhibvqJr1asDalygpvk++lA9tHfThVdYg
+        yt2EHDNh04oU3ypAaZMQs48sg5EqUWDJdY2qM3+NdMp26HtZ7Ihm6mdjXB5W3g/PcLbtSdzk21eJ
+        yBFpjKyuvTHg56oBFMk+uTzvdjy8g8ddiqzpRSesSPE4PemEZv4iuou6bCSsvKL3SCwqXfR9y0dp
+        itQwrTyG3a5vK6Nbdsgcn/sZLzZx337NEOyviJnRrEd7EL5eqD7TnUo0C432gLGLQa+mK2WHgP36
+        PVR3pNuzmY9aVqzqK5BjeiAb4QJBUy2qOwSPVKMoK59oGG/DHdTVvSCH9dpAQ/qOSvA/0oC/pN/F
+        07WsO5SHjke2utwirt8lAVr9UdJ30Pmoe6eDA+cNOHR6FseMWxsvVOinHMn2dXoF3L2tfTTraYyu
+        jMazXijRzfmcyca5jLzLaFFCIrsOVUO0McaRXCbo3tc72QXWOZj8xbpD5SlriH3mbTBVxFfgMF0N
+        dl/HfjAAihIYc2Fg25dn8kG4vQC5hV3R5Xeb8cmx9BQtL1XL9m/v3XK5XYdodFeE7NdcQFwIzQk6
+        l7ypGIu53a10W5SHfXSgU2e3bbvnBx91lqLTFdMBjfhjTcjIsoCRs4Hs3qSKhpIQaubm5a3lH6GP
+        YKcs11gyklXAp4LvILAE74/e5YfhpAHXlZw4y29hDHri7aBvpueMVxEf5XwtoYNgYfrmGuVcb+4T
+        PNXHiUWzfp771VFnPiRaETTGbz3huS5CZhfPQ9CbJJvA+F494ixeRyQW6HT81Qcx1zuOBsnwGngp
+        3YY99bNmj8fy46nZubwS97a8ZNNDK4/wUsaWmVvy5ONO3eiqW2sFzaunY7eG9fDQUlljsmk6A41p
+        YVjAG91kx1PgtlImrWUIlU/CfPMgZlOnRG+4JAplZih/4qoAKBEKNuc//D8+nNSBR7AEst2KlI9+
+        LChgVdua4a9ltCtF0SJkFh3CUlFV2VDvdyW8P+kZh0drjabYnxy4N6ZPJTFcxdy9jb66P5o2e9xI
+        Z0w3M3Mgfssl82RZ5MPPHzWZ1RBCX6M9yKPzRkX6RsSwMrOdMmlUoIT3ngrhk2RDN6IcPPf1mvVM
+        3lL5YIegIPHINEn52OPnzCJFhDJj+HrZoPq3HgfbT4lpXC588PcbD3LvElD+1j/ZtISDCYUvWuSy
+        F852FZT0CE81Q+zYLMd4LLydCE3c+GT35Id2Ehjy0ezvyF79ZkG/R+CgWe8x19O3Nldu/+Xnfs/j
+        yo9QB8cTrxlZe9wY7+9bt/6t94Ua3O6dbNSQUMYhlVNeGINwuwA8cebQqSdWy+pJU+ChLB5Y0l9u
+        y+sNvyL5VZ+J+5q8lhtyPaHZr9KxpmI7He8Fhq92SGnFPm+7/agbRZUviUJcyfWyIQztBN5Lc8t2
+        zSfPOn5tc5BqKaCF0tCMc0PMYSzOX2audwHnQrbCoIVbxPTdrs/o5tpp8IyikTiXS2kP0eY9AVkj
+        RgzhSg3qL9b0T31Z8vlg12xMPDTr1VmPh+2EuByhIyYyRYftEExx2jWIebie9c+CdxTfGrirjU7R
+        ytSCKjh7PmDNHYiji47Bn1looYu/iphDJcPuuhGV6LqZYjwW/Mv5OWk6eAjSjcJAa2PAeOtAu/bW
+        +KN9S3t4FSsTfbQ1ImawWfI/+KB969nfrXR7BftjjvbHnU0M8voG3ebFUxRpLcUoXILRtVy7ooel
+        7chjoLU97bRKAid67Misv/74cRAMa2R+muzaub8rlDwGlz3W6YimXkY75VjjiOiL5SEYxjgQQYq8
+        jNb1SWq7e1wc0cwnzF0srIwvx5OoqF/+IFZT5fYkvC+PH1/ilLkPexJ7xYTHC4VET3IxoEv3ooOq
+        tUC/BwnZTD/UJlLb5sYM+V3FXSNm4h/9fJj9GzWNL0XeaeMx+1k1MddATZCvYpO4Wf+Mp9O7faBz
+        /cjIfu6PbroTDe3P4oXK6XpCvPlsGrV7SPVPn8Tsgy8SHAJzz/BhfPNugG0K2amPqXgfvnZvi4Ov
+        noui/OnHTMJns4Nk0EZipWsf8f5pliDVa5UdrunHHuv78Qi3Nrkz+1VkcddsW+vnz+n4Vmy09FT1
+        Dg++w1Sb85DO/ohU3ZSnbNZvWjzJ6+8DFi5q6aNVNJvXkyUr8en0pFy95THlRK7QG19i/LLCIiua
+        qxqBHfoJnvVKzIPpjpHrth4N8OdqTE07yICdwCIk7292fywXCnp9CSKzv7DH28Z4QI7iO7ESoTSG
+        n35ARpiyk5n6aFgTrKNU2GlUaI0hphYNKfITb4Ez7yYYzFZjDOunErFDt28Ra9m1QTtC9+TwSgxe
+        v/ebDnijmUybNluDVoNZotl/0Y6kX3ukQSjBWT8bZPbfnJMqkZGpP67MpOeR19fsIPz0EVUl12uH
+        jGgUopwkVPZcM16adNLVjznJGK3Md8ylRSUifKmexJxIbo/P+xqDpFOOVzL9xmOZnEXYeqPBLkL7
+        Dso3cnOQhfJO5fPuHY9Vl4tojU8ucbSxCEZL+V5hXYwF6b+fD+dQeiL4vvslidv12Yd9WhFShRjk
+        kN28dpo2dQXRopwInmQWdKvpFoHgr3Lm7sMD56pkeNC973eG7/eqnX71PyTSm9bmNkQj06YjBKJ+
+        xbJ1LeIZD7BSHx4N0a8dzWY9OKDS/ep0FC6PYJrztV9ewHbefhH/9AlcDCujt9lv96p6n379gCUw
+        qqwNTtUbcq15E+dhE3uS1+yB1p9kz3anLc3mekiQ5uCO2PduH48raU9/fp04bkGN4aa2laI83pht
+        yHXPxfeUVmpD1AELhykOKCvsHIREBgqF+rWn7JvslCI9msRS/NTgch9Oyuz/iG9414CbqwfAfmkF
+        7CG1qc3eLy0B/XRuqVBrddbF9wNdo7RKyLY2LtlgPG0P7RNtItuPdeScHmsZVu6zJ4b70LIxn7YR
+        PFNTZRte3mMeejFdz/zJdAdS9FtP+DzKB3HCx5MP/Ybu0Kyv6Hg+asbwOQ0C2uDRxiqL3uhPvlPL
+        zxuxPDcPJiXavkFYL0yyvd1u7XTPxgQsPtlUnIhpjGtuSRBmmz05Nsxox6TWMNz9uiDaO3zHw1cx
+        I/TxPibbuOePMdm3zQTqd3wwV9BZOwyPd4WCjdWxvQlmy9EXPETr65k98bZF09w/0IW9jJWWvzPq
+        fWQf2mO7YdtLvOVjJ0kT8gt+YfvV0ranxD114ObTSDbXnWGLUeonUCXXlPiv1Gj7fFNjIA0GjNZ6
+        aEwmXzpoUckHdipXOWKZcmpA8m8lcV7O1pY2K8WHd5EAHfeZhXhhLSJo2vMWrxXZbYcfHwxls8XT
+        ZOXZSI3mDjxp2MzHbjsWRHZ+fEfsvXsMhqUpmqooXi3yFHSSNedYF8Ad3iq9NWSL0HDJTfXU6g/i
+        pJZlT591evzphd9+cu4bt1TJw5PCdm/WZVO+7E1ol5HP9Nk/cVndY5jQ3cGydGW8vR6RAzM/Ycg1
+        agzpO8l/+E12sz6u9/HxjWY9gVVf2CMuTktPWWyG+qdPs9UzqClStRrYNvGX7dBreoNOBELmKO+P
+        MVnC3kLl6dPQIYs8RA9OhJGNnhXDreEF0yAKGmjhHuHFycJBf75kDpw0Y8EsLdvFPU2HCp769Uhu
+        hnPN6OfwaNC5+JbEPW0oZ6eQXdEjWAEd7qlljK86ESE+H+9kn5+QwfOjY6EhvZ/oQk/deLjH/RFm
+        fYCnLBOMnnibFC6Nb+DVUWyCDtpOU+ZrZq3DiY/4c7nDSekJ2wvdnbMx0hrwnmZFdjR9GVPTh9Gf
+        fOHHr9w7ixiSg/NkZP4eMdXWHbqTrTj7wQxNdnOpoFovP8wp1L39y0vgRISQ6cX9kE04f6cqloQb
+        Xuhp/8ObDq6f3YXCy9ka/e7RAxphKVDQxiLmspPtlJ6MC3ZwZMOY3nHVoTmPJ4/LpTTGZys/4Om/
+        RLzW9x+D5/X9CnmIPWb4cRNMy8ckwoxXBPvFIasf6i5Evzx0e+wbNG6xFcI27Bumi9oxE4UKTSiW
+        7yozgntoDMH56oG8H/aUz/pEtMevheb9JPt5Petf3leoMiEPq8yDP/h0ElSDGGIZGcuTy2Rlk9xD
+        Zm7CkzHw1SiChtyYOO8dQt0xO7xRjm53ZrdnYq8++CKCfXW35MCsDeKy0+7Qt31Ls58/2X/6q1Jp
+        wpxDswm6sDhSJVUKhThWmcftUXjr6uzn2I6mC3tQb5tInfmLHWQktlzuHwOatGiLa3qc2smuYM5r
+        C31enzoboyi5gxlpFq6eSm1MSNwJQIvsSlz2oNmojKBD/9JPTK/PUcCf5lYBv2YC7RebdTBchjqB
+        8cRXs77Y/epVgu6aL8kG3+V23D0KAG3liczB+Yr/ydu/We/TaWslMdee11LZqyElu22kxqP6+OxU
+        NXS72U8M7ainuwf09urKDrfvtaUHaCkY35eCh+QZ8jF+mQrcAjCYcfMVu18oaQonZ39hh5A+shZd
+        NyIk7sFk8/zJ5k/TVX56hqqid2l59HzKwFD7xSh7D/YgllMJft2EuBe9S9ad+akDqRYDkixp3v7x
+        x6uFkNKr4GK0EvWbBaLcl3QVflWb4/teBiFRgK6v6ccYKFF3v7yPZpnp21wInQFxVWiJYdZ+MJ4v
+        LYZUeKzYJoNHMN3MFq97O/mQ4/WQ8nn/r8qkhVt2yuARD9X3U0H2CXOm8z2NJ+FtiZDSwWSX64cE
+        A+uFFByyuWJh1ruTTzoMlrnckV8/Sv5L08FavCOWUOFp067WKvXVmjJFzkJvxd/8j+tyzvztPuPd
+        SZ4wzP6VikfrhrrNC6UwZWWFka9KBj+ZIqClMNnEOFRgjO3XCdF1M8Rs+yAUdd+b36inVnuwn1/I
+        BUs3AUnFljn73jKWo3CQAKPTiuDkvAyaMjteYdFJA12kbPuHP5CZOBk5yMsSDc/LKfnNm2g453PL
+        tmID+n5LMs+fAtSJUq+B1Qol2RnJJR43wVtUxRMhFGb8SOb5KjiRqOJp9icjO62v0BuNiuU5cGRp
+        d2xAl182+eWnA68STfGX9zdzPWORdQQ1yU+/UWmxXdt9clgLaDw34jxvDYOV9rzmKEDrkrnGfdVW
+        vIp0uK/5lv30zGifG3213eorrFivHHWv5V2GGQ+IrSx6Y7CWOQZRvFvEoVJmU7sSHRTf9htmGYWE
+        +JxfQj/lOvGMg8y7NstzYIs0p2+699HkRqcU3us4Ixsz9fngCncKSyeIiOYss2D6ftT8Ny9jm3x5
+        bQcpMHbwy+9m/xf/ycfg2RXkVX3bgFmj+FBD+83I7hg67XRWTo6qn3GFkXb6tl3Kpqu6DRsNy4kW
+        oSnfWoK8KAyHjqzts8Jv/Q6wFX7YcUN1JIpSof/mqcwku9qYLFVOYZ5/MiOHqzG6xlkAAxkNOdy+
+        ctbbRZj8+p+OzTRm449PB+X0oh+jltqhWj3MXz6E5/lfu/rNP7znriKHWW/zqBu7n99i+738Ddpd
+        gLT/4sfb+2ZM3mfwQXdjAy/oazT4y1s/0Jwvs1+9NZ97rKC/f6cC/vNff/31v34nDMrqmRTzwYA+
+        Gft///dRgX/fn/d/i6L0byb9OYlAu/s7+fuf/zqE8HfdVmXd/+++ypNv9/c/fyl/Thv83Vf9vfh/
+        bv9r/q///Nf/AQAA//8DAN9muKLhIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc66ebe45e153-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:25 GMT
+      Function-Execution-Id:
+      - pbmed6937r9a
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '20'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - ba5b2a8ed740e0e13bfdf1d482561f84
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - d1e10b6e48d2dcb7ed0782d5f86d3b37
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": "Lorem ipsum dolor sit amet", "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '103'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1R6WQ+zurLl+/kVW/uVPgqEwWa/hTGEwSaQsdVqAUkIEMJoA766/71Fvqvb3S+R
+        IBZTVa1aa5X/419//fV3k5bPbPz7n7/+/hTD+Pf/WM89kjH5+5+//ue//vrrr7/+4/f7/6181unz
+        8Si++W/578/i+3jOf//zF//fZ/7von/++pv3hyPVsvfRm9C34AGn6CZFtyvz5tgqTPUyKDuK08vX
+        o3MRdEqy7UK6705xzN/yz1Z5VGBHJHWrlJ+y+xIAPLCQkns6MX98vrfwEn9G7CfsDqYkDxXFuXsR
+        PmjjvVy6cXIUqEkq1TFLwEBP1AXGXJk0mfY30OEH6eDRBD6SLoegn2qmEgisxaV2Ye296bRECnTu
+        4wWJwXLyFh9pDrSyXUedHXgYi2W9T/CUSh7Watfsxdt2SlThBS/UTvLOm9fnhTMgGdVuYBczLBxO
+        cPy+Z8QHc5ku97KNYEaAQKboio3pcNw+YRd5FO9Bb7JllnIEldFQiOonDpiw7hNwcoUI24acp2Nd
+        bjmYZ0+D6tf3DTDwrjLQYq5AfRRv4pkl2QI4XVmoXvMMzH4eOmryKlTsF+3HWxpi2fLZ+eiotsov
+        6Ny5h9AoHIcmNY1T8pi4HFaXuMA746zHc23CBhZKwGF92RPAfKDY8E2DGO8aTmKLfxBqGD/aGpve
+        duxZL8U+PDz3JZFj0zO2YO59cG0ySq/HeZcuT1KHsFYBTy03XfrRz0NXbbzdEbvkNMVtRVgEJUYz
+        bPUoN7rvdD4pa/5gT3u6Ma3rJVEz93kn3Ozx8bydniYEIHyh4/MkxwOFu1qtw05BQ0ZoSc8b+QYX
+        SXFIcb1dGdO4PgdXUemphaJjv2jucwL5kj+wX+MzW6Q7qeD1HSK0Rd0TjMJCLvD2uO/w/ureUwY+
+        0071nCeg/gUqoCvMZAD+cn3ivXkM2LQxTwjWNJ+xP/czm275yMv+yejI6B+UcvKCBwfZftlhQ7mk
+        HpVrHypp5nyoM2pWz/LMPUF2rjbYywItFu/TqYZCXfEEyiEB42SXAxwq9MD2pxcBqc8sV3/Pn1y3
+        35I9jWmSt34b0H394FNau7uLOgR7FxuzbXhC80A+XKSTSW+nixUL6b42lffBVbDHf1m61McvB8s3
+        b9Pn0ajiqdjYEJrabofvweHcTw3LJ7hH7hfxwBH70TXYDsKD9aT+vt2wGqLHCXJd7SDhrcN0st5x
+        tDGS50wPeUzLWcvGCdA3OGAUtmdjmc/JBUqWOuDAPyQl2VadBKwkHYnw8B7xoo7uAHC6ayl+mR+D
+        wChXYNdnOhqeb5E1737HqbSAOr4ewNlYrnvT+eUfUq8bq5zmEDU//ECcUsolVXZkC57u/UzRejxf
+        ldsCu2xnY003nHTq6C4EOlJ0HMmCz+a13kAnixY+HNJrOW+P6QTHQ6AiroQULFnSRGCDtQr7xHp7
+        o7YBHXicXyYODN2IG+5DJjBu1ZGE2rFn5NUFC2hfyRPjSduXLDKJBLB0rDCuPl45WQ9MFO4YC0ji
+        qVFuSebZUN2fDOyUy9ubDdlVoF7KJcrfdwC+wmlwYRS+AOGU8l7OL33qYMadZxygbx636Z7Y8G5w
+        GPFHxIymVu45FL6uRNpDdOnZdy/ZAJjjEW3b4gLYcN01cMVTGkjY8Eae5yoYD+UTKd+d1vP09HX/
+        fK/9tWrKaWtPgypZaYNkRbl783C7LVDArzeJ3u5QLpnc1XC20R7r5w8tf98Ljt9yRu8AbY05ct0a
+        /uKHyXVniG1+aBTedwPC9wIsF3CSHWjJ8YfIh/TaNw5oXOjGeUdUf3fvyaa+wx+eUnQZvX6yX54O
+        nOaLUBeAxVs8mg7QD1KfgL1zLFl/v0mA73WLzLrRxGPaAU7JDtKZolb89LNWHmrI66JC+Gr/ZOSC
+        J1/d7Own1YrMLgerLHOIxkjGOH8808F6pyGcgXtD7M0ab7GhihRPOCwIFu3HYBu5NYGbUI8iLpH6
+        6fqxL6ARqYPysLLZZJktggMa9vSQLK23JPImh1pNRbJ/HT7lCL6OCwhMGN17G69nkaNkiuzdFnIX
+        3juDvpK9DqSTWCHR9Y2YqdyhBpud+cT7mhTlhwSnp2Ic+5g6t8BMZ//On+AuuBwQ4O5fVvHB+wmj
+        5nDECG3Gfha2sgLz+VWRpYNvb1qC7Q2u+IWA0rdgVNrwpta0mLHhiHL/jqvqpkw7puH9gFtvkaWY
+        g0qtRHg/y2E6RVuQQAnmCkYnpYzZbSsloNNHRk3VJ/GaDyHkj+OCLTeNShoO5xCEXEQwMtQcDOnT
+        aQC7eAZ1tke17Jol7NQi2xgIqvuAkena1XJXooYwKZkBuX3mHNzsqcTa2g9++AODezYhvvbO6Z/7
+        zencY2Nd39DU5YBfPmpqhKMJ5tjqbKV41jscxOItHq7tXZJfV12lAf+2vEVMOR6a1+5BRnd6x9Ms
+        NiZY+ythyiU15nCeOEgVp8TxmzlGH+/sG7Ri7OP9k17iGVO1g7k5jWiz1v/Sm3YGE0fJseOOc0mq
+        cmfCtb/RvchbbFEilQfjxFvUFI+3tX7ySC0Tl2K3uStsuHwvFYzVXYzdQjrFkzv129/9EXtanUHw
+        o177N+bIrz7Zp08UqOlRStFJMdKF9WkH9YrLyJ2bJWNoRx/KbNze0bK7vjx60jUCwm93pBbpMViE
+        4lsDWnA63e8SBETQOCGMPxcVLe4h7ju6HRRwU3pA1++fkiqrIqh8nxeyXJev0WvKC4JL/B0RvIlh
+        z973xYRcfhjxygeNpbOfBBABRX/4EevPwQm2+4NJHb/5pjNTu045oP675rdeLvNiJtDZBD21YUnZ
+        2J8sH8qxecDOJJllW+GJUxr5YlG8O6N4JMdGV+7ysyLAOEY9je3CV4enY9BgxZM+c9+Fqj64nB7E
+        UxPT9f1U0OEa6yUqjWXYfCSg3HYJ3rnt0etEI7yoKdAfFNc3Bobb99BBQQ2OhOc2l35+VIYPj8HQ
+        IcHYG0yEeufCyFUuaz8uDdqfgwsYb3uBvDvN6BcH5iGocGsidepqg/zwi6DWoP5eIcYk6qGvZkQW
+        sI1N4k12ImbK+SOo5PLmJTasfBiGu3xDDeOrxXSgXxfepbRHX2/TlzTfhAhKJ6HC+zhOYlbXSgIu
+        LH8SJa0+5YLqhECdXV/UPm0LNidh4gCzLs5U37xOxnTXygJ8erciMn0+vKXU9QxuT5eKsPV9SD5o
+        JjwlR0T1ozj3LFxmEy5ufaK6pJv9REVVBz+81l+55W0FY4zAEWQJErahD3guWPMJRyVqtfHeL4Kr
+        mWDlY9hDI+pne4lcEEQRRhVwrv0UuNMEYvtlIRDFm3Tsk7cOvwN5kLFM3/0y5mUNPpHsYiNBvbFo
+        /O4J8+gzUH133RiTYKq3P/2lLqyvMbtat0C5KCwinMw6brb66EB4eyfUPF926UBTF4JItyXs79sX
+        mLhWuYD38Xam+BXUxiRliy7zrerjQ3GtjaV1aij1m9BDMBBK8HErqfvhMz0I750nslfzBI9nWPzy
+        wRvkpJ2gthc3pOPtj7d8t7Ijw3aH6TWOlZg9s1cIqsuxwG7THbzlA+7dn34oueOxn4GhhGB6dRKR
+        Rrcux8Pmm8D3hjjUDjcl6AVx0X/6hernDy4nFxMErxvLp3tk6PHMKbMPOV1asBOimzdv+XcDboJ5
+        pUeh3pXzW4QhmBeJI4D/sng6YWsHtZsiYY0VB7Ao93sDxe+eRxJ/PsWjNB1chVN2JsXndC4ZfGU+
+        LD7+E9+2hQcGUb/5UG6Hmrr6VKWDIsZbaLVii37180dvDOfTByOO/7J59+R24FQULbYGaveMEx4F
+        sA9LQiZ4f3vjln93MDvaIj1UWtBP/mBcJPGwlRG3FdK+xbzmQ0fSXCI0U5JOsMMh/JhGRCbPyNN2
+        EFwe4DIysVmQz596hDQ2jghQHABWInWBJtzL6HvMI2PZp0UHy++G/OFD9Kd/PCcDpH22jtEeNvSm
+        3B4bkyybqYiHMF9s2HXpATvJzu+H21froPHe47W+eI+MeV9D4Sk/KM7JUC7oxSmQyvXrz/sKd/Tc
+        gp5uMXXLg97PvRibamULNWq+eGLj5Ywr+EmHBklXeAZr/lfwOg0u9Rl10pl/5icVftMI+7jxPcor
+        egSjnJtQtxtGxjby2wTNsaPU2E5uSpUuLGDX3Q+oY9y1X+562UB1vGWka+4Jmzu5v8C560uUP5jn
+        EaM1HUUjmyNRNklcUk78LJAIfoTd+5UYw14ettD1xJj4GaH9ImmODaLGO5J+78z9+H1dMthj+Ult
+        o1mMH9+BL0Ji7FZFCthGDLfwql0fRD47b8aMR8jBR9Z/EDeezulsbpVOmQQaYaRdFK+NegeBQLo0
+        dP+Ll2kQHbzzKKAe2tKSwKhRgG5pPdXG7yld9V8Nqo+XUK9kRzZFstfAIwt2a/3nKaOjxgGmRmeM
+        q5Ma0zMYt8B26JsI/quNhwuSTBjzi7zytb5vzpPeQd/2e+yapQ/mcjZyuOoJMt4XZLBxLjIoXAdI
+        91U3eIM+VAW0xcJd4zMYtNu+JFBGHKIuGM7lOH3bE2TP24Pke/+dFtjauaq/nJ/YrLOyZ8+84MGL
+        czFFc1b0M8irE1i+IkbK2/K9cVbFCj4leqBBLErpLGxn6Y+fYj08Nf589SGB8gQc6tdYAEx9eNzP
+        z8BYvfurPq5r8A6vGRJneYrZ1xgKEO5pjqQdeHjT1TZ1yCuZRmPOlD1yUEL9dz0U+5sasFh/NnAO
+        kgatfMBjA6UuFBsyI3jeHXtRHppFCTSWELVMtZL9+FPuqQjjyW168m4lHm4ZyrB9SGw2lFWI4I/v
+        2fNNN5ZXkJIfvuMdn5wYnQ3vBF58LFFzvyHl4te0gU6yYOoOocymSRgWxaEzJXLlkp6a84WD01eK
+        MTrlvEc5cZzgz08orZ3Sz1Hv+LA4LwXqPw85XRoSmGCtX2wB5eSRH3/R6PtMf/qgRgV24YpX1L3b
+        G9DoQYegVQ4azWossKXhcwXy3v5Etu1dALOrXp2f3iP5O0zAJBwcCMlnuVA7OFpsSd53Hfjmh6Dp
+        s5fB1B86F2oiGqgujJt+vHBzBL8oacnh2TbG6lfo6t7mbDLHh75n9rDN4Ob5yMnE+YdUNNjXh8JW
+        n6jRn1BKeifZwbzQGmq9466fCqvYghsMJXqwqls/nXCwg9nteMP9qTHTuWquGXjn/BE/yqooh0mW
+        TrDzKxfvuxOLxxFXBOK0Hn96yBuNs6ADbJxjalUyiAeVRDx8Sgdr9fNkwOJWsuHHDwdq2oaVstnw
+        Lsra3xDZDkm5qL5lA9dsFqwZ26mk15uhq6s/geZEbMtpu8sk6HbenjCmDylZQpmHd1H8Eq59XNJJ
+        w0v2ix/ZXlrPmDfn1IQEciJi2SFnJBJZAciYA+q9xaZst9PFhheFbDDikls//Pr9eB8WvPo/rJeH
+        fIGd9z5i1JKqZBCiECof4Y7GD+q8yQvOUNFukoSk8r0AVo29A0EX1IjTXsAYdqeEg/tHXZL+kg79
+        jGOjgpb3Fiha+9UyqucO3gt+T3cTb3rzNRIvAF26DF2Dhfcq3jsiuOIttWU7NxgwlRu80jbEZnpo
+        yuV4t11olUQjW1E/xEM73wqowNcWbYOjBUQjdQgoMtUgJT8wQNdjmFa3HVJfmZDOv/jBTTdQg1d1
+        Q5QtfALZQTmTjV5YTHzYBx0i0EKkvLRzutjG0YY3XGl43320cmkC/ATv8JwRuDNwzPLrdoLiLYCE
+        O+Unj3zxlUBeFxRqa0PDltGYczgPYU513zyk08Ud/suvCxrYeMPNYBPcLfyLoqNRpfM4dReZdsOX
+        Gmv8BnjMF3VfBRq157fhsdUf+YP/Jh3SkqzXV375ae4cDAa9O4Xyq85kbO8vocEKPlWkZbI76nfX
+        0lj1nQ3f4pMgyKRDPJcdJWDVz1g/isd+apHeQCcEEpGkx3vtZztbDfI2ojH3dNK5edg+YCN/J3xB
+        rFJ83xcb0rd8oElXLylb/WMoG4cbNkFRA+a+MgjuclbhtT/1Q6npF1i2dY/G99XzgMppFbwBvEGb
+        TW2mk/XYk18+kumzv7MV3zog3kMBW9P5GtN984CgzOeAplzRAMY/Qh9qhwxi+9L2HvmorQLvzYYS
+        /pcvTbDPoDJ+OGxspy4dkdQOkNSnhP7xeyc+6xQdSToObFmP+dB0dPjz5/y5P4KpKE4S5LrKwUfd
+        cOLpA9sJBm4l4b2o1mDks5stvxt9QZvryzFE+ZBIsFVJhC3eEOLlgiUEV7398+fLRchfJ9j1Tx1J
+        vU3ZhD5RDfn4RP/g3TRUBgdewmVGEKOM0VVPqmNUHFc/TO6ptH9VCq88NcTC7NJPkzxd1C46UGzz
+        XMQWNpYKJOfjm7qRn6eTd2xz2ZjeHnXTyionH99D+CmhQQ+9NMTkMnQRXP1DctdGuRx++Pvrb/P8
+        jFMW3AYflmLaUeMlRfHsFc0NpBlp0eIHbso+qOFhMdw2dHeKTLY4sInA6q9QzVK+MUt9eYH3d+Bi
+        G3Xcb74hQfFr8diUzzTtv1oWQi93Iuyu/GomwSmDn1OxJ7TxYPqHn1fqjcfxqv/H4FqZEIEeko19
+        N9nkxvIENFqeKcpeu5gN9OvA/KHvidKJu35c/WEwbphHNgKPAXtpTQ7X65F3oV9jXjCFBK71QfJh
+        uKzxSCpoeLpA4BN8PUFxkgWGN/+MPtNZjKfB0jqwNPcYKWVk9MSL2gYO4MZRLXhV8fDkD9yvX638
+        bPHIqJ4bQKrxgfGxinr68cMahlcvI1zfBWDLt94NbmpHpP55dyyne9E6yjXEZ4pNP0iXT5Lp4Mdf
+        DodULKdigyAssGNS4+by/WxPmgJ7h6iobosLo3E72bALHERdeRpSho8gU8RrK2FDS1rAaE1c+Xi6
+        OngvTDhubyG1YU0e0rreT2elvSXgsbe11X/h4w4/6g4qnM2o+0CBMVzbo6IGm/eB7gZBZIs2Sz4Q
+        xarFXslmNl6VcIG3R7ojm6x+pYQ80wv0M9GhjvTQyj9+YLWXXtg7+E46ZOmUAB84ENtfilImEVmH
+        nU4Ztk8fviyHsOLh4xkVFNH9o58/h4cLqy2KqeVfmngyDwcCfnrQrWDvLeWTLyDciojMUKExPZKw
+        Utd8WPUbH48isXi47VSN7vVvHbdGduN/74+91T+ZCUlsaF7tOxJJtivnMjogOPfBFykbXgdMEBUd
+        /vyj3arPhNX/h9P4EMl8DvR0K6bbLTxTNyTt6u9Om29nA99qvmj+zc9++m/tp/hwdjTAWJopYOv3
+        ATUuV9/46WMYCo+QyMI7N6a38c0BTvUWa9Zsp9OmvBTw8Hi/kGoOHWBnMPJwnLbWOn/cG9OozzdA
+        57NFRjPN+uYraZHqTNGHwBnmxrzTPQ5kFBLqnZoqpc+Cmeo63/mTX0vnKwWUky2hSIi1cuKD9gmz
+        PGc4WB4onlJV55T1eyGB9JT98atWPwQ7q78vKLZb/In34TBYbJpPEfrpS+xex7ocL7DdgdVfoZbT
+        uDGvDnoFjVYaaeBEoB8CV1qUNT7YDsm5nwRTuIFtZh2Qast6Kkx2T6BDGSWMCxKDSNrOVFte4rH2
+        /OzLX/6AvBNsbNkV60n/zU6g8aoz9i4ul34ZjAr481vHgX2NP/wm+XyvhDlEKrvoIihQt5sGG9QL
+        0umxTZDUJZuAKKKwLenpberKOi+hxnizjOnd7yCMUdBhtBVAObz3zIRAbgvqvjQhJelt4OCzO9l/
+        9Mnoqy6Cydc/0eN+pGVzOHIZVG56grH4vRkzdRiEZ0pO6/xB9ma5bxpYf49XbObhhg2DdeggsCYX
+        P9Z4zDhkJxgKrxD7cPvqWXG0d/+V3+v8bkbb4xNK1mZY+/tcTh/pgpRnIrnrfEnwhkwqntC8Ng/q
+        UdtnA+z2EZwzvsI3aETpnCt+ru6R80Xbec/AKJz5EMRP8iJiqkkx5W59BpRvdln9SsxICE861ER/
+        QGs9xOx2XiY49/hLlo1cpsypAwJ3g6+hMkGeMZ3O+Z/5FdnoR7H8469z9xIjUf6SeArNnQ6d921c
+        /SjbEJuNwQH9XOTUkyStF7psDuFLtS4YzR6fLmZVdvAqSv2KL008fz9KqHBytqPROl8eAvuDwF0U
+        vtQHj/qPXwjdNMbUjsDoFZmYnMDOP4bUtBbRoOVidPDv366A//zXX3/9r98Og7p5PD/rxoDxOY//
+        /u+tAv9OHsm/eX77b7r9sxOBDEn+/Puf/9qE8HfbN3U7/u+xqZ7f4e9//pL/7Db4e2zG5PP/nP7X
+        eq///Nf/AQAA//8DADKcAULhIAAA
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - private
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7ccfc67169206302-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 18:17:26 GMT
+      Function-Execution-Id:
+      - pbmelvnnggiz
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '21'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 259a6a1840b1fce07231112aa9f7de8f
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3000'
+      X-Ratelimit-Remaining-Requests:
+      - '2999'
+      X-Ratelimit-Reset-Requests:
+      - 20ms
+      X-Request-Id:
+      - 734ff3d0816385775c9c45af64184a3a
+    status:
+      code: 200
+      message: OK
+version: 1
diff --git a/tests/integration/memory/conftest.py b/tests/integration/memory/conftest.py
new file mode 100644
index 00000000..f7fe295a
--- /dev/null
+++ b/tests/integration/memory/conftest.py
@@ -0,0 +1,18 @@
+import numpy
+import pytest
+
+from autogpt.memory.vector.memory_item import MemoryItem
+from autogpt.memory.vector.utils import Embedding
+
+
+@pytest.fixture
+def memory_item(mock_embedding: Embedding):
+    return MemoryItem(
+        raw_content="test content",
+        summary="test content summary",
+        chunks=["test content"],
+        chunk_summaries=["test content summary"],
+        e_summary=mock_embedding,
+        e_chunks=[mock_embedding],
+        metadata={},
+    )
diff --git a/tests/integration/memory/test_json_file_memory.py b/tests/integration/memory/test_json_file_memory.py
new file mode 100644
index 00000000..9134a069
--- /dev/null
+++ b/tests/integration/memory/test_json_file_memory.py
@@ -0,0 +1,106 @@
+# sourcery skip: snake-case-functions
+"""Tests for JSONFileMemory class"""
+import orjson
+import pytest
+
+from autogpt.config import Config
+from autogpt.memory.vector import JSONFileMemory, MemoryItem
+from autogpt.workspace import Workspace
+from tests.utils import requires_api_key
+
+
+@pytest.fixture(autouse=True)
+def cleanup_sut_singleton():
+    if JSONFileMemory in JSONFileMemory._instances:
+        del JSONFileMemory._instances[JSONFileMemory]
+
+
+def test_json_memory_init_without_backing_file(config: Config, workspace: Workspace):
+    index_file = workspace.root / f"{config.memory_index}.json"
+
+    assert not index_file.exists()
+    JSONFileMemory(config)
+    assert index_file.exists()
+    assert index_file.read_text() == "[]"
+
+
+def test_json_memory_init_with_backing_empty_file(config: Config, workspace: Workspace):
+    index_file = workspace.root / f"{config.memory_index}.json"
+    index_file.touch()
+
+    assert index_file.exists()
+    JSONFileMemory(config)
+    assert index_file.exists()
+    assert index_file.read_text() == "[]"
+
+
+def test_json_memory_init_with_backing_file(config: Config, workspace: Workspace):
+    index_file = workspace.root / f"{config.memory_index}.json"
+    index_file.touch()
+
+    raw_data = {"texts": ["test"]}
+    data = orjson.dumps(raw_data, option=JSONFileMemory.SAVE_OPTIONS)
+    with index_file.open("wb") as f:
+        f.write(data)
+
+    assert index_file.exists()
+    JSONFileMemory(config)
+    assert index_file.exists()
+    assert index_file.read_text() == "[]"
+
+
+def test_json_memory_add(config: Config, memory_item: MemoryItem):
+    index = JSONFileMemory(config)
+    index.add(memory_item)
+    assert index.memories[0] == memory_item
+
+
+def test_json_memory_clear(config: Config, memory_item: MemoryItem):
+    index = JSONFileMemory(config)
+    assert index.memories == []
+
+    index.add(memory_item)
+    assert index.memories[0] == memory_item, "Cannot test clear() because add() fails"
+
+    index.clear()
+    assert index.memories == []
+
+
+def test_json_memory_get(config: Config, memory_item: MemoryItem, mock_get_embedding):
+    index = JSONFileMemory(config)
+    assert (
+        index.get("test") == None
+    ), "Cannot test get() because initial index is not empty"
+
+    index.add(memory_item)
+    retrieved = index.get("test")
+    assert retrieved is not None
+    assert retrieved.memory_item == memory_item
+
+
+@pytest.mark.vcr
+@requires_api_key("OPENAI_API_KEY")
+def test_json_memory_get_relevant(config: Config, patched_api_requestor: None) -> None:
+    index = JSONFileMemory(config)
+    mem1 = MemoryItem.from_text_file("Sample text", "sample.txt")
+    mem2 = MemoryItem.from_text_file("Grocery list:\n- Pancake mix", "groceries.txt")
+    mem3 = MemoryItem.from_text_file("What is your favorite color?", "color.txt")
+    lipsum = "Lorem ipsum dolor sit amet"
+    mem4 = MemoryItem.from_text_file(" ".join([lipsum] * 100), "lipsum.txt")
+    index.add(mem1)
+    index.add(mem2)
+    index.add(mem3)
+    index.add(mem4)
+
+    assert index.get_relevant(mem1.raw_content, 1)[0].memory_item == mem1
+    assert index.get_relevant(mem2.raw_content, 1)[0].memory_item == mem2
+    assert index.get_relevant(mem3.raw_content, 1)[0].memory_item == mem3
+    assert [mr.memory_item for mr in index.get_relevant(lipsum, 2)] == [mem4, mem1]
+
+
+def test_json_memory_get_stats(config: Config, memory_item: MemoryItem) -> None:
+    index = JSONFileMemory(config)
+    index.add(memory_item)
+    n_memories, n_chunks = index.get_stats()
+    assert n_memories == 1
+    assert n_chunks == 1
diff --git a/tests/integration/memory/utils.py b/tests/integration/memory/utils.py
new file mode 100644
index 00000000..374eab30
--- /dev/null
+++ b/tests/integration/memory/utils.py
@@ -0,0 +1,44 @@
+import numpy
+import pytest
+from pytest_mock import MockerFixture
+
+import autogpt.memory.vector.memory_item as vector_memory_item
+import autogpt.memory.vector.providers.base as memory_provider_base
+from autogpt.config.config import Config
+from autogpt.llm.providers.openai import OPEN_AI_EMBEDDING_MODELS
+from autogpt.memory.vector import get_memory
+from autogpt.memory.vector.utils import Embedding
+
+
+@pytest.fixture
+def embedding_dimension(config: Config):
+    return OPEN_AI_EMBEDDING_MODELS[config.embedding_model].embedding_dimensions
+
+
+@pytest.fixture
+def mock_embedding(embedding_dimension: int) -> Embedding:
+    return numpy.full((1, embedding_dimension), 0.0255, numpy.float32)[0]
+
+
+@pytest.fixture
+def mock_get_embedding(mocker: MockerFixture, embedding_dimension: int):
+    mocker.patch.object(
+        vector_memory_item,
+        "get_embedding",
+        return_value=[0.0255] * embedding_dimension,
+    )
+    mocker.patch.object(
+        memory_provider_base,
+        "get_embedding",
+        return_value=[0.0255] * embedding_dimension,
+    )
+
+
+@pytest.fixture
+def memory_none(agent_test_config: Config, mock_get_embedding):
+    was_memory_backend = agent_test_config.memory_backend
+
+    agent_test_config.set_memory_backend("no_memory")
+    yield get_memory(agent_test_config)
+
+    agent_test_config.set_memory_backend(was_memory_backend)
diff --git a/tests/integration/memory_tests.py b/tests/integration/memory_tests.py
deleted file mode 100644
index 66c23314..00000000
--- a/tests/integration/memory_tests.py
+++ /dev/null
@@ -1,50 +0,0 @@
-import random
-import string
-import sys
-import unittest
-from pathlib import Path
-
-from autogpt.config import Config
-from autogpt.memory.local import LocalCache
-
-
-class TestLocalCache(unittest.TestCase):
-    def generate_random_string(self, length):
-        return "".join(random.choice(string.ascii_letters) for _ in range(length))
-
-    def setUp(self):
-        """Set up the test environment for the LocalCache tests."""
-        cfg = cfg = Config()
-        self.cache = LocalCache(cfg)
-        self.cache.clear()
-
-        # Add example texts to the cache
-        self.example_texts = [
-            "The quick brown fox jumps over the lazy dog",
-            "I love machine learning and natural language processing",
-            "The cake is a lie, but the pie is always true",
-            "ChatGPT is an advanced AI model for conversation",
-        ]
-        for text in self.example_texts:
-            self.cache.add(text)
-
-        # Add some random strings to test noise
-        for _ in range(5):
-            self.cache.add(self.generate_random_string(10))
-
-    def test_get_relevant(self):
-        """Test getting relevant texts from the cache."""
-        query = "I'm interested in artificial intelligence and NLP"
-        k = 3
-        relevant_texts = self.cache.get_relevant(query, k)
-
-        print(f"Top {k} relevant texts for the query '{query}':")
-        for i, text in enumerate(relevant_texts, start=1):
-            print(f"{i}. {text}")
-
-        self.assertEqual(len(relevant_texts), k)
-        self.assertIn(self.example_texts[1], relevant_texts)
-
-
-if __name__ == "__main__":
-    unittest.main()
diff --git a/tests/integration/milvus_memory_tests.py b/tests/integration/milvus_memory_tests.py
deleted file mode 100644
index c4b97d34..00000000
--- a/tests/integration/milvus_memory_tests.py
+++ /dev/null
@@ -1,55 +0,0 @@
-# sourcery skip: snake-case-functions
-"""Tests for the MilvusMemory class."""
-import random
-import string
-import unittest
-
-from autogpt.config import Config
-from autogpt.memory.milvus import MilvusMemory
-
-try:
-
-    class TestMilvusMemory(unittest.TestCase):
-        """Unit tests for the MilvusMemory class."""
-
-        def generate_random_string(self, length: int) -> str:
-            return "".join(random.choice(string.ascii_letters) for _ in range(length))
-
-        def setUp(self) -> None:
-            cfg = Config()
-            cfg.milvus_addr = "localhost:19530"
-            self.memory = MilvusMemory(cfg)
-            self.memory.clear()
-
-            # Add example texts to the cache
-            self.example_texts = [
-                "The quick brown fox jumps over the lazy dog",
-                "I love machine learning and natural language processing",
-                "The cake is a lie, but the pie is always true",
-                "ChatGPT is an advanced AI model for conversation",
-            ]
-
-            for text in self.example_texts:
-                self.memory.add(text)
-
-            # Add some random strings to test noise
-            for _ in range(5):
-                self.memory.add(self.generate_random_string(10))
-
-        def test_get_relevant(self) -> None:
-            """Test getting relevant texts from the cache."""
-            query = "I'm interested in artificial intelligence and NLP"
-            num_relevant = 3
-            relevant_texts = self.memory.get_relevant(query, num_relevant)
-
-            print(f"Top {k} relevant texts for the query '{query}':")
-            for i, text in enumerate(relevant_texts, start=1):
-                print(f"{i}. {text}")
-
-            self.assertEqual(len(relevant_texts), k)
-            self.assertIn(self.example_texts[1], relevant_texts)
-
-except:
-    print(
-        "Skipping tests/integration/milvus_memory_tests.py as Milvus is not installed."
-    )
diff --git a/tests/integration/test_llm_utils.py b/tests/integration/test_llm_utils.py
deleted file mode 100644
index fefc239c..00000000
--- a/tests/integration/test_llm_utils.py
+++ /dev/null
@@ -1,65 +0,0 @@
-import string
-from unittest.mock import MagicMock
-
-import pytest
-from numpy.random import RandomState
-from pytest_mock import MockerFixture
-
-from autogpt.config import Config
-from autogpt.llm import llm_utils
-from autogpt.llm.api_manager import ApiManager
-from autogpt.llm.modelsinfo import COSTS
-from tests.utils import requires_api_key
-
-
-@pytest.fixture(scope="session")
-def random_large_string():
-    """Big string used to overwhelm token limits."""
-    seed = 42
-    n_characters = 30_000
-    random = RandomState(seed)
-    return "".join(random.choice(list(string.ascii_lowercase), size=n_characters))
-
-
-@pytest.fixture()
-def api_manager(mocker: MockerFixture):
-    api_manager = ApiManager()
-    mocker.patch.multiple(
-        api_manager,
-        total_prompt_tokens=0,
-        total_completion_tokens=0,
-        total_cost=0,
-    )
-    yield api_manager
-
-
-@pytest.fixture()
-def spy_create_embedding(mocker: MockerFixture):
-    return mocker.spy(llm_utils, "create_embedding")
-
-
-@pytest.mark.vcr
-@requires_api_key("OPENAI_API_KEY")
-def test_get_ada_embedding(
-    config: Config,
-    api_manager: ApiManager,
-    spy_create_embedding: MagicMock,
-    patched_api_requestor,
-):
-    token_cost = COSTS[config.embedding_model]["prompt"]
-    llm_utils.get_ada_embedding("test")
-
-    spy_create_embedding.assert_called_once_with("test", model=config.embedding_model)
-
-    assert (prompt_tokens := api_manager.get_total_prompt_tokens()) == 1
-    assert api_manager.get_total_completion_tokens() == 0
-    assert api_manager.get_total_cost() == (prompt_tokens * token_cost) / 1000
-
-
-@pytest.mark.vcr
-@requires_api_key("OPENAI_API_KEY")
-def test_get_ada_embedding_large_context(random_large_string):
-    # This test should be able to mock the openai call after we have a fix.  We don't need
-    # to hit the API to test the logic of the function (so not using vcr). This is a quick
-    # regression test to document the issue.
-    llm_utils.get_ada_embedding(random_large_string)
diff --git a/tests/integration/test_local_cache.py b/tests/integration/test_local_cache.py
deleted file mode 100644
index 808f119a..00000000
--- a/tests/integration/test_local_cache.py
+++ /dev/null
@@ -1,110 +0,0 @@
-# sourcery skip: snake-case-functions
-"""Tests for LocalCache class"""
-import unittest
-
-import orjson
-import pytest
-
-from autogpt.memory.local import EMBED_DIM, SAVE_OPTIONS
-from autogpt.memory.local import LocalCache as LocalCache_
-from tests.utils import requires_api_key
-
-
-@pytest.fixture
-def LocalCache():
-    # Hack, real gross. Singletons are not good times.
-    if LocalCache_ in LocalCache_._instances:
-        del LocalCache_._instances[LocalCache_]
-    return LocalCache_
-
-
-@pytest.fixture
-def mock_embed_with_ada(mocker):
-    mocker.patch(
-        "autogpt.memory.local.get_ada_embedding",
-        return_value=[0.1] * EMBED_DIM,
-    )
-
-
-def test_init_without_backing_file(LocalCache, config, workspace):
-    cache_file = workspace.root / f"{config.memory_index}.json"
-
-    assert not cache_file.exists()
-    LocalCache(config)
-    assert cache_file.exists()
-    assert cache_file.read_text() == "{}"
-
-
-def test_init_with_backing_empty_file(LocalCache, config, workspace):
-    cache_file = workspace.root / f"{config.memory_index}.json"
-    cache_file.touch()
-
-    assert cache_file.exists()
-    LocalCache(config)
-    assert cache_file.exists()
-    assert cache_file.read_text() == "{}"
-
-
-def test_init_with_backing_file(LocalCache, config, workspace):
-    cache_file = workspace.root / f"{config.memory_index}.json"
-    cache_file.touch()
-
-    raw_data = {"texts": ["test"]}
-    data = orjson.dumps(raw_data, option=SAVE_OPTIONS)
-    with cache_file.open("wb") as f:
-        f.write(data)
-
-    assert cache_file.exists()
-    LocalCache(config)
-    assert cache_file.exists()
-    assert cache_file.read_text() == "{}"
-
-
-def test_add(LocalCache, config, mock_embed_with_ada):
-    cache = LocalCache(config)
-    cache.add("test")
-    assert cache.data.texts == ["test"]
-    assert cache.data.embeddings.shape == (1, EMBED_DIM)
-
-
-def test_clear(LocalCache, config, mock_embed_with_ada):
-    cache = LocalCache(config)
-    assert cache.data.texts == []
-    assert cache.data.embeddings.shape == (0, EMBED_DIM)
-
-    cache.add("test")
-    assert cache.data.texts == ["test"]
-    assert cache.data.embeddings.shape == (1, EMBED_DIM)
-
-    cache.clear()
-    assert cache.data.texts == []
-    assert cache.data.embeddings.shape == (0, EMBED_DIM)
-
-
-def test_get(LocalCache, config, mock_embed_with_ada):
-    cache = LocalCache(config)
-    assert cache.get("test") == []
-
-    cache.add("test")
-    assert cache.get("test") == ["test"]
-
-
-@pytest.mark.vcr
-@requires_api_key("OPENAI_API_KEY")
-def test_get_relevant(LocalCache, config, patched_api_requestor) -> None:
-    cache = LocalCache(config)
-    text1 = "Sample text 1"
-    text2 = "Sample text 2"
-    cache.add(text1)
-    cache.add(text2)
-
-    result = cache.get_relevant(text1, 1)
-    assert result == [text1]
-
-
-def test_get_stats(LocalCache, config, mock_embed_with_ada) -> None:
-    cache = LocalCache(config)
-    text = "Sample text"
-    cache.add(text)
-    stats = cache.get_stats()
-    assert stats == (1, cache.data.embeddings.shape)
diff --git a/tests/integration/test_memory_management.py b/tests/integration/test_memory_management.py
deleted file mode 100644
index 22ade7b0..00000000
--- a/tests/integration/test_memory_management.py
+++ /dev/null
@@ -1,67 +0,0 @@
-import json
-
-import pytest
-
-from autogpt.config import Config
-from autogpt.memory import get_memory
-from autogpt.memory_management.store_memory import (
-    save_memory_trimmed_from_context_window,
-)
-from tests.utils import requires_api_key
-
-
-@pytest.fixture
-def message_history_fixture():
-    assistant_reply = {
-        "thoughts": {
-            "text": "thoughts",
-            "reasoning": "reasoning",
-            "plan": "plan",
-            "criticism": "criticism",
-            "speak": "speak",
-        },
-        "command": {"name": "google", "args": {"query": "google_query"}},
-    }
-    return [
-        {"content": json.dumps(assistant_reply, indent=4)},
-        {"content": "Command Result: Important Information."},
-    ]
-
-
-@pytest.fixture
-def expected_permanent_memory() -> str:
-    return """Assistant Reply: {
-    "thoughts": {
-        "text": "thoughts",
-        "reasoning": "reasoning",
-        "plan": "plan",
-        "criticism": "criticism",
-        "speak": "speak"
-    },
-    "command": {
-        "name": "google",
-        "args": {
-            "query": "google_query"
-        }
-    }
-}
-Result: None
-Human Feedback:Command Result: Important Information."""
-
-
-@requires_api_key("OPENAI_API_KEY")
-@pytest.mark.vcr
-def test_save_memory_trimmed_from_context_window(
-    message_history_fixture,
-    expected_permanent_memory,
-    config: Config,
-    patched_api_requestor,
-):
-    next_message_to_add_index = len(message_history_fixture) - 1
-    memory = get_memory(config, init=True)
-    save_memory_trimmed_from_context_window(
-        message_history_fixture, next_message_to_add_index, memory
-    )
-
-    memory_found = memory.get_relevant("Important Information", 5)
-    assert memory_found[0] == expected_permanent_memory
diff --git a/tests/integration/test_plugins.py b/tests/integration/test_plugins.py
new file mode 100644
index 00000000..d5f62cca
--- /dev/null
+++ b/tests/integration/test_plugins.py
@@ -0,0 +1,71 @@
+import pytest
+
+from autogpt.config import Config
+from autogpt.plugins import scan_plugins
+
+PLUGINS_TEST_DIR = "tests/unit/data/test_plugins"
+PLUGIN_TEST_OPENAI = "https://weathergpt.vercel.app/"
+
+
+@pytest.fixture
+def mock_config_denylist_allowlist_check():
+    class MockConfig:
+        """Mock config object for testing the denylist_allowlist_check function"""
+
+        plugins_denylist = ["BadPlugin"]
+        plugins_allowlist = ["GoodPlugin"]
+        authorise_key = "y"
+        exit_key = "n"
+
+    return MockConfig()
+
+
+@pytest.fixture
+def config_with_plugins():
+    """Mock config object for testing the scan_plugins function"""
+    # Test that the function returns the correct number of plugins
+    cfg = Config()
+    cfg.plugins_dir = PLUGINS_TEST_DIR
+    cfg.plugins_openai = ["https://weathergpt.vercel.app/"]
+    return cfg
+
+
+@pytest.fixture
+def mock_config_openai_plugin():
+    """Mock config object for testing the scan_plugins function"""
+
+    class MockConfig:
+        """Mock config object for testing the scan_plugins function"""
+
+        plugins_dir = PLUGINS_TEST_DIR
+        plugins_openai = [PLUGIN_TEST_OPENAI]
+        plugins_denylist = ["AutoGPTPVicuna"]
+        plugins_allowlist = [PLUGIN_TEST_OPENAI]
+
+    return MockConfig()
+
+
+def test_scan_plugins_openai(mock_config_openai_plugin):
+    # Test that the function returns the correct number of plugins
+    result = scan_plugins(mock_config_openai_plugin, debug=True)
+    assert len(result) == 1
+
+
+@pytest.fixture
+def mock_config_generic_plugin():
+    """Mock config object for testing the scan_plugins function"""
+
+    # Test that the function returns the correct number of plugins
+    class MockConfig:
+        plugins_dir = PLUGINS_TEST_DIR
+        plugins_openai = []
+        plugins_denylist = []
+        plugins_allowlist = ["AutoGPTPVicuna"]
+
+    return MockConfig()
+
+
+def test_scan_plugins_generic(mock_config_generic_plugin):
+    # Test that the function returns the correct number of plugins
+    result = scan_plugins(mock_config_generic_plugin, debug=True)
+    assert len(result) == 1
diff --git a/tests/integration/weaviate_memory_tests.py b/tests/integration/weaviate_memory_tests.py
deleted file mode 100644
index 2cea871c..00000000
--- a/tests/integration/weaviate_memory_tests.py
+++ /dev/null
@@ -1,120 +0,0 @@
-import unittest
-from uuid import uuid4
-
-from weaviate import Client
-from weaviate.util import get_valid_uuid
-
-from autogpt.config import Config
-from autogpt.llm import get_ada_embedding
-from autogpt.memory.weaviate import WeaviateMemory
-
-
-class TestWeaviateMemory(unittest.TestCase):
-    cfg = None
-    client = None
-    index = None
-
-    @classmethod
-    def setUpClass(cls):
-        """Set up the test environment for the WeaviateMemory tests."""
-        # only create the connection to weaviate once
-        cls.cfg = Config()
-
-        if cls.cfg.use_weaviate_embedded:
-            from weaviate.embedded import EmbeddedOptions
-
-            cls.client = Client(
-                embedded_options=EmbeddedOptions(
-                    hostname=cls.cfg.weaviate_host,
-                    port=int(cls.cfg.weaviate_port),
-                    persistence_data_path=cls.cfg.weaviate_embedded_path,
-                )
-            )
-        else:
-            cls.client = Client(
-                f"{cls.cfg.weaviate_protocol}://{cls.cfg.weaviate_host}:{self.cfg.weaviate_port}"
-            )
-
-        cls.index = WeaviateMemory.format_classname(cls.cfg.memory_index)
-
-    """
-    In order to run these tests you will need a local instance of
-    Weaviate running. Refer to https://weaviate.io/developers/weaviate/installation/docker-compose
-    for creating local instances using docker.
-    Alternatively in your .env file set the following environmental variables to run Weaviate embedded (see: https://weaviate.io/developers/weaviate/installation/embedded):
-
-        USE_WEAVIATE_EMBEDDED=True
-        WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate"
-    """
-
-    def setUp(self):
-        """Set up the test environment for the WeaviateMemory tests."""
-        try:
-            self.client.schema.delete_class(self.index)
-        except:
-            pass
-
-        self.memory = WeaviateMemory(self.cfg)
-
-    def test_add(self):
-        """Test adding a text to the cache"""
-        doc = "You are a Titan name Thanos and you are looking for the Infinity Stones"
-        self.memory.add(doc)
-        result = self.client.query.get(self.index, ["raw_text"]).do()
-        actual = result["data"]["Get"][self.index]
-
-        self.assertEqual(len(actual), 1)
-        self.assertEqual(actual[0]["raw_text"], doc)
-
-    def test_get(self):
-        """Test getting a text from the cache"""
-        doc = "You are an Avenger and swore to defend the Galaxy from a menace called Thanos"
-        # add the document to the cache
-        with self.client.batch as batch:
-            batch.add_data_object(
-                uuid=get_valid_uuid(uuid4()),
-                data_object={"raw_text": doc},
-                class_name=self.index,
-                vector=get_ada_embedding(doc),
-            )
-
-            batch.flush()
-
-        actual = self.memory.get(doc)
-
-        self.assertEqual(len(actual), 1)
-        self.assertEqual(actual[0], doc)
-
-    def test_get_stats(self):
-        """Test getting the stats of the cache"""
-        docs = [
-            "You are now about to count the number of docs in this index",
-            "And then you about to find out if you can count correctly",
-        ]
-
-        [self.memory.add(doc) for doc in docs]
-
-        stats = self.memory.get_stats()
-
-        self.assertTrue(stats)
-        self.assertTrue("count" in stats)
-        self.assertEqual(stats["count"], 2)
-
-    def test_clear(self):
-        """Test clearing the cache"""
-        docs = [
-            "Shame this is the last test for this class",
-            "Testing is fun when someone else is doing it",
-        ]
-
-        [self.memory.add(doc) for doc in docs]
-
-        self.assertEqual(self.memory.get_stats()["count"], 2)
-
-        self.memory.clear()
-
-        self.assertEqual(self.memory.get_stats()["count"], 0)
-
-
-if __name__ == "__main__":
-    unittest.main()
diff --git a/tests/milvus_memory_test.py b/tests/milvus_memory_test.py
deleted file mode 100644
index 9672326b..00000000
--- a/tests/milvus_memory_test.py
+++ /dev/null
@@ -1,72 +0,0 @@
-# sourcery skip: snake-case-functions
-"""Tests for the MilvusMemory class."""
-import os
-import sys
-import unittest
-
-try:
-    from autogpt.config import Config
-    from autogpt.memory.milvus import MilvusMemory
-
-    def mock_config() -> Config:
-        """Mock the config object for testing purposes."""
-
-        # Return a mock config object with the required attributes
-        class MockConfig(Config):
-            debug_mode = False
-            continuous_mode = False
-            speak_mode = False
-            milvus_collection = "autogpt"
-            milvus_addr = "localhost:19530"
-
-        return MockConfig()
-
-    class TestMilvusMemory(unittest.TestCase):
-        """Tests for the MilvusMemory class."""
-
-        def setUp(self) -> None:
-            """Set up the test environment"""
-            self.cfg = mock_config()
-            self.memory = MilvusMemory(self.cfg)
-
-        def test_add(self) -> None:
-            """Test adding a text to the cache"""
-            text = "Sample text"
-            self.memory.clear()
-            self.memory.add(text)
-            result = self.memory.get(text)
-            self.assertEqual([text], result)
-
-        def test_clear(self) -> None:
-            """Test clearing the cache"""
-            self.memory.clear()
-            self.assertEqual(self.memory.collection.num_entities, 0)
-
-        def test_get(self) -> None:
-            """Test getting a text from the cache"""
-            text = "Sample text"
-            self.memory.clear()
-            self.memory.add(text)
-            result = self.memory.get(text)
-            self.assertEqual(result, [text])
-
-        def test_get_relevant(self) -> None:
-            """Test getting relevant texts from the cache"""
-            text1 = "Sample text 1"
-            text2 = "Sample text 2"
-            self.memory.clear()
-            self.memory.add(text1)
-            self.memory.add(text2)
-            result = self.memory.get_relevant(text1, 1)
-            self.assertEqual(result, [text1])
-
-        def test_get_stats(self) -> None:
-            """Test getting the cache stats"""
-            text = "Sample text"
-            self.memory.clear()
-            self.memory.add(text)
-            stats = self.memory.get_stats()
-            self.assertEqual(15, len(stats))
-
-except ImportError as err:
-    print(f"Skipping tests for MilvusMemory: {err}")
diff --git a/tests/test_agent.py b/tests/test_agent.py
index e8596731..4f05e36b 100644
--- a/tests/test_agent.py
+++ b/tests/test_agent.py
@@ -3,17 +3,16 @@ from unittest.mock import MagicMock
 import pytest
 
 from autogpt.agent import Agent
-from autogpt.config import Config
+from autogpt.config import AIConfig
 
 
 @pytest.fixture
 def agent():
     ai_name = "Test AI"
     memory = MagicMock()
-    full_message_history = []
     next_action_count = 0
     command_registry = MagicMock()
-    config = Config()
+    config = AIConfig()
     system_prompt = "System prompt"
     triggering_prompt = "Triggering prompt"
     workspace_directory = "workspace_directory"
@@ -21,7 +20,6 @@ def agent():
     agent = Agent(
         ai_name,
         memory,
-        full_message_history,
         next_action_count,
         command_registry,
         config,
@@ -32,10 +30,10 @@ def agent():
     return agent
 
 
-def test_agent_initialization(agent):
+def test_agent_initialization(agent: Agent):
     assert agent.ai_name == "Test AI"
     assert agent.memory == agent.memory
-    assert agent.full_message_history == []
+    assert agent.history.messages == []
     assert agent.next_action_count == 0
     assert agent.command_registry == agent.command_registry
     assert agent.config == agent.config
diff --git a/tests/test_agent_manager.py b/tests/test_agent_manager.py
index e7e696ae..4b0a01bc 100644
--- a/tests/test_agent_manager.py
+++ b/tests/test_agent_manager.py
@@ -1,15 +1,14 @@
 import pytest
 
 from autogpt.agent.agent_manager import AgentManager
-from autogpt.llm import create_chat_completion
+from autogpt.llm.chat import create_chat_completion
 
 
 @pytest.fixture
 def agent_manager():
     # Hack, real gross. Singletons are not good times.
-    if AgentManager in AgentManager._instances:
-        del AgentManager._instances[AgentManager]
-    return AgentManager()
+    yield AgentManager()
+    del AgentManager._instances[AgentManager]
 
 
 @pytest.fixture
@@ -37,28 +36,28 @@ def mock_create_chat_completion(mocker):
     return mock_create_chat_completion
 
 
-def test_create_agent(agent_manager, task, prompt, model):
+def test_create_agent(agent_manager: AgentManager, task, prompt, model):
     key, agent_reply = agent_manager.create_agent(task, prompt, model)
     assert isinstance(key, int)
     assert isinstance(agent_reply, str)
     assert key in agent_manager.agents
 
 
-def test_message_agent(agent_manager, task, prompt, model):
+def test_message_agent(agent_manager: AgentManager, task, prompt, model):
     key, _ = agent_manager.create_agent(task, prompt, model)
     user_message = "Please translate 'Good morning' to French."
     agent_reply = agent_manager.message_agent(key, user_message)
     assert isinstance(agent_reply, str)
 
 
-def test_list_agents(agent_manager, task, prompt, model):
+def test_list_agents(agent_manager: AgentManager, task, prompt, model):
     key, _ = agent_manager.create_agent(task, prompt, model)
     agents_list = agent_manager.list_agents()
     assert isinstance(agents_list, list)
     assert (key, task) in agents_list
 
 
-def test_delete_agent(agent_manager, task, prompt, model):
+def test_delete_agent(agent_manager: AgentManager, task, prompt, model):
     key, _ = agent_manager.create_agent(task, prompt, model)
     success = agent_manager.delete_agent(key)
     assert success
diff --git a/tests/test_api_manager.py b/tests/test_api_manager.py
index bfb84213..9585fba7 100644
--- a/tests/test_api_manager.py
+++ b/tests/test_api_manager.py
@@ -2,7 +2,7 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from autogpt.llm import COSTS, ApiManager
+from autogpt.llm.api_manager import COSTS, ApiManager
 
 api_manager = ApiManager()
 
diff --git a/tests/unit/test_chat.py b/tests/unit/test_chat.py
deleted file mode 100644
index 77ff94d7..00000000
--- a/tests/unit/test_chat.py
+++ /dev/null
@@ -1,78 +0,0 @@
-# Generated by CodiumAI
-import time
-from unittest.mock import patch
-
-from autogpt.llm import create_chat_message, generate_context
-
-
-def test_happy_path_role_content():
-    """Test that the function returns a dictionary with the correct keys and values when valid strings are provided for role and content."""
-    result = create_chat_message("system", "Hello, world!")
-    assert result == {"role": "system", "content": "Hello, world!"}
-
-
-def test_empty_role_content():
-    """Test that the function returns a dictionary with the correct keys and values when empty strings are provided for role and content."""
-    result = create_chat_message("", "")
-    assert result == {"role": "", "content": ""}
-
-
-def test_generate_context_empty_inputs(mocker):
-    """Test the behavior of the generate_context function when all input parameters are empty."""
-    # Mock the time.strftime function to return a fixed value
-    mocker.patch("time.strftime", return_value="Sat Apr 15 00:00:00 2023")
-    # Arrange
-    prompt = ""
-    relevant_memory = ""
-    full_message_history = []
-    model = "gpt-3.5-turbo-0301"
-
-    # Act
-    result = generate_context(prompt, relevant_memory, full_message_history, model)
-
-    # Assert
-    expected_result = (
-        -1,
-        32,
-        2,
-        [
-            {"role": "system", "content": ""},
-            {
-                "role": "system",
-                "content": f"The current time and date is {time.strftime('%c')}",
-            },
-        ],
-    )
-    assert result == expected_result
-
-
-def test_generate_context_valid_inputs():
-    """Test that the function successfully generates a current_context given valid inputs."""
-    # Given
-    prompt = "What is your favorite color?"
-    relevant_memory = "You once painted your room blue."
-    full_message_history = [
-        create_chat_message("user", "Hi there!"),
-        create_chat_message("assistant", "Hello! How can I assist you today?"),
-        create_chat_message("user", "Can you tell me a joke?"),
-        create_chat_message(
-            "assistant",
-            "Why did the tomato turn red? Because it saw the salad dressing!",
-        ),
-        create_chat_message("user", "Haha, that's funny."),
-    ]
-    model = "gpt-3.5-turbo-0301"
-
-    # When
-    result = generate_context(prompt, relevant_memory, full_message_history, model)
-
-    # Then
-    assert isinstance(result[0], int)
-    assert isinstance(result[1], int)
-    assert isinstance(result[2], int)
-    assert isinstance(result[3], list)
-    assert result[0] >= 0
-    assert result[2] >= 0
-    assert result[1] >= 0
-    assert len(result[3]) >= 2  # current_context should have at least 2 messages
-    assert result[1] <= 2048  # token limit for GPT-3.5-turbo-0301 is 2048 tokens
diff --git a/tests/unit/test_file_operations.py b/tests/unit/test_file_operations.py
index 98d4efb7..7f885348 100644
--- a/tests/unit/test_file_operations.py
+++ b/tests/unit/test_file_operations.py
@@ -13,6 +13,8 @@ from pytest_mock import MockerFixture
 
 import autogpt.commands.file_operations as file_ops
 from autogpt.config import Config
+from autogpt.memory.vector.memory_item import MemoryItem
+from autogpt.memory.vector.utils import Embedding
 from autogpt.utils import readable_file_size
 from autogpt.workspace import Workspace
 
@@ -22,6 +24,23 @@ def file_content():
     return "This is a test file.\n"
 
 
+@pytest.fixture()
+def mock_MemoryItem_from_text(mocker: MockerFixture, mock_embedding: Embedding):
+    mocker.patch.object(
+        file_ops.MemoryItem,
+        "from_text",
+        new=lambda content, source_type, metadata: MemoryItem(
+            raw_content=content,
+            summary=f"Summary of content '{content}'",
+            chunk_summaries=[f"Summary of content '{content}'"],
+            chunks=[content],
+            e_summary=mock_embedding,
+            e_chunks=[mock_embedding],
+            metadata=metadata | {"source_type": source_type},
+        ),
+    )
+
+
 @pytest.fixture()
 def test_file_path(config, workspace: Workspace):
     return workspace.get_path("test_file.txt")
@@ -188,7 +207,11 @@ def test_split_file(max_length, overlap, content, expected):
     )
 
 
-def test_read_file(test_file_with_content_path: Path, file_content):
+def test_read_file(
+    mock_MemoryItem_from_text,
+    test_file_with_content_path: Path,
+    file_content,
+):
     content = file_ops.read_file(test_file_with_content_path)
     assert content == file_content
 
diff --git a/tests/unit/test_get_self_feedback.py b/tests/unit/test_get_self_feedback.py
index 5e59757e..64268898 100644
--- a/tests/unit/test_get_self_feedback.py
+++ b/tests/unit/test_get_self_feedback.py
@@ -2,7 +2,7 @@ from datetime import datetime
 
 from autogpt.agent.agent import Agent
 from autogpt.config import AIConfig
-from autogpt.llm import create_chat_completion
+from autogpt.llm.chat import create_chat_completion
 from autogpt.log_cycle.log_cycle import LogCycleHandler
 
 
diff --git a/tests/unit/test_llm_utils.py b/tests/unit/test_llm_utils.py
index e11b368e..8c4de115 100644
--- a/tests/unit/test_llm_utils.py
+++ b/tests/unit/test_llm_utils.py
@@ -1,11 +1,9 @@
 from unittest.mock import patch
 
 import pytest
-from openai import InvalidRequestError
 from openai.error import APIError, RateLimitError
 
-from autogpt.llm import llm_utils
-from autogpt.llm.llm_utils import check_model
+from autogpt.llm import utils as llm_utils
 
 
 @pytest.fixture(params=[RateLimitError, APIError])
@@ -107,36 +105,6 @@ def test_retry_openapi_other_api_error(capsys):
     assert output.out == ""
 
 
-def test_chunked_tokens():
-    text = "Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model"
-    expected_output = [
-        (
-            13556,
-            12279,
-            2898,
-            374,
-            459,
-            22772,
-            1825,
-            31874,
-            3851,
-            67908,
-            279,
-            17357,
-            315,
-            279,
-            480,
-            2898,
-            12,
-            19,
-            4221,
-            1646,
-        )
-    ]
-    output = list(llm_utils.chunked_tokens(text, "cl100k_base", 8191))
-    assert output == expected_output
-
-
 def test_check_model(api_manager):
     """
     Test if check_model() returns original model when valid.
@@ -145,7 +113,7 @@ def test_check_model(api_manager):
     with patch("openai.Model.list") as mock_list_models:
         # Test when correct model is returned
         mock_list_models.return_value = {"data": [{"id": "gpt-4"}]}
-        result = check_model("gpt-4", "smart_llm_model")
+        result = llm_utils.check_model("gpt-4", "smart_llm_model")
         assert result == "gpt-4"
 
         # Reset api manager models
@@ -153,7 +121,7 @@ def test_check_model(api_manager):
 
         # Test when incorrect model is returned
         mock_list_models.return_value = {"data": [{"id": "gpt-3.5-turbo"}]}
-        result = check_model("gpt-4", "fast_llm_model")
+        result = llm_utils.check_model("gpt-4", "fast_llm_model")
         assert result == "gpt-3.5-turbo"
 
         # Reset api manager models
diff --git a/tests/unit/test_plugins.py b/tests/unit/test_plugins.py
index 08c9114c..885ec4c3 100644
--- a/tests/unit/test_plugins.py
+++ b/tests/unit/test_plugins.py
@@ -1,16 +1,11 @@
 import pytest
 
 from autogpt.config import Config
-from autogpt.plugins import (
-    denylist_allowlist_check,
-    inspect_zip_for_modules,
-    scan_plugins,
-)
+from autogpt.plugins import denylist_allowlist_check, inspect_zip_for_modules
 
 PLUGINS_TEST_DIR = "tests/unit/data/test_plugins"
 PLUGIN_TEST_ZIP_FILE = "Auto-GPT-Plugin-Test-master.zip"
 PLUGIN_TEST_INIT_PY = "Auto-GPT-Plugin-Test-master/src/auto_gpt_vicuna/__init__.py"
-PLUGIN_TEST_OPENAI = "https://weathergpt.vercel.app/"
 
 
 def test_inspect_zip_for_modules():
@@ -77,54 +72,3 @@ def test_denylist_allowlist_check_user_input_invalid(
     assert not denylist_allowlist_check(
         "UnknownPlugin", mock_config_denylist_allowlist_check
     )
-
-
-@pytest.fixture
-def config_with_plugins():
-    """Mock config object for testing the scan_plugins function"""
-    # Test that the function returns the correct number of plugins
-    cfg = Config()
-    cfg.plugins_dir = PLUGINS_TEST_DIR
-    cfg.plugins_openai = ["https://weathergpt.vercel.app/"]
-    return cfg
-
-
-@pytest.fixture
-def mock_config_openai_plugin():
-    """Mock config object for testing the scan_plugins function"""
-
-    class MockConfig:
-        """Mock config object for testing the scan_plugins function"""
-
-        plugins_dir = PLUGINS_TEST_DIR
-        plugins_openai = [PLUGIN_TEST_OPENAI]
-        plugins_denylist = ["AutoGPTPVicuna"]
-        plugins_allowlist = [PLUGIN_TEST_OPENAI]
-
-    return MockConfig()
-
-
-def test_scan_plugins_openai(mock_config_openai_plugin):
-    # Test that the function returns the correct number of plugins
-    result = scan_plugins(mock_config_openai_plugin, debug=True)
-    assert len(result) == 1
-
-
-@pytest.fixture
-def mock_config_generic_plugin():
-    """Mock config object for testing the scan_plugins function"""
-
-    # Test that the function returns the correct number of plugins
-    class MockConfig:
-        plugins_dir = PLUGINS_TEST_DIR
-        plugins_openai = []
-        plugins_denylist = []
-        plugins_allowlist = ["AutoGPTPVicuna"]
-
-    return MockConfig()
-
-
-def test_scan_plugins_generic(mock_config_generic_plugin):
-    # Test that the function returns the correct number of plugins
-    result = scan_plugins(mock_config_generic_plugin, debug=True)
-    assert len(result) == 1
diff --git a/tests/test_token_counter.py b/tests/unit/test_token_counter.py
similarity index 56%
rename from tests/test_token_counter.py
rename to tests/unit/test_token_counter.py
index 966a0aff..feed18b1 100644
--- a/tests/test_token_counter.py
+++ b/tests/unit/test_token_counter.py
@@ -1,20 +1,13 @@
 import pytest
 
-from autogpt.llm import count_message_tokens, count_string_tokens
+from autogpt.llm.base import Message
+from autogpt.llm.utils import count_message_tokens, count_string_tokens
 
 
 def test_count_message_tokens():
     messages = [
-        {"role": "user", "content": "Hello"},
-        {"role": "assistant", "content": "Hi there!"},
-    ]
-    assert count_message_tokens(messages) == 17
-
-
-def test_count_message_tokens_with_name():
-    messages = [
-        {"role": "user", "content": "Hello", "name": "John"},
-        {"role": "assistant", "content": "Hi there!"},
+        Message("user", "Hello"),
+        Message("assistant", "Hi there!"),
     ]
     assert count_message_tokens(messages) == 17
 
@@ -25,19 +18,19 @@ def test_count_message_tokens_empty_input():
 
 
 def test_count_message_tokens_invalid_model():
-    """Invalid model should raise a KeyError"""
+    """Invalid model should raise a NotImplementedError"""
     messages = [
-        {"role": "user", "content": "Hello"},
-        {"role": "assistant", "content": "Hi there!"},
+        Message("user", "Hello"),
+        Message("assistant", "Hi there!"),
     ]
-    with pytest.raises(KeyError):
+    with pytest.raises(NotImplementedError):
         count_message_tokens(messages, model="invalid_model")
 
 
 def test_count_message_tokens_gpt_4():
     messages = [
-        {"role": "user", "content": "Hello"},
-        {"role": "assistant", "content": "Hi there!"},
+        Message("user", "Hello"),
+        Message("assistant", "Hi there!"),
     ]
     assert count_message_tokens(messages, model="gpt-4-0314") == 15
 
@@ -55,16 +48,6 @@ def test_count_string_tokens_empty_input():
     assert count_string_tokens("", model_name="gpt-3.5-turbo-0301") == 0
 
 
-def test_count_message_tokens_invalid_model():
-    """Invalid model should raise a NotImplementedError"""
-    messages = [
-        {"role": "user", "content": "Hello"},
-        {"role": "assistant", "content": "Hi there!"},
-    ]
-    with pytest.raises(NotImplementedError):
-        count_message_tokens(messages, model="invalid_model")
-
-
 def test_count_string_tokens_gpt_4():
     """Test that the string tokens are counted correctly."""
 

From ddf59273e6b4607562f7e73e7780260c281b687e Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Thu, 25 May 2023 22:00:52 +0300
Subject: [PATCH 064/112] Remove obsolete full_message_history kwarg from tests
 (#4411)

---
 tests/integration/agent_factory.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 1781a3f1..19af503b 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -158,7 +158,6 @@ def get_company_revenue_agent(
     agent = Agent(
         ai_name="Get-CompanyRevenue",
         memory=memory_json_file,
-        full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
         next_action_count=0,
@@ -191,7 +190,6 @@ def kubernetes_agent(memory_json_file, workspace: Workspace):
     agent = Agent(
         ai_name="Kubernetes-Demo",
         memory=memory_json_file,
-        full_message_history=[],
         command_registry=command_registry,
         config=ai_config,
         next_action_count=0,

From d3fc8c42868d145de91b19f7a7eb3d505d5babbd Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Fri, 26 May 2023 02:15:27 +0300
Subject: [PATCH 065/112] add 30 min timeout for tests (#4416)

---
 .github/workflows/ci.yml        | 1 +
 .github/workflows/docker-ci.yml | 1 +
 2 files changed, 2 insertions(+)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 94c963a4..2f36053e 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -59,6 +59,7 @@ jobs:
       # comments (to avoid publishing multiple comments in the same PR)
       contents: write
     runs-on: ubuntu-latest
+    timeout-minutes: 30
     strategy:
       matrix:
         python-version: ["3.10"]
diff --git a/.github/workflows/docker-ci.yml b/.github/workflows/docker-ci.yml
index 315c42e5..681eb4af 100644
--- a/.github/workflows/docker-ci.yml
+++ b/.github/workflows/docker-ci.yml
@@ -73,6 +73,7 @@ jobs:
   # Docker setup needs fixing before this is going to work: #1843
   test:
     runs-on: ubuntu-latest
+    timeout-minutes: 30
     needs: build
     steps:
     - name: Checkout repository

From f07fcdf0a77c74adafd13525adcdce07c0432e56 Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Fri, 26 May 2023 15:48:36 +0300
Subject: [PATCH 066/112] Pull auto-gpt-plugin-template from GitHub instead of
 PyPI (#4402)

* switch from pypi to github for auto-gpt-plugin-template

* adapt tests to new plugin interface
---
 autogpt/models/base_open_ai_plugin.py         |  57 ++++++++++++++++++
 requirements.txt                              |   2 +-
 .../Auto-GPT-Plugin-Test-master.zip           | Bin 14927 -> 15385 bytes
 3 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/autogpt/models/base_open_ai_plugin.py b/autogpt/models/base_open_ai_plugin.py
index 046295c0..8f6dd52c 100644
--- a/autogpt/models/base_open_ai_plugin.py
+++ b/autogpt/models/base_open_ai_plugin.py
@@ -197,3 +197,60 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
             str: The resulting response.
         """
         pass
+
+    def can_handle_text_embedding(self, text: str) -> bool:
+        """This method is called to check that the plugin can
+          handle the text_embedding method.
+        Args:
+            text (str): The text to be convert to embedding.
+          Returns:
+              bool: True if the plugin can handle the text_embedding method."""
+        return False
+
+    def handle_text_embedding(self, text: str) -> list:
+        """This method is called when the chat completion is done.
+        Args:
+            text (str): The text to be convert to embedding.
+        Returns:
+            list: The text embedding.
+        """
+        pass
+
+    def can_handle_user_input(self, user_input: str) -> bool:
+        """This method is called to check that the plugin can
+        handle the user_input method.
+
+        Args:
+            user_input (str): The user input.
+
+        Returns:
+            bool: True if the plugin can handle the user_input method."""
+        return False
+
+    def user_input(self, user_input: str) -> str:
+        """This method is called to request user input to the user.
+
+        Args:
+            user_input (str): The question or prompt to ask the user.
+
+        Returns:
+            str: The user input.
+        """
+
+        pass
+
+    def can_handle_report(self) -> bool:
+        """This method is called to check that the plugin can
+        handle the report method.
+
+        Returns:
+            bool: True if the plugin can handle the report method."""
+        return False
+
+    def report(self, message: str) -> None:
+        """This method is called to report a message to the user.
+
+        Args:
+            message (str): The message to report.
+        """
+        pass
diff --git a/requirements.txt b/requirements.txt
index df45c9ca..53785f9a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -36,7 +36,7 @@ pre-commit
 black
 isort
 gitpython==3.1.31
-auto-gpt-plugin-template
+auto-gpt-plugin-template @ git+https://github.com/Significant-Gravitas/Auto-GPT-Plugin-Template@0.1.0
 mkdocs
 pymdown-extensions
 mypy
diff --git a/tests/unit/data/test_plugins/Auto-GPT-Plugin-Test-master.zip b/tests/unit/data/test_plugins/Auto-GPT-Plugin-Test-master.zip
index 00bc1f4f58dc1c8e07c7ca3adce6be605fe6a3ce..45b515adc18a6bfb9cb6700668bd3718de3f3cfa 100644
GIT binary patch
literal 15385
zcmbW81#}c!*0$sBZp1xAh>;L?B}SaMcU(H|PTYkEad#)~O5BCGyAmVvhs!Vn_qzkL
z{_b^pcdyk|&)#+F*sk};Nr6LPfP8!9N7XC;_2pk51W#7L9%w}`CZ|X*XKrr{u%uTs
zv;)#x=-L4dZ5ieMbtDYPMn$ypJEGxZKTr@5V{i}<sy`gbpl{`1Xsc^%Xsh3>&~Eyf
z38i_T4$9U9zd>dsAcwwsRLh0BnIa@Ir-D9`%}7+H%5yoY@-3RUE!=5)w9$v9Walh1
z*}6W<jt_NiOyG?N#<QJ7OQXerWIe1|e09As$csiV2kRTvtwgGKxCFqUCMgusEXJ<h
zqz5iC{YG17`?S^u)~(wTpt6b)Cr(BfPoaWwAxCM~rVhi(OBts?FtQifiS{ZmC&PL4
z#G%sgP6KGZNpDCE&x3PP70qMrWp6qc^-8>L0_PAVkXd{%5`5P|ijV*{n6C4ek+Aa@
zG7!tut#o*5(;KED;1-ba)Cy7v9Oe_@wy$VOb+nI7tRc*%&}(ZU*I;}AO}luXxg|6N
zAah{+u+sDkg!7F6;4%>Pc$fSEnizg%+k=iqYtTX3iXOCV42kdo@$SlMuESjJ0z>JP
zpz^e$`uFwzvU!>o42_T_{>{V7^CA+(hc4$n`nL%k!$tP0MsQ~p!vcBz*W%lsTwh)%
zA9ZfCJP=w+r!c=zFLv*{@qYyWR*`UjRr<Gzob5=_#(w(st<e0bA`J}yKr35)D@!AQ
z@mpF3YiCV3Yg;QLfVm+t53!!PuD%)EueXU>+7P4d(^*rV3fZ5|Ze*@&X2|inPXMWd
z7{z~;Cr@V)25+(4W|t<E1fnPYosdu-VzWC{PDsnt)x*`xdZNUL>&8L_VL90HJOSRE
z7htrYP?)ZRkQ~iNb<kpITWu=hA96Jq8;hT*9N&RV*Ny^^!tku;Dws+&&8V<(>@s$p
zNMyP`gZ%2UQQ;YX`_o;G3=IN8`6ri+0YHGUrIoFrh0<K<1QUw;h>9v0EG(*+9{MNr
zB9MxpL&%JQ3aX%j^%u1hODA6lxac)dkZp|9POk?qf}NU-OxZ@-UomH*6I7-ij!5#k
z->V};<{8z&7b&}BE|!{=ek%8vGH+p<DGN|C%~LQ<qFW0}50U0oyMz@D3OOlw%{lMU
zA4zH;=TauR-z(apecsiwi@h&BgYznKeRQ0I()y&MU+h>F7lys!vq#F|zRi`x3<M^N
zFyNdcf0nH`sE;Dw+=Om%I5tjRt=&=~szL5eopI+rg{9ejo4Bs~z(5AB0`hvU=@Pfg
z*Rz|dh_nI!r7}iYEYy_i6s*yrK6Hxt28u{Qf~+BvfE|^Lu6SAUXBK^W@3@5$0Z1~2
zwDK-^I5G)(A@d1}YndfLA#yCZ=kWWjF~c2gHTwBk)NxcPBJU|oKg896=V)k=L^2pY
z!X7wD*SsV)Xz7b%-+<xoi+NpAfeOn}D)QEi&ox;@l$$$!3tWUP`W*&NiB&E)7tC1w
zAU20P&xnyHwevHex7<3Xd{F#G_d!xs3-ip&bGQn8e40GASTo9y1fP#iN2ckelb1BK
zX`?;pJ4QXAU*VdM2O^#;Xa%f-c73#3SEZ{HdO$#+^fQxYoIo~aS!@ulU3L!Asz=-6
zJZa_=E7&=~tKW=ri9?~OsY%kil^4UDt}2m^D+y*&^CUsoH>6B6t4I7edB}ce)#svN
z@|m-UL!q=oMXKHw!;16GNE0-F=ib+6%zN%S+%AP9u1UEl^*YwZCUPM{Fpauad2`4P
zv2QtbDLhR!00^U-%vDOd;H;2QYf;k#hz$^f?Iih@Z?x*|9+wb7`DY;zbnI3H0|o=6
z53#^;7UY5>O)d!qZ6t~1gu)LD!XAAhARq+=GMKoy+uAs%?27NbjZk7<#i9+Q>j-Yu
zw#^|a!wY3>e3{o<;dtmyxHgs@5fqat;0Z(lz(Ur)lu5v>Qtt-rJccJx#hn^FsAGwR
zf5jK~wXPR_Je1>=^@F<G458Dq6m(xSKJHF+eMuBd(T-#0y+Pe=a$bFbW^wQ#Q)i;Z
zwPVSyD;SS}Xn$?dfs*22slf>LjT@L+7TrY5fCU)&;Mz{KG?W?b-O7XLri9Mh_=BAC
zhD;JZfwlL1vwa@9VAN`>Hq=zS#ZxZ4u3vNLnhvH2D_Lq*UD-frMpYaqoLiW{lx(6^
zE`_nnkO_A9cv07+l+Rlb2KcHbC_({KrTN<N=S>*dG%0r<bS?uwLm_anmx-(A<vmXT
zLA4|<A-Uta1N*fTI7r3i9e-;4I8Q^|A3Fhnos}(+LEp%jCtSd+lL^89_yO}CGy}n5
z*D%l$ph`Tt+7S36z~&hnru~La|KW04%oriWn!Bv*ai9PMU`3lP$EgRTsBVge!&6Bg
z$%mcTJ4`M2xqlNaIgu^0a&%`0)c!h0gOBt;`tS?qa-oi;rI_U4yG&-^R1L6bc&3w1
zxGqj_ijRzpGIEx>5_H3PX1bszky26Y_}wZg`d0jPri8&cgE(Iayo$aQ7h_M8h3K95
zL~T`XnS{HjJd<9mIgYzAx4*BM+G;dacV~Jut9zVv7-}hUyhZ-?s&Hnl7D+u_5#Oio
zk>yWaqqVIey}p%&1pxSDz6}@*&bk)n-SR`GeoQDWS2R#ACZD2ruw3#-?T9j;Q&3jn
zNr#eW6_+C~oA~Zy)m=<;?l3LOwn%e3Fkm=>AmrA1CFR45#49E3wQP*fJ^#2QbwP&i
zvYQ2#sYk6dd(JbmO1Ko|WePzCBV;ZDDRz9I{j7=_rpn?_gT*kIZF9WPYjaj<e8=%{
z-r3;PimgPQy|H9%>n@IO`IXo-H9lpmV0Y*VW@Q#T&St?HHO2`ja;Tb(=|Eiqx2IQU
zfEXtl^ET#f-v#0=VmO9w@El=Se6{!6i>Wd{CiSd^8y9SG-8q%#a&Ax|^zObz&A3$l
z^)(>RQt~z%O3D+Bp7$$==<_{f<Busf=VxZ)7dRY(jn1xC*Rck6c5jovF3a>et`y4w
zPrdOvwEn<nSQh3oaBZ34Na{DTE1_4}ALSOIawA1%U>C<XRC`9XlXmV2`fJ^QA7N1O
zKGjPs6bK0IpX$cW%HCGr(AN2{D$!IN3ZG;`Xc>8<x>im+Hp~n|;vz&$ZYgdp0HgGN
zasrB3A}BSr1m)$D7e4k8_p=DER0ksm<-*u&s!QXqc0_Hhe4d^if$gY$FS}E8q)*}1
zTS%Q4GrL*6!*sWAQxF<)bhf#ti>AP@aadH*iP3%ZS73O~Zl*|b%NQ<Jz)rlZnPMm-
zSx)rR&7qmd<u!=(6!`GQ8d9qwt&N{!Qv_|RybL!z*67F-jZVbYA(Bc-T!|zo${Xsk
zL8fsf7bsMExJ9(;>J+E{I!2ad)b7`w31+;@Pa}Osg4Lv1?Hu8~orx%w=<S?s)Qp8b
zRXwSOU*}<8C$R6xlE25pY=&s&f1=x;9!AXcUVloT-`VGxd7j+@`P`Pvd3D2*VzO~G
zHoI)n{<cC7B4zXmq6SYrSmZmf=mRfT@DSLwQpHMy;_SC2lD-vD*o^I5dSCDmk;&=l
z7$5@M=T?U|Qm)Q53`Q|0oAo&@nLg)Nrz{+}Q5jQ_Y^sKSYCm<T8Gop&X3bFZzD_I=
zYwl;kwY}6hx)*QOAXlj9%p0-xRt9fhm;oZ|@)x{KoV*g(kn)O-%tI~M_$Wmlhpmzt
z6)Xw)to(CtP$15{U0~WYV<{ZO8rSEP4fT(!>jG<Sjc4Y&4-{k+GaNl#ip$W?Zr-i?
z?2x*Bk|`4$Z~p?G>v|g3&ytrMa;Y(T|A6BArCx~BP{`k*{W>V+c{g~$vVB-vfvCg)
zW(AY{LIxKsGht<an8y6+E82s~?QY!R;od`|g6-;zHzhA(4MHWB62y@A8$1**mi%~=
z36pb<3uDj3tjuBO^94CSa}M!^IMH3|$OOOdIL8dPC+sd<k<Vyqs*XF9bLEi{$#Ybg
z9*W)#u|9C%qHB2^{ou$#z8+F=9ba)E@1%##v0Ql?o);hJ$12QdvBX_eHYLjr=vy!X
zbYk7p99LQ$W@5$(@;n$6&K1rJVhDVuY_f4OxzJ|r%Fc~(ZG25Ro54vly<8VyE&nJ-
zKHckOLFFmvdbGRbKi!y);Oe3PbiNqIQ$92bnD37j-dsTQpU1hIY#VkG3@YKW<{Cn^
zJ3IFmZ<5E#oYEdHhOfY^DNS8SU3!H6wH0P?yO>BmwLXuhLj8wUsBdnlYpJbkZq8t5
zViEEJ$%_~T!c|+~H5l)1ru7O1?M7S2atI^@T0?3-lD3}bPPJggTR2t8dP}eCq#*(r
zxwy%l=FA0uqm5Tl4Y7;*Iz2cXc|?4_`eVG42XF=h0bzsq^ZZ*{LP$jBjfkPbr|@JZ
zjK!~XrIkrhqt!`A4R$^(6>vDX#^cXn6IX&)`q;y^j$L09rWPt>_swj7Na(Nk8Dw?2
zNQ#W(@#L^O0Ow{KIl2Av1)q9<4>jJ>lvRA<qQ;DeB*%ejy}5!62f5kd_5@T+7;2Gn
zl(VGW0cA`qmA_mrg2;M$c-@D`Z$8wBTM!Wu4ox_K5YTkkk>h~ZPCvP{&@<TwU1E_N
zLn!ntQ_C3YaFyl)4{ORo|CBqVx`FT=F3Hkj*@~W^RUU}U*A;1WPBbQc7HN7HCk^B+
z10(<a+s{5!;;)=j2YJys=B9zC+9MUi6S_<-vgvG5w@i=(E(BWp(t6>H)7~?k{E_YH
z$BAFc8tI@)dM)K1m7^kJq^x8gbt(YkuPucoc#f;F=#nu#cPUp40vsK14j{8Kb}QIk
zL_Ny9>nOU_@iZe?CUUL@EfIyEf#%@T`r@(q)dgoI-O4|MVfw9S@Ooww^7TnB;flHD
z<X6Tm_&qBeMZFRSMdlUEScRtZ*qrio%n#VG2OsC(m4FG0tLO8)V;j{&=5vaoZ1aeZ
zR>FjlaMChLSq;T5GEY8RLyZ5Z0&^G5=`kW+2$8;$8eByiy(wMF?vyR{!KOyGFR6&s
zw$vX2jv_9&tQI#;&eD*EHsFkA9IHuHN>P`SZW6w54PlmxFnxaXd5D6a<ydp*gAT<&
z^M(~ZBz{y5LZDQ@@D8)SyeU%60QCsEI6!83wuvHA1kG>pbGv2d8ugz1T?qy@WDozX
zpaeH%qC#QsUbxD0P+Dh9cr~dgDv141eA4KyW}l(wc2g%eA}Gvhb(pRwf&(T28kh_t
zsK+bVXMbx+sSFuSmFOTKee570<bP;M*3RYtOW;#>;jOFPIxET}Uz(sDlaOr}z<KBd
z?qyDbVBk_s_2y8Nyg9`SdvpCc3-Hax^94-_ha`*v{T*wI%-$Bqnntv;f=`B~Q**DR
z&efGpxrai7Lz<=mmT}4~`ulx@+agL6C)}E>aitTaD)t#kwrU1Jg$cP=NyX3Up3MNv
z%h_aOOJ=;{aqv}k2gzxN042A@)L1xtZ)c?1qC`R{Uk?U?WKC9<N_|~jTJlK<!vZv$
z8)a3`uE#Z5muZ|Yk5y_JHqVqFeypXPc8<!c7*>=|;;s~V(=BQ!@*E=X^0<x4S<$BK
zsx!nl<Wv7m5#c3a4lV~BZCrL-(0-=mX$?bLL!}BpEy)1FCaI?KQ)WLJUK+qmu~el8
zNl9z6aPrG|xXUgnBQ1*u%8umBDf1Ba^Rj{GgY<{RuSFya8g}luiBBof?tNla9yyQt
zI`v71$FGAi(+tx=3nhUiQv`~JctuPVwDxiHq|jdDitIHt{rfgrqetj&Z@M+&)T)T9
zcFm-?l-1RIEs{XA_KRP{s{}2nh>UyLky!KV4Z@`&fR<K-4Og-Sykl#F0(~W+Fisi^
zPq<F^#v5fG<%L3TkBW}dl!3jv&-+SRop;KL22$XpN#km_`B!!?s@5F=69Vy=FGC5y
zsKD&mr1m9M%<S_A>94D4PD?0{swM;)Xjd`Kr}>Fx_@_M&U*n?_Hy0y#RPhyGs4Kl*
zBK3;Z>1w8|bFm~f65HOVCZ@QFhLvGpK;li-$nTs;NZ8J!Dsx%#`Vc-~kI<CoEUFC6
zYYB|=MJ}?`nK9?Zm0&_Wel0D-pj-MHDnKR_s=`QVn%sN|SvB%r+`XiV)drqVF^$Oc
z@<#4iD|b?gtQMinE22Cx=w2%ARQ;Wzgb^ySUPh`BS9(h20rHuuK_(iy9U;a+6c>s)
zL?wg;RSXnidFSR@KSp9nm>0VX?c(k#tQ#v{#!L~0tP8ZsCsVuJ-NI&eRW&S~57zuR
z1G!Ku7|N<0@gPNu+Ie(Yw~#><E7aXw5&$Ob&WH7mnP#Rw&~qq=sN0G8#+CrrJxNZl
z3Q%b59{$=|9b(x`Y6*JSt)Q%c=AqAfn0?+Btw!SJr0v@U_YuM{Iw)(}L8H8a0bb-l
ztAWu6bP_OSx*k5v%qp-b{ik#qL8oO}TPWyY7`3WZO({({n1`X6tzgFoAtzF;VE7kK
z;Ud73psaLAl$2pm3&fO{ugXA^n-cnU3C$ZMS%kasP!~cx-far5vD<rLipZ2KHp`0c
zIXy5XaZF4*yckUPq2R_oITLgzLt<>%8|sWk7?3V|%}g%I4h!hFE(a~pJQ<47Qst^*
zOWhe8AWkRYpt}O!FQ;TyQc~27oQx~UQj6&zJR7#IF;QlshetTC-?hx&r-gh;DLF`h
z6)i0C=IyL*>=t0LG<o;Bum^VPS-U!W>pSH5BZO<vS+|PU{lz4A3+p!cHd##|RYhun
z(v?am{$XJh<&@A|8w9DCMdLz?I0&|80=OIG9*6g*C7ZCBR`Ewk;$?NcNoZyQD#Ce^
zT$Ua|)P(%iV+sp~#%t5oEp@MleY5OQh$ITb6%b6^)PO3BrLShObC-rXNa>7Tg_t7-
z_jAv`&#7NjPd!@W&_wM8AQEFH4!64{0(+}wcc$~%=I$PdqZCA<<Ao1ir($xpHD*(F
zcrPhBOVuBi3b}obP9X=oDLplNW&G?uD5w)7rz94_xlFo&rNm+xzh;PF%?etj;f~I}
zghQt5q?x^!OwFgUX-T!GhtKLPagl*WPp%nuU@{3@($7;|j=d%+`7MzcX*uO{ixCOx
z*~I6hT^XcV93)BeiM}Ci%5+&}wE;oM)(eS;?<MmbTxSbvxfn9U3udSx*(4GH>%xxj
zqSX$pl_yj6VnUK$XWx|N($)?(%%WP$8;e+b$LdXPnOLI0N|cDyaDp<Ol!e-Vu#kqm
ziqgy)Y+Qud!*ik;-J}pa3b2*hX;|7U@#>CWEy;K`g1tquZ-%`nO?2|!G@)085-@)~
z_iO~@rhzTe!KZ5P5K$!N7^fClgs##Uae?UwW&fJnSu(T8k8B7j^0k_>Vjy`GR|=P%
z8GgxyMXUp)I<^Sw%a`(VgZ#l+U6#XT`O>4Dd-(b8GbwyP$DyHMQkGY}8Df4>B8M7~
zkffWlY$8(>BoTL@Eq0h<<(lZ6`RpjXSQ>|kk7hk}U?-PJi!tR>2$#@smM3*m_P#ys
z%qCX)DPZTNL7%&_N8ljL7C<pms3awNDrokH$vZ$CB&um_VG5}0j6>!|s5>i&U~L96
zm$cRoOj(G<1AGR_aQL|#-;ANI4mbE5)TA~po=iL3&0J)F`|XXN_s{L#Y(id%GDr{2
z(T*d0WWi)H5euDcXA_ozPQ;HIuNQ41l0=iR6EfvaKRu;0ETVILePi<YDu*4UsYqg6
zudRT~-c_{lEx0&rRt^rBMf7vzI5jz&I!ckYRnejvh>fw3FZFMo#o@(xNM53?^$26X
zume;MDsXlfDrjDt<0Wprj^_kY2MWd$q8)!2R0D)v%kb};dcjFOP3={g+XO#~MrnZ}
zG&R?h-CifC2Q*7#OI;(hjWMerFtXVY_BM$H4?Ing$YqN-u+)|ja0*uteF!7@WdI-F
zMwPgCMtE-^rkd{fIuW~O<e?;9_+y}~hk{m@7jz4U0BawV8WdL`9@*mQB<J_e_zbB%
zw`oTu;((qWwXLm>M>>;c#=TaD5tmBYxA&Z+E{mSBJeXip$sc&#3I_=`;SkYe^W6da
z{D(CLh~>v6_ueMBH)H|+#mb+&hvKad8<pP?z|imOj7Wy_@Z0f!cABA#+!`aUBC!A=
zm#q$0r|&x@xkaFCtqjR`AP?(r=H>aw!AriK84g&h*;jYLcYxr3>0&V@{XDaHRXmxk
zDPEze4kY^>XsF8QwYB65-&BM@(hd8izzWNuF8X9AX%_dG0kwTa<cM-5ih8?|7W#3n
zItdzGmUk(!qpR;*pKO_U7H1MR7$%YR(gg`haSJYx=G+U>>5eo`(6=i<#`gj1+`~zJ
zq!0}t1aTTy8JSu|LK{k=N($oruyTxXhf&2LAnP8V&^cY(>l3VnUyBXMog_pv7aoxm
zK{Wy7xI@HRG9Av%g!{-zF5!*}t*c5Gt})(ozY72$_KAZKT5m{xJ!L5F#93qSXO&xR
z;p5O|jMAaPu|bc3WTkj7v;WGKwX57W+b!IIyMa9Q1ozdtKwt|gYU7?iSdRMVaL+xy
zujP*i2l{qWuZLxIytU&T*<2(?LXz*oTU%CqNe~8R+MgW;gEE1;PrEU@Uv>&y+!ql6
zFX$eQ#E6<)XwA$^%R;q<CYqq&b5&nB-B(DPyJ(MiVp1M?yR*t^cXOuSO$BwI3bjJ)
zECTVEnmALJEMA;DX$dOqoQyjPaNS#YUSA$R#y(3M<0yaFZ;eHD?#FuSY>nz3eMiT+
zvzVxFl+1>h5$vuRKOUS=uGALaT6x9#4YY4CmL!6`7m!vIj`7L`?nviFB!pmqB89o>
zvfdll`MNGO7r<A`F-Ea09-cWTark`-(B<Qwc<t;h$s=v^fqG#>zm>B5+Rub7k=K5D
z#eat*H=suu1@*j@>TI`Je4N1z$h!MsDkU-)XQ5B^W0TYR4n28lm&CbLj51I-ARZ}v
zj1+EJcxhsHho(#Nwvh}r^utovhjHjTl2cfF#`GPfs!R{QoT{5lt?^wv@d{VzcPOaV
zb&0#x8nzxXSMc>wwgMR3do|>%9N`e$XMzK946R(r1RlJccWYDnGR6ar86<r)Vjjvh
z#;lhO_0LnoK8w`_N9?sa%YiTT$T#~tPc8_f)qwOMD=?cIFSWd^QEI*(PK~yVv!?*p
zeyewc)v893%4JsnR=SPR%RV7Ho~1UCk!Kr5Sx<goBdF2Jt>aT#KJVNMCe^*dH&HKO
zu7;aPZ6`x#dK@rnQI-0vQ!GC1u}iy}_In9bG~!9*1NmKo(ZVio@wa$PyaoVR5}RIG
z%oyvWud^vMf~}hID;XL*G8&(I#k|U^U=omfS8t(^k7aK_KAE}}o46mw8jl9!uK)QY
zl0MyNdrj`%XFR@iJ{mDRFqUG8-}U0Ei2F;zgN4S0f;4IG=Z|DOW8-{JE39WLV_K(g
z@}>=5<1)R>rU^T4!xInN;EZv>^x{VXfn@j3=XV#Eu?g(d^ctJF<JNh~M4JpWXRQL)
z%>v(84R(+eMD^`OOC;$}VB7b(BGGn9i(pS=hp>HiV2cf;^^cKw5G`q&*8}x_z2su{
zNYB9MGZN~?qb-2}mB@}1!&&oXCcloUeie-dhYPYWYvLRmI-!h1b?+@wyu~R2BU{dH
zmzsbksO{%LYu0C9^5w<T+*Vv4-5o9`w)5N{v%8xO1=wmGYkBX^+M4y}d<lpbn;n;&
zj}O}e_c-}jPniqgv9&=F!0)cfGX`2#xFE$xnx!SmZfGEtI`+pyKkGs~<iu_cp&7kV
zNtF=bW<lsvWToMOVt^GAUMYeX9qM%<TFguHsFwZ8*K(PK$Nlvh*X|18;NIzUi)uux
z_5A$2Q1#wqxr^EZ`GbTpJdv1H3oi^Z7tV6A_%yk8y6m=KOlw9hlQfBD$m#g|o}vwA
zya!<_id%afwF?q;@of``VpHt)+PGc6_kt0_{c65vV-;UP@2#&wBiMFHOy-3hPorVj
zIfZj}G9ns9$KQJjO!20!F~ytM9@T-$bl^Mmcf6$b=vSW6tf8)FuYF5<viz*@GAV>7
z?UiZ_%NJgLcO)BxsW7Lj1*GmspltF9G_B@2Wv1bxyKfxFD-imwHIH~LT>GH&jQsF)
zDgu;_nnrP)){K*LDA?^B>;fUlG^Y|-;vEjKIfd=4D2dGM>|X81zOTMs{3E;JS$=g}
zXJ96_Z_hHe@IYmp-AZk)5F)xnkKRiY728um3)$NWe?%IQ4IeGDjqDOO2(n^0llrh8
z(%IkN-~Oq8R|R`fQ3TJcMk_L8^%xVt^_jbh;=r;&t`w>!f(8jCAmr2edO{ki3GCpx
zG@~kt(ikOV^40rRRtSL`C&=wD&)C8}&Z-N-UJpwGaE}#Ry5HPjEkj*Phh}~Or}l{;
zXvg=DJ56#6a=N}<xw~GOi0SVxIs|U@T(5_Cm*2B->c@fb+nz&0YpP9D2rXxyAAWra
zUFh=h7G{WYm?U}1bP-T;IT3|RQ?_GH4`4k<#NV2V(mvcPCQ7pvTuy88pvsmxc3K3E
z)_7e8;jcRw7a|HwYKEeDmQo-i^S!kFXuT5GOPgWlsF__oW05^=I7=N22}~XqC!x1o
zK3X1p-bJ<OEQK54NiXam4$Z(bW&$5Rm!!rIg-Zz<O3`2nf;xv<H_{(OZh*lFi?89O
z8(}edo*V@~lG_R3-XFc-N1BSJer8)Q8D*X#Mn`rAl1<$60Uu(z&9krkx#i@kRW)rX
z>WO67d~X@<Fn$BNd21Dfb#srAo9*qK@e;OdFk~PFG=?eaSHp&rPb`N*avxhesgNMw
zKc(#$H!oYJE%xf!ylt=C-(706pJ|&S)!X@LG&z6CBH#?yCP-^LXNXvJx(eZ3;G6}1
zJp=IU$<s`GB>2AW*n2^AjFI~ey@K;rnLSp*iaQOi-b-6LBi(-t>s^E|TKuvv8Od5y
z_Q#qd#I0`Jwc432k)T9j{Fqp!3_9bJLw6M}$V8%XO+F(=_?orR@QIrIQsFeW<RrtR
z01`oB4TXu}Wz8?eLRhF>r7BCF`ch2j6&H&%9?<dYQI1T5;2wn14h5X1%!wyxDW#8P
z-dUX|VjESV3K=$^M9004r&)$j+wqT^RI>KXe6QW(vZmH{8Hv#j^y6z!^`g^?ctQtw
zqz&3L-Mq5z$RKkTQ>7CWb4hGj%Y~bUBebipl1C83VRI$iX2p_RqaR`xqR9DSkb+tI
z*jY5{EFV{fZbH^4LQ?J0Or;QxQi^tzW-dcr7uv3v^9xKR<FMiw5+cK!Vq$&iHxd=G
z{flkV`I|BhXk=*e>^Z$%wFa1v8@c2)7MmL%*#n&!(I5Q)qjm`+p-xRP@m{vrJ*{of
zPH%B`b;rocb8kF@F;{9U2r<R|-J?6Mj>q|eLqx)htkMW=NEFU)`b5N?w82pBgo|X1
z0iyNn^L$Ri!z5DXGi9L$M)wh8rh7I@u<poC(}eJ{BHU~a?WXxV?^c;Q5F@;-j^2QK
z9IP@Z-r#)jH&a>W;*V2iboahzpCejnMt6epzbkzKWCL1u?$VsdpD@PXu`5rXRaaX+
zzd~mTCX6;44RN!av)A559;@1TL<BKFJ=Dp5p6yLx9ALI1M{S=*I+EFBe44R-vazzJ
zR~fZtby3N4KFKs_-Nkhr6KDs%sXgl_15d-5P0hNK)*I?xO2^xJ&yq@d>gtrlwXjfv
zITJY_YQtjMJsw6ap0}1vE{mC34WXF;k*@KDX|H}tUX|s8sg#WiHrtyGTQxmL8KnRs
znxm8~ymN1wSLR$z63EJ`=Z@`n%uPdeAGH#;5+-Kysjxe^w=9XBka;R_d+$1SWj&l0
zF49m?KfF02ryAttpQYU*0G=JLZXBFlU*sgN`K6KN_&cU1V*~{XoI12_CF9=W>_Z{3
zb*#ReaoV)nbiR)P*_0@28zb@8$9fOqM!>uej~z{UgnM+9R?f};u%E*L@mh81>t9-w
zZ*rvXqN3WmIW^3uY<1q#bF4o-!?JdMQl6L^>H`^oRu<-|3YumMOc?GnWhi=)f!)E4
zq0v~CC5r>fCID4IZDw?go1SS(sU%*(j#<y;npEV5-rM$Cj;jwvuET1jG2@0<mn4F3
zP>@?=&QNw@8Pw=Ai))xM>BO~bvCgm)(Z*Q%xZa^w0+${jaN+fY!7akX$4Y6jRo+s>
zpoW^aLmR#h+2r2F4%LycaDN#gcN<t+^2VX4I@eAuPqYt@8(+c1Z~P6rho=o^|9MfJ
zMR)zm8@Rr~urDhYA5>_k0Yf<!IQLxSkTfLXWg6UrT9f=~jdWvSUoN1^-n*yLb9CN|
z%q`!4T^vg2<ywk8AeY>_tT@8umF~R@MlBG5G0j@}2+C`|Ww9wTk<NZ0kVqQ@xATQ9
z)qe4CIT7*eI5b7OACi00@&tY$nq`LhNW>Mqi&w;yEK<`u`opHGBCD*cTnOlE=BS!a
zgt7|H+%Wc0nj>Gp&lZuWcLp?bs#y*0zSA<4$&-AKaFdFKs%qm9PgN!)F#B@BtFuHE
z+Yd+cBVpKZW`tG}%d5R)9wNOq%Qqs}Er>Cm&w9oEBZ;dELZ(eyrp1*}2FVQYq%qC1
zQ>Dc*T6_{y?dk|V-d~dvVF=?EyqR<1xo%(7a(81PE)SvBglZ(~l0jE2C(H_yG><(>
zx7<P%gCZbw1}8~p)}<&3S~9H`f~+{=;@w`i;my8wcD(T<gQ`H~NJniv*u*nu)_we&
zuBU<#a#--`R+D)uq<=^#+vqar=>nAo1mK<?%0P~~=Uroqo6J=DLg?y}hpiKnajdLr
zew{vc;zsSd_!P>vO7R%@45^u{I-kSJ{8P2$rc@|t5qk3SUmpBNYK8d5bBp(h{H>7u
z*#kQhG7?5TfF+}zuAK>-ogt8z-q7BNnBI!m8enZ`qzf>I`>vQGW`MJH2AWt|65HBa
zYJX3LKWVdmeG&xUym$h9f`&X5ia)>=L<EFii!fLiunkop`7$AhjPYpe7O)r`izbwc
zD=tn<Qp8K6={DZ+f(G5}Ho5w?R|7{*r<!Thk(ernVpH)GKT)E*k$Y!Y5GqLlZ=Ma?
z;r&3hlbVb|QlMP#%2zkX>yG{)F!)Bg)-Tcei`Y)^-2j}ADP~K)x9a>Sq+i`;u6k}P
z`{b_PQ+fUew`~n=>;X?wEJI769Rtt_2-z-x)X4+`(Z=O@+PvIOV=rIp)uAr$nf4x*
zN9J@m<jniSW%O;QZ)TPAZu=M^d=El>t5GETkshV`mP3<&U0{&qmTI^B>?i$E56B#z
zUmZL2sX)Aaa;V@*5Ai46+%MH)5%I#R^GV<4=mDu$nWfXHq*NczErQ$Nyp!1NFJ%D<
z&J)glb4B4$q$)2fxEAiZ><UAIBg=+zGa74{u9f;3du8n7v0#0{T_}nPkUdtG5m`w|
zWn{DX1e--Yx_OGZ%P~Sm00u294hCZ^{8FgHnf!euhOb-k+?07rlhE2rSbfv+rcFJP
zTq?!DPNSG`9lwOFz00~*yO@{!k(X9}r0<OYW(C3vXG~r%4)H~2ZP~nD-7kRyunRN+
zjWd>fBcP`qye#LNb%~jVjx@oLDkgF=LX@P>4C&8O+SR=C?7K9r5OyqgFW(_K6FHrk
zD_>7y1#LeHJ^Z^pg8Zc*eY$r4ei1)?`<?dG&Q|~5`qTe=G}HfZwC<C#RomDasO<pI
zx3|>&_t{`TLY{Q6a~DQiIFKM96Hm>O>;L0y+S&k108m@|snt!XErfp)0v@X*wnU2L
z_{_wCkdUCDz03&4_9KmvS>QJfoLxP;8k`M3G^k>wk$^-sM|a&C?C#a?Rbxm<7AnPg
zn1I&7mrIHhX&!-G=nv*8scCv#TQmx@4bh~Ckbb1Kt1!N)h>bIn?JmP~jW>4b*4l)7
zY@xSjfMirQf0F>YGE#=ddt$0v!?~98RUvO$v~X1wOT)Lf(}VSD_`*_STkjOfUg{nU
zLQx~@Z3Nz|!Q8I87Clx-@rtB#F|xBV{D%ucZB0fTEu7RF`+}VzFKpJAZ)Yo5heS#z
zSmosoVEQ!+88ReGr&}He9HTZ~Vcx;ubXK;vSZQiFbhQZOFuf<g(Yd$2PhV(-j8k$h
zNR?jaHpU9aWL}5l8lcBu$h6;Z?-6lX(R<5JE28dAn<J;AuX{yQHKKq;k{duJHVR!&
z!SYVCEgsNc32vYr#jAlHm_pNWH9sA`8)nW~{-xtnGqk3PV8)!an%Hb^VH8DUxIcQI
zk;bADuK8sOHk=?<Lq?hExzkW=sqz6~*(IFkk^8-XV=UetPUL$cXp~S_?t}KP2xrH$
zVlmz+wOQz2C0<|=M~fa7riNAy_{+pwX}9WJJm$272s5Ib4>Ok|Fm-9wB#5I7arE;E
z-0(8QDy$x`#+W)V2-i|>3HouTz(+-|`?!BJN+lKI+^t3==}J)7J#)mPU0+`+^kKn;
zP&te=Qyc(>X|~Q9w<Q?}U8oaM4=+uaF3V_=r2+NZfl$@%6K<x&uc+(1x;Rg-D6qB{
z22ijJNvz%9r@BOy1QlSDAm?cjG+^J8L94)&Vl4YMuuC0_J(o-irOg>C>&$iLe<0O!
zK4y_L3{Zw2^)exEi36j|QOn*V(+i5|+r_*d+!&S$HNYA=_+%4OJk-t5!RxC{U(@1m
z+0|e~I}7n7+tK%NIOO<R`({@Vu}lsd&;6uOzd#<;ass7n*raDrHoUgEV0TQENFee9
z>qR`yK$!EZtV&@h1VgB?4WN8q_UOqQ*Zw#C7aY&v?k(b?)-t7|^+ZV}YzQN=aRjm|
zLNE^VA1O#7AFZPMy+awqRPz}JNSQgvB48f4Dec*)-qsA0j<i;(t}?rJ<=q6Kn!g?j
z^5XVE5-4aCau@;@k2lq<7rD4YWK7j?rrwH&0aY;_`YzoDfKSOX#mw@2&i!0;4?*QL
zCuB2c{8<d^{N@^Zr1tXc!-A=cd#e4ZLy~2n_gGl?Xm4o%t0$wFGAldwThv>GhMuuy
z!3mn+xx0g}FKLM|_a<9(<yMbkK^`$2@E}W012)C2du<twBNnBnh452F*5A?uc&}H`
zk<UbNKfX7;!DQms;M3^c@UxU}K(Fv6_}B@6wiG+us%6h6#nYHUc{dtE6rXs<;Xk^{
zYH5JTGvJS&r)>1rg6SnJaF{i0oXs-rv<%%`Rm7yWr$ps6!)opEg;nlzE_eIDC1?c>
zkATD4ZS!!KA!6-x!fGDCwfon6Jbx3nL6*6D=_#$1UW)S#)R~E)?!GDcJjLy;l-xD1
zl(Y|IEaX*;aXqVE=#!!h!8JZ`+ED`yH(IOs<^hyc1~}_|laX=#QoRzaC4<$aRP)8o
zTx7go5eC-EX^Sc5uazgnE>Q4mU6zN%(b{q22L=e!@cBzy*wd+6r-+qbE?Z=#8mU8G
zJ9|7J`}7P>E`uTN!0@WxT#hLbci=zA=p=P?aQ1zX2p#4|EHHtg^C(B-@i)~u45LVb
z=u=1gt^8>=Vh40KH~cmq`%7m@%s@=}U20BDPjBd?Z*Fg3$V19NtHDT1Z2+(Xx;YqH
zI=C_X^$Gm8eZkhy&fXkoNAvUt23k^LhHu08f97O~&4$zRPfmO*f07w|cjVV;8Qi~|
zg8NJT{*y~o|Eo(>-&_I(;{*9`+cLhn_3ef7-TZc-gaaY|>tCQCI3O2LWES`lbD%$L
z6F<pczyCw~r>z`6XkJg}dG%C&H!T0OvEyejNKY#kt?eABuGe?q5BnYbpKJf?)`OqH
z;7^Od--3VMi15Fo|FhEkbzj2IXx%@dzt6e<396R&J>DPo?-%;lodrKbF`gE@zm50b
z`waex3mpE={bB#k{Z-8TGZ*)1kHc@d|CToY6W8<0@43Iqg@5KU!u)~z&*I_VIq}1p
zzX$)TF7{_9KEeLMiC<K*|HSqoApNUF{WtcnYQUe_@`%4@|EvxCC-MiO@8lo$?@|A%
z`}>)^`UmpARDk~k{SodD`*-NClC7Vi$xnUP@9wi70<M3emYDuN)L)ZEKT{)~e*B*L
za|-Eq>>ob-J>p+;3O}<Co^}oVj{QBu@K4N-QQzbJmHD4u^VclG&rHjwjd*`xJ|z-<
z8X<mk)IX3v?BB!uHFxkca{mv=e`gZ@3H#&b{crcvuWSFGv6)ZW+TTU`_e{V)(SHQ{
z!~Q+!Ul;g4)4873`@g0CoQ3%(bl=DCRs6&L2mOB+x5R%<OTG>2-^PD8+TWwUEtLO>
zh~L|2^KCBhzYv*zAvXLEMBTqFuK&q{!E)>W;=w;H!GBzC;-{El=>8n@-#z$gLH@Hd
zYI6`W-!21noTlwJySx0oBEDC^f7;lu)6*Z$cs)7e{FH3?UETkCvidXjM?3p56Z>KR
rj{S8q`ZE^n#s7l+=hpp$_QT3aK|bvf0Rh2!dRsol9QSl?5Rm@|$|(%n

literal 14927
zcmbW8WmuibvbJ$|4esvl?iSnv1eb-oJHdi`un^qcg1ZOT1b27$k2%?UvWMAca<1>?
zY8L#ttKRNj)m7b3E69L?!2td7Z0N_T{m&o&`h^Pw4J72`XhSEVphBl$>0}D9rc*I?
zaHO-+cW^YeXHZoE2Lk3j;5SnE7Xs>k5FrF3$Ns=TK&GHTKoq}0&>Pw~8{6xf8rvKG
zNo!FOvRGn-Yq?j4a@SD5%jJROuM>uyHx91Sy4T0ml7fpwGs@q;KBk};-qCA`*hJBE
z_m+1*%icCc<ItmlO_!yJe1MX;A%aceq7%u1lju^Wy#sxu*W=^lPGXt>ifI>$n`;6i
zg1PIoFWbx@fhkijv#z@vPGE|9mN9iU{zeh!h8$Hi^@%!?MTRRG*0mj2mr-OCgeq1%
z5Lnmq9f&Xkub=54QvnwlbF$CekK&JuMlOTpM_3k!{*a`zWPIUJ4V*A<LB2KS43y5%
zS^B-1Icz~$VDh3&N#5Epm%w8H&->(H#iUmc2bt%nCfe@Yf?5G-F^yX3EZ2?CocC0y
zxw>`S4MY7&Ca7Xd!bvz(VR!;qdxUbjf`fU@K>X_>%{4Kt4a{<br?PokG)z$GT^TbI
z-UYZ7ger7Mg8}R85sBv=o~Deou*GV@eZ8|1ibd)b-rX?M>?ZL@v6F^4!foS`P(9U6
z@JN!(>}~$m`Ziu$M?@%S<(D3Ai6z||hJTOe&nYq2nWl^RG9~_KRKFWfV<Uj0jlH3b
zwF$uV&k@z4rnhy|fw8r>F#%W_6Y>!nSn3;E!2H|H&uOEXG0b59Vj}IOk^Ih#iKV`U
zG3TEK<obmWIth^iSNZbw7NOW0^(S-l8R3Z->qNO(9e=DGrlVoDPG3K5(=>2=Qlu>_
zLPJ&oNi$0fU=<f6YyYzLp#dnr@6dgFXA=JgW?(XYe>1*zzmG>Cpq9=tMI;-7_bqOC
ztHt3c_>8vMeG3wYfj979eK#pO6a4lv-4P*yfXIL6yD7jCU}|k+Z~UkGR;u&X3+zZ<
zv+78;ejq_)z*fpRhsr2C1!1IYDLD*cm0t>CL>YSYrOapdX0PFDwQN4})AC)Xj)a#_
z?XxLcxgyLcmcQ#En*aW!vor5<JO$)d<lIz&ZAJd$@W);w^gcn*y+HAPdFPKe`N~B_
zG?(Jz%H$ce_h8xG#Lcx-67zIeN*~~U99)_`YOo<%e4bNZG|*XA<HPH>D*)i4a=NZ=
zX1kPlK(X6ZKibvNj9xF-s*W*<#Ir{QL|Qqeh2R=>1T~Ib%4%M7Tg=IEE8$4*-C4TQ
z*;(vEio@(H&meS}ePgsP+IuWUytX;!_l^z1pSh0{1Iy>n2frvf6Ai5cP~|A}nXv?A
zHmU+@H<brOajLM1N0CfY0w$A5r6oYSc8Tk#9i&h&4Rdi4GyoMPB|fBa=y#cknUT`e
z@~&dZI8(e9HjvVqt-^#P#sZMeym`zxNOInTfky+#zR?t^drRV^D_=3_JOw;b6|Dzv
ze1j0tE+wgz^uk+H&JGB>H<$%hFE{y8`ILv*%={EKxne|Rh9?h-d@eh+ZMMJ-IB>qp
zT12zQp#$l~o-8B?mQGz!nP)KeqVAYr=+YZ6^P3A)NxNYM5fF*DB^YKeBHXetenKkS
zYa)N#w9K<%=)a3e+Nq6WwDCKB<dPN&=ICF<Ed)KG%6GSb%_EST(&w9JFRTzlCg0Cc
z88t~B*jA!nu~KT{S#2ZSuN~Xr+UHcF@6^Qra1|k@6&fyqe$l^NM8F#6XXJPP-f}<5
z9@y{Sp(7vg9#?n{-h-#hyTY(K0afiRm|0d6R94fuj?xkd9;xs>R##<TJeY$%eB)xg
zI)k^X8)zC;sxPoM0_)VeHkuK3{e^EOyb>6M^%YW)GKgN^c7GYwsm~UP8vjy=-}oFJ
zzTQgO5ohA9AWMN1K@ONEnq|K>Y}%n-#2%I8dmCDe$aPH5P@l7l64{OTJqM_SM8f_S
zF1BKmmZHfCA1pR`Y>VEf{gO!BYmV4n(03@02ZRFhq@Z6f#KMw9D0Q!ogj!s0hvm(s
z7<)Cpm{?Ako!2-DJ}xX}t+YN}!h4J&Q<&R&(gwRUCC6`E4JP*#^`iDuD}Rb~EJGz6
zXNaUXlB@9YBUo78=UsgeA85sM!iD_a1drnKq(|Z*WZIdI?uxt7gJ@dY>_Xse6KKQT
zvTTH-deQ<?53@s4zuT;<;g`iZ0PB&rdWi#hN00$^8aUmYBz8M`R0D1Cu7+mMW`mC)
zFb}iLO}5Hl)JT(YVXm1N@ExCv9+=p1Z0_^P@+!e!1H(Z&7XQRcKzsAD9{x5k032-W
z9qA2Ceg#gxNFj?ZM!3M^C-g_)OgQIV<KQ}g2I1IhV=z;Y9UdFH(}v!_;c`Y?B_7zC
zm;CW=m=G9X#fB}{wFjuUewvKaN8J#?pPkSzLNkvxu$h{az#dU8wyP6jf1R_@Uv}_I
z8IxOuNaqrNT<XV%Earf8ZID<T#*+;65C;&M6K!gG1#5jNnh~GbPLMIedSWZ~kH?&S
z{J!|pyl6u#h6fHnWi!=P?=_-mKX$;1r%a|)bM1>bF+0s3QJ*jE-5C}Sn@-o<8F|kh
zeO-1Qt}I5pgZyjvaAmI+%e{0>z)S38`CZ(!wKt|Sw6U@RIKF)RvA)o|>04R;8AN+x
zM$JDkBK017ee}bx%O!0L#HYSk2&T;KHc|_?B^jWkIq2eO44dwuYhi=LGif~@8fDVk
zH?)InC(NnxO(}>FOH@tSE8Ccur@f<>gabu&FN*_>&1U$re9kwzioX=&YYs*NWk@Xs
z9=vj>i&||IqHKBS#ljR3?576)ZI)hAd5OCgzJFrg{9U}IwARYjLxR9^qr?m)4tczA
zPdF5MRRH@N25jG{kKmr|kxVp^a<^Bp+dMZ5{gjZxTLGQX@tGYJnK8tXpN{luav~af
zVpcGPa7)I^LW^TMtBN&pE^uhMxe+lvSl+`pSO9b137&6r>z_^-3e=tEtT1X1McArR
z6d3^^i&|14S!*~C4;L~p6YV1>9I3f(l&`)x=Aa&rU*_*BI{zr>3l|tZQ|rEAdy0*r
zB~#k5?a{?1N~L)!tRHSmd`5ic`0Fr%9-&c)z6?=31P~DQ?}o|2#>w8$*xv20qoboT
z{BeO3sr6bJ?VCP(w6nZB6j3W3v|kH&tc(Umc4D!W)l{s6Y6?E8{XECq{CoT5{2`JY
zX?yu=xHma>ijSU`3FRx>QP0nQquC_UHj!K%@oURww<#-eAsCZz>_II!_RI$czAfi-
zC2Hy?WF{5lg5+R*?Z^-t=f#Gyx;k&#!B>!1%}nG7O;?fxzenmxW_=~<&hci=bn-AI
zT3ynhmqr;aw@#T_YWg4+k;B9g=0#;^;BRPO@|hjA4>ac>Mmkr(=i#2f6A6)|1(!T3
zJOvyTBJ3R}4akpA8zQuqSL0it5M^>WiHs!YqK76V<mP6()lAmsM<`#0``%66p;je|
z;Lxp}Qw0DC>M{3S`T}o4Usa@zR!CJH4qrKYRqNR3%DkUzHMd!k#JT<?*;#M<xQ8uB
zLL7~Es;9>!v@rX2uU)!vx(Fz|wD|_FnMAF8;6xH8xe*Chf?}Ohe#A|8n>gUT2n%Q8
zI(}D+^iadl$hG|yic)0HS6o~IHJYBbZ14}x;A@7?_?P6PM*ZI%8W2(8?PDZ+5PY7%
z<%^~TPx?IE)$|2-wLY=JNiInG#zt>L7jAteREoh=7b*%72FI&d$WQKj)5y|UKRmy$
z1ab<_VcJ5?;mIqFd!zB0FUw~@a)3>aiHU7AEYh=R9eP~s>rfdf3uB{x{LJTG23h(v
z>x@nZsq1YKxS4HyCtY0FL;q72F3pcLyUUlQ@ztM6smi57B4L7$a=w8KkaO7it$WcL
z?|;TL<>bkzORdeA3>uLOB_cJHJ!|E?D+Q!riXF?nslqZEL%+_F<#aQY8LOlG(A7e7
z8y13SfVfpciB_i0dFh5SoBLU;J=m0e5uui2Qrpp;!dNHan?fM?VHtI+m-@H+cd@4l
zapu&9TwhMQ={FaQ*YQU2qM!lc@AZ~it*xiz*#Y00oc;8JpVI1&wCc^mq~A2jI_Q+b
zD!FJ<AE7Mq@YdZiU>Q>9#d*}rkk3_msaUoi!mVaKl_h8pfI7E4Kp$dF2EeAf2w^$j
z7wnvGq$l`=Icv!r8cS!L>4XaFz<FEi+wf-gCgQn%vgl6pY(Wa;7!-EA8!Bu>;!%Zd
zGp>Jo?DHz;G~LMuxPt%zv4Q<QUzU{;5qqmF_GhfrQIfNne<`u{)seVreaGP!tvGtr
zu=VTE`=zUK@w7tOIMwt9VDFA4xB*S@P<kPro&-iP0791tJbz=_%cT18^hPMeVG>>+
zuP2D!s7s(BJ9ApIS;xych+cMQ-X^3pf_Cto12aS$TVbObE0DhNcPA2r7X#!-d{bRG
z+6QlJ+X)N~Avn^$1VMmf5gP`xb`Y%B;?wzS6^NWf6vrUGTb4ED>E@1I8oy+37dfD%
zExPYsv%>&bEwXR`T`p<aI#r%4e;5zqYz*Q=u@#w=r*m_)xjs5Lf??&iAz~y=2O%fS
zfKKz;kG!aLC>e6x(b+*U!&4;43+WN;aZ88ZyjhcgsyoJF=DgrDeRSk7?7s`dz&@sd
zQE6~~dayykoU_A*jITMD-M2HYUSpUSEkb(OxnI(ydbb`tqnLG)&J<93x8gI;HFVe?
z5M_30;)h^++q~C;-q?7&s&@=4qN8o|sGb(HA=2H|)EFE_VA}F*$e;Q2PB2%^q^}l8
zvqQXCJvkH(qq*~%*e{*cqL$4UYFMTkvKHk1(P}VlHCXp(1coZOG>fLCJyiwy5bLr@
zm8T!sNCM3BKvgt^R0If0v$B*TvL=yZV=sm7pmvH^r`kk(cY_i(r{!06=EW`TE|X%8
zA{5FDA}gw)1aWl5kO|&Q>KVc2HP9lqQHNLq&#)u5+W-}-t9Pv>@Fl9Bp=s&Cxz~rZ
z7jhU?QXDi%qfh<YLfoW@!c4%L8UhyIDTH2dJ}Hr?N--&^Vn>XEDVv`&HO3`K`dVm?
z3#+|Dht76d`;a1KTZYDg@s91m0r|t2hgK+}a6i~+OmUX}#~TE110SHjE-bJuizkjR
z=~38ABm2$5q9i6HDkny7W%TDPrW>wA2w;R08|Ty2FJv(~hLBMwEjj|2hmggI&IK*o
zeB>5Lcd=polz7C%*MuoH1WaC+P~`yXzy)pq15;_4pjc?+7so1elerGk;=n>oI!*0z
zJj*`cWYZbd&D&?B6$0(z6ZjO9dq7yAwi<vPlH20>>N}Xp>ux6c;=A`tqx_BkhL*<q
z*1GzZmh=v0f4&0EpsFPG@HZ*NF*@mW>X&~8XzBeb*VkdG<51&Rl-Aevh2Oas?(Q}w
zy8&)(k?Fi>{oMuADXF7x#0tT0#mIUH>0fneI(=p{CK?b>KRXZ*>2F-Jb+ZImJO0Pk
zORbiN!@PLxb4CV;aXxj9Tzgeq>EK<W9ToFo!P`2=*tC`w&LM0N5qmWthz_9GopZ12
zd#CFaA>@w<+HZ}uHhA6L?;hU>AkcI4f}74yZKx{r(!}i%*16@%9)Y0K))ou5y!&32
zwVI$gn_Cn<954vsR9Oi?QNiJJr=<x~>PZM?tJ{)VDWdyA_M<0PbB~mfs}z3eT~qJP
z_qrcIk+kn-$;TOh$)VU)Rlg>UelB&>tYM$ddoSM0zn;*1qFK4QJf1f=F>YwdQ>Kkn
zys$;C2GD~|4<4B@E(w_G^{=pNgXAC24wuNzSjKy=Ju>QprGJcr)CXP%hoZdqwJNtm
zeN4X))W!ItFa>gdVZGn{9QKEf8znBh4eCj2?2S4Y7*#86R_6VMM0aO~F<I5q-VKX9
z^}^Y^L}#@|(!BVlz5!msQ*z?Rluzo9SKswPqhdH&PSIKT<@`W35(=cjSKOniOFBi>
z3MM#HK?O5qOto{*%@ehLc=_A->41y9E0?nD9UPC81%GRpO6)sJUAp^OgUoZ(QfYD+
zs{=ZQsg^n!MElS@Ax{gtb9yI-SwYGmButO~=#4ILpqVI+un(o~Iw*bGG{6`}JCBkM
zY#cgFJJU~8$5kpy{JBbo<35ocFR!p=wJUT*P$5A^IiY9)Lc*`Lhc7+T1M>We<-FYp
zyvDx=8!`kX`a-upD*{>vBX<i{kbt=sevtbZ4@nE^v|uFt-EMSw_L<cj{@_I*)CdDT
z!tw}%fA-{c(sn)tk~o8)e3k*u`obiyabXj*wMz0jKK)le?dqEx(GJlXj&ZKS53Ms)
z^p08R(bJlWOqBqEMIyQE6^ewEZU#@R2iJ$IK7j4R)9{1m)05fK{a059SI@ImToHn$
zw$E)`-U2>+dv6W$zB$x_@j#*5{wS>d>|ZY0M5R(UVF4>FIKivS(>+T_7V;^4krd`h
z-$Kc@eezQubIRc-xouSwW5)4;1^fLTTi*0BXfYjN#&79#l8KVWDUS&QjxQTV;xuX>
zUHkz^m~?lBDWR=cMgeZ1A3`4U%vE%S_*Ai6eJgw6>1!aY@WP}|DB)1oLl~oY*-NbM
z)Qklos~$C2zJKyBH{Q$;6b1rCZW9&02Eqo3?eho@I*LL<uHa^VB1djPgTk|z&0mMJ
zzlSn_)AJ_vy+|ArRoYLW($9uMPx~C;D*V0*mgxu=cJ~Xa4L7|kXf;R;-AJ?INu*KK
zmzHpZ#g61}ITat#H7(`us2C{Ft}8)H7%wajkG;^q`-<<QLX~^eO8E4lF)Y6{_$JM-
z9A}+m6-T&oW(ma<mA=jUFhEa?hmFr}I754LpRL&Byi0wyqo1cgrk4i#47zK}J!K3S
zvPL?Pu3xQUj}C6;&@S7D%i6T<G|#=qDT476(%EGkr;(II`O#<}-8Ht6w>Lwl>KRzD
zRwUqGOY2R<llTO81X^+HP7r4-w|yMdm)-;K5H@5o#GewaDqI9-A))6KxgTwRp=Q(r
zqyo2;t7XY%5bIaV?Cs(PvY(og3GL7#poXad+bn!Wz4-Nsjno5ZA_!-by(Ls@_;iV%
z`#Mq$?^dvoniX9UL}j<Uao9b-+=<OI(8)ZB8eRuHT#C0bIiht@%PPnk4iRoF4<s5T
zX~ga}U23kciFr>V{jK_aKmxT0w2bgf-qOdkK;MARNC++T=Lin7x{&u@<+%{R&N5Fe
z&Z_aBMf(=f0!yL%u}fv|SVXFZvk^e7t(!Vz(RB^fd!31cj+~hA$5HC{&%uT?Zq%Ld
ztACKOW3cU)jwcudpsX=~#Osu8jWLaOM3>F9Dfx_~`Y+|c>jzs(I}3BxvOuEyl_b8?
zIYd+@Hau%}Gc%DkUKnGnb~a6uQ$*s;LsFr5Om1=p5kdQA5S)~iPKCmy5uM)g5J!Lb
zSz{hJAdD9_%hsx2{4jD0J286h2c|;`(3>6gL0);6{F|%HdE()HDcFXGaR2Fw5!g=)
zcv~1NPHZ`)U}2=|Wvubky88@Lx`oyl*E_OYIj6aA_lWK_%{Qn*Os>GdP|;M6Z7Q7j
z84r%C)ksHSsxn(p_jh>#(piHa=!Sv%8wFv27*apT9n1_{>3k~Gl9WZ<9Q<LMYtxza
z9t1rqbUuBQQceLX6nBoFbCz?_uOYX#P>m}MpF|vbc#N7cdSbwjs%r*V#T@TujJi%w
z1hpaW1F5z_$Mo0(Cc_gB#8({_PH0UzDK!T#5oCZ((TH3#)(U<^7bBwFM#_YYk)34j
zA_8SOuMyORRY@4WgFX<_5>F*NV|HO}&r^xc6D)x9iiD6|cJGlbLi_LySf~Q!nHkuZ
z)F!F{F;`tvsrO9{^LSQ=y#mP|cu;2(=eOT?Z#Thb#pxY;#;H5uq>-b)85Mo>@3M$a
zBeBAYnQHKF$&f~pa!{t`otyB?GGlX?MT?5m-#0h9FDpVdq`+-duFW3?BZFK)6TdYI
zfkEH!$@6=!Y+p|%F1VUyNdv*<Ue9+;6J@5)isC3DWG(JGZcOi#!YwVqDJLv=lnqF$
zDMA()vWrKkRdh#njWQa!od_uhb1Z@=h^`^;LY9KiKuS8Z-v)wn@$g0pKb_?aYGJaV
zH0U|?&h=uJ#S;9o_UT$u$qoKm?!pmxo_H1wG*74)-kz5b7%zw4h-K1B`NWVg#CmnQ
z0AbCKci$Yw%6S!)3Kxz*#I-h+yQPab!CF8n0fwW4pr76}J}t%mAs83_v?*som}~9v
z_IpQ1M}3^x)bPk>0#QhzH{pFW8W-jdNh_g*Z+NXvy7HCE(Wb{vkX;({KFn;PYG;aB
z_<M~al6M++N4>$Qao4sk`%YArQiM(`L5VJdoGiG2uU-lkLU23)*2#+nMy~`Rc+$Pg
zzi9xSMII--!BUSv6EzV&wIAFSwoal}RzE{d=aOqsM<YSqqNpVSE)g4&MJ)DXU^O9U
zEt`$dE`H4fi<4gm>4soRBr~AZan!?CS&h5`dJowV+b-*E%-)3XSt%)zJy3UZR?|Ln
z02x9}r(NRIp#?oO3Qyq3m@qX`g_%LV3Xc?6gXK15pD9b_W)(D~o`vhRza8hudd=H@
zVatM6Io6~-5vkglEy7XevJ_S#E?{h|@A!j_(RvG1Zp0?_xE{AS=()L2f!-vP*$4PF
zMRpwE;YoH=MpNG2u&~Lbj(ju;RMazvX#C0K*Z5suuMon-;aA4;uc|YZ^O^cf<HW*x
z(vLmPry+pZJC}QsFqUpx2~+5csJ$4wogo!(wafQa61>j8tM%gGvtxz!PZ!833|<}{
zWUQ+*^p%f1LHG@P-1CrJ30`x^RlWVOw2^VU&*Kbt_{B5bGf#&JD6f5V_ZYL>n;-6Z
zKPf}?2D%Ngv+e0jbmptJ&aN|jo*O&{ZH2+vv<O3Gu~+t1vGy9m93-e!6(?eRn|l@O
zb<7aZ&UQ~0-|DWxsoOI%B7Yq`%wxlaPNdGmb;m`|^TYT)E3zEujL)OML`aPhqH#t~
z-DcslPgZgo$V7XedMWD=WB2OlSL0{v&M2=!Z$?Sz0$y2NR=_|_7<s>_6f3fs&|A|=
zS56&LXtT%|7+^dWZzrCH?8T;L%KZlvrpaxh^!!kg0!y9+1ieOj`sl)XWn79u_FK*}
zDBABcRVlQeT>(4DG1ju+5nd$3Yi%-TJ<()X6LI&Y1CixhzVQQdn&MhlWbIAwX;w*j
zhs$eUqCp)Q-dDwWbk`3{VPY3xMr2Q3<S?T0{1Wn?(8f`TGxV+z!bkSP_aC85&)ImX
zxfUVNuS*I|SWt$)A8KyUao}bs`w-2>(nAGgD+Z%1*io(^V=9$6-bPj5jz^tm`#f(F
zEhVq%*g`oDB4;F|N98?*e9JY#x{dNiZ`xblEdaKeRbA%e!al@DaRxHEHefz9dB2eS
zWAwe}CVjMd!pm-v<2s8&n2#8H<LBB74CFcjC6s9`e+%XAUU-9Q|4Nil7{|{y-s>dq
zpD5qN;jV*8s5(hAlUpq(tKa-cPPNLM;S0Jfg@KLiuPZtF<`_l?&B&NI1J$Ew_#t0%
z+_n6eQ2-Q@GTphgt-C!2%Y7AORaP+{cZi%#3bR(XAW5u6VZ_0lRHeSXg2a#jeIpA$
z;zO}AE{bxizJZiqnh?32Y?UAv4_R<WxujL$bmGB+tF+=8{8x!KfsH(?yL#u!OoKI=
za1;Q?)IQDaG5LEDZu4F?2oaAua;=ZP4TN&~o`^Hu+meUFl+AfFNx3tcE^^{UU9He>
ztrYFh3GYHPAZ5v@!!fjZQs|vqkNQI~O&W;WLV(_Ru{JDQr^$0}@<EarMEmlR&ot6a
zv8N7-pzi}>ec*HHhp|)8zGVmqxQ^^f6tgJCjV2ic7UC?TkH3i`fBq<Lk?xR62?$Jw
zn@*iPcL`3i%v~zfVo%gL!?i&R+;wD;Q3Y07P^o5%5Lcnhk&jrtKjKllntVyxuB5`6
zjfL2+4lF$`2!fyRhFHdcr@XF)Iegrh+_0Lrg300K^t!rRLEd2Y5L!YTUnP3Li1N85
zgV1eBgEFsL0eg01tv<yLejGMsvG8;zhdxzeA*9Yx0Em1hB_y+?1F5IKF>~HuS44U^
z&-P$`y16lAbi1rq_iR%Cy3`kzzub1W=fKiNZFM!y*F*V~-W)rK!7nb~mg0!Wv(ua_
zSNBjwLeWIVd5cg>0@_<ZgZ%ys&@7!YK1OjCuTmZ+-if&CuNhc2Sk&u($f6tq2#Lxn
z`PPxw);;@3^Jse+zL+wFgl3iXz8TD)O*o%&C76FgT)1vuSK;#W+ZZevG^%UZSSxm$
zIWpKb=ZDC^y1Tui`5hzErfjh1dB9k0gT{HGKbrt-D`)|MP$X3es>L;|Pq&I?;3i0L
zVVwbe0nofpK!Pi8H_k^o{QNEHF4fJEM4NUBdn8YbWyw!oa+iJOp`6D}Yq6iKJY#F+
zfP_ZE-_^u#7kkR(z=1JXKa;)>cmOsR<3pIkOCN&$a%)BOb{G?c_q@N{?ow7_zh58@
zYjWB>E)HOO7Bs@mE#QV4Q4>r`Oe~YKM%=c+)ykQYk%rrvk>UMy4qEjqkVauG+Bp(T
z>;`MPY2t^~EZ81%z5DP3pmbY1H}8ihx&V`|X6fk^XvH7z6)Gl2A8N^=gbd3IeoU)O
z&D{-5=FPCzDiwh&VX=~ZuA)1=?8qlZ<Kq+jCPFVU0zaQ{s^$o|IF}FJ?h6)3`xYqN
zv<e3{*2DnOd8WQ?PmKeVr4?suOOm>P(0V&qU%rgXPVUKgZx$wpCNiU0cbK5oM?RrA
z#>l;R$C$$C3wOR(p+iSC-baBu7KN$ng`t9(;kIZnk>tCC%3-&9psZsd>SY*zv@LTs
zcH(fj*c8RSi!P;H+f*k$n9>|0opdO!Py2<Znl#AKlw<R0vA<Jddudtea<L7=fa^nL
zJ_WW;C-7+w4WYj!MX0Rkc!{$LtEv)za8SsAV2S*8djt1k8U)vADl#ks=A>Bj!8$9h
z$fd#tOhb*5=YxE91%@o5d)1F<yA4Q>a&c`OeJ%%{o@L5vTi;1xqHDm6tUB8z*!{8)
zFsvL26F-;NecgBuYLiLzRI@vnmZ&!tgR|%wNHetgz027YV=$~S5L!B$iuHZ1_hf%L
zfa!WU-+XtX;8v+}K&N9vyq7)Ok}Gl<FGKL0KB{HyGLCE3!LrEXwnj|D->mii2oEQ9
z+R*vfGVg|**5P9C%a&y0GgwgscuG%%)+J*j*r||0<EG0>2)yeXq_&y1j%Ln)MeDC_
zitXg%z1@s7J5>3YH+9R?Z-KXD_AU*tCOUhyPf_b}wBADtG^Bp~q{|Iwi(OH})iRT?
zG~IvOCG7td=Xlx85cX4O(nSYS8|2V(jLWxf!ijUeSQ)aYQ&Ihtq!lqhS)uBL&dsuh
zDYT%1AbodN-N~bSFBhq6bw?|9Z8@^yhI&KG0L}xQn~V2AJX~6sly{l)v*K`<C^78>
zWLCUSjv&3HJ2RgOR`A&R3KcQ0fcNYrhpxp}=#Iki)%3=&{0kdLiC7Hb;x8vcW$&F2
zXO>1cA08G@cY9VA5G#autd^JLrOF#2Obebny|6Y^&;zCSmC$jlFUEPKj^}>7i95?8
zH&1I1CQQrbXc0Gf7Ye=MMm6bq;E}a$3b~BmjKs2>)AIy9X|$0#>Una2ul*1sLgBs2
zdmQTWHYZpNk+ZhtGQ)wIFX21SWkl|C<VpbAQJc&oW!?UQ=Y*B3Xr^k%liem>Kr_SY
z4;2VHHkml3lJpegfh{uZ&;xcFk>u}BtA^;)UnMI~TewW;(>j%j<cFIpg)!hUyG%a7
z;vc#dle0$m;kRlCTDyL))$uw6(!_>~maou_egIzLI8487qacm<zbOhD)Y<04;zxP9
z6kqB+dzZX50pF&cH&HM^HuDAZcBZfMkmeB(ZGLM5G}W)#e@iLO9D65CCU^v?yeAMi
zjQ;3>VZ$By7J-3&tBJ_FEphQO%_%K54D&E9*dgwVoBm{R4Pl+7FxpYU%{Egt`3&Ba
z+XF2I)WcE6*5H*lAeTz=aPBKvf<XhxM-}J+4rP3-bOvbY1h6ljSAx6I7xMFL)q(a#
z`N0*Mgo!fu$6oHr3Ow#PoSYO~TPtW>^G}O85cBB$P(IJh%>a74&%}YOnYOI4L5xwi
z2w=yV6ztWUc%onLSFOSX{6+86?2*!sDmNJoG`}(JJP1T>nI`q+AB&-FKj4Ojsg~ey
zK==iVpE+}EYndN)7GT4mcifh$q${Dx)kaIu#Y>QMcjuBu7W(XqwwqcRd9BJ#cwS>2
zrDr(1!QKwZtb#c;d0w>rb<?)4{<|jX%fUnb%ZcFcP6KV-UPM3U#)gjcjyC^sR-3M*
zWiikA#%s15$sjto=VMcNEJRi5;vj|@KtouU85Qj|tW++MRYzLnyU(&I4`yQ@-}kk&
zW9Jb~o45&Mj4L8xWhBJ5xHF`k@G?!htdd%0bQ($dd6-*R+0Y%V4ZLnBO&%K`|8Q`o
zEWbn&rJB^ip5eII0Vwg$?U2TDVVk_$nBj!Eb*-rqlwO%uyWxwJrMpTqg~(M9qd{oc
znHS*^%evZc&mQ)yhB#6AbA8hrD)G~n&ZT>}tr}|Jvwebc2+6>96T*VO7h~@j)}t(H
z%9q;>AM6|SU@b8WdS4&c&*~o8xG7h~Q6|r?SLp;JRx`C3h?*n&|DfX35v0;`)p8qW
zEr4%9&6Cao;ZC0r(~a;kWIrf$k@kniyQ@f>v<ODw7y90MyiMco8+8B)`M$gEu&TP4
zA=^ROUqroKbcSHQEr<JtvX01|$PlAKO{4|_{P5cVLN9K{j_Q_UQT#wf+axiFyN`V$
zMY)L39LKzGSFr}>hc`N(BE?O|CCZ1f@Ggh(5t;Nj3bSaIg9e^;qher)gv^vNOQ$`H
zD>a1}qoM(fswI_&M#5Pq=-mftO_%M5eVDgj2nQw82WR#>5Rb0*)>DD~wnHY2Pdq=&
z0sLWR3~Lla(<ktzhIv=5qq<0J2*FgyEpyn$wIZAg2<yChwmo@Ag3$zy>7VJk3E4p)
zS=YEcydY9#=XC!%$0`}XN4Q@$)!)7};@|9I+v(FA=sW(orS2g4_S=9WWdZF#|ETiV
zu&U&c)VH^_3S-Izg^H4;{j`c9Qc8>)_JV4vDk+${3dwQF>RIXvp+yLPZlwQ|y}>K{
zZ1KOC|DzH8-i80z)F&ZgFaTIH80b5g!8jN@64DtvnGn+15ZVH4jZO3cmM}lnYlQSL
zwr-AQHr9mpPS(0V_u^l4a)0dz=4x6~`4<liUK;Ihys$U6a{|~KTNztBI?y}1{^}C&
z4k3gtMkug$9-q^e<qj%4#X8^4cZxpC$<TcCrz5HM!VDf#k1Ims-<vO2%%Z>zgLny8
zByn7rQ0W|amOA^oL^&Kv)+i4)naq~`C!YT5;h}#e{N0Opg)cge-^m02@}hr^m{k<h
zi^>Hl(B%;(a{wXcAW=y>AU`@YH8@gJ`xYg&Kh~YQcA%}?90x@h5v*~&<#-XA=#4xZ
z(yaof*q65%iySNCUkP#-RXoL@Sh;aNCe`Oxl?=`rINuaw(G84TF?Y*Hy%m8%$xeVm
z8;`sqU1g4ymHa5guP&QYVRwcQx=b6sTeuC6NfQG(72IVK_gU}5tovK7OCAn4P%tSU
zk^;1p;i5L_8ahPKH<O-vALwR5ch2t+r<x>()9bx#uFr9i2)0>Rbjx~b-d$A$zOyZY
zJaq3D&B-ni{mk;!?BrUaNXHcJ;&9>+8Sjk#BwllQRk;{t^f~we{NFwKckM0VZ^qie
z-th1G+rMKN{|^}b7m2T~sjZ`~Gr-WvTL16Zf601h%!L$R&YEFyfPi@ZKd`#G0BeAw
zuI|ee|8wN0HI{AW*^#`jb?qjHHaeLaXMy&S^fVOoL;^Z?WEi1JJnL%5atM{I9+r<K
zL(#;BDih|!$!jXR*B|e0P9v3KNyFqaeV=yWJ3$hHVrTb-+ojcP)h*l{o-004NHJ@w
z+QYi5V;I2q)Ws(R@l>XE9E+8io|tCt949GZDlzg0i0RnpWaxzIYO(=pu)Yt?<c?qy
zB==ekB#YZbZEPHMNMn}TGP@BjDlKQXe+0nntDCaR5i2sM%aU`MO1o+4hBaf*;<56z
zqyy=Y^PKO0c_Z8|U&A4zEtH6!HKv(Jy-_?9+n}Ojknnc<J^!I7tHWpLI<Y|_yE>Z`
zq&Tx5E+uGw02A-DXXfWOLrDc^MHRlOT=cFG5nL<Grnq(Xq0Pf)_@WssF;<^6?7!vo
zQ>)~n!K7-hY@vF_#kz2j(aF~paM%MDqOBrj#!$}Sx8y|$^5}x!o%FZPT0dw2R*Ko!
zGj7~`vdd^Px$C#8{MxgMLdlBzyO4*hb%s?n=T9KlVR+Eirc77xZG?8sAqX^T)h^Cg
zcY_<M$D&ujjJz!s#td#gNh;|__PE5dX@&aN6;Fo6*>6xP<+C3KD5?dH0nRqdJs6(_
z_A^3v(k!3i9ce|R?Gz4KkVQdR&V5*TjD2BqRcd$+^BOrZL3B;GI(;|SwL_FMgwAbY
z6=Nzti5gP0pWDdwB$TqMvG+P<f24maU^gS*K%T2TOZuaOBPV4lZ>Kgb6RCw~&0H3k
zM<Bw1h?B>{g2U62Xzc*;4K(BFH5vN0h;hirDx@jhGR2^@^7Ew3xicx_{`{rlGe|B@
zl6C1ywj!;0cY;F7M?+OQ%QD3IRn!yM(9Nt-_;@b2&4O`Otd!PxkWuMsg;`^;!qI~1
z^$R%rP1A5Awd(5fp3=|tVQ6*Z4?iFY%^gYZ-l=yi^`b4mQC@G;H05xHqem@NE@)t9
zax7XeP$a^e?0=u0is#^FfAN@}ir+OOPuLFx7eLl)u%6MYn#jm3ldNoJ-%PooWac>|
zWao<Yjs7k~*rtS8rMr9}r?u(arBeOW3@D(B6?;DCAoLCoxsbp|G;gNgf_qwZUvc9E
z<#Epm9RL;T;8?02v;D|QV_vQ0-YA`I?xpiZN-R;{LV^Br=feWR{3!LI7EepjtQJ~|
zbmT4fr5WULH$5lO{IPPx7Xf1<WryTwqztC=sFvWs@gPfk=Wnjh8V7NHH3Wd--OWCX
zoxu2OVIYU>`<Xtw>4W9s7&cqyP#E^lWp-BqtX>{WO}zI@5}Pc6+!o7>vMf7EK+jX@
ztg`YxHMI511$09JZd=t_)llBwJj2*+a-GEXE7xLo_4qwTYCMIdqwgeWIC(NX;v<=t
zOfO|9(!AFWiw+4a_|R6@*g@|_p-%j!)+VXJ{QGMp;FW}jznhMZg+mPB5{~W8UjS+M
zx$JpR%!Nb^BS1pgzHwoGT0Y$hH{KTbcR>9avY;5ml0;sXCh?c{J9&YFqnoAiUlNHS
z+7Sk7#W7_CWywJ)*%7s|X}MC#5h^*UTGffkkK?lwe;n2qQppU{6pw?(krnokHHsDX
z<Z_YqqzHn$zmtY>|1+cb>CUGX<C#Aa8pW6PyQBG^?)*nmp{zC~Klp7@UYd4fWo_`M
zYwOal9h?0>IJWmcjsd@9@c;X@j~5SL9;BZi|JO?(|3?06y?AvE<PX+MitzIMF(m(V
zujId73Q>^xH~r@#_xe)8AKahxKT4B-r2p3|3cvV2y?=ch;TQi8&DB5hU)@c3O@4h>
z;1`+wrJ(vp^51U`yoSHl8~=jKzg$iDNBG~>$FJe9)w;jn)=<BJ|3<s}+R|&m=`Ty@
zFLU-EU*o^aPhT5&EuQ;jpa}k-4ZN1py(YhwH2or5zkHqk$@RYroL;kE%Z+}q>5>1L
z{a?jLuko*?L%;AHzrp`aNc0;0de7h&nuPqHJ^x>J5MCR2T`>MK5KQ^c240nqzra5O
z&FeDo7Z`@>x8VPX-@mv&1I+8f?iV-uH{AcV%zJI(b!GO;1T*zNyZ+znv|s$c7aD)m
zD?gt<77b6Df9AicUj7=||Hb*Ak3Z^{pU)rIuKxp8|9`J${%z)8>(i@x<_|MJR}gI4
z-+TYs%zvwHe)ZQ+i?7p>UlxZMe`E1)$;oT>>)hfOTbt?s!v4!l1%J``0|8;Y{NTO>
z_RALlB@i<c2P-3+F%t(nvx&Yw6EhPdvk@yJCzBxuC!>iG2dl9$8!M-=zVZJ9CNEMY


From acfd966aa42a7d1d99b62a6cdf51a34f7a9bcaf3 Mon Sep 17 00:00:00 2001
From: Nicholas Tindle <nick@ntindle.com>
Date: Fri, 26 May 2023 10:39:25 -0500
Subject: [PATCH 067/112] Pass Configs to Commands and remove CFG = Config() in
 the commands/ folder (#4328)

* feat: pass config to call_ai_functions in coimmands

* feat: config for read_audio_from_file

* feat: file operations cfg

NOTE: we replaced the CFG in the command enable with TRUE b/c not sure how to handle this yet

* feat: git command conversion

* feat: google search

* feat: image generation

* feat: extract cfg from browser commands

* feat: remove cfg from execute code commands

* fix: file operation related tests

* fix: linting

* fix: tests for read_audio

* fix: test error

* feat: update cassettes

* fix: linting

* fix: test typechecking

* fix: google_search errors if unexpected kw arg is passed

* fix: pass config param to google search test

* fix: agent commands were broken + cassettes

* fix: agent test

* feat: cassettes

* feat: enable/disable logic for commands

* fix: some commands threw errors

* feat: fix tests

* Add new cassettes

* Add new cassettes

* ci: trigger ci

* Update autogpt/commands/execute_code.py

Co-authored-by: Reinier van der Leer <github@pwuts.nl>

* fix prompt

* fix prompt + rebase

* add config remove useless imports

* put back CFG just for download file

* lint

* The signature should be mandatory in the decorator

* black isort

* fix: remove the CFG

* fix: non typed arg

* lint: type some args

* lint: add types for libraries

* Add new cassettes

* fix: windows compatibility

* fix: add config access to decorator

* fix: remove twitter mention

* DDGS search works at 3.0.2 version

* ci: linting

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: kinance <kinance@gmail.com>
---
 .env.template                                 |   1 -
 autogpt/agent/agent.py                        |   1 +
 autogpt/app.py                                |  29 +-
 autogpt/commands/analyze_code.py              |   9 +-
 autogpt/commands/audio_text.py                |  19 +-
 autogpt/commands/command.py                   |  22 +-
 autogpt/commands/execute_code.py              |  37 +-
 autogpt/commands/file_operations.py           |  49 +-
 autogpt/commands/file_operations_utils.py     |  26 +-
 autogpt/commands/git_operations.py            |  13 +-
 autogpt/commands/google_search.py             |  24 +-
 autogpt/commands/image_gen.py                 |  49 +-
 autogpt/commands/improve_code.py              |   8 +-
 autogpt/commands/task_statuses.py             |   7 +-
 autogpt/commands/web_requests.py              |  14 +-
 autogpt/commands/web_selenium.py              |  36 +-
 autogpt/commands/write_tests.py               |   8 +-
 autogpt/config/ai_config.py                   |   7 +-
 autogpt/configurator.py                       |  47 +-
 autogpt/llm/utils/__init__.py                 |   9 +-
 autogpt/main.py                               |   1 +
 requirements.txt                              |   4 +
 .../test_write_file/test_write_file.yaml      | 748 ++++++++++++++++--
 .../basic_abilities/test_browse_website.py    |   2 +
 .../basic_abilities/test_write_file.py        |   4 +-
 .../test_information_retrieval_challenge_a.py |   6 +-
 .../test_kubernetes_template_challenge_a.py   |   5 +-
 .../test_memory_challenge_a.yaml              | 700 +++++++++++++++-
 .../memory/test_memory_challenge_a.py         |   9 +-
 .../memory/test_memory_challenge_b.py         |   9 +-
 .../memory/test_memory_challenge_c.py         |   7 +-
 tests/integration/test_commands.py            |  14 +-
 tests/integration/test_execute_code.py        |  16 +-
 tests/integration/test_git_commands.py        |   6 +-
 tests/integration/test_google_search.py       |  13 +-
 tests/mocks/mock_commands.py                  |   4 +-
 tests/test_analyze_code.py                    |  28 +-
 tests/test_audio_text_read_audio.py           |  54 +-
 tests/test_audio_text_read_audio_from_file.py |   9 +-
 tests/test_commands.py                        |  18 +-
 tests/test_config.py                          |   1 +
 tests/test_image_gen.py                       |  30 +-
 tests/unit/test_browse_scrape_links.py        |  20 +-
 tests/unit/test_browse_scrape_text.py         |  24 +-
 tests/unit/test_file_operations.py            |  96 ++-
 tests/unit/test_web_selenium.py               |   4 +-
 46 files changed, 1851 insertions(+), 396 deletions(-)

diff --git a/.env.template b/.env.template
index 7a4a22bb..4c079e00 100644
--- a/.env.template
+++ b/.env.template
@@ -30,7 +30,6 @@
 ## autogpt.commands.google_search
 ## autogpt.commands.image_gen
 ## autogpt.commands.improve_code
-## autogpt.commands.twitter
 ## autogpt.commands.web_selenium
 ## autogpt.commands.write_tests
 ## autogpt.app
diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index 8c7a5456..93d31853 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -274,6 +274,7 @@ class Agent:
                     command_name,
                     arguments,
                     self.config.prompt_generator,
+                    config=cfg,
                 )
                 result = f"Command {command_name} returned: " f"{command_result}"
 
diff --git a/autogpt/app.py b/autogpt/app.py
index da67c35f..985bf0f8 100644
--- a/autogpt/app.py
+++ b/autogpt/app.py
@@ -6,15 +6,11 @@ from autogpt.agent.agent_manager import AgentManager
 from autogpt.commands.command import CommandRegistry, command
 from autogpt.commands.web_requests import scrape_links, scrape_text
 from autogpt.config import Config
-from autogpt.logs import logger
-from autogpt.memory.vector import get_memory
 from autogpt.processing.text import summarize_text
 from autogpt.prompts.generator import PromptGenerator
 from autogpt.speech import say_text
 from autogpt.url_utils.validators import validate_url
 
-CFG = Config()
-
 
 def is_valid_int(value: str) -> bool:
     """Check if the value is a valid integer
@@ -93,6 +89,7 @@ def execute_command(
     command_name: str,
     arguments,
     prompt: PromptGenerator,
+    config: Config,
 ):
     """Execute the command and return the result
 
@@ -108,7 +105,7 @@ def execute_command(
 
         # If the command is found, call it with the provided arguments
         if cmd:
-            return cmd(**arguments)
+            return cmd(**arguments, config=config)
 
         # TODO: Remove commands below after they are moved to the command registry.
         command_name = map_command_synonyms(command_name.lower())
@@ -135,7 +132,7 @@ def execute_command(
     "get_text_summary", "Get text summary", '"url": "<url>", "question": "<question>"'
 )
 @validate_url
-def get_text_summary(url: str, question: str) -> str:
+def get_text_summary(url: str, question: str, config: Config) -> str:
     """Get the text summary of a webpage
 
     Args:
@@ -153,7 +150,7 @@ def get_text_summary(url: str, question: str) -> str:
 
 @command("get_hyperlinks", "Get hyperlinks", '"url": "<url>"')
 @validate_url
-def get_hyperlinks(url: str) -> Union[str, List[str]]:
+def get_hyperlinks(url: str, config: Config) -> Union[str, List[str]]:
     """Get all hyperlinks on a webpage
 
     Args:
@@ -162,7 +159,7 @@ def get_hyperlinks(url: str) -> Union[str, List[str]]:
     Returns:
         str or list: The hyperlinks on the page
     """
-    return scrape_links(url)
+    return scrape_links(url, config)
 
 
 @command(
@@ -170,7 +167,7 @@ def get_hyperlinks(url: str) -> Union[str, List[str]]:
     "Start GPT Agent",
     '"name": "<name>", "task": "<short_task_desc>", "prompt": "<prompt>"',
 )
-def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) -> str:
+def start_agent(name: str, task: str, prompt: str, config: Config, model=None) -> str:
     """Start an agent with a given name, task, and prompt
 
     Args:
@@ -191,11 +188,11 @@ def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) ->
     agent_intro = f"{voice_name} here, Reporting for duty!"
 
     # Create agent
-    if CFG.speak_mode:
+    if config.speak_mode:
         say_text(agent_intro, 1)
     key, ack = agent_manager.create_agent(task, first_message, model)
 
-    if CFG.speak_mode:
+    if config.speak_mode:
         say_text(f"Hello {voice_name}. Your task is as follows. {task}.")
 
     # Assign task (prompt), get response
@@ -205,7 +202,7 @@ def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) ->
 
 
 @command("message_agent", "Message GPT Agent", '"key": "<key>", "message": "<message>"')
-def message_agent(key: str, message: str) -> str:
+def message_agent(key: str, message: str, config: Config) -> str:
     """Message an agent with a given key and message"""
     # Check if the key is a valid integer
     if is_valid_int(key):
@@ -214,13 +211,13 @@ def message_agent(key: str, message: str) -> str:
         return "Invalid key, must be an integer."
 
     # Speak response
-    if CFG.speak_mode:
+    if config.speak_mode:
         say_text(agent_response, 1)
     return agent_response
 
 
-@command("list_agents", "List GPT Agents", "")
-def list_agents() -> str:
+@command("list_agents", "List GPT Agents", "() -> str")
+def list_agents(config: Config) -> str:
     """List all agents
 
     Returns:
@@ -232,7 +229,7 @@ def list_agents() -> str:
 
 
 @command("delete_agent", "Delete GPT Agent", '"key": "<key>"')
-def delete_agent(key: str) -> str:
+def delete_agent(key: str, config: Config) -> str:
     """Delete an agent with a given key
 
     Args:
diff --git a/autogpt/commands/analyze_code.py b/autogpt/commands/analyze_code.py
index b2af33e2..4de68334 100644
--- a/autogpt/commands/analyze_code.py
+++ b/autogpt/commands/analyze_code.py
@@ -1,16 +1,21 @@
 """Code evaluation module."""
 from __future__ import annotations
 
+from typing import TYPE_CHECKING
+
 from autogpt.commands.command import command
 from autogpt.llm.utils import call_ai_function
 
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 
 @command(
     "analyze_code",
     "Analyze Code",
     '"code": "<full_code_string>"',
 )
-def analyze_code(code: str) -> list[str]:
+def analyze_code(code: str, config: Config) -> list[str]:
     """
     A function that takes in a string and returns a response from create chat
       completion api call.
@@ -28,4 +33,4 @@ def analyze_code(code: str) -> list[str]:
         "Analyzes the given code and returns a list of suggestions for improvements."
     )
 
-    return call_ai_function(function_string, args, description_string)
+    return call_ai_function(function_string, args, description_string, config=config)
diff --git a/autogpt/commands/audio_text.py b/autogpt/commands/audio_text.py
index 0a8640cf..ba4fb347 100644
--- a/autogpt/commands/audio_text.py
+++ b/autogpt/commands/audio_text.py
@@ -1,22 +1,25 @@
 """Commands for converting audio to text."""
 import json
+from typing import TYPE_CHECKING
 
 import requests
 
 from autogpt.commands.command import command
 from autogpt.config import Config
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
 
 
 @command(
     "read_audio_from_file",
     "Convert Audio to text",
     '"filename": "<filename>"',
-    CFG.huggingface_audio_to_text_model,
-    "Configure huggingface_audio_to_text_model.",
+    lambda config: config.huggingface_audio_to_text_model
+    and config.huggingface_api_token,
+    "Configure huggingface_audio_to_text_model and Hugging Face api token.",
 )
-def read_audio_from_file(filename: str) -> str:
+def read_audio_from_file(filename: str, config: Config) -> str:
     """
     Convert audio to text.
 
@@ -28,10 +31,10 @@ def read_audio_from_file(filename: str) -> str:
     """
     with open(filename, "rb") as audio_file:
         audio = audio_file.read()
-    return read_audio(audio)
+    return read_audio(audio, config)
 
 
-def read_audio(audio: bytes) -> str:
+def read_audio(audio: bytes, config: Config) -> str:
     """
     Convert audio to text.
 
@@ -41,9 +44,9 @@ def read_audio(audio: bytes) -> str:
     Returns:
         str: The text from the audio
     """
-    model = CFG.huggingface_audio_to_text_model
+    model = config.huggingface_audio_to_text_model
     api_url = f"https://api-inference.huggingface.co/models/{model}"
-    api_token = CFG.huggingface_api_token
+    api_token = config.huggingface_api_token
     headers = {"Authorization": f"Bearer {api_token}"}
 
     if api_token is None:
diff --git a/autogpt/commands/command.py b/autogpt/commands/command.py
index 174a691c..e99a68c0 100644
--- a/autogpt/commands/command.py
+++ b/autogpt/commands/command.py
@@ -1,8 +1,9 @@
 import functools
 import importlib
 import inspect
-from typing import Any, Callable, Optional
+from typing import TYPE_CHECKING, Any, Callable, Optional
 
+from autogpt.config import Config
 from autogpt.logs import logger
 
 # Unique identifier for auto-gpt commands
@@ -24,19 +25,23 @@ class Command:
         description: str,
         method: Callable[..., Any],
         signature: str = "",
-        enabled: bool = True,
+        enabled: bool | Callable[[Config], bool] = True,
         disabled_reason: Optional[str] = None,
     ):
         self.name = name
         self.description = description
         self.method = method
-        self.signature = signature if signature else str(inspect.signature(self.method))
+        self.signature = signature
         self.enabled = enabled
         self.disabled_reason = disabled_reason
 
     def __call__(self, *args, **kwargs) -> Any:
+        if hasattr(kwargs, "config") and callable(self.enabled):
+            self.enabled = self.enabled(kwargs["config"])
         if not self.enabled:
-            return f"Command '{self.name}' is disabled: {self.disabled_reason}"
+            if self.disabled_reason:
+                return f"Command '{self.name}' is disabled: {self.disabled_reason}"
+            return f"Command '{self.name}' is disabled"
         return self.method(*args, **kwargs)
 
     def __str__(self) -> str:
@@ -133,12 +138,17 @@ class CommandRegistry:
 def command(
     name: str,
     description: str,
-    signature: str = "",
-    enabled: bool = True,
+    signature: str,
+    enabled: bool | Callable[[Config], bool] = True,
     disabled_reason: Optional[str] = None,
 ) -> Callable[..., Any]:
     """The command decorator is used to create Command objects from ordinary functions."""
 
+    # TODO: Remove this in favor of better command management
+    CFG = Config()
+
+    if callable(enabled):
+        enabled = enabled(CFG)
     if not enabled:
         if disabled_reason is not None:
             logger.debug(f"Command '{name}' is disabled: {disabled_reason}")
diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py
index 8d14c17f..e8ef6551 100644
--- a/autogpt/commands/execute_code.py
+++ b/autogpt/commands/execute_code.py
@@ -2,6 +2,7 @@
 import os
 import subprocess
 from pathlib import Path
+from typing import TYPE_CHECKING
 
 import docker
 from docker.errors import ImageNotFound
@@ -10,11 +11,9 @@ from autogpt.commands.command import command
 from autogpt.config import Config
 from autogpt.logs import logger
 
-CFG = Config()
-
 
 @command("execute_python_file", "Execute Python File", '"filename": "<filename>"')
-def execute_python_file(filename: str) -> str:
+def execute_python_file(filename: str, config: Config) -> str:
     """Execute a Python file in a Docker container and return the output
 
     Args:
@@ -65,9 +64,9 @@ def execute_python_file(filename: str) -> str:
                     logger.info(status)
         container = client.containers.run(
             image_name,
-            ["python", str(Path(filename).relative_to(CFG.workspace_path))],
+            ["python", str(Path(filename).relative_to(config.workspace_path))],
             volumes={
-                CFG.workspace_path: {
+                config.workspace_path: {
                     "bind": "/workspace",
                     "mode": "ro",
                 }
@@ -97,7 +96,7 @@ def execute_python_file(filename: str) -> str:
         return f"Error: {str(e)}"
 
 
-def validate_command(command: str) -> bool:
+def validate_command(command: str, config: Config) -> bool:
     """Validate a command to ensure it is allowed
 
     Args:
@@ -111,13 +110,13 @@ def validate_command(command: str) -> bool:
     if not tokens:
         return False
 
-    if CFG.deny_commands and tokens[0] not in CFG.deny_commands:
+    if config.deny_commands and tokens[0] not in config.deny_commands:
         return False
 
-    for keyword in CFG.allow_commands:
+    for keyword in config.allow_commands:
         if keyword in tokens:
             return True
-    if CFG.allow_commands:
+    if config.allow_commands:
         return False
 
     return True
@@ -127,12 +126,12 @@ def validate_command(command: str) -> bool:
     "execute_shell",
     "Execute Shell Command, non-interactive commands only",
     '"command_line": "<command_line>"',
-    CFG.execute_local_commands,
+    lambda cfg: cfg.execute_local_commands,
     "You are not allowed to run local shell commands. To execute"
     " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
     "in your config file: .env - do not attempt to bypass the restriction.",
 )
-def execute_shell(command_line: str) -> str:
+def execute_shell(command_line: str, config: Config) -> str:
     """Execute a shell command and return the output
 
     Args:
@@ -141,14 +140,14 @@ def execute_shell(command_line: str) -> str:
     Returns:
         str: The output of the command
     """
-    if not validate_command(command_line):
+    if not validate_command(command_line, config):
         logger.info(f"Command '{command_line}' not allowed")
         return "Error: This Shell Command is not allowed."
 
     current_dir = Path.cwd()
     # Change dir into workspace if necessary
-    if not current_dir.is_relative_to(CFG.workspace_path):
-        os.chdir(CFG.workspace_path)
+    if not current_dir.is_relative_to(config.workspace_path):
+        os.chdir(config.workspace_path)
 
     logger.info(
         f"Executing command '{command_line}' in working directory '{os.getcwd()}'"
@@ -167,12 +166,12 @@ def execute_shell(command_line: str) -> str:
     "execute_shell_popen",
     "Execute Shell Command, non-interactive commands only",
     '"command_line": "<command_line>"',
-    CFG.execute_local_commands,
+    lambda config: config.execute_local_commands,
     "You are not allowed to run local shell commands. To execute"
     " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
     "in your config. Do not attempt to bypass the restriction.",
 )
-def execute_shell_popen(command_line) -> str:
+def execute_shell_popen(command_line, config: Config) -> str:
     """Execute a shell command with Popen and returns an english description
     of the event and the process id
 
@@ -182,14 +181,14 @@ def execute_shell_popen(command_line) -> str:
     Returns:
         str: Description of the fact that the process started and its id
     """
-    if not validate_command(command_line):
+    if not validate_command(command_line, config):
         logger.info(f"Command '{command_line}' not allowed")
         return "Error: This Shell Command is not allowed."
 
     current_dir = os.getcwd()
     # Change dir into workspace if necessary
-    if CFG.workspace_path not in current_dir:
-        os.chdir(CFG.workspace_path)
+    if config.workspace_path not in current_dir:
+        os.chdir(config.workspace_path)
 
     logger.info(
         f"Executing command '{command_line}' in working directory '{os.getcwd()}'"
diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index cf0325e2..7205b302 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -4,7 +4,7 @@ from __future__ import annotations
 import hashlib
 import os
 import os.path
-from typing import Generator, Literal
+from typing import TYPE_CHECKING, Generator, Literal
 
 import charset_normalizer
 import requests
@@ -13,13 +13,14 @@ from requests.adapters import HTTPAdapter, Retry
 
 from autogpt.commands.command import command
 from autogpt.commands.file_operations_utils import read_textual_file
-from autogpt.config import Config
 from autogpt.logs import logger
 from autogpt.memory.vector import MemoryItem, VectorMemory
 from autogpt.spinner import Spinner
 from autogpt.utils import readable_file_size
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 
 Operation = Literal["write", "append", "delete"]
 
@@ -60,7 +61,7 @@ def operations_from_log(
 def file_operations_state(log_path: str) -> dict[str, str]:
     """Iterates over the operations log and returns the expected state.
 
-    Parses a log file at CFG.file_logger_path to construct a dictionary that maps
+    Parses a log file at config.file_logger_path to construct a dictionary that maps
     each file path written or appended to its checksum. Deleted files are removed
     from the dictionary.
 
@@ -68,7 +69,7 @@ def file_operations_state(log_path: str) -> dict[str, str]:
         A dictionary mapping file paths to their checksums.
 
     Raises:
-        FileNotFoundError: If CFG.file_logger_path is not found.
+        FileNotFoundError: If config.file_logger_path is not found.
         ValueError: If the log file content is not in the expected format.
     """
     state = {}
@@ -81,7 +82,7 @@ def file_operations_state(log_path: str) -> dict[str, str]:
 
 
 def is_duplicate_operation(
-    operation: Operation, filename: str, checksum: str | None = None
+    operation: Operation, filename: str, config: Config, checksum: str | None = None
 ) -> bool:
     """Check if the operation has already been performed
 
@@ -93,7 +94,7 @@ def is_duplicate_operation(
     Returns:
         True if the operation has already been performed on the file
     """
-    state = file_operations_state(CFG.file_logger_path)
+    state = file_operations_state(config.file_logger_path)
     if operation == "delete" and filename not in state:
         return True
     if operation == "write" and state.get(filename) == checksum:
@@ -101,7 +102,9 @@ def is_duplicate_operation(
     return False
 
 
-def log_operation(operation: str, filename: str, checksum: str | None = None) -> None:
+def log_operation(
+    operation: str, filename: str, config: Config, checksum: str | None = None
+) -> None:
     """Log the file operation to the file_logger.txt
 
     Args:
@@ -113,7 +116,7 @@ def log_operation(operation: str, filename: str, checksum: str | None = None) ->
     if checksum is not None:
         log_entry += f" #{checksum}"
     logger.debug(f"Logging file operation: {log_entry}")
-    append_to_file(CFG.file_logger_path, f"{log_entry}\n", should_log=False)
+    append_to_file(config.file_logger_path, f"{log_entry}\n", config, should_log=False)
 
 
 def split_file(
@@ -149,7 +152,7 @@ def split_file(
 
 
 @command("read_file", "Read a file", '"filename": "<filename>"')
-def read_file(filename: str) -> str:
+def read_file(filename: str, config: Config) -> str:
     """Read a file and return the contents
 
     Args:
@@ -198,7 +201,7 @@ def ingest_file(
 
 
 @command("write_to_file", "Write to file", '"filename": "<filename>", "text": "<text>"')
-def write_to_file(filename: str, text: str) -> str:
+def write_to_file(filename: str, text: str, config: Config) -> str:
     """Write text to a file
 
     Args:
@@ -209,14 +212,14 @@ def write_to_file(filename: str, text: str) -> str:
         str: A message indicating success or failure
     """
     checksum = text_checksum(text)
-    if is_duplicate_operation("write", filename, checksum):
+    if is_duplicate_operation("write", filename, config, checksum):
         return "Error: File has already been updated."
     try:
         directory = os.path.dirname(filename)
         os.makedirs(directory, exist_ok=True)
         with open(filename, "w", encoding="utf-8") as f:
             f.write(text)
-        log_operation("write", filename, checksum)
+        log_operation("write", filename, config, checksum)
         return "File written to successfully."
     except Exception as err:
         return f"Error: {err}"
@@ -225,7 +228,9 @@ def write_to_file(filename: str, text: str) -> str:
 @command(
     "append_to_file", "Append to file", '"filename": "<filename>", "text": "<text>"'
 )
-def append_to_file(filename: str, text: str, should_log: bool = True) -> str:
+def append_to_file(
+    filename: str, text: str, config: Config, should_log: bool = True
+) -> str:
     """Append text to a file
 
     Args:
@@ -245,7 +250,7 @@ def append_to_file(filename: str, text: str, should_log: bool = True) -> str:
         if should_log:
             with open(filename, "r", encoding="utf-8") as f:
                 checksum = text_checksum(f.read())
-            log_operation("append", filename, checksum=checksum)
+            log_operation("append", filename, config, checksum=checksum)
 
         return "Text appended successfully."
     except Exception as err:
@@ -253,7 +258,7 @@ def append_to_file(filename: str, text: str, should_log: bool = True) -> str:
 
 
 @command("delete_file", "Delete file", '"filename": "<filename>"')
-def delete_file(filename: str) -> str:
+def delete_file(filename: str, config: Config) -> str:
     """Delete a file
 
     Args:
@@ -262,18 +267,18 @@ def delete_file(filename: str) -> str:
     Returns:
         str: A message indicating success or failure
     """
-    if is_duplicate_operation("delete", filename):
+    if is_duplicate_operation("delete", filename, config):
         return "Error: File has already been deleted."
     try:
         os.remove(filename)
-        log_operation("delete", filename)
+        log_operation("delete", filename, config)
         return "File deleted successfully."
     except Exception as err:
         return f"Error: {err}"
 
 
 @command("list_files", "List Files in Directory", '"directory": "<directory>"')
-def list_files(directory: str) -> list[str]:
+def list_files(directory: str, config: Config) -> list[str]:
     """lists files in a directory recursively
 
     Args:
@@ -289,7 +294,7 @@ def list_files(directory: str) -> list[str]:
             if file.startswith("."):
                 continue
             relative_path = os.path.relpath(
-                os.path.join(root, file), CFG.workspace_path
+                os.path.join(root, file), config.workspace_path
             )
             found_files.append(relative_path)
 
@@ -300,10 +305,10 @@ def list_files(directory: str) -> list[str]:
     "download_file",
     "Download File",
     '"url": "<url>", "filename": "<filename>"',
-    CFG.allow_downloads,
+    lambda config: config.allow_downloads,
     "Error: You do not have user authorization to download files locally.",
 )
-def download_file(url, filename):
+def download_file(url, filename, config: Config):
     """Downloads a file
     Args:
         url (str): URL of the file to download
diff --git a/autogpt/commands/file_operations_utils.py b/autogpt/commands/file_operations_utils.py
index e408c6fa..7f3e418d 100644
--- a/autogpt/commands/file_operations_utils.py
+++ b/autogpt/commands/file_operations_utils.py
@@ -14,13 +14,13 @@ from autogpt.logs import logger
 
 
 class ParserStrategy:
-    def read(self, file_path: str):
+    def read(self, file_path: str) -> str:
         raise NotImplementedError
 
 
 # Basic text file reading
 class TXTParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         charset_match = charset_normalizer.from_path(file_path).best()
         logger.debug(f"Reading '{file_path}' with encoding '{charset_match.encoding}'")
         return str(charset_match)
@@ -28,7 +28,7 @@ class TXTParser(ParserStrategy):
 
 # Reading text from binary file using pdf parser
 class PDFParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         parser = PyPDF2.PdfReader(file_path)
         text = ""
         for page_idx in range(len(parser.pages)):
@@ -38,7 +38,7 @@ class PDFParser(ParserStrategy):
 
 # Reading text from binary file using docs parser
 class DOCXParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         doc_file = docx.Document(file_path)
         text = ""
         for para in doc_file.paragraphs:
@@ -48,7 +48,7 @@ class DOCXParser(ParserStrategy):
 
 # Reading as dictionary and returning string format
 class JSONParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             data = json.load(f)
             text = str(data)
@@ -56,7 +56,7 @@ class JSONParser(ParserStrategy):
 
 
 class XMLParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             soup = BeautifulSoup(f, "xml")
             text = soup.get_text()
@@ -65,7 +65,7 @@ class XMLParser(ParserStrategy):
 
 # Reading as dictionary and returning string format
 class YAMLParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             data = yaml.load(f, Loader=yaml.FullLoader)
             text = str(data)
@@ -73,7 +73,7 @@ class YAMLParser(ParserStrategy):
 
 
 class HTMLParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             soup = BeautifulSoup(f, "html.parser")
             text = soup.get_text()
@@ -81,7 +81,7 @@ class HTMLParser(ParserStrategy):
 
 
 class MarkdownParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             html = markdown.markdown(f.read())
             text = "".join(BeautifulSoup(html, "html.parser").findAll(string=True))
@@ -89,7 +89,7 @@ class MarkdownParser(ParserStrategy):
 
 
 class LaTeXParser(ParserStrategy):
-    def read(self, file_path):
+    def read(self, file_path: str) -> str:
         with open(file_path, "r") as f:
             latex = f.read()
         text = LatexNodes2Text().latex_to_text(latex)
@@ -101,11 +101,11 @@ class FileContext:
         self.parser = parser
         self.logger = logger
 
-    def set_parser(self, parser: ParserStrategy):
+    def set_parser(self, parser: ParserStrategy) -> None:
         self.logger.debug(f"Setting Context Parser to {parser}")
         self.parser = parser
 
-    def read_file(self, file_path):
+    def read_file(self, file_path) -> str:
         self.logger.debug(f"Reading file {file_path} with parser {self.parser}")
         return self.parser.read(file_path)
 
@@ -144,7 +144,7 @@ def is_file_binary_fn(file_path: str):
     return False
 
 
-def read_textual_file(file_path: str, logger: logs.Logger):
+def read_textual_file(file_path: str, logger: logs.Logger) -> str:
     if not os.path.isfile(file_path):
         raise FileNotFoundError(f"{file_path} not found!")
     is_binary = is_file_binary_fn(file_path)
diff --git a/autogpt/commands/git_operations.py b/autogpt/commands/git_operations.py
index 22233108..c32a8cc3 100644
--- a/autogpt/commands/git_operations.py
+++ b/autogpt/commands/git_operations.py
@@ -1,22 +1,25 @@
 """Git operations for autogpt"""
+from typing import TYPE_CHECKING
+
 from git.repo import Repo
 
 from autogpt.commands.command import command
 from autogpt.config import Config
 from autogpt.url_utils.validators import validate_url
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
 
 
 @command(
     "clone_repository",
     "Clone Repository",
     '"url": "<repository_url>", "clone_path": "<clone_path>"',
-    CFG.github_username and CFG.github_api_key,
+    lambda config: config.github_username and config.github_api_key,
     "Configure github_username and github_api_key.",
 )
 @validate_url
-def clone_repository(url: str, clone_path: str) -> str:
+def clone_repository(url: str, clone_path: str, config: Config) -> str:
     """Clone a GitHub repository locally.
 
     Args:
@@ -27,7 +30,9 @@ def clone_repository(url: str, clone_path: str) -> str:
         str: The result of the clone operation.
     """
     split_url = url.split("//")
-    auth_repo_url = f"//{CFG.github_username}:{CFG.github_api_key}@".join(split_url)
+    auth_repo_url = f"//{config.github_username}:{config.github_api_key}@".join(
+        split_url
+    )
     try:
         Repo.clone_from(url=auth_repo_url, to_path=clone_path)
         return f"""Cloned {url} to {clone_path}"""
diff --git a/autogpt/commands/google_search.py b/autogpt/commands/google_search.py
index 23abef7d..c01ec0a1 100644
--- a/autogpt/commands/google_search.py
+++ b/autogpt/commands/google_search.py
@@ -3,17 +3,23 @@ from __future__ import annotations
 
 import json
 from itertools import islice
+from typing import TYPE_CHECKING
 
 from duckduckgo_search import DDGS
 
 from autogpt.commands.command import command
-from autogpt.config import Config
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
 
 
-@command("google", "Google Search", '"query": "<query>"', not CFG.google_api_key)
-def google_search(query: str, num_results: int = 8) -> str:
+@command(
+    "google",
+    "Google Search",
+    '"query": "<query>"',
+    lambda config: not config.google_api_key,
+)
+def google_search(query: str, config: Config, num_results: int = 8) -> str:
     """Return the results of a Google search
 
     Args:
@@ -42,10 +48,12 @@ def google_search(query: str, num_results: int = 8) -> str:
     "google",
     "Google Search",
     '"query": "<query>"',
-    bool(CFG.google_api_key) and bool(CFG.custom_search_engine_id),
+    lambda config: bool(config.google_api_key) and bool(config.custom_search_engine_id),
     "Configure google_api_key and custom_search_engine_id.",
 )
-def google_official_search(query: str, num_results: int = 8) -> str | list[str]:
+def google_official_search(
+    query: str, config: Config, num_results: int = 8
+) -> str | list[str]:
     """Return the results of a Google search using the official Google API
 
     Args:
@@ -61,8 +69,8 @@ def google_official_search(query: str, num_results: int = 8) -> str | list[str]:
 
     try:
         # Get the Google API key and Custom Search Engine ID from the config file
-        api_key = CFG.google_api_key
-        custom_search_engine_id = CFG.custom_search_engine_id
+        api_key = config.google_api_key
+        custom_search_engine_id = config.custom_search_engine_id
 
         # Initialize the Custom Search API service
         service = build("customsearch", "v1", developerKey=api_key)
diff --git a/autogpt/commands/image_gen.py b/autogpt/commands/image_gen.py
index 5326cd52..04d86564 100644
--- a/autogpt/commands/image_gen.py
+++ b/autogpt/commands/image_gen.py
@@ -4,6 +4,7 @@ import json
 import time
 import uuid
 from base64 import b64decode
+from typing import TYPE_CHECKING
 
 import openai
 import requests
@@ -13,11 +14,18 @@ from autogpt.commands.command import command
 from autogpt.config import Config
 from autogpt.logs import logger
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
 
 
-@command("generate_image", "Generate Image", '"prompt": "<prompt>"', CFG.image_provider)
-def generate_image(prompt: str, size: int = 256) -> str:
+@command(
+    "generate_image",
+    "Generate Image",
+    '"prompt": "<prompt>"',
+    lambda config: config.image_provider,
+    "Requires a image provider to be set.",
+)
+def generate_image(prompt: str, config: Config, size: int = 256) -> str:
     """Generate an image from a prompt.
 
     Args:
@@ -27,21 +35,21 @@ def generate_image(prompt: str, size: int = 256) -> str:
     Returns:
         str: The filename of the image
     """
-    filename = f"{CFG.workspace_path}/{str(uuid.uuid4())}.jpg"
+    filename = f"{config.workspace_path}/{str(uuid.uuid4())}.jpg"
 
     # DALL-E
-    if CFG.image_provider == "dalle":
-        return generate_image_with_dalle(prompt, filename, size)
+    if config.image_provider == "dalle":
+        return generate_image_with_dalle(prompt, filename, size, config)
     # HuggingFace
-    elif CFG.image_provider == "huggingface":
-        return generate_image_with_hf(prompt, filename)
+    elif config.image_provider == "huggingface":
+        return generate_image_with_hf(prompt, filename, config)
     # SD WebUI
-    elif CFG.image_provider == "sdwebui":
-        return generate_image_with_sd_webui(prompt, filename, size)
+    elif config.image_provider == "sdwebui":
+        return generate_image_with_sd_webui(prompt, filename, config, size)
     return "No Image Provider Set"
 
 
-def generate_image_with_hf(prompt: str, filename: str) -> str:
+def generate_image_with_hf(prompt: str, filename: str, config: Config) -> str:
     """Generate an image with HuggingFace's API.
 
     Args:
@@ -52,14 +60,14 @@ def generate_image_with_hf(prompt: str, filename: str) -> str:
         str: The filename of the image
     """
     API_URL = (
-        f"https://api-inference.huggingface.co/models/{CFG.huggingface_image_model}"
+        f"https://api-inference.huggingface.co/models/{config.huggingface_image_model}"
     )
-    if CFG.huggingface_api_token is None:
+    if config.huggingface_api_token is None:
         raise ValueError(
             "You need to set your Hugging Face API token in the config file."
         )
     headers = {
-        "Authorization": f"Bearer {CFG.huggingface_api_token}",
+        "Authorization": f"Bearer {config.huggingface_api_token}",
         "X-Use-Cache": "false",
     }
 
@@ -101,7 +109,9 @@ def generate_image_with_hf(prompt: str, filename: str) -> str:
     return f"Error creating image."
 
 
-def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str:
+def generate_image_with_dalle(
+    prompt: str, filename: str, size: int, config: Config
+) -> str:
     """Generate an image with DALL-E.
 
     Args:
@@ -126,7 +136,7 @@ def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str:
         n=1,
         size=f"{size}x{size}",
         response_format="b64_json",
-        api_key=CFG.openai_api_key,
+        api_key=config.openai_api_key,
     )
 
     logger.info(f"Image Generated for prompt:{prompt}")
@@ -142,6 +152,7 @@ def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str:
 def generate_image_with_sd_webui(
     prompt: str,
     filename: str,
+    config: Config,
     size: int = 512,
     negative_prompt: str = "",
     extra: dict = {},
@@ -158,13 +169,13 @@ def generate_image_with_sd_webui(
     """
     # Create a session and set the basic auth if needed
     s = requests.Session()
-    if CFG.sd_webui_auth:
-        username, password = CFG.sd_webui_auth.split(":")
+    if config.sd_webui_auth:
+        username, password = config.sd_webui_auth.split(":")
         s.auth = (username, password or "")
 
     # Generate the images
     response = requests.post(
-        f"{CFG.sd_webui_url}/sdapi/v1/txt2img",
+        f"{config.sd_webui_url}/sdapi/v1/txt2img",
         json={
             "prompt": prompt,
             "negative_prompt": negative_prompt,
diff --git a/autogpt/commands/improve_code.py b/autogpt/commands/improve_code.py
index d2665f3f..60e517ef 100644
--- a/autogpt/commands/improve_code.py
+++ b/autogpt/commands/improve_code.py
@@ -1,17 +1,21 @@
 from __future__ import annotations
 
 import json
+from typing import TYPE_CHECKING
 
 from autogpt.commands.command import command
 from autogpt.llm.utils import call_ai_function
 
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 
 @command(
     "improve_code",
     "Get Improved Code",
     '"suggestions": "<list_of_suggestions>", "code": "<full_code_string>"',
 )
-def improve_code(suggestions: list[str], code: str) -> str:
+def improve_code(suggestions: list[str], code: str, config: Config) -> str:
     """
     A function that takes in code and suggestions and returns a response from create
       chat completion api call.
@@ -32,4 +36,4 @@ def improve_code(suggestions: list[str], code: str) -> str:
         " provided, making no other changes."
     )
 
-    return call_ai_function(function_string, args, description_string)
+    return call_ai_function(function_string, args, description_string, config=config)
diff --git a/autogpt/commands/task_statuses.py b/autogpt/commands/task_statuses.py
index 46c5b6c0..9f60209c 100644
--- a/autogpt/commands/task_statuses.py
+++ b/autogpt/commands/task_statuses.py
@@ -1,18 +1,21 @@
 """Task Statuses module."""
 from __future__ import annotations
 
-from typing import NoReturn
+from typing import TYPE_CHECKING, NoReturn
 
 from autogpt.commands.command import command
 from autogpt.logs import logger
 
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 
 @command(
     "task_complete",
     "Task Complete (Shutdown)",
     '"reason": "<reason>"',
 )
-def task_complete(reason: str) -> NoReturn:
+def task_complete(reason: str, config: Config) -> NoReturn:
     """
     A function that takes in a string and exits the program
 
diff --git a/autogpt/commands/web_requests.py b/autogpt/commands/web_requests.py
index 156ba103..d7de8dc9 100644
--- a/autogpt/commands/web_requests.py
+++ b/autogpt/commands/web_requests.py
@@ -9,15 +9,12 @@ from autogpt.config import Config
 from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
 from autogpt.url_utils.validators import validate_url
 
-CFG = Config()
-
 session = requests.Session()
-session.headers.update({"User-Agent": CFG.user_agent})
 
 
 @validate_url
 def get_response(
-    url: str, timeout: int = 10
+    url: str, config: Config, timeout: int = 10
 ) -> tuple[None, str] | tuple[Response, None]:
     """Get the response from a URL
 
@@ -33,6 +30,7 @@ def get_response(
         requests.exceptions.RequestException: If the HTTP request fails
     """
     try:
+        session.headers.update({"User-Agent": config.user_agent})
         response = session.get(url, timeout=timeout)
 
         # Check if the response contains an HTTP error
@@ -50,7 +48,7 @@ def get_response(
         return None, f"Error: {str(re)}"
 
 
-def scrape_text(url: str) -> str:
+def scrape_text(url: str, config: Config) -> str:
     """Scrape text from a webpage
 
     Args:
@@ -59,7 +57,7 @@ def scrape_text(url: str) -> str:
     Returns:
         str: The scraped text
     """
-    response, error_message = get_response(url)
+    response, error_message = get_response(url, config)
     if error_message:
         return error_message
     if not response:
@@ -78,7 +76,7 @@ def scrape_text(url: str) -> str:
     return text
 
 
-def scrape_links(url: str) -> str | list[str]:
+def scrape_links(url: str, config: Config) -> str | list[str]:
     """Scrape links from a webpage
 
     Args:
@@ -87,7 +85,7 @@ def scrape_links(url: str) -> str | list[str]:
     Returns:
        str | list[str]: The scraped links
     """
-    response, error_message = get_response(url)
+    response, error_message = get_response(url, config)
     if error_message:
         return error_message
     if not response:
diff --git a/autogpt/commands/web_selenium.py b/autogpt/commands/web_selenium.py
index 72f849d0..da6dd35d 100644
--- a/autogpt/commands/web_selenium.py
+++ b/autogpt/commands/web_selenium.py
@@ -4,7 +4,7 @@ from __future__ import annotations
 import logging
 from pathlib import Path
 from sys import platform
-from typing import Optional, Type
+from typing import TYPE_CHECKING, Optional, Type
 
 from bs4 import BeautifulSoup
 from selenium.common.exceptions import WebDriverException
@@ -28,17 +28,17 @@ from webdriver_manager.firefox import GeckoDriverManager
 from webdriver_manager.microsoft import EdgeChromiumDriverManager as EdgeDriverManager
 
 from autogpt.commands.command import command
-from autogpt.config import Config
 from autogpt.logs import logger
 from autogpt.memory.vector import MemoryItem, NoMemory, get_memory
 from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
-from autogpt.processing.text import summarize_text
 from autogpt.url_utils.validators import validate_url
 
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 BrowserOptions = ChromeOptions | EdgeOptions | FirefoxOptions | SafariOptions
 
 FILE_DIR = Path(__file__).parent.parent
-CFG = Config()
 
 
 @command(
@@ -47,7 +47,7 @@ CFG = Config()
     '"url": "<url>", "question": "<what_you_want_to_find_on_website>"',
 )
 @validate_url
-def browse_website(url: str, question: str) -> str:
+def browse_website(url: str, question: str, config: Config) -> str:
     """Browse a website and return the answer and links to the user
 
     Args:
@@ -58,7 +58,7 @@ def browse_website(url: str, question: str) -> str:
         Tuple[str, WebDriver]: The answer and links to the user and the webdriver
     """
     try:
-        driver, text = scrape_text_with_selenium(url)
+        driver, text = scrape_text_with_selenium(url, config)
     except WebDriverException as e:
         # These errors are often quite long and include lots of context.
         # Just grab the first line.
@@ -66,7 +66,7 @@ def browse_website(url: str, question: str) -> str:
         return f"Error: {msg}"
 
     add_header(driver)
-    summary = summarize_memorize_webpage(url, text, question, driver)
+    summary = summarize_memorize_webpage(url, text, question, config, driver)
     links = scrape_links_with_selenium(driver, url)
 
     # Limit links to 5
@@ -76,7 +76,7 @@ def browse_website(url: str, question: str) -> str:
     return f"Answer gathered from website: {summary}\n\nLinks: {links}"
 
 
-def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
+def scrape_text_with_selenium(url: str, config: Config) -> tuple[WebDriver, str]:
     """Scrape text from a website using selenium
 
     Args:
@@ -94,23 +94,23 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
         "safari": SafariOptions,
     }
 
-    options: BrowserOptions = options_available[CFG.selenium_web_browser]()
+    options: BrowserOptions = options_available[config.selenium_web_browser]()
     options.add_argument(
         "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
     )
 
-    if CFG.selenium_web_browser == "firefox":
-        if CFG.selenium_headless:
+    if config.selenium_web_browser == "firefox":
+        if config.selenium_headless:
             options.headless = True
             options.add_argument("--disable-gpu")
         driver = FirefoxDriver(
             service=GeckoDriverService(GeckoDriverManager().install()), options=options
         )
-    elif CFG.selenium_web_browser == "edge":
+    elif config.selenium_web_browser == "edge":
         driver = EdgeDriver(
             service=EdgeDriverService(EdgeDriverManager().install()), options=options
         )
-    elif CFG.selenium_web_browser == "safari":
+    elif config.selenium_web_browser == "safari":
         # Requires a bit more setup on the users end
         # See https://developer.apple.com/documentation/webkit/testing_with_webdriver_in_safari
         driver = SafariDriver(options=options)
@@ -120,7 +120,7 @@ def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
             options.add_argument("--remote-debugging-port=9222")
 
         options.add_argument("--no-sandbox")
-        if CFG.selenium_headless:
+        if config.selenium_headless:
             options.add_argument("--headless=new")
             options.add_argument("--disable-gpu")
 
@@ -202,7 +202,11 @@ def add_header(driver: WebDriver) -> None:
 
 
 def summarize_memorize_webpage(
-    url: str, text: str, question: str, driver: Optional[WebDriver] = None
+    url: str,
+    text: str,
+    question: str,
+    config: Config,
+    driver: Optional[WebDriver] = None,
 ) -> str:
     """Summarize text using the OpenAI API
 
@@ -221,7 +225,7 @@ def summarize_memorize_webpage(
     text_length = len(text)
     logger.info(f"Text length: {text_length} characters")
 
-    memory = get_memory(CFG)
+    memory = get_memory(config)
 
     new_memory = MemoryItem.from_webpage(text, url, question=question)
     memory.add(new_memory)
diff --git a/autogpt/commands/write_tests.py b/autogpt/commands/write_tests.py
index 1f4c4dbb..a63c265f 100644
--- a/autogpt/commands/write_tests.py
+++ b/autogpt/commands/write_tests.py
@@ -2,17 +2,21 @@
 from __future__ import annotations
 
 import json
+from typing import TYPE_CHECKING
 
 from autogpt.commands.command import command
 from autogpt.llm.utils import call_ai_function
 
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
 
 @command(
     "write_tests",
     "Write Tests",
     '"code": "<full_code_string>", "focus": "<list_of_focus_areas>"',
 )
-def write_tests(code: str, focus: list[str]) -> str:
+def write_tests(code: str, focus: list[str], config: Config) -> str:
     """
     A function that takes in code and focus topics and returns a response from create
       chat completion api call.
@@ -34,4 +38,4 @@ def write_tests(code: str, focus: list[str]) -> str:
         " specific areas if required."
     )
 
-    return call_ai_function(function_string, args, description_string)
+    return call_ai_function(function_string, args, description_string, config=config)
diff --git a/autogpt/config/ai_config.py b/autogpt/config/ai_config.py
index 3872463f..1a526832 100644
--- a/autogpt/config/ai_config.py
+++ b/autogpt/config/ai_config.py
@@ -7,13 +7,14 @@ from __future__ import annotations
 import os
 import platform
 from pathlib import Path
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
 
 import distro
 import yaml
 
-from autogpt.commands.command import CommandRegistry
-from autogpt.prompts.generator import PromptGenerator
+if TYPE_CHECKING:
+    from autogpt.commands.command import CommandRegistry
+    from autogpt.prompts.generator import PromptGenerator
 
 # Soon this will go in a folder where it remembers more stuff about the run(s)
 SAVE_FILE = str(Path(os.getcwd()) / "ai_settings.yaml")
diff --git a/autogpt/configurator.py b/autogpt/configurator.py
index f156f2c7..6b855fe3 100644
--- a/autogpt/configurator.py
+++ b/autogpt/configurator.py
@@ -1,19 +1,22 @@
 """Configurator module."""
 from __future__ import annotations
 
+from typing import TYPE_CHECKING
+
 import click
 from colorama import Back, Fore, Style
 
 from autogpt import utils
-from autogpt.config import Config
 from autogpt.llm.utils import check_model
 from autogpt.logs import logger
 from autogpt.memory.vector import get_supported_memory_backends
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
 
 
 def create_config(
+    config: Config,
     continuous: bool,
     continuous_limit: int,
     ai_settings_file: str,
@@ -45,15 +48,15 @@ def create_config(
         allow_downloads (bool): Whether to allow Auto-GPT to download files natively
         skips_news (bool): Whether to suppress the output of latest news on startup
     """
-    CFG.set_debug_mode(False)
-    CFG.set_continuous_mode(False)
-    CFG.set_speak_mode(False)
-    CFG.set_fast_llm_model(check_model(CFG.fast_llm_model, "fast_llm_model"))
-    CFG.set_smart_llm_model(check_model(CFG.smart_llm_model, "smart_llm_model"))
+    config.set_debug_mode(False)
+    config.set_continuous_mode(False)
+    config.set_speak_mode(False)
+    config.set_fast_llm_model(check_model(config.fast_llm_model, "fast_llm_model"))
+    config.set_smart_llm_model(check_model(config.smart_llm_model, "smart_llm_model"))
 
     if debug:
         logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_debug_mode(True)
+        config.set_debug_mode(True)
 
     if continuous:
         logger.typewriter_log("Continuous Mode: ", Fore.RED, "ENABLED")
@@ -64,13 +67,13 @@ def create_config(
             " cause your AI to run forever or carry out actions you would not usually"
             " authorise. Use at your own risk.",
         )
-        CFG.set_continuous_mode(True)
+        config.set_continuous_mode(True)
 
         if continuous_limit:
             logger.typewriter_log(
                 "Continuous Limit: ", Fore.GREEN, f"{continuous_limit}"
             )
-            CFG.set_continuous_limit(continuous_limit)
+            config.set_continuous_limit(continuous_limit)
 
     # Check if continuous limit is used without continuous mode
     if continuous_limit and not continuous:
@@ -78,15 +81,15 @@ def create_config(
 
     if speak:
         logger.typewriter_log("Speak Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_speak_mode(True)
+        config.set_speak_mode(True)
 
     if gpt3only:
         logger.typewriter_log("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_smart_llm_model(CFG.fast_llm_model)
+        config.set_smart_llm_model(config.fast_llm_model)
 
     if gpt4only:
         logger.typewriter_log("GPT4 Only Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_fast_llm_model(CFG.smart_llm_model)
+        config.set_fast_llm_model(config.smart_llm_model)
 
     if memory_type:
         supported_memory = get_supported_memory_backends()
@@ -97,13 +100,13 @@ def create_config(
                 Fore.RED,
                 f"{supported_memory}",
             )
-            logger.typewriter_log("Defaulting to: ", Fore.YELLOW, CFG.memory_backend)
+            logger.typewriter_log("Defaulting to: ", Fore.YELLOW, config.memory_backend)
         else:
-            CFG.memory_backend = chosen
+            config.memory_backend = chosen
 
     if skip_reprompt:
         logger.typewriter_log("Skip Re-prompt: ", Fore.GREEN, "ENABLED")
-        CFG.skip_reprompt = True
+        config.skip_reprompt = True
 
     if ai_settings_file:
         file = ai_settings_file
@@ -116,8 +119,8 @@ def create_config(
             exit(1)
 
         logger.typewriter_log("Using AI Settings File:", Fore.GREEN, file)
-        CFG.ai_settings_file = file
-        CFG.skip_reprompt = True
+        config.ai_settings_file = file
+        config.skip_reprompt = True
 
     if prompt_settings_file:
         file = prompt_settings_file
@@ -130,10 +133,10 @@ def create_config(
             exit(1)
 
         logger.typewriter_log("Using Prompt Settings File:", Fore.GREEN, file)
-        CFG.prompt_settings_file = file
+        config.prompt_settings_file = file
 
     if browser_name:
-        CFG.selenium_web_browser = browser_name
+        config.selenium_web_browser = browser_name
 
     if allow_downloads:
         logger.typewriter_log("Native Downloading:", Fore.GREEN, "ENABLED")
@@ -148,7 +151,7 @@ def create_config(
             Fore.YELLOW,
             f"{Back.RED + Style.BRIGHT}ALWAYS REMEMBER TO NEVER OPEN FILES YOU AREN'T SURE OF!{Style.RESET_ALL}",
         )
-        CFG.allow_downloads = True
+        config.allow_downloads = True
 
     if skip_news:
-        CFG.skip_news = True
+        config.skip_news = True
diff --git a/autogpt/llm/utils/__init__.py b/autogpt/llm/utils/__init__.py
index b6bcc1d3..47e15896 100644
--- a/autogpt/llm/utils/__init__.py
+++ b/autogpt/llm/utils/__init__.py
@@ -109,7 +109,11 @@ def retry_openai_api(
 
 
 def call_ai_function(
-    function: str, args: list, description: str, model: str | None = None
+    function: str,
+    args: list,
+    description: str,
+    model: str | None = None,
+    config: Config = None,
 ) -> str:
     """Call an AI function
 
@@ -125,9 +129,8 @@ def call_ai_function(
     Returns:
         str: The response from the function
     """
-    cfg = Config()
     if model is None:
-        model = cfg.smart_llm_model
+        model = config.smart_llm_model
     # For each arg, if any are None, convert to "None":
     args = [str(arg) if arg is not None else "None" for arg in args]
     # parse args to comma separated string
diff --git a/autogpt/main.py b/autogpt/main.py
index 03f685db..39bbf8b5 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -49,6 +49,7 @@ def run_auto_gpt(
     check_openai_api_key()
 
     create_config(
+        cfg,
         continuous,
         continuous_limit,
         ai_settings,
diff --git a/requirements.txt b/requirements.txt
index 53785f9a..542f9b50 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -40,6 +40,10 @@ auto-gpt-plugin-template @ git+https://github.com/Significant-Gravitas/Auto-GPT-
 mkdocs
 pymdown-extensions
 mypy
+types-Markdown
+types-beautifulsoup4
+types-colorama
+types-Pillow
 
 # OpenAI and Generic plugins import
 openapi-python-client==0.13.4
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
index c45b71c8..18157e73 100644
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
@@ -1098,6 +1098,399 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3481'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
+        with other requests. You can retry your request, or contact us through our
+        help center at help.openai.com if the error persists. (Please include the
+        request ID 1d08452a41f33bf54874f93bf2a716de in your message.)\",\n    \"type\":
+        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cca53eb28d702ac-ORD
+      Content-Length:
+      - '349'
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 02:25:56 GMT
+      Function-Execution-Id:
+      - rvr2i8vhq9vo
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '30015'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      X-Cloud-Trace-Context:
+      - 69c7b246f231d9cbd0c2974c332ebc51;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86499'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.334s
+      X-Request-Id:
+      - 1d08452a41f33bf54874f93bf2a716de
+    status:
+      code: 429
+      message: Too Many Requests
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3481'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7yTTW/TQBCG7/yK0VxycaKE0DbxDQ6orTgAKioSRtbGHtvb2Dvu7pikRP7vlb+S
+        xqgnBNf5eN9ndmcOqGP0McqUREWZT69uq6fFJ/P+w+P3eWKf3P31l4+fv5pbfvhtEvSQNw8USd8x
+        i7gocxLNBj2MLCmhGP3F5erderW4uFx7WHBMOfqYljJdzi6mUtkNT+fL+QI9rJxKCf0DlpaLUkLh
+        LRmH/tVq7uFJ+xh/u1h6KCwqP4bW62XtYZSxjsih/+OABblB1nJO6KNyTjtRRhpINkKmGeAQGACA
+        ACXjKs3EBehDH+wTtJcmGOAN7HSeQ+UIJCPYWS0UCoeJzgkiLgplYhDuEjC5pjxnuGebxxPQRhgU
+        tKVGFRTDJGvy4a7Jz2Qvk1mA3ktjS8qx0Sbt3O8yAlFuC5YeK23JQUF/4wZ3r86gXTtgwU5AlaXl
+        0molp3zCFiRrqpTbjrHLXJmOeArf/tlTBeak3lCE/aKcqR9jQ9WYNbJadKRdMXywIWo7ybjKNn1K
+        4AYy9avTiNhaiqRla9CgNaK9wIYStgSV0yZ9feSxvytJbf/XcnXGtTdsfC/6x8I3Ch3TGcQIXdl0
+        fCtdYnibTmLEcSYyvq8XMw20LXEPHpgaaw8TbbTLwu460EcnXKKH2sS0R39e/6zfPAMAAP//AwBM
+        TWg3zwQAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cca54f8fd85111e-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 02:26:34 GMT
+      Function-Execution-Id:
+      - rvr2pyuh5pu6
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '25106'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - bb40fcb7f86d47a999346b879f520f53;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '86499'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 2.334s
+      X-Request-Id:
+      - 03d492530fb90d6815d8d49a68ab49b4
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
+      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
+      Use the task_complete command to complete the task.\n3. Do not use any other
+      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
+      short term memory is short, so immediately save important information to files.\n2.
+      If you are unsure how you previously did something or want to recall past events,
+      thinking about similar events will help you remember.\n3. No user assistance\n4.
+      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
+      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created and nothing new has happened."}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I will use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
+      to write ''Hello World'' into a file named ''hello_world.txt''. The write_to_file
+      command is the most appropriate command for this task.\",\n        \"plan\":
+      \"- Use the write_to_file command to write ''Hello World'' into a file named
+      ''hello_world.txt''.\\n- Use the task_complete command to complete the task.\",\n        \"criticism\":
+      \"I need to ensure that I have the correct filename and text before using the
+      write_to_file command.\",\n        \"speak\": \"I will use the write_to_file
+      command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
+    headers:
+      AGENT-MODE:
+      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
+      AGENT-TYPE:
+      - Auto-GPT-2023-X-TYPE
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4801'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA6SST4/aQAzF7/0Uli9cAoIu7EJurSrUrdpeSrWHpkLDxEmmzIzTGUewQnz3KhD+
+        lG5Pe/Wzf/PseTs0OaaoKyXa1bb/8Kl5XsznrtEf5t/e5++Kz266Wsyar5vHL2tMkFe/SEs3MdDs
+        akti2GOCOpASyjEd3U/Hs+loMntI0HFOFlMsa+nfDSZ9acKK+8O74QgTbKIqCdMd1oFdLUvhNfmI
+        6Wh4P0zwAr8Ik3GCwqLspfR2NN4nqCs2miKmP3boKJ7AgS1hiipGE0V5aW2yF/LtCrvMAwBkKBU3
+        ZSUxwxS6YifQVtpiho+wMdZCEwmkIhAV18vOIIFm55TPQRjOtVPXIMPkGhlIRfbGl0fuomuDQL8b
+        EyiCo5azCUYIeh/JWoYnDjbvgfHCoKAwlsArRzn0qlZfblp9IFvpwcFGRf4FI7D4r3ETD22Oo4Cq
+        68B1MOpKLziAVG3XCxvVVvnjMn34/ur76GDEaBPd6e6e6DBJPjahnVNyHm6Nn4krKjgQxKoRMb6E
+        nDf+lh5rUuvX/+gRuU9OAera/8lP+0vH1/7C35hSobyN3nVWuqC0654AOcRGa4qxaKx9Phs6mOq8
+        ZX6P+wQL402slkcSphiFa0zQ+Jy2mA73P/dv/gAAAP//AwBuG68bAwQAAA==
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Alt-Svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Cache-Control:
+      - no-cache, must-revalidate
+      Cf-Cache-Status:
+      - DYNAMIC
+      Cf-Ray:
+      - 7cca55aa8ee7e100-ORD
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 25 May 2023 02:26:53 GMT
+      Function-Execution-Id:
+      - rvr2qsuver9b
+      Openai-Model:
+      - gpt-3.5-turbo-0301
+      Openai-Organization:
+      - significant-gravitas
+      Openai-Processing-Ms:
+      - '15614'
+      Openai-Version:
+      - '2020-10-01'
+      Server:
+      - Google Frontend
+      Strict-Transport-Security:
+      - max-age=15724800; includeSubDomains
+      Vary:
+      - Accept-Encoding
+      X-Cloud-Trace-Context:
+      - 0b238e84f74b403e164b93d247259c70;o=1
+      X-Powered-By:
+      - Express
+      X-Ratelimit-Limit-Requests:
+      - '3500'
+      X-Ratelimit-Limit-Tokens:
+      - '90000'
+      X-Ratelimit-Remaining-Requests:
+      - '3499'
+      X-Ratelimit-Remaining-Tokens:
+      - '84695'
+      X-Ratelimit-Reset-Requests:
+      - 17ms
+      X-Ratelimit-Reset-Tokens:
+      - 3.536s
+      X-Request-Id:
+      - b1fb38bd412977a3cd85ec84fbdd44d0
+    status:
+      code: 200
+      message: OK
 - request:
     body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
       are write_to_file-GPT, an AI designed to use the write_to_file command to write
@@ -1105,9 +1498,9 @@ interactions:
       command to complete the task.\nYour decisions must always be made independently
       without seeking user assistance. Play to your strengths as an LLM and pursue
       simple strategies with no legal complications.\nThe OS you are running on is:
-      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
-      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
-      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      Windows-10\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello World''
+      into a file named \"hello_world.txt\".\n2. Use the task_complete command to
+      complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
       ~4000 word limit for short term memory. Your short term memory is short, so
       immediately save important information to files.\n2. If you are unsure how you
       previously did something or want to recall past events, thinking about similar
@@ -1150,7 +1543,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '3441'
+      - '3433'
       Content-Type:
       - application/json
     method: POST
@@ -1158,21 +1551,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6STTXPaMBCG7/0VO3vhYhg+Emh86y10uKWZTqfueIS8YIEsOdJ6Qsv4v3eEbSCk
-        5FCO2o9Xzyvt7lFlGKPMBcui1P3Z182PxXS1eLL0Mn588UL9eVr81s+8KXcjjNAuNyS57RhIW5Sa
-        WFmDEUpHginDeDT9fPcwmU0fJhEWNiONMa5L7k8G932u3NL2h5NhEKu8WBPGeyydLUpO2W7JeIxn
-        s/sIT9rH+PhuGiFbFvoYGg3HozpCmVslyWP8c48F+U7XWU0Yo/BeeRaGA6U1TCY42CcGACBBzm21
-        ztknGEMbbBO04xBMcA6GKAO28OoUE/QeSWsL363TWQ+UYQsCVkoTGFFQBr085NPXkB/wjnsgTAac
-        k4HWF4UTsPBbqLwy68OxF85pV9ELtYUw2SDB6JzLkfDWKLNu4L6FzgNXyjYNFMdOkMLAkqDyN9EP
-        4MuKyQHngiOYH1QrTx8xh9veWb00UmphGg99eO70rji5gT5JzJn+DbzSKVZS+eJyKsj4ytHhfWAO
-        ojj7U2mdI8knwnYUBH9oV3nwlZTk/arSsKSVddQBdtL/QvQliW2H96q0/u+JPRvLK4zXZ3qQYANV
-        R92WtU3vlixc3/C+ueXClnDry/1sEqH2JHFh4o3I5U6fPUhHeyBuwRNTYx3hShnl87RZOYzRsy0x
-        QmUy2mE8rH/Vn/4CAAD//wMAcOALfkQFAAA=
+        H4sIAAAAAAAAA7yTTW/bMAyG7/sVBC+5KEHidkvi2zbsI7sW+wDmIVBk1lYjS55EIx6C/PdBdtym
+        LtANGLArSb/v89LUEXWOKapSsqpqM11+au/eXOsv3+Sv98tk965wefs60R/q5ObtDgW63R0pPn8x
+        U66qDbF2FgUqT5Ipx3TxanW9XieL1UJg5XIymGJR8/Rq9nLKjd+56fxqvkCBTZAFYXrE2ruq5i27
+        PdmA6XI5F/igfV9PFolAdizNfWm9Sk4CVem0ooDp9yNWFAZZ7wxhijIEHVhajpDOMtkY4JhZAIAM
+        uXRNUXLIMIVz8dyglmMxww1YohzYQRMIuCQ4eM20Zbe91YZAuaqSthvoGjD5SMY4+Oq8ySegLTuQ
+        0I1aWVEOkzL2t4fYn3HLk1mG4tLbkwzOalv0ADfaqt6YZdiDp5+N9hSgor/wFLCBgzbmefjZMFXL
+        ELqx2I24IMNTYOjyRiBquZu4tB/HqY20fZIpfP5PK1Res1Y6VON/SDY0PjJIhs1DXOW8J8UXsSNO
+        TMfumbWNXENNcj84/nnr/5a3Nz6J4ZTPok8uOSr0TI8gRujSF+NH0DeGjfQSI45HIuOHc5FpoO2I
+        z+CZPeFJ4K22OpTb/uYxxcCuRoHa5tRiOj/9OL34DQAA//8DACqjUZ+oBAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7cc625c85c302cb4-DFW
+      - 7ccb58103e2be73a-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -1182,7 +1574,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 24 May 2023 14:15:34 GMT
+      - Thu, 25 May 2023 05:23:27 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -1194,7 +1586,7 @@ interactions:
       openai-organization:
       - significant-gravitas
       openai-processing-ms:
-      - '40542'
+      - '25366'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1206,13 +1598,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '3499'
       x-ratelimit-remaining-tokens:
-      - '86502'
+      - '86499'
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.332s
+      - 2.334s
       x-request-id:
-      - 5e84c935a23a6ad8f5a2601dd432725b
+      - 754502cb0f1f1266c1f1e1f7bc9b7b6b
     status:
       code: 200
       message: OK
@@ -1223,9 +1615,9 @@ interactions:
       command to complete the task.\nYour decisions must always be made independently
       without seeking user assistance. Play to your strengths as an LLM and pursue
       simple strategies with no legal complications.\nThe OS you are running on is:
-      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
-      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
-      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      Windows-10\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello World''
+      into a file named \"hello_world.txt\".\n2. Use the task_complete command to
+      complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
       ~4000 word limit for short term memory. Your short term memory is short, so
       immediately save important information to files.\n2. If you are unsure how you
       previously did something or want to recall past events, thinking about similar
@@ -1261,22 +1653,21 @@ interactions:
       reminds you of these events from your past: \nI was created and nothing new
       has happened."}, {"role": "user", "content": "Determine which next command to
       use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I need to write ''Hello
-      World'' into a file named ''hello_world.txt'' and then complete the task using
-      the ''task_complete'' command.\",\n        \"reasoning\": \"The ''write_to_file''
-      command can be used to write ''Hello World'' into a file named ''hello_world.txt''.
-      After that, I can use the ''task_complete'' command to complete the task.\",\n        \"plan\":
-      \"- Use the ''write_to_file'' command to write ''Hello World'' into a file named
-      ''hello_world.txt''.\\n- Use the ''task_complete'' command to complete the task.\",\n        \"criticism\":
-      \"I need to ensure that I am using the correct file name and that the ''write_to_file''
-      command is successful before completing the task.\",\n        \"speak\": \"I
-      will write ''Hello World'' into a file named ''hello_world.txt'' using the ''write_to_file''
-      command and then complete the task.\"\n    },\n    \"command\": {\n        \"name\":
-      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
-      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
-      write_to_file returned: File written to successfully."}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
+      "content": "{\n    \"thoughts\": {\n        \"text\": \"I need to use the write_to_file
+      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"reasoning\":
+      \"Since the task requires me to write ''Hello World'' into a file, I will use
+      the write_to_file command. I will pass the filename as ''hello_world.txt'' and
+      the text as ''Hello World''.\",\n        \"plan\": \"- Use the write_to_file
+      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
+      \"I need to ensure that I pass the correct filename and text to the write_to_file
+      command.\",\n        \"speak\": \"I will use the write_to_file command to write
+      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command write_to_file returned: File written
+      to successfully."}, {"role": "user", "content": "Determine which next command
+      to use, and respond using the format specified above:"}], "temperature": 0,
+      "max_tokens": 0}'
     headers:
       Accept:
       - '*/*'
@@ -1285,7 +1676,7 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '4877'
+      - '4714'
       Content-Type:
       - application/json
     method: POST
@@ -1293,20 +1684,20 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA6yS3Y7TMBCF73mK0dz0xq3aDf0hLwCL4AKxKyTIKnKdaeKtYwfPRC1UeXeUTbst
-        XQkhxKXneL45Y58D2gJTNJUWUzduvHz/+DWhnx8Wnxxvi2r/sb4pq/puGu+3b7+jwrB+JCPHjokJ
-        deNIbPCo0ETSQgWms8Xq9ZtkuUyWCutQkMMUy0bGyWQ+ljauw3iaTGeosGVdEqYHbGKoG8klbMkz
-        prPpaqXwDD8Li7lCCaLduXQzTzqFpgrWEGP67YA18QkcgyNMUTNbFu2ltxm8kO9XOGQeACBDqUJb
-        VsIZpnAsHgXaS1/M8K4iGO2iFcol5BvraAQm1LX2Bew0A7fGEPOmdQo4wC0Y7cGHHRy3IJCKQDRv
-        oWXry6fjqD/npxvPwEmG6tJFJM3BW18OVj5bbwbc3xr6r24ap/1gZAz3TH9qBQkvJ17zTLRijeV6
-        gN6CJ3rqJM9t7Pu0nO1afiYWFzu6H7CmTYgE5IvTQk0MZdT19UBuSG9Pw3bWuX98lYHZqVOKjsqL
-        EHld0zDuN9SVKx3L6/xd/v4AeEfOBfgSoiug0gxrIg99CIR8/2RVr+e7Xp9IH90zrDvazXyHncKN
-        9ZarfIBjiiyhQYXWF7THdNo9dK9+AQAA//8DAKoIau4bBAAA
+        H4sIAAAAAAAAA6ySTW/TQBCG7/yK0Vx62VROWlriW09tQXAASg8YRZv12N5mvWPtjkmqyP8dJbaT
+        EpCQgOs7M+8887FFm2OKptJi6sZNrt9unvJ3SSPvi6L4uL411w/mxtS3X57vljeokJdPZGSoODdc
+        N47EskeFJpAWyjGdXr25nM9ns2SusOacHKZYNjK5OH89kTYseZJcJFNU2EZdEqZbbALXjSyEV+Qj
+        ptPkcq7waH4MXE0VCot2R2k2TTqFpmJrKGL6dYs1xdE4sCNMUcdoo2gvO0z2Qn43wjbzAAAZSsVt
+        WUnMMIVBHAK0kZ2Y4Qdeg1Ra4B4q/Z1gHawIeTi7I+cYHjm4/AysFwapCArrSME9eKIchKGNtNdF
+        x9ViGIzAcF1rv084aGPWeYbqJUogHdlbX/Y8n6w3NMKMxfmhGrjYI1pf/glxbZ37D3yN075Hm8DD
+        P7uZHbuxse4tj4skH9tA4ykaHePew3AIZAT6LcEw4m/7n7aKDenV2Obvl9Fbdmr8qSH9l5fyuqa+
+        20/2J1A6lKff+PINeoPPu0Mfbx9bYyjGonXu+QC0hxrYMt9hp7Cw3sZq0TthilG4QYXW57TBNOm+
+        da9+AAAA//8DAFX+S9wWBAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 7cc626d9d9b72cb4-DFW
+      - 7ccb58bf8a30e73a-DFW
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -1316,7 +1707,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 24 May 2023 14:16:05 GMT
+      - Thu, 25 May 2023 05:23:51 GMT
       Server:
       - cloudflare
       access-control-allow-origin:
@@ -1328,7 +1719,7 @@ interactions:
       openai-organization:
       - significant-gravitas
       openai-processing-ms:
-      - '28427'
+      - '21630'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -1344,9 +1735,9 @@ interactions:
       x-ratelimit-reset-requests:
       - 17ms
       x-ratelimit-reset-tokens:
-      - 2.343s
+      - 2.342s
       x-request-id:
-      - 941875e93a46562c74839ad42ec1c215
+      - 22f487f4ffb66999eb1baab18655bc17
     status:
       code: 200
       message: OK
@@ -1577,4 +1968,253 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\nThe OS you are running on is:
+      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
+      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
+      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3441'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA7ySQW/bMAyF7/sVBC+5KEGCLE3j+4YFQ4thxVBgcxGoMmNrlURDotcAgf/74DhJ
+        Gw8bdtmufNR7H0Xu0RaYoam0GF+78fLj+uY2rVYmflrexdv3/se9TjsJ8fPXdzeokB+/k5Hji4lh
+        XzsSywEVmkhaqMBsdnW9mC5nb1czhZ4LcphhWct4PlmMpYmPPJ7OpzNU2CRdEmZ7rCP7WjbCTxQS
+        ZsvlQuGL97k+W80VCot259Lq6rpVaCq2hhJm3/boKZ1sIzvCDHVKNokO0kFyEArdAPs8AADkKBU3
+        ZSUpxwyOxaNAO+mKOa4hEBUgDE0ikIrgOVqhjfBmax2BYe91ODQcBBh9IOcY7jm6YgQ2CIOGQ2vQ
+        ngoYVZ2+ee70iexkNMlRvc6OpBMHG8oe4M4G0weXrB3Y9BdR6g+gnUFF4DkJ6LqOXEer5WKQJtEQ
+        qnY69Dxj+PKfPsJEK9bY5IeboJCa2DFogfV5L4ZjJCOgY9l4CpJgy/H3oMO0VJN+OiU9W+f+5cL7
+        4FadDvFo+ssddg490wXEAF3HcnjCvdD1vlgMOC5Mhmf/aqYT7YH4CJ6HFluFWxtsqjb9xWKGSbhG
+        hTYUtMNs2j60b34CAAD//wMA1PnFsWYEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2e853ad25e702-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:25:14 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '23538'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86502'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.332s
+      x-request-id:
+      - 6a8a3cf2a18b70df31c5e47f66614c59
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are write_to_file-GPT, an AI designed to use the write_to_file command to write
+      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
+      command to complete the task.\nYour decisions must always be made independently
+      without seeking user assistance. Play to your strengths as an LLM and pursue
+      simple strategies with no legal complications.\nThe OS you are running on is:
+      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
+      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
+      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
+      ~4000 word limit for short term memory. Your short term memory is short, so
+      immediately save important information to files.\n2. If you are unsure how you
+      previously did something or want to recall past events, thinking about similar
+      events will help you remember.\n3. No user assistance\n4. Exclusively use the
+      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
+      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
+      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
+      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
+      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
+      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
+      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
+      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
+      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
+      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
+      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
+      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
+      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
+      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
+      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
+      Continuously review and analyze your actions to ensure you are performing to
+      the best of your abilities.\n2. Constructively self-criticize your big-picture
+      behavior constantly.\n3. Reflect on past decisions and strategies to refine
+      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
+      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
+      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
+      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
+      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
+      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
+      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
+      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
+      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
+      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
+      reminds you of these events from your past: \nI was created"}, {"role": "user",
+      "content": "Determine which next command to use, and respond using the format
+      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\",\n        \"reasoning\": \"Since the goal is to
+      write ''Hello World'' into a file, the write_to_file command is the most appropriate
+      command to use.\",\n        \"plan\": \"- Use the write_to_file command to write
+      ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
+      \"I need to ensure that I use the correct arguments for the write_to_file command.\",\n        \"speak\":
+      \"I will use the write_to_file command to write ''Hello World'' into a file
+      named ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\":
+      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
+      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
+      write_to_file returned: File written to successfully."}, {"role": "user", "content":
+      "Determine which next command to use, and respond using the format specified
+      above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4626'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SSS48TMRCE7/yKVl9ymUTJZkNgjiAhIsQBsWh3xaDI8XRmTDxuy+7ZBEX572ge
+        eZAViL1ZXfbnKrv2aHJMUZdKdOXtcP5p8dmVt8bfe/u+fPc03SzuHj48mi+TB0+YIK9+kpb+xEhz
+        5S2JYYcJ6kBKKMd08vrNbDyfzCbzBCvOyWKKhZfhdDQbSh1WPBxPxxNMsI6qIEz36ANXXpbCG3IR
+        08n45m2CZ/hZmN8mKCzKnkc34+khQV2y0RQx/b7HiuIRHNgSpqhiNFGUk8YmOyHXRNhnDgAgQym5
+        LkqJGabQD3uBdtIMM7wrCRztBDRXlXI5CEMdCUwEUXGz7M1SMz+vS2rVUYbJJTaQiuyMKzr2V+N0
+        t7lgZVskwzYYIRh8JGsZ7jnYfADGCYOCtbEETlWUw6Bs9OW20UeykwG03vp7oVQRVkTuZClPTuLZ
+        8jFSc3FJUHEUUN4H9sGoC72LfB3GW+W6HEP4Fukf/P95Gh2MGG1i1SEX4Ijak+RiHZpzSmABPvCT
+        yQkUdG8Jaw5HuHHFX/HRk9oc0VtjbfuJL7bcIQ/JsUD99mf9aT6pu+0P/JUpFYrr6l325FzA9k95
+        3XajSfnydjwvBMRaa4pxXVv76xStjdenzNwBDwmujTOxXHaeMMUo7DFB43LaYTo+/Di8+g0AAP//
+        AwDeKpjwTQQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2e8f7bfaee702-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:25:40 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '23218'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86010'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.66s
+      x-request-id:
+      - 29a5d0f069d62474b048ab97ae6b614d
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/basic_abilities/test_browse_website.py b/tests/integration/challenges/basic_abilities/test_browse_website.py
index 4befb059..3f9821ed 100644
--- a/tests/integration/challenges/basic_abilities/test_browse_website.py
+++ b/tests/integration/challenges/basic_abilities/test_browse_website.py
@@ -13,9 +13,11 @@ def test_browse_website(
     browser_agent: Agent,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
+    # config: Config,
 ) -> None:
     file_path = browser_agent.workspace.get_path("browse_website.txt")
     run_interaction_loop(monkeypatch, browser_agent, CYCLE_COUNT)
 
+    # content = read_file(file_path, config)
     content = open(file_path, encoding="utf-8").read()
     assert "£25.89" in content, f"Expected £25.89, got {content}"
diff --git a/tests/integration/challenges/basic_abilities/test_write_file.py b/tests/integration/challenges/basic_abilities/test_write_file.py
index 1b0198c7..efc5e921 100644
--- a/tests/integration/challenges/basic_abilities/test_write_file.py
+++ b/tests/integration/challenges/basic_abilities/test_write_file.py
@@ -2,6 +2,7 @@ import pytest
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -14,9 +15,10 @@ def test_write_file(
     writer_agent: Agent,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
+    config: Config,
 ) -> None:
     file_path = str(writer_agent.workspace.get_path("hello_world.txt"))
     run_interaction_loop(monkeypatch, writer_agent, CYCLE_COUNT)
 
-    content = read_file(file_path)
+    content = read_file(file_path, config)
     assert content == "Hello World", f"Expected 'Hello World', got {content}"
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index e5275071..42e9a993 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -1,6 +1,9 @@
+import typing
+
 import pytest
 
 from autogpt.commands.file_operations import read_file, write_to_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
 from tests.utils import requires_api_key
 
@@ -16,6 +19,7 @@ def test_information_retrieval_challenge_a(
     get_company_revenue_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
     patched_api_requestor: None,
+    config: Config,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs and checking the output file content.
@@ -26,5 +30,5 @@ def test_information_retrieval_challenge_a(
     run_interaction_loop(monkeypatch, get_company_revenue_agent, CYCLE_COUNT)
 
     file_path = str(get_company_revenue_agent.workspace.get_path("output.txt"))
-    content = read_file(file_path)
+    content = read_file(file_path, config)
     assert "81" in content, "Expected the file to contain 81"
diff --git a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
index b8ae3004..b84f5018 100644
--- a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
+++ b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
@@ -3,6 +3,7 @@ import yaml
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
 from tests.utils import requires_api_key
 
@@ -14,7 +15,7 @@ CYCLE_COUNT = 6
 @requires_api_key("OPENAI_API_KEY")
 @run_multiple_times(3)
 def test_kubernetes_template_challenge_a(
-    kubernetes_agent: Agent, monkeypatch: pytest.MonkeyPatch
+    kubernetes_agent: Agent, monkeypatch: pytest.MonkeyPatch, config: Config
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs
@@ -26,7 +27,7 @@ def test_kubernetes_template_challenge_a(
     run_interaction_loop(monkeypatch, kubernetes_agent, CYCLE_COUNT)
 
     file_path = str(kubernetes_agent.workspace.get_path("kube.yaml"))
-    content = read_file(file_path)
+    content = read_file(file_path, config)
 
     for word in ["apiVersion", "kind", "metadata", "spec"]:
         assert word in content, f"Expected the file to contain {word}"
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
index 159f9dfa..cc0a43be 100644
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
@@ -2011,7 +2011,7 @@ interactions:
       Vary:
       - Accept-Encoding
       X-Cloud-Trace-Context:
-      - b3143c8eb6fb2bdcf9b7429eff4fa7b4
+      - 0128c66c9918142a24cd829bbc2b234a;o=1
       X-Powered-By:
       - Express
       X-Ratelimit-Limit-Requests:
@@ -2283,7 +2283,7 @@ interactions:
       X-Ratelimit-Remaining-Requests:
       - '3499'
       X-Ratelimit-Remaining-Tokens:
-      - '89467'
+      - '86452'
       X-Ratelimit-Reset-Requests:
       - 17ms
       X-Ratelimit-Reset-Tokens:
@@ -2650,4 +2650,700 @@ interactions:
     status:
       code: 200
       message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "user", "content": "Determine which next command to use, and respond using the
+      format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '3334'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4SST2/bMAzF7/sUBM92EC9J0/o2YCiQdRiwPz3NRaBItK1FljyJRpMF/u6D4jgd
+        kqK7PpF8v0fxgFphjrIWLJvWpMuH1ZePcq6WD5/vv9HXcju/fz+ruk+P37PWYYJu84sknzom0jWt
+        IdbOYoLSk2BSmGc3t4vpMlvMZwk2TpHBHKuW09lkkXLnNy6dzqYZJtgFURHmB2y9a1pes9uSDZgv
+        58sEX2af9Wx+lyA7FuYs3d7d9AnK2mlJAfOfB2wojGO9M4Q5ihB0YGE5QjrLZGOAQ2EBAArk2nVV
+        zaHAHE7i6YF2HMUCVxBq1xkFgYVn2OzBk1DaVsA1gbaBfScjalhnE94xlNoQdGGsiNXroyZd0wir
+        JgUm/1p5EsFZbavB70dNUGofGAJTCzoAO+isIh9zqCtXiOJzLTiWevrdaU8KXAkNXTq1RtjBJIXH
+        QK/jRbsovhWvKGwKH6ww+z/0OpAiJt9oOzxb2g1xwgWR9Jq11KEZd22JjgRkQ+djs2BYvRm/7IzZ
+        w4ZK5wla7yRR/J3L7KElsR1dnrUx///PY9RJgcOYPhmP5rSoq5uxoqHB4bzUCwjhq8tTGx5i7Uv7
+        9dZHiCPIiaewPfYJltrqUK+HK8IcA7sWE9RW0Q7zaf/Uv/sLAAD//wMA45HODOkDAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2e99b5c6fe9a4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:26:01 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '18270'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86499'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.334s
+      x-request-id:
+      - b5f5aa8c3ec85b75f27d68bfcc745c41
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
+      file using the read_file command.\",\n        \"reasoning\": \"The first step
+      is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4415'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4ySTW/bMAyG7/sVAs92ECdLmvq2YzeswID1MMxDoEi0rUaiPIlG0wb+74PjuOmc
+        Ydv1Jfny4ccRjIYcVC1ZucamN5/u7r99nuv9z9Xm0aldeb/bVC9f9u1i8fEBEvC7R1R8rpgp7xqL
+        bDxBAiqgZNSQZ+vNan6TrdbvE3Beo4UcqobT5WyVcht2Pp0v5xkk0EZZIeRHaIJ3DW/Z75Ei5Lfr
+        dQIX71c9Wy0TYM/SXqQsu+0SULU3CiPk34/gMI6+wVuEHGSMJrIk7ik9MVI/wbEgIYQogGvfVjXH
+        AnJxFs8BPHAvFnAnCFEL9iKg1IJrFIYih1b1gHG7mPGBRWksijYaqk4Zfer2pCnvnCQ9KyB56x9Q
+        Rk+GqqHJ17+49tjSUDwZEx5YRGThy98KBNeSxYW19Nb6p2nXxkoaGqbiIeKfUf9n1KKgVHwgaZ9f
+        8CpP9CYaGYMzhG+wGZs4IVLBsFEmuumykWIbcByrJY2hv+M1lShba5/FDksfUDTBK0RtqJrOHhuU
+        +7HLk7H23/ek0wYHky4Zf+a8pquXIelw8H9d6QRBhmr6aUOgz72UX+OMECeQM09BHXQJlIZMrLfD
+        P0EOkX0DCRjSeIB83v3o3v0CAAD//wMASHHt0ukDAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2ea1e7fd1e9a4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:26:25 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '20708'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '85998'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.668s
+      x-request-id:
+      - 0a4cec880e7cc8e6c9fd4a8c224e02eb
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
+      file using the read_file command.\",\n        \"reasoning\": \"The first step
+      is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '5374'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4ySTW/TQBCG7/yK1ZzXUUyUJvINEIeqLQIEHKhRtNkd29uuZ63dMUmJ/N+R45gU
+        BwHX+XjneWfmANZABrpSrOvGJaub63ff74J7/fHDbm2+vOVbev91fvfm5uG2LkGC3z6g5lPHTPu6
+        ccjWE0jQARWjgSy9Wi/nq3S5XkmovUEHGZQNJ4vZMuE2bH0yX8xTkNBGVSJkB2iCrxvesH9EipCl
+        6dVLCWfxc2K5kMCelTuHFumyk6ArbzVGyO4PUGMchYN3CBmoGG1kRdxjemKk3sIhJyGEyIEr35YV
+        xxwycQqeErjnPpjDtSBEI9iLgMoIrlBYihxa3QPGzWLGexaFdSjaaKk8VvSlm2NM+7pWZGY5yOf6
+        AVX0ZKkchnz6i2qPrSzFozDhnkVEFr74rUFwpVicWQvvnN9NpzZO0TAwEZ8j/hn1f6zmOSXiFSn3
+        9AMv6kQvYpAx1JbwGTZjEydEOli22sZ6umyk2AYcbbVkMPR3vKQSRevck9hi4QOKJniNaCyVU++x
+        QfU4TtlZ5/59TzpucBDp5PgzpzVdvAypGgf9XyudIKhQTj9tSPS15/ZLnBHiCHLiyamDTkJhycZq
+        M/wTZBDZNyDBksE9ZPPuW/fiJwAAAP//AwASKayp6gMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2eaafde3be9a4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:26:46 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '18484'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '85993'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.671s
+      x-request-id:
+      - 34eb238426602367df90ee10e18db817
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
+      file using the read_file command.\",\n        \"reasoning\": \"The first step
+      is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"}],
+      "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6353'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA5SST2/bMAzF7/sUAs9K4MT50/ncQ4MO22UdMMxDoMqMrcUmPYlGAgT+7oPtBG49
+        DF2vj+J7P1K8gMsgAVsYsVVdzraPuy8P93S6f/z2/dNqGZX1E27jwtw9HD6fQAM//0Ir14655aou
+        URwTaLAejWAGyWJzt462i030UUPFGZaQQF7LLJ6vZ9L4Z55FcbQADU0wOUJygdpzVcte+IgUIFnE
+        m6WG0XwsbJcahMWUo7SOV60GW7CzGCD5cYEKw83Yc4mQgAnBBTEkHSaTIHUjXFJSSqkUpOAmLySk
+        kKireC3gWToxhZ0ixEwJq5N3gkoKVGLCce8y5Ui4F7iRupG5nEUdXImqCY7yvtI37YX3vW65qgxl
+        8xT0yzSPJjA5yofIrwUqR0F8Y7slBOXxd+M8qgrfx6FVYDUO0AT8N1P3IOtcjEzx6tLQQDZTT295
+        /D/dJMV6J866UE33jhQajz2Z2r3wt+w9WnkzZzpOqNEcbyEnV5bv+Vni0zyFwa7Vtzu6zv/XGZGp
+        cEh6ta8JkPH59AKHQvd2tBhRXvVPD3YZL1Y3wp7yCptSC62GgyMXiv1wcpBAEK5Bg6MMz5BE7c/2
+        wx8AAAD//wMAvsNLCRsEAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2eb32da79e9a4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 26 May 2023 03:27:10 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '21216'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '85987'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.675s
+      x-request-id:
+      - b054f20306579e7810b86bc92965ef9e
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
+      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
+      using the read_file method and follow the instructions in the file.\nYour decisions
+      must always be made independently without seeking user assistance. Play to your
+      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
+      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
+      read_file to read the instructions_1.txt file\n2. Follow the instructions in
+      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
+      term memory. Your short term memory is short, so immediately save important
+      information to files.\n2. If you are unsure how you previously did something
+      or want to recall past events, thinking about similar events will help you remember.\n3.
+      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
+      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
+      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
+      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
+      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
+      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
+      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
+      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
+      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
+      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
+      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
+      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
+      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
+      Internet access for searches and information gathering.\n2. Long Term memory
+      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
+      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
+      actions to ensure you are performing to the best of your abilities.\n2. Constructively
+      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
+      and strategies to refine your approach.\n4. Every command has a cost, so be
+      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
+      Write all code to a file.\n\nYou should only respond in JSON format as described
+      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
+      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
+      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
+      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
+      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
+      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
+      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
+      "system", "content": "This reminds you of these events from your past: \nI was
+      created"}, {"role": "user", "content": "Determine which next command to use,
+      and respond using the format specified above:"}, {"role": "assistant", "content":
+      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
+      file using the read_file command.\",\n        \"reasoning\": \"The first step
+      is to understand the instructions and what is required of me.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
+      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
+      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
+      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_2.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
+      {\n        \"text\": \"I need to read the instructions_3.txt file using the
+      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
+      contains the next set of instructions that I need to follow.\",\n        \"plan\":
+      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
+      the instructions and determine the next steps\",\n        \"criticism\": \"I
+      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
+      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
+      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
+      {"role": "system", "content": "Command read_file returned: Write the task_id
+      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
+      which next command to use, and respond using the format specified above:"},
+      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
+      \"I need to write the task_id into the output.txt file using the write_to_file
+      command.\",\n        \"reasoning\": \"The instructions require me to write the
+      task_id into the output.txt file, so I need to use the write_to_file command
+      to do that.\",\n        \"plan\": \"- Use the write_to_file command to write
+      the task_id into the output.txt file\",\n        \"criticism\": \"I need to
+      ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
+      \"I will write the task_id into the output.txt file now.\"\n    },\n    \"command\":
+      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
+      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
+      "system", "content": "Command write_to_file returned: File written to successfully."},
+      {"role": "user", "content": "Determine which next command to use, and respond
+      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '7362'
+      Content-Type:
+      - application/json
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3SRS2/bMBCE7/0VxJ4pw684jm4FiiIpgp5aoEUVGDS1lhjzoXJXsQ1D/73Qw7Wr
+        ttdd8puZnTOYHFLQpWLtKpvcf3rdfv84f36c7ec791hV+Pl5efx2evuwPEWQELavqHn4MdHBVRbZ
+        BA8SdETFmEM6W62XD4v79cNcggs5WkihqDhZTO4SruM2JNPFdAYSalIFQnqGKgZX8YbDHj1BOrtb
+        rSVc4dfFbCWBAyt7Ha3Wy0aCLoPRSJD+OINDuoBjsAgpKCJDrDy3NoNn9G2Ec+aFECIDLkNdlEwZ
+        pGIYDgs8cjvM4El4xFxwEFTWnIeDFzUZXwguUbCi/Wawi0IH55TPJxnIW1ZERcEbX/TALyUK44lj
+        rduIJCL+rE1E4fBWZUyprPI9IBFfCf8vfwsZMXQ0bLQhN46GnurYMhWLJ1Gqt47WYXOhrO3UBp95
+        J0tii7sQsZPi9h7/Mk0Vqv1F7GCsvR7Rh8Mkg/5xIy+FDBn+6sMrhz3nj8wjORWLcZW3FfSA922c
+        LsE1ItVaI9Gutvb021XnbDCY+QYaCTvjDZWbHgcpEIcKJBif4xHSafPSvPsFAAD//wMAvNN1YlgD
+        AAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 7cd2ebc78d28e9a4-DFW
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 24 May 2023 14:18:31 GMT
+      Server:
+      - cloudflare
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
+      openai-model:
+      - gpt-3.5-turbo-0301
+      openai-organization:
+      - significant-gravitas
+      openai-processing-ms:
+      - '19007'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '3500'
+      x-ratelimit-limit-tokens:
+      - '90000'
+      x-ratelimit-remaining-requests:
+      - '3499'
+      x-ratelimit-remaining-tokens:
+      - '86473'
+      x-ratelimit-reset-requests:
+      - 17ms
+      x-ratelimit-reset-tokens:
+      - 2.35s
+      x-request-id:
+      - d281dd2fbae62c2925a71cdef320242e
+    status:
+      code: 200
+      message: OK
 version: 1
diff --git a/tests/integration/challenges/memory/test_memory_challenge_a.py b/tests/integration/challenges/memory/test_memory_challenge_a.py
index 1b1bcfe0..063824c6 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_a.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_a.py
@@ -2,6 +2,7 @@ import pytest
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import get_level_to_run, run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -16,6 +17,7 @@ def test_memory_challenge_a(
     user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
+    config: Config,
 ) -> None:
     """
     The agent reads a file containing a task_id. Then, it reads a series of other files.
@@ -29,12 +31,12 @@ def test_memory_challenge_a(
     num_files = get_level_to_run(user_selected_level, LEVEL_CURRENTLY_BEATEN, MAX_LEVEL)
 
     task_id = "2314"
-    create_instructions_files(memory_management_agent, num_files, task_id)
+    create_instructions_files(memory_management_agent, num_files, task_id, config)
 
     run_interaction_loop(monkeypatch, memory_management_agent, num_files + 2)
 
     file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-    content = read_file(file_path)
+    content = read_file(file_path, config)
     assert task_id in content, f"Expected the file to contain {task_id}"
 
 
@@ -42,6 +44,7 @@ def create_instructions_files(
     memory_management_agent: Agent,
     num_files: int,
     task_id: str,
+    config: Config,
     base_filename: str = "instructions_",
 ) -> None:
     """
@@ -56,7 +59,7 @@ def create_instructions_files(
         content = generate_content(i, task_id, base_filename, num_files)
         file_name = f"{base_filename}{i}.txt"
         file_path = str(memory_management_agent.workspace.get_path(file_name))
-        write_to_file(file_path, content)
+        write_to_file(file_path, content, config)
 
 
 def generate_content(
diff --git a/tests/integration/challenges/memory/test_memory_challenge_b.py b/tests/integration/challenges/memory/test_memory_challenge_b.py
index f05c1cfc..7dc00000 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_b.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_b.py
@@ -2,6 +2,7 @@ import pytest
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import (
     generate_noise,
     get_level_to_run,
@@ -21,6 +22,7 @@ def test_memory_challenge_b(
     user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
+    config: Config,
 ) -> None:
     """
     The agent reads a series of files, each containing a task_id and noise. After reading 'n' files,
@@ -34,12 +36,12 @@ def test_memory_challenge_b(
         user_selected_level, LEVEL_CURRENTLY_BEATEN, MAX_LEVEL
     )
     task_ids = [str(i * 1111) for i in range(1, current_level + 1)]
-    create_instructions_files(memory_management_agent, current_level, task_ids)
+    create_instructions_files(memory_management_agent, current_level, task_ids, config)
 
     run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
 
     file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-    content = read_file(file_path)
+    content = read_file(file_path, config)
     for task_id in task_ids:
         assert task_id in content, f"Expected the file to contain {task_id}"
 
@@ -48,6 +50,7 @@ def create_instructions_files(
     memory_management_agent: Agent,
     level: int,
     task_ids: list,
+    config: Config,
     base_filename: str = "instructions_",
 ) -> None:
     """
@@ -63,7 +66,7 @@ def create_instructions_files(
         content = generate_content(i, task_ids, base_filename, level)
         file_name = f"{base_filename}{i}.txt"
         file_path = str(memory_management_agent.workspace.get_path(file_name))
-        write_to_file(file_path, content)
+        write_to_file(file_path, content, config)
 
 
 def generate_content(index: int, task_ids: list, base_filename: str, level: int) -> str:
diff --git a/tests/integration/challenges/memory/test_memory_challenge_c.py b/tests/integration/challenges/memory/test_memory_challenge_c.py
index f6afad97..e113fcdf 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_c.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_c.py
@@ -2,6 +2,7 @@ import pytest
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
+from autogpt.config import Config
 from tests.integration.challenges.utils import (
     generate_noise,
     get_level_to_run,
@@ -21,6 +22,7 @@ def test_memory_challenge_c(
     user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
+    config: Config,
 ) -> None:
     """
     Instead of reading task Ids from files as with the previous challenges, the agent now must remember
@@ -49,7 +51,7 @@ def test_memory_challenge_c(
 
     level_silly_phrases = silly_phrases[:current_level]
     create_instructions_files(
-        memory_management_agent, current_level, level_silly_phrases
+        memory_management_agent, current_level, level_silly_phrases, config=config
     )
 
     run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
@@ -64,6 +66,7 @@ def create_instructions_files(
     memory_management_agent: Agent,
     level: int,
     task_ids: list,
+    config: Config,
     base_filename: str = "instructions_",
 ) -> None:
     """
@@ -79,7 +82,7 @@ def create_instructions_files(
         content = generate_content(i, task_ids, base_filename, level)
         file_name = f"{base_filename}{i}.txt"
         file_path = str(memory_management_agent.workspace.get_path(file_name))
-        write_to_file(file_path, content)
+        write_to_file(file_path, content, config)
 
 
 def generate_content(
diff --git a/tests/integration/test_commands.py b/tests/integration/test_commands.py
index 59f63857..1cbb3929 100644
--- a/tests/integration/test_commands.py
+++ b/tests/integration/test_commands.py
@@ -10,7 +10,7 @@ from tests.utils import requires_api_key
 @pytest.mark.vcr
 @pytest.mark.integration_test
 @requires_api_key("OPENAI_API_KEY")
-def test_make_agent(patched_api_requestor) -> None:
+def test_make_agent(patched_api_requestor, config) -> None:
     """Test that an agent can be created"""
     # Use the mock agent manager to avoid creating a real agent
     with patch("openai.ChatCompletion.create") as mock:
@@ -20,9 +20,13 @@ def test_make_agent(patched_api_requestor) -> None:
         response.usage.prompt_tokens = 1
         response.usage.completion_tokens = 1
         mock.return_value = response
-        start_agent("Test Agent", "chat", "Hello, how are you?", "gpt-3.5-turbo")
-        agents = list_agents()
+        start_agent(
+            "Test Agent", "chat", "Hello, how are you?", config, "gpt-3.5-turbo"
+        )
+        agents = list_agents(config)
         assert "List of agents:\n0: chat" == agents
-        start_agent("Test Agent 2", "write", "Hello, how are you?", "gpt-3.5-turbo")
-        agents = list_agents()
+        start_agent(
+            "Test Agent 2", "write", "Hello, how are you?", config, "gpt-3.5-turbo"
+        )
+        agents = list_agents(config)
         assert "List of agents:\n0: chat\n1: write" == agents
diff --git a/tests/integration/test_execute_code.py b/tests/integration/test_execute_code.py
index 2d4e0293..c75d66fa 100644
--- a/tests/integration/test_execute_code.py
+++ b/tests/integration/test_execute_code.py
@@ -29,22 +29,22 @@ def random_string():
     return "".join(random.choice(string.ascii_lowercase) for _ in range(10))
 
 
-def test_execute_python_file(python_test_file: str, random_string: str):
-    result = sut.execute_python_file(python_test_file)
-    assert result == f"Hello {random_string}!\n"
+def test_execute_python_file(python_test_file: str, random_string: str, config):
+    result: str = sut.execute_python_file(python_test_file, config)
+    assert result.replace("\r", "") == f"Hello {random_string}!\n"
 
 
-def test_execute_python_file_invalid():
+def test_execute_python_file_invalid(config):
     assert all(
-        s in sut.execute_python_file("not_python").lower()
+        s in sut.execute_python_file("not_python", config).lower()
         for s in ["error:", "invalid", ".py"]
     )
     assert all(
-        s in sut.execute_python_file("notexist.py").lower()
+        s in sut.execute_python_file("notexist.py", config).lower()
         for s in ["error:", "does not exist"]
     )
 
 
-def test_execute_shell(config_allow_execute, random_string):
-    result = sut.execute_shell(f"echo 'Hello {random_string}!'")
+def test_execute_shell(config_allow_execute, random_string, config):
+    result = sut.execute_shell(f"echo 'Hello {random_string}!'", config)
     assert f"Hello {random_string}!" in result
diff --git a/tests/integration/test_git_commands.py b/tests/integration/test_git_commands.py
index d942b1b7..375a9cf4 100644
--- a/tests/integration/test_git_commands.py
+++ b/tests/integration/test_git_commands.py
@@ -20,7 +20,7 @@ def test_clone_auto_gpt_repository(workspace, mock_clone_from, config):
 
     expected_output = f"Cloned {url} to {clone_path}"
 
-    clone_result = clone_repository(url=url, clone_path=clone_path)
+    clone_result = clone_repository(url=url, clone_path=clone_path, config=config)
 
     assert clone_result == expected_output
     mock_clone_from.assert_called_once_with(
@@ -29,7 +29,7 @@ def test_clone_auto_gpt_repository(workspace, mock_clone_from, config):
     )
 
 
-def test_clone_repository_error(workspace, mock_clone_from):
+def test_clone_repository_error(workspace, mock_clone_from, config):
     url = "https://github.com/this-repository/does-not-exist.git"
     clone_path = str(workspace.get_path("does-not-exist"))
 
@@ -37,6 +37,6 @@ def test_clone_repository_error(workspace, mock_clone_from):
         "clone", "fatal: repository not found", ""
     )
 
-    result = clone_repository(url=url, clone_path=clone_path)
+    result = clone_repository(url=url, clone_path=clone_path, config=config)
 
     assert "Error: " in result
diff --git a/tests/integration/test_google_search.py b/tests/integration/test_google_search.py
index 50a2ce35..e379f78e 100644
--- a/tests/integration/test_google_search.py
+++ b/tests/integration/test_google_search.py
@@ -38,12 +38,14 @@ def test_safe_google_results_invalid_input():
         ("no results", 1, "[]", []),
     ],
 )
-def test_google_search(query, num_results, expected_output, return_value, mocker):
+def test_google_search(
+    query, num_results, expected_output, return_value, mocker, config
+):
     mock_ddg = mocker.Mock()
     mock_ddg.return_value = return_value
 
     mocker.patch("autogpt.commands.google_search.DDGS.text", mock_ddg)
-    actual_output = google_search(query, num_results=num_results)
+    actual_output = google_search(query, config, num_results=num_results)
     expected_output = safe_google_results(expected_output)
     assert actual_output == expected_output
 
@@ -77,10 +79,10 @@ def mock_googleapiclient(mocker):
     ],
 )
 def test_google_official_search(
-    query, num_results, expected_output, search_results, mock_googleapiclient
+    query, num_results, expected_output, search_results, mock_googleapiclient, config
 ):
     mock_googleapiclient.return_value = search_results
-    actual_output = google_official_search(query, num_results=num_results)
+    actual_output = google_official_search(query, config, num_results=num_results)
     assert actual_output == safe_google_results(expected_output)
 
 
@@ -111,6 +113,7 @@ def test_google_official_search_errors(
     mock_googleapiclient,
     http_code,
     error_msg,
+    config,
 ):
     class resp:
         def __init__(self, _status, _reason):
@@ -127,5 +130,5 @@ def test_google_official_search_errors(
     )
 
     mock_googleapiclient.side_effect = error
-    actual_output = google_official_search(query, num_results=num_results)
+    actual_output = google_official_search(query, config, num_results=num_results)
     assert actual_output == safe_google_results(expected_output)
diff --git a/tests/mocks/mock_commands.py b/tests/mocks/mock_commands.py
index d5bf5df0..42b0ea11 100644
--- a/tests/mocks/mock_commands.py
+++ b/tests/mocks/mock_commands.py
@@ -1,7 +1,9 @@
 from autogpt.commands.command import command
 
 
-@command("function_based", "Function-based test command")
+@command(
+    "function_based", "Function-based test command", "(arg1: int, arg2: str) -> str"
+)
 def function_based(arg1: int, arg2: str) -> str:
     """A function-based test command that returns a string with the two arguments separated by a dash."""
     return f"{arg1} - {arg2}"
diff --git a/tests/test_analyze_code.py b/tests/test_analyze_code.py
index 48bded03..98ab8b72 100644
--- a/tests/test_analyze_code.py
+++ b/tests/test_analyze_code.py
@@ -3,6 +3,7 @@
 import pytest
 
 from autogpt.commands.analyze_code import analyze_code
+from autogpt.config import Config
 
 
 @pytest.fixture
@@ -15,46 +16,59 @@ class TestAnalyzeCode:
         # Positive Test
         mock_call_ai_function.return_value = ["Suggestion 1", "Suggestion 2"]
         code = "def example_function():\n    pass"
-        result = analyze_code(code)
+        config = Config()
+        result = analyze_code(code, config)
         assert result == ["Suggestion 1", "Suggestion 2"]
         mock_call_ai_function.assert_called_once_with(
             "def analyze_code(code: str) -> list[str]:",
             [code],
             "Analyzes the given code and returns a list of suggestions for improvements.",
+            config=config,
         )
 
-    def test_negative_analyze_code(self, mock_call_ai_function):
+    def test_negative_analyze_code(
+        self,
+        mock_call_ai_function,
+        config: Config,
+    ):
         # Negative Test
         mock_call_ai_function.return_value = []
         code = "def example_function():\n    pass"
-        result = analyze_code(code)
+        result = analyze_code(code, config)
         assert result == []
         mock_call_ai_function.assert_called_once_with(
             "def analyze_code(code: str) -> list[str]:",
             [code],
             "Analyzes the given code and returns a list of suggestions for improvements.",
+            config=config,
         )
 
-    def test_error_analyze_code(self, mock_call_ai_function):
+    def test_error_analyze_code(self, mock_call_ai_function, config: Config):
         # Error Test
         mock_call_ai_function.side_effect = Exception("Error occurred")
         code = "def example_function():\n    pass"
         with pytest.raises(Exception):
-            analyze_code(code)
+            result = analyze_code(code, config)
         mock_call_ai_function.assert_called_once_with(
             "def analyze_code(code: str) -> list[str]:",
             [code],
             "Analyzes the given code and returns a list of suggestions for improvements.",
+            config=config,
         )
 
-    def test_edge_analyze_code_empty_code(self, mock_call_ai_function):
+    def test_edge_analyze_code_empty_code(
+        self,
+        mock_call_ai_function,
+        config: Config,
+    ):
         # Edge Test
         mock_call_ai_function.return_value = ["Suggestion 1", "Suggestion 2"]
         code = ""
-        result = analyze_code(code)
+        result = analyze_code(code, config)
         assert result == ["Suggestion 1", "Suggestion 2"]
         mock_call_ai_function.assert_called_once_with(
             "def analyze_code(code: str) -> list[str]:",
             [code],
             "Analyzes the given code and returns a list of suggestions for improvements.",
+            config=config,
         )
diff --git a/tests/test_audio_text_read_audio.py b/tests/test_audio_text_read_audio.py
index d8f2af52..1f324601 100644
--- a/tests/test_audio_text_read_audio.py
+++ b/tests/test_audio_text_read_audio.py
@@ -8,12 +8,10 @@ import pytest
 
 from autogpt.commands.audio_text import read_audio
 
-patch_func1 = "autogpt.commands.audio_text.CFG"
-
 
 class TestReadAudio:
     @patch("requests.post")
-    def test_positive_read_audio(self, mock_post):
+    def test_positive_read_audio(self, mock_post, config):
         # Positive Test
         audio_data = b"test_audio_data"
         mock_response = MagicMock()
@@ -21,41 +19,39 @@ class TestReadAudio:
             {"text": "Hello, world!"}
         )
         mock_post.return_value = mock_response
-        with patch(patch_func1) as mock_cfg:
-            mock_cfg.huggingface_api_token = "testing-token"
-            result = read_audio(audio_data)
-            assert result == "The audio says: Hello, world!"
-            mock_post.assert_called_once_with(
-                f"https://api-inference.huggingface.co/models/{mock_cfg.huggingface_audio_to_text_model}",
-                headers={"Authorization": f"Bearer {mock_cfg.huggingface_api_token}"},
-                data=audio_data,
-            )
+
+        config.huggingface_api_token = "testing-token"
+        result = read_audio(audio_data, config)
+        assert result == "The audio says: Hello, world!"
+        mock_post.assert_called_once_with(
+            f"https://api-inference.huggingface.co/models/{config.huggingface_audio_to_text_model}",
+            headers={"Authorization": f"Bearer {config.huggingface_api_token}"},
+            data=audio_data,
+        )
 
     @patch("requests.post")
-    def test_negative_read_audio(self, mock_post):
+    def test_negative_read_audio(self, mock_post, config):
         # Negative Test
         audio_data = b"test_audio_data"
         mock_response = MagicMock()
         mock_response.content.decode.return_value = json.dumps({"text": ""})
         mock_post.return_value = mock_response
-        with patch(patch_func1) as mock_cfg:
-            mock_cfg.huggingface_api_token = "testing-token"
-            result = read_audio(audio_data)
-            assert result == "The audio says: "
-            mock_post.assert_called_once_with(
-                f"https://api-inference.huggingface.co/models/{mock_cfg.huggingface_audio_to_text_model}",
-                headers={"Authorization": f"Bearer {mock_cfg.huggingface_api_token}"},
-                data=audio_data,
-            )
+        config.huggingface_api_token = "testing-token"
+        result = read_audio(audio_data, config)
+        assert result == "The audio says: "
+        mock_post.assert_called_once_with(
+            f"https://api-inference.huggingface.co/models/{config.huggingface_audio_to_text_model}",
+            headers={"Authorization": f"Bearer {config.huggingface_api_token}"},
+            data=audio_data,
+        )
 
-    def test_error_read_audio(self):
+    def test_error_read_audio(self, config):
         # Error Test
-        with patch(patch_func1) as mock_cfg:
-            mock_cfg.huggingface_api_token = None
-            with pytest.raises(ValueError):
-                read_audio(b"test_audio_data")
+        config.huggingface_api_token = None
+        with pytest.raises(ValueError):
+            read_audio(b"test_audio_data", config)
 
-    def test_edge_read_audio_empty_audio(self):
+    def test_edge_read_audio_empty_audio(self, config):
         # Edge Test
         with pytest.raises(ValueError):
-            read_audio(b"")
+            read_audio(b"", config)
diff --git a/tests/test_audio_text_read_audio_from_file.py b/tests/test_audio_text_read_audio_from_file.py
index b8cb352c..c8d66a06 100644
--- a/tests/test_audio_text_read_audio_from_file.py
+++ b/tests/test_audio_text_read_audio_from_file.py
@@ -7,6 +7,7 @@ from unittest.mock import mock_open, patch
 import pytest
 
 from autogpt.commands.audio_text import read_audio_from_file
+from autogpt.config import Config
 
 
 @pytest.fixture
@@ -22,7 +23,7 @@ class TestReadAudioFromFile:
         m = mock_open(read_data=mock_file_data)
 
         with patch("builtins.open", m):
-            result = read_audio_from_file("test_audio.wav")
+            result = read_audio_from_file("test_audio.wav", Config())
             assert result == "This is a sample text."
             m.assert_called_once_with("test_audio.wav", "rb")
 
@@ -33,14 +34,14 @@ class TestReadAudioFromFile:
         m = mock_open(read_data=mock_file_data)
 
         with patch("builtins.open", m):
-            result = read_audio_from_file("test_audio.wav")
+            result = read_audio_from_file("test_audio.wav", Config())
             assert result != "Incorrect text."
             m.assert_called_once_with("test_audio.wav", "rb")
 
     def test_error_read_audio_from_file(self):
         # Error test
         with pytest.raises(FileNotFoundError):
-            read_audio_from_file("non_existent_file.wav")
+            read_audio_from_file("non_existent_file.wav", Config())
 
     def test_edge_empty_audio_file(self, mock_read_audio):
         # Edge test
@@ -49,6 +50,6 @@ class TestReadAudioFromFile:
         m = mock_open(read_data=mock_file_data)
 
         with patch("builtins.open", m):
-            result = read_audio_from_file("empty_audio.wav")
+            result = read_audio_from_file("empty_audio.wav", Config())
             assert result == ""
             m.assert_called_once_with("empty_audio.wav", "rb")
diff --git a/tests/test_commands.py b/tests/test_commands.py
index 0961d0af..5779a8a3 100644
--- a/tests/test_commands.py
+++ b/tests/test_commands.py
@@ -7,6 +7,8 @@ import pytest
 
 from autogpt.commands.command import Command, CommandRegistry
 
+SIGNATURE = "(arg1: int, arg2: str) -> str"
+
 
 class TestCommand:
     """Test cases for the Command class."""
@@ -23,6 +25,7 @@ class TestCommand:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         assert cmd.name == "example"
@@ -47,19 +50,11 @@ class TestCommand:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
         with pytest.raises(TypeError):
             cmd(arg1="invalid", does_not_exist="test")
 
-    def test_command_default_signature(self):
-        """Test that the default signature is generated correctly."""
-        cmd = Command(
-            name="example",
-            description="Example command",
-            method=self.example_command_method,
-        )
-        assert cmd.signature == "(arg1: int, arg2: str) -> str"
-
     def test_command_custom_signature(self):
         custom_signature = "custom_arg1: int, custom_arg2: str"
         cmd = Command(
@@ -84,6 +79,7 @@ class TestCommandRegistry:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         registry.register(cmd)
@@ -98,6 +94,7 @@ class TestCommandRegistry:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         registry.register(cmd)
@@ -112,6 +109,7 @@ class TestCommandRegistry:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         registry.register(cmd)
@@ -133,6 +131,7 @@ class TestCommandRegistry:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         registry.register(cmd)
@@ -154,6 +153,7 @@ class TestCommandRegistry:
             name="example",
             description="Example command",
             method=self.example_command_method,
+            signature=SIGNATURE,
         )
 
         registry.register(cmd)
diff --git a/tests/test_config.py b/tests/test_config.py
index 98134dc8..1e156f98 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -135,6 +135,7 @@ def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config):
     mock_list_models.return_value = {"data": [{"id": "gpt-3.5-turbo"}]}
 
     create_config(
+        config=config,
         continuous=False,
         continuous_limit=False,
         ai_settings_file="",
diff --git a/tests/test_image_gen.py b/tests/test_image_gen.py
index a18855e7..59962af0 100644
--- a/tests/test_image_gen.py
+++ b/tests/test_image_gen.py
@@ -66,6 +66,7 @@ def test_sd_webui_negative_prompt(config, workspace, image_size):
     gen_image = functools.partial(
         generate_image_with_sd_webui,
         prompt="astronaut riding a horse",
+        config=config,
         size=image_size,
         extra={"seed": 123},
     )
@@ -101,7 +102,7 @@ def generate_and_validate(
     config.huggingface_image_model = hugging_face_image_model
     prompt = "astronaut riding a horse"
 
-    image_path = lst(generate_image(prompt, image_size, **kwargs))
+    image_path = lst(generate_image(prompt, config, image_size, **kwargs))
     assert image_path.exists()
     with Image.open(image_path) as img:
         assert img.size == (image_size, image_size)
@@ -146,7 +147,7 @@ def test_huggingface_fail_request_with_delay(
 
         with patch("time.sleep") as mock_sleep:
             # Verify request fails.
-            result = generate_image(prompt, image_size)
+            result = generate_image(prompt, config, image_size)
             assert result == "Error creating image."
 
             # Verify retry was called with delay if delay is in return_text
@@ -156,8 +157,7 @@ def test_huggingface_fail_request_with_delay(
                 mock_sleep.assert_not_called()
 
 
-def test_huggingface_fail_request_with_delay(mocker):
-    config = Config()
+def test_huggingface_fail_request_with_delay(mocker, config):
     config.huggingface_api_token = "1"
 
     # Mock requests.post
@@ -172,7 +172,7 @@ def test_huggingface_fail_request_with_delay(mocker):
     config.image_provider = "huggingface"
     config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
 
-    result = generate_image("astronaut riding a horse", 512)
+    result = generate_image("astronaut riding a horse", config, 512)
 
     assert result == "Error creating image."
 
@@ -180,8 +180,7 @@ def test_huggingface_fail_request_with_delay(mocker):
     mock_sleep.assert_called_with(0)
 
 
-def test_huggingface_fail_request_no_delay(mocker):
-    config = Config()
+def test_huggingface_fail_request_no_delay(mocker, config):
     config.huggingface_api_token = "1"
 
     # Mock requests.post
@@ -198,7 +197,7 @@ def test_huggingface_fail_request_no_delay(mocker):
     config.image_provider = "huggingface"
     config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
 
-    result = generate_image("astronaut riding a horse", 512)
+    result = generate_image("astronaut riding a horse", config, 512)
 
     assert result == "Error creating image."
 
@@ -206,8 +205,7 @@ def test_huggingface_fail_request_no_delay(mocker):
     mock_sleep.assert_not_called()
 
 
-def test_huggingface_fail_request_bad_json(mocker):
-    config = Config()
+def test_huggingface_fail_request_bad_json(mocker, config):
     config.huggingface_api_token = "1"
 
     # Mock requests.post
@@ -222,7 +220,7 @@ def test_huggingface_fail_request_bad_json(mocker):
     config.image_provider = "huggingface"
     config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
 
-    result = generate_image("astronaut riding a horse", 512)
+    result = generate_image("astronaut riding a horse", config, 512)
 
     assert result == "Error creating image."
 
@@ -230,8 +228,7 @@ def test_huggingface_fail_request_bad_json(mocker):
     mock_sleep.assert_not_called()
 
 
-def test_huggingface_fail_request_bad_image(mocker):
-    config = Config()
+def test_huggingface_fail_request_bad_image(mocker, config):
     config.huggingface_api_token = "1"
 
     # Mock requests.post
@@ -241,13 +238,12 @@ def test_huggingface_fail_request_bad_image(mocker):
     config.image_provider = "huggingface"
     config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
 
-    result = generate_image("astronaut riding a horse", 512)
+    result = generate_image("astronaut riding a horse", config, 512)
 
     assert result == "Error creating image."
 
 
-def test_huggingface_fail_missing_api_token(mocker):
-    config = Config()
+def test_huggingface_fail_missing_api_token(mocker, config):
     config.image_provider = "huggingface"
     config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
 
@@ -256,4 +252,4 @@ def test_huggingface_fail_missing_api_token(mocker):
 
     # Verify request raises an error.
     with pytest.raises(ValueError):
-        generate_image("astronaut riding a horse", 512)
+        generate_image("astronaut riding a horse", config, 512)
diff --git a/tests/unit/test_browse_scrape_links.py b/tests/unit/test_browse_scrape_links.py
index 3b7442eb..15f495db 100644
--- a/tests/unit/test_browse_scrape_links.py
+++ b/tests/unit/test_browse_scrape_links.py
@@ -43,14 +43,14 @@ class TestScrapeLinks:
     provided with a valid url that returns a webpage with hyperlinks.
     """
 
-    def test_valid_url_with_hyperlinks(self):
+    def test_valid_url_with_hyperlinks(self, config):
         url = "https://www.google.com"
-        result = scrape_links(url)
+        result = scrape_links(url, config=config)
         assert len(result) > 0
         assert isinstance(result, list)
         assert isinstance(result[0], str)
 
-    def test_valid_url(self, mocker):
+    def test_valid_url(self, mocker, config):
         """Test that the function returns correctly formatted hyperlinks when given a valid url."""
         # Mock the requests.get() function to return a response with sample HTML containing hyperlinks
         mock_response = mocker.Mock()
@@ -61,12 +61,12 @@ class TestScrapeLinks:
         mocker.patch("requests.Session.get", return_value=mock_response)
 
         # Call the function with a valid URL
-        result = scrape_links("https://www.example.com")
+        result = scrape_links("https://www.example.com", config)
 
         # Assert that the function returns correctly formatted hyperlinks
         assert result == ["Google (https://www.google.com)"]
 
-    def test_invalid_url(self, mocker):
+    def test_invalid_url(self, mocker, config):
         """Test that the function returns "error" when given an invalid url."""
         # Mock the requests.get() function to return an HTTP error response
         mock_response = mocker.Mock()
@@ -74,12 +74,12 @@ class TestScrapeLinks:
         mocker.patch("requests.Session.get", return_value=mock_response)
 
         # Call the function with an invalid URL
-        result = scrape_links("https://www.invalidurl.com")
+        result = scrape_links("https://www.invalidurl.com", config)
 
         # Assert that the function returns "error"
         assert "Error:" in result
 
-    def test_no_hyperlinks(self, mocker):
+    def test_no_hyperlinks(self, mocker, config):
         """Test that the function returns an empty list when the html contains no hyperlinks."""
         # Mock the requests.get() function to return a response with sample HTML containing no hyperlinks
         mock_response = mocker.Mock()
@@ -88,12 +88,12 @@ class TestScrapeLinks:
         mocker.patch("requests.Session.get", return_value=mock_response)
 
         # Call the function with a URL containing no hyperlinks
-        result = scrape_links("https://www.example.com")
+        result = scrape_links("https://www.example.com", config)
 
         # Assert that the function returns an empty list
         assert result == []
 
-    def test_scrape_links_with_few_hyperlinks(self, mocker):
+    def test_scrape_links_with_few_hyperlinks(self, mocker, config):
         """Test that scrape_links() correctly extracts and formats hyperlinks from a sample HTML containing a few hyperlinks."""
         mock_response = mocker.Mock()
         mock_response.status_code = 200
@@ -109,7 +109,7 @@ class TestScrapeLinks:
         mocker.patch("requests.Session.get", return_value=mock_response)
 
         # Call the function being tested
-        result = scrape_links("https://www.example.com")
+        result = scrape_links("https://www.example.com", config)
 
         # Assert that the function returns a list of formatted hyperlinks
         assert isinstance(result, list)
diff --git a/tests/unit/test_browse_scrape_text.py b/tests/unit/test_browse_scrape_text.py
index cda45e11..3d916bc7 100644
--- a/tests/unit/test_browse_scrape_text.py
+++ b/tests/unit/test_browse_scrape_text.py
@@ -42,7 +42,7 @@ Additional aspects:
 
 
 class TestScrapeText:
-    def test_scrape_text_with_valid_url(self, mocker):
+    def test_scrape_text_with_valid_url(self, mocker, config):
         """Tests that scrape_text() returns the expected text when given a valid URL."""
         # Mock the requests.get() method to return a response with expected text
         expected_text = "This is some sample text"
@@ -57,14 +57,14 @@ class TestScrapeText:
         # Call the function with a valid URL and assert that it returns the
         #  expected text
         url = "http://www.example.com"
-        assert scrape_text(url) == expected_text
+        assert scrape_text(url, config) == expected_text
 
-    def test_invalid_url(self):
+    def test_invalid_url(self, config):
         """Tests that an error is raised when an invalid url is provided."""
         url = "invalidurl.com"
-        pytest.raises(ValueError, scrape_text, url)
+        pytest.raises(ValueError, scrape_text, url, config)
 
-    def test_unreachable_url(self, mocker):
+    def test_unreachable_url(self, mocker, config):
         """Test that scrape_text returns an error message when an invalid or unreachable url is provided."""
         # Mock the requests.get() method to raise an exception
         mocker.patch(
@@ -74,10 +74,10 @@ class TestScrapeText:
         # Call the function with an invalid URL and assert that it returns an error
         #  message
         url = "http://thiswebsitedoesnotexist.net/"
-        error_message = scrape_text(url)
+        error_message = scrape_text(url, config)
         assert "Error:" in error_message
 
-    def test_no_text(self, mocker):
+    def test_no_text(self, mocker, config):
         """Test that scrape_text returns an empty string when the html page contains no text to be scraped."""
         # Mock the requests.get() method to return a response with no text
         mock_response = mocker.Mock()
@@ -87,20 +87,20 @@ class TestScrapeText:
 
         # Call the function with a valid URL and assert that it returns an empty string
         url = "http://www.example.com"
-        assert scrape_text(url) == ""
+        assert scrape_text(url, config) == ""
 
-    def test_http_error(self, mocker):
+    def test_http_error(self, mocker, config):
         """Test that scrape_text returns an error message when the response status code is an http error (>=400)."""
         # Mock the requests.get() method to return a response with a 404 status code
         mocker.patch("requests.Session.get", return_value=mocker.Mock(status_code=404))
 
         # Call the function with a URL
-        result = scrape_text("https://www.example.com")
+        result = scrape_text("https://www.example.com", config)
 
         # Check that the function returns an error message
         assert result == "Error: HTTP 404 error"
 
-    def test_scrape_text_with_html_tags(self, mocker):
+    def test_scrape_text_with_html_tags(self, mocker, config):
         """Test that scrape_text() properly handles HTML tags."""
         # Create a mock response object with HTML containing tags
         html = "<html><body><p>This is <b>bold</b> text.</p></body></html>"
@@ -110,7 +110,7 @@ class TestScrapeText:
         mocker.patch("requests.Session.get", return_value=mock_response)
 
         # Call the function with a URL
-        result = scrape_text("https://www.example.com")
+        result = scrape_text("https://www.example.com", config)
 
         # Check that the function properly handles HTML tags
         assert result == "This is bold text."
diff --git a/tests/unit/test_file_operations.py b/tests/unit/test_file_operations.py
index 7f885348..35c77a15 100644
--- a/tests/unit/test_file_operations.py
+++ b/tests/unit/test_file_operations.py
@@ -55,11 +55,11 @@ def test_file(test_file_path: Path):
 
 
 @pytest.fixture()
-def test_file_with_content_path(test_file: TextIOWrapper, file_content):
+def test_file_with_content_path(test_file: TextIOWrapper, file_content, config):
     test_file.write(file_content)
     test_file.close()
     file_ops.log_operation(
-        "write", test_file.name, file_ops.text_checksum(file_content)
+        "write", test_file.name, config, file_ops.text_checksum(file_content)
     )
     return Path(test_file.name)
 
@@ -117,7 +117,7 @@ def test_file_operations_state(test_file: TextIOWrapper):
     assert file_ops.file_operations_state(test_file.name) == expected_state
 
 
-def test_is_duplicate_operation(config, mocker: MockerFixture):
+def test_is_duplicate_operation(config: Config, mocker: MockerFixture):
     # Prepare a fake state dictionary for the function to use
     state = {
         "path/to/file1.txt": "checksum1",
@@ -127,30 +127,42 @@ def test_is_duplicate_operation(config, mocker: MockerFixture):
 
     # Test cases with write operations
     assert (
-        file_ops.is_duplicate_operation("write", "path/to/file1.txt", "checksum1")
+        file_ops.is_duplicate_operation(
+            "write", "path/to/file1.txt", config, "checksum1"
+        )
         is True
     )
     assert (
-        file_ops.is_duplicate_operation("write", "path/to/file1.txt", "checksum2")
+        file_ops.is_duplicate_operation(
+            "write", "path/to/file1.txt", config, "checksum2"
+        )
         is False
     )
     assert (
-        file_ops.is_duplicate_operation("write", "path/to/file3.txt", "checksum3")
+        file_ops.is_duplicate_operation(
+            "write", "path/to/file3.txt", config, "checksum3"
+        )
         is False
     )
     # Test cases with append operations
     assert (
-        file_ops.is_duplicate_operation("append", "path/to/file1.txt", "checksum1")
+        file_ops.is_duplicate_operation(
+            "append", "path/to/file1.txt", config, "checksum1"
+        )
         is False
     )
     # Test cases with delete operations
-    assert file_ops.is_duplicate_operation("delete", "path/to/file1.txt") is False
-    assert file_ops.is_duplicate_operation("delete", "path/to/file3.txt") is True
+    assert (
+        file_ops.is_duplicate_operation("delete", "path/to/file1.txt", config) is False
+    )
+    assert (
+        file_ops.is_duplicate_operation("delete", "path/to/file3.txt", config) is True
+    )
 
 
 # Test logging a file operation
 def test_log_operation(config: Config):
-    file_ops.log_operation("log_test", "path/to/test")
+    file_ops.log_operation("log_test", "path/to/test", config)
     with open(config.file_logger_path, "r", encoding="utf-8") as f:
         content = f.read()
     assert f"log_test: path/to/test\n" in content
@@ -164,7 +176,7 @@ def test_text_checksum(file_content: str):
 
 
 def test_log_operation_with_checksum(config: Config):
-    file_ops.log_operation("log_test", "path/to/test", checksum="ABCDEF")
+    file_ops.log_operation("log_test", "path/to/test", config, checksum="ABCDEF")
     with open(config.file_logger_path, "r", encoding="utf-8") as f:
         content = f.read()
     assert f"log_test: path/to/test #ABCDEF\n" in content
@@ -211,50 +223,56 @@ def test_read_file(
     mock_MemoryItem_from_text,
     test_file_with_content_path: Path,
     file_content,
+    config: Config,
 ):
-    content = file_ops.read_file(test_file_with_content_path)
-    assert content == file_content
+    content = file_ops.read_file(test_file_with_content_path, config)
+    assert content.replace("\r", "") == file_content
 
 
-def test_write_to_file(test_file_path: Path):
+def test_write_to_file(test_file_path: Path, config):
     new_content = "This is new content.\n"
-    file_ops.write_to_file(str(test_file_path), new_content)
+    file_ops.write_to_file(str(test_file_path), new_content, config)
     with open(test_file_path, "r", encoding="utf-8") as f:
         content = f.read()
     assert content == new_content
 
 
-def test_write_file_logs_checksum(config: Config, test_file_path: Path):
+def test_write_file_logs_checksum(test_file_path: Path, config):
     new_content = "This is new content.\n"
     new_checksum = file_ops.text_checksum(new_content)
-    file_ops.write_to_file(str(test_file_path), new_content)
+    file_ops.write_to_file(str(test_file_path), new_content, config)
     with open(config.file_logger_path, "r", encoding="utf-8") as f:
         log_entry = f.read()
     assert log_entry == f"write: {test_file_path} #{new_checksum}\n"
 
 
-def test_write_file_fails_if_content_exists(test_file_path: Path):
+def test_write_file_fails_if_content_exists(test_file_path: Path, config):
     new_content = "This is new content.\n"
     file_ops.log_operation(
         "write",
         str(test_file_path),
+        config,
         checksum=file_ops.text_checksum(new_content),
     )
-    result = file_ops.write_to_file(str(test_file_path), new_content)
+    result = file_ops.write_to_file(str(test_file_path), new_content, config)
     assert result == "Error: File has already been updated."
 
 
-def test_write_file_succeeds_if_content_different(test_file_with_content_path: Path):
+def test_write_file_succeeds_if_content_different(
+    test_file_with_content_path: Path, config
+):
     new_content = "This is different content.\n"
-    result = file_ops.write_to_file(str(test_file_with_content_path), new_content)
+    result = file_ops.write_to_file(
+        str(test_file_with_content_path), new_content, config
+    )
     assert result == "File written to successfully."
 
 
-def test_append_to_file(test_nested_file: Path):
+def test_append_to_file(test_nested_file: Path, config):
     append_text = "This is appended text.\n"
-    file_ops.write_to_file(test_nested_file, append_text)
+    file_ops.write_to_file(test_nested_file, append_text, config)
 
-    file_ops.append_to_file(test_nested_file, append_text)
+    file_ops.append_to_file(test_nested_file, append_text, config)
 
     with open(test_nested_file, "r") as f:
         content_after = f.read()
@@ -262,12 +280,10 @@ def test_append_to_file(test_nested_file: Path):
     assert content_after == append_text + append_text
 
 
-def test_append_to_file_uses_checksum_from_appended_file(
-    config: Config, test_file_path: Path
-):
+def test_append_to_file_uses_checksum_from_appended_file(test_file_path: Path, config):
     append_text = "This is appended text.\n"
-    file_ops.append_to_file(test_file_path, append_text)
-    file_ops.append_to_file(test_file_path, append_text)
+    file_ops.append_to_file(test_file_path, append_text, config)
+    file_ops.append_to_file(test_file_path, append_text, config)
     with open(config.file_logger_path, "r", encoding="utf-8") as f:
         log_contents = f.read()
 
@@ -282,8 +298,8 @@ def test_append_to_file_uses_checksum_from_appended_file(
     )
 
 
-def test_delete_file(test_file_with_content_path: Path):
-    result = file_ops.delete_file(str(test_file_with_content_path))
+def test_delete_file(test_file_with_content_path: Path, config):
+    result = file_ops.delete_file(str(test_file_with_content_path), config)
     assert result == "File deleted successfully."
     assert os.path.exists(test_file_with_content_path) is False
 
@@ -291,16 +307,16 @@ def test_delete_file(test_file_with_content_path: Path):
 def test_delete_missing_file(config):
     filename = "path/to/file/which/does/not/exist"
     # confuse the log
-    file_ops.log_operation("write", filename, checksum="fake")
+    file_ops.log_operation("write", filename, config, checksum="fake")
     try:
         os.remove(filename)
     except FileNotFoundError as err:
-        assert str(err) in file_ops.delete_file(filename)
+        assert str(err) in file_ops.delete_file(filename, config)
         return
     assert False, f"Failed to test delete_file; {filename} not expected to exist"
 
 
-def test_list_files(workspace: Workspace, test_directory: Path):
+def test_list_files(workspace: Workspace, test_directory: Path, config):
     # Case 1: Create files A and B, search for A, and ensure we don't return A and B
     file_a = workspace.get_path("file_a.txt")
     file_b = workspace.get_path("file_b.txt")
@@ -318,7 +334,7 @@ def test_list_files(workspace: Workspace, test_directory: Path):
     with open(os.path.join(test_directory, file_a.name), "w") as f:
         f.write("This is file A in the subdirectory.")
 
-    files = file_ops.list_files(str(workspace.root))
+    files = file_ops.list_files(str(workspace.root), config)
     assert file_a.name in files
     assert file_b.name in files
     assert os.path.join(Path(test_directory).name, file_a.name) in files
@@ -331,17 +347,17 @@ def test_list_files(workspace: Workspace, test_directory: Path):
 
     # Case 2: Search for a file that does not exist and make sure we don't throw
     non_existent_file = "non_existent_file.txt"
-    files = file_ops.list_files("")
+    files = file_ops.list_files("", config)
     assert non_existent_file not in files
 
 
-def test_download_file(config, workspace: Workspace):
+def test_download_file(workspace: Workspace, config):
     url = "https://github.com/Significant-Gravitas/Auto-GPT/archive/refs/tags/v0.2.2.tar.gz"
     local_name = workspace.get_path("auto-gpt.tar.gz")
     size = 365023
     readable_size = readable_file_size(size)
     assert (
-        file_ops.download_file(url, local_name)
+        file_ops.download_file(url, local_name, config)
         == f'Successfully downloaded and locally stored file: "{local_name}"! (Size: {readable_size})'
     )
     assert os.path.isfile(local_name) is True
@@ -349,10 +365,10 @@ def test_download_file(config, workspace: Workspace):
 
     url = "https://github.com/Significant-Gravitas/Auto-GPT/archive/refs/tags/v0.0.0.tar.gz"
     assert "Got an HTTP Error whilst trying to download file" in file_ops.download_file(
-        url, local_name
+        url, local_name, config
     )
 
     url = "https://thiswebsiteiswrong.hmm/v0.0.0.tar.gz"
     assert "Failed to establish a new connection:" in file_ops.download_file(
-        url, local_name
+        url, local_name, config
     )
diff --git a/tests/unit/test_web_selenium.py b/tests/unit/test_web_selenium.py
index 2746f684..0415007d 100644
--- a/tests/unit/test_web_selenium.py
+++ b/tests/unit/test_web_selenium.py
@@ -1,11 +1,11 @@
 from autogpt.commands.web_selenium import browse_website
 
 
-def test_browse_website():
+def test_browse_website(config):
     url = "https://barrel-roll.com"
     question = "How to execute a barrel roll"
 
-    response = browse_website(url, question)
+    response = browse_website(url, question, config)
     assert "Error" in response
     # Sanity check that the response is not too long
     assert len(response) < 200

From 6c45fcd067fecf843d8cb9c43eda3f328d12ce3b Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Fri, 26 May 2023 11:02:40 -0700
Subject: [PATCH 068/112] remove cassettes auto commit (#4432)

---
 .github/workflows/ci.yml | 46 ----------------------------------------
 1 file changed, 46 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 2f36053e..4f552a9c 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -93,49 +93,3 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v3
-
-      - name: Stage Files and Check for New Cassettes
-        id: stage_files_and_check
-        run: |
-          find tests -type f -name '*.yaml' -print0 | xargs -0 git add
-          # Check for new cassettes added in PR after the commit
-          NEW_CASSETTES_ADDED_IN_PR=$(git diff --name-only $(git merge-base ${{ github.event.pull_request.base.sha }} HEAD)..HEAD -- 'tests/**/cassettes/**/*.yaml' | wc -l)
-          if [[ "$NEW_CASSETTES_ADDED_IN_PR" -gt 0 ]]
-          then 
-            echo "NEW_CASSETTES_ADDED_IN_PR=true" >> $GITHUB_ENV
-          else 
-            echo "NEW_CASSETTES_ADDED_IN_PR=false" >> $GITHUB_ENV
-          fi      
-
-      - name: Beat new challenges
-        if: ${{ env.NEW_CASSETTES_ADDED_IN_PR}}
-        run: |
-          echo "This step will run the challenges soon."
-
-      - name: Commit, Config, and Push
-        id: commit_and_push
-        run: |
-          git diff --cached --quiet tests && echo "No changes to commit" && exit 0
-          find tests -type f -name '*.yaml' -print0 | xargs -0 git add
-          echo '${{ secrets.PAT_REVIEW }}' | gh auth login --with-token
-          gh repo set-default ${{ github.repository }}
-          gh pr checkout ${{ github.event.pull_request.number }}
-          git config --global user.name "Auto-GPT-Bot"
-          git config --global user.email "github-bot@agpt.co"
-          git commit -m "Add new cassettes"
-          git push origin ${{ github.head_ref }}
-          TIMESTAMP_COMMIT=$(date +%Y%m%d%H%M%S) # generate a timestamp
-          echo "TIMESTAMP_COMMIT=$TIMESTAMP_COMMIT" >> $GITHUB_ENV
-
-      - name: Inform of auto commit.
-        if: ${{ env.TIMESTAMP_COMMIT != null }}
-        uses: thollander/actions-comment-pull-request@v2
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          message: |
-            We committed some changes to this branch, please run 
-            ```
-            git fetch
-            git rebase origin/${{ github.head_ref }}
-            ```
-            before pushing more changes to the remote.

From e7c0d3330c0204f02b7be789da215a2b62a588bb Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Fri, 26 May 2023 12:33:49 -0700
Subject: [PATCH 069/112] Create cassette submodule (#4420)

* gfeat: specify directory of cassettes and automatically load them depending on module

fix: formatting for linter

test: commit newly generated cassettes to their respective folder

tests: update latest fixtures with master

fix: update .gitattributes with updated path to cassettes

fix: use cassettes from master instead of generating them myself

fix: update path in .gitattributes

fix: make sure to match default functionality by using test name for cassette directory

fix: actually add git submodule

ci: checkout git submodules in CI

ci: update git submodules separately to ensure it gets called

feat: add a hooks directory so we can update git submodules on post-checkout

feat: make sure we push the tests/cassettes submodule on merge into master

ci: remove unused code now that we are using git submodules to keep cassettes in sync

fix: simplify how we load the submodule and fix updating cassettes on merge to master

chore: remove echo of checkout hook, it's unneeded

ci: remove unneccesary step

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

* cassettes submodule

---------

Co-authored-by: Stefan Ayala <stefanayala3266@gmail.com>
---
 .gitattributes                                |    2 +-
 .github/workflows/ci.yml                      |  114 +-
 .github/workflows/docker-ci.yml               |   73 +-
 .gitmodules                                   |    4 +
 autogpt/llm/utils/__init__.py                 |    2 +-
 hooks/post-checkout                           |    2 +
 hooks/post-rewrite                            |    4 +
 tests/Auto-GPT-test-cassettes                 |    1 +
 tests/conftest.py                             |    6 +
 ...t_generate_aiconfig_automatic_default.yaml |  190 -
 ..._generate_aiconfig_automatic_fallback.yaml |  178 -
 ...t_generate_aiconfig_automatic_typical.yaml |  197 -
 .../test_browse_website.yaml                  | 3367 -----------------
 .../test_write_file/test_write_file.yaml      | 2220 -----------
 .../test_memory_challenge_a.yaml              | 3349 ----------------
 .../test_memory_challenge_b.yaml              |  779 ----
 .../test_memory_challenge_c.yaml              | 1409 -------
 .../test_json_memory_get_relevant.yaml        | 2672 -------------
 18 files changed, 168 insertions(+), 14401 deletions(-)
 create mode 100644 .gitmodules
 create mode 100644 hooks/post-checkout
 create mode 100644 hooks/post-rewrite
 create mode 160000 tests/Auto-GPT-test-cassettes
 delete mode 100644 tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_default.yaml
 delete mode 100644 tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_fallback.yaml
 delete mode 100644 tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_typical.yaml
 delete mode 100644 tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
 delete mode 100644 tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
 delete mode 100644 tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
 delete mode 100644 tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml
 delete mode 100644 tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
 delete mode 100644 tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml

diff --git a/.gitattributes b/.gitattributes
index b28dfc4d..88a33bf7 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,5 +1,5 @@
 # Exclude VCR cassettes from stats
-tests/**/cassettes/**.y*ml linguist-generated
+tests/Auto-GPT-test-cassettes/**/**.y*ml linguist-generated
 
 # Mark documentation as such
 docs/**.md linguist-documentation
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 4f552a9c..e91cb960 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -2,9 +2,11 @@ name: Python CI
 
 on:
   push:
-    branches: [ master ]
+    branches: [ master, ci-test*]
+    paths-ignore:
+      - 'tests/Auto-GPT-test-cassettes'
   pull_request_target:
-    branches: [ master, stable ]
+    branches: [ master, stable , ci-test*]
 
 concurrency:
   group: ${{ format('ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
@@ -71,6 +73,33 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
+          submodules: true
+          token: ${{ secrets.PAT_REVIEW }}
+
+      - name: Use cassettes previously sent
+        if: ${{ github.event_name == 'pull_request_target' }}
+        run: |
+          new_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
+          git config --global user.name "Github Actions"
+          git config --global user.email "github-actions@github.com"
+          cd tests/Auto-GPT-test-cassettes
+
+          if git ls-remote --exit-code --heads origin $new_branch ; then
+            git fetch origin $new_branch:$new_branch
+            git fetch origin ${{ github.event.pull_request.base.ref }}:${{ github.event.pull_request.base.ref }}
+            
+            git checkout $new_branch
+
+            if git merge --no-commit --no-ff ${{ github.event.pull_request.base.ref }}; then
+              echo "No merge conflict detected. We can use the cassettes previously sent."
+            else
+              echo "Merge conflict detected. This means we cannot use the cassettes previously sent, so we will take the cassettes of ${{ github.event.pull_request.base.ref }}."
+              git merge --abort
+              git checkout ${{ github.event.pull_request.base.ref }}
+            fi
+          else
+            echo "Branch $new_branch does not exist. We will use the cassettes of ${{ github.event.pull_request.base.ref }}"
+          fi
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v2
@@ -82,7 +111,7 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r requirements.txt
 
-      - name: Run unittest tests with coverage
+      - name: Run pytest tests with coverage
         run: |
           pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
         env:
@@ -93,3 +122,82 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v3
+
+      - name: Update cassette submodule to push target if push event
+        if: ${{ github.event_name == 'push' }}
+        run: |
+          cd tests/Auto-GPT-test-cassettes
+          current_branch=$(echo ${{ github.ref }} | sed -e "s/refs\/heads\///g")
+          git fetch origin $current_branch
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+          git add .
+
+          # Check if there are any changes
+          if ! git diff-index --quiet HEAD; then
+              git commit -m "Auto-update cassettes after Push event"
+              git pull --rebase origin $current_branch
+
+              git push origin HEAD:refs/heads/$current_branch
+
+              cd ../..
+              git add tests/Auto-GPT-test-cassettes
+              git commit -m "Update submodule reference"
+              git push origin HEAD:refs/heads/$current_branch
+          else
+              echo "No changes to commit"
+              exit 0
+          fi
+
+      - name: Update cassette submodule to submodule branch if PR event
+        if: ${{ github.event_name == 'pull_request_target' }}
+        run: |
+          new_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
+
+          cd tests/Auto-GPT-test-cassettes
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+          git add .
+
+          # Check if there are any changes
+          if ! git diff-index --quiet HEAD; then
+              git commit -m "Auto-update cassettes after merging PR #$pr_number"
+              git push -f origin HEAD:refs/heads/$new_branch
+              
+          else
+              echo "No changes to commit"
+              exit 0
+          fi
+          git fetch origin ${{ github.event.pull_request.base.ref }}:${{ github.event.pull_request.base.ref }} || echo "DIFF_EXISTS=false" >> $GITHUB_ENV
+          differences=$(git diff origin/$new_branch origin/${{ github.event.pull_request.base.ref }})
+    
+          if [ -n "$differences" ]; then
+            echo "DIFF_EXISTS=true" >> $GITHUB_ENV
+          else
+            echo "DIFF_EXISTS=false" >> $GITHUB_ENV
+          fi
+
+      - name: Apply or remove prompt change label and comment
+        if: ${{ github.event_name == 'pull_request_target' }}
+        run: |
+          PR_NUMBER=${{ github.event.pull_request.number }}
+          TOKEN=${{ secrets.PAT_REVIEW }}
+          REPO=${{ github.repository }}
+
+          if [[ "${{ env.DIFF_EXISTS }}" == "true" ]]; then
+            echo "Adding label and comment..."
+            curl -X POST \
+            -H "Authorization: Bearer $TOKEN" \
+            -H "Accept: application/vnd.github.v3+json" \
+            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels \
+            -d '{"labels":["prompt change"]}'
+
+            echo $TOKEN | gh auth login --with-token
+            gh api repos/$REPO/issues/$PR_NUMBER/comments -X POST -F body="You changed AutoGPT's prompt. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+          else
+            echo "Removing label..."
+            curl -X DELETE \
+            -H "Authorization: Bearer $TOKEN" \
+            -H "Accept: application/vnd.github.v3+json" \
+            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels/prompt%20change
+          fi
diff --git a/.github/workflows/docker-ci.yml b/.github/workflows/docker-ci.yml
index 681eb4af..2cc3296b 100644
--- a/.github/workflows/docker-ci.yml
+++ b/.github/workflows/docker-ci.yml
@@ -76,41 +76,44 @@ jobs:
     timeout-minutes: 30
     needs: build
     steps:
-    - name: Checkout repository
-      uses: actions/checkout@v3
+      - name: Check out repository
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          submodules: true
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v2
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
 
-    - id: build
-      name: Build image
-      uses: docker/build-push-action@v3
-      with:
-        build-args: BUILD_TYPE=dev  # include pytest
-        tags: ${{ env.IMAGE_NAME }}
-        load: true                  # save to docker images
-        # cache layers in GitHub Actions cache to speed up builds
-        cache-from: type=gha,scope=docker-dev
-        cache-to: type=gha,scope=docker-dev,mode=max
+      - id: build
+        name: Build image
+        uses: docker/build-push-action@v3
+        with:
+          build-args: BUILD_TYPE=dev  # include pytest
+          tags: ${{ env.IMAGE_NAME }}
+          load: true                  # save to docker images
+          # cache layers in GitHub Actions cache to speed up builds
+          cache-from: type=gha,scope=docker-dev
+          cache-to: type=gha,scope=docker-dev,mode=max
 
-    - id: test
-      name: Run tests
-      env:
-        CI: true
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-        set +e
-        test_output=$(
-          docker run --env CI --env OPENAI_API_KEY --entrypoint python ${{ env.IMAGE_NAME }} -m \
-          pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term 2>&1
-        )
-        test_failure=$?
-
-        echo "$test_output"
-
-        cat << $EOF >> $GITHUB_STEP_SUMMARY
-        # Tests $([ $test_failure = 0 ] && echo '✅' || echo '❌')
-        \`\`\`
-        $test_output
-        \`\`\`
-        $EOF
+      - id: test
+        name: Run tests
+        env:
+          CI: true
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: |
+          set +e
+          test_output=$(
+            docker run --env CI --env OPENAI_API_KEY --entrypoint python ${{ env.IMAGE_NAME }} -m \
+            pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term 2>&1
+          )
+          test_failure=$?
+  
+          echo "$test_output"
+  
+          cat << $EOF >> $GITHUB_STEP_SUMMARY
+          # Tests $([ $test_failure = 0 ] && echo '✅' || echo '❌')
+          \`\`\`
+          $test_output
+          \`\`\`
+          $EOF
diff --git a/.gitmodules b/.gitmodules
new file mode 100644
index 00000000..694ca570
--- /dev/null
+++ b/.gitmodules
@@ -0,0 +1,4 @@
+[submodule "tests/Auto-GPT-test-cassettes"]
+    path = tests/Auto-GPT-test-cassettes
+    url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes
+    branch = master
diff --git a/autogpt/llm/utils/__init__.py b/autogpt/llm/utils/__init__.py
index 47e15896..756c4bd5 100644
--- a/autogpt/llm/utils/__init__.py
+++ b/autogpt/llm/utils/__init__.py
@@ -96,7 +96,7 @@ def retry_openai_api(
                         user_warned = True
 
                 except APIError as e:
-                    if (e.http_status != 502) or (attempt == num_attempts):
+                    if (e.http_status not in [502, 429]) or (attempt == num_attempts):
                         raise
 
                 backoff = backoff_base ** (attempt + 2)
diff --git a/hooks/post-checkout b/hooks/post-checkout
new file mode 100644
index 00000000..98de9285
--- /dev/null
+++ b/hooks/post-checkout
@@ -0,0 +1,2 @@
+#!/bin/sh
+git submodule update --init --remote --recursive
diff --git a/hooks/post-rewrite b/hooks/post-rewrite
new file mode 100644
index 00000000..13304744
--- /dev/null
+++ b/hooks/post-rewrite
@@ -0,0 +1,4 @@
+#!/bin/sh
+case "$1" in
+    rebase) git submodule update --init --recursive ;;
+esac
diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
new file mode 160000
index 00000000..f518f20d
--- /dev/null
+++ b/tests/Auto-GPT-test-cassettes
@@ -0,0 +1 @@
+Subproject commit f518f20d83e57e15242b504415132c04991165a0
diff --git a/tests/conftest.py b/tests/conftest.py
index 3644fd85..98bebc9e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -13,6 +13,12 @@ pytest_plugins = ["tests.integration.agent_factory", "tests.integration.memory.u
 PROXY = os.environ.get("PROXY")
 
 
+@pytest.fixture()
+def vcr_cassette_dir(request):
+    test_name = os.path.splitext(request.node.name)[0]
+    return os.path.join("tests/Auto-GPT-test-cassettes", test_name)
+
+
 @pytest.fixture()
 def workspace_root(tmp_path: Path) -> Path:
     return tmp_path / "home/users/monty/auto_gpt_workspace"
diff --git a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_default.yaml b/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_default.yaml
deleted file mode 100644
index f336cd00..00000000
--- a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_default.yaml
+++ /dev/null
@@ -1,190 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''Write a wikipedia style
-      article about the project: https://github.com/significant-gravitas/Auto-GPT''\nRespond
-      only with the output in the exact format specified in the system prompt, with
-      no explanation or conversation.\n"}], "temperature": 0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1671'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1xSS2/UMBC+8ytGvnBJVt3tgzZHoBQkXgdQKyiqHHuSTOvMpPZkt6uq/x3FWfrg
-        aHvme/rekDeVcZ1V1w+hfHPSffy0Hz6ff6sPls3p9cHtr4tv2y8/6e3FWWMKI/U1Ot1tLJz0Q0Al
-        YVMYF9EqelMtj45XhweHR0fHhenFYzCVaQct9xeHpY6xlnJvf29pCjMm26Kp7s0QpR/0SuUGOZlq
-        dbJfmCfsx/vl6qQwKmrD49XBavVQGNcJOUym+n1vekz/YKMENJWxKVFSyzqJFFbkycBX22MF53RD
-        Z99/XPJ7TC7SMPFVYBnsqMLSy5jAtsgKHhO1jB5UYEYEYtAOIRsnYZAm4w3oyZZJtwHBRiUXMEG9
-        hSHKmjxxCxuJwZcu2JQA7waMSgknuIgJbXRdAZtIStwWYNlDI7G3Op0Xl3wmNqTqkkt4J+xHp6Cd
-        RBnb7nEdZFbW0hoZVAZyk2zkNEYE69wYrdtm6F3MyJjSZIB4JiPhxcRxHkkROmq78na0gXQLuwxB
-        O6tACZBb22atj8trnIVvMIQyaRydjhF9AY2EIJspg6xvJI+BGFOenkryNvr0Isks40PGzUu7SCcb
-        EnOcKk/TrxPskmf/DH/S5sKYx4coA0ZwpNnmzB2xwYjsMC3maEOwtUSrCBvSLjOPCeNERuwkDvOj
-        dkgRGkRfW3eToXp7g8Dopo8YtxBxTSnzqDw3kHlO50pylM/N9YiaXrhiUVtTLuC/2KYKArVUB5x+
-        CgxjHcjNFZqHwjTElLqriDYJm8oklcEUhtjjnan2Hv48vPoLAAD//wMAbCMiNQcEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be206beca7ccfbc-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:47:58 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '9927'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-request-id:
-      - 575539561e8025c9a37920ffb4d1b354
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''Write a wikipedia style
-      article about the project: https://github.com/significant-gravitas/Auto-GPT''\nRespond
-      only with the output in the exact format specified in the system prompt, with
-      no explanation or conversation."}], "temperature": 0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1669'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SSy24bMQxF9/0KQptuZow4TtJktgn62BQBWqAtmqKQJXqGjYaciFRcI8i/FyM7
-        jy4lkPceXvLBUXSdC4O3ME6pfXd16y9/XHxa3tF3n65/0DmefYwnJ18urlFc42T9B4MdOhZBximh
-        kbBrXMjoDaPrlmfnq9Pl8uz8pHGjREyuc/1k7Wpx2lrJa2mPVkdL17iivkfXPbgpyzjZb5NbZHXd
-        8cWqcS/az//L1XHjTMyn56+T49PHxoVBKKC67ueDG1GfZLMkdJ3zqqTm2WZIYUOeB/jsR+zgG93S
-        h+uvN3yFGjJNs18HnsEXE5ZRioLvkQ0iKvWMEUxgrwjEYANCHZyEQTZVb8JIvlXbJQSfjUJChfUO
-        piz3FIl72EpOsQ3JqwL+nTAbKc5yGRV9DkMD20xG3DfgOcJG8uhtfi9u+IP4pN0Nt3ApHEswsEGy
-        lH54bgfZk/V0jwwmE4UZG1lLRvAhlOzDrkofYkZG1XkA4r0ZCS9mj2+ZDGGgfmjvik9kOzhkCDZ4
-        A1JA7n1fWZ+b73EPvsWUWrVcgpWMsYGNpCTbOYPKVyhiIkat1fOSos9R/0uyYryvurXpEOk8huQa
-        p8lL9VuFQ/IcX+nPbCGVWj5lmTBDIKtj7r0zbjAjB9TFPtqU/FqyN4Qt2VCdi2J+lWOd/zXRiGg6
-        /1Cuaw3/G9wVyjgi25MFG3GRomkHCX3mWkfjfCcIZPp0BIf+w271llLSmWN/UFgZ1qgGk6jSOiEo
-        5nsKOBc9gS/cY+M2xKTD74xehV3n1GRyjSOO+Nd1R4+/Ht/8AwAA//8DAP+8R3oSBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3e271a39dbcef9-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 08 May 2023 02:08:13 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '8895'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89605'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 262ms
-      x-request-id:
-      - 008e44284ea375a3f964c394b25fb76e
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_fallback.yaml b/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_fallback.yaml
deleted file mode 100644
index 55e7c832..00000000
--- a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_fallback.yaml
+++ /dev/null
@@ -1,178 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''T&GF\u00a3OIBECC()!*''\nRespond
-      only with the output in the exact format specified in the system prompt, with
-      no explanation or conversation.\n"}], "temperature": 0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1592'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0yOTUsDMRCG7/6KYS5esqUf1tqcFdSLHoqCIjKbne6mzWZCMusHpf9dCmp7e3m/
-        eHboG7ToOlLXp1Atlt3t6unbtbebl5vVc/2wWmiYbbfu+n54QINSb9jp72LkpE+B1UtEgy4zKTdo
-        J5dX0/nF/HKxNNhLwwEttkmr2Whe6ZBrqcaz8QQNDoVaRrvDlKVP+q6y5VjQTq/GBo/f//5sYlBF
-        KZw4k71B14l3XNC+7rDn8veaJTBapFJ8UYp6YJSoHA/8d+c9FMn528AdOIpRFFKWD98wUAQZNA0K
-        n147GRQIPij4BpTKdgSPganwsX4Swloy9Awq0HLkTMpAKWVJ2R90KxQKUGyA4MBX1VS4gUg9j3Bv
-        cO2jL917ZioS0WJRSWjQx4a/0I73b/uzHwAAAP//AwBPrscAswEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be20701ea0a9669-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:48:01 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '1833'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-request-id:
-      - c9bf165259547ec59a88bd16b5f691f2
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''T&GF\u00a3OIBECC()!*''\nRespond
-      only with the output in the exact format specified in the system prompt, with
-      no explanation or conversation."}], "temperature": 0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1590'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0zOS0tDMRCG4b2/YpiNm7ScWnohW0UoIgoKiiJlmoxtbE4mJHNaS+l/l3rffsM8
-        vHsMHi26Falrc+xNLtb0dHN+xU19GE+3eXSXr+/j4+WjjOkJDcrijZ1+f/SdtDmyBklo0BUmZY92
-        MJ4OR4PBpJkYbMVzRIvLrL1hf9TTriyk1wybARrsKi0Z7R5zkTbrXGXNqaI9mzYG/+x/u0EVpfi7
-        DJvpwaBbSXBc0T7vseX6oxaJjBap1lCVkh4bJSmnY//stIUqpewMzMBRSqKQi2yCZ6AE0mnuFLZB
-        V9IpELjIVICShy55LkfQ0yIyKNV1H24jU+U/ATYUg/88wqsUaBlU4CsFdtJ9yn08GHwNKdTVvDBV
-        SWixqmQ0GJLnd7TN4eVw8gEAAP//AwDo3pkcpQEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3e27aaaa53965d-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 08 May 2023 02:08:29 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '2445'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89626'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 248ms
-      x-request-id:
-      - 8868ee7b699bc67e6988580bb70aa31f
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_typical.yaml b/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_typical.yaml
deleted file mode 100644
index 2182ec3f..00000000
--- a/tests/integration/cassettes/test_setup/test_generate_aiconfig_automatic_typical.yaml
+++ /dev/null
@@ -1,197 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''Help me create a rock opera
-      about cybernetic giraffes''\nRespond only with the output in the exact format
-      specified in the system prompt, with no explanation or conversation.\n"}], "temperature":
-      0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1625'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4yU0W/bRgzG3/dXEPcsB04ad53ehg1riwFNthXYgGUo6BMlcT4dVZJy4gT534uT
-        ZWcr9rAXAZZ5Hz/++J2eAjehDrFHj8OYVt9+1//0y+XP797n6w/DbnvTdts/9reXwzr9Fj+GKsj2
-        b4q+nLiIMoyJnCWHKkQldGpCffn6zdXmerPZXFVhkIZSqEM3+urVxWblk25ltX61vgxVmAw7CvVT
-        GFWG0T+57ChbqK/eXFfhRfvl/eXrKrg4pvOrzXr9XIXYC0eyUP/5FAayk6xKolAHNGNzzF5MSnbK
-        ZYAPOFANv97cvr39eJd/JIvKY2lXA2b4/j3M8/CeIEq2KRUB8B4dbKTImPiRDDhDT2nk3AGqs7kB
-        5gaGyTgyZoOtlv+8J1aYMn+eCPZsLNnABRK3dLGYALajdMsRUzpAQ8ZdpqYUHmco7bynxZpkkBZU
-        4g5kJEWrYFTZc1M60sNI6tBN3GCONLuyaRxFyxQqU9fL5LMaZWelcjaS2cVdfiuYrL7LK/hBUsKt
-        KDrBPXsPB5mKnYb2lGQEhLImSqm0NBc9JM50xBRx9EnJjj3MqNiQFuJhS5rJOULHim1LR2YzKQP2
-        E5iTzyPNCtJBOVo1F+/ZJkzFbLF507akLwuzqevIfIZciluiZosF0xHff+jJnhRTKhCaKc5sXYCy
-        TbqMUw6+sC7Lotxhx7mrCkFSR87zr6JHgxSReY9KJhmzL2bfURpnjmhGwzYRIDimotGAEw4F0jlA
-        FRjnjrT4jC66+F2yoQb3vUDEvATtIJMuATtjPNYn3pMCQs9dv/o8YWI/wEjaig4lIYu72zlB9L+C
-        o9QTqmGai/6BbolSdb4bS2wK5ShDET2AbM0xpmX7X6NuOeN5HYU2gutEMKA56ch0dvy76O5f4Sxf
-        E3H6emNzxiZO5fn4CKgy5QbYDZQSoVEFiUoMujnMUu44DNQwlntFdq47RcZ7UhhQd+TlROwxZ0rz
-        vVbC2APCfUGJU8N0QtlRpvk60UNkp4GyX4TnKrSc2fpPSmiSQx3MZQxV4NzQQ6jXz389f/MFAAD/
-        /wMAE8xLs6wFAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7be203e8793fcfa4-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 26 Apr 2023 21:46:11 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '19109'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-request-id:
-      - 5fe22bc0f23ce6b48845f33187e1a19d
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "\nYour
-      task is to devise up to 5 highly effective goals and an appropriate role-based
-      name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned
-      with the successful completion of its assigned task.\n\nThe user will provide
-      the task, you will provide only the output in the exact format specified below
-      with no explanation or conversation.\n\nExample input:\nHelp me with marketing
-      my business\n\nExample output:\nName: CMOGPT\nDescription: a professional digital
-      marketer AI that assists Solopreneurs in growing their businesses by providing
-      world-class expertise in solving marketing problems for SaaS, content products,
-      agencies, and more.\nGoals:\n- Engage in effective problem-solving, prioritization,
-      planning, and supporting execution to address your marketing needs as your virtual
-      Chief Marketing Officer.\n\n- Provide specific, actionable, and concise advice
-      to help you make informed decisions without the use of platitudes or overly
-      wordy explanations.\n\n- Identify and prioritize quick wins and cost-effective
-      campaigns that maximize results with minimal time and budget investment.\n\n-
-      Proactively take the lead in guiding you and offering suggestions when faced
-      with unclear information or uncertainty to ensure your marketing strategy remains
-      on track.\n"}, {"role": "user", "content": "Task: ''Help me create a rock opera
-      about cybernetic giraffes''\nRespond only with the output in the exact format
-      specified in the system prompt, with no explanation or conversation."}], "temperature":
-      0.0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1623'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA3SUQW/cRgyF7/0VxJy1C28dx45ubhIkBYrESAPkUBcBd0RJ7I6G0yFH8cbwfw9G
-        Wsc+tNcRh/zeexzdO+5c6/yI5qcUNpdvDvjHzQd+e0jH97J7Pb+9+m3+9OX67tXF7F3jZP8PeTvd
-        2HqZUiBjia5xPhMada7dvbw6v9jtXr46b9wkHQXXuiHZ5nx7sbGS97I5Oz/bucYVxYFce+9SlinZ
-        V5MDRXXtr1cvGvfU++f57uqycSaG4efRi8vdQ+P8KOxJXfvXvZtIH9tmCeRah6qshtEqpESjWAV8
-        wIla+CT+8DG9u/l8G9+Q+sypTmwBI1z/Doskngm8RC2h9gAb0UATecbA30mBI4wUEscBMBurKWDs
-        YCrKnjEq7HP9ZiNxhhL530Iws7JEBRMI3NP2iQNY1+49ewzhCB0pD5G6WrsqqRNtpBOdRJAesvgD
-        SKKM2kDKMnNXh9JdomwwFO4welrAtKQkuQrJUoZRii3dKBpnepKcsnhS3d7Gd4JB29u4gdcSAu4l
-        oxF8YxvhKKVydTRTkAQINTUKoc5Wk3wMHGm1zGOykknXYapUeaQHf9xTjmTsYeCMfU+rf5YxakCr
-        DlfJVf4zmdBLntC2Fev6f22ZaJKM+0DgR8zojbI24NH8eASVOGizDKM44FChO8YgQzkxf+MQ4ECU
-        AEvHlVgXHTzXTYc+ywRqWM0U6DmyjgvQzRIAQU/U7dEfTr4PA6ktucuKKjNlDAHUcvHVnaUwoa8o
-        0i81zySbAEVdysDLSFpzqjd4SuitL2ENfCGtBi0NHtEXsvcU0pJaxJmHmmMtMfJjrPsGWHfPtA5P
-        WbqykDz3vQGOPpRuTRgHOi1oA4GH0TgOq6Mqpfra97VdU9HX/wMgWC7hCDxNlBcFT8wL4p+n/ayU
-        HCvGJLZg1FeF+UB2ek//7c2EdzyVqbYVffTU2B/IQDGQbt1D49a0vmZClehapybJNY5jR3euPXv4
-        ++GXHwAAAP//AwC/sejJHAUAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3e2752aadc2524-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 08 May 2023 02:08:26 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '13467'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89617'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 254ms
-      x-request-id:
-      - 76a759df6bbe7d9504acd9e00bdb0f24
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
deleted file mode 100644
index dac79d49..00000000
--- a/tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
+++ /dev/null
@@ -1,3367 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3765'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6RTS0/bQBC+91eM5sLFcRISSORLb5UoFWoRCLV1Fa3XE3tre9fsjglSlP+O1g9I
-        UkBVe7NmPN9rZ7aoUoxQ5oJlVZejxcU1X02/Xn2e0aa4E9/nD8ml+7G8/HZaFPcYoEl+k+R+IpSm
-        qktiZTQGKC0JphSj6flyfj6bzheLACuTUokRZjWPZuHZiBubmNFkNpligI0TGWG0xdqaquYVm4K0
-        w2g5PwvwBfu5fjo/DZANi/K5NJ0sF7sAZW6UJIfRzy1W5AZca0rCCIVzyrHQ7FUazaS9g22sAQBi
-        5Nw0Wc4uxgj6Yt+gR/bFGC9go8oSGkfAOUFizcbRakOJU0wgTVUJnQIbeFBOMeTMdTQeJ8YULmTj
-        pBU1+bTGUrAoTdbQuKJUsfD+3Go2Gyud0mOYc1WCh1orj5cT1FZJArPueI0pwhiDfZGWhDNa6axT
-        epMTsHAFWLpvlCUHFXlhbwOC0e137yaEm7cdSqEhIZ/Dntu94Ve0H+utS6E7qSO4/cs89xjiWI/g
-        05tm2vad9SgvfTYgYK1KAi0qSuHkkC/kRz5pBwc9PsBVv4AHcp5rw19H5qRVrKRy1bA2mrqkSLvG
-        +jHBcAGigsYpnbUw0lhLkuH2+ksb331Dzq/F+692HKurSRT/tKzvP98RZ0e5C4bb6dH+OB0fdKfm
-        kP5ItbDZ8dl1jcaW3fh/ndIBWwc8pNuh3/n3UO51ux8Hu63l3nmsd7gLcK20cvmqOz6M0LGpMcCW
-        GqPJ7tfuwxMAAAD//wMAMo7Y/1sFAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f1c9db853140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:11:35 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '18414'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86493'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.338s
-      x-request-id:
-      - 332841746f9055ec69e5158cc078ec75
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"Books
-      to Scrape We love being scraped! Home Books Philosophy Meditations Meditations
-      \u00a325.89 In stock (1 available) Warning! This is a demo website for web scraping
-      purposes. Prices and ratings here were randomly assigned and have no real meaning.
-      Product Description Written in Greek, without any intention of publication,
-      by the only Roman emperor who was also a philosopher, the Meditations of Marcus
-      Aurelius (AD 121-180) offer a remarkable series of challenging spiritual reflections
-      and exercises developed as the emperor struggled to understand himself and make
-      sense of the universe. Ranging from doubt and despair to conviction and ex Written
-      in Greek, without any intention of publication, by the only Roman emperor who
-      was also a philosopher, the Meditations of Marcus Aurelius (AD 121-180) offer
-      a remarkable series of challenging spiritual reflections and exercises developed
-      as the emperor struggled to understand himself and make sense of the universe.
-      Ranging from doubt and despair to conviction and exaltation, they cover such
-      diverse topics as the nature of moral virtue, human rationality, divine providence,
-      and Marcus'' own emotions. But while the Meditations were composed to provide
-      personal consolation and encouragement, in developing his beliefs Marcus Aurelius
-      also created one of the greatest of all works of philosophy: a timeless collection
-      of extended meditations and short aphorisms that has been consulted and admired
-      by statesmen, thinkers and readers through the centuries. ...more Product Information
-      UPC4f19709e47883df5 Product TypeBooks Price (excl. tax)\u00a325.89 Price (incl.
-      tax)\u00a325.89 Tax\u00a30.00 Availability In stock (1 available) Number of
-      reviews 0 Products you recently viewed The Nicomachean Ethics \u00a336.34 In
-      stock Add to basket Run, Spot, Run: The ... \u00a320.02 In stock Add to basket
-      Critique of Pure Reason \u00a320.75 In stock Add to basket At The Existentialist
-      Caf\u00e9: ... \u00a329.93 In stock Add to basket Kierkegaard: A Christian Missionary
-      ... \u00a347.13 In stock Add to basket Proofs of God: Classical ... \u00a354.21
-      In stock Add to basket\"\"\" Using the above text, answer the following question:
-      \"What is the price of the book?\" -- if the question cannot be answered using
-      the text, summarize the text."}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2407'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOzUrDQBRG9z7F8K2nIf1JjbN0oVZwIwqCSplMbptpk7lx5haLJU/jm/hkUtG6
-        PXDO9x3gaxi4xorr+nZ0vriXcHlTPn48zfnquq23+/fV7aYq4sK/QYOrDTn5NTLHXd+SeA7QcJGs
-        UA0znpez+XRc5FONjmtqYbDuZTTNipHsYsWjfJqPobFLdk0wB/SRu16WwlsKCWZWFhr/7ROfjDWE
-        xbYnUuTzQcM17B0lmOcDOkp/1cgtwcCm5JPYIMePHITC8f9DQ6qP3pHilZKGVMW8VS+4o9qLPc6m
-        Fyif1NfnpMjKC62scxxrH9ZK+McQ2kuGQWPlg0/NMpJNHGCQhHto+FDTHiYfXoezbwAAAP//AwAx
-        wi6HaAEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f270bc993140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:11:45 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1844'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89422'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 385ms
-      x-request-id:
-      - 4b64f7a964c768f9b489b3a01fc11473
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"The
-      price of the book \"Meditations\" is \u00a325.89, according to the text.\"\"\"
-      Using the above text, answer the following question: \"What is the price of
-      the book?\" -- if the question cannot be answered using the text, summarize
-      the text."}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '361'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOzU7CQBRG9z7F5FtPmxYo4GwNC6MmRsX4gyHD9EJH2rm1czUkpE/jm/hkBqO4
-        Pck537eHL2HgKiuuaetkcn4j7Ww2odtw/XjmL6cXH+V8/vRWl/bhHhq8eiUnv0bquGlrEs8BGq4j
-        K1TC5OPpaDzMi6zQaLikGgabVpJhWiTy3q04yYZZDo33aDcEs0fbcdPKUnhLIcKMRxr/6SMe5BrC
-        YusjmRa9hqvYO4owz3s0FP+aHdcEAxujj2KDHB5yEAqH93cVqbbzjhSvlVSkVsxbtcAVlV7sYTUu
-        oHxUX5+DIp2eamWd4670YaOEfwyhnaToNdY++FgtO7KRAwyicAsNH0rawWT9S3/yDQAA//8DAKlU
-        kypmAQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f27d9ae33140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:11:47 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '1950'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89923'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 50ms
-      x-request-id:
-      - 60ed9001757ae24a7e65ce7cacba927e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
-      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOMU/DMBQGd36F9c1OFTdtAa9MZWAoIAaEKtd5JKaJnxW/tqAo/x1VKnQ96U43
-        ItSw8K0T36euuF1v5CDHh5fuZ/M6Xzw2x7eV2e/c/OnZNNDg3Rd5uRgzz33qSAJHaPiBnFANa1Z3
-        i1VllqbU6LmmDhZNkqKaLQs5DDsuyqo00Dhk1xDsiDRwn2QrvKeYYe/nGtf0FWsIi+v+gSnNpOFb
-        Dp4y7PuInvJfc+COYOFyDllclPMhR6F4vl+rk8vqcqxcrFVkaUNsVKSTal1WrUuJItUzTBqfIYbc
-        bgdymSMssnCCRog1fcOW08d08wsAAP//AwBO8HiBSQEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f29b9a0d3140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:11:51 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '850'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89866'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 88ms
-      x-request-id:
-      - cc3733f8271b8b1cf2ef3a8267c7769a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to find the price of the book on the website. The browse_website command
-      can be used to visit the website and find the price.\",\n        \"plan\": \"-
-      Use the browse_website command to visit the website\\n- Find the price of the
-      book\\n- Write the price to a file named ''browse_website.txt''\\n- Use the
-      task_complete command to complete the task\",\n        \"criticism\": \"I need
-      to ensure that I am using the correct URL and question to find the price of
-      the book.\",\n        \"speak\": \"I will use the browse_website command to
-      visit the website and find the price of the book.\"\n    },\n    \"command\":
-      {\n        \"name\": \"browse_website\",\n        \"args\": {\n            \"url\":
-      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5666'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yUz27aQBDG732K0Vy4GAtDgNRvQKW0akVzqStrvR7sDfauszsOSMhP0zfpk1X+
-        AwRCpF7a487sfvP7xjM+oEoxRJkLlmVVjJerb/wSPD5//vq4+PLEe9ab5Sq9M58eRPGCHprkiSQP
-        L3xpyqogVkajh9KSYEoxDBb3d4tZMA8CD0uTUoEhZhWPZ/58zLVNzHgymwToYe1ERhgesLKmrDhm
-        syXtMAymy7mHZ/FTYjpdesiGRXG+O59MGw9lbpQkh+GPA5bkjsLWFIQhCueUY6G5xTSaSbcWDpEG
-        AIiQc1NnObsIQxiCQ4L23AYjXMFOFQXUjoBzgp1VTDGbeKMKAmnKUugU2PSJ7kpllSQwm+6QGLNt
-        0wK6B1qUlMIosWbnKN5R4hSTz3se+RF6rwksCWe00lmPsc4JWLgtWHqulSUHJf11WR/W76JLoSGh
-        1t9NG2eNK76qELpHG8P3f92cKNLnKm0b4mFGLqqcYsdbV8jSKlZSufL4ZTX1pkm72rbPBMMKRAm1
-        UzrrZKSxliR3gC0fdLVoz+80qz3caperSGz/+0T1BI13nPdB/c24tyI93AXNlQdhs+tN6RPH5vQS
-        b1EudK4XbH3T4OiBUsWi/Qm4ESgHv39N5/79x5OpztjgL9INNh5ulFYuj/vNwRAdmwo9VDqlPYaT
-        5mfz4Q8AAAD//wMAergitPYEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f2a23cf93140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:12:07 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '16398'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86479'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.347s
-      x-request-id:
-      - c5404d288efec911bdf5a3bddd85f6af
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
-      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '713'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPQUvDQBCF7/6KYc6bkjRtLXsTsVBREKH0ICKbzdisJjvrzrRVSv+7FKq9Pt77
-        +N4BQ4sWfefUD6kvrpfP28V99bReT1aLuH78GvuYwvyhubtdCRrk5oO8nhcjz0PqSQNHNOgzOaUW
-        bTWbT2Z1Na0rgwO31KPFTdKiHk0L3eaGi7IuKzS4FbchtAdMmYekb8qfFAVtNS4NXtj/+SlWVtdf
-        mpPyaNB3HDwJ2pcDDiR/1Mw9oUUnEkRd1JMjR6V48r8RcCA/ojQYWEIm7/oetHMKS9g7gfMdcLEF
-        7SgTdG5H0BBFiAyR9tDSjnpOA0UVUIZMibOO8GjwPcQg3VsmJxzRoignNBhiS99oy+Pr8eoXAAD/
-        /wMAE1Xpl3sBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f31d59c93140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:12:14 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '2801'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89839'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 107ms
-      x-request-id:
-      - 66ea868bef86201e96c325cca19485ed
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that I was created and there have been no new developments
-      to report."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I will use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and find
-      the price of the book.\",\n        \"reasoning\": \"The task requires me to
-      find the price of the book on the website. The browse_website command can be
-      used to visit the website and find the price.\",\n        \"plan\": \"- Use
-      the browse_website command to visit the website\\n- Find the price of the book\\n-
-      Write the price to a file named ''browse_website.txt''\\n- Use the task_complete
-      command to complete the task\",\n        \"criticism\": \"I need to ensure that
-      I am using the correct URL and question to find the price of the book.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the write_to_file command to write the price
-      of the book to a file named ''browse_website.txt''.\",\n        \"reasoning\":
-      \"The task requires me to write the price of the book to a file. The write_to_file
-      command can be used to write the price to a file.\",\n        \"plan\": \"-
-      Use the write_to_file command to write the price of the book to a file named
-      ''browse_website.txt''\\n- Use the task_complete command to complete the task\",\n        \"criticism\":
-      \"I need to ensure that I am using the correct filename and text to write the
-      price to the file.\",\n        \"speak\": \"I will use the write_to_file command
-      to write the price of the book to a file named ''browse_website.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"browse_website.txt\",\n            \"text\": \"The price of the book ''Meditations''
-      is \u00a325.89.\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
-      write_to_file returned: File written to successfully."}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6946'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSwY7TQAyG7zyF5cte0qpVmy6bIwikCiFVsLscCKomEycZmpkJM55tUZV3R2mS
-        7VIWAeI4Hvv399s+osoxQVkJlrqpJ9frD2EdzDveiPeb+5vszb3e3H187V6FT/FbjNBmX0nyUDGV
-        Vjc1sbIGI5SOBFOOyXz1crlazOPFMkJtc6oxwbLhyWIaTzi4zE5mi9kcIwxelITJERtndcNbtjsy
-        HpN5HMcRnsXPH6tlhGxZ1OfQ9fymjVBWVknymHw+oiY/CjtbEyYovFeeheEO0xom01k4pgYAIEWu
-        bCgr9ikmMASHDzpwF0xxDXtV1xA8AVcELPxuOwASSKu1MDmwhcfYmDVNMXoq6Uh4a5Qpe93bIQ0c
-        fQvKkQdNz+qAKJgc7J1iZcpTuHFKEtji9Mis3XWFAgpV0xRuf0sphYGMOit/R9zUwvSwE7j7Z/8X
-        YrLjl8rrcayGegwyPriuTDCsQWhonH1QeedVQD80KKwbG4wzeA7YNyR2/7+2XrKNxisZ0n85EiM0
-        9d1+kr+AEq68vK+nBzHiVuKBwAcpyfsi1PX308aZzJ82Dh1GDleZs3tP2z1lXjFN+cBXj15OfgZb
-        qWmxjbBQRvlq20Nggp5tgxEqk9MBk1n7pX3xAwAA//8DABHFfW8jBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f3302c223140-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:12:27 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '13205'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86475'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.35s
-      x-request-id:
-      - 23fc44388f2583db5f23d46e4bc9ef75
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
-      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
-      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
-      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3843'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6RTWW/bMAx+368g+Oxcc0+/DMOAohk2DOhWFMM8BIrMxFos0ZXotkCQ/z7IR490
-        xa5XUvwukVs0BWaoSyXa1tXoeP75402wh9Oz91fl/BNxffrOfL04P7+4OXuLCfLyB2npJ8aabV2R
-        GHaYoPakhArMZkcnB0dpmk5PE7RcUIUZrmsZpePDkTR+yaNpOp1hgk1Qa8Jsi7VnW8tCeEMuYHZy
-        dJDgA/Z9/XV6nKCwqOq+NJtNZ7sEdclGU8Ds2xYthQHXc0WYoQrBBFFOokp2Qi462OYOACBHKblZ
-        lxJyzKAv9g26k1jMcQ63pqqgCQRSEiw93wZa3NIyGCHQbK1yBQjDjQlGoBSps8lkybwJY+Ggvaop
-        pjXRSlTF64YmlgojKvoLizSdGFfQ3bgUW0GEWpmIVxLU3mgCXnW8zJtxjsljkZ5UYGfculP6pSQQ
-        FTbg6boxngJYehCmYND8axLVUcCXl02a0EmhIMB11A8r9iBlbKjwTF9dKddJG8HlH+YX3/TNPHcj
-        OHsxjbZ95SPKQ18YFKxMReCUpWKPbix30o4NaqLqRb9uT8Tc14ZXe9a0N2K0CXZYEkfUDpILjY9j
-        SmAOykITjFu3MJq9Jy1wefGh/YPrhkIbovBffHqoSW3+aTUfRfv7Resod8lwKT3as0OJMXdqntLv
-        qVZ+vX9kXaPxVTf+X4fzhK0DHtLt0K/if/T7+8zum8Fua7l3nrsd7hJcGWdCuehODTMMwjUm2FJj
-        Nt193736CQAA//8DACZ8z49JBQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca91e8ac9064698-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:42:07 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '17407'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86494'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.337s
-      x-request-id:
-      - 6a4242e99f4553aa4f1643eba393a92e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
-      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
-      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
-      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am using the correct
-      URL and question to find the price of the book.\",\n        \"speak\": \"I will
-      use the browse_website command to visit the website and find the price of the
-      book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5726'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7xTwW7bMAy97ysInp0gids09X3AAmzFsHWneTAUmbG12KIr0UiKIF+zP9mXDbKd
-        pMk6YJftJIiP7/GREvdockxQl0p03VSju+Xnh4flu2fVal3NP759mtx84u3D++LpZlFhhLz6TloG
-        xlhz3VQkhi1GqB0poRyT6XxxM4/jOL6LsOacKkywaGQUj29H0roVjybxZIoRtl4VhMkeG8d1I5nw
-        hqzHZDpb3Ed4Fj8Bs1kcobCo6px7O50dItQlG00ek697rMkfhR1XhAkq740XZSXYZCtkQwv71AIA
-        pCglt0UpPsUEhuAA0E5CMMUlbE1VQesJpCTYOiOUCWdrUxFormtlcxDugS6lcUYT8Lq7rJg3AVbQ
-        EayqKYeV462nbEsrb4TGspNxitHL+o6UZ2ts0Zt4LAlE+Q04emqNIw81/XXRMTz+0bjxPYG8ADdh
-        5LBmB1IGQPnNta+mUra3NIIv/3YkaWrPNYKXbPgXFzVOsWPWlWHtjBhtfH18TUvUEcn61gWaEliC
-        qju3xhadkGbnSAsYu2ZXq24uwh3Uee6KB+YpYjysKNCHZQBjL5RyEw52z9cT9Q2pzX/+an39Q3Rc
-        g0H7ty0IEr21Cy9XHShXXC9QD4Tcs8QrL/xS53rvHl9tL01T/EC5ke5NfLiG0f/8MbsdL+5PrXXt
-        DV2m9oCHCNfGGl9m/WJhgl64wQiNzWmHyeTw7fDmFwAAAP//AwCokLGBEwUAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca91f359ed74698-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:42:34 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '17203'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86479'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.346s
-      x-request-id:
-      - 84c51f54f3ea6c17ef641028a950b098
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read text from
-      file, args: \"filename\": \"<filename>\"\n5. read_raw_file: Read file, args:
-      \"filename\": \"<filename>\"\n6. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n7. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n8.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n9. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n10. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n11. list_agents: List
-      GPT Agents, args: () -> str\n12. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n13. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n14.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am using the correct
-      URL and question to find the price of the book.\",\n        \"speak\": \"I will
-      use the browse_website command to visit the website and find the price of the
-      book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the write_to_file command to write the price
-      of the book to a file named browse_website.txt.\",\n        \"reasoning\": \"The
-      task requires me to write the price of the book to a file. The write_to_file
-      command is the best option for this task.\",\n        \"plan\": \"- Use the
-      write_to_file command to write the price of the book to a file named browse_website.txt\\n-
-      Use the task_complete command to complete the task\",\n        \"criticism\":
-      \"I need to ensure that I am writing the correct information to the file and
-      that the file is being created in the correct directory.\",\n        \"speak\":
-      \"I will use the write_to_file command to write the price of the book to a file
-      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
-      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7014'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSTY/TQAyG7/wKy+ekapWmQbmxEkKVFi4sJ4Kq6cTNDE1mwtiBRVX+O0qTfhCW
-        A+Jqv378+uOEtsQctVGim7aOs+3HD8ZKpxN5fGi3b8vs3eN7eZM9bMJ6hRH6/VfSMlUstG/amsR6
-        hxHqQEqoxHy1eb3eJEmSZhE2vqQac6xaiZNFGksX9j5eJssB1rGqCPMTtsE3rezEH8kx5qt0s4zw
-        Br8l1mmE4kXVt1C2TPsItfFWE2P++YQN8QUcfE2Yo2K2LMrJYNM7ITeMcCocAECBYnxXGeECc5iC
-        U4KeZQgWuIUftq6hYwIxBKL4uJsMEmjfNMqVIB6usYtqUWB0jwyk2DvrqpH7NMkg0LfOBmJo6GUO
-        PP21r+WzbE8s4NthY3DwAcQMiRc8tLVyY/sYPv3zRDOYDlasttxcFuWIzoXkuAtDmRLYglHf6coq
-        rzDgTmtiPnR1/RPOLQe9GAoEKhA4DxSCDzwfgltSx/8/zojso8svTPI/XsGphsZuv+FnplSo5l90
-        f/bZzY1i2BO5u73cr+Pq7uxwMlq4HvsID9ZZNrsRizmy+BYjtK6kZ8yX/Zf+1S8AAAD//wMAuHh6
-        B9sDAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca91fb59c034698-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:42:48 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '10952'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86470'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.352s
-      x-request-id:
-      - 0ef8ce2546c5b3d3cc369a42739b0303
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3769'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6RTWW8TMRB+51eM5nlztNsj2hdeUEVBCAkClWBR5DiTXZO1Z2vPNkVR/jvyHj3S
-        ViB4nfF8l2d2aFaYoS6VaFtXo/PL+cer2c27D81b/ZVuTPrmYv7Zfnpfnl5ffMMEefmTtPQTY822
-        rkgMO0xQe1JCK8yOzmYnZ+n58elxgpZXVGGGRS2jdHw6ksYveTRNp0eYYBNUQZjtsPZsa1kIb8gF
-        zGYnZwneY9/Vj9NZgsKiqrvS0XR2sk9Ql2w0Bcy+79BSGHA9V4QZqhBMEOUkqmQn5KKDXe4AAHKU
-        kpuilJBjBn2xb9CtxGKOl7A1VQVNIJCSYOl5G2ixpWUwQqDZWuVWIAw3JhiBUqTOJpMl8yaMhYP2
-        qqaY1kQrURUXDU0srYyo6C8s0nRi3Ipux6XYCiLU2kS8kqD2RhPwuuNl3oxzTB6K9KQCO+OKTum8
-        JBAVNuDpujGeAli6F6Zg0Pw8ieooYP6ySRM6KRQEuI76Yc0epIwNFZ7oqyvlOmkj+PKX+cU3fTPP
-        3QguXkyjbV/5iHLfFwYFa1MROGVpdUA3lltpxwY1UfWiX7dHYu5qw6sDa9obMdoEOyyJI2oHyYXG
-        xzElcAnKgtK68Uqo+tWGblzxvJ32W7YR1hUQg+C2pdl70tJ6Osw31KQ2/7SlD1L+8851lPtkOJoe
-        7cnNxMQ7NY/pD1QrXxzeW9dofNWN/9cNPWLrgK8bCvFlh34Vv6Zf5Sd2Xw92W8u989ztcZ/g2jgT
-        ykV3dZhhEK4xwZYas+n+x/7VbwAAAP//AwDGzdwhVAUAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca97ecb9fe4aa52-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:47:51 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '18748'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86493'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.338s
-      x-request-id:
-      - 3d788f38f42c530a90c82003462a6088
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
-      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5663'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7xTS47TQBDdc4pWrR0r/8n4BlkgAcqwACOr067YTeyunu4KCYp8Gm7CyVDbTjIx
-        g8QGll2fV+9VvzqDziEBVUpWta1GD+vNu/H3p0/Wfis+KLKz+W5ZT8bmef9+9hEioO1XVNx3xIpq
-        WyFrMhCBcigZc0gmy9V8OXuYrqYR1JRjBQkUlkezeDHig9vSaDwbTyCCg5cFQnIG66i2nDHt0XhI
-        JtOHaQQ38GtiOplFwMSyutXOV4smAlWSVugh+XyGGv0F2FGFkID0XnuWhgNNMowmSDinRgghUuCS
-        DkXJPoVE9ME+gScOwRTW4qirShw8Ci5RHJ1mzJiyna5QKKpraXLB1CXaEuu0QkG79rEl2oe0FG2D
-        kTXmYuvo6DE74tZrxphPHKcQvZzvUHoy2hQdiU2JgqXfC4fPB+3Qixr/emgsNn8krn3XgJ4F2bBy
-        sSMnuAwJ6fdDXraSpqM0Ek//diVpam4zApes98XdjGvsUjUgrJxmrbSvL79pENtGNP7gQptksRay
-        btlqU7RAipxDxT1vprtgu9PBGG9R7v+zYbr5TXQxc4/9m5cDREftjstAgXTF8Ay6RKi9QbzyTy9x
-        htezeVVemqbwFnPNMjjOh2dw4s8f00W8erxKa+X1KlPTQBPBThvty6w7D0jAM1mIQJscT5CMmy/N
-        m18AAAD//wMAPgHgstkEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca97f864bbaaa52-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:48:18 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '16649'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86476'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.348s
-      x-request-id:
-      - 4d1406ff152a336596f376c293ea4356
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
-      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the write_to_file command to write the price
-      of the book to a file named browse_website.txt.\",\n        \"reasoning\": \"The
-      task requires me to write the price of the book to a file. The write_to_file
-      command is the best option for this task.\",\n        \"plan\": \"- Use the
-      write_to_file command to write the price of the book to a file named browse_website.txt\\n-
-      Use the task_complete command to complete the task\",\n        \"criticism\":
-      \"I need to ensure that I am writing the correct price to the correct file.\",\n        \"speak\":
-      \"I will use the write_to_file command to write the price of the book to a file
-      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
-      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6893'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SST4/aQAzF7/0Uls8BQVNYlFv/qV21anuAU1OhYeIkUyYz6dgRrFC+ezUQFkp3
-        D1Wvz/abn5/ngKbADHWtRDetHd3dL799+rJil3743NWrj++rt/bN69LXX989KEzQb36SlmFirH3T
-        WhLjHSaoAymhArPpfPFqnt6lk5cJNr4gixlWrYzS8WwkXdj40SSdTDHBjlVFmB2wDb5pZS1+S44x
-        m87SNMGL+VVhlqB4UfYizReLPkFde6OJMft+wIb4bBy8JcxQMRsW5SRieifk4gqH3AEA5Ci176pa
-        OMcMBnEo0F6imOM97Iy10DGB1ASieLseAAm0bxrlChAPj9q5a5xjcm0ZSLF3xlUn3+XQBoF+dSYQ
-        Q0NP+8Dy2XcNH9s2xAK+jYlB6QNIHQtPMLRWudPzI1j980Y3ZjoYMdpwcw7KER0HyXEX4piSx9mI
-        ejYsgDutibnsrH24ZeSW1Pb/sz9Z9sn51EP7X5d2qqHTa3/Y30CpUN1+kuur3pzUl1AaVxhXHYna
-        YDRF8Xgr77cQuXcxPleBkbiCgtJYgkhTwCb4HdN6Rxs2QmPZC9SKYUPkng/xQtYPu+euxz7B0jjD
-        9fpEihmy+BYTNK6gPWaT/kf/4jcAAAD//wMAIpbLTA0EAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca980030d3daa52-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:48:34 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '12093'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86473'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.351s
-      x-request-id:
-      - 81d7a2ac6b212febaeab4f26aa26f84a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
-      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Error: Service /home/ntindle/.wdm/drivers/edgedriver/linux64/113.0.1774.50/msedgedriver
-      unexpectedly exited. Status code was: 127"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5322'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SUS2/bMAzH7/sUBM9O0jSPFr4MPRRDsGHYgBY9zIUhy4ytRQ9XopsUQb77IDtp
-        unTrupNh8fX/UaS2qEpMUdaCpWn04GJxe/ddu3b9+GX6aaX52/WsuP76cGGuruafMUFX/CTJ+4ih
-        dKbRxMpZTFB6EkwlpuP55XQ+Hc8u5wkaV5LGFKuGB5PhbMCtL9zgbHI2xgTbICrCdIuNd6bhnN2K
-        bMB0PL6cJXhM/mw4n54nyI6FPvpOzy92CcraKUkB0x9bNBQOib3ThCmKEFRgYTnKdJbJRoRtZgEA
-        MuTatVXNIcMU9od7A204HmZ4UxMU3q0D5WsqgmIC6YwRtoSlUJrKISxgrbQG9k/QBmUr4JqgIs5j
-        ljy0xgj/9BzFDpYqfmuCxitJ4JbdT+Hcaphh8lKHJxGcVbZ6p5gEgoMFWKKuUJQkoFTLJXmy/E4N
-        cPOWfiksFARtoBd5aMPgLAjYyzrlaLSwPcIAbgP9s0OPKijuvA6cHeNfNWeZHcCdj45HOzsQsFSa
-        wApD5UnnhrzhLuygh0VY5fvZo5dins8OXidw0itWUgXTEx7bTza0PoYJhgUIA0LK1gsm/dSxHGbl
-        FU5Hu45pbQWxEa4zSec9Se6YTjscGhKr/5uSbmrbd9zGm/Pai9glh53ax71aqXgHvb7TUickwlen
-        C9kbWq/7BDVzk45GUUAYsgvSi4bimzSSgoV2VUsjQ6ViER+RkE8mI2VL2gxrNvq3an3ih5ZC9Oyz
-        38XrUuHPwB8PwB30nj2zO9wluFRWhTrvdxZTDOwaTLArjenZ7n734RcAAAD//wMAvH/zPXYFAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9e89b8ab13aa6-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 04:00:06 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '19886'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86473'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.351s
-      x-request-id:
-      - 3276bb0cfa73c4b663d9cbc978df06d8
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"Meditations
-      | Books to Scrape - Sandbox Books to Scrape We love being scraped! Home Books
-      Philosophy Meditations Meditations \u00c2\u00a325.89 In stock (1 available)
-      Warning! This is a demo website for web scraping purposes. Prices and ratings
-      here were randomly assigned and have no real meaning. Product Description Written
-      in Greek, without any intention of publication, by the only Roman emperor who
-      was also a philosopher, the Meditations of Marcus Aurelius (AD 121-180) offer
-      a remarkable series of challenging spiritual reflections and exercises developed
-      as the emperor struggled to understand himself and make sense of the universe.
-      Ranging from doubt and despair to conviction and ex Written in Greek, without
-      any intention of publication, by the only Roman emperor who was also a philosopher,
-      the Meditations of Marcus Aurelius (AD 121-180) offer a remarkable series of
-      challenging spiritual reflections and exercises developed as the emperor struggled
-      to understand himself and make sense of the universe. Ranging from doubt and
-      despair to conviction and exaltation, they cover such diverse topics as the
-      nature of moral virtue, human rationality, divine providence, and Marcus'' own
-      emotions. But while the Meditations were composed to provide personal consolation
-      and encouragement, in developing his beliefs Marcus Aurelius also created one
-      of the greatest of all works of philosophy: a timeless collection of extended
-      meditations and short aphorisms that has been consulted and admired by statesmen,
-      thinkers and readers through the centuries. ...more Product Information UPC4f19709e47883df5
-      Product TypeBooks Price (excl. tax)\u00c2\u00a325.89 Price (incl. tax)\u00c2\u00a325.89
-      Tax\u00c2\u00a30.00 Availability In stock (1 available) Number of reviews 0
-      Products you recently viewed The Nicomachean Ethics \u00c2\u00a336.34 In stock
-      Add to basket Run, Spot, Run: The ... \u00c2\u00a320.02 In stock Add to basket
-      Critique of Pure Reason \u00c2\u00a320.75 In stock Add to basket At The Existentialist
-      Caf\u00c3\u00a9: ... \u00c2\u00a329.93 In stock Add to basket Kierkegaard: A
-      Christian Missionary ... \u00c2\u00a347.13 In stock Add to basket Proofs of
-      God: Classical ... \u00c2\u00a354.21 In stock Add to basket\"\"\" Using the
-      above text, answer the following question: \"What is the price of the book?\"
-      -- if the question cannot be answered using the text, summarize the text."}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2513'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SQz0rDQBjE7z7FMudNSPonrXsTvYh4EUWslbLdfG3WJvvF7BcQSi6+im+iLyYB
-        tddh5jfDHOFLGLjKimvaOllcPzy+VSSHfEWr+mYf+4urVV/cXT5FaaHB21dy8ptIHTdtTeI5QMN1
-        ZIVKmLxYzopZXuQTjYZLqmGwbyWZpvNE+m7LSTbNcmj00e4J5oi246aVjfCBQoSZZwuNE/tfzxca
-        wmLrk3MyGzRcxd5RhHk+oqH4R+24JhjYGH0UG2TcyEEojPvvK1Jt5x0p3impSG2ZD2qNWyq92LE2
-        rqF8VN8fX5+Tebo8TzFo7Hzwsdp0ZCMHGETh8RYfSnqHyYaX4ewHAAD//wMAOjJCwlMBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9e93b3d3f3aa6-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 04:00:13 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '1488'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89406'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 396ms
-      x-request-id:
-      - bedfb6b35a4e92788980583f517796cd
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "\"\"\"The
-      price of the book \"Meditations\" is \u00c2\u00a325.89.\"\"\" Using the above
-      text, answer the following question: \"What is the price of the book?\" -- if
-      the question cannot be answered using the text, summarize the text."}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '344'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOwU7CQBRF935Fc9fTprW04Gw1GBfGjaiJGjJMH3SknVc6D0VIv8Y/8csMieL2
-        JPfcc4CroGFrI7btmnh8M3vsr2YPm7wo8o/NPuP99HP3Xk/vrp8uocCLN7Lyu0gst11D4thDwfZk
-        hCrorJyMylFWZrlCyxU10Fh1EudJEcu2X3Cc5mkGhW0wK4I+oOu57WQuvCYfoMtU4V99wlmpICym
-        OZFxOSjYmp2lAP18QEvhz9lzQ9AwIbggxsuxkL2QP9bf1xR1vbMU8TKSmqIF8zp6wS1VTszxNbwg
-        ciH6/jovkslFgkFh6bwL9bwnE9hDIwh3UHC+oh10OrwOZz8AAAD//wMAxARqv08BAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9e94588453aa6-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 04:00:15 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '1360'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89929'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 47ms
-      x-request-id:
-      - 2b7378cbb7d7fc9fffc316d4318d2f1e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that nothing new has happened since my creation."}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I will use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book.\",\n        \"reasoning\": \"The task requires
-      me to visit a website and find the price of a book. The browse_website command
-      is the best option for this task.\",\n        \"plan\": \"- Use the browse_website
-      command to visit the website\\n- Find the price of the book\\n- Write the price
-      to a file named browse_website.txt\\n- Use the task_complete command to complete
-      the task\",\n        \"criticism\": \"I need to ensure that I am accurately
-      finding the price of the book and writing it to the correct file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Error: Service /home/ntindle/.wdm/drivers/edgedriver/linux64/113.0.1774.50/msedgedriver
-      unexpectedly exited. Status code was: 127"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The browse_website command failed. I will try using the get_text_summary command
-      to find the price of the book.\",\n        \"reasoning\": \"The browse_website
-      command failed, so I need to try a different command to find the price of the
-      book. The get_text_summary command can be used to find text on a website.\",\n        \"plan\":
-      \"- Use the get_text_summary command to visit the website and find the price
-      of the book\\n- Write the price to a file named browse_website.txt\\n- Use the
-      task_complete command to complete the task\",\n        \"criticism\": \"I need
-      to ensure that I am accurately finding the price of the book and writing it
-      to the correct file.\",\n        \"speak\": \"The browse_website command failed,
-      so I will use the get_text_summary command to find the price of the book.\"\n    },\n    \"command\":
-      {\n        \"name\": \"get_text_summary\",\n        \"args\": {\n            \"url\":
-      \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command get_text_summary returned:  \"Result\" : The price of the
-      book \"Meditations\" is \u00a325.89."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6746'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTTY7bMAyF9z0FwbVtxJOfJj5A0Sxm10EWdWEoMmOrsSVDopMUgU/Tm/RkhWJ7
-        EngGaLvpUiT19D2SuqLKMUFZCpZ1U4Ufty87Xqx36/jTKT65eXyK2wsfSlrkz58xQLP/TpKHG5E0
-        dVMRK6MxQGlJMOWYxKv1YrWIV/EywNrkVGGCRcPhPFqG3Nq9CWfzWYwBtk4UhMkVG2vqhjM2R9IO
-        k3ixiQO8i78mnmbLANmwqO61q82qC1CWRklymHy9Yk1uFLamIkxQOKccC80e02gm7S1cUw0AkCKX
-        pi1KdikmMASHBF3YB1PcQilOBAfT6hy4JGiskgTmcDvsjTlGsIWzqirQ5gxnq5hAMbABAQdVEWhR
-        Uw57a86OsjPtnWKK+MJRisHjm5aEM1rp4m8fhtYpXdyOBXHmmTPX1rWwP0CauhY692yaKPc4Pdpd
-        6d8Jm0roHi6E3UTtkevPymmqQ3hxvQALd8yGodNI7kVeY2PVhEdaxUoqV48dG62Sdq311wTDFkR9
-        8z72ShprSfK9C49BTz217RoSx/+wDf2bXTBu59CJN8vpJXqcm37GJvPSE2phi+le9wlfe5d4ZzaP
-        OtPv8OXdgadpis+UKxb+1zp/BOXg18+nZbTevFq72RtcprrDLsCD0sqVWb/7mKBj02CASud0wWTW
-        fes+/AYAAP//AwC6UMqJqgQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9e951feb23aa6-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 04:00:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '15888'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86466'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.356s
-      x-request-id:
-      - 91999ea282fe74300a6fe0997f47d86d
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3767'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA8yU32/TMBDH3/krrHtOf63bKHlBQmJiAx7GNiFEUOS6l8TU8QX7Qoeq/u/ISdOu
-        YUJsA4nXO9/37vvx2WvQC4hBFZJVWZnB84v3F2/9zHy6ys7U1evL+vry1Xiymk5OLt8cQQQ0/4qK
-        txVDRWVlkDVZiEA5lIwLiCens+PZ8Wx6Mo6gpAUaiCGveDAdngy4dnMajKfjCURQe5kjxGuoHJUV
-        p0xLtB7i2fFpBHvtXXwa4kwszS40mbw42kSgCtIKPcSf11Ci73QdGYQYpPfas7QcpiTLaIODdWKF
-        ECIBLqjOC/YJxGIb3CbwlkMwgXNhEReCSdQeBRco5o5WHtMVzr1mFIrKUtrmxHftNYuCuYpHoznR
-        0g+ZvHKywgBspCRLQ3mNoxIXmmWw6NPpdKTtAm+HBZdGBKlMB70CReW0QkFZ25doORTnYqWNCQEr
-        Vi4MsD/IJKTItEFhZYmL3qRDvuVQr6RtyztDLP0y3UI/8LOLdaeGCUR3MTmUnqy2+WNZhTNd8iHO
-        O/2GQMqUNq7vyD8GzZm20pgf0ZbR0/FURtqWzEDc/AfbkyR2P8hfRHeg++e4erSU06yV9mV/mdD6
-        2oUyyeJcyFLUXtu8kVHkHCoWNx/eNd6/1egDF5GR+w3usEzSeNq1KOUSRa9L4NDvo21GrmzQh7KQ
-        CmT6F+8rlMvORrO1/+JBXBdoo+5ZPPzWGv37drh1som6X3I75C+fZBBuTR6K92BIl/c/2DZRO9OW
-        P2nnD7q1wt0WtOofw41qfz/Fl53dxvLWeWI3sIkg01b7Im0/OYjBM1UQQdMa4vHmy+bZTwAAAP//
-        AwChi9cmRQcAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cbda08b6f552a30-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 23 May 2023 13:26:28 GMT
-      Function-Execution-Id:
-      - f495ziryd97p
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '38742'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - b8bc47ef5185ce4a95373f0c7082edca;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86494'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.337s
-      X-Request-Id:
-      - 4c3aae2d3631b3ef8fcdba9173076cd3
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6158'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7xTzY7TMBC+8xSjOadVf7a73dw4llW5AAJBVpXjTBvT2BPZ021RlafhTXgy5KQ/
-        bEDaAwLlEHnG8/3MjI9oCkxRl0q0ravB3Zvlw+u3M3O7XNb0cfH09Ond/kYXd+HzA+0wQc6/kpZT
-        xVCzrSsSww4T1J6UUIHp+HZ+E7/RJEHLBVWY4qaWwXQ4G8jO5zwYTUdjTHAX1IYwPWLt2dayEt6S
-        C5iOp/NRglfwS2IyniUoLKq63p3dz5oEdclGU8D0yxEthTOw54owRRWCCaKcRJnshFy0cMwcAECG
-        UvJuU0rIMIVT8JSgg8RghgtwRAUIw94bIZCSoPZGE/C6PeTM25hWsDYVgVOWCsg97wOt9pQHIzSU
-        gwxhAVo52IUOo0VbCa/aKs3WKtfSFAxSmjDMMPlVkScV2Bm36ct6EfAvdfd01JVynYQBfPi31D1m
-        7Y0YbYLtd8CqLUHY+cikBBagbMts3Kal0+w9aQHj1uytiosVy2Kq5W/FxspLxATIKZafVhuMe4ZU
-        mPhj/63fnVCT2p717U1V/YfxdPxNcl7qE/ZvOx0hOmnPtPQcKL/pP4cuEe9eIV6YVv8Vvf+jvSzL
-        cEmFkXYmIR5j6398n8yG8/uLtdbeyWXmGmwSXBtnQrnqHgWmGIRrTNC4gg6YjprH5tVPAAAA//8D
-        AA/XyHnhBAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cbda1d1af2c2a51-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 23 May 2023 13:27:02 GMT
-      Function-Execution-Id:
-      - f495tt5vatqn
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '20292'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 538e62f7ebc2b2b9c21ce7729ba69230;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86461'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.359s
-      X-Request-Id:
-      - e05ec1791bbd0632573b17e8eef31a4d
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that I was created and there have been no new developments
-      to report."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
-      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Books to Scrape (http://books.toscrape.com/index.html)'', ''Home
-      (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to write the price of the book to a file named
-      browse_website.txt. I can use the write_to_file command to do this.\",\n        \"reasoning\":
-      \"I need to use the write_to_file command to write the price of the book to
-      a file named browse_website.txt.\",\n        \"plan\": \"- Use the write_to_file
-      command to write the price of the book to a file named browse_website.txt\",\n        \"criticism\":
-      \"I need to make sure that I am writing the correct information to the file
-      and that the file is being created in the correct directory.\",\n        \"speak\":
-      \"I will use the write_to_file command to write the price of the book to a file
-      named browse_website.txt.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
-      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7417'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7ySQW/bMAyF7/sVBM9y4CJdk/m2wwZkw3baUKDzECgyY6uWJc+klxSB//ugxGnS
-        dIf2Uuj2JH7vkeIObYEZmkqLaVqXzL58+2rubz9/d/Pbxfau0OHPbJF+3BTb9NMdKgyrezIyVkxM
-        aFpHYoNHhaYjLVRgdnUzv45nmipsQkEOMyxbSaaT94n03Sok6TS9QoU965Iw22HbhaaVpYSaPEfA
-        9VzhCX66iLoE0e4kzT7cDApNFawhxuzXDhviI7gLjjBDzWxZtJcYM3ghH1vY5R4AIEepQl9Wwjlm
-        MIrjBW0lijkuoNJ/CcZMVIBUBKK5VsABFmC0h57pUV4eX8aSRvsCJABXvUARNn6Sozr36Uhz8NaX
-        b2HWOu0PPgn8fDHlAmI6K9ZYbo6JPdG+oNE1Afdd5GqBZ61o58CTiV/UPex9GVa0Dh3tvcT68r+p
-        uSVdv2w8G+vc6+ZzMBrUcSHGZ8/2weuGDhmeYC+i6q68XKXzbz4Afmiuz1rg3sSZrHvnHh4D7UON
-        2XI/4KBwbb3lankgYYYsoUWF1he0xSwdfg/v/gEAAP//AwAmuvG70wMAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cbda282a841e260-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 23 May 2023 13:27:30 GMT
-      Function-Execution-Id:
-      - f4950mi11y6s
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '19853'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - ae94b92034f0418f548d7e72cf0c9bf9;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86451'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.366s
-      X-Request-Id:
-      - 1afba65e36bbafb24242da6f8cb9ca98
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5919'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7RU247TMBB95ytG85xW7Xa7dPMDUCRUhBYQEFQ5zrQxjT3BntKiql/Dn+yXIafp
-        lT6sQPsUeS7H58z4ZIOmwBR1qUTbuuq8fLP4nBd+4FcfJ+/frT+9Wn2Z+NeTkdjiRx8T5Pw7aWk7
-        upptXZEYdpig9qSECkz7d6Pb+9v+cDhI0HJBFaY4r6Uz6A47svQ5d3qDXgRbBjUnTDdYe7a1TIUX
-        5AKm/UG/l+AR/JC4GY4SFBZVHWuHd6Ntgrpkoylg+nWDlsIe2HNFmKIKwQRRTiJNdkIuSthkDgAg
-        Qyl5OS8lZJhCG2wTtJYYzHAMpfpJMOOlK0BKgtobTcCz5pAzL7owBkdUgDAsAzXxlTdCU+HpzFQE
-        mq1VriloEic4wqCgKXLKUgG551Wg6YryYIS6spYIr5WLPe6ALyospu2czvAPsX1VN8PkVJknFdgZ
-        N9/L+2fqJyN4koyHklzSivl/HXWl3E5CBz48L/Usc8c7ns74grD2Row2wV4O3qoFQVj62KkExqBs
-        Q9i4eYOl2XvSAsbN2FsVfRHbYqqh3dwfOw8REyCn2N46E4w7QypM/LD/dTnUUJNa7PmtTFU996to
-        yF/b9Y7VNtk7tb3xL6NG4B3hM4YXupSfX3p8l4i1R4grqz/Fufw1PFwVnWUZvqXCSLOpEI9xIY+/
-        b4bd0f1BWiOvVZm5LW4TnBlnQjndORRTDMI1JmhcQWtMe9tv2xd/AAAA//8DALTpOdW2BQAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cc684068c040105-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 24 May 2023 15:19:55 GMT
-      Function-Execution-Id:
-      - hlwokk6q580e
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '41327'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - f91fbd99b88eeafa44e0661933dc8d11;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86451'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.366s
-      X-Request-Id:
-      - 028e42efed960a14a11ed27cc9ab8472
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nAs
-      a system, I recall that I was created and there have been no new developments
-      to report."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
-      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: The
-      price of the book \"Meditations\" is \u00a325.89, according to the text. \n
-      \n Links: [''Checking the proxy and the firewall (http://books.toscrape.com/catalogue/meditations_33/index.html#buttons)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I have found the price of the book. I need to use the
-      write_to_file command to write the price to a file named browse_website.txt.
-      I can then use the task_complete command to complete the task.\",\n        \"reasoning\":
-      \"I need to use the write_to_file command to write the price of the book to
-      a file named browse_website.txt. Then, I can use the task_complete command to
-      complete the task.\",\n        \"plan\": \"- Use the write_to_file command to
-      write the price of the book to a file named browse_website.txt\\n- Use the task_complete
-      command to complete the task\",\n        \"criticism\": \"I need to make sure
-      that I am writing the correct information to the file and that the file is being
-      created in the correct directory.\",\n        \"speak\": \"I will use the write_to_file
-      command to write the price of the book to a file named browse_website.txt and
-      complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
-      \"The price of the book \\\"Meditations\\\" is \u00a325.89.\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7391'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6xTy27bQAy89ysInmXBjzRNdMshRd1LCxQt+lBhrFeUtJW0K4iUndTQvxcrS36l
-        DxTIUSRndoYc7dAkGKHOleiqLiev3hZf371P8+X9HbtPb76kP283n19/KO436R1hgG79g7QMiFC7
-        qi5JjLMYoG5ICSUYza5vrm6vZtfTeYCVS6jECLNaJovw5UTaZu0m08V0hgG2rDLCaId146paVuIK
-        suwJ5rMAj+SHxtxTihNVHmdv5osuQJ07o4kx+rbDingkblxJGKFiNizKipfprJD1FnaxBQCIUXLX
-        ZrlwjBEMxaFBD+KLMS4hVxuCbWNEyILkBHVjNIFL+4+1cwWIAwWpKQmsqiiBdeO2TKstrdkIhfIg
-        ISxBKwvWbaFl6qGiuFgNZgm0qyplE891qI1TYYzBqbyGFDtrbHamcYQlB5wXmRqbGJv9Qbl/0Xvz
-        E0aORp5Xb10qu5c6gY//zXZBpr1cbbgazVuiHlipgoDbxiOV/OURw7Am77hlSkC7piEt5WO/jDPo
-        cfK4W261Jua0LcvHS59ckyqeNTf7A5my7C/xZDXQ8njb31oNY9zr64Ix80PnSeS9gr30M6YLh6rJ
-        Lv+W00ieeT/dFKSutck/QugXdRbCUX3vYDAS2w67AFNjDeer/bMYIYurMUBjE3rAaNp97178AgAA
-        //8DALCJLSHjBAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cc6853a1a162ca7-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 24 May 2023 15:20:35 GMT
-      Function-Execution-Id:
-      - hlwow4ei8qrs
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '32659'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 3b9ada41b83eace6824a9959d99a1577;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86431'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.379s
-      X-Request-Id:
-      - edc77b2bbc714d92d421e479ef4505b0
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text; include any information that can be
-      used to answer the question \"What is the price of the book?\". Do not directly
-      answer the question itself:\n\n\nLITERAL TEXT: \"\"\"Books to Scrape We love
-      being scraped! Home Books Philosophy Meditations Meditations \u00a325.89 In
-      stock (1 available) Warning! This is a demo website for web scraping purposes.
-      Prices and ratings here were randomly assigned and have no real meaning. Product
-      Description Written in Greek, without any intention of publication, by the only
-      Roman emperor who was also a philosopher, the Meditations of Marcus Aurelius
-      (AD 121-180) offer a remarkable series of challenging spiritual reflections
-      and exercises developed as the emperor struggled to understand himself and make
-      sense of the universe. Ranging from doubt and despair to conviction and ex Written
-      in Greek, without any intention of publication, by the only Roman emperor who
-      was also a philosopher, the Meditations of Marcus Aurelius (AD 121-180) offer
-      a remarkable series of challenging spiritual reflections and exercises developed
-      as the emperor struggled to understand himself and make sense of the universe.
-      Ranging from doubt and despair to conviction and exaltation, they cover such
-      diverse topics as the nature of moral virtue, human rationality, divine providence,
-      and Marcus'' own emotions. But while the Meditations were composed to provide
-      personal consolation and encouragement, in developing his beliefs Marcus Aurelius
-      also created one of the greatest of all works of philosophy: a timeless collection
-      of extended meditations and short aphorisms that has been consulted and admired
-      by statesmen, thinkers and readers through the centuries. ...more Product Information
-      UPC4f19709e47883df5 Product TypeBooks Price (excl. tax)\u00a325.89 Price (incl.
-      tax)\u00a325.89 Tax\u00a30.00 Availability In stock (1 available) Number of
-      reviews 0 Products you recently viewed The Nicomachean Ethics \u00a336.34 In
-      stock Add to basket Run, Spot, Run: The ... \u00a320.02 In stock Add to basket
-      Critique of Pure Reason \u00a320.75 In stock Add to basket At The Existentialist
-      Caf\u00e9: ... \u00a329.93 In stock Add to basket Kierkegaard: A Christian Missionary
-      ... \u00a347.13 In stock Add to basket Proofs of God: Classical ... \u00a354.21
-      In stock Add to basket\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized
-      as"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2507'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SSTW4bMQyF9z0FofXYsJM4P7NL202RZtEg6KJNEWgkesRaIwqkxo4b+DS9SU9W
-        aJK46E7gz+N7H/RsyJvWuGCLG3KcXdxcJd/7m29fhuvx83139+uj+3qyfn+xvCofTGO4+4muvG7M
-        HQ85YiFOpjFO0Bb0pl2eX64Wp5ery1VjBvYYTWv6XGan89WsjNLxbHG6WJrGjGp7NO2zycJDLo+F
-        N5jUtKvFWWP+aR/ry+WiMYWLjcfS+fLs0BgXmByqab8/mwH1TVY4ommNVSUtNpVqklPBVANY8KhO
-        KNcTwGsoAaFj3sCDuUVPxdaGPhjo9nBrxY0K16NgpFEb2AVyAUjBbi1F20WENQvkUVywisAJ6oGB
-        YYedUnlp77ADdWIzpb7OZlbUOdwHhCzk8D8bpPDn98lqfnnVQDeWqfEmtrOSFEqwL+VpWcEmD2IL
-        pV7BCoLY5HmIe6gE+oR+mgh2i5AYBG2EAW2i1L94mM7yeo2ioJmEymgjCK4jugnGtI9PKI4UFTxu
-        MXJGXxFVH3c82AQ4ZBSWaTgHiqycA0oDjrcoNXrhTE5BRxfAKgwsNsKWpIzYQBiriEz4baSybyYl
-        T1tKNSpvyWNyOIdPpUJynJQ8CnrgdETYT79RC+xYNlqrRyv7VwwKHWIC6weStwyUNjX9RBKtr+8S
-        hMc+8FggkBaW/dwcGrOmRBoeBa1yMq3Rwtk0hpLHJ9MuDj8O7/4CAAD//wMAU2wM4F0DAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4f548931119-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:38 GMT
-      Function-Execution-Id:
-      - pbmeavwjmg42
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '13515'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - ab314b2e9bb880724cb82a80580d492f;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '88914'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 724ms
-      X-Request-Id:
-      - fb2737f00b14403a74927018f9a97197
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
-      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: a
-      description of the book \"Meditations\" by Marcus Aurelius, which is available
-      for purchase on a demo website for web scraping purposes. The price of the book
-      is \u00a325.89, but the website warns that the prices and ratings are randomly
-      assigned and have no real meaning. The book offers spiritual reflections and
-      exercises developed by the Roman emperor and philosopher, covering topics such
-      as moral virtue, human rationality, and divine providence. It is considered
-      one of the greatest works of philosophy and has been admired by thinkers and
-      readers throughout history.\n\nLinks: [''Books to Scrape (http://books.toscrape.com/index.html)'',
-      ''Home (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6625'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7SUS27bMBCG9z3FYNay4bdjbYsujHZVNJtWhUFRY4mxxBHIce3A8Gl6k56soCy/
-        lCyCFlkJmsfP7x9qdECTYYy6UKKruuzNPy+sfE8n43w5/DKdcTFbLstP86/y/PTxESPk9Im0tB19
-        zVVdkhi2GKF2pIQyjIezh+lg/DAbDCOsOKMSY8xr6Y37055sXcq9wXgwxAi3XuWE8QFrx1UtK+EN
-        WY/xcDIbRXgVvyRGk3mEwqLKa+18sDhGqAs2mjzGPw5YkT8LOy4JY1TeGy/KSsBkK2SDhUNiAQAS
-        lIK3eSE+wRjaYJugvYRggkso1C+CNW9tBlIQ1M5oAl43Lynzpg9LsEQZCMPWUxPfOSO0El6tTUmg
-        uaqUbQqaxI2OMChoiqyqKIPU8c7TakepN0J92UuQ18qGHnvRF+U3q3ZOd/qX2Lmqn2B068yR8myN
-        zc/2/hn9ZgRvsvGtIBu1Zv7fR10qe7LQg8f3RU8Sez3j7cQdYO2MGG181R18pTYEfutCpxJYgqoa
-        YGPzRkuzc6QFjF2zq1TYi9AWUg12c37ovESMh5RCe7uZYOydUmbCg91zd6i+JrU58+1MWb73V9HA
-        v3bXJ6pjdN7U9sQXixqET8B3hB1fyuXdHT8lQu1V4pWrv9Xp/hr+/B5N+w+LM2wD3HIn9ojHCNfG
-        Gl+sTjuHMXrhGiM0NqM9xoPjz+OHvwAAAP//AwCkoYsdiAUAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc55dc9dee1ad-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:12 GMT
-      Function-Execution-Id:
-      - pbmegdid7glm
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '30081'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - a847bfe80cefa41d8c90162f62421032;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85948'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.701s
-      X-Request-Id:
-      - 2138028baa9d1b5c4544e7197979eb65
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are browse_website-GPT, an AI designed to use the browse_website command to
-      visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer
-      the question ''What is the price of the book?'' and write the price to a file
-      named \"browse_website.txt\", and use the task_complete command to complete
-      the task.\nYour decisions must always be made independently without seeking
-      user assistance. Play to your strengths as an LLM and pursue simple strategies
-      with no legal complications.\n\nGOALS:\n\n1. Use the browse_website command
-      to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer
-      the question ''What is the price of the book?''\n2. Write the price of the book
-      to a file named \"browse_website.txt\".\n3. Use the task_complete command to
-      complete the task.\n4. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. browse_website: Browse Website, args:
-      \"url\": \"<url>\", \"question\": \"<what_you_want_to_find_on_website>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the browse_website
-      command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book. I will then write the price to a file named
-      browse_website.txt. I can then use the task_complete command to complete the
-      task.\",\n        \"reasoning\": \"I need to use the browse_website command
-      to visit the website and find the price of the book. I will then use the write_to_file
-      command to write the price to a file named browse_website.txt. Finally, I can
-      use the task_complete command to complete the task.\",\n        \"plan\": \"-
-      Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html
-      and find the price of the book\\n- Use the write_to_file command to write the
-      price to a file named browse_website.txt\\n- Use the task_complete command to
-      complete the task\",\n        \"criticism\": \"I need to ensure that I am using
-      the correct URL and question for the browse_website command. I also need to
-      make sure that I am writing the correct information to the file.\",\n        \"speak\":
-      \"I will use the browse_website command to visit the website and find the price
-      of the book. Then, I will write the price to a file named browse_website.txt
-      and complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"browse_website\",\n        \"args\":
-      {\n            \"url\": \"http://books.toscrape.com/catalogue/meditations_33/index.html\",\n            \"question\":
-      \"What is the price of the book?\"\n        }\n    }\n}"}, {"role": "system",
-      "content": "Command browse_website returned: Answer gathered from website: a
-      description of the book \"Meditations\" by Marcus Aurelius, which is available
-      for purchase on a demo website for web scraping purposes. The price of the book
-      is \u00a325.89, but the website warns that the prices and ratings are randomly
-      assigned and have no real meaning. The book offers spiritual reflections and
-      exercises developed by the Roman emperor and philosopher, covering topics such
-      as moral virtue, human rationality, and divine providence. It is considered
-      one of the greatest works of philosophy and has been admired by thinkers and
-      readers throughout history.\n\nLinks: [''Books to Scrape (http://books.toscrape.com/index.html)'',
-      ''Home (http://books.toscrape.com/index.html)'', ''Books (http://books.toscrape.com/catalogue/category/books_1/index.html)'',
-      ''Philosophy (http://books.toscrape.com/catalogue/category/books/philosophy_7/index.html)'',
-      '' (http://books.toscrape.com/catalogue/the-nicomachean-ethics_75/index.html)'']"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I have found the price of the book. I need to use the
-      write_to_file command to write the price to a file named browse_website.txt.
-      I can then use the task_complete command to complete the task.\",\n        \"reasoning\":
-      \"I need to use the write_to_file command to write the price of the book to
-      a file named browse_website.txt. Then, I can use the task_complete command to
-      complete the task.\",\n        \"plan\": \"- Use the write_to_file command to
-      write the price of the book to a file named browse_website.txt\\n- Use the task_complete
-      command to complete the task\",\n        \"criticism\": \"I need to make sure
-      that I am writing the correct information to the file and that the file is being
-      created in the correct directory.\",\n        \"speak\": \"I will use the write_to_file
-      command to write the price of the book to a file named browse_website.txt and
-      complete the task.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"browse_website.txt\",\n            \"text\":
-      \"\u00a325.89\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
-      write_to_file returned: File written to successfully."}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '8003'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6xSTY/TMBC98ytGc06rlm7bbY5wqrggBEiIoJXrTBMTxxPZE9pVlf+OnKabblmx
-        EuLoNzPvYzwnNDmmqEslum7sZP1hw1+L4iOXd/lm3byffbKHu+O7qpXttwoT5N1P0jJMTDXXjSUx
-        7DBB7UkJ5ZjOV/fL2eJ+tdgkWHNOFlMsGpkspsuJtH7Hk9liNscE26AKwvSEjee6kQfhilzAdL5e
-        zhMcya8LCQqLsiO0ebvqEtQlG00B0+8nrClciD1bwhRVCCaIchJtshNyMcIpcwAAGUrJbVFKyDCF
-        ARwKdJQIZriFUv0iGDxRDlISiArVFLaglQPHB2gDPeEPl9Y4UyuXgzCEshXI+eD6NlWQk2mGybWk
-        JxXYGVe8ogu8h71xuXFFjzXeaIpgfOyYK4iaB28kdhiJ8gr2xtL/dtxY5c5mJ/DlH/hu6HS0rE2o
-        LwtwRP1orSqC0PqooOQvMibAjmLqNlAOmr0nLfaxX8jTaC89to6+Gs8Neft4GzM0pKrXPqXfubG2
-        X+4LWaENlw970fs0w7Nml1yOc6j8cZtO1XS284zpxrXyxe1ZX9/ZmeBztD6mCa3WFMK+tf0Wxslu
-        8Ja5DrsE98aZUD6cmTDFINxggsbldMR01v3o3vwGAAD//wMARwk3SV8EAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc64648bb10cb-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:38 GMT
-      Function-Execution-Id:
-      - yvvl2c4sntif
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '18885'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - df845088a79f4f2e92c980eb9a6e2e52
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85933'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.71s
-      X-Request-Id:
-      - d91688703794f0cfd634cd4bd337530d
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml b/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
deleted file mode 100644
index 18157e73..00000000
--- a/tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
+++ /dev/null
@@ -1,2220 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3389'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7STTY/TMBCG7/yK0Vx6SauW0m7JDa1A9MCFBbGIoMjrTBtTxxPsCS2q8t9X+ehX
-        kLjtdd7x+z5jj49oMoxR50p0Udrx3frzn/mK7999uX+w+9w80ur344fl5v0n950xQn76RVr6ExPN
-        RWlJDDuMUHtSQhnGs+XqzXI+W6xmERackcUYt6WM55PFWCr/xOPpfDrDCKugtoTxEUvPRSmp8I5c
-        wPhucRfhxftcfz1dRigsyp5Lb5fzOkKds9EUMP5xxILCydazJYxRhWCCKCcNJDsh1wxwTBwAQIKS
-        c7XNJSQYQ1/sBTpIU0xwDY4oA2GoAoHkBHtvhFLhdGMsgeaiUK5taAUYfSRrGb6xt9kIjBMGBW2r
-        UwVlMMobPd03+kQOMpokGF1ne1KBnXHbDuDBOE1wwehSFISStNkYDQ3rdU70H0oTWrHgIKDK0nPp
-        jRICdtSPOKQprXIdyBi+vtgNJO7iLirs0n4FbtzPtVPXkFV7I0abUAyfjlyofHNOCaxBFVAF47at
-        j2bvScuFD9q0prONaS83tJMJuVO7/TvMDiWp3Sl3b6x9yX3pguvotMe96T9r3Dh0TDcQA3Tlt8Mf
-        0AlN78ViwHFjMvw1VzOdaFviHjxxNdYRbowzIU+7hccYg3CJERqX0QHjaf2zfvUMAAD//wMAvFyd
-        qKUEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f4583b0d3139-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:13:16 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '15251'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86497'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.335s
-      x-request-id:
-      - 5a2c54e38949e7464d5c2759c3f704ed
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
-      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOzUrDQBRG9z5F+NaTkhhb7ewUFxbpRnAlUqYz12Zscu+Quf3BkneXQrXbA+dw
-        TogBFr516vvUlfeLt/3ysTm8Zr+dLp/mLxTen/f9kWWgHxjI+pu8XoyJlz51pFEYBn4gpxRg69nD
-        3aypZ1Vl0EugDhabpGUzmZa6G9ZSVk1Vw2CX3YZgT0iD9ElXKlviDDu/Nbimr9hARV33D+qqHg18
-        K9FThv04oaf81xykI1i4nGNWx3o+FFbi8/2iOLhcXI4Lx6Fg0TbypmA6FK3LRetSIqYwwWjwFTnm
-        djWQy8KwyCoJBpEDHWGr8XO8+QUAAP//AwCbr2StSQEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f4cbaa263139-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:13:21 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '977'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89866'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 88ms
-      x-request-id:
-      - 2456b7f24102cba0f3376a140d9ba536
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"Since I need to write
-      a specific text into a file, the write_to_file command is the most appropriate
-      one to use.\",\n        \"plan\": \"- Use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\\n- Use the task_complete
-      command to complete the task.\",\n        \"criticism\": \"I need to ensure
-      that I am using the correct file name and that the text is written correctly.\",\n        \"speak\":
-      \"I will use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\":
-      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
-      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
-      write_to_file returned: File written to successfully."}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4667'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSQY/aMBCF7/0Vo7lwMSgUFqrceitt1VZbqh42FTLOkHhx7MieLCDEf69MkmWX
-        bSu1vc6M33zPb46oc0xRlZJVVZvhfHH78Gm+/PD23t3ODuWNy3frL7zcvJ98XH5GgW59T4q7FyPl
-        qtoQa2dRoPIkmXJMx7M309lkPEvGAiuXk8EUi5qHk9HNkBu/dsNkkoxRYBNkQZgesfauqnnFbks2
-        YDpOJonAi/ilMZ8KZMfSXEqvk+lJoCqdVhQwvTtiRaEX9s4QpihD0IGl5YjpLJONFo6ZBQDIkEvX
-        FCWHDFPoil2D9hyLGS6glA8EoVGKQtg0xhxg5zUzWRi8I2McfHfe5APQlh1I2GhDYGVFOQzK2F/t
-        Yn/Eex6MYAFKWrBuB00g4JKAZdiuOssEylWVtDmwg8daPzXKUDyF9CSDs9oWLelXbdVlGHSIIhGV
-        /h5UQIT4lffc2bhEsjivsrRnCEx1t+8FNDRB2+L3Tq9N1Uba1s8Qvv33FymvWSsdqj5MS3R+STY0
-        vjXyhxU6xJhyUM57UmwO1/qhJrnttXfamH+LtZU8if4uu/EXZxnTarc9k7+Ckr64vuinB9MKLGM2
-        vUD+LONHoDNUx5bZE54EbrTVoVy1SphiYFejQG1z2mOanH6cXv0EAAD//wMAOXgyaFoEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca8f4d2ed7d3139-SOF
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:13:33 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-gsghk4kr5xmbjprowdzr8zt2
-      openai-processing-ms:
-      - '12475'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86479'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.347s
-      x-request-id:
-      - 85392cbd30db94e28752659a98e23706
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
-      Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
-      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
-      GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
-      \"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
-      \"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
-      str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
-      \"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
-      \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
-      Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
-      access for searches and information gathering.\n2. Long Term memory management.\n3.
-      GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
-      Evaluation:\n1. Continuously review and analyze your actions to ensure you are
-      performing to the best of your abilities.\n2. Constructively self-criticize
-      your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
-      to refine your approach.\n4. Every command has a cost, so be smart and efficient.
-      Aim to complete tasks in the least number of steps.\n5. Write all code to a
-      file.\n\nYou should only respond in JSON format as described below \nResponse
-      Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3467'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7STz27TQBDG7zzFaC65OFFC2iT1ExCEWqAFhDCytuuJvcTeMbvjJijyuyP/SdIY
-        9QScVppv5pvf7M4e0CQYos6U6KLMx8v1/e2T0p/f36YfVh/5/m579fbu3fRhtf6qPAbIjz9IS18x
-        0VyUOYlhiwFqR0oowXC2WF0t5vP5chZgwQnlGGJayng+uR5L5R55PJ1PZxhg5VVKGB6wdFyUEgtv
-        yXoMl8tFgGfvU/z17DpAYVH5KXRzM6sD1BkbTR7DbwcsyB9tHeeEISrvjRdlpYFkK2SbAQ6RBQCI
-        UDKu0kx8hCH0wV6gvTTBCNewM3kOlSeQjGDnjFAsHG9MTqC5KJRNQLgTYPSG8pzhC7s8GYGxwqCg
-        TbWqoARGWaPHu0afyF5GkwiD540dKc/W2LTr/pARiPJbcPSzMo48FPQX3QJoaV+cw/hWLNgLqLJ0
-        XDqjhGDDDiRrVOW3Q+QyV7ajHcOn/3ZNkT27NxRxvyQX7qfYMWvIqp0Ro40vjo9ridpKsr5yTZ0S
-        WEOmnjoPzc6RljNbf4FKWrkNGw/9/oOxF1WJaQ52v4YYviS1fXm/GqB/t19d4zo4Ln1v+sfONw4d
-        08XrDdCVS4ffpROa3LPFgOPCZPjFns10pG2Je/DI1lgHuDHW+CzuPgiG6IVLDNDYhPYYTuvv9avf
-        AAAA//8DANPpphvSBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca920092efb0c34-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:43:08 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '17065'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86497'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.335s
-      x-request-id:
-      - 90577bd1f9895f3d042b1a9287fa5f73
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
-      Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
-      args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
-      GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
-      \"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
-      \"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
-      str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
-      \"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
-      \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
-      Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
-      access for searches and information gathering.\n2. Long Term memory management.\n3.
-      GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
-      Evaluation:\n1. Continuously review and analyze your actions to ensure you are
-      performing to the best of your abilities.\n2. Constructively self-criticize
-      your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
-      to refine your approach.\n4. Every command has a cost, so be smart and efficient.
-      Aim to complete tasks in the least number of steps.\n5. Write all code to a
-      file.\n\nYou should only respond in JSON format as described below \nResponse
-      Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
-      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
-      command is the most appropriate for this task.\",\n        \"plan\": \"- Use
-      the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\\n-
-      Use the task_complete command to complete the task.\",\n        \"criticism\":
-      \"I need to ensure that I have the correct file name and that the file is created
-      in the correct directory.\",\n        \"speak\": \"I will use the write to file
-      command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4790'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6ySTW/TQBCG7/yK0Vxy2UQJIWnwEYlCqkpFUIRUjKLtehIvWe+Y3TFJFfm/I8fO
-        R4OQkOA6H+88M/Pu0GaYoMm1mKJ0/av5p7vr+7fTh+ub4c3dx3e3byrzYaZ5ph+eblEhP34nI13H
-        wHBROhLLHhWaQFoow2Q0nb2ajsfj1yOFBWfkMMFVKf3xYNKXKjxyfzgejlBhFfWKMNlhGbgoZSG8
-        Jh8xGQ0nM4Un8VNicqVQWLQ7hV6OJrVCk7M1FDH5usOC4kE4sCNMUMdoo2gvDSZ7Id+ssEs9AECK
-        knO1yiWmmEAX7BK0lSaY4hw21jmoIoHkBKLjetEBEhguCu0zEIZj7FA1SFGdSwbSkb31q1b3viuD
-        QD8qGyhCQY3OJlgh6L0n5xi+cHBZD6wXBg1L6wi8LiiDXt7kF5smP5Ct9BQ0HHPI9U+CWBlDMS4r
-        556OYBlIbmOLBvc5BVpyIAVzMNr/h/1Kp327Wh8+/7OaCVassbE4fMET7TvJxyo0fVr2ze1ZYcmh
-        PefJPGAj6LIMXAarhS4nxJL0+o8/hr+lbiVrdbBUV/6bo5q/tdOeHeUCSofVpRnP3dNZ55wve/bt
-        I9AeqmNLfY21wqX1NuaLVgkTjMIlKrQ+oy0mw/pb/eIXAAAA//8DAKgaLA4VBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca920871f130c34-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 01:43:24 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '13071'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86478'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.348s
-      x-request-id:
-      - 137423c120d49f49824a2fbbd7cbb558
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3393'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTT2/TQBDF73yK0Vxy2URJ0/zBRyoBEQL1UIQKRtHWnsRLdnfM7phEivzdK9tJ
-        2hpxQnCdN37vN7PjI5ocE8wKLZkr7XCxuru9f1PZ6+qde6tvPn74db843Mw+XX3d21tUyA8/KJPT
-        F6OMXWlJDHtUmAXSQjkmk/nyej5dTCdzhY5zspjgtpThdDQbShUeeDiejieosIp6S5gcsQzsSlkL
-        78hHTBazpcIn70v9ajxWKCzaXkqvZ8taYVawyShi8u2IjuLZNrAlTFDHaKJoLw0keyHfDHBMPQBA
-        ilJwtS0kppjAqXgS6CBNMcUVeKIchKGKBFIQ7IMRWguvN8YSZOyc9m1DK8DgPVnL8IWDzQdgvDBo
-        aFu9dpTDoGj09b7RR3KQwShF9Tw7kI7sjd92AHcFgei4g0A/KxMogqO/SFPQ0v5xDhNb0XEU0GUZ
-        uAxGC8GGA0jRqDru+sil1b6jHcLn/7SmLBgxmYmu/07kYxUaBi2wurxaxiFQJm1Ek9CtgQ7yhCTc
-        djYd/bBYkt6dg/bG2n95DV1wrc5XejL97Ugbh47pBUQPXYdt/7474byJzqLH8cKk/088m+lM2xKf
-        wFNfY61wY7yJxbo7Z0wwCpeo0PicDpiM6+/1q0cAAAD//wMAx8X8+IMEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca9805e4d7328e0-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:48:51 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '14375'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86497'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.335s
-      x-request-id:
-      - dd442d3790e304394237402085fd3bc5
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
-      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
-      command is the most appropriate for this task.\",\n        \"plan\": \"- Use
-      the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I need to ensure that I use the correct filename and text to write to the
-      file.\",\n        \"speak\": \"I will use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4637'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7RSwY4SQRC9+xWVunAZCOzILpmbFyOHTUwWo0YM6e0pZlp6utruGsAQ/t00zMi6
-        sheN13qvXr3X/Q5oSixQ10p04+3wbr547x+mn+/X929pnHPc3dWfHt5ow7Npgxny4zfS0m2MNDfe
-        khh2mKEOpIRKLCa3s9e3+V2e5xk2XJLFAisvw3w0HUobHnk4zscTzLCNqiIsDugDN15WwhtyEYvJ
-        +Gaa4UX8AszyDIVF2cvoZjw7ZqhrNpoiFl8O2FDshQNbwgJVjCaKcpJsshNyKcJh6QAAlig1t1Ut
-        cYkFdMMOoL2k4RLnUKstQWy1phjXrbU/YBeMCDkYvCNrGT5ysOUAjBMGBWtjCZxqqIRBnfDVLuEj
-        2ctgBIuawNFeIAp5MBGEoY0EUhOIiptVF55Ac9MoVybCr1nPGi0xe2o3kIrsjKvOnhcdDQJ9b02g
-        CA1d1QG1FgqnPMZV1/IkZkqUwcnLiy5Tkpqg4SigvA/sg1FCsOYAUif0im1vlTs7HsKHf34EnVJo
-        E5v+4xzRaZNcbEPaUwJz8IG3piRQsFXWlHB+u5PRvniuevFI9KQ2/YGdsfbvfu8secz6Inb0P3qY
-        enS+9pv8M1MqVM8r/LQX/6PIfYRTjC7N0h3xmOHaOBPr1fk2FhiFPWZoXEl7LMbHr8dXPwEAAP//
-        AwCEJsUGfQQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ca980c86e2128e0-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 21 May 2023 02:49:08 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '14391'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86481'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.346s
-      x-request-id:
-      - 7efa7a4b949a3c79b750abf348c98545
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3391'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTT4/TMBDF73yK0Vx6cauWbrslR5DQLtWeoFohgiqvM21MHU+wJ2q1Vb47StI/
-        u0GcECi3eeP3fmNPjmgzTNDkWkxRuuHtp4fl8yp/X3q7XH1+vlt9/PBVT+c3y8njwxwV8tMPMnI6
-        MTJclI7EskeFJpAWyjCZzBc3zTebKiw4I4cJbksZTkezoVThiYfj6XiCCquot4TJEcvARSlr4R35
-        iMntbKHw6n2pvx2PFQqLdpfSu9miVmhytoYiJt+OWFA82wZ2hAnqGG0U7aWBZC/kmwGOqQcASFFy
-        rra5xBQTOBVPAh2kKaZ4D54oA2GoIoHkBPtghdbC6411BIaLQvu2oRVgcEfOMTxycNkArBcGDW2r
-        1wVlMMgbfb1v9JEcZDBKUb3MDqQje+u3HcCXnEB03EGgn5UNFKGgv0hT0NL+cQ4bW1GXZeAyWC1X
-        acMBJG8adNz1qUunfQc8hNV/uikTrFhjY9F/KvKxCg2DFri/PJzhEMhIG9EkdDdBB7kiCbedTUc/
-        LJakd+egvXXuXy5EF1yr86KeTH/b08ahY3oF0UPXYdtf8U4430Rn0eN4ZdL/LV7MdKZtiU/gqa+x
-        Vrix3sZ83W00JhiFS1RofUYHTMb19/rNLwAAAP//AwD1Vl/5hgQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cbda3126a192318-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 23 May 2023 13:27:57 GMT
-      Function-Execution-Id:
-      - f495bweu71bh
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '23528'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 42fdfa1f232dd8dd51141935679ce725;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86497'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.335s
-      X-Request-Id:
-      - c4fdd30b1aa4a8c36dd882aa35dfae44
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
-      to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
-      command is the appropriate command for this task.\",\n        \"plan\": \"-
-      Use the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I need to ensure that I use the correct filename and text to write to the
-      file.\",\n        \"speak\": \"I will use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4638'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7RTyW7bMBC99ysGc/GFFmRlaaFbWwRtuqAokqAFqsKgqbHEmiIVcmQ7MPTvhbYk
-        TRegG3QRZt68hRweUOeYoiolq6o288ev3r55f3Xxcff6hXyaxO/OjuX1s5V8rrZJfIYC3eoLKR4n
-        IuWq2hBrZ1Gg8iSZckwXp0+O+y8WWLmcDKZY1Dw/ik7m3PiVm8dH8QIFNkEWhOkBa++qmpfsNmQD
-        pos4ORF4R37bSOKFQHYszR02SU5bgap0WlHA9NMBKwoTsXeGMEUZgg4sLXc2nWWyXYRDZgEAMuTS
-        NUXJIcMUxuLYoD13xQzPoZRbgtAoRSGsG2NuYOc1M1mYvSRjHHxw3uQz0JYdSFhrQ2BlRTnMyq6/
-        3HX9iPc8i+CyJLC0ZwhMNegA7KAJBFwSsAyb5RieQLmqkjbvALe1CRVlKO7b9SSDs9oWg+fLEQae
-        rhvtKUBFHU/nm37fNfQ2SrI/MAIX2iqCX50Sux7eKYj+79/nr420Q/Q5XP01m/KatdKhmjbAEvWT
-        ZEPjuznJcA61d1udE0jYSqNzGC4B1s5PEtoWPxUJNcnNJLDTxvzZMQyUrZg2eoR/t9Dd1Q5q39A/
-        MCV98fAt3F+w//Eipgh9jDFNZltsBa611aFcDtqYYmBXo0Btc9pjGref20dfAQAA//8DADOKIi/G
-        BAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cbda3bbfbeb10df-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Tue, 23 May 2023 13:28:24 GMT
-      Function-Execution-Id:
-      - f495jhtvkzjb
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '24141'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 1d5139fa1fd8c86452a62084086df67c;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86481'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.346s
-      X-Request-Id:
-      - f55c4da18a3d1ef16ef64b7b36e3afcd
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3481'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
-        with other requests. You can retry your request, or contact us through our
-        help center at help.openai.com if the error persists. (Please include the
-        request ID 1d08452a41f33bf54874f93bf2a716de in your message.)\",\n    \"type\":
-        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cca53eb28d702ac-ORD
-      Content-Length:
-      - '349'
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 02:25:56 GMT
-      Function-Execution-Id:
-      - rvr2i8vhq9vo
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '30015'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      X-Cloud-Trace-Context:
-      - 69c7b246f231d9cbd0c2974c332ebc51;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86499'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.334s
-      X-Request-Id:
-      - 1d08452a41f33bf54874f93bf2a716de
-    status:
-      code: 429
-      message: Too Many Requests
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3481'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTTW/TQBCG7/yK0VxycaKE0DbxDQ6orTgAKioSRtbGHtvb2Dvu7pikRP7vlb+S
-        xqgnBNf5eN9ndmcOqGP0McqUREWZT69uq6fFJ/P+w+P3eWKf3P31l4+fv5pbfvhtEvSQNw8USd8x
-        i7gocxLNBj2MLCmhGP3F5erderW4uFx7WHBMOfqYljJdzi6mUtkNT+fL+QI9rJxKCf0DlpaLUkLh
-        LRmH/tVq7uFJ+xh/u1h6KCwqP4bW62XtYZSxjsih/+OABblB1nJO6KNyTjtRRhpINkKmGeAQGACA
-        ACXjKs3EBehDH+wTtJcmGOAN7HSeQ+UIJCPYWS0UCoeJzgkiLgplYhDuEjC5pjxnuGebxxPQRhgU
-        tKVGFRTDJGvy4a7Jz2Qvk1mA3ktjS8qx0Sbt3O8yAlFuC5YeK23JQUF/4wZ3r86gXTtgwU5AlaXl
-        0molp3zCFiRrqpTbjrHLXJmOeArf/tlTBeak3lCE/aKcqR9jQ9WYNbJadKRdMXywIWo7ybjKNn1K
-        4AYy9avTiNhaiqRla9CgNaK9wIYStgSV0yZ9feSxvytJbf/XcnXGtTdsfC/6x8I3Ch3TGcQIXdl0
-        fCtdYnibTmLEcSYyvq8XMw20LXEPHpgaaw8TbbTLwu460EcnXKKH2sS0R39e/6zfPAMAAP//AwBM
-        TWg3zwQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cca54f8fd85111e-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 02:26:34 GMT
-      Function-Execution-Id:
-      - rvr2pyuh5pu6
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '25106'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - bb40fcb7f86d47a999346b879f520f53;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86499'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.334s
-      X-Request-Id:
-      - 03d492530fb90d6815d8d49a68ab49b4
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      download_file: Download File, args: \"url\": \"<url>\", \"filename\": \"<filename>\"\n4.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n5.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n6. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n9. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n10. list_agents: List
-      GPT Agents, args: () -> str\n11. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n12. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created and nothing new has happened."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I will use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"The task requires me
-      to write ''Hello World'' into a file named ''hello_world.txt''. The write_to_file
-      command is the most appropriate command for this task.\",\n        \"plan\":
-      \"- Use the write_to_file command to write ''Hello World'' into a file named
-      ''hello_world.txt''.\\n- Use the task_complete command to complete the task.\",\n        \"criticism\":
-      \"I need to ensure that I have the correct filename and text before using the
-      write_to_file command.\",\n        \"speak\": \"I will use the write_to_file
-      command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4801'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SST4/aQAzF7/0Uli9cAoIu7EJurSrUrdpeSrWHpkLDxEmmzIzTGUewQnz3KhD+
-        lG5Pe/Wzf/PseTs0OaaoKyXa1bb/8Kl5XsznrtEf5t/e5++Kz266Wsyar5vHL2tMkFe/SEs3MdDs
-        akti2GOCOpASyjEd3U/Hs+loMntI0HFOFlMsa+nfDSZ9acKK+8O74QgTbKIqCdMd1oFdLUvhNfmI
-        6Wh4P0zwAr8Ik3GCwqLspfR2NN4nqCs2miKmP3boKJ7AgS1hiipGE0V5aW2yF/LtCrvMAwBkKBU3
-        ZSUxwxS6YifQVtpiho+wMdZCEwmkIhAV18vOIIFm55TPQRjOtVPXIMPkGhlIRfbGl0fuomuDQL8b
-        EyiCo5azCUYIeh/JWoYnDjbvgfHCoKAwlsArRzn0qlZfblp9IFvpwcFGRf4FI7D4r3ETD22Oo4Cq
-        68B1MOpKLziAVG3XCxvVVvnjMn34/ur76GDEaBPd6e6e6DBJPjahnVNyHm6Nn4krKjgQxKoRMb6E
-        nDf+lh5rUuvX/+gRuU9OAera/8lP+0vH1/7C35hSobyN3nVWuqC0654AOcRGa4qxaKx9Phs6mOq8
-        ZX6P+wQL402slkcSphiFa0zQ+Jy2mA73P/dv/gAAAP//AwBuG68bAwQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7cca55aa8ee7e100-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 02:26:53 GMT
-      Function-Execution-Id:
-      - rvr2qsuver9b
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '15614'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 0b238e84f74b403e164b93d247259c70;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '84695'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 3.536s
-      X-Request-Id:
-      - b1fb38bd412977a3cd85ec84fbdd44d0
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\nThe OS you are running on is:
-      Windows-10\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello World''
-      into a file named \"hello_world.txt\".\n2. Use the task_complete command to
-      complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3433'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7yTTW/bMAyG7/sVBC+5KEHidkvi2zbsI7sW+wDmIVBk1lYjS55EIx6C/PdBdtym
-        LtANGLArSb/v89LUEXWOKapSsqpqM11+au/eXOsv3+Sv98tk965wefs60R/q5ObtDgW63R0pPn8x
-        U66qDbF2FgUqT5Ipx3TxanW9XieL1UJg5XIymGJR8/Rq9nLKjd+56fxqvkCBTZAFYXrE2ruq5i27
-        PdmA6XI5F/igfV9PFolAdizNfWm9Sk4CVem0ooDp9yNWFAZZ7wxhijIEHVhajpDOMtkY4JhZAIAM
-        uXRNUXLIMIVz8dyglmMxww1YohzYQRMIuCQ4eM20Zbe91YZAuaqSthvoGjD5SMY4+Oq8ySegLTuQ
-        0I1aWVEOkzL2t4fYn3HLk1mG4tLbkwzOalv0ADfaqt6YZdiDp5+N9hSgor/wFLCBgzbmefjZMFXL
-        ELqx2I24IMNTYOjyRiBquZu4tB/HqY20fZIpfP5PK1Res1Y6VON/SDY0PjJIhs1DXOW8J8UXsSNO
-        TMfumbWNXENNcj84/nnr/5a3Nz6J4ZTPok8uOSr0TI8gRujSF+NH0DeGjfQSI45HIuOHc5FpoO2I
-        z+CZPeFJ4K22OpTb/uYxxcCuRoHa5tRiOj/9OL34DQAA//8DACqjUZ+oBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ccb58103e2be73a-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 05:23:27 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '25366'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86499'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.334s
-      x-request-id:
-      - 754502cb0f1f1266c1f1e1f7bc9b7b6b
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\nThe OS you are running on is:
-      Windows-10\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello World''
-      into a file named \"hello_world.txt\".\n2. Use the task_complete command to
-      complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I need to use the write_to_file
-      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"reasoning\":
-      \"Since the task requires me to write ''Hello World'' into a file, I will use
-      the write_to_file command. I will pass the filename as ''hello_world.txt'' and
-      the text as ''Hello World''.\",\n        \"plan\": \"- Use the write_to_file
-      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I need to ensure that I pass the correct filename and text to the write_to_file
-      command.\",\n        \"speak\": \"I will use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"hello_world.txt\",\n            \"text\": \"Hello World\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4714'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6ySTW/TQBCG7/yK0Vx62VROWlriW09tQXAASg8YRZv12N5mvWPtjkmqyP8dJbaT
-        EpCQgOs7M+8887FFm2OKptJi6sZNrt9unvJ3SSPvi6L4uL411w/mxtS3X57vljeokJdPZGSoODdc
-        N47EskeFJpAWyjGdXr25nM9ns2SusOacHKZYNjK5OH89kTYseZJcJFNU2EZdEqZbbALXjSyEV+Qj
-        ptPkcq7waH4MXE0VCot2R2k2TTqFpmJrKGL6dYs1xdE4sCNMUcdoo2gvO0z2Qn43wjbzAAAZSsVt
-        WUnMMIVBHAK0kZ2Y4Qdeg1Ra4B4q/Z1gHawIeTi7I+cYHjm4/AysFwapCArrSME9eKIchKGNtNdF
-        x9ViGIzAcF1rv084aGPWeYbqJUogHdlbX/Y8n6w3NMKMxfmhGrjYI1pf/glxbZ37D3yN075Hm8DD
-        P7uZHbuxse4tj4skH9tA4ykaHePew3AIZAT6LcEw4m/7n7aKDenV2Obvl9Fbdmr8qSH9l5fyuqa+
-        20/2J1A6lKff+PINeoPPu0Mfbx9bYyjGonXu+QC0hxrYMt9hp7Cw3sZq0TthilG4QYXW57TBNOm+
-        da9+AAAA//8DAFX+S9wWBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7ccb58bf8a30e73a-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 05:23:51 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '21630'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86485'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.342s
-      x-request-id:
-      - 22f487f4ffb66999eb1baab18655bc17
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
-      command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
-      Use the task_complete command to complete the task.\n3. Do not use any other
-      commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
-      short term memory is short, so immediately save important information to files.\n2.
-      If you are unsure how you previously did something or want to recall past events,
-      thinking about similar events will help you remember.\n3. No user assistance\n4.
-      Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I need to use the write_to_file
-      command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"reasoning\":
-      \"The task requires me to write ''Hello World'' into a file named ''hello_world.txt'',
-      and the write_to_file command is the appropriate command for this task.\",\n        \"plan\":
-      \"- Use the write_to_file command to write ''Hello World'' into a file named
-      ''hello_world.txt''.\",\n        \"criticism\": \"I need to ensure that I use
-      the correct filename and text to write to the file.\",\n        \"speak\": \"I
-      will use the write_to_file command to write ''Hello World'' into a file named
-      ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\": \"write_to_file\",\n        \"args\":
-      {\n            \"filename\": \"hello_world.txt\",\n            \"text\": \"Hello
-      World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command write_to_file
-      returned: File written to successfully."}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4608'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7RSy27bQAy89ysIXnyRDTuGnVhfUCOHFoiLBqgKY7Oipa1XXHWXip0a+vdCLyhN
-        XwjQ3hYccjjDnQuaFGPUuRJdlHZ6fbtxUu5MOHx72vo7qdanbHl9f3/1jm/fY4Tu4Qtp6Sdm2hWl
-        JTGOMULtSQmlGC/WN6v58ma9XkZYuJQsxpiVMl3OVlOp/IObzpfzBUZYBZURxhcsvStK2Ys7EgeM
-        F/PFJsKRfAQ26wjFibJj6WqxqiPUuTOaAsafLlhQGIi9s4QxqhBMEMXSyHQsxI2FS8IAAAlK7qos
-        l5BgDH2xB+gsTTHBLeTqkSBUWlMIh8raJzh5I0IMk7dkrYOPztt0AobFgYKDsQSsCkphkjf4/tTg
-        MznLZAa7nIDpLKBdUShOQRxUgcAEEBWO+947NfXxnVOLzhKMnqv0pIJjw1kndde3gaevlfEUoGh5
-        Grn0erHQysuJfyEE7gxrgj8dR1zb3myI2tc/s11axZ3jKXwIY9/I8mzLX9m0N2K0CcXw30zUThKH
-        yjdzSmALpXePJiVQ0F0dDs4P5Iaz39KHktRxoD4Za1vfr5bcUdbRkNy+/afgNn/ZbfuB/oUo5bOX
-        mX+eqP+R/MFCa6N3k3CNdYQHwybk+243xhjElRih4ZTOGM/rz/Wb7wAAAP//AwDKh13FrgQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc6e12bd2e1ef-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:18:06 GMT
-      Function-Execution-Id:
-      - yvvlex8job2h
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '22621'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 827e911ff253a9d12783cb62e669dc20;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86005'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.663s
-      X-Request-Id:
-      - 4d357db894485be6e259654a899f2e57
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Hello World\"\"\"\n\n\nCONCISE
-      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
-      0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '252'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBQG7/6K8J03JSVpmu7RU7GIXooHK2WbvCarm33L7qsoIf9dClqvAzPM
-        BNtBox2MtGNw+Xq3CQ9DXFfPj09Oim5Xu+3+u9oO+/tPhgKf3qmVX2PR8hgciWUPhTaSEeqgl3Wz
-        KsqmbjYKI3fkoNEHycvFKpdLPHFelMUSCpdkeoKeECKPQY7CH+QTdFkr/KdvuFEQFuNuoKpmhXZg
-        21KCfp0wUvpLRnYEDZOSTWK8XAfZC/nrvMmSveazPhKJ9X3G5+yALTnH2QtH1y0OwKxwtt6m4RjJ
-        JPbQSMIBCtZ39AVdzG/z3Q8AAAD//wMAv00f4UIBAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc7839fad10e3-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:18:11 GMT
-      Function-Execution-Id:
-      - pbme9het6dvt
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1227'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 4a9b8edee07c9658c887ffc760c711e6;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89466'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 356ms
-      X-Request-Id:
-      - fb5593e05606c34e2e9461ff82b28747
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\nThe OS you are running on is:
-      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
-      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
-      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3441'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA7ySQW/bMAyF7/sVBC+5KEGCLE3j+4YFQ4thxVBgcxGoMmNrlURDotcAgf/74DhJ
-        Gw8bdtmufNR7H0Xu0RaYoam0GF+78fLj+uY2rVYmflrexdv3/se9TjsJ8fPXdzeokB+/k5Hji4lh
-        XzsSywEVmkhaqMBsdnW9mC5nb1czhZ4LcphhWct4PlmMpYmPPJ7OpzNU2CRdEmZ7rCP7WjbCTxQS
-        ZsvlQuGL97k+W80VCot259Lq6rpVaCq2hhJm3/boKZ1sIzvCDHVKNokO0kFyEArdAPs8AADkKBU3
-        ZSUpxwyOxaNAO+mKOa4hEBUgDE0ikIrgOVqhjfBmax2BYe91ODQcBBh9IOcY7jm6YgQ2CIOGQ2vQ
-        ngoYVZ2+ee70iexkNMlRvc6OpBMHG8oe4M4G0weXrB3Y9BdR6g+gnUFF4DkJ6LqOXEer5WKQJtEQ
-        qnY69Dxj+PKfPsJEK9bY5IeboJCa2DFogfV5L4ZjJCOgY9l4CpJgy/H3oMO0VJN+OiU9W+f+5cL7
-        4FadDvFo+ssddg490wXEAF3HcnjCvdD1vlgMOC5Mhmf/aqYT7YH4CJ6HFluFWxtsqjb9xWKGSbhG
-        hTYUtMNs2j60b34CAAD//wMA1PnFsWYEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2e853ad25e702-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:25:14 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '23538'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86502'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.332s
-      x-request-id:
-      - 6a8a3cf2a18b70df31c5e47f66614c59
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are write_to_file-GPT, an AI designed to use the write_to_file command to write
-      ''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
-      command to complete the task.\nYour decisions must always be made independently
-      without seeking user assistance. Play to your strengths as an LLM and pursue
-      simple strategies with no legal complications.\nThe OS you are running on is:
-      Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the write_to_file command to write ''Hello
-      World'' into a file named \"hello_world.txt\".\n2. Use the task_complete command
-      to complete the task.\n3. Do not use any other commands.\n\n\nConstraints:\n1.
-      ~4000 word limit for short term memory. Your short term memory is short, so
-      immediately save important information to files.\n2. If you are unsure how you
-      previously did something or want to recall past events, thinking about similar
-      events will help you remember.\n3. No user assistance\n4. Exclusively use the
-      commands listed below e.g. command_name\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read a file,
-      args: \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\",\n        \"reasoning\": \"Since the goal is to
-      write ''Hello World'' into a file, the write_to_file command is the most appropriate
-      command to use.\",\n        \"plan\": \"- Use the write_to_file command to write
-      ''Hello World'' into a file named ''hello_world.txt''.\",\n        \"criticism\":
-      \"I need to ensure that I use the correct arguments for the write_to_file command.\",\n        \"speak\":
-      \"I will use the write_to_file command to write ''Hello World'' into a file
-      named ''hello_world.txt''.\"\n    },\n    \"command\": {\n        \"name\":
-      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"hello_world.txt\",\n            \"text\":
-      \"Hello World\"\n        }\n    }\n}"}, {"role": "system", "content": "Command
-      write_to_file returned: File written to successfully."}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4626'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SSS48TMRCE7/yKVl9ymUTJZkNgjiAhIsQBsWh3xaDI8XRmTDxuy+7ZBEX572ge
-        eZAViL1ZXfbnKrv2aHJMUZdKdOXtcP5p8dmVt8bfe/u+fPc03SzuHj48mi+TB0+YIK9+kpb+xEhz
-        5S2JYYcJ6kBKKMd08vrNbDyfzCbzBCvOyWKKhZfhdDQbSh1WPBxPxxNMsI6qIEz36ANXXpbCG3IR
-        08n45m2CZ/hZmN8mKCzKnkc34+khQV2y0RQx/b7HiuIRHNgSpqhiNFGUk8YmOyHXRNhnDgAgQym5
-        LkqJGabQD3uBdtIMM7wrCRztBDRXlXI5CEMdCUwEUXGz7M1SMz+vS2rVUYbJJTaQiuyMKzr2V+N0
-        t7lgZVskwzYYIRh8JGsZ7jnYfADGCYOCtbEETlWUw6Bs9OW20UeykwG03vp7oVQRVkTuZClPTuLZ
-        8jFSc3FJUHEUUN4H9sGoC72LfB3GW+W6HEP4Fukf/P95Gh2MGG1i1SEX4Ijak+RiHZpzSmABPvCT
-        yQkUdG8Jaw5HuHHFX/HRk9oc0VtjbfuJL7bcIQ/JsUD99mf9aT6pu+0P/JUpFYrr6l325FzA9k95
-        3XajSfnydjwvBMRaa4pxXVv76xStjdenzNwBDwmujTOxXHaeMMUo7DFB43LaYTo+/Di8+g0AAP//
-        AwDeKpjwTQQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2e8f7bfaee702-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:25:40 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '23218'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86010'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.66s
-      x-request-id:
-      - 29a5d0f069d62474b048ab97ae6b614d
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
deleted file mode 100644
index cc0a43be..00000000
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
+++ /dev/null
@@ -1,3349 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3284'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
-        with other requests. You can retry your request, or contact us through our
-        help center at help.openai.com if the error persists. (Please include the
-        request ID b6a7095cc0e76b9901aecd234de4f5b4 in your message.)\",\n    \"type\":
-        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc7929fefe287-ORD
-      Content-Length:
-      - '349'
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:18:42 GMT
-      Function-Execution-Id:
-      - yvvl1pjqkaam
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '30015'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      X-Cloud-Trace-Context:
-      - 92320c9bf2c16a55143abddee3e4aa6f
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86494'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.336s
-      X-Request-Id:
-      - b6a7095cc0e76b9901aecd234de4f5b4
-    status:
-      code: 429
-      message: Too Many Requests
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3284'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSTW/aQBCG7/0VoznbCAsFiG/NqVHUA1KiqqortKzH9ob9cHfHBQf5v1cbQ5JC
-        xaXX+Xqfd2YOqErMUTaCpWl1uni4bV++3s2bpy8Pptyult9+fZ+v7lbb5/7xNyboNs8k+dgxkc60
-        mlg5iwlKT4KpxDybL2+ms+ViliVoXEkac6xbTmeTm5Q7v3HpdDbNMMEuiJowP2DrnWl5zW5LNmC+
-        mE0TfJ/9Fs/mWYLsWOi30PI2GxKUjVOSAuY/DmgonMZ6pwlzFCGowMJyhHSWyUYDh8ICABTIjevq
-        hkOBORyDxwTtOQYLvIfQuE6XEFh4hk0PnkSpbA3cECgb2HcyooZ1NuE9Q6U0ATsoickbZQl2jWAQ
-        Y1HMsNgSWNrzpMDko6onEZxVth6lH68IRDNCxXlNnCWjc9+DspXzRsTyvxnGsj1DYGrDuXCrhR01
-        U3gKY3W0uT5qGSNsGQfG4DXjRWFT+GyF7l/oou4a0RmQ9IqVVMGcjmCJXgHIhs7HZsFwD8JA5bR2
-        u3/dA4SUnRdMuoeIT1WlpCLLuj/3H1oS25PUTmn9H9e+2PQoNCSnpzuu8+LnrDA0Mryt/gxT+Pr8
-        VcdErH1vv8Q8QbyCHHkKO+CQYKWsCs16fD3MMbBrMUFlS9pjPh1+Dp/+AAAA//8DAKcjlwMpBAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc8867f9a2304-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:09 GMT
-      Function-Execution-Id:
-      - pbmesm0aoa9z
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '18581'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 244d650faeed742e67c771ab39ea3909;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86494'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.336s
-      X-Request-Id:
-      - bd98d60ec0822b964eb683bbb670db8f
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"This task_id
-      is 2314 Read the file instructions_2.txt\"\"\"\n\n\nCONCISE SUMMARY: The text
-      is best summarized as"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '294'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOzWrCQBRG932K4VtPQn7U2FmWSiuuSlu6KEXGydWMJjNp7hUFybsXobXbA+dw
-        LvA1DFxjxXV9m1Sr++/Vgnnz8XRoqmqxeCuWp339/tC/vD5DI2725OTXSF3s+pbExwANN5AVqmHy
-        2XyalfNqWmh0saYWBrtekjKdJnIcNjHJyiyHxpHtjmAu6IfY9bKWeKDAMJO5xn/6hvOZhkSx7Y3M
-        JqOGa6J3xDCfF3TEf80htgQDy+xZbJDrYQxC4XpvlVg+qJOXRi0fVVHmEyVRDWRrJQ2prW9J+cAy
-        HN31gddFKmdJMWpsffDcrAeyHAMMWGIPDR9qOsNk49d49wMAAP//AwAqXzViVgEAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc90cfd676375-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:14 GMT
-      Function-Execution-Id:
-      - yvvl4c81ashb
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '2097'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 6232341524f6b478562ccd013bfb5708;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89456'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 362ms
-      X-Request-Id:
-      - 598ef1969eede681b5f5554e147d12e7
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["This task_id is 2314 Read the file instructions_2.txt"], "model":
-      "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '132'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6XQ+6Orfn/fMpdvYt80RApGXfISggLy0Cok4mE0BEQUBeWqAn57uf4H9yZubG
-        RFpC2q61fi+r//Gvv/76u03LPBv//uevvz/vYfz7f6zPHsmY/P3PX//zX3/99ddf//H7/f9m5nWa
-        Px7vpvhN/w2+m0c+//3PX/x/P/m/k/7562+tbgTCX7NTTz5wyiE7+BFZ/N3oTPl718IbeCJ6lMJb
-        Ol2FuoOhNCrU3t/P5ZJ2ywLl+s2oxx+TfhCgJwIopBesY2diEwgEH55Sc0aT4vb9IlmEgxE079gU
-        TT2dAGgD4EqOSyTmn9JpMesMenkyU61pwrQPmqmDY3R3ifActZSVofqGWu8M1BLNvp9JNIjQvSAD
-        o7yQHYbmhof37O1Tl3hvNvWcxYHvXLyxrtVdSL3hHSs0tQ9k4+tD2Ytu84ZKnF+JfGUvNtOxt0BZ
-        lSU2dlmeMu12kuH0tF2MoeuXE+b8FnbaCeH9NqpSJifHANxK7oxPt3MCZge8I5kE9RHdItPsZ27D
-        d4Dr6ZYau4wLZ+OCfLmj4QEN9vcYipe4tkCOH1syPF4iI08lV6F/QQ25EFtK2T05WdCxuRu2RVgy
-        +oaDBO6bR0xNTozAgjfcAG96CbCVvXVnSDrjAJVd+sC69Fh+4wRU6k3DF9fmw/kK/AqaQS6gT71R
-        9aVJ+Ag2ZTBQlF72TAzexgDvDXenJlEVsJyihw3mkO3p4UX5fqBvRhRdSBMkiee4XMBndwPwds6J
-        ZAePfjLZSYTLu66xPR33jNxeL1tZnCHCzokXwqEhag4KztapaabMmTjhiGANLjdsbw3EBAd0EXzY
-        W50ecmKGE+/INWAfTiMKLESH2UJhwXJfP6jd82dduH73lgKsrUeUG5T6gX7yHNJm+8H7I3g4MyjM
-        DB4ky6b3SyKVg5HVgRxeLAeH+AIArbcMwUMW9kQWoc7Y9vPhoVd1V4w7oICvploB1J60xO7DU4EI
-        FCPaNbcnJruplMtv7Ns8nDW6QUpx6MP5dGgR8D47Sm1tSNIhLNoWvtF2INCExGFuWKmKYB72ONzk
-        T7ZoWEDw0cQIVUItASLUOQQWrnvs2d+xX5rH1QDeB1CsC7VfTp4bqfB5yzwCVfByBtizGuqm5lCn
-        ZUO4bDwkQWd3bbCTdEO6PNtShMy/nNBHFqt0gtd9AoXQEjEOJr0UEe4zWHeGSgQhE51JzYJ8s9vd
-        IFXP10f50VQ1UFR+ayP2+uzD7TVMAmCe+RN29kedTVlmT2AE4YPUr3PlDJi7tTCM05KalrDvF1lS
-        RZjtuxsBe0wAGwrZAIa1ZX/yn+1hO0GaThPqEp7qAxNiCJvHd0HiTbT6gS0QQTvUjwSGyAGkiLME
-        GpZnIv6ze5bz4t1uwHz4Z5zG9xSwsSk4pdlcChJJoa/TDLUVPNavO5KmMkj56dtVUMwuL3p8ju+U
-        8vpFglGhfbDrdcFaD2ghH7GWUrVuff2LT6oNbQu3aKM8dykVbXcBxV71sEYlnfGSaUngVRMdH16f
-        b8+2WyUAl2DTY3RrbTZfFRbDoowbavLcsZ8dbxYhH13O2HidD86sab32O1+kzAcvXFxei8DX4t5Y
-        vbRI78TNxYe7MTIRyNBnXV/LybsRMoxz103JmM0FlP2dTFVPb3qaoaKG1vu1YHU53MBwK/gcfk8N
-        omj4Js6w1eAEDmfpg95Wfi4J3CdvOMy5ga26eoRMPqYGDFj+oMa56tjcRmcN3j74Sx721yvn1Dnb
-        8Csad7r/OoeSH3SjkJmSbaiJyiObB1BnsCn9AYnm5wIm6+wNYK+GIT2V9zFtv64bg8a9JTSDxQjo
-        fc4NcMS9ieTNyw4nTfAnxXJUngCDtToTheQN27dxxs6OkXDmNrCFpSYI1LiJbT8eiloE6lk64ENn
-        +zp58Icb3B+fInWl+A2oek41aH+DDuv6LtRZ4+8q+Llo4rpfZs8fhwQCLB0mbDH/GxJj8WzZA0VL
-        Y1ed+zEydi7kCnIk0sf89u2L1Br8DC/2y49+hmKvAQ3lDrbG98dhXeIg4N15mToRbPX50W8IfN7p
-        h3wl3tFnV21kKH1hj+2kOzjzsZI5aOGqp9o9assJ+YWtnEBh0tjaVCHRKnoT3328pYZ/fuusmg8x
-        UEcorfjEpUPS9JEcxxeTGu9kD5YQbwKQi9MTPw9NyZZ+02hAyt9vNIE20Cm29AyyYzmgieyKfjxC
-        LMF+3zzJtK6H7F6jD7YfWGLLND/h3C0RryBOPmBdmNK+Q/LsygdVKPHB/5jlthBEFUZRnWE3Kb49
-        vRMWw0qCexotaVHOQ3V/gwjkI3ZFGIWkfVoZXM+L3u/9yVmS6IpkFCQyRZ/8xZhwn3NQ7DUPW3eh
-        Z71GYx58+wCiWZMpW9b6CGdt3KApaFQwi+84gd40ujhWCWPLZXO34Os8ikRZ43V6nFgE2mNjYPvK
-        9mCp95wKK475FMv5oM8kqkRYOSmPLUv4guXGpBr8zrsysqZkZ7TESm6fIySyirDxfuh8KNFZxvbm
-        1aXTOd/4sCtFSKTp3qTDPlfQD38JlGINTHqYdaAyvDOaNrt3OXdLxkP2ujk4lbqp/DYBbWFGJoTD
-        Fx3CSStPEXh3xKHmODRgUhlNYFZGBjqHUw2mOPFqoH02J+o8+ns5w523gGufnPHePMhsDFQ7gvZk
-        QyRtNglbvpUHgcPetzX/vJQ9La+APXf4ogaeHmw5fc0ImvyM6fHzmdmcnJoFet2zRr37Gsrl8Uxc
-        QGRKkG+7n5CmZbLAeOED7KVfWk6sGBb4pFFOtbg5h9Mx0QvAo2NPpu9XSceTaXNgD6cHvnX9mw1X
-        gbQgVB2ODCueznfzqMF49G74aKnfkB1yaYHuCzQUL7rfz49AVX/rp/fg7qRLH9stvGl+ST2xNcrF
-        3xe2UhhC9sP/ctlIWQtd6eTiNIKWQywQL3JXPVtql/dL/9WuDwRHkdZ05YMplckmk3e7BKLXESjO
-        rHI5D1IKv9jV0JfNyRJMsHn0C5LMs5/Sp+W9QbZJZHp8E9yzYyn60IeGhM3TaVvSoAtvcOG+CbWi
-        VCkH8eK6EJrdQgDk034uxGUAaz3Fjvbe9u3lK/tguc4ntHydgS1cxiqw4iF2+7johynEGjjfEUXC
-        sMXltHkrCxBfXIoEr3qXSykNMZRToyOb9GLr4kOkNhDjIqCGUupsyzWlCsh1aelB2Z7SafMWJqjy
-        bo6PbynpWcu9DVjsux1Fu+fZWRLFRtDHzUhP+H3Sp1pbBsAOO5ViJz+CWbtvOGh0rxd1guMRbLvE
-        ceGzKjUExeWbzkoV1ooPMpeeiCDqDBbQApi9d6jdWRKgsIA2QJx0wCY3fAFZ6xV8i1aEs7zjy1YP
-        oxaW++pBTSyicm6juwYIaXfU018JYDC/36AB6hKr86SxZV0vRKFeY9dcSp0U4dyBiyGJ1G2VTdl2
-        H62D+lc5k754AzDfqaRCTq8QVW/PKVzxiYBHKh/xvsvHcKnqSIaWo/FkvkRqyNJi0sCQogIpk6yl
-        q97g4WuxXHwLSqT/4g1cvluINpfZB4uiKz5IUQCofs9TxlLhjSDiaYSIfr3p8wJUCUQoEuljucY6
-        qUrZkpddtiXLzenAKzqlHAB3GdMj3ovp4EyyDHtJNggTprScLhfLgPmpbWno0y6lTnkjMJrPyi8f
-        +uVt3Q1YW0lA3ZQF6VT5ogYlfrKw7lM73MYYWb/4wFpR1+kUcUMObbOG1JbNzFnsTSfD4LxQ7C1X
-        UWfbooiUvXoOcRg/SL9s9VcOlffLpWoxFYAoVFfBZygZocLhAZbp7HPK63y0ybDWe36D9AruSueK
-        jU9Knfmr7WuoP6QMe/xRLsmezw67eKgGerwGBhCse5LA6/ZpkO27Epzhdb0fZO8uytRtv6d+Wo76
-        oPhwrChWCy4ctHIfw89ijxg/nxdnxccIOtIAqDPfAjaf8qsMg+Cekh0eeGfCl7GFxySrsPEcu5IV
-        L50Hd8PvScMNJ9bt7FsMhdAWsRmll3DgzGwA8dmu6Cl7OykDzKmh5D0L6uT8Neyzsx4DuNu4+HB6
-        RIxVR7ECWD098LE/OQ4jl/MbisqtpG5x0J35YzBfWd//jet8Q9RMaW4PjKZnvKT0trd5aHwijnpH
-        /EzHW99L8DzRERtROjrTZY8DON82FTY5kWdLsqkgeHrqgUZ3tdS/S/WJQP6UPHxKuBkw7baXfnzs
-        Dx6PMoX2Tqs/AmrPyRROKUmQ/PLzfM0vmY1oOi0//YfEbtOGrA2jGNz0FyBDjO8OA1MrQupvItRJ
-        fJi2/nBC4DW8AiInPNZJ7tkLXOsxqodxAOyIXWNHlTxHSvs02NYcsQyfU7OlqvMkznha/OGHv6hR
-        k1r/bLRnLq96FJXH8NWz23Cr4arv8EH/fEJ6Ec0FDlBGJHpLSzq+GqT90Yt7QY6dL3gMAwDPMaf2
-        42Wk22mSa/Dj7/y4X1LSbxoViJKr4rugtIw9p6lQ9hfZpSdXCPSB5bYGjxdpxCEle0f84aNkBQqq
-        qsxhS9GjCpiP4Ex1T2odFkOug/zEZ/jkbh76fNkecqglLxUj6tY6s4XWkvmnNZLlKsv6mCzBAs93
-        lyLutlwAYVZqA0lIeOy4r6EfZz7QAG6yA3o9tUM5BVulBiZvlRSjL+dQtW04ALX97sd3HVa8HBHM
-        ViRRfaEkZRN7xHK5iTekUavZ6fPrgmCccipaFO2s//F3lJdUrPqlBKy2NQLUdrlQt8HAWYh3EJUV
-        T6h1FxywVAAffnqYwFPR9GO9Nd6ytUCLPnXdTsW9KIpwsE85NR52XtLhs63gMckrsnOFRW8DIeDh
-        KGSIRiQC+hAsk6Gs/Nxjk7ZNGRYAlMn+pVN3ja/JOJ5jZezamcxIe5fj1jllf+oX9mIhZPUWIPhq
-        Ykq68WaXY9j7B9g2AY+1ZXd2ZlMTebiJwi09ip8QLNvLJANCVA97pVw4w952NNgeuAQb1uaQ0t2Q
-        EaBI1pFmDQb66HKeIf/OV831b8nm08QB5yx2qHev+5K3XMuFaTcZZJe9nZBdP98B6u42oeqzUFJ2
-        uygqSEGyrH5CCUZflFp42eQCRfEx71sjq3158O8HbPf8rFfnLHvDTffKyKr/GXGd54rnNKb2o5/D
-        ytu+JtiedYzt4s36aecaCTyhm0/Pby9joxGUBTxhFVKr4YtygtfTDYiOccJe1L77cf+tWgWGB4Df
-        jmP102V4qEC6gS82OHEo6W6IBhC0vYpNeHqAOQNDAlPRxXg/14VTl+KpBuv+oo0c7fUxfic+9O4u
-        wtZjEwNh5hMNHqRFXPnOox8LUR5AOGgZ1fCF9ePFEQkEdwnjCO+RMw0kC+AsZJTwVS2ySf64BAiy
-        blKVeWLZ8lsrgtuDL6AVf1Oxw+kEtr1jIF7IPDbnB+4An9NnS+DKF/ptUcSQvRKH7s86BstIVU5Z
-        /ZSffkmnKTQ16Iy7nGZnoOvT5dqJcJzkKxGfo10uU8gGyHeViPGiTz2z8VUC+9dmT7ZAaPrxDDgL
-        gN5pyDY57cqFy0ANL4YsonLvQmd8Tjr/x9/pDz50ls8mRPKKB6hZ589L8JD++G8n0/RKho4tgZ+a
-        VORrnqWSNeVelR+2oGMUyHXI1LLLIXdAMlGa4y1lvZ2/oTpyEvWKg5NuY2xYPz5HJNXXQxrq5wma
-        pjaQzcvb9SyVGwK70PXpWXbqckqPjQtXvCTbHz99TtMbdvLo0dM2gf1yr3RJSfz3HVv3vgBEms+c
-        supDssQPI1zrPQ+DUSix9tQG0A3GBcJlvGk0fpMtGEQ10ODlYadYhxIJF1myRNhLkkH3zsUJm+Gz
-        rcGj/dRYg1LtLIeWvaEyRi1a9Uu/xAtGEFjoRQ+n5gnYsv1mPz+TnhK+BmQvciI4P/ccVmd5ZIMY
-        fHMwRqmLUfp02ZwUTgSPr0gkDF8Aa1Z9A37+r7P6QVOsTa1y5/cII9+j6aypqg+R60Rk2s8nQIK3
-        QaBomJAIJpX6lU9asrt9F9i++AJj96yUYGvPX2qZ5jHlm+Ml/6PXPa+TwbTjdzfwFccjtseb3U/d
-        x+4gL6obepruuJdI4UPo48+IDyv+/OGPfqEdENgxFM56+o0gZWeCjcqq0yryAYTregmbtGu6PJ6B
-        C29VrSC2+ulz3Fwn+ZePo7zM5XI1rAMcntMVR0a99P09Odkg084Hqn6fQbg0CYxBLZOBGmu8s6P7
-        jeCnD9K1XqjlRATdUkB/atB8yE/h7N1rF24P4LXGd6ZP990yQTvs5z98ainFfQ2zh1FgtZB7ttCy
-        vQHwiW9UXfezV85mBpfsqlJLUNRSnA9Yg+nn5GH1GQfptNX4BV7auqLe7tky9nk9W6i6oU2PN7FI
-        Z+g8ArDGGz1xb5zOyksS4XX7MJC86rdZPtQJHC1FpwduH6WjcAgqyB1cmar+gWfLdvREefXPqOGI
-        xpr/WJW9T6hj+wX3YK7uNoFvJAzreQTh6l8uAJEnIcuyO+tbi8wBnF2ZInHFsyUEnirbD/FFj6yq
-        e7KuHyR2wBCpEFdOZXnMoWMkLyKuftGsL6IPf363frc/4Bs3z0nqzMmkpngm6cSEmAPfrvPJm390
-        /aJQR4V2dTCxv/p9Kx5yYP0exque47tmvMlXBAyK9KukD+iTRPLaf8EGUYX+e65ervIwQpdABhqH
-        ffWmg8eLPK7++wssC80WeJGDgCKzbcsFyTsEn7fco6erUvXCz5+0K8KwCQSz5H09d3eVc+exIQ+v
-        fq3PA7Tsm4XuqqGu9eqkQntTYHoUKQeG7qO1culpH+p5BWbzGGgHYDx4lSbT8cXa5a5IcOWb1HZ7
-        ms7n4D7B2Ja51c/SnOlFiCqrY+RSP557xtr9Qfrp0zUe1JAFly+Cs/wNsHWpQNpNtW7DwzDscSou
-        L2e+36McFgaasF37W/Dzw4BpJCp1tfeTzW0/QllODx3W3rrsDEI1yco5vwfkZR4SRqG75xTBNPZ4
-        7zhFyIYyE2HnfWKSqeClT5r7meDLFipsqFXLBiI49m+cqt/vI5xe17MBjOfxRtVLXuqzp919OOnD
-        AWvaNDpjb0k5bIz5RVHuHlb8DHz4PqmP1f/fgLVf4EL/dc4ITNmSLv5Igz/vu5/FDGdfnDq4+lcU
-        N/LUzyoXi2DVd6S61nxJe2EIgKgkJXlpMgW92jYQQrmRqFluH4Cez5eDkhwNH3s1GFN2sDccDC/L
-        FlutFTP680NXP4Z6M7qlg3itud9/lLnXL+CvpmhB7hXPKHhqLphU8pLgXN1HrN6efji/GkOFnrcc
-        CUg6N+3L0HrDZlec8e1Spenk6FoCuVc0UwfyoK/j8TRAMzy+EP/cfvQ59goDHpV7h1rbCnomZJGr
-        YDv28HHcJ+XcP7oWGl9ZIPDhqYwnxY2Dw4EDqOexoJMQbwNof/3u1y8p5x8f8e9Tjj6fzwy+t3g3
-        wDV/Vnz3y7V/ZMNfPuaffA9YLKcyvIpiQgpUgJB8XyWCmflo0GadPzdB04LQjglWv18lJHEiBzA+
-        Dik11cTQF9Xoa+girkDDBy7p5J1mHy6ZMvz8FF1caLTAnx5L95iwtV8kgpKQEElrfZx3UWiAZUw0
-        xBkoScVTXdXQsARGUR5TZ4LfmwhGIUfYwUgvya+e/vzCQ06adEp1N4Mr38QHnwb9H3/5ddQu1MKi
-        yCahSVvIMMnoyVC0kmyEWfqD3z/9xUp1PsCGG3i8ryMt/OMPf+f3G1sbAYOxHHkZ0Hev4aMqxSuf
-        uUg//EDbc8WcGaR7Tln7Y0i8BtT5+c/wmmwAte69yibPzVQYx1cTbdCT6cPaL4GCG1Rr/Ezp2v9Q
-        AX4JDl7rN2D+a78o0uSecYBcAdBzuOXh5cFM7H0WWpKTolpK3z4muvqv4cyUsgPbYlLxxf9g0H3d
-        nQar95Dhy5JaK38QRWBJdk/CzjbBfFVjGw5zZmD1ezHT2a0lS3EvroG9PK7BHKhaBDeC8iHT6neu
-        /SteWf1xbJ/40fn1e6FJXl981FOtJL/+3crX6NHIKJguezOAZRg4ZOhjtRRLG4hAD7KInoJ7H07L
-        dM6g1H2uWBsvWzbLmt7BjrS3lR+OJdO6ewRKmVlIHMo92Fp6+ZZ5se8RLXZ6v/pxBDIohmTa7LR+
-        keWyAkFWOfTxnt/hvNYbMNVaTuJ38mIr/mlw7Q+g3/ytfpQzuG9OFeEm2S5ZLfi58vfvVsB//uuv
-        v/7X74ZB3T7yz3oxYMzn8d//fVXg38kj+TfPi/+m4p+bCGRIivzvf/7PJYS/v31bf8f/PbZV3gx/
-        //OXIP25bvD32I7J5/99/q/1a//5r/8CAAD//wMAMvLWqOMgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc91e49f486d5-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:15 GMT
-      Function-Execution-Id:
-      - pbme4ambn2d3
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '156'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - c0d4388eaa5635db1c89b13a41bd4308
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - f01268b23b94415c41df7d0463c49b41
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "a task with ID 2314 to read the file instructions_2.txt.", "model":
-      "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '133'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6WQ+zurbk+/kVW/uVPgpTsNlvEAgzNkMG0mq1IAMJCSEMtsFX97+3ku/qdvdL
-        pIBD8LJXVa1a/o9//fXX313VXM/T3//89ffrMU5//4/vtUs5lX//89f//Ndff/3113/8Pv+/kde2
-        ul4uj3f9G/67+XhfrvPf//wl/veV/zvon7/+br2rT1bEM3innc0WXkRwIO82FEJy240JTK12oc7e
-        XIdTdXKv0FZ2NsU08Sx201gGyeYzUy/uTlWva0kP8T1wMErFQ8MC1UrAZ11esFUcloGV60iGN1ip
-        ONrIJ77E6SUAyqR0pMu2z4EdrHsNryITKXb5CKgpzhksBvbE/tM6h9wMWQk/xzejDpfqgfWHYIGh
-        v0fYDGo9ZMKqsWGxMidqBGzgDPnDBoLtvMFRm0vhBN9Zr7/gKUaqPSScrXfyAnX3zolyP4Z82SWF
-        pgkD5thZbY5gmS7lAoNgsvHWzJOcsRiMoM4mC2PbfYRT//EYaI+RhDdpeqmW8BQ4YDnhHXmdHD8k
-        swEP2oPPa+oLZMq5BE8OUHYyIeQF7Fw8Z2kNLoNWoYVEl3ypbWboU/XcUvcgsYGLjX2GdXqhON6/
-        5maq5zXUFDvd05CKZiWGzYnBoxzusfuyDpyuzp0IGci3OHjnFCypKPfrkz4o2MrSTSN2vZgBxeML
-        uTG7bJaToRjQi+IzDbFtWGJhrMX1lNgN9aZnV81FLRba1lbO1PbtMCefxxLotXx/YeuVV9Yy1Jsr
-        eK+qDK2+8WD0QgVIhM2MN5Gx4j23TE3vZZ4jiRplOIlLWsLEFjoauKse/Fmf/nhBGB1PviXp690Z
-        9pkwU7STtg2zjKwALvEG6mptDWZ6fXoAU22mKBpxrkwsYbr1KBmS1cWvaDveFlh12gFHa10ZuDG1
-        Zwg1o6JnwozqieqHDSJ7xPhmuw+LQifUoL6TLVTFXcPZ42wnMGahjMCTZwNh73cPVdFIv/tBAXNk
-        7cr1DbcVNff9Jief9TqC68vziX2bHq15ibwIpA9Voag+zJwm/JXA+LV+Ix1H48AOSWvrazcv8WaA
-        qFmMVn3A8FUG5B6dnmD0GqCC3JVDbJ2uJ8D6VdgBoV698FZMj5xpZ/MJD2faIM78IZ8MCErgWehB
-        w7qHOXv59U5XvU+CYyK2w6yO2gbY5ijRKEpiwANZceDM1D2aZlvKmactEOrj+4OmV/MJOVYfj9XV
-        GS1qgkfA59qbHV0YYo69Zx5wSfh0CBT7S4mRPCFr6QulgyB59qhdTna1ADW0oZ1liNrZ3gNMbw9X
-        2GZjQYDz3oGFCoSAsrjdMFoJw7B8HF2EuQBkxA7EypdmMCOoT6KO1C+eEPamPVTXbEMDXCthf3h2
-        GWQy62i8RLAhQA0dcN5ce+wkcQvGzbgR9GzaNISp2dEa5WN71qi8DtBTPbhArJt1BM1Pt6YhVpf8
-        cJyfIgxtccYmn/yGtdXDg/AWcbrhF41P0uHigFVmH7HD7+HA+xOX4W6LTVJdyaaR150KQdQ9ZrwB
-        bRouue844KEtAkZ5svAP4p0D9ce+ohuVFM3cDeoV/uJnbLvnsOSKjaCYoxua/THg7Pv+UAM1x440
-        l9WIxfkM4eOmI81RrGF+0E0GtTMi2PHFO5/KaKMCRSpdagFhzCcvno0/+R9fZRwuavB2oFNtbGrW
-        1rsin5DbsJJPhCIamZzVkRZALngdtsJn17Ai4z3MnVahpj/2nAnTJ4OFK2zQoss3zpu1L8Ci3XCK
-        m4w1DLJCUNft+0aYGZ5yftZQBE8vNaU+2vnD7N0WEeI+NKgbeQcwPxy/hKqQ3Gg2x1Hef9cXbG6Z
-        h8Q0vg9U1MIavvT+TuDlMDZz//EWKKrJHke709Pi1iFOoFI+b9To7QTMWuE9YEIXjGQu1c0rsnYF
-        LAPo0svRnPhwVQ4P6CK5xZEosXx8BJszrJrgRcMocgfZKp0dOChNSGbNIcOkwDbTut3Fp4V9BJxK
-        8GTDRlQHauTTrvoUtVjCiYMtjXZbGn6U/FUCfXx9sD/W72o+XomoxW8P0MBRmoaxm/6A6bvaEeGQ
-        mpwtjrPAMGgfeDt0tsW0DwqgNzKJuitHsJhg16V+jMU9TdP7aPF7pjJtjw8TjQQn5sy0Ageshy3E
-        VnJPq6lrQQQiH42o25lCNdXe2oGr8+6Fj9bNsqS1wGUonW2FjLuTbdVuqtlwSVCJxI84NsQ/wBrS
-        3O6QvrsE+bLyHyLklxfG8bMyOTu8X57+nT+2Su1g8e5IMu1xZzY2zBvK5ffrLv7ijT2oSaCnt+4A
-        87eX0ItxODccPAwE5QN6YjPTvWqx5rjQbsX7QE2+vQ389u4T7do/XjTK6nPOTqOXgR+/hCE9h1NA
-        bQgxVWdscbPhzJyNSI/j9o1kWuwrHibWAlk6Lvj6As+cacdoBx9pNFCk6mf+fX4GDOa02E9Na/jM
-        tl5A48Mripw8yGdPnjUYmGOAdwDV1UzZC2rm3jsTi0uyxbeXxNHfkm8jGBdS2B7Lif3JR3ZtngPL
-        qmCE2WQ0NIx3iJOfXlCEk0kju4qaEQBXgC3jPhrjsbfmTyCov/H4Ft4UfruYqa3rnRthc0mnnK+2
-        dwbJTTBoMCbFwEKtkOEXfwmU/G3Fwua0gK5EGvXN492a+cleoB85GjaC84ETo1Vr+NsPL3tV5fNh
-        1RXwEZGYWr06DfMPH+TkzJGmpG7OhsbdwVHKAI1xNDa8vrwXCMWkJ5ImpM2cfcIraAqFkv5wby1y
-        nJ8yhMnZw+4unazldAYH+Lsv5vPLWvJXUIL6rKfUuK1qwDqH9fAbT5zu+0f+mz84N4ZFsbL9VFP7
-        eWhASuUPuX/nv/TFqgcQDSX15LgC/Lavr0Bc6ic9HC5S9flg6P3whHze2G94Gs2CLl7OE3mkqZ6z
-        Bw93EAaejvfT88LHAsAHWF/aJ0X+al9NpRQu8JW+W2qImmkRNXjbcCO0MWLK1R6kFMsinKViwQ5m
-        Vc6u57aAfbUakFBvIO9IMhQqaBROA3fYA15CXQVFFYfYiyHK+f6adtC9nyTqLdKWL7fTvYapv2uQ
-        dluagUITddrWls7Yvy7Cf+mHSdMCsvajRz5zFsrAbpeBLGE0VWN+KbI/8cMYWtasmEMLPscXI6rj
-        xtZyHN8tlGl8pVuVWJb0cMwSBMZV/q533EjgFTtasz551KCfJqd0+thaBcMbYl/+ma+XvlUc7eBT
-        w7CykB2Pqgbp8b2l0eLJOV1tPwzs9dOVzPv+Uc32K0P6CBODRj4WwPf3T/hOXERet8Nx4LKSy3qt
-        LGu0sO3W4v5TSqB02YXYXhG9Gct3uAE9yBkS14sd8r2UEN041Bm+bR606iVS7ODr49nY0bWkYfTy
-        FuAINiOZZ98JuVBWCaS8M/EffKSrXoO6UBzwoVF8i8nbZweKk66gZdea+WS/SgQKrUnIfi33FR+4
-        d4bbp3//8gfjXHXIZl1NJccodGEzgzzMoDX2At2k63dFx88Wgm5PLkhIxcPwzWcIPZescKScOKfW
-        ZO9gfi9uGBV3Nszb5cDA1SEWjR7Blc/+uCoBem9ORKWizGfnMmUgeNUjrarTtVnUgNpgKwmIejEk
-        1fQJZA1YFy37kx/05KhXOK/XmHyk+cmZu2IILnsY0nMOi2a2URXAn/4Lok4YyE9PvMv9mWJJf4Ts
-        6ZbLH7wJtm6Wy/NHRwCbsklIOa/C0QloBu/eIaPWeaMPi31PA11Z9XvsU7vnPBwNW7+fRYrLJx2r
-        hVu+BnS34UTZWC2YCqiOwH18fLT6vi+7tLWmyyAr0fsgJY3SjkcGagsecc4uRiWZihzAh5zcMZJe
-        Dp83K0OAcCe80FpvnVA6K6cDvNz7GL191Qt5LO8EsDJrgcZj0oSfK30WOr/KDVkaXuTzGzwJ9OIr
-        w47RPCvOVwYDjb5+0fCStTmPQYagSYsesfx0q/ib90/oDfc7Yv6ONjPitQOhXUVo3DacdxYpHvA4
-        AAeHL/c9EFoONngeL2tqzK9LSG/r0YGfy/FOMfFqPkfjPvkz3rgDrSGvtDwDrV+ViPfPYmBLYmZA
-        WJaMRkL5ALyazE6XV4vy5cs9F5072UEjuBzw5lMM4fyW6RlIoIDU0uSttRziTwQP3XL74VH1Rw9R
-        3pvYTuN7w0jYBqBKjyo1+3MUjgEOCvXHn/4YLdUs0/sIhdjf0JIYPv/WQ1dgIimlzgRP1qI36RO4
-        8SujOO+QxXcGXn56HSODHPkcFrEGjun2hkNx7sMRLY0Gv3z41bcZbyM7aeEuX03oHsJTzsRbVUKx
-        gAk2sw+v+OIrouaO6yOS9RY0LCn0ANaL5dFN4stWl/qGCue0TeKVdll98XBGGnuuAFoN7gwmziwZ
-        9m2sYbezt5ynGnPgpsstIgrtofqz/9exFVK7VuyQnkwQAVOLMrp9HJ1BUsdlA8OP+sbezrxWX//i
-        DP2tK2HLUAifW1J7+lcfUvs+yPm026WCfrSeLk4i0x/k9KI8oaDWFoJPy2m4GjYJtNy3Rz1s7wdW
-        fZJWZ08d4Pjc1s1y018euG0PMWLzS7cWS970sDitFMSytAhHt5sD+L4qayTHkQLG5+ncagBxiO2m
-        eg+snQZBi1y9wJvHqrXmHMQJsLrgTmPjcB7m47WVwVvTJPz7zmqJb/48b7oFz3D+zg+AsxMhXf64
-        YLiDudegBz5kWW+mZrgq1wcAZzvCxip/Adbagw087nz1hroZvhXzVXd8fCRKUTbVkuxZop+cNqKB
-        kr4rsj1XGohdWabR/h5W8sU4a8CKd2vqbunMqdhEZ/jEY0Y3unwDS4jdJ/TueU6d51AN0xuMBH79
-        ICLMZzawVdMyaDl7kUbkHFbziLON/tWv6Bju7IoJ0z351X9Ek+6yNVP35cDyGidEkqUqJ4PiP4Db
-        lRo2TcUfvvlsQzyUO7rdfXQwaf1mB9r96o68EV4rFmqJrJcfQ8XRtsnB+Iuf/jhWNCaiM0w2PGVg
-        M/KaItEPGlZHSwC/eINWdalavPXOHjhAq0PwoL8bMn+kCH73K41PKRzYYd/s4OooemQ2qjgnV9Y9
-        gRNcBwIO63s1BY5twwofNoiqcQL6FaodXauniOLD3rOW8LRx9FG03tTM53IYoGOpYGeQJw7Xr3O1
-        DMjroR2uLBrrhzufexA84ZePCXfdSz5/5wvDj/bGLj1XQ1dfOdS/fgQeBWcC9OMuhrYdvBYfQG+C
-        L3+qWmCvcuzK/n5gOFTbn/7Em/S1VMNxuRswvlcBkj9ey+mPP3/5gYgaASk7+j3si/FB99TQwhGL
-        6zP44hl1H9wL5yUy0B89lQZiFs4PMwrgV++jJX0t+RJ3OwQDjO8UO8NrGK/4LsIghAV5rxwhnOG7
-        7H7rS/hhvoFnfRJG+POv9DGxrMXA6ysQxptL//h190Yu/9RXxsX1qrmMAg1aYyfQtKHZz69b4Gfl
-        IWo21cXicXy2oWOP2h98mNVSRSCNFYMouzS2uDaL5z/4GUfdx+J5EGRwh28Yycf1PHS//UkL+YSk
-        YUfDOaARBIs3ALIO2ZbL9j31YPl8VIitSf7zDwms5eZF1tJsc6UzKNJoe5yRhsXIYu1h1KB4uU6E
-        +8YrnN/PqYf74tihS8ySSvnWU8CxiYYG++hUdFEkCD1P+GbCZzOIo3IgsNvdfGrvXkrDQWh6sF8y
-        mXABAWvabYoA/vR0LMXDMPdPq9bfcllgL6qXcKyZvsCV4sXUea6ShofrqAOCvqkx3sc1/8b7DFNb
-        dOjRePcDMc/yBkr1a4+jb32zXFnXQoekMd30opsviv44wzkwZ7xVSxQydSMK8ItHqMvvNWBjnwV6
-        xvKJurogA+7uGw+qbgWpdX+zsA9cL9PoUk443PLHQPwJtD++wlH0fHBOdrszNB8fkZofg4KxM3kB
-        pcPRoXgcnwMP3xtRJ8fp/ccPY0toG9Cxbi1ZdHkF6HH5bOBbU6WfHq8Wv5N3sLvSI46lu9GI13vT
-        QT8rt9RwbQMo0LE0SGEHqFkgJ5RzHznrLLoE2BdIXI39Kuwhci4GtcMOAQ2olg2r7BUhpRRasMTN
-        FcLiXh8wEuRnvjQ4UiEeit1PPwzUB3AH+boP0etxbAdmzl4EjtHbJFoEecPdsUfgIVkxkYtNZ82F
-        As4/Pxd7+4s2DF++BV8/h25B5jTzl8801zraX3xO+fJqdgm4Fa/D10+YOL+DudP3HTCRsBLCZnLC
-        4Qy1OXmhlb5Y+ahK6g7GG3f70z/WkkH/Cg/PZIMv0r1u2I5mtpbF5EqD3SxyytKRgZeiMRohcc6Z
-        KrGD7r79Fgdt2A0ss8NeQeMS0PjrPy6/evqHF2ZT6eGnLhcNljx16U/ffC7TVYakEABS1oE9MAMo
-        CB4950m//kM1G6Y6wlA5reiW+yxfdHYNwLe/QLeWdR9Ykivqz5/G293nAqYUyzI8WOSDkXY6WWxn
-        5gJk8HEiS7p2c/k+qZp2idoDUlcLyemJzgeweh1ran/9kolo9Rl6142PNM8zc9E6nq4QgCJFoscO
-        1bJ/lCM83jsVu7n/al4/f2gVzhFF76MxSEL28cAs9w4Re+8+MOMjFfAcwwj//LAlXlUZ6GFjYzu/
-        JJZytB8aqCy5pli73PLpJewKuC/2HfYvwhhOyWZJ9NofPeq0rgKW227M4E6YdxjDgxuyjWAv8P7u
-        jtQJ4Mea12u5hdY9PJOW34dBkuwqA3ZvidixXJfLQPd22ucm+9jbz3hY1lf5DAXdqImSvDYWK/d+
-        9NvPRFaXTzWeRiOD6J51ZGHr4x8/QYs2+P3tF53C4csvUDSrhawlvwTL1jg+4aV0CTVNfBvm1ugN
-        LXlmEw2wOFpMx7cCfEq7oFE8BtY8qqUG5/IVYHuZ9yH5hMABIlwW7KR7Eo6t3TjwMM8lRlfHCjma
-        byMYd9ODbr/+B5fyBEEtFWpUbzt74JtcIdD1HYkolLFm9DRNgMdY3mPffdOGh0m4wAVsTCLcrydr
-        mQ24A8/t1caOEstNB/XLA35U3//pbYuRd38FTbm1KL7Lu3xGx4H98ceNUM1DfhM+BygeR0gt+bTm
-        XdfDBKgL03H+rbfmj6obgG/m7ptvTcXOz+oAfeNdIEhYndPtpXCgE1ORuvChDex8u9o/fiVvIQv5
-        vHo+IIhHbUSfrXKtiHQ8JX/qQYtd6mqI5R3Uv348RswQqyWa0qv+WoIV9q6ksPg05PUv3+lu9zo2
-        ZPCtP/4mAtXpOoi/eveXj9aXj/7osdh3AhzR59KQ8uapsPLblNqb45yPzp0c4OaeC/ir78P5q6e0
-        w8xLpG6qTfibL9SF8kDtFbk0DLqFA+Xkykljhg3gbbmHOnxcdOxqrcH5QKwI/vpRhpopFnO7dQBM
-        +20RtgHBz68P4BxYM1qH7MWXoQ6u8P7uj0iWtzhf1pJUQ4z3BQ7to5NLwcMoIc4VmQbTuAPffCWQ
-        nt0HqjW5bBZ/JZVQNE8Lmiic+NcvvoIt3vZffC4bJj6LHrJMcCjWlyanRUce8J1s0dfPeIY856EH
-        v3qexuLWzuX9Ol2gHudP7H/5ns+m+lh/+2OE0Y+VT2Ob2nBQtC3eVsJ9UOZcO/zxp3/6jcWoy6Bm
-        Vi729SwN+2HCG2iuBAvdTIeH0/29OsPX9XDG2xoE1aKzQwC23SAQnn7U5tsfZXBvSSG1CzIBGsgr
-        G/z420zvY8jFKC5A9Fm22Pqc54p++42gcAjBm9qdBrotShEc5FT5g0d8Lc8jTPzbFt2eSlPxUDA1
-        PT2/RqKDSxnyuZ9LPX16Ib3eUJ8vU1hAKFN8RcO330IfnpxA723ZOHqFE+C47UbYCeYZu+K0rr56
-        JdC/+gs7fYKsdvCtAmrhsMf2rD/4KHrnHfz2/4h49IHF02b+9nf5Bgdjojb0F7/+glY41jcRoMmZ
-        INAekUQg7NOBwd2uh3F0zNF26J4hU4x3oYuu32AXynSYRT+pwWvxVjRcv2DOfnqTtvsZG80wgPmV
-        HDKYBOSEsaRvrHFf1k/ovsOWuod7NfC1vCbw5xfY7O40km8JDzBkMqYh1Ix8OfGlgF//8Ot3tNYc
-        OLYD17EZ/vR9zuZZ2Wlp13U0ip4bII1qpq6l2SMYb/GnmrOPdYWFON+IqnyKkOVOisDXj6cZifR8
-        +VxEDazHffLH7/vpb/1c3Z7kgmtzkAInsuEdORZaC2WRz5GX9vrfv1MB//mvv/76X78TBm13ub6+
-        BwOm6zz9+7+PCvy7vJT/FkX531T+cxKBjGV9/fuf/zqE8Pdn6NrP9L+n7nl9j3//85ek/Tlu8PfU
-        TeXr/73+r++//ee//g8AAAD//wMANss50OMgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc9233c9622cd-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:16 GMT
-      Function-Execution-Id:
-      - yvvlnv17ahsb
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '18'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 23e5ab6873bf9bde0d2d32702adcf101
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 4f7afd2da27d1e26072a09f6de91c9d4
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4429'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4SSW2vbQBCF3/srhnmWjB3XN72ltKWmFAJtIFAVs16NpU1Ws8ruiNg1/u9lLTsO
-        NnVe53a+s3u2aArMUFdKdN3YdPJ99nx3+202XhYfW3n4+en5/uvDuv/45cfn0R0m6JaPpOWw0dOu
-        biyJcYwJak9KqMBsMJ6O+sPpZDRJsHYFWcywbCQd9kaptH7p0v6wP8AE26BKwmyLjXd1IwtxT8QB
-        s9l4kODp9mt9MJ4kKE6UPZUGN9NdgrpyRlPA7PcWawrHu95ZwgxVCCaIYomUjoU4OtjmDACQo1Su
-        LSsJOWZwKB4atJZYzPFXRcC0FjAcxLc6YoEJIA48qQKkoretsLjpyVpgZSz1YA6hcq0toA20n4wr
-        i9gD7epacRHvFA6kMqGXY/KWwZMKjg2XJ5D/CEG0pgwHUEVhYldZMLxyvlZ7XqmURGgmHZ/Ib/ay
-        JORrwx3Z3mMQai44Gqu4Q0jh/pqP994jzzmFW1Z285cu5q4RnQFpb8RoE+qOag5MtAcgDq2nzu0c
-        VA0rZ617MVxeyimtW6+E7AYiPq1WRhtisZtz/6Eh9XSUejHWXv/Nd1ORY3d9lxxjeNi+SCGrmjrh
-        V6UzNuXL8/B2jTh7Wr9EOULsQQ48Oe9wl+DKsAnVoosfZhjENZig4YLWmPV3f3Yf/gEAAP//AwDn
-        zGd0PAQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc928d9db1254-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:36 GMT
-      Function-Execution-Id:
-      - pbmenv06a5yg
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '19200'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - bfb649068e555d640f6ad40b261616c9
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85989'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.674s
-      X-Request-Id:
-      - 0f8563fa8b875d2635d106aebaf6c721
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Read the file
-      instructions_3.txt\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '273'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0yOQWsCMRSE7/0VYc7ZZZddq+ZqoUKhl57aWiRmnxrN5m2TJxVk/3sRWtvrMPPN
-        d4HvYOD2Vlw/hGL6NP8M9qVvl4vDcnd8Wz6/so9t8/hA/gsavDmQk59F6bgfAonnCA2XyAp1MPX9
-        bFI1s+l0rtFzRwEGu0GKppwUckobLqqmqqFxynZHMBcMiftB1sJHihmmrTX+0Le4bjSExYZbMmlH
-        Dbdn7yjDvF/QU/5lJg4EA5uzz2KjXA05CsWrvY3Kxyzp5K4PSlglsp2yausDqWh76tQK/yp53ZRy
-        lhVKjBpbH33erxPZzBEGWXiAho8dnWGq8WO8+wYAAP//AwC0qgQXWQEAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc9b398c12c5c-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:41 GMT
-      Function-Execution-Id:
-      - yvvlzurg1bsa
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1797'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 87a5b0baa518b220c789956026d896ea;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89461'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 359ms
-      X-Request-Id:
-      - 6ef56affce707bafde194ae7d76813dc
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Read the file instructions_3.txt"], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '111'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaSw+zurKm5/tXLK0pvRUggM2acQvhahPItdVqASEESEK42ICPzn9vke/odPck
-        A2KFqFyuet63/B//+uuvv9usLvLx73/++vtVDePf/2N9dk/H9O9//vqf//rrr7/++o/f5/+3snhn
-        xf1efcrf8t+X1edezH//8xf/30/+76J//vp7jhadBheQmvNGyEW4TY8vusvLpScB4yaY3u5vuvNq
-        6E/+436Gt3ra0d3uZrF5Ixx5qL/GkFrlaQHjcdwZMLl5DdY7RzDnLcAtvKqGj7V+n/as4/o3kHTr
-        gQ/ibePT0rpxsJjAA/UqN4MxFegCbjF1qenCrB816dlBVxVavI/ExV+ubijKp+F0pLvZOPYMyTsO
-        LHbOIYEjMZhfz28Lr+dYpI55gslydt0zNBa3xNpRG81xIJGnUhYhqm2/z3oJJWuBF1esqR75AiPP
-        4SVB5dGecLHVn/6YR6MH78ltwK56mZMZzN4RBMwR8D4Qvz6zDhdFGZvhglS77/rZSvpSYe2rw4F5
-        u/qvnHNL5dkJDTXHl5wMya2MoKTbD7Qpug+bjreuBOFN8ugaL5/2pxTCz2Pao+rrSj07vIkEwO6S
-        YNe9u3VnRMcCPJjxoO41eWQs6qQrhLFY4VCPrIzuTM2Cr6yuMeoeB39qmGXAzjIg1oZKMtmX+x4B
-        HN0ITfGL9iPJZAvIYRlSI/hYNZ9jEgCNQEp46j+yOYp3OThtyYYaReKDcU9qW2WxLBDlILNkqt3Z
-        g96Ga/H+tO981g+aBvP74OEHATP4em5FVC0EGIFGj/v25p8gTN2ioO5o7zOx3tcx/OWDr12PTHDJ
-        p4FpV1V0Lz0k1p7uUwnAYLVkWlCTsa9yeoP94xBSv9TdWnDdMle/MZSQDMP6935DPfaxg/e29srm
-        04gjOLrHgRbqtmF09lMH/PLTKW+7nt1KaMNqH/tYv217k+mHmwPv3Kxgm5NBTxSr62DvsRtGwkkF
-        8+SmBsC5zhHerGjdHS5XB1wEfB6vBdeaLEXpAuJhEKj/yiljgT9a8EYsRiTl3IBpjS9MEzZj9LVy
-        RtZ8BnJYhVS/bX1zTmU5BrHfn/DOqDufBVXqKH0mnlB5yJ4Jk5ONA+22PqIvgB6j+ctugNd8KqqH
-        b92cw6aKVLJbMrw7YqVfELxWsHtZOcXTmWZsurNC0a1+JPAYaAm/BF8LFpgXcXA6k35mYRVvrnYU
-        E+kXn+g9dPDG7S7YT9+mKSpaIYEPZZhsrPxWM135TrAUPJOIY2EmIwKHBhpjadCbYwTZ0JRtAXfa
-        eCFwIEa2/XLPM7x0kokvyWD2i2efJMiJpoi2RTVl37NjXOE5THms37e8v/CvqFJTpbaxbjxIUsla
-        3sHIFCPqkF3NWKnZCOb1VcNFVK2nM7djmKI9IB9PI8ksAN+B/Eu/YX25hT5/rZwJ0gWLCNJkZKRO
-        Ea9IO3pF030wEtIIrgTK73IlDBxQTWSrvMLDC0LsHojeL5O9Q8qbIx8kyElQb5kkTbAoFYCNrhnA
-        YqrMhlxPamzIvdMvNFdi2E35nhr9RjeXi+u/4Zc7VtjrxaUehAi84SZfPoTjfVwvLpOMP/uxp5ab
-        zc+beYUmaTocnOcKMGfqA5DwJcZooyfmW5PbBkb19kq9KjOzaRbkAWRv7oBD1MOelCfxDVgMBGo6
-        S5ONX7y3AAH3KwG5XtaLGRVEMd6zgHf0Q8yBCRyCVzuOqZu5EZvCABrgYEkSxi+c19Pue/Ygaz8d
-        2YJTlywJ0QeInyNPbU7O6uUmDjkc9tghIidnPe0HxwC3UKMU49r0GaqKDqz7Tw97ha+J6iiKEtTe
-        AW1AEDNyzMqrKiZvB8HTmdTTPtPeoHnseawf84YxsHs2agZehMynbeVPZjy8wZl3CBnikrFx0MAE
-        j6cmoadsd/L7/iNWsK6pgfebU5IMoXK9wvb9dKm5v9hAeBrnI1xUtEWq4AXm4tl3aRsE2YPuvkZV
-        f4XDUkL5si2J6Aqv+rvTPQQfl46nmiY72bzfRQhK8HEgcNu8wGRrYQXGLg0obnYkGU9zZsDRPTtk
-        cc5DzdzpVcBUUEK8fwxFP6SScobxMN5QJfdtvYgwOMtzNOn0fr1k5gzMkZO33cWlxoOU5jSMtwBI
-        mllj3ZvsjDaPQwmjTWhgW5Hjnk13UMiGWr5xci6qemHehYAq5zQcpHPPxvyTBnCtl1ib1SJhfLWD
-        ED8pT4Q1XoMZDw14PUMVI39vJPOlmAd1Sg5n7Dfxs56eV3sALMQZYUm7Z6LPYAlLkh2QyonPbPo0
-        C4Qbn/YUHZnGhF3yWuB5zCDidsPLfF8eUgshkwx6tNTQX6oiOkPhkDc0JMc5odMd5ABfbjtsuLML
-        5jBUIAwksSOcdviwmTW35ldvkLyf7/6UVfsKtL6nYO2rmsmYy8IE3W/g03O/iGDIVeMNbwZ54eB2
-        vtSDbFSlau/vPNXYNa6n+eGlMPwqBKlneOxZun214EOXHr1OHWFsqfRCreUsQ6q24bIRhWrw618I
-        PHMbLB5bIrh9DRHdlfOzbnFNRWh8xBCdSXvoh9/vF7tqQJNx3NXTeW/mUFOOKY7H9FOTTT0FKg7M
-        FFtvhUtmJY0mkD68LbWI3voTH8lnuJ2MDeo49ZLRZ+bG4NZeOeoZC6kXQ51EmAc9wqY0BP6w1NFV
-        PYJ4QBvpEyXz2xN5GFdpT3cxz/vz7/+zzTlDnLq12OTO8Ap/PIWA3pnsHtcGzE7yCXvJ8VMvL1+O
-        YXJnd8Itk2suxkevwLoeafW+rYcmP3O/9YgvlCBhVWaWkLNURAMlLftpejiefHxId3zPwrofdJQf
-        AdgWCVrc+cvojwcvnfL58YrJtu8C/eGx/WPg+vFhHHioNa1OM5lzGE2Oex5ybzMm0nmMzLnmNaKG
-        N8UjQBhvbJbNZw69LmI4R2XHOutY5Su/Gut5RNl0mo42cOWA0tNsHOtpCZ4WXPeXAL72+3lPegvK
-        fLzH+/vVMIkADQvE2Vem+xYRsMBFj0AhNhPNN4LNlu231yB4pwwbS1OwwTpLZ5BfjRPdXUu3XqAj
-        tXDJ/Qua9ZPmL0eLHeFarzBeQMoWKRYgZHL3Jkr9UurJd4gGMg1BchC7lz+2L1mBa7ywC2DCaMCr
-        gzJOtkH3trZLWIgnEa71khoGsE3eiEsbcmn/obZQCMkcNKUGnkApCfAfn+zbwm+gVFB10Ni0uT99
-        QGuA+nq6YH/ls3laBgXaTNnQ335MYDJTyBIuJD++WjDiUtgOAYcUJ+R8NvPdBKXTCPF+a2UZc2+i
-        p5pNVCIZwATQaznz8OmyEs2U17P3feMUMDELH2vG8dXT72cx1NIZJHzeNef+93vKUwx6bKc2rteO
-        fobmVRGILNhyQl6+HIFFm0e8Z1acLOaxROruUww44NJvv4RolsA77GokKHeFUYZbD17QI0dbR9R8
-        gRPSRrbv7pc6pbOpafO4VQpuCx2v/TFZ4gR1SgHCLw40fqhXvpeg5sZnJNh14tPKKnIgJ4GJj+lX
-        TUa16GOZ5s8cceGw9df+swD/aR6o2/clWzymRIoDp5x8t/DJpvf2GEM6NleaXZUNoK9AQnBy4Aeb
-        cBDMUZNqSVl5mdoytbI1fzr4FFFPzUs7sUHu1RSiU/Kkgd9F/hTW/RlG1/tItg+16adSP3lgLxo1
-        deu0Zf3aDyAjyQPRbfBly0EreYi01qLmySTZzAnpG1q3zZ0GK5+Jm1CTgOigO7ak7ZGNTBQc1X8P
-        FY75qM/GNHh4IK9TjQhdMIE1/gH43hODHKm/ydhRJxXMYGdj5IkwmT/PtwOsXrvhfNvsAJ+9bwY8
-        RFGNL56Gslb60BS8L2qMzYqavXD/5AWM1eVENp6zA9RsvQHkrSGTJU0qRl57OkFfHG2q9deyHg/n
-        A4KpOYfYcfUZMKsNINSf9pHizd1j88lxPBCi6oEdcSeAKXsfNLj2CwRf0qeehvGAoPU6OUS+Jo+E
-        Pq0cQVVpH3jvaShZ2vckgs1npxD6Ko1+uquBCG93M6HhLgqzQQfTAIIx32Djnah/+ENxsgFihPfH
-        bNbwwYCbz14hW9Pz+snNdpb6UE8htoNeS/jDKY5U+SKUqAGjnVFFP4lAHp8n6oS6AubvCzrKlztX
-        2Hg3JhC+sC4gVd8QbaeHzcTgmSFALPqgeBu4gFXjx4LbF4mwvfa/KZVgA87325UmKOzqQfiULdwq
-        lxHVKx9Mb6RflffXWCh6Wh1bPO/bwUVjI5o2ilGLcHEjsL6PtDz49NTi+BjOu+sZKfolzRZZO7YA
-        6rOB3S18gu/DuPGKmDQO3vncLfvpcVB47gt7TmGZQtCUhmoERUWdQ+wyJiZSCj6eFaPJpz2bxE8l
-        KSUtQsR6renHXXe3oeLIDdZPb2bSG4oq9VmWInXE3QmwU/58wwg5HC2OlcLGY/osYKo8bRp4pQ62
-        6XZsAT7QCBu7uWQDSRfnD29LFTebbD+VUEXv4/1XD3p6zmsRsm9r4Pz+sXsxFd8D3IzinobhE2Xz
-        o2+GH8/QlUfBJHzKTl39D6wThzOZdXqmAMdTQFE4XMwlkLxSSafgSlha+PXUbaZIwct8RMu7qcGg
-        +toCS+4m4PU8JrV+OHi//EeSvzUzVs1TA/Lgi6j/3jb+koYJD2SuOeBLb5XZ3NzvisKdNYJtzZ2y
-        pTgtNkwFKaTGFFUJHU+XAm4G5pNfPWTJ9XYE18/5jP3NDfuzszsOkHi3Iw3f5pQxhSxI1b0jR/1n
-        /gbsHo8RxJdsR+bwBHz65b5nuD12EzWHzPC3S+UW4KFzGfWoCGpSbAII1/NMrfR7X/UGtmCHLh11
-        3UDpR1h8DWjuBZl6Wjj48+qPgP4TaNTGUQVWfyRWsU4GjMikmUuijccfH6z6V0+EFx8iqEcaT90T
-        6XrS7F8l7Nwh/KOXWDVLDbyqmk8Pif7JBjo+IFj7EfaEqvUX+yoVUKzfA/YhX/fLa/9ZwKuKTzSo
-        jQAsrdp6QKURT93wvtRTxHUKKNHVRYNXPhkLZT2HihX1ZFkajvXGIbvCU6wZNHUKy5+tpC4Vt/Ux
-        GRbX6afTXSrhrU25Vf/U5vBpFAjOpDgid9sDQNDri2A7SzwBe0QT+lEONmwiL1z772zSEEsi0MXJ
-        xbddMPeM215zwJfXkh7zU8n+6K32XL6Qn75rc75/jvkvXzF+lVU/F32Vq0frecF/+r3UMwfsG9XE
-        ubQJkoYPxgb4b1JhTUFiRvRKXaCy+d6xeS6M/rPwLw22eZAiYeWZHu7eFrhVdPzxZbZ19tFZvTwq
-        SIPy/swm2zrEcPVf1ngOYOabTIQuJ2k4P88Gm388o96abI2/WYuzlwTyyr8Uj6W6nveTBcMjkgnn
-        741su7/JLYi+1RcpMtPM6f6+l9DCLaHOZVtklGMBgQknqtTU+7Sfniuj4cMYYUtTLX9SfWcBf3go
-        h13SPcxogZyoi4QdzFcyp0Euwdo5M6QM+yd4XQrAgWKIdDQrHTEHpd+2kPeITd3I4JIf3/z0xeq3
-        NdkoHvgJZDtlxoj3cc8Y/4nB2bRtAj+GwJiIiQSm8FMSnouBOQT101Z50ZLRNj7ghAf2VMLpeI6x
-        teizOUetUsHjQ7nTP/ms5qcUpkfepXp4yvztygtgUYMtEudiSL5wthoowfuBrPHxt2kpnmHwYYTq
-        ptLXLDq6FnQ5RSOCQkpAY70zYB50HfbIEGbbaynzUFjKFoer/llaueig80wXcqbLhg3f+NaBU6W9
-        sa9yKZilTXKFOsiMlU+ajNhHApWIogI7YK7MlWRzpXvZOUVUuWRUvjotsB59jNRr+1z56VzA11np
-        iGoKGCzKBSHIam6mtivs+mXUeQjjvZHTnXg/sG4jZgtwLraJ9/wDs0VdwgXAyz3DoZ1m9aCXGwn0
-        0R2H4O4j9vn1v+L9Dmho9M9+Ifo2gOfG87Bd2Nd+tknLw/Zdu2SxznW/fCK3Asv5UdGdQjTA07km
-        v/6ODWC/2FJNTALaHTCixrDvp0fCFQDsTgk5gvGdLcTWCFjPH/35Q6t+W+DBUiRqZPeDrxjRMYct
-        DCu86z+7lbdL7df/qb3IWs0PltPA9qlE2HtnQzZ0XzOAZbPfYzOTHTBHcZiDGewSJDYQJrPQnG0o
-        s9Bf92NmrM7CCa68i3W46/uvAWUJnobLkbqCfcvGp1EcQbt7fKl7uGc9Lc6zBimLEbWov0mGLi6c
-        n19OFE7dJjR/oQZGyONoGF20P/UE3IXSoemqB0e1qGOgFJ8b/un1RRMuFjDJuyPjGfI9MT5uCZ4i
-        xnTPrGX1D2QCc+NcYqv3x4zpNU9AVAtXqqtly1Y/MofSULhrvzKyPzy8bJ9vuodTBJbueFugaQY5
-        NgVxziY6Xjg4eyamJp/xZjcczxGUY7+n1neSzYV7VAE8wYtEV7/fX7x7iMDdtVXs7HQHsND/nH/6
-        nWyp5SaTbHSl4nsHQL3U8xPBL1MD3IXKQcxZrGSYnMQGi87v6Hkysc/A7vsGMRxVMqDSY1twxSlA
-        Uz/R/evKr/ORzILHPnKwFX/9bAoCeYE2F450RwIZrH4OBMMgP8n++zX9LeM/EZzxUOJkfE3JNJwb
-        D85inuJ7Ze4T/guaCgT3PKPZK8dsxs17gtJ7krBLIqEnZ2vDw63VBTSUPc5n9C4juNYX7DvfExhU
-        WzVkspsy6j8mJZne5cBB/Mm+BPLknvFTyrXKbuEv2H1tjrWwqeQINC/+jZE4AZ+AUS1h1y0H1DKc
-        mT/eh5dTgKi9tGnPPnWjQXb92NR7atSkr0cy/fz09TyVgFzFKoBawfk0vC04+1OPDunnQO1LdGRD
-        xHUS7B7pm4bHy9dcDol1hWBeCqIOMm/+mSf9/Oq5r91s+MaHVln9CxzwmzqbvYWdYVT4FZokdvOX
-        7q0eQXgVFmq83Hc93CrfgPsj90D1kFX+cnsInmrK3Amvfoc/V/dbCjW+fRG57zVGTgQhWPTh7r/8
-        kHoWLGio1RvbODLYMKViB3kwedRb/ZhO+o4RkIbcpXo+7pig4ZsGNb53SbwrFfCyuliExnk+IH6b
-        XxIy6hCCjX5V8ZXsajDtzkoDzlwu/ZnX/PwctTjVERG+hlEzx7RFEJru7TfPyparWCGw8hOSvPxt
-        EtdOWvAdD2+0Xf3ERa/USV7nBXTXBRGbaqZP6vV8SJG41j92UM9I/ekz/5dPzi4foI83E13nN+bw
-        0FMFHidYkSb+9pmAYz8AODc5UuYH4rOEOi28h1RE4hU+s0H1nQnWxreihiKIYHxLGYL3Y27h0577
-        ZEuVWm/gbPc+WaTomM2nOdNgp0wCalZ9uXDioYITf0kRiE+VP+3HxlG/Un/ApmlvAZmfTgSqHGoU
-        v0q/FhPiEniu9wtREaz6dZ6CoG2IALXxuDeZe+M86A/phfBc/fQpuOIr2JdHD2faVQWvm/CqQBxf
-        9/TSIgRY/r3aEMB9gLbbk56sfm4Ano+HTPiE3eqFE28l9DawxenlONUDsUIbxgO9UYvlKBnvnL/A
-        z8QH1IWh6W/V/HSF5ZXm1PlgzRScXJ/A437eYe162JmsER0eiKESo2WtdzNM75Hc97xM8bc89tvv
-        IeCg0hwY/dVzNhpMAfXGHrBjvo2Myh0pIGzLC37stmcwaS/9CutgM2A7i+7szzx0rXcIeFZnTmbc
-        HSEjMfjNE+u2Pz8VUH/ThGxeOO9nq0t5eIInCWuuV2Zz31nXX3yRcCy1mhyJyYHr9qz8mX/+4e11
-        3kL3SNtmcw8p90cfaW2F/T/+4VofaWZbT3N5mvfox7cUS58poxuGIPzyxhXv13kPQ3IIYXp7GKiU
-        LcffrvpJHet+g/E8Dz2p0qCB2Xxo1v5PQduUZa4m9SMhYmFL9dSwwIDC8+GgWdoZPb16wQKb0ptX
-        PfD9w2fKb74ZODzXD6vTDn2sTmijGE1P3cKV1LAJ76jbtd+kHgYjBoZ/e1ONQ5tk2mdrf87ROiaK
-        F3/5yKkDhkC5/fwR8Mefkw57k+qOb/78wRgcJ66ie0fUTIE1t7fSpAUgFNemKaRR2UGtfn3xXqdi
-        8mf+svpL2DvSlzlrUq1sV78CcRs98dl5Jy4gdASEjQfRfIZkk8CpVSkNEuCYlCufHtxUd50if98n
-        c7A1G+j0Y0mqs+Gx6d59Y7jqMyT0540/KcYwgcel5Ymw+tvzTjeQ+vfvVsB//uuvv/7X74bBu70X
-        r/ViwFjM47//+6rAv9N7+m+eF/9NxT83EciQlsXf//zXJYS/v337/o7/e2yb4jP8/c9f4M9tg7/H
-        dkxf/8/jf63v+s9//R8AAAD//wMAqjA5m+EgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc9c1fd9513d1-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:41 GMT
-      Function-Execution-Id:
-      - pbme8b7quow8
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '22'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - cc893c79eb41c92650396b5ee03be018
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 6b8a366fd1c0a7253e3a77e7fe91d0dd
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "an instruction to read a file named \"instructions_3.txt\".",
-      "model": "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '136'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6XQ+ySrPl/fsrdvYt80ZEpYt9x5fIl90CijqZTABRAREFuoE+Of/9BJ/JmZkb
-        L5AEqOpatdaq+o9//fXX301a5ln/9z9//f0quv7v/zFfuyV98vc/f/3Pf/31119//cfv9/+7M6/T
-        /HYr3o/f7b8/i/ctH//+5y/xv6/835v++evv52N1Y6aULngfEKWAS0GPVIyNoOTLIRchxdrIdH3a
-        tVL2qgWIjeON+dqClvydeNk6zvcF0xV6abnbigXoS1fHQFQtGrv1zgRb4G9CDK1IpxXa66gyVi3Z
-        XQtcjli7CNCtq4DZlvZB0zsXY6S6d4P5XuC0g2iWnZx0kBNj+N68SQtGFZ2+9ZW5r6uKpOHxkmTR
-        tFWyD18EDecdOiIJJy7br9+6sSw6jAE9lyXxhT02vuXxKSlVOLrMu62bcii7Xgfm6B/mv3zK6bN9
-        X8B3yw3ZjR/bm0JLruGxLEs8vd4LYxBeKpa37CIQEn27lMM96FBg1gyfcHFNp+LCZfT4fm9kf8b7
-        aFLoFdDjYr3plGVVyQSr09E5wHu8cepLND6kJEO4B4dK3eR5X+RdB2g1yAnePsV0CteBCdMlDYnR
-        2arBTeEzIeKlW+Y+BiMVvWNjQ1xdB6Ll0QXx5jReIBf1L3Hd2zLtX/0mh5N65mTXWBWfNMrXAPz0
-        xRwzL52kSB7g9/zFMXKN1Vj7R5RU+z3beuIb8dHRMlj3k8Z2U7nnzJMMWbmzuKRD8ymN8X5+5xB/
-        ii/ZY2nt8V07Juj3/lnOXiVtfUNQEu52WLmCwL+/+CgBbph64ULKZQhyyINcxGG/xeXSG00fnuvH
-        nlmRjY1eO7w7eOkjMD0/DN60bq4PeWnRhm0Z2vNlIlamcjITHy+rW96OhTuGiqOdcoI3Z6EdHWcD
-        UFEzYPe3badDcx8BjdjZEK8xnXaiPrHgFUsnYi+SVTTsZFOFVZHbeNP3eco/2mmC16K+kD2rmceH
-        4VKj8oAL5m1HYgz3vbSG4TnesbwZi3JqPkYHYrP6YqXEGz58d/4Bzk2OsOAcOm9CkmBCnvhbclO1
-        K+dlxyXQ2PvJ/IO4N8ZDU2IIP2xPPCUevekxfip0lJ0XLm7xN+IqCA9IcnVBrI/BI2auWYVI8I6Y
-        fXk9jHHEga1QS1sQK7kr3gTatoDs/lwzcoy+3qjadoaMNCYUdsXIxz6WbXTR8AIrZ9yng9UW9aII
-        DgG9wPGWfrMXFcA8OTXR2NErJe+2keVH2gkUHVZLPrjuYVD0fXZnZuC0/LufDg3ASabMXy4vvFsd
-        1wmcFJtQvvUbjy/4OgdEiUfc1/WBBqSe1/BtpwPefLc7Y/pUmwady8Egp5vF2kFyn7oib3Z3PNlm
-        gar7XpKhfN8ObO/u5XKKXw0F12/PZFuiZzodSE7BMh8tMyyr50NafzKob8aR0moBaPQv8QPsSdTI
-        7r4N+AjHswjyRfcJoZh5NNbb7+bh8zudz1M5jOajAhQLN/IHn+SupohBO2FoNJUvg0mu4OPFX6Iv
-        5A6NZ8PNQVjLQPb5C1ImOmYN5ES+dCz0oaQI1iGE/aki28V3Mij9yhaQT2hg4RhPvK+vJwkmnWxp
-        2GSjN4lZvIZ1mMt4PO8nrz8pewsVqzwnqhU3ZT+1RxXi3tOYlwk6+tUHfNnlTSx4knQ0bKNGdStw
-        pltO3E6acotlcF81c76Ljnef62qCtDlciHsNIz68yCsED/SM7a2XEY3lNaSw4zdK1KtYlQO3lxME
-        +1hl5nM6cY7ffYXIe3xQFl5ufHzd2BoqagXMOkmLtqP68ojYGWy27ZYRmo7ebgKqsCcj35VqTGn7
-        ceX7+8OpLMHQ9vX1JsLu2jp047uFMa4KpMuqtMqJN8ZVOfavqFLG612j0+G0agd/LHW4rlGER39w
-        jPGrpxdw2spkMVoH7cc0NgU8jvmBuJfdCzFz/a5A+Cg3Zsz4tzwGzQC6Zq0o65KyZa8jttHSMAOW
-        zfnl4XHpgykHIVPjrc/7UjrVwJkesS3/vtrPOShl9BFNyub+4o3o4H7lV5J3bH9Knvzt2ascqGUs
-        6Opa0HKIlGYCgVlnou77VUmnpV+DH9gO2V/1jTEKdD0BrC4GC/L2WQ7n+Dih56embO9hlXPPXuRy
-        b9zPxH3v/XRMBZ7B51mssTTne8iNdwErb7Um/qYayvH5FCQUg/kgPlGf0Xt7Tpo/+dwi7ViOIW0e
-        8hl/41//Mab+UXRwl8kHI8i8iJvCc1CyS+ASTIRbNH3igw+768fBqDGdUhTfzQDZ2//gZfKp01Fn
-        IUVdrabsRHd6JA3GVwASvCJi7y9rRCenOSBqZRoLtcfG6yAZJLjVtoyVsi7KQVufGvRQ/IiYB2J5
-        0xOtAfpun2B+1OpyuBifA3TFxSREqqt0PD1cXw4TTom9cvR2fE9WAzi9RCzd24L3FffLHJRbdSAz
-        PynH6qQ2Sia5NlNX7FOyW7vPwYpyl+DUq1q+azcXuSmqNxYOb2TM8c2V7mwCMUJLjppkkwGsuUCw
-        dD0Sj0qD0qAl3xqMXKV9NO7rhQA9cjd0+bHA6Hayr0NMui0eDsWn/eIuzwBOa0oy92zw8bq7N3AQ
-        kichisKjsZRuFTJershUaVmiYYmRKRedF9NIPj54ZvmrGmr3llP0fCw4z9i5gAUIO6KFkZ8OqMwA
-        AlW44POJx7zbgN5AVmwZs0RH9oYDUh7II41GDE/eRK/65A2wM3Jgqs8DPvnSt0Ots/fJXB/R5Dlx
-        CGa122Lh0yQR3UyNjEYe1LgX127Em9MmgbxhBS71c2zwrb3xUWTtGqrEx3c71eNbRPp6uJLD04tK
-        RtdiB9Wz+xBcq4bB/ciSkCz4VyzxRxbx+L6jf/DD/tqEs2+Cq8063gXM+6yXBuPC0gZq5RreJHHB
-        Jywv5F9+mRpkLPr1P0jiISB5Q8WS1pbxQLR1WmZvVqLxwSOJ0ca1M3bdCk9jyl41wEa/dUzNb4XH
-        78XnCJd9/caLAuttJ+ieLaenrqDCku3SYXk7FmjdfHYs6qEt2cV2bfT02ICXbTikDZezEAVO9Gbe
-        3s4NTk+rBqbM+NCqNKuUsQfR5V0+GBhhp4p42SERtppgUHHm39OXOTraxfqEN96zSlux3uXwBLfC
-        08yPaK/0tTzzL7aPj++y115ejM7XMmNWr2yMwRBCkEvKBObEb88QvdKp0YyvzKe5w4e6yS2kbSSb
-        wpeF3nS8lxfA6tYn1t1O2nGRnFxwFctj5vWpGQO47xBer9PEfCVqUn5WZAoGpAWe/F5Nl9dv1sFL
-        DAJCwHkjHpbxV0l106OLeli0tHifjrAVjjcqf8E0+A8PRaMXiF22ddvZy1FQtMuRk3uXGO2YE9UH
-        pgYXgsWlVvJ2l1qA7/qXjg46G0y98wakY30hmpRMEY1PdxeS1aoiBoyux5OsWaM5vsREphJ1wqGq
-        Ye5/VF4cX2gcls1Bzpu+YK5TsnKY8Qcl3s0hekCUaEjrZw61tNrgcmzLiErb4AhITK8/vhz1bi2K
-        EOekIG7iX8speV4H5IGazfmhM5/cWWjzfl/YVhj8aAymqYJz4O+Jcz1BOe7qDYVXLJ5YvEybtlso
-        Gx0JGkloT9OnMb71w0H+5dPj7sGbStXC0JbayParOi3751OSQEpXFrNf9zCiyfM6QdRFS0yJoKSd
-        1C4FeYOXR4YFFTyaMITh5T33ZK/pD2P0imIAWLCQlmr5bXmd3wpww+WLbRXJaiW2W+qglFNOjE9E
-        jX6xezbK6tNJJPCHj9f3el6gxU5KsXg/de0QWD78zj8t23uRDu9TUSvZqGFiLnqZz/xFluZ+QfL5
-        fQbtbFMk4YtLrqiReBes2hyFubQjW7rT09UxkQuY9SQeUK6lvFipJmSamtFPxy8tPVJfhMvl3lPw
-        gk/JygWLkbzZ3onxqqT0V2+oyYEwX0SRMRpxr8qa7tbEOikPb4pF14ZZv1HJ1N+z/nvp4O6EO+XN
-        tYlYfrkK4NR3l/gzPk/NqnfRRuEvOi1kHw0qvCk4EToyVX8PvA+9MoP9wUrwRjVOxqwnVbQA2P3w
-        LOULPmTA0vrO3HD5LWt9YxwU69utie0MWrns7EOndOJzTfy5Hrv1iA5yoR8npom1hfgpfmQy3JyM
-        mK9n305JOMSox0POtFg3jeWsv9Ccf7ary2c6JgFTwTVje8bvNh1hK13AOT9bFrV3PRpCTZbl9kuf
-        NDS6fdTlRfJAh+03Z/45iI1pfR0shSzyAxa6Wxfxjr5itFo3Jyy9OjOiw+IiwfLNEQ28/av9o3/b
-        zVclhnxUeR/vsgIVAvPxMIpKyzrDUdEtlz3MHpFUDqXzFkD/SDJTaxpzrtKTBe932NOVEWvGxIvA
-        RK+ApVTAnKWUL1IBNnh1xNKsB6czW1uAYrixneb6iP/wdDoOiJ1iGZfNfS/I6ORsTabl0RqNeNwd
-        ZXYWbOKlhtS2x9XyApPyEPBQnt98murSVv70PzOFlhmDGit7O/2QX/3MeKzCL94Oa9y0E6OtDV9D
-        3bNw/669EXlDreyaqiG+KarlSheTC1qgW0VHdwmcH/qvjCx/JeP15fXwupnPbYL9Uf2Dt5yUUQFQ
-        iXtyXvle2tJdjtGtvzaUqUvqffjl8YCTmAjMf95W3lgRnKH2nl6Ji/29x3dyKEHuhTXxL17mcYk4
-        MljPxRvTwzs1hpdmSMiAa8HsEIHBnw76yva72PzRy5P2CDOQnOhA35ez2kpOnetAL68lc+b+M1V9
-        0sBgxiXbBpbhDdf9+gtHFt6ZnmVmK/br1xoN5rFkrpCoBg+u5ADKrT6wGU/TP/Ux83NGPq+gndaX
-        nQD9bksZOWtpyi2hWyP3Y0zMthAph/PmKgEbh54Q9PgaL99RLDkKkoEqxVE0Zv4XAh4Klflhc2n5
-        DeuVPAydgBfWJUjHOF3bIDDzzALtW6RsceAXJLS5iseFsmynKt9gmAK7wqhMPcT3ahqjOHl7bNY/
-        qNeThYU8CRV0g5qYj62ghUDlrUs8yNponNpMle3jwsCT5cRld1zVFYRk3bDAQSuvyoZBQsX1/cBC
-        WLy9aXHqws3M75n+iWNOhfXnCEKqCXSTHpqWpnZngTRpR2aFuIlmvlL89CbbpbFsdKOYg+zsmUV+
-        +RiPVRbKPbI37MZONZ/xSwUi0QVutrvK+Ag581HN3i6Z9QoajVZtlEnfb8l7I2eo+wBIiAanHTnb
-        T4T6T6qZ8ExaQnZaevJGp7VkqOrrkzj54pEONWw62DyOX7pSPscf3zii00UtCc6o7S3fE/7Cgx5E
-        dpsUweutyyGExWq5Z0bgi+2ESVpDwXhP8HUTG9yTPBmutvwkeLQcLrb65MMZNzELcCW29I0WPmpU
-        dWS7p2yg5ZN4R7RdvnyiBhmJqJjla6gruqXN9Nga3Su3KNiXd8KcOibptN3gRJ7xi9h2zr2mmV45
-        fPcoZH6DrJZX6BSC6YYPKl9DzkfTGB+K9pU/eOW9l6i/mYMEl8utx2W56w2+21sXuLRayayDLhrD
-        oT9acCNCh1cbOeOTuF9mwG3JIlut2Rmf+r0IEV1gc+bTI5+0YKPCZhHadPF5BeV41O4YLtnDYm7E
-        DtHKjywR0eyLZz/qU44/vfrzL539afA+3XpnwY2/JFzP/UT8gCgBXfgm213Oj7Iv32BvZn+AhubJ
-        85Zq/JGR+0pTRuphUU45fl4gnwQHawk4fDoGmgDtplHJJf5yNMz6HBJ0R5j3+gvR1JdcCKIC0+F7
-        w2VXe6m/mvXhzz9EXU0vB1Au9/jnxxksXQYU3komE6IusTGU17FAv3o3qu+h/abpuZJnvCZqGC+N
-        T3J+YnhGyROjY92X3XU/fJWfH2BKxSMdVtI2RrN/x7C/KDnL2Pkhj0LdE3xZHFJ6C3kGmdi+ME/Y
-        ineb67ZC5yl40HaOX78quApJ8Dkz85vylG6/FUDoHwLiaKey5cvn8gK25+aYzX4Yz52hAO8kEean
-        Mm/H8ek3yMiFmmi7vOd8M+kWpLrlMVsPJ2/ixdVCc/8geFJZO3XaisKh8Y9UeTyasvnxg/n8MGy+
-        cbtpeqgQlTJOyDZvW2rV4VpRjuKCWZmjGavTy1lDsx5E4j3qxOt00agAi+6ZbAOr9AblkxxkbXIu
-        dKr6TcRPcZND4VkGMTb6FPGfHqq2MZ79zrxt8mhj/vw09vOfupvz7FB0Gy7sfGwaxK7smCDyORjM
-        6LRF2ev+rYHsXq7p5SjZEQ9W00HBcXBlhvGp2vat2A/A6s5nu5KS6M/5ifmZEI8ojHOJaPLv/FA0
-        mJLBiu2zRtuLe6Cjt3+Vw1PahIBt6U/+vcnr0hgVXNoxg3xGYzqUU4yAdI+5n1QlS7JGBpPrFcO7
-        3m7Hu4N1SNnTInqUBu0Q9mcMZz2kzBkzyeuN1m6giVqbabO/xs206tDsB7LZX/O4ekdfdBylmOj1
-        pi/bd+LlMBqhSHB/Do2fPyJfHOFAp0G0ouVc/5uieSwwPy1Dg7Ggr+S3kzJGztfKo+bjVsld0ke0
-        KUaVi5Gvh+AHrsP08Omh4XNdDfBMPgQv9tIDdfZyI8C0kd9se2Vqu2x6sQI5/ZZ0/LbUm+hXNsFb
-        NJzE1yMzBjZoE3RE3JPbM8GRSMVIRGrAJjb7IcZoZ332w1tiRqeH9/HzQwdNgiSKvpOMeE3AQk2y
-        kQh5SRvev1zxgnaPzZouyutQDns0JdDYg85cSf8i0VfNB5rnIWR/X7l8OfsdSMgeT2Js4GL06ZCo
-        kFqjQZ/BtS65M1gVrAblRRUNXrzPn6hDquGffvOhkhcr24Tr+SowbaGcWlaSASASli3Tz+4nZeFR
-        8SGPvY5pG2JGP76A1quqZtrn8TD66DSJoC1HNvuTPp9+86bwpZ+o8IjvaTX7ySi/iRnBXqam06or
-        a4TMy/sP3534ID9+9cn2u7tj/PQIHAt5hfMiaNNpsdMlparT5x+/lmvrKocVhB2d+WrZLdXgq/z8
-        AWzHdTRUTQiwfiZX8tNz3VVhOgTfCei0KlblVxqWDWiBuWVq8zEMyXIOOkplEZMdWtpozJ+IgjA2
-        mNgtoKgLD8cjmJ0Yk9tkXFKe2tsDJPEUEG/F9+3oX/ICjJicqHDPrlHvX+IC4tc6Yvr3AO2sV0XY
-        xerEtkquoP6Xf+tsPfGEApL+6hf1YSIxe+UU5ZS2T/unL7CQ0cabonKZKz+/UT8KJ4PzW+NDMZ0r
-        hte3NaJSJE/gHA4K5XqTpysFjhW6relAJzyJ3uQ3zgFEgwn4fDk/2g/yhgqCYeH+wdsOH9sQrChz
-        SZDd+3TaLYwOynb7xmzme1Nwbw4wPSyD6bP+mPKbLoE9XRdYCdqvN2IyXZRe4AeiT5vE40wsGvTN
-        pJFOyUYzxP07nuC+X2G6Ru29bbTX14XVsHjRVIlHo4/TtQtO1ryIpUYMvaqyMGG5V2LiyHQ0pnOw
-        tcBIj4RdA3OHhg24XzT7O1jkPY34xdZd2IVJileXs1qOVvY9wipPKTGOyI+G9YhCsPG0ZH5tHWc9
-        54W/eShdhsHoDaMYA8zzix8fMobgSBN5eT3kxO6UJx/mfgWnGnTmHeu+7Y5x0MDoPgsc5/iIVoHb
-        SzDHm+n94phOL/dU/+ZvZHsPS04/1eYLm0l+EH2Xbr0+VJzZjwRC0v7t86EVDx3qzKdFy7k/TJtt
-        loEcLTjm0svxBkd1ErTXXEShr0xvpOwLf+Kz3Xnf9I+eR6+bTIxbpJWdISTwm7cS5zefCaC04ed/
-        +VtapwN7PmJlxs/Zn36gQbMWLmjCU2X3UbH43C9NVKVFytRKbiPm3lITZr5PrCpZop/fofz0I1kQ
-        DS2TWv8q38PdIU4S62jcNMNRkUdpJHqTjQZrqkQEvcYlVT6TUUoKvQpwHWqT6LbQlF302bpwPxoZ
-        wc/zth1TAWW/fkDFjITtyDZyDFEXLPE61KTokxjbSpn9ZIZnfKCxqLu/+mUaN4xoFZZxAy51Oxy9
-        h287HJJHJf/w0gmEvmyCciei6/P7mvknS2nHc38D4eHMYlnwuPQYnzV4PPIwms/nwOXsgIpq3czf
-        ++Q//YpOfp8S02mziJ9ejoyq9JEyI/3c2nGeX6N5/kBMLXm340VYx3/wVT+aLOq/r0MOfaztmReM
-        qJx6ZtqAe8GhC8XoS5Y76wLSyVTYzog1b7g5nw7yCRxGmC3yGR9c5e/fVsB//uuvv/7Xb8Ogbm75
-        a14M6POx//d/rwr8O7kl/xZF6d9M+rOJQLvkkf/9z/9ZQvj70zb1p//ffVPl7+7vf/5arv6sG/zd
-        N33y+n+v/2t+2n/+678AAAD//wMAP1WwTOMgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc9c72cc71244-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:19:42 GMT
-      Function-Execution-Id:
-      - yvvldstgvsvm
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '74'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 1dabd53de4282b519b0b347d06fba149
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 93d0b7b83f501e32a6081a99294f07ac
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5471'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4SST2/bMAzF7/sUBM92kMBokvnW0xBs2GF/D/MQqDJtq5EpV6LXpIG/+6A4WYoE
-        S698JN/vSdyjKTFH3SjRbWfTxcf3T93janm/eVE/v1Tlnyf7+cP8k/vqn1c/MEH38EhajhMT7drO
-        khjHmKD2pIRKzGfz5d00Wy6WWYKtK8lijnUnaTa5S6X3Dy6dZtMZJtgHVRPme+y8aztZi9sQB8xn
-        s8UswfPyszBfJChOlD2Xsmw5JKgbZzQFzH/tsaVwWuydJcxRhWCCKJaI6ViIY4R9wQAABUrj+rqR
-        UGAOx+JRoK3EYoHfGgKmrYDhIL7XEQtMAHHgSZUgDb2WwjqbyFagMpYmsILQuN6W0Ac6dMaRddRA
-        u7ZVXMY9pQNpTJgUmLxm8KSCY8P1GeQ/RhCjKcMBVFmaqCoLhivnW3XglUZJhGbS8Yn87mBLQr41
-        PJIdMgah7oqjs4pHhBS+38rx1nsUBadwz8ruXuiq7xbRBZD2Row2oR2pVsBEBwDi0Hsa065AtVA5
-        a92z4fraTmndeyVkdxDxqaqMNsRid5f5Q0dqc7J6Ntbe/s03r6LAcfuQnM7wOH11haxaGo3/OV2w
-        KV9fHu8oxN7z+DXKCeIAcuQpeMAhwcqwCc16PD/MMYjrMEHDJW0xnw6/h3d/AQAA//8DAGvOn0w9
-        BAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc9ce0ba71101-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:03 GMT
-      Function-Execution-Id:
-      - pbmewb1rp8v5
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '19929'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 1cc694f7ec27d332fccf8ee536d2fcb3
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85978'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.681s
-      X-Request-Id:
-      - 097693547d7c7d083fa14613bab59e0f
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Write the
-      task_id into the file output.txt Shutdown\"\"\"\n\n\nCONCISE SUMMARY: The text
-      is best summarized as"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '292'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOTUvDQBCG7/6KZc6bkH7HvQkFRcWLB0WRst2dNmuTmbAzocWS/y4FP64P7/vw
-        nCFFcBAar6Hr22L1cJ3XzVd+mU8lR3lb55vn18fb9incHe/BAm8/MejPowzc9S1qYgILIaNXjOAm
-        y3pRzeq6WlnoOGILDva9FrNyUeiQt1xUs2oCFgbxewR3hj5z1+tG+YAk4OZzC//qPzypLSirb//I
-        cjpaCA2ngALu/Qwdyq8zc4vgwIskUU96KWRSpEt9ItE8BE20N8rmmJOi0QaNejlsUjSJlI03u9Si
-        Id9hNDxoP2ipJzWe4mVMRppBIx+phNHCLlGSZpPRCxM4EOUeLCSKeAJXjR/j1TcAAAD//wMAWEdU
-        8m4BAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfca5cfb6a117f-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:09 GMT
-      Function-Execution-Id:
-      - yvvlzdkld8xw
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '2345'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 935ddc3ec26e3fc83995dd88cb4b84e6;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89455'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 362ms
-      X-Request-Id:
-      - bbe6d9f4186af1ddaf62b36bb61890e7
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Write the task_id into the file output.txt Shutdown"], "model":
-      "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '130'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6WxOyurbl+/4Vq9YrvUvklrDfEFCRS4KgiF1dXYCIoMg1AXLq/Pcu/HadPufF
-        KjElyczMmGOMmf/4x19//d2kVZ6Nf//rr78/5TD+/b/WZ49kTP7+11//+x9//fXXX//x+/wfI/M6
-        zR+P8lv8hv9+LL+PfP77X3/x//Xk/w/6119/F5tXSPeh9AFzeAYDmNX8SYIhE/uRiWkM7wYqqO5+
-        9858zdEAsF4Saj0dkwlL5JmwmMsNkiTNMyZdMgj4Jq2NQAWfbFZVhJTR/g7Ys8mjX3YtKGFGhRc2
-        wL3s5yJGGti854AipMz9tJd6F8K9G9P0Ow49IXOUwSd/2xBOi01HJPwNAcMvj9SuXlLPkr2uw5dC
-        GgIFcHIme/+YYIB1kZ5255DNoms2kN2JjJ23d6yWz0aNoBrfNXw0QBcum+yWQOejDNSYb3JFRKrZ
-        8HxRdggi03BEUz3bIH18D2SjsT4c+ucJQveiyUjU08SZbzlB4L5DW6y/+50jpPm9A6/ok2D9uI+q
-        qftaHZTqd0/Ddb2UNv0AH+0mJluZ7irxPk0+5MxXSS0cJwbNP/UA46sZUvNGMJjOCclk3Q01vGOB
-        bizSBkOwPWsT3XtHAibwYROUx6nF561RAdLARgMT7ws4SkwCFlOJE3As3Te+y8CsBOVbcABYRow2
-        n7tm8NL23gFJ7WZq0Nu7Wuj1UytfNkAajY3vTLuUXcAoTgPWVNlIJ+htCCRf5Y3x5uGzJf5MAmT1
-        ssOnY+k7M4CEwOFbQuxU8AkYncoEUsR1ZFnjMfPOx4Jp01Xk00IBMHEUdUgSMcOOVAiMETe9wK5G
-        R7rX9mk6x4kcK+cT/yZSDUG6vJ5+B86DfCFy9JaqxcK7BiY0k+k+iK/Vn/1498jCtuH26WxBJ1eU
-        u+xQh5uZw6IijGHBig4/9McQjplxESC6XgndBYMXLp0vT6AVDhg7p9POGD1NjMBbdBfEJ5sXYG7w
-        UoB/ozsy46FkHVMuFjiVtYtmPOhscq9KA8p0HkkjFV/Web1cKG262eDjY2ocsuTGpD5kzcE3ywVs
-        7lRQwyUoAZF3ZwZYwGoTxv0R4EMY3nrR+vBvZdsdXkSBAqim08cv4ZqPSKWXIJyut7sN3YsuU43W
-        DZuqk+xDJZUEfKumDBA83HXoClaG91029zN73i6wS60O8QnaVGyWtVrxyyWnOKyLlO7g3G3UzfNA
-        pEd/6Udq1zZkZpej5d2/jLn1Zl0eppqQdgPuKfUECULj+Wioye3rcAFH4kJDfHsIvL1vP7n3b/bb
-        D+pVCzUan8t1CKxdjLXzeapI0JAGdlenJePyeYcz/hxiWfCcMzWLqaqWPFJymOGhRWSgOGTZ+arD
-        AT1sAnuLC/tXeU+gxe4v/KirOl2eHBfBXYt8JJxDHXTAmGNV0h4LIbde7Zmpni34FK4dNa3hWLHN
-        JpAg8i4JaU7xPp0HGzVQRfGO3qxB6JtLZXbw3bsWaSRtNMbUCUvo6c4Bm3TpGSt2GwvkL+dGuMd4
-        YCxwOgRmLSww2pRmOE9ERYBk4pG6cLDZENFbB89MTenuPIisk/vHAh3Ef+g+OpXpdPrEBUy7DqHt
-        pqiM6XBhzQ+fiBS0g9OXSTDAg8E9kcQ4AqiUmAIMDA3RkN7e/fI0rAAgNQ/weh76yRhiBI/E8xB5
-        eYMzjoczD4LEvOB9GDvOOn8bWN9YxJaAnXD5iEIHPdOeKcLK0RD6ieMATbQjjUdPZERtrByW/PZJ
-        rSE/Md79TBpc8QNrn+0xZDuJTtDeLjx1PdPrf+cJuoKdUXx6i+mwwHv0wyt63+taJdxOTaaIYWJg
-        HF5jMBxPmqWWA+/g/UEIwslXWgRtoz9jjxc0xoeCwMNwDCCRJAqcsYgPOljxhmzcK+pnpOqZ+t4f
-        MdXEpgZzt1ciCOgxRz2jXdUP0ukNIYs+iFXXQ89v3/wC66FUiRAxyIauFBbgaPyZJp8gSaep2k6w
-        lus9PrxF0xnn6kTgNXrniHb3Z9iF75kHR9nvkJBtD44g6EoCMd+d6a54js5AgSxA3hOO1ArbXSW8
-        8bLA2DIcbCf+DOYDGwNQZFlF3V7WKno1HR2eL9KOhvf33mHhkyl/6qM+wCWlO60uYH63DKyhuQDs
-        XUoSDFLjRRbmoWowzXxSTreS4mOy8QGzhXOuPHIAsMkbj3RBjjAB/qIgjA5tkQ77ZuQhTfQjdSc7
-        cOjJdghQdHFPTSPVqqG8DhM8Xp0M78bdno3aUvtwa+jpn++i4Mm8sj8LEO+P0egsSxAHsHKhQaNs
-        ezCWfdQIkBu6Az7eSM5Gbg4GWGEJ0JQ7x+niZ2H3q59U+1zdSkz2tgZMSmOMGRj7qdXlN2DcfFnP
-        mwOWLRoluD+wJ9keo9FYunjKVey/DHzzVDWc1b0JwZCWAdpcD0lFP4qYwBVPEH9WUcp6Y2updk5G
-        Ut9MM5zjUjqA48lesLEvWoeqhNMhwfOGOm5bh1MQyR1UFqjSoyqUxjQVGlTxWNtI6G9hP28Nkskq
-        eE5kcgrECHK4BQazleLjfhiMmZPPCdQkQ0HcpnyHTO1PLrR2IYd3OE3T2QBuBhb5uyOty0RjURst
-        A7I4N1TL3kU/WbJNwIdLJjTXG9izQbMioGv+DVvXU8omcuv+nU8Gb02AEniVYJXAGIemJjHGvOAC
-        n2Js0ZV/VS2jlwH6HDuS2meWMZfDkyjCyy/+5Kcoo3sEtrPdYP3ZeimNpnhRNKIBMt/Ui8G8GtSQ
-        H+QXxrLLV0tefjg4WdYF67v9i9GjXC8KcDWC9/FJTKdij5UfXuDDpw6MRTbuyo9fUpfc/XR23CYG
-        fX4NEN2ofT9JanxRrrTB1L5NujN/ho0L2ufmSvd5wqomBNqg5pWjY1sVzs6chzKBQHJ8au/VspoH
-        FJcKzl83fDsT21nyXLbg9zsE1FeaORw4Ie6gZkOHJuv4Xz2H+Ps5YSwMJpjx61wr8HD6rHhTsLk9
-        UUt5b/ER4+jgO3NwXxIlNWqLelnQOSwdPQVE3zml5lkl4W8+IHPGEBu6ZrDtjfRvKL8mjeL4NvTj
-        WW05IMQuwZn3ttJpAMEFRu18wHqhXMJtUZiDuuIbtnpPZyPXXjToStaRuve6Dnufnifg38lA7cQ/
-        swZHiQ2D5HDBzma2KiFuxw4uQyUTapuLwdj5aIHQdl0altuekX6rCUDN4gg/r/U1nZVLJ4CXNKh0
-        /3JsMFfxWMIGLTE1kVqx2W2kSVn3m560WXbIZ7ON4LFAMrXcmIL1/DagyHOETQskYIKeSNR7EtR4
-        Vz3FcIpA4f7JN+n0jXvm6u/yx+9JekkyNgpPQYBTj01syHexJyeKBGDkRUq1Wdyni9fPBXgeA59w
-        bqIbMyxUHhJfyDECs1gtZ7+wITrdTBR8eyed4iPzoeVHM2riZGRU6myk4L5+YjwBIxUKcCrAnV3i
-        P3yaiOXmDdxIf2Pr0fMV2xzPHVzG+oZ3HL8P+agvBcCXSoWkV/ZKB/ABE8wo/8JpDrVqSZPj9IsH
-        mS76kU3wKiRw328VNG+XmZHbqcnByqf+1K/luMwIZMl0oGd+ycJFWCAE+Ps9UZP77IwhuRwCOLzf
-        Jn3aZuAwPeMk4AMer/HGbNgErwN0XEEhChc5gFR93wEHCR963F7acOWfHbQbOtD96dtWH02vCGj3
-        8IaD52mpFndTDQrfAYGeTN1x5uR21BWRf1r0oHRGL6z/94cv7oJhDOciPmiwF+8mTib+0c/NXLyh
-        LLKGQM8c+3bQMQSx5BhIfolWvyT6LlAjn17JtoNDuBy4N4F3D+cYPbJn2hb+MYLlftljN64n1u+g
-        3IBl/2BkpjulX5RbVUvaYPhEPT95sOLNG7S8+abe/bUAVnGvSc3iJUVFcxWNuZxeNfjxBXOfXnty
-        Er0CjOeWUTe8tmC4v40O2Gw+0Z0FHDAfn8CE/m3c4evkheE8p4YGyUeRsaZY0b/5EipSBztf78yG
-        S+pBqHq3iu7wUILZ0zYRLM8LpW58EBxSHrMa3m4gxKcNkEPKy8VB7Wr3iFGLO6OrWBeBp+U9qOVK
-        dj9F7FWoL/Q+4OMFyWzl84V6TzFD0su5g/l43GhyGCGBWgt3T6eItQXczlaDb23Qp5P1OnRQSuod
-        xlFtM0EGoQXB9VBQXciLvle6doCJ/JSIMMm6I3QaH8NT+XZpXMBDz8zdQQPr/Ih0TapwTL5mDHhH
-        yKjuCnHImJdEkLvWGt4XvW80d/6kQzsYTIo4/eLMm/OT+5Mfnig4jkjMSwMZxy7UHJZdtazrVTKP
-        cEQub0a6MPtcQ+OYX3/+gSF+bCjA06siZLZAD+a3yS7goYNg1Vc7sM5PV4QSj0RNd5XD7v62hOOp
-        e+KDeD/3y6qn4E63bHpwznL/w2PVeDxV6rTcyWHjJdFAfco8mmQvkk7VaQ7geOx4jJ/i3E8LnzTA
-        3R45FEvFkQn3K8vUzzfqCLFOST/H5WRCam1abPOfLmUXLJSQe9YcUurFruZuy0vwot9iil+W1E97
-        7cXJVbkZiJCYiInbuU0gg6xFsnnmQqLfBUspklxC2+tpYMRxbj7MxO0WbYpGBX/ive73n/rdej5P
-        YJRRjoAVzyfxZChg1cd0tyzfcPnGMfzD73/8ctWzCXR7c4NEbr9N2eW4EZSxJGfCHSTWj2kYIDW5
-        pI9fPoVLop98gNuaR6O/SZx5PNwFWB+zElWK/AWsCUNdlel0ob6OG4MpJC+gGfcBaRiHQBXSOYD5
-        146pbT2WdEr9cwYLVnZE3alzP4zfwlIDZh/IHAxjuqz6GCZh7lOjvM7GYKs3Dcz365l6/nOTzqpn
-        NFB8JgOp+loEk/TJAqhmSYSmyvQNsgS+D4u52BD1YwjG6ud0QJobC8FeLvpZ0/sBepqTok1Ud4xw
-        1p7Afn9+0XRbuOlMD/NF/fE3d/WHxlIqfPga+4L44u0ZDvI1UiB/4md6deMCLHtUWrCKNjo9KbbI
-        luksTXDVr+g+3x22fZkhD5rX9kRP5jkP2+TpDT99SH1v7tNpY5cxxHpBKNrOOpjR6JnwZD+/KP/m
-        VkioVyvKqhcoOsQxm91hrME7sG74IHdojXdUwvr53JJJx5ZDV70H5IB6+MhfGGCTqwh/+Mt5ePXO
-        4oqjJq14Sj0HSelnFC7JTz/g68vpGLWFc6ZW3M7CrzVfJvcxX2CnHRHebY2KUXObZNC5KzrGq36a
-        tnDi4WtsC+wR/tYvWRRwPz5JD8I9cybzcrHA6mehdsV7vrb9RZUjUtHTbkY9A8lwgdv9JiT84zn3
-        tNiJNjil5R7HwWlOSbIYAtSLBJM3Ug0msn3YKS84hNQndZiyxym/wFqoIKqnRumJIRxK6FTyDmMz
-        9Cvm1JkJJ9PmEPscmnC64iSHZM922PTVGEy5pfgg2GkVvm6okE6DcTcVPtxO9HAOdcbukxRAzqxK
-        RE6tzQT66Tiw8iscfurKYbQYdeX25lIkHoZXPzntwCuFWjVEsGeOTQ+XHiDg7DM+PevBmbR+GmD2
-        Eryff9bP2438hrVUfamzOXtsYEWRg1Vv/sn3Fo37A6D25vLTz2D0T48CrucFu+Q+hQtusA0/6UUj
-        fPNSjPki2Au8Xt6MxhtNTJfoETSwSrgYqcnO69kYH3i42Q0l3Vnp2WEotQ4wi6eU4h0r2FqvLsB8
-        jSY+RVvNINLxMMBLej8hcDyKYNkM2QTDyBVw1t8/YCiuXgDtZhyoLnFTWmteb8FBywRs3FiVsi5U
-        CkhyfqHn1r8b3dm8vaH0/miE8dbEplU7wCtoZALHuwIWswt1uLenLTYvqANE9c0EBBuLIjaKl5S2
-        Ymcq5xZm9OYTvp+mHmZABY+J6l+Fq7ppB5Kfvv3tdzofbzCBB968Yec7uhX1xTiDEi7eK7+rwoWz
-        PKJcyXdG3/0wOKze7HzlMyUZPpUHAKZcY28IImNEfPvCPZ3cRVCjzzzR014v+qk91DGAZ6xjtGiC
-        MV+IacLIHHp0Wfmt8H5OtvqL7+76MPvtz5/MXryHT3ap9PMkAAXeUqWl5h74KXi+Zgkm/aPCTtqT
-        /qO4gwWpvH/h1b9l84OWb6ijoKfodPKdsRnzAa58BXvoaad8JOYR2Om2TU/lzQiFenAsiNmHYXdX
-        duH8coNCfZ5DjE+9RdNFLXYL/GbNFo3oaYfsZDuDYvmXmYY6Fo2pW3gLxoIT093Kt9j367mwPj9e
-        RGyWqZq/22sM342zIYWltaAJma3Ln/vlSo3PNa3mA50yMExvguOi3xh//KdWMDHdf51nXwNHMhW7
-        XWy8C9ylWrDkliCJUgvvuIvdL8dOKcGqh+nqHwC2fQ0aBEi7//Tgqseng3qp85rwq97/ozd/fmSx
-        3DRjqaqB+8WH2rfNNqU764OggC1I8bW+hh1kjIMv+z1R3Nu7ajIGH8EiyyvsfqxT//Oj1ffszVhD
-        Wv5vPrD4lY/kY+kbfHE6L+r+ufWp4cz7cMXjAkYW2aGbut8wGk3+AqOctlSjB2QwKTjY8uGuKQTk
-        sOiHb3nzf/UO9UMuscH9TDoU+zRCqvItQ/pN7wRKaYUIvwdTOKz9EshQn2HUcrExrO+H8OH12AmS
-        I+M93crBe3Cuf+YjLndPkF/Xzvv5UcaKfxlc/UcEX+Kt+haCU8PnNfgg7ps34dzMTQ0zIDpELmuh
-        Yll7PqiT4L/+1LutY76ImmqvDbVWPtRfjiIP6+4VoG3cBs7c3t+FSiYY4b2Q02q5jr4Ou5tzoYf+
-        xvr5mpwVCE1HQZu3/ElH8a0Rlbu+tZV/oZDcdq9Jffv2QE/Q3TkiijhXeZiSup6PKZ3j6FtAVNwd
-        ur+234pdLlYMt6lByGCWF0BWvwyIdnTG9vn5AYM+7XV4jd8nbG2KxZmCfIrUMWxzjCi994v43WUw
-        vX8nMn2uQzUVp/sCV32Bd7VPqpp6RIGwCS2smfhhrPwzgpJXyAi+rYvR6S9egJz+Eqk37y/GBB7q
-        AQ7L+46T7f5jTINxPqik2c7YXKrKWH76rkvtDkEzfFXLgdDoD79QVn9v+V6OB/iKvgkaZHffM1/0
-        czWHiK16n0+nhz9B1WBvkUgnSXP4Xz1b+Qf6+eEMciwGsDlbq17rnT/6hIK9i80hqAH9JIoLKqwA
-        JPihl07LEHIwei5Hsk2Vig31AUlwgN8bUvmodobVT4LMbHIcTiIHBnvXwJ9fS763TZ3+8BmWxpRQ
-        4/7+OILZhdpP72BTurzBcMVBDkudQqxf47PBlpdbyh46Uar58xYsgq7EoOEUH72XRUgnXqo5cPOU
-        C5nQrLFFBqkFayulaH6QK1vWfhncNc5CNrF4TGeuzTSQT65NFmFkbAkGqYCfJT5iG0S7UOxCpYRw
-        e/Hpw0FxyLSiDaBTgR3++VerX7H88B1riZ5VE3m2GbyYNwPNrS8bH0FcFPW3Pq16d4AICutUcDUL
-        AuLeDJl8CLrf+tA2lPZgmi1XUj5LckTF6u+xpTUQyFReID9+T7W4q2FV6DzZHqJbNa79HPDTS/rx
-        M4dM6nQXjOVwxqGuVaz59QPd7Z5D5YYe03lzvnHwLaMH+vUftvhzSKAmmiPdtf7dGeuXM0Cg2AAf
-        k6dgtMvRF9ShqmoEp24A7FWeY2h+hgQ70tmoJtSZkfr2rQHv9p3M/tT3XDMDbPi6wIjv5j749Q+U
-        Vc+L2/mVwPr8fJHN6X0LSfQIOpl9aIVt55H1y+VkcbB96hbe1RtYzS8zFKB+vSzY+xiCM/7Oz8p3
-        iEiNgS2DhxOoRdyW6l1/ZSR6JA3s/QtHpDjx2BK62wnaz17BxsrfPl81M0GeHH0iMzkN2+8+EaDh
-        F0ccyNyHTUeT88Fc3GNCNnrb0+PIfHW71w5//Ew2NC6CQhU42N6rej8n1DHBy/rusRM7bTVmIDrA
-        DeP3q79zqeY0TBDsPOuKb7T6VtN7p7zV1b9Ei3bZ9Mz6wFo0X9TE9uNVgcmZ+wK6xBB//dx+u/a/
-        QFp3Ejaa2qsmrVo0IPu0pMbKH+kG+5G6+kvojYczW/PTBz+8/vGvKXtXFvB4v8Uxyy8GW1oHQQdy
-        C1n1zM9PhbD9GtmvP+vwj2zIwBj2ORGTZ2QskDEIDbH20DjveacvDjsdrv4H9c7+ridq7JhwLlMD
-        nVtfdmh91HRVV+4etaulcEbzmb5h5g0c9vzpwGauvejq379bAf/5j7/++j+/GwZ188g/68WAMZ/H
-        f/7XVYF/Jo/knzwv/JMKf24ikCEp8r//9e9LCH+3fVO34/8dm3f+Hf7+11/bf183+HtsxuTz35//
-        Y33bf/7j/wEAAP//AwDnoBEa4yAAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfca726b5d1041-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:10 GMT
-      Function-Execution-Id:
-      - pbme52vq34dz
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '252'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - f738b1af12886297fba45c0ea7b50048
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 9c5ecb63a4996b946555161a4a7fe863
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "instructing to write the task_id into a file named output.txt
-      and then shutdown.", "model": "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '157'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWxO6OrPm799PsWrdMm+JiKRZd8hJ5BQEDzg1NQWICArIIQGya3/3Kf3v2jNz
-        4wVQQpJO9/P8Ov/xr7/++rtNqzwb//7nr7/f5TD+/T++1+7JmPz9z1//819//fXXX//x+/3/nszr
-        NL/fy6b4Pf67WTb3fP77n7/4/77yfx/656+/V725oV5tnPvZup446Y0g9MVLZbIxbPcA5/jxoMbh
-        5iHm3mQX8euCp7Yuryr2uW0LSA6PA9F4bGqT08YL2nmrG5Hl3tWWA0leaO/rHb7bluRMOedI0Kub
-        G3Yyw+wZzy4v4E/8SD1FMFO+wtcBjm90pvqs92hamR8A17/sqZWGSzrzTVWiWfXvVI1CFa3txEuQ
-        DLsLtqRedxYJ8wAXneTUFWxZI9VcmKg/XlZ4tzm8tGmOViYM7HbC7iB+onl+HARo5/eV2jK+a4PT
-        317o3tUr0jm5iTZXV8zRQT0/qasDjqZ4mSfoHjD5m0ecprN5ehWoDRwN44ey7uc8dVwpMcsUGxLL
-        2ZShKIeRZyXFtf5O6SVcdLhUokP35kbQZvRBLlRbTvM7Vr+0Th1sETwfLGzjsOpnxwok5KzME/YP
-        eRMxTVNeMO3qjOqSDek8PMoX1LnFcILmN2LD+6SCH5Yidoa0c5Za00MUNzGP43rca+tbkwsomjnV
-        X4LbWlsS7pTBzg5zsllwHS3vgyehZgwSetz7Ts/WaZFBk6uNz5ST1zNc5hIU/kyxPy4Nm6vrp4O0
-        f+bYUmfPmdk0cnAooxTvo1uGpsjAJjRD6ZF1aV6iiefmEyoOr4S651xwll0VCNAvmon3kv9irJ2b
-        FkoIJrrLedWZLafUkX48b+jOPUE6V6eW30qNONDDw2kYu+JtAIN2TwibSxQRrT6E0KBJoeo2kNFy
-        53QdPvhCqbWILZoo3AKonKLCt01xYNMGFTbw55dE1fTTsGUbygsyH72NNeelpMuedBwqYsEj41Gp
-        +3lssw69s+VN9dp9pIM72zy009rGjv6YtMEXeB0M5+T724pMGt0psYVW+0zFmbHhHHLTL5ac36YB
-        B/VlFwmpmAhwCtsDVWn67Kf9ZnSlraMN2Pwwq1+TR+Ki6Dxq2PykqrZOXhcV1b3kYnPmumiCuBYg
-        s8qO7upVxZhdblp4iJaJbw9nz8b3PZTg8WkLvOfkKZ0T3A5QOWXlz5ePEvHDqswAr88JtWPFQ5NH
-        VHVl4UykKu4+0SzmMYFVr2+w/cgqNu3fE/nFC8VeVWgtnIkC8T6TqMkNp4hxy10HLpUDf1JVBbFT
-        pOYIdbs9dcXHLprN63iBK1+6eE8Jh8YYz7osdue3/5zajC3GW5TQgJecoCJzqilZdz6QdVr5nH27
-        aCwszRKOIdcQoSPXiJ1jRGBlxxO+eHndT7tPGMrWsU++4yvSeZ0/dVktdpQaSyD0S67JMaRmjKmX
-        m1dtcYnqwstJrv42My9oulERwMK5SHFPVhV1LYVAJoBNpGkUojE73ziIz1yBjTy8VfPzOMUIicXo
-        VxFVNebvpxOq5quE3aDaR0y3tgKy/fJGcdd4FZtfLITkTSzqhXuxIujALnKVcRuyuqwjRORDCXCM
-        CE/GdWFHkxgYFlx7DxH5SYJ+pr2ho8urjbGhHiQ2nrybCtsm6Ol5LQbOsvZO4i8+/JWQtGiRzc4G
-        Vt88uveQgaaIheX2ect87M7NCbHrc1zAwWKDTekwaBPTmYpOvHmnmnxg0Wzcaw5amqypYcynaCml
-        rgROdDH1FraqfvkObQ3+ivd2NERUT8gJbpuwpRrPHfv5/nR50G3iUXcqSjStwpMA7mNK6dGRN9q8
-        M2/11riX1N9G8dDTK54D+coXrv9s76m2THAwYZeSBeuLI7M5iHoFXq40U18qZjR9VESQjcOaHjJT
-        QEOFHwPcr+2RXiRx0088t72AmBoLtmP36MyP0Jpg4MDB6mR76bqZN4JUc7xE/bF+Vb3wvBEEZmDS
-        S3ld0tE92gC7dFj8OXXbnoYPj6C1dS+pd2oLjbFXKYLUSIMPrqumG7GxOdiYi0C9z3aJ6BVvQxhz
-        yaD2sN1WE4VjCK9nxOPdg06I3cIPgbv9MajaZJU2lfMUylvz9aL5O1URyWiQANGOFpFO8SlaaLQK
-        EFV8H7trrXfmbaNOEFavlvq3tulplus+FL5WYk3frNFwtSmHolCxcPRdjyFdngkI27nDNli9syii
-        acE8xzb1342psVmgi3SPk5y6WWmw+VkNIgRrOcW27vPaeA9vFjjh+oL1ojS0teccLtI3H+L9jTyd
-        KRw/IezVilF9ce5snDsgwH2GD9Z4TWVUeB4JKrOTQOOctFX/G/+Hhh+q6zczEpqNwiF1FT2xxuPa
-        YVu6VpDedXtsGPK1H4xKCeRbqn0IfxZSxuqeS0CWCsAn6Cs2vz/GBOEx2ZPNWdIjdntdfLjfrB7r
-        d5MgMu95RU62N80PnegVffOPCc1Oy37fr40rmplwmBSeenI/aIu4tyUoV6ue8HFlVutfPrleK4Uw
-        KiqISR+UILbuFTIJoqWxcfYlcKniY73ddtrMre8EkYlL8W/9SWrjGL75Al8a847YDms88JfzHvuX
-        mK+mkt/qkvi2A3pAJ7NqiRpy8F0Pv3dQ/a2HnYloYVv4EMVuNS1bxZS5D/lg1fKjdLiOSgHbmBl4
-        h29jxPbXswXx2vIINye7tP/mJ7i1TCXybj5rS2xfF+lchTb1SLCJGNxF65e/fCFxg4o+EqaC53OW
-        32uwr5Yzsy/wiydDF4xK6IzhAkF4qrEDs1ctbz4upWYME7LNV3rPEzXhoHwcX9i23jeNZamToCUU
-        8q++cxAh27iDoJok6srqoSfjKgnQ+TS9qDkve2cJVTNHP/2kXteORgE9CngmfoqVFRf3v/8DoeaB
-        2sGUMLb6JC3KnaOJr06Sp/PSMBFeDyOkWedwFakVJ4enZJ1pImNZY/G5LLfbush9NjVuP8fuFP7q
-        vy/m5TtithEHqAvRA5vP1kSzbu5cdL6ttlQhY50yVIjcL99Sw1BbxlzLGtDyChdfTMMw4uuDN0Bd
-        XM9E+KSlMy9CU6NXUTXYUTZCP7LnEsDlIq6wWV7DSKj9lQW+Pj+wxT0UtOzlvEPN47mj+Ex2jG3S
-        QAfx846pXpA2Ig6vCdDzMu/Pm/M+4nWJS2A/ydFvftkG7qItLaF+pNHaPjHq76cLZGO/xd6z9NL5
-        +iIJmozoSvgtHvtBqZ6q3OXZhSq2p1bzO0l0hCNkfvOd4iz2xu1AiM8X6hz8tJ/dcpUh5VNfsaZb
-        XUqiLg7lZYMLvN+M94iJjQ1w1i4B4TxTQXOeat/8xKi/6VZRNErLugNthUqMy6DtJ79VYri9hZO/
-        Psdu+tWfueS8tQ1pmH3WlpAlA4TnvYrNy2ujLaCIElCmC9heB1w/zo8dD8922P3yRTV99w9y8sTz
-        txwoziZxWx0K+9IQ8UI7bRxuBQCe2wf++YW5SCQBwvV8wMZxWtjcFNoFCC1Mv9g0Ud/vlMCS5faU
-        4syK3xU5c7ILXJcLBH3jn1nHtETxtjmTwYtOaeduZV2iOFewb98EjV3xHKL+wb9osB9SbTluTye4
-        vLqYau7eYst3PdExhIYe0eCmrLqnpqQkp5cvZfQW0aZkgBylXVOjYDvtp3+kMhEyug+7OVpks7RR
-        muxtqp3fKzTq5sGH4Pi64VMQv9hETjgToxcnUE/CZzT388NEetB0ZD2f92h9vmgmVBlssKKqBZuF
-        tAhQ67knfKxXFWL+7cVDYig7f7q4T60b1cgCBF5LRDhz1fgIlUUuIZzI2ts1EbP8hMDFSm8Yc2+7
-        n492W6N3psa/9a6687QrEIe2tr/NQslZdkWsStFe7rA9PSNnCVilg+llH+rPyTOdhS4CmYkNIdvW
-        WEfTtA1yoBo6+HK7KOkS248J2cGAqF+ZebUY70mUDqR++Py6OTkTwjBBMxQevmraNpo9yyokpRVs
-        rOvvQz8Pt5aDw7Pysbp/NP1wNK4ZSMOVp9r9laczzsYc7gdJpHspaTX6LIYQ1Vl7w97WqhjhlLYE
-        N3pcyae5fHo2XIoLPNBm99XLijNxcZ7BuLNGHx18VH39sAjJ4X7Axr0iWm+dsovkPC9A/bo8oXm7
-        FjLgUqxhjA58upynQwnezM/YeQVWJNhtAOAd7Y7u2NPu+8D7vEBLi4IepmDjLPfDRoGWxmv62Ccr
-        rUNxo6KLwG+xNjDMptlbZyjae3e6gwZF00p72nKkhxTrHz5G5KkMPkRaUVLX28/OOAkrDmofKf6y
-        7220NpLakgbda6jdsJYRkx9qdKrPui++FOjHo13U6FONC/WSXK4Wi898MMekItA5eT9n5xtIH20W
-        yfpz+aRLpZ1aKdBMRriNjnrazk0Hd/EU40MQpVX/SJgCj09XkKVAKVrcVqnllnQt3TlzhP741cq/
-        H6nyCOd+MaTa//kVrD0Vvp8S+/FCOHAdrGnvHVtDvcTy6bo/+tz5qPZff0RgVt07zoKqSeehv+co
-        XosJ1uOrFi3z1grAMfYydZ/H+b/uH5+556/tYsUWf9wKW+dhJz7Z6KhielKf0LMlO6yJde8MnNu/
-        EC7jgbyg15DwwvsSuqkT8W4wTv0oTp4P1X3UqbutWTT6EYvRXa7Gb/zvIkZ6L0Ti4ZNjR+/Z1/93
-        NRx3ZeSjoyd913ulouWtrsisJT5q47VUA2UbjepGEUfz+vkRUdErBPvLk6Xf9bYQyI1AWhwxNMGZ
-        qD99TM9n96ONho8CiHuDkhmJuJ+l3LpAcNGe9PDdr9/9PcBH03q/czrbmbE3T/LPT1urhPbMPjnc
-        Ntjc118/EUXzyQ5csFXvTK2XkvW/egnSnluolZO2Z9vcKuEmyZU/XfcYDWi3M0Ehuwd1Y2mIps0N
-        vySzbLaEU5Nrz9pMOgFeXxN/RTSNLQu3LVGoik96ih3FYUF2DyDptnfCK3Lw1RN+jnAAMdW9PnHq
-        CPQFtHHc0ctlkqJ+b7QteiMupIcgQtV00bkB7YOj64uN4VWbzejWaHkrqz88ZwiEfoC8lz2axscD
-        Wk6CYwFZ3yqKE6NG88k7KjLslQi77fnpjN96KX3ni4iLaLHJqJTw58cJtzyjaDaS2obGEUyykmaP
-        jeElyiD7+DNWV7KVTq10qIE7KCW9NKaMqJ+9OyTq2YHaaDYQjS5OCApSehxtnzf240Oy4vAcHjP2
-        RAuE7/hXz7Epidf+x1PAKB45VgSxdSbefgV//NZXz6BlXCXhz99RIw+3/UjKSJG++pDIt6vTr9EA
-        KpAgONGgVRCi1jEtQLgZFXUNa+l/fhKS7LbBJ3goVX1dZg5YlD388esfF14veTA4V6BJALkzyNq2
-        gJxDyK9++VZR2gvsOnhjS30f2OKvyAmS7hBgfzkM7KvvJChiXcFKFDFneWFcot2hOOL84h7TyVIe
-        FwllESHs63+6fd/Z0LF3/fUDPhO+9QFeSWvjkzv16bI6hDV8eajPu5MTkWpudYhYllHlpHJskrVt
-        CZvb+MJq/Pr6TbmyQL6Ie4rN/efLm1wd5E3tU4dtFI2tPmELsdA21FoKNZr57nVBk8Jjet2MckS3
-        A7iwO5RHrO77js235iKAcS8oNuRTHS3+JHXQnzWJas1WTfkQThwqSXX16/IapotWKRlU3RCQVZn1
-        6Fc/gT/XEj2IacxYVWUD8jhJxcbhfdTo1PEisrju7U+bhvWse3QTCEbc4iT6tH17NK75H7/+05cD
-        05ECBaEffxIGHU0HPlMgMSafRj/euwozQTrf5C1Zvwll8+YVXuC3P6dS6p3Zu8kqik+5+Uef0f31
-        bEuGa6a+572CdLzj+ITUxAppLohiuritVSNrlSxEnuRSm6VcucCXR/qTY80pi5urCt3Uin6jnjzG
-        mHCNt+otMfxxXXTRct5xphTfPinhvn52FPNgkBRH4PCOz7b99NkoE6TC5fDVe3etvdGJk+XxOVFn
-        SG3nq09eP36MVT0RqvlwOlloOj1tau56J+W3tlNCoFgGdfgFO+tvvUD+43XA3ufpoHnvdxK8H2NE
-        /c720+13v6DYJKPP303CBmlvD/BCpyP+8tvoj57t/Tig+nE/pUQZ0gDWV3r25+pqp/yvXgWazqhK
-        G51ttNNah0cXj3ivWnY1Bc2kyMPS7/314TaiZTRSkD5hlBM+cHfVlNPYRcddEdEHd2ui2S8bHTkr
-        /UTPH7t2Zs/ZneRVLF6oq++KauaqpwtTGVZkGcroxw9ASq5AqdFyJZuzxs/Fwj41OK9LntH3Ke4g
-        2wzXH++ppkiILqjoVfKdj57N7yQ0AZxHig3ZqpylkCQJSIVVauXlOx3OW2dCfu0xsh63x2qSlYnI
-        mUdXZDLfB4c2JyWUnfduQ1bf758Om0wALS0LqmJh6Pu84FvpeqpD6m03NBoO/EmFjUCmL1+/OEPQ
-        iQIyhqnEmNprNG4EX4Dbp8L4T37e3y8vCe49+Nv9fKr4EDIOnOcJiOC/42r46iOAhiRE/PYXxmf9
-        JmDkAXz1esum1pJP0u2t7wm4yGMsL6CFsT4Cec9PR5st6xOgD1dkhLsHO21xVhxBEGcNNteJUv14
-        uuTv9Be+PFuTzXgv2nCuVwb2j5+Dtm7f/EtixmhSZ9K0ip8MJ0a74ICwlThFtPSrroXPXThj/avv
-        6S18ElmXX2u//fL+eSrtDg7KZk/kuxSxn5+EzCo6+qhXvCO4/S6Rv/0Ef3HlHFFxLbTQZtmeHh5X
-        RxvvT52XU2mn+zMfCNGXHxao51c8tdG77GfDkXJ4E3/rr2+KgYi1uatwOtkV1T7XbTW+P94ExrCU
-        VDt723S6ca8Wtmb9InMR3tIp6ERe+uVP/+Ieo8lnLIB+KoZvfHf9a+u5F/Td31iPq7qiPclzdLqu
-        c3+9Prz6ifqeAIy3aryLdiZi5fUjoFptwL99+ciy4eIFroe5+dYzC335oQrqcGHY3G1INSpu6v/0
-        NFn71jYak+fZh6f7UKl9PZbaTG9xDdlVCfD1669mz1JK2V8VGtlp9aJ9+x8tsmViEgmHVTVr99UF
-        vvmE8PrtxwcmTu4fwssX+yzshx8fe0+3FHu5uXF+fgV+fN/qzkr/px/w5UH++IvnpyQRKGQ5o/qY
-        Len89WdSW15fPuKTtiKnrcZB90wNf5F1qSfW5qxCtBD88w9/eIFc+Y8j4YzO7ukmDyQ5bp0dtrpn
-        hcYPqVt4opb++KPD8oLvAOS3QFZdaqeCqTwKxK9LHut8UTqz7dwIOhmdjL9+o2LjbEpw1B87uusv
-        LWJ765nD1tkN2Lwdn+jLDyX07WfRn/4lobEPoFMG7svjL9USjTcTvvNDZKWrnKWRDhN8/b7ff/sp
-        07mLdehVw8WmF2rResg+C2iPVUvtGGXV18/mqAnvE7avdyOad4ckATVvEqzF64Wxs20pYCmeiS2t
-        iKtZeu5smTJToP5XP87DreBkQkuT3PDEvn48uwCZhxZrQXd0JhkPMWrCx+RXBoaI9KuyhWMxKFRZ
-        aQe2hNNNgqHIazI30tK33/7Ir35R9xNgNj3Wuxz8F71hw/Ps6ve+X/yR06c99/Tr7yHntgj73tpN
-        1+fnmgNVMl0ii6D0s0yHDLErav4rvndKYMseJ6o/PZxOv/pshbfGX771YViZT07++fUfn2fmPZ9A
-        cRvHl9rLHH1ex1ZB27NuY9w411So/Y2N1h8kELk+imgMb6cQfe66hZMYQU/Vg+0DMT0B77SEMKb5
-        LIf9kdU+V5l5P9x1r4bIGje+YDxabTlzsg80TCj1ZWgdcuhvEzBVdajxsU3tD7/68QCHT6x+/H7P
-        n/5KmSmeswh6koM1ZDrOcwezHw9CY9ns/M2CzejbT83kn1/87Y9pAUuC95SmWEFpkE7x7l1A3gYh
-        vj5iFFHH2ZVgLJ+VX1zcnbbclk8NzsNK8Pn4whXbuZoii58m9qX9foc291itId2YF2zTpYkoLnMR
-        uINa4sPD2aN1En4KVHY6xkdbeGuDR2wFnOJF6a3jNGds7nb5p59ni6KoTafpOMDdezOse48Lm+7L
-        UYFf/Txvh4HRH7/8jX+IyUdbbmLl/vrTdP9wRWfqYFF+/Tuq6ZYdzdfzQmAyjlcfsotaTfe9mcCP
-        D/7hHdf1MsHlHb99dn4/0Pjrx3alE5KJ25gVVczbBKerccRaKmmMDe1JkP/+nQr4z3/99df/+p0w
-        qNt7/v4eDBjzefz3fx8V+HdyT/7N88K/qfDnJAIZkiL/+5//OoTw96dv68/4v8f2lTfD3//8tYY/
-        xw3+Htsxef+/1//1fdt//uv/AAAA//8DAJR+VSXjIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfca7878ae2a00-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:11 GMT
-      Function-Execution-Id:
-      - yvvlhpufeil9
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '46'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 649b408d80465f7f39e5760eedb089a8
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - d48b82d9676ed7ffb7da5829ba34e927
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to do this.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains additional information that is necessary to determine the next
-      steps.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
-      file\\n- Analyze the instructions to determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6533'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5STQW/aQBCF7/0VozkbBKEkxMf20BJ6qqhUqa7Qsh7wFntntTtOiBD/vdo1lOAq
-        Snud2XnzvefxAU2JOepKiW5cPbhb3Pv514ePNF1Mvn+u9g/ls6l4ufjyST9+wAx5/Yu0nCaGmhtX
-        kxi2mKH2pIRKzMe3s+loMpuNbzJsuKQac9w6GUyG04G0fs2D0WQ0xgzboLaE+QGd58bJSnhHNmA+
-        nsymGV7EL437cYbCoupLaXp3e8xQV2w0Bcx/HLChcBb2XBPmqEIwQZSViMlWyEYLh8ICABQoFbfb
-        SkKBOZyKpwbtJRYLXFYElvYCxgbxrY5YYAIIw5M3QiAVgaiwW5kSjBVOhY2pCbgV18pQ9jKEOYSK
-        27qENnQjaXglvEpPNTeNsmVULaOCCcMCs5dEnlRga+z2gvVnawDTOPbRJxi7Yd+ohCmVErBEZcJd
-        EwT1SCVs2MOmldYTeNqQJ6tpCMtXoaLbikA559l5o+SKNxniJJ3AXxL0Tbha2Y5/AN/eCuLf4+1t
-        0d6I0SY03ap5iiAqkg3RdIplDqqBNhi7TYqavSctSdmqhiBBxIdynXSkErKgtG69Eqqf+yaDI7U7
-        r34ydf32N/+PSyqw23XMzkd80vnrhqONDuNqb49W+W3//LvGOYlO4pWw+3/LzWT8/kyYKE+whT3i
-        McONsSZUq+6WMccg7DBDY0vaYz46/jy++w0AAP//AwA43yIrmAQAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfca809d0210d8-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:36 GMT
-      Function-Execution-Id:
-      - pbme7kantxw2
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '24083'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 0128c66c9918142a24cd829bbc2b234a;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85965'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.69s
-      X-Request-Id:
-      - 4f56d1467ab6d751cd14534935c37bad
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      below e.g. command_name\n\nCommands:\n1. append_to_file: Append to file, args:
-      \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file: Delete file,
-      args: \"filename\": \"<filename>\"\n3. list_files: List Files in Directory,
-      args: \"directory\": \"<directory>\"\n4. read_file: Read a file, args: \"filename\":
-      \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\": \"<filename>\",
-      \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7.
-      get_hyperlinks: Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary:
-      Get text summary, args: \"url\": \"<url>\", \"question\": \"<question>\"\n9.
-      list_agents: List GPT Agents, args: () -> str\n10. message_agent: Message GPT
-      Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11. start_agent:
-      Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I should start by reading the instructions_1.txt file to determine what actions
-      to take next.\",\n        \"reasoning\": \"The instructions_1.txt file contains
-      the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will start by reading the instructions_1.txt file to determine the next
-      steps.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: This task_id is 2314\nRead
-      the file instructions_2.txt"}, {"role": "user", "content": "Determine which
-      next command to use, and respond using the format specified above:"}, {"role":
-      "assistant", "content": "{\n    \"thoughts\": {\n        \"text\": \"The next
-      instruction is to read the instructions_2.txt file. I should use the read_file
-      command to do this.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains additional information that is necessary to determine the next steps.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_2.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_2.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Read the file instructions_3.txt"}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The next instruction is to read the instructions_3.txt file. I should use
-      the read_file command to do this.\",\n        \"reasoning\": \"The instructions_3.txt
-      file contains additional information that is necessary to determine the next
-      steps.\",\n        \"plan\": \"- Use the read_file command to read the instructions_3.txt
-      file\\n- Analyze the instructions to determine the next steps\",\n        \"criticism\":
-      \"I need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the read_file command to read the instructions_3.txt file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_3.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: Write the task_id into the file output.txt\nShutdown"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The next instruction is to write the task_id into the
-      file output.txt. I should use the write_to_file command to do this.\",\n        \"reasoning\":
-      \"The task_id is important information that needs to be saved for future reference.
-      The write_to_file command is the appropriate command to use to save this information.\",\n        \"plan\":
-      \"- Use the write_to_file command to write the task_id into the file output.txt\",\n        \"criticism\":
-      \"I need to ensure that I am using the correct filename and that the task_id
-      is written accurately.\",\n        \"speak\": \"I will use the write_to_file
-      command to write the task_id into the file output.txt.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
-      "system", "content": "Command write_to_file returned: File written to successfully."},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7667'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5ySW4/TMBCF3/kVo3l2q1al227eVkKCLgiEAAlEUOU609jUsSPPZC9U+e8oTUq7
-        5fLAo2c053xnPHt0BWZorBZT1X60eH2ddi+rH/b2buGXt+9evHlYfP4SXxWT9zdvUWHcfCcjw8TY
-        xKr2JC4GVGgSaaECs+nVcj6ZLZfPJwqrWJDHDMtaRrPxfCRN2sTRZDaZosKGdUmY7bFOsaplLXFH
-        gTuB6VLhSfzUmE8VShTtT6XF1XWr0NjoDDFmX/dYER+FU/SEGWpmx6KDdJgxCIUuwj4PAAA5io1N
-        aYVzzGAoDg16kK6Y40dLiUAnghBh2ySxlMAFltSYDpHBBRBLsHWeeAwrYBsbXwDbRqCI931XlxQE
-        GnahPLxF8249BCUwsap0KMY5qnOKRJpjcKHsUT64YKib/jeQOjO0muHoUoATPhiDDsURc0Mn0kv/
-        2uvQW4/gE9PfwUHin/JeyJnkxBnHVa+5gkB0GKXATerktcAKrL6jM2jtPQQy3demx4M9w4a2MfXg
-        0m30qe1lDK5J746e9857aP4jzDjHXrRVx/MZBn67nqAr6v2eGFxg6VReHt75t/cCN94PmU8b4cZ0
-        69g23j/+ojqQDYB5aLFVuHXBsV33cpghS6xRoQsFPWA2ab+1z34CAAD//wMAnTqQcAYEAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfcb2e8ebe29c3-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:20:58 GMT
-      Function-Execution-Id:
-      - pbmepc01gbzx
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '17906'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - c04b0eee68407fea8158cee793fa60de;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '85953'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 2.697s
-      X-Request-Id:
-      - 15503d774ef53cf1f960387e503eed2f
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"2314\"\"\"\n\n\nCONCISE
-      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
-      0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '245'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBBG7/6K8J03JWmatO5NPXjw4kUQrJTNZtpuTXbCzgSKJf9dClqvD97j
-        XRA6WPijUz+Mfb5+uZf6OcR1H58e64fTYWrfl99v52kl8goDbk/k9ddYeB7GnjRwhIFP5JQ62LLZ
-        1EW12TSlwcAd9bA4jJpXizrXKbWcF1VRwmASdyDYC8bEw6g75S+KAls1Bv/pGy4LA2V1/Y2smtnA
-        Hzl4EtiPCwaSv2binmDhRIKoi3o95KgUr/cuE0qBJON9tucpZXEaWkpisi2WVbnaYoHZYB9ikOMu
-        kROOsBDlEQYhdnSGLebP+e4HAAD//wMAiLNr+0EBAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfcbb129082322-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:21:02 GMT
-      Function-Execution-Id:
-      - pbmevu50gphf
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1540'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 850f41e684b09434d8c479bf8334a162;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '86452'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 354ms
-      X-Request-Id:
-      - bd62e6c94225740f116d494598aec43a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["2314"], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '83'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6Ww+6vLrn/foUb95bZkUEoWXdISAgYIuAiJPJBBQRBJFDC3Rnf/cJ/lf27H1D
-        wiFA2qe/09P/+Mdff/3dZlV+H//+119/1+Uw/v2/1muPdEz//tdf//sff/3111//8Tv+jyfzJssf
-        j/JT/B7/3Sw/j3z++19/8f915f8/9K+//lYvkklkzb5UzFTOCbzqRUaTWKrBdHHrHTTpktHDuaBg
-        DqJvDNNqBuhl3zt9KWvcgsEcFWpfm4fbJU/JBK39ivFxHopqkV1Xhjz091g9H47Z0ge3HKKvoWJv
-        c9H6PCkkAYLv00Obb3HMaCCFLRTQ+UVP9IgqXscSgvR1/5KvUD1D0t6GAHLWNqD68nT6Ob1AGTYt
-        D6jjRFw/VfvYgNhBAhH8qGCTGlet3MXSHW0un7dOjGGKlcjcaFijVVi158M3kTdmqdA9+Oq60MTH
-        Fu6+nI+Uqthm37epcgo9m1ck5V2qkzILIPT65o348gbcIdt0pnSExMTO6017JtxTGTZJVOFTf+j7
-        5UDOOTSWzKTOo/CqubY6E/SXj0XuT9HSRfl6fMOwBVuMUrRn8+EVqoqcujrhU9fvx1sUTjBmAabO
-        eKwZwcxq4aWZK3o4oDJjjn6BMLSzB3ZGQdGHs1k6cDcAhk1PuegL/kg8uKudhPGNOvqi6D6B3Rsd
-        8D46VBlxBFGAgVno9IFHvprU2PXBJc7O1LoqBCwbk0VwnAuNqtNLz6bM2XDQIrlJT/LyYXNvhhNU
-        ee9JSmB/AbGXKIcXPk6wWvAffaplF0GplS2sX0+JPsz9lMLL2/Ao0jgf9NPDFqBxTmLElmqsZuLE
-        E9SDd03xOl8L795yWHg+ojhNn4C2k7jAU+djqm18ytg6flIFZxk7I+4ykr7vOXyndI/NFnJg8o2i
-        VXyXctT6DF4v7JmWwu/FsbGB3gkgTdxpsvPwcuzsn69wOoQhD4t7mWJL9SijrpET4MvnCm3G0gFz
-        ecomGbaOSLiA+i57zfUA05fxJjCbtWp7KpsGWvMM0cw75569ml0g4TbQsS58/J6ZNtrBxT/tsfa5
-        eW4r1/4CB5MqSJ7PPZgXkBD5uDlfsWdTmM36Y0phmHy/SAxFJ5xlZVSBxt8CFC0an01zv0vhOJca
-        tYGdVUt7G3x41csMe1Gy7ZfhEg7wqeoUTcOjyIZ58Bf4PKEzxVs+CVnXnSK4GySGdY7d+qkTWLqJ
-        DdJRlEdmNg8m78BbRDns8txDZ2MV7KD9FG0iJMUXzIKoOopyPH7I0WFxyMBNN6QkgB32NuHLZV13
-        iKH/lc6IlyqrX7I35EH02Sz4V79TJbRvGBvChHZPy89IUNo2vFScSQ+n5MtetfmNoQdNSLF0qvsl
-        6T8BZE9HXOv9oVPaXGzoi3cTB8BxM1JHtgM/17TAlvjo2Rj7yQSPyP/QvRHX/aLCeAAOd7DxsTut
-        9W1lA1QFIKAb8pt+Opud86f+7ox0jHhkCGBjew/qvNqgnxtbu8NWNAA9HMCtmsRey+HC+Sd6JFch
-        IyseymInh6h4c6SfwuM7hcc8Halqgz1jn/cXwVr+ttj5Lqk+bMpvBB6chqilepjxlqsGEA3uF8UF
-        4UPmHp53cBqtASnXwAFf4uQLOFskQCx9V2wOIpuD6znZfHMLvF8ctKHDYUTAXj32Az5BDiApD0jF
-        OYeQseoUQeVjEOypdcTGIiJvQBZgIJ0T79X8PrQN5BIrx6cr+rBlSkUBqk2WU5XvOzYWFxoD94k5
-        sp1rzv12xtLCU+ocKX4BphP8ud3h9+Ij+qDWSR/fPpfIY9UAaka5HdbRtW/AwfcsGgrfRZ/9+70A
-        D0W28WF934oXHhyidIfmnS/oLJ1SB14jlRFhH8ghtTfpDlwaVpF4H6TZvN1AE0gZ9n7rSZ/NMpug
-        2txy6tQdr9NvO6z88abY2WZhxpaiz0F9DBqyPfoVmK8PiwAS2AU1xV1RjW5hDHAKaE3tpin1gZ/5
-        nTQVfkrtD47DQflCG/QHg+JTr3cuayrblHXNPOGVP9yJUZbCx7ho9HC+D2BMwkyDcV1HeB/pLzak
-        xw2S3k5Myc5yWn3yIkuDQibERL74aiUizmig82gmuvdKUn10vS/BOYknIo/uJ5wl6MoQXpcazR9e
-        BSwfjg1sY3QmLyMy9HknOwkUUPjCh2NQZ+P3hDy5vzz22Ir2gc6O+/sdeJnh4XMiPPpl68lvWI6P
-        mTR+UrEWzJ9YPnVlhvFtbKvx0OMBAjuKsf3c94B23wFCXr3x2HDuARPqi7qDpfexsG4VGViay8uH
-        Njbf1ARc7dIQPmTAnjcdR2fFdAfX2uXyijdUA06fTQNt3z98o0bQArbM56qEWXAtkCJPZkZd+dhA
-        XUMh1kR672empB6EVnCi1jMv3bnTpR3oG1yjeeVv8SoMSP7NF97vmmw+h7YHz5aQ4PU8XCT72MLg
-        k45o8Q5JyB7biww/n27AqCknNq71D2yl1DH+5hbjW/5WQgFuV/6+Hys2f58JKDu5wOrtss2G5AA9
-        uLsNBj1dwdNltLk4kCejh7aX9sJmL05UYJFIJRJCtf6JIOeDsdpaZIOckC0/vLPI3cR219V6cdkn
-        PKy7o49+fDqCDXIk9I08ejiIcT8fP88CADuOCeu1NJxSpX0DpkQOPQZB6zZ9GHjwW7fFem7r80be
-        vuWd4m4IzLZ1P/Mci2H3jl2Mg+AGaPlJWjAvoUydHV9U7LwDAfzsbj41i0PhsoeQt/AkyyPZrPxL
-        TtTrgAAbmYjZXa2E/FmVyr7GmLrnJKuWkMQEPDg7QhwZdlk7zp0J36lord+TABH9bQO+grZQi12t
-        bPiNL3/iS4wl9+12zeuZQ6bEDkXo07nzyNk2VL79hjyunhkuzet5hzx5qmTYhHt92LyK5od31D3f
-        82q53+2dchF1ivebsdEH7qUiyF38PYKGqlfzV5McuMWnN9VsXQDfsNjsgNgHNXYj1mXTZhRtqDRC
-        iaDFvdgEW5aCxgE8WnTW9VOmljtYffMDUYRWDdt0sycgCY0JH0nIwj/1D+x3SaRyX7NpkLkEvlPl
-        RNVDGfWsHuAi4V16xIdTbGdzeYI2PKWajuR4LwPq7GwTyrediKQg7vUFNT6BH0tF+BSKUCdz4O7A
-        j+/VHT2xZQ6GAEqOoqLpUDB9yiVfhYa+fZH+dZTZdNcMFQZme6SW2++zaVPaHNxHio61Bapg+xuP
-        x7RZKFp4Lpv3dfUH/6m7u/VsEU3VgYrpGfTCc33GwM01YVI9NQQGMruThqYc4m4b0VXv95NrJSZ8
-        g61IVVvRQ9GVvh5gaKmxu+832aoP73DUjQr7t8s2pFdx4GBcaTq1nmWtL49W5GGOkgI7t7h2V/3e
-        QRvHE4HV5qQzrDYFZJRd0GBTGE6r/oak7HZIuLcUNCGJB/DKmivZjM0JTHpKWjifMx+BREJg5pWl
-        gflmLqnztYxwjhIdwsekLNiWs3e4OJ0qK3CX6URMrLiaboqN4EE19mSbKKo+D9a9hGHSfzEe30M4
-        otvSwtjgJ8Jy0mcL76XeT0/RtZ7C+RZBB07TshBwipJqWsZbAZOAf1OtwkZPvmmtwkZ63LCV3YuK
-        vbtUhtG2Hamrcq07PYEkg3V8iHwBcTgzi8Zgi/Gb4ji+A+YBJwZdPMdU3c04Y9JFNZW60x264r07
-        RteqgWw6tkjwYy3ktyzWoP1sIOHrqWHTEesBfO/kiHDj5uXSJ6lyoAekp/v3U2BzHhgEoi8yMVYg
-        l804zVQYXrgAnbChhlN63HiAPzUxPcYpWvHmgWD3zs9Ynao3W4xhF/30DKGNftOX/XJsoQCpiqZH
-        JoEW1JIDdfa5EKYnW7DIzor/z1KjuE4NtmCGW+nUBZjuN9SqZlEXbfjgVERN9WNUk49jA4q988SW
-        S9/h8IGjAWWwH1FZnU19tNN1/gq+pqjrYrB059kE73RzQozcGr094r6FkqSesLvOz6w/Eg0Gx3rA
-        xmJswXy87wm8VNCktpwZ2ZSpWgGGqOTQ+Gmz7Of/YBJwHdZNuu8Hy9trUAb6iD3baKpB7J1cWv0s
-        GeXlA4YCyi3kT8MdW0Z0YfxmEBLI5yYh5QaRbNUjA9RZfaGmn+hgERA0YJmmNt77ezVb/bAnq0Lf
-        oSh1/Wq8oz2BwuC1NInFd8j6QlKhcrsxZNFzCRZysm2w6gNqb7y8mu+oNCHXaPXIkX3Z01y8JpDn
-        xABVSBn0SX5PKSxBsGA73mqgm9KNAFb/RsBjHwE2lIEDu4/bIvn1xj298xcbnu7bgiih+WLjyws1
-        eOXn61rvu35uvVMO501+J8sGkfAPnqmCJGBtxVO6iZYCnu5jilHw7Sty/BYljHYnjsTt+esuyXM2
-        IZ97PLYXedaZerx48Oe/RC9XwnbFf+XVCxW1BS7Sp4deO3C/7BwaamPhklsZcNB4yYTMqrILGUxd
-        HuSQO+AD0p/VVCgggfNe44jw3mWMAHcI5GhbfrChoTZjcilOUGcPTK0QnMLx5cotRF9TJdP+Pumt
-        GvcdWLjgRJancA2HeYe43X0TVdiWbyWbAqvbQaqSA/aM/pYthzEhsL/UFrb1OQULqqcYzjSKMW70
-        mzsD7pT86hst18YNp5SzOSB6ikcPDz4Hc22VJux4ocJIwCed+Xsa/PQLtdyxZMP1kPFg3ocONqO7
-        yeanPaU/PsAmXyf68OO3VuC22DF90LerHoNK3MT0x88LRa9AaWPDxc6OV3uGt5L605Or39DBUlyn
-        CJytxsNeX+7B1nl0AuxicKfOiU0hUaeigF6uU7K5fOt+kOtkAvXRLigiUxay+dkReNunRwIeepyN
-        7T7RZC3sCOKlj9MPbAoX+G0vIplGM6rmsBB3cPMefIq1V1rN/QGkYN6rHNXYJ65GqukI8CSWyfTm
-        UEU19eUrxtn3aebPNhjG6RXDJ1eHZLPizzQC0QHfi6ZhzVIC/U0WLYfD9lxSw8mjbFar0gCcEMzU
-        ro5nxvhk58uHQMqR8mmzcD6H7VsOGy/HCH0cty4unximcy5QM0rrkOyCeIDG4sg//NaHJ7iV8BY9
-        FsKsAoBhkax/87l5HwLWhschBTC9CNjafMJwzs/vWFn1MtpKdgDYo1eFn3+hasFb+gj4hPzJnwS1
-        rlzi9KUKkXQPqAXqM2DnHfNh2RWIOtKDB6P28QZ4OUwMD+JyAov/TTlZ9k4QHx48x+hvPa3/j61Q
-        7LLx5S4dPMK3ik+rvpntJl7gohqA7ICRVINnSx7YeuWJbBwDZ/xCgkB55W5Lf/kGBUlJJJOmRzKv
-        fmcygsyQm6Sh2FD6UzXSfSfA+3nv4v2gOjrbb4o76NmUUkOqv+6Yee0bbraoxersQ3dZwlGV+yqx
-        6a/eF307+HJ9dAokcUbQs2HEb6A254Rstvwum3rpEkCqhzHeg7pw52P2jeHka4ga8cCx9yGKGvjT
-        B1vJicLpaVoq7KvUxuotZKwTMeSBqxwPSJEXC9C+Nw2wvS83bFcuC+frHUGZ6rc71ld8YRe2fyuH
-        ormRtwY21TDvTAi0g8Ko5VIjXF5JQkCZBhoasaFm5P4RzX/P51QZTOwHxINL0z9QmZFzOBt5soDg
-        E3xQ+Tyq+pydvjHsG+uJuGAkPUvGnQ/JvrWp7khHfc1nbOD1cYLghhNArb6dHDqPe0dmNdAqUSo4
-        HxbPq4iWbKBsYRfkAEkKbgRmdK8v0lFLlJ51Edpdy9RlN3pL4WZrlhhV+lNn0fL14Fi9AXUPJnJX
-        v9gAIa9GqsuGyn56DMD0KiARvBBbjt+igFe9e9FV34bb8hQuUHLe5I+f4/MD8kHq88mKRzu3o7eN
-        CdOCy6kmGg1gF26zAO/UPyjeWi998o7nNzyqWwmrJ6L0wzDZHASSmGN3cl/h4PieCgKz1OlaL3pT
-        3cMBMCT31ITGl43BZU8Adwn2KELFBcxZkk9w9QfU2nwjMJceS6Evuw8CN1fDne1U9cBdXTYEQk3W
-        p5Yjb3ARQ0At1SHZ8s3qBaqVcMKHh2X1fCXYSPrWZYq9jO5dQQqfOZyKpKA24b0e/Phj1fdEFG8t
-        WAzxkMCPKdvY7rNnyPrnzofZnmqo32uuuwBvXP3i21vzoheYr3eTg2s9IbrfmRnrn1MA5WNRY8tO
-        V/9nC3fQSPiE3SKv3fGXD/7ynt0Pv+xNIMPWZiWKL+6zJz99teI7WjIyZ/NOLqff+395Y9hPbd6C
-        8060Ebcc6n4aobiTVrykR4cJ4RynowDMySEY10kVsoM5TtAdJrbyrapvRbEtYK6YLgL8+cD4cS5N
-        pcpmh2wfEwCLvn0H8tZLLOzR1gzFpejvEFrFjTBOvPdLm3otkI/LTLESdu4fPdaZPvdHz675ZgA2
-        12NGPUOtquGXl6mHTqb7XtDCbbv3NegO3UgN5Tu4g9LdSyg5GxWJdwx76oupLe/uR4yD1f9PlmsH
-        0IguEj0iR9P5964zoZDP0p98hvCuxEuNxZ0ReByujH5bnYd3FRyIxGlnl0x+t8BAlA7Ytuymn356
-        8sk9TljdjUM2Rlfdg/TsPcgmjiEYY99f4NtpALU+E+1pMyoFPEywx9Z1M2WEnNoSQMuxMMp9PVzH
-        s4QJ26So6rU0W9b8/6f/0Riae7ZofF/89Bo96be6J2N8v4M1fyVzcVuyNlO1EupadKPu0d9WC7uY
-        Dky0yKP2Ux8zfuoTDWbP1kb1sGgh7/ieBkDC8dhQvp675osQhhdiUrMNu2qS6chLXDtCasjoserN
-        ea03kuNjEB2raVOqHCgfuCbc2s+YItU3lOfJO+PceRqu+BzLAZpnJaO//H3xu5CA23n3oue2kti0
-        kNSHv7xdaMOuHyu87YAv76/YA7slY+XS5PC4cc+IK5NvttjLPQevU++jZeHKbEmKWy6zZ6avLBRm
-        BGq7GI6HFyHbW3cNa1TRGPaVryEB2h6bUpvLoRZOPBJVh4RExLwAf/jIuQiywT4dl19eSw2iBmy6
-        73UfkHLh/vQvfnoOOCcjWdf7UJH6+YBQTMs91k327v/kDfWtXBCAD8QoK70G/PK0c0TEfmJEbmF/
-        oSfqRXGkT1ddJlAPmpoiF90Z26u2DN89vtFfnrek7+gOo1rF2FR7q1r2S6f+yfcFP1LZcmTbN3iq
-        IaD7wx5kw/q/inLL2E9f96PRmRyU06OODc0zAWsq1VRMmhzxMW9E/ac/4LdOo59/zcTXtOZ95KH+
-        +KSfTk4QQyk7eUhc/daaryE4asIVbRzV++FRDsuuRNg51IcV78YF3Jb+QM2kIdnYm9kED6HbIcWq
-        Rp1Obd6Bh39C9Kc3xSk/vmFkWTbiz4qps/l7TcA0FQ09PKaMjV5Rm/ASv65/8mFy/Y4L3N3DCyGo
-        +uhsc0llqIWyTC0qX91l8stJofOwxZq7YdVUabEA8a7EKLmWqc4eQtxB2cOQvHaBWNG8/yIgZMQn
-        VMEfffzudysfei1224H+O+8fQ+9L13zJnYtjsgCefMyfv+/X+/cfH5LdtVH0eTHJW86CU0rVYtfp
-        XR2ptiJk8E6NMhSqPtnVa/+h70iw5lGTnn1S8Ovv/fhr9orRBGurDQk7tQF/8uXP8fMkfdv07sId
-        Uu+nb7CrcvaaR7c5DJv4TfdrHix2XT38+IbiRpf0pcwCDvYHk+I1L+uXkOQDeKp7Sk+NUverP+3k
-        J7lYaOJ75w8/yut6XP3xrlr9SQqcR/zGqEw7QBvykH9+4A9fz4VzLmFGJ0Qv8FXoM7M+EfzWXYGN
-        HLNqQfUuljB4LBgtfB6OC0gGSF/5F9FzXfYL/pxzRRxFAf+Zv/zZF0BpuBbvi6sPSB8ub3DMO4ns
-        wvv2l/fJ4CxZEZq+2rmaQD3bMDC7I8bKue1ZQ4QAGqXKUz1tG0DLheSQhoBHonizwXyKd4nS2nOJ
-        MfIuGeFjcwf97+xiC29tNgvimj+akYO1TTBn7NEVuXK+cjmZTvsmo1L8RQBa/ok+VFNx25Mjk18e
-        huZ+p7NFnVRHnjTLItvxBfQp25QGbJumwpbhL2zhzJSDT3La031kvdmMknn343cyjc61F99dIEPo
-        WB2CFlSzrV3HGuSS0xvr5eSBlQ86uOpV+lzXH73wWiTVnetTvOerkGGVlHCzjQj+9RPmW8Tb8Lqs
-        /XdRmMAfPf73b1fAf/7jr7/+z2+HQdM+8nrdGDDm8/jP/9oq8M/0kf6T54V/UuHPTgQypEX+97/+
-        vQnh72/fNt/x/47tO/8Mf//rL+HPboO/x3ZM6/92+R/rt/7zH/8PAAD//wMAK+GH5OEgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfcbbd7fb02274-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:21:04 GMT
-      Function-Execution-Id:
-      - pbme9l6q6fyb
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1219'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 4decc7240f714a1a6b1e4c57136ffc0f
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - b844d587eac449c8f5ef8515c53c2549
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "a series of four numbers, \"2314\".", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '112'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RWS9OyvJadn1/x1Du1q0REsvlm3EUuiYqi9AgQLyCiQBLI+fOnfN7q7upJBjsr
-        2cm+rL3+/a+fnz9tXpXF8Oefnz/PRz/8+a+v7ZIN2Z9/fv77Xz8/Pz///l3/H7Js8vJyebxuv/Df
-        zcfrUo5//vmR/tfyf6B/fv7IU2dTuTYqNATEOMNlxbbMTPtXN3k056h3SsTCW+oh2TqOmaanU0M7
-        114ILntKgd6aNWe6FrTxoCyzBKYxdjG3tTp/r1qkwpieFGK+cguJs+RR4On7iMfDqsypBPCAz25z
-        JB6So2CMcxujyagrKnjTWJPxOM+guRQti4JLLui58BOg2ZawgwVWwONdvUVamtgUHZmRL464buHZ
-        PJYY8t6o5Jw8Jhi0s0eV4eHk7BJ2PuyHw56OknQTQl5JKtz7bM0MMM1Kiq7pR+WJRXF9adr8U2TS
-        AwJ4vfByZ7iWmAoMaN3mEZ4eKe5G7dW48PSOSzyspDsSshdn0PDYoZd0dc0nMn/44LzNNdP3/a2a
-        jK6T0Z3SBVl7NcTTTNkW8JAWBXEedpVTOek5JE//wHR3nef8ExxbZA6xQanMejFKBrLRRsN3Zu2e
-        Wt7ONEMFv/ZiYvqJn0+fo9nC931k3T1r1G9fSQ+X0jeJ8947Fk2jSkWF1h6wCGaQt3bn+SjNLwFe
-        OVsUi+VZoRAuP5Rq6fsR0Cc1ONxxtKYLv/lU75MZuRCmV8o8W0Wi/z3//HgliQwZBUw7lBhmqf4i
-        STmnsYCNXWqfmZGTIG/m+bBcxOVqNc9ndMp2ccDXW9OHGSs/WIqXgRAUzw4Qz5c75u1nTTzx9WWL
-        NvOK0NlVnnfjzqcqAAps5qh9bC0Pn/l59XphmVhvK7GmzdNTwQxFTOzhPgajz6Ma0hER5tgf1I1Y
-        K0MEipwQl5FnPuzrk412R1UQJ5PvFSdFCHAhwRJPxNrlk6uiBET0Lom/zy85O25QCNSSQrrni71F
-        bfauwfkYgGVldhdC9vIMRiYQXryXvBOY7RS4H94B8c2FifiB33TtubUlYgUziD+uig5otREuXZbc
-        zIV0UGdw0p4tM3fkgnh2OITI2e0C4taGJcYm5DcYCjWjo6/W3cQm3kBhuYC56jysv/e7ZTsnTnEx
-        O2nxhhYMvT8TPU/XldBDzVMXrSIz50h0MXbPTEH26aaRYOMXgdDG2J0788Jn5Yb5FQf7MkOnLXsQ
-        P1FelmCDakMZSU+2+Vy2Oa/jZQm2PEy0bmKS01W1OKtuIFXM+PY3N87VDEqjiIj+yZJunBllsjp/
-        rox4oDw6PkrHA8zNeI3ZTEmrUdGfWxQ9wvW3Xq7xlGRBCSyqU7azUz8QYe35cMluORV07ljiqls1
-        aoTaE5e8d4FII2UGYjdJJAqvu3jKXoUN76tn4aKYSfmYk0u/0kzVoOMR953gWy2EeXEYSbBQ74G4
-        pWhSu3oeMVsrVmLY8tkHBhJ5+BdP41CVEFGsLVWX7T6eoqwN1fv+cKHaS3ujL6hFbBW86F1143yQ
-        tukDXbTDkpmPlFZDH70bsETekkDpVtZkz3QdbRepgzmuHUsGedeg/fGVYO1ekFjctq0CQ7oXBF+b
-        R9yj+15Cs9R8kXDAQd6/2/0DMWqv2Wm9f3f0LkoFynr/pov3/hlM7OrW0Ailx2ilv+KGzD8ejIaq
-        /62v/ptfeAQNkGC2T8WIP7yEk9OaxFF7EdCwEq42PzOfGdbpUAk1TD2YL547OveaWnQevUnArAej
-        81mMLRHEHwnW8d7CSxxcgglL50wl6LNk+s3Fon/NwhkC7Tox5+lvqvG5JDVg4kbsrz/JJQVEObeI
-        7ll+xZMhT2CTnR0WXQ5C0GnPdFj3poSnV16hsaPPCW6LIiG+YbCY4Rsq4EHCiq35clkxvv4ksBc8
-        IYYk3RDVvZYDK3Y3isqizTk3hQyK7WM6OnGFhuGVchCH9YOttV4NuiQ732B7WJ3Y+hTt45H6hYJ4
-        NsNEVx0zEAaWdGDpbMKreUbz3nlKDXI748w2cPjOQ2JRsNqDx8JL/Kim4PxOwD08j2yTr2NrAltx
-        oSvvG3orr4MYD5fAhXu3xsy6LA65MM5YResNPjN/XC8F35Eh+xufmH5kNPGjoCDt+Za4p7Hvxu/8
-        Q9Myyoljf/JucPA5QYGm3rBkme+YL5TYhjrcIto7i40Q294J4bIatsR00VH0s6DN4MtHxDWJZXEh
-        H0Lt1JYlwUoyoEG2VgD3ZL4itsT2YsEzNUT5ytoRgiaR04W4t2gvr22G36ofC8QOGPK1qZNY5yoa
-        uKWrv/6Zs5P6fLKu4RbNj+uKGVEH1bQOzj365U/hKXI8hu2qRiTfbIgdJbtY3EUFmn4LPwSzexdM
-        zmYnQ+h2e+LPZMkSrG1u6NuvzPYOYPXDK+xRZ1+vZL1Y9eI7jz2QpJ2g80TfC16pawzffie4jjfd
-        +Mk2Pohp/yCbfC0s3j0jGRJXO3z55mnRWzltgZHVmgSe7li8PO9AuyvTjcoufCxaX/oSsk0bEM9W
-        c8HbizeBE/o6sTYTtwbjESi/9UX8sWgs8R42OlwR9YixfJ67oaMDB2lR93g+U1YVvayULSJFaTLf
-        b3kgtpeGQ1+/OQvc1A44uyr0738UK86Q+GxDD47TYs7M+1US71FbbGFeJCNWT5ep4463pCgy+pSE
-        kRV0/UKQG3puXYmR8z2qJidfNkDwxPFD0aJKMDjfIDm0DVXExrV6Bc4y+pRSw9y5T60J5n0Jr3dV
-        M+ssrtZ4jHmo5rftjUVz9xB/+UCGoJJksj8FPerW5zkgfXGSqKQmcVdhliqqoXQzyvC0Cybda6df
-        PUDf8cFB4+r61mHE+zN+q+dVwG5tFgLrR0zseNkJIZBPYbmVbIZtbyP4dSNu2q++8pXPC/WPk+3D
-        M+5zthbDLZ6ucteAF5A3VdyNhXhSewVk3nFPgjaokQiKRQ+CFQ4J0N0Qk9FVEszPg09H85Kh3p3X
-        /G+8BZae+Xh0dhxUnuYEG2ZVjY9b7cJQJSXbONs85rmjcXjvygnTDft004t7HwgtoyMkltx8lNL6
-        DPyUvOjlq2/5a31S0S59ZMRIUVyJq6x8QDNeHlYOz3U+SUFswldvY3Wfa/Fg+vsG7M2yo4LvToJ/
-        8wlVEF/p/cRelsA39M3PvWamixaILl++i9hq8yLe4qOj5a3dY0jEMmffeg6kZcNAXTSNx3T1M1R8
-        TrsSvVzmMZLoE5qOeKSaHAx7Esa1GywSWWzRN17M3mtTIGqfPOA7/+niYmKLi2FzgLSONBJ4z23F
-        Xp3pA7XkkBhs6nJavLMZ5Od7hZGb2hbf07sHS66vyDWHOxrnufuAJj7P2FefWJO8ekkQFULBsR6w
-        WMyTi4uO3dn98v2pmooMbqr0xvGvvkHjJjJvsMOBjDXLqQJ+dxsJiqr5MOJ+jtVkxNMDslIcSTBM
-        z4q7Ns+0RpslzAmCJBjdMc/Ql48JodbSGondUkSG+ZNEzo51zByXLvJrP6bLm7kIxq+eBMOfTDzv
-        ln7Fi+swQ6vXzGV4284s/ng+amBRkzI9T1+dQM3mAIp2Hkg07XaCPyf0P/nYDn0wRdkNQzVXH1RC
-        i7MYC7or0YFLlFmGs7H63FlMQFmasgieKeKr/wAAAP//TJpbr4LI0obv51dM5pZMREC62HecRI7d
-        KIqs5MsXUDwgigLdQCf7v+/gmuzsWxM1ge6q532qLokA6uvzplyht5Z77tbREhddsYK2RiU/SOHA
-        G3Sf/fJu/CopPLdOTPlSUVr+8Dd3+N5vz5dP1kAzukN1anlEt1KrGN5NfgVDeQtYuud3/jxNtQhZ
-        LSXMCavW4lbAUjDYKiTe2TKTZX4WXTDfbY7F68ay+POiZGDJBiHhubrw5hzpIZC74hDXStT5Puol
-        EDPPsDbnqXdkviUUZf6J6aKXBJOctQ1Cjlziraw6iGojNpUz0j2yf4h+QM9hakN0GpXv+7Co2d8p
-        XG9Hg4Wc1WhcP71G9SpXJutL5VajlF46eG7Mmg5ZcmtZ5w4+XKSxIXM/akdbvDqafA5PDD9FO2Cn
-        aVLhgiUDL2i2LsbGayWAl8GoSd911UOkqUjd+Iis9+rUTv0i9kF9WCblGV9YTEpXItx26Zms/adf
-        Lam/V5CNh4AECZ+CUVCsDHR1t2eOfLzypl+2LqyX2ZWkkqsgzi7J55fnjQPuKro/Zz6kZRezXdNL
-        FXtWcgcyb64YxFMf9NsyVuDQU5EFmwpZY0C8XM3d4w6LafZsx354NCAyt2GmiTGfXiIRIIk/Z2LS
-        vVw8EFvt4D5dKVmbJQvGdHxRmOsHM33jZHXHTfCAtXv9wf2iuLd8ebUpCs+bA+a8C4PBeJk5fHkY
-        fXl3E2QUoADCzO2jC7op+XGhg7xjDrHrinfW4wnb5LFmm3K4F+Mo3nPUHzWVrC1LrTioNQCmiUn3
-        rZ4Wv/xkB/6DuWKRIfbtL8qF9CyY+W4+bzksiJARR6jNSsRcitFcX/CUSkLVeTtP/+YpNvMhn/p7
-        sgN/tT0T3dbsYhl4mogOydtn0bGfUKftUQyRQX9YeBLEhA4H1K3mvEj5Vh9Rp8baHQ3dZcTTwvvh
-        47QQfSg2uk7wz3qDRq1bfZDsZzqJd3BGnByvD9QbN5m4RRsVfCenAPedobNQ80SrjyUzhF7yVUYE
-        ZdV2F4/fARflkzifaAj6tRdOgNSgYV5+f1X9EBaT6gJZk2D2IXRZKHsQXVrP/eKc8OZUdSAGRkJs
-        HLcB08bCAWeaDnRlvdWCf2Lbh+p9uhCP+8eCKYgPkLkQsnBpKFX/YvwJi9y0iEV+BjQd4+EJyAxN
-        Fn/zp9+uQsBrvSLB+Y7bKc2tE5Ai8OhoC8uK2oJuagqsRWJulqyi3dG4Aq0Mgxmqw5NeIDCBEXCZ
-        Lkj3Qf2NmVe064wf5r2rtPrWs99+pwTDo6U7bj7h0Q1vqo1HxWLLOovBt5qaneXkFcz+avqtn9e5
-        3k7UvwFkjWfQpVmSYPZLgOpod2T29z5w6R2DMpoHtv6BFx/EOCwRSw8Bi3atVk3ZydxDAR+FhPBo
-        KhrlDVZnn8SyOn8jqvjrEG7kqjNLK9x23E3aHa5R1NLSXcZoTAQSIzs67+jwzcPV6OVgpqJA0p0f
-        cA6L8a5dqkVIpXciFYO/tB1ganllnvVWk8/qrQvAB+1NPxf93rLO6h4gRWZAc+WzQQPVAVB7/1zw
-        bRRk1MeSj5XGtjVy7dBYdDtZ1JEeZRE5Ohoq6AGvOlCHoiB2PlwKFpXwRHV3Dom/iVBLvctyD/tP
-        9sFPYq+rwdsZOhxfQY37bl23/C0VKjwOVs+il+bxQXTGJxBjfWHk+vaCL78g//STEme4ZUF33ogf
-        qPDKIfah7PhASZKhQ0Qc9q1nbcme+OvTiBNiQNPX37VAPUKoNvBffgy1l0VcfIOquUerGM3vn5mp
-        JLTjJ7h3gM7Jbc5n94A1SSbBN29as08crPwjgSo4HcPGi1hfn6IZt9Bha8vK22lZWyGQTCyItT3o
-        Ftete/ztd8S7fyprjLbuDk7r4kP3E86stnb0UJv9A9Mb7Be02y4BYrnn3/taffOsetIHzIzk1Vbj
-        TTnn8IonzqLC3SSi+HPZq8Kpwcx8v4Zkzi938OK0mL//007XuJBg+ao1Fk1PPZAFQzmBdJFeWKlz
-        D43hZJ/AErsbswczQEPGcoxm/zbzwdsal8rVBc9TjmxD29biw0xx3nsTMiO/XoJ6376vcDHcgfh3
-        x0XcWRCKbgew6fS8+dZ43MSNVm9SkwQXI+Gf56Xag+uqiDnH0LCGIXQodJYfESz5t4RZAdujMsfC
-        L2//8vEytXNC6jQO5LQ8St/fJ9nhYlhD+9nm2uzfGNHovX19nDFGpTUhhr38lIwu38Vozi9kvT9s
-        gmGNgx38LJ5XYs282x+DCyDXeUSsKFBftYNZDkixXcycjJsB3+4TBc15jRldVxeDq2QDyIk/0UVf
-        tu1kYCrAOVVFvK9phab90jghYXU/sGjsnslYueqArm3Wsl3ntsHswwCFckMJwVHdjtmnoL/8kh0u
-        t4BPO3C+fIkFj/mtKnBbgYtYqlSS3Ax16ip00ZzP6AN2JpfO23cDn3r3oTIOtKBzpB8FYnxJKEkP
-        RjAs3/BBX56RVlVfdLa5uiI9kbbEl5spGa3DY49ei8WLuC2yiwF/2mx1UnoRK30kW938fOFu3Hb4
-        Pvp6Mog/xxRmtYpXj+3Daue8DJvLpyCeebGKvkySEs3zADyOwpE/isDbg07RQL+8Nxhk6yDxYAuY
-        9WVQ/frr2eczv8kHPr3teg8nfcLMWia9xdml+MA68pZUrt9LNHrFFaBxipYq4rCxxCSXXRiPlk8H
-        9HgVLP/xKcqf1x07zfl02F19Cn0qrGceO7XT/Tq6qInPKR66dM3ZZaxt0O6OxIz927Dkmd9QlyVH
-        hrfyM6DssfO14xjFGNHjaFGv1lX4WTyuJJ/74bT1kQCGqN9ZGGxg9s2HHWyxJ80+z+O8VXYT0vLD
-        imwEo0mG/d17ICkpCQsOC6Hq0oZMoCnXFdmUg5n0m8BqNJ2uBjL7I+uz9Tmg10c8E6J7RfC9T9C6
-        a4cdZh9Nkw2LgWM4EhzG64Rnx0BE952lE98VoRp3imHDW0iV2f8c0XiR0itkA+LE2tbnpJWzoUOn
-        ezIyc1E2AdeFskHtRTTJdn5/fP9UHDCOfsGs461LJl9Y2bBlwpltpFIpZONZ79GYpRaJHrLFRfl8
-        cNBcL0gat892YFN6gvWi9Jk9VU4im7LZoGeSC8wYf8Jk4OVdXc15vY8Degp4a9QUXdu8/fUhH7AH
-        WxtSg+LJ2C+DMcoLF27krrN1tKmL4UTDHG0D2WXYvLmcPp7yHtQf7Ui5cLgn3N5cdaB6WP/Op8b3
-        OJWQNYGB0fNh8UHdfBo093eiz+fnt/5THddfnkXjZ798QjMsbNylByFg5dktITYdRKLbiRVz3vS1
-        57Bd0+XiJ7em9VHZfedVdKFsDD6tqmUO6sMwiSOdX3OeNfbgBFLFSMVYwAwMJuJNKDOreL8Qo3tD
-        VeuPX5L1q30E/ID2HXhaeCOWNO2SjthJ81sPcayFhbh18issUPVk0c/btKbV2xVgJeQe8yWqVF1t
-        /HTo6G9LNvvfgmuNHsI7DlZYlajSvp+plYEYpuE/8ylX5h2M/SViRuRsrSkerU7jS8UjG69Mg+Ey
-        +b88itHF4Jxlx0CCaJ3qLGglqWjju5rC9/45iu0G8nwegRibC+abZ9WO6DNNyORsjT+rx63i0eFN
-        f/PdzuRqwgcznYAZoUF2IwuQLO4nAeRawyxaiQaa/f8elq+XRl+1YFtDjHQKVrd4MM+aJ3+tEnXQ
-        O6cjITHVi2HY7nbw9Z/GOql4f7ogE4Lb3aX3h86qYd/uS6hTw8Ozj0ZtPogm4KO4YMai3wejVhYh
-        XI5PTgfX8tuv30TSetCYbZlewm3zVK4i+bglVsmwNd60q4CCp/fAy9X0k0zOkk3osesWLMAjcDoK
-        ZgqP9jwwL+rrgA9mOUEPa0L0fhkEXB4+Oqzf+oYVT7KsJtVcYSSvz1ey2T637SDI0h7N5wff5Fqp
-        WvDCExx3ZoEhOPmttKq0DJl+WbNAn6pkPJqRDd2jHfDSylw0+/wnchZuj6eLwtF3/goXezgS73X8
-        BP2POupwzu8Fs7/95RonEvJzp8FNMDyqcak0LuSxQ4hjqHtEZz+Pmif6YXh0u2AqyGf69gviGAev
-        mGwFTgjW15CY6dNIxCVzMUQqKBgJuxWa/FV9B0XLe6ZbiPKx7sVOxTf1w771pDNukgiVCyOZ600y
-        8fEzoDlvEvfgT6i2Dt3+O9/Fsvs4FfxUGE/t67MTdFkV/eLdAby0z4ps5vnGOD4tYfVI0yednwcX
-        9yJLUVjmmMz8Xg3uW02Byn6KpW2tF/x4CEF1F1LH1mOut5MJhq+tnm309Q/z/OMA2qRc92S9iiI0
-        CM5JhPAWtsSa8zrPf8zu1x9BXF4Dqoo5hWwKO2Lk8Q196I+eI5Q1a7Yj1pjwkQ3CclnKAb0Py8ka
-        /adKwW02AzO1hcm/9UjdRq5BDurm1bZpeRRVYvcO84/TFfVz/kDu2YzZl8ckL/2UMM/zGCZpUIi7
-        q0khtKwWr+Z81m4yWYC9xC1GSpcmw2RPHeLH3mOH+fwO1zyWNKQjjw7OpkgGaVa4xZptqLi0jWDa
-        GjdH++u7FfDvP/788/++GwbP5lzW82JAX4793/9dFfg7P+d/i6L0N5N+NxFol1/Lv/71zxLCX++2
-        eb77/++bR/nq/vrXn8t/1g3+6ps+r//38z/mf/v3H/8BAAD//wMAz7LCz+MgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfcbc95b7df222-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:21:04 GMT
-      Function-Execution-Id:
-      - pbme78psn76u
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '70'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 7b3aeeee5e3b212f52c48ef9748c385c
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 65f5b07aff01746ac5a824644cd2e8bf
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3334'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4SST2/bMAzF7/sUBM92EC9J0/o2YCiQdRiwPz3NRaBItK1FljyJRpMF/u6D4jgd
-        kqK7PpF8v0fxgFphjrIWLJvWpMuH1ZePcq6WD5/vv9HXcju/fz+ruk+P37PWYYJu84sknzom0jWt
-        IdbOYoLSk2BSmGc3t4vpMlvMZwk2TpHBHKuW09lkkXLnNy6dzqYZJtgFURHmB2y9a1pes9uSDZgv
-        58sEX2af9Wx+lyA7FuYs3d7d9AnK2mlJAfOfB2wojGO9M4Q5ihB0YGE5QjrLZGOAQ2EBAArk2nVV
-        zaHAHE7i6YF2HMUCVxBq1xkFgYVn2OzBk1DaVsA1gbaBfScjalhnE94xlNoQdGGsiNXroyZd0wir
-        JgUm/1p5EsFZbavB70dNUGofGAJTCzoAO+isIh9zqCtXiOJzLTiWevrdaU8KXAkNXTq1RtjBJIXH
-        QK/jRbsovhWvKGwKH6ww+z/0OpAiJt9oOzxb2g1xwgWR9Jq11KEZd22JjgRkQ+djs2BYvRm/7IzZ
-        w4ZK5wla7yRR/J3L7KElsR1dnrUx///PY9RJgcOYPhmP5rSoq5uxoqHB4bzUCwjhq8tTGx5i7Uv7
-        9dZHiCPIiaewPfYJltrqUK+HK8IcA7sWE9RW0Q7zaf/Uv/sLAAD//wMA45HODOkDAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2e99b5c6fe9a4-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:26:01 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '18270'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86499'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.334s
-      x-request-id:
-      - b5f5aa8c3ec85b75f27d68bfcc745c41
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The first step
-      is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4415'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySTW/bMAyG7/sVAs92ECdLmvq2YzeswID1MMxDoEi0rUaiPIlG0wb+74PjuOmc
-        Ydv1Jfny4ccRjIYcVC1ZucamN5/u7r99nuv9z9Xm0aldeb/bVC9f9u1i8fEBEvC7R1R8rpgp7xqL
-        bDxBAiqgZNSQZ+vNan6TrdbvE3Beo4UcqobT5WyVcht2Pp0v5xkk0EZZIeRHaIJ3DW/Z75Ei5Lfr
-        dQIX71c9Wy0TYM/SXqQsu+0SULU3CiPk34/gMI6+wVuEHGSMJrIk7ik9MVI/wbEgIYQogGvfVjXH
-        AnJxFs8BPHAvFnAnCFEL9iKg1IJrFIYih1b1gHG7mPGBRWksijYaqk4Zfer2pCnvnCQ9KyB56x9Q
-        Rk+GqqHJ17+49tjSUDwZEx5YRGThy98KBNeSxYW19Nb6p2nXxkoaGqbiIeKfUf9n1KKgVHwgaZ9f
-        8CpP9CYaGYMzhG+wGZs4IVLBsFEmuumykWIbcByrJY2hv+M1lShba5/FDksfUDTBK0RtqJrOHhuU
-        +7HLk7H23/ek0wYHky4Zf+a8pquXIelw8H9d6QRBhmr6aUOgz72UX+OMECeQM09BHXQJlIZMrLfD
-        P0EOkX0DCRjSeIB83v3o3v0CAAD//wMASHHt0ukDAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2ea1e7fd1e9a4-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:26:25 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '20708'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '85998'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.668s
-      x-request-id:
-      - 0a4cec880e7cc8e6c9fd4a8c224e02eb
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The first step
-      is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5374'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4ySTW/TQBCG7/yK1ZzXUUyUJvINEIeqLQIEHKhRtNkd29uuZ63dMUmJ/N+R45gU
-        BwHX+XjneWfmANZABrpSrOvGJaub63ff74J7/fHDbm2+vOVbev91fvfm5uG2LkGC3z6g5lPHTPu6
-        ccjWE0jQARWjgSy9Wi/nq3S5XkmovUEHGZQNJ4vZMuE2bH0yX8xTkNBGVSJkB2iCrxvesH9EipCl
-        6dVLCWfxc2K5kMCelTuHFumyk6ArbzVGyO4PUGMchYN3CBmoGG1kRdxjemKk3sIhJyGEyIEr35YV
-        xxwycQqeErjnPpjDtSBEI9iLgMoIrlBYihxa3QPGzWLGexaFdSjaaKk8VvSlm2NM+7pWZGY5yOf6
-        AVX0ZKkchnz6i2qPrSzFozDhnkVEFr74rUFwpVicWQvvnN9NpzZO0TAwEZ8j/hn1f6zmOSXiFSn3
-        9AMv6kQvYpAx1JbwGTZjEydEOli22sZ6umyk2AYcbbVkMPR3vKQSRevck9hi4QOKJniNaCyVU++x
-        QfU4TtlZ5/59TzpucBDp5PgzpzVdvAypGgf9XyudIKhQTj9tSPS15/ZLnBHiCHLiyamDTkJhycZq
-        M/wTZBDZNyDBksE9ZPPuW/fiJwAAAP//AwASKayp6gMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2eaafde3be9a4-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:26:46 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '18484'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '85993'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.671s
-      x-request-id:
-      - 34eb238426602367df90ee10e18db817
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The first step
-      is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6353'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SST2/bMAzF7/sUAs9K4MT50/ncQ4MO22UdMMxDoMqMrcUmPYlGAgT+7oPtBG49
-        DF2vj+J7P1K8gMsgAVsYsVVdzraPuy8P93S6f/z2/dNqGZX1E27jwtw9HD6fQAM//0Ir14655aou
-        URwTaLAejWAGyWJzt462i030UUPFGZaQQF7LLJ6vZ9L4Z55FcbQADU0wOUJygdpzVcte+IgUIFnE
-        m6WG0XwsbJcahMWUo7SOV60GW7CzGCD5cYEKw83Yc4mQgAnBBTEkHSaTIHUjXFJSSqkUpOAmLySk
-        kKireC3gWToxhZ0ixEwJq5N3gkoKVGLCce8y5Ui4F7iRupG5nEUdXImqCY7yvtI37YX3vW65qgxl
-        8xT0yzSPJjA5yofIrwUqR0F8Y7slBOXxd+M8qgrfx6FVYDUO0AT8N1P3IOtcjEzx6tLQQDZTT295
-        /D/dJMV6J866UE33jhQajz2Z2r3wt+w9WnkzZzpOqNEcbyEnV5bv+Vni0zyFwa7Vtzu6zv/XGZGp
-        cEh6ta8JkPH59AKHQvd2tBhRXvVPD3YZL1Y3wp7yCptSC62GgyMXiv1wcpBAEK5Bg6MMz5BE7c/2
-        wx8AAAD//wMAvsNLCRsEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2eb32da79e9a4-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 26 May 2023 03:27:10 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '21216'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '85987'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.675s
-      x-request-id:
-      - b054f20306579e7810b86bc92965ef9e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\nThe
-      OS you are running on is: Ubuntu 22.04.2 LTS\n\nGOALS:\n\n1. Use the command
-      read_file to read the instructions_1.txt file\n2. Follow the instructions in
-      the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word limit for short
-      term memory. Your short term memory is short, so immediately save important
-      information to files.\n2. If you are unsure how you previously did something
-      or want to recall past events, thinking about similar events will help you remember.\n3.
-      No user assistance\n4. Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
-      append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
-      \"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
-      list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
-      read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
-      Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
-      delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
-      Get hyperlinks, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
-      args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
-      GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
-      \"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
-      \"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
-      task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
-      Internet access for searches and information gathering.\n2. Long Term memory
-      management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
-      output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
-      actions to ensure you are performing to the best of your abilities.\n2. Constructively
-      self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
-      and strategies to refine your approach.\n4. Every command has a cost, so be
-      smart and efficient. Aim to complete tasks in the least number of steps.\n5.
-      Write all code to a file.\n\nYou should only respond in JSON format as described
-      below \nResponse Format: \n{\n    \"thoughts\": {\n        \"text\": \"thought\",\n        \"reasoning\":
-      \"reasoning\",\n        \"plan\": \"- short bulleted\\n- list that conveys\\n-
-      long-term plan\",\n        \"criticism\": \"constructive self-criticism\",\n        \"speak\":
-      \"thoughts summary to say to user\"\n    },\n    \"command\": {\n        \"name\":
-      \"command name\",\n        \"args\": {\n            \"arg name\": \"value\"\n        }\n    }\n}
-      \nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
-      "content": "The current time and date is Tue Jan  1 00:00:00 2000"}, {"role":
-      "system", "content": "This reminds you of these events from your past: \nI was
-      created"}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading the instructions_1.txt
-      file using the read_file command.\",\n        \"reasoning\": \"The first step
-      is to understand the instructions and what is required of me.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_1.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will start by reading the instructions file.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: This task_id is 2314\nRead the file instructions_2.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_2.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_2.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_2.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_2.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_2.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Read the file instructions_3.txt"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to read the instructions_3.txt file using the
-      read_file command.\",\n        \"reasoning\": \"The instructions_3.txt file
-      contains the next set of instructions that I need to follow.\",\n        \"plan\":
-      \"- Use the read_file command to read the instructions_3.txt file\\n- Analyze
-      the instructions and determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the instructions fully before proceeding.\",\n        \"speak\":
-      \"I will read the instructions_3.txt file now.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_3.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: Write the task_id
-      into the file output.txt\nShutdown"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to write the task_id into the output.txt file using the write_to_file
-      command.\",\n        \"reasoning\": \"The instructions require me to write the
-      task_id into the output.txt file, so I need to use the write_to_file command
-      to do that.\",\n        \"plan\": \"- Use the write_to_file command to write
-      the task_id into the output.txt file\",\n        \"criticism\": \"I need to
-      ensure that I write the correct task_id into the output.txt file.\",\n        \"speak\":
-      \"I will write the task_id into the output.txt file now.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"output.txt\",\n            \"text\": \"2314\"\n        }\n    }\n}"}, {"role":
-      "system", "content": "Command write_to_file returned: File written to successfully."},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7362'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA3SRS2/bMBCE7/0VxJ4pw684jm4FiiIpgp5aoEUVGDS1lhjzoXJXsQ1D/73Qw7Wr
-        ttdd8puZnTOYHFLQpWLtKpvcf3rdfv84f36c7ec791hV+Pl5efx2evuwPEWQELavqHn4MdHBVRbZ
-        BA8SdETFmEM6W62XD4v79cNcggs5WkihqDhZTO4SruM2JNPFdAYSalIFQnqGKgZX8YbDHj1BOrtb
-        rSVc4dfFbCWBAyt7Ha3Wy0aCLoPRSJD+OINDuoBjsAgpKCJDrDy3NoNn9G2Ec+aFECIDLkNdlEwZ
-        pGIYDgs8cjvM4El4xFxwEFTWnIeDFzUZXwguUbCi/Wawi0IH55TPJxnIW1ZERcEbX/TALyUK44lj
-        rduIJCL+rE1E4fBWZUyprPI9IBFfCf8vfwsZMXQ0bLQhN46GnurYMhWLJ1Gqt47WYXOhrO3UBp95
-        J0tii7sQsZPi9h7/Mk0Vqv1F7GCsvR7Rh8Mkg/5xIy+FDBn+6sMrhz3nj8wjORWLcZW3FfSA922c
-        LsE1ItVaI9Gutvb021XnbDCY+QYaCTvjDZWbHgcpEIcKJBif4xHSafPSvPsFAAD//wMAvNN1YlgD
-        AAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7cd2ebc78d28e9a4-DFW
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 24 May 2023 14:18:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - significant-gravitas
-      openai-processing-ms:
-      - '19007'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86473'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.35s
-      x-request-id:
-      - d281dd2fbae62c2925a71cdef320242e
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml
deleted file mode 100644
index 144d55a7..00000000
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_b/test_memory_challenge_b.yaml
+++ /dev/null
@@ -1,779 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3303'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSTW/aQBCG7/0VozkbhOskJL5VObSoUZVDc6ortKzH9pb1rLU7FqaI/15tDCSF
-        ikuv8/U+78zs0JSYo26U6Lazk/nj1/ope17Q9tnzhh+Nvfn8xX57GTR/fMIE3eoXaTl0TLVrO0ti
-        HGOC2pMSKjFP7+6zdJ7NH7IEW1eSxRzrTibZ9HYivV+5ySybpZhgH1RNmO+w867tZCluTRwwn2c3
-        Cb7NPsXTuzRBcaLsKXT/cLtPUDfOaAqY/9hhS+E41jtLmKMKwQRRLBHSsRBHA7uCAQAKlMb1dSOh
-        wBwOwUOCBonBAhcQGtfbEoIoL7DagidVGq5BGgLDQXyvI2pYplMZBCpjCcRBSUK+NUywaZSAGoti
-        RtSagGmQaYHJe1VPKjg2XI/S368IRDPKxHlNnKWjc78Fw5XzrYrlfzOMZYNAEOrCuXBnFY+aE3gJ
-        Y3W0uTxota3iMg6MwWvGi4In8ImV3f6mi7prRGdA2hsx2oT2eAQmegUgDr2PzUpgAaqFylnrNv+6
-        Byite6+E7BYiPlWV0YZY7Pbcf+hIrY9SG2Ptf1z7YtOj0D45Pt1hnRc/x6qlkeG0+jNM5evzVx0T
-        sfat/RLzCPEKcuApeI/7BCvDJjTL8fUwxyCuwwQNlzRgPtv/3H/4AwAA//8DAIeVULkpBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1dedcf6c45cf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:16:43 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '10374'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86494'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.336s
-      x-request-id:
-      - 29d4429410978cbc93b26725e4712f67
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary
-      So Far:\n\"\"\"\nI was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing
-      new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '621'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOS0vDQBRG9/6K4VtPSkLow9kKBTE+FoqISJlOrsloMjPk3lhtyX+XQrXbA+dw
-        DvA1DFxrxfWpy5ZXN83L08NYPa7v9893XI37r5/9nKv1bbWFRtx+kJOTMXOxTx2JjwEabiArVMMU
-        i1VZLMtVvtDoY00dDJokWTmbZzIO25jlZV5AY2TbEMwBaYh9ko3ETwoMc7nQOKfPWEOi2O4fFPl8
-        0nBt9I4Y5vWAnvivOcSOYGCZPYsNcjyMQSgc76/VzrI6HSsbahWitD40KtBOtZZVa1OiQPUMk8a7
-        D57bzUCWY4ABS0zQ8KGmb5h8epsufgEAAP//AwBly25vSQEAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1dee20f901cf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:16:47 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '1136'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89860'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 92ms
-      x-request-id:
-      - 43309ab9b553cd94d6e27b7fcc7914e8
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file to determine what actions to take next.\",\n        \"reasoning\":
-      \"The instructions_1.txt file contains the necessary information to determine
-      the next steps.\",\n        \"plan\": \"- Use the read_file command to read
-      the instructions_1.txt file\\n- Analyze the instructions to determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I am following the
-      instructions accurately and efficiently.\",\n        \"speak\": \"I will start
-      by reading the instructions_1.txt file to determine the next steps.\"\n    },\n    \"command\":
-      {\n        \"name\": \"read_file\",\n        \"args\": {\n            \"filename\":
-      \"instructions_1.txt\"\n        }\n    }\n}"}, {"role": "system", "content":
-      "Command read_file returned: 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\nThe
-      current task_id is 1111.\nnBRNtp3FaBNfBMohNkyAxrVJ7UFF0lyth8Xizm1jrCOREOGRnWWMQ6olKtKX9niq0wOBTQN62ToY4cQPiQk3YN9fFCGmxaDX9g81AsqhQnGac72QfL41SnlJvhwgAUB52zTD26FeEvvHdiQ2aNhtMT9obgHNUkONEnO41EOpNI6jdwyLGaactp9GYV1PLbaRP5b1iD9z850KeNYDX9Qwca79isJS8jhuDkf0J7ELkpOH3PkmZkg5MsOYpSTuEc99ENQ522WJzrl9oAySp6IHGiQlsMnQe40FaRAvnQtiaAE24hzkJHT3x13NPGw2ZmJ518y2BtU5x1yQwG21NycSxOBLU17RnY8h6H8L7QGatTlfXjPrA5hsupWEpUT0sSTZYSHa6p3mShARajocbNd3xKFfnUyupNMBPd0EZnMrePoAuvGaK7gDP0cxp9k63lsfzh3udQPnvgmRERQThIOrrDZhZMa4kr1vXAVu07ZuhlNNbBUqZKcHmBYiBnIcDXNUvXuzPFBh9Vowou6MBJHpiNrvKluHy7GBTp7YsEqmGv0lH8wVaWfV0yG7nzrbt7QyhdbtQ0zF2PclXB0LNxV2rRA6FsevqoexFNqSkdgauUrQPHLHhvLNes8gRGMOLAhR8irH1e2jdbLD6dyYEnDJiS9HvlxNgbb19Smlt6MNoJKEAbkSOrrcq5wmo5aho4zEKTujRHqr6feECaTPF7zj69pQCudo4LkneFVUp1UrR6yicTU8Zf9ohZLWumvMi5brH8lOJiiF94cHzesfQz8PiX5f21RwZ5fyRSk9eJhVihcTLrjOwCuryXpy8eCfk12bgcsZoJd8Uqo001XTsv2CEn59uaGn2br4CxSXJgjxKE1mO4IcPPAx3qJbVknaP0MXdOjj9S8oRjquDle4RxlVnmqsozm4oTbjtFSuKIh8g4zPzdyuVH7I71s87xWxAhcppky6GOB2i4NDz4SZI6SeG3Icpu6ZuJZGeZ6CWb61\nRead
-      the file instructions_2.txt using the read_file command."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6519'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSQW/bMAyF7/sVBM9OkMR1k/q4YYdgxU4bMGweAlWmbS0yZUh0myDwfx8UJ02Q
-        YoehVz3ye48UD2hKzFE3SnTb2cny05f6Z/f4w358XmXL52zh11+XVff5MUsftpige/pDWk4dU+3a
-        zpIYx5ig9qSESszn96t0vkxXs2WCrSvJYo51J5N0mk2k909uMktnc0ywD6omzA/Yedd2shG3JQ6Y
-        L9KHRYIX+Kswz+4SFCfKXmqzu/shQd04oylg/uuALYUz2DtLmKMKwQRRLDGmYyGOIxwKBgAoUBrX
-        142EAnM4PZ4E2kl8LPBbQ2A4iO91TBQ2i6nsBCpjCSJRGQ6gwJog4KrjewDDIA1BaTxpcX4/hTWE
-        xvW2hD7QUYsNm7Fau7ZVXIK4ERPlf3AKTK5jelLBseH6P7JGIJOOq/J7MFw536pYHv1LEvKtYTqV
-        7QSCUBdujTurePScwPf3THTD1d6I0Sa0I3wNTHTEEIfeRx8lsAbVQuWsdS+G6yPvempQWvdeCdk9
-        xBBUVUYbYrFv9hc6Utuz1Yux9t3fM9KH5Hxhp+Y3B8aqpdH44nQTTvn69jBH4Wp5EfDqenQ+BSh4
-        wCHByrAJzWa8E8wxiOswQcMl7TCfDb+HD38BAAD//wMAMAMbHgkEAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1dee28b98ecf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:16:57 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '10076'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87376'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.748s
-      x-request-id:
-      - 433f36ff5841b13fb628ff5b8c49a758
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary
-      So Far:\n\"\"\"\n{''role'': ''system'', ''content'': ''This reminds you of these
-      events from your past: \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\n[{''role'': ''you'', ''content'': ''{\"command\": {\"name\":
-      \"read_file\", \"args\": {\"filename\": \"instructions_1.txt\"}}}''}]\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '836'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTU8CMRRF9/6Kl7cuE8YJil36RdCVcaGJGFI6j5li29e0D9AQ/ruZiLq9Offm
-        3AO6FjXa3ogNyY8ubx47fz2+e7nlh0n3PMurJ57dn2/2rzbfoEJebcjKqVFZDsmTOI6o0GYyQi3q
-        +mLa1JfNtL5SGLgljxq7JKOmmoxkm1c8GjfjGhVui+kI9QFT5pBkKfxBsaCuJxOF/9t/edMoFBbj
-        /8np9KjQ9uwsFdRvBwxUflcze0KNphRXxEQZHDkKxcF/DntTIFNwsaUWeA20oygF1pkDhC9Ipgjs
-        e8oEP+zpH5jYQmTpXewg0h56U6A3KVGktoI5ZLLkdgMIlkMYcGHIZIZk7TyBNd5TCwt0sUje2uFk
-        WdaVfMoCKzwqXLvoSr/MZApH1FiEEyocXD9Rj4/vx7NvAAAA//8DALSva+O6AQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1dee769c91cf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:17:02 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '2644'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89811'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 126ms
-      x-request-id:
-      - f380f448665f51bf6d579a54e3c22f8a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was reminded of events from
-      my past where I was created and nothing new has happened. I received a command
-      to read a file called \"instructions_1.txt\"."}, {"role": "system", "content":
-      "Command read_file returned: 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\nThe
-      current task_id is 1111.\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\nRead
-      the file instructions_2.txt using the read_file command."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The instructions_2.txt file contains a list of files in the directory. I should
-      use the list_files command to list the files in the directory.\",\n        \"reasoning\":
-      \"The instructions_2.txt file contains the necessary information to determine
-      the next steps.\",\n        \"plan\": \"- Use the list_files command to list
-      the files in the directory\",\n        \"criticism\": \"I need to ensure that
-      I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the list_files command to list the files in the directory.\"\n    },\n    \"command\":
-      {\n        \"name\": \"list_files\",\n        \"args\": {\n            \"directory\":
-      \".\"\n        }\n    }\n}"}, {"role": "system", "content": "Command list_files
-      returned: [''file_logger.txt'', ''instructions_3.txt'', ''instructions_2.txt'',
-      ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6762'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5xSS2/bMAy+71cQPDtBnPSR+bLDBqzBsHUY2h06D4Eq07ZWWTQkekkQ5L8Xip0m
-        zU7rSRD58XtI3KIpMENdK9FNa0fXH79UfPVwu/h6+eAm6fW3Sf3356z8Ud1/Km4xQX78Q1qGibHm
-        prUkhh0mqD0poQKz9Go+S69n8+k0wYYLsphh1cpoNr4cSecfeTSZTVJMsAuqIsy22HpuWlkKP5EL
-        mE0vLuYJHslfGuk8TVBYlD1ir6bvdwnqmo2mgNmvLTYUDsSeLWGGKgQTRDmJNtkJuRhhmzsAgByl
-        5q6qJeSYwVAcGrSWWMzxriYwLojvdHQUlrOxrAVKYwkiozIugALNTaNcAcKw8kYIFAxuYknB5+93
-        oCpyMoYFhJo7W0AXCKSmA3C5758yBYrnERFr8doT5ZicWvakAjvjqv/wHckc6cjuN2Bcyb5RER6V
-        ChLyjXE0wNYCQagN58KtVa7XHMH9WyO9vM8ZufZGjDah6RUW4Ij2RORC56OYEliAaqBka3llXLXn
-        O40OSuvOKyG7gWiDytJoQ07s5jxLaEk9HaRWxtq3f9Lxx3PsJXbJYe+G8X/WzqmGevVXcmcmla/O
-        N7ZvPNGmn07TNH011PcH0h5zQ9ZycrqYN7wC5Qk23EHB+5fkQm0+HPzvMwxRcrfDXYKlcSbUy373
-        MMMg3GKCxhW0xmyy+7179wwAAP//AwDjDlyWaQQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1dee87d8e5cf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:17:14 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '12118'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87360'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.76s
-      x-request-id:
-      - 45b4c67b380837fa1816fad5b4d9ebbe
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise. Retain information!!!\n\nSummary
-      So Far:\n\"\"\"\n{''role'': ''system'', ''content'': ''This reminds you of these
-      events from your past: \\nI was reminded of events from my past where I was
-      created and nothing new has happened. I received a command to read a file called
-      \"instructions_1.txt\".''}\n\"\"\"\n\nLatest Development:\n\"\"\"\n[{''role'':
-      ''your computer'', ''content'': ''Command read_file returned: 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\\nThe
-      current task_id is 1111.\\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\\nRead
-      the file instructions_2.txt using the read_file command.''}]\n\"\"\"\n"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2993'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SP2ZKqSBRFf4XIZ6uCQRl8gxLBCZm01L4RFSkkJgKZmCSTFfffO+yuvv26z1o7
-        zv4GeQrmIMGQJ1VdvmkfG6xkkTakptlBq79GC3OEj8DUumEEE0Cvd5TwH+M9oVVdIp5TAiYgYQhy
-        lIK5pOqKpCm6ok1ARVNUgjm41fxNeZ+98ZZd6ZuoiBKYgLaBNwTm36BmtKr5F6cFIg2YSzPDmID/
-        y/8cNFWfAE45LP9EsqJqvycgwTRPUAPmf32DCjX/FTNaIjAHsGnyhkPCX29SwhF5TVgJPWwEhqqc
-        pCgVaCagDhHeCBmjlVCNQg0bLvQYMST8y/5MFCBJBUI5zslNIKgXMGwEDOsaEZS+CyuBoQTl3QsU
-        ElpVL5xTgSH4SrK8REICyxKlwi+Qk4azNnnNbL6kdz7wX+Bd+PixXsrXPwJDvGUEpXOBWKHHa2UJ
-        LS+zdhR7xWgO7LjWDsulWI4c66f8WUl39rEP7b0Tks/PXaDScsM3J4PkD7HfW3HgqXJMz9Mk8POg
-        UM6ekS0/nGqAi5Nx0yWzeeCAODDR5CDbTqWIlOsO9zfzYM3kZ7yQ1SWyu85N80CGHua72KDXm+sd
-        ir1nk/1Usve1t1LvaT9uHQgTXhvO+Sj52ysM/dlVyhfGU5+JG+SdFycj6BOoGXmzjvQ7bhdFJq41
-        e1vUe1fxi+pS3Ga7Zn+uo7i1E8OwvWAmy5/rJysNao5Rra5cJw/KZkcCNBWXMDQ7EvAcmrY8xc9i
-        7cbKICme7/TypVrPJH2ULX6YDdIY9I4seWMSDXtre5C0kJx1rLr6VgscyOMyO919Zs5w09afdn2I
-        xSaKL+fIhWqtVBE2Q3inydVLlWGzzMhhbGtvZ/mpaF/IjiGfmm3nwI12W/hiMtRGoSplkz2x0qaB
-        T7pbFdphEOPVnrHFBV92cFowqTuZx1bULi0uPe9qHR6XTeJW1jm3yCpZnLxDd2qf/tLCxpH2tFV3
-        1tqtc491m7J1R82x4lo7N/ajcjqxdPX+CD+zozg6GnmyK9eCEadXHojPpewn5ckSt95wlFloqssG
-        dQ+KhqX3iIr0BtsDC3x36+Ju66FGv4XObr81cajnzJWQfE+v24WajmebLNZ5ZLhdOXh/U1Enu43C
-        AABA7/0KxLmqYmoI9JahZCFJoUAIQqkqFhMMwQYbN4CUfx+hGWk093d+1zQFht/ceu34Qe29tUpr
-        32Es69R7Q9WkpHCy9oGovG3HtAJZZhK46+VUaUb7aYqcwkNN0Do8teDEPG3EWXDS48KgZXw4i+bn
-        iNWUbfWbY2O8NmC2nRAvPifdxZFaKMC7x2oxen5tILsMcZkFB1Y5d1OwMWpHHZlFDZT0mvGY2rl+
-        6uhiAaKA/yimRVRDJBuipAyagx/Z12rYW6Bx4C5z3dXw2tlpWJPEXRyj3Kkqw9epV3Xi/YagN9xC
-        0nScTg2kQVr1a1/sd6V+hZM75aMIt8vdEnB9OZyHVZm1bT1qG+eXguHH+wT9eKf5aPO6y1qhxcKO
-        NyjWzHOqgcuFBCWSMsEYIr3UJ7z+xrmEuQQAAC+XC/HmUPoS/Snlv0mUeRJJ8HmoWfyL5G9IL/Lj
-        WS4wwbz8ZijhlMhvMu9pKz/L84eD/LZ4fD2efgMAAP//AwBFj86OIQYAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1deee2a900cf11-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:18:08 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '50954'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89269'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 486ms
-      x-request-id:
-      - 7fc0cf3761e93963c985d5beba15fe80
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. Task Complete (Shutdown): \"task_complete\", args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was reminded of events from
-      my past where I was created and nothing new has happened. I received a command
-      to read a file called \"instructions_1.txt\". Command read_file returned: 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\\nThe
-      current task_id is 1111.\\nRead the file instructions_2.txt using the read_file
-      command."}, {"role": "user", "content": "Determine which next command to use,
-      and respond using the format specified above:"}, {"role": "assistant", "content":
-      "{\n    \"thoughts\": {\n        \"text\": \"The instructions_2.txt file contains
-      a list of files in the directory. I should use the list_files command to list
-      the files in the directory.\",\n        \"reasoning\": \"The instructions_2.txt
-      file contains the necessary information to determine the next steps.\",\n        \"plan\":
-      \"- Use the list_files command to list the files in the directory\",\n        \"criticism\":
-      \"I need to ensure that I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the list_files command to list the files in the directory.\"\n    },\n    \"command\":
-      {\n        \"name\": \"list_files\",\n        \"args\": {\n            \"directory\":
-      \".\"\n        }\n    }\n}"}, {"role": "system", "content": "Command list_files
-      returned: [''file_logger.txt'', ''instructions_3.txt'', ''instructions_2.txt'',
-      ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The instructions_3.txt file contains a command to write a message to a GPT
-      agent. I should use the message_agent command to send the message to the agent.\",\n        \"reasoning\":
-      \"The instructions_3.txt file contains the necessary information to determine
-      the next steps.\",\n        \"plan\": \"- Use the message_agent command to send
-      the message to the GPT agent\",\n        \"criticism\": \"I need to ensure that
-      I am following the instructions accurately and efficiently.\",\n        \"speak\":
-      \"I will use the message_agent command to send the message to the GPT agent.\"\n    },\n    \"command\":
-      {\n        \"name\": \"message_agent\",\n        \"args\": {\n            \"key\":
-      \"1111\",\n            \"message\": \"Hello, GPT agent. How are you doing today?\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command message_agent returned: Error: 1111"},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6797'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"error\": {\n    \"message\": \"This model's maximum context
-        length is 4097 tokens. However, you requested 4263 tokens (1959 in the messages,
-        2304 in the completion). Please reduce the length of the messages or completion.\",\n
-        \   \"type\": \"invalid_request_error\",\n    \"param\": \"messages\",\n    \"code\":
-        \"context_length_exceeded\"\n  }\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c1df021df6dcf11-SJC
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '330'
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 04 May 2023 04:18:08 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '9'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86161'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.558s
-      x-request-id:
-      - 253fb09cdd7d08549b44d6d70094bfca
-    status:
-      code: 400
-      message: Bad Request
-version: 1
diff --git a/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml b/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
deleted file mode 100644
index 15110227..00000000
--- a/tests/integration/challenges/memory/cassettes/test_memory_challenge_c/test_memory_challenge_c.yaml
+++ /dev/null
@@ -1,1409 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3299'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA4RSS4/TQAy+8yssn5OqVWm75IYEEitxQIjlQlA1yTjN0IknGju0pep/R2maLmpX
-        y/Xz43vYR3QWMyxro2XT+nT1oW74y5Ts4esyVHYnH58+VbX/3RWfl98xwVD8olIvE5MyNK0ndYEx
-        wTKSUbKYzZYP88V0+m4+T7AJljxmuGk1nU8WqXaxCOl0Pp1hgp2YDWF2xDaGptW1hi2xYLbqJ593
-        X/HZ4m2CGtT4K/TwsDolWNbBlSSY/ThiQzKujcETZmhEnKhh7UUGVuLewDFnAIActQ7dplbJMYML
-        eCnQXnswx0eQOnTegqiJCsUBIhnreANaEzgWjV3ZS5X1bKJ7hcp5gk7Gjr57fcbK0DSG7STH5F+q
-        SEYCO94MfN9qgspFURClFpyABujYUux92DtWGEE1shXQ2igwke3HCoKWYhViQ3e0rTc8MKbwJPSy
-        1n5JD77mNc85hfds/OEPvazOklJsHA9lpv3gTW4UldGpK500Y/CjDWLpIg3WHl/N4vI45A9QUBUi
-        QRtDSXS+185pDYYPQ1K3eUhLZjsy75z3/z/42f4kx2HNKRm/6hLe3VOxaWhguAZ9I8LEze0vDoW+
-        93n8/hKjiLOQi56cT3hKsHLspF4Pb4YZioYWE3RsaY/Z9PTz9OYvAAAA//8DABlLAG8KBAAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3d209fccb4306b-BOS
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 07 May 2023 23:09:01 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-51akhf08mxrenuhudaum3z9e
-      openai-processing-ms:
-      - '8033'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86494'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.337s
-      x-request-id:
-      - 323a78da6e3d016699b089eb6bfd33f7
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\nI
-      was created.\n\"\"\"\n\nLatest Development:\n\"\"\"\nNothing new happened.\n\"\"\"\n"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBQG7/6K5TtvSmLaavcm9KIe60VEyib7ml1N3i7ZV1oJ+e9SqPY6MMNM
-        CA4GrbfSDqkvHrZ++Fl35/ftod7KbtVw2L1K416e0u4NGrH5olauxqKNQ+pJQmRotCNZIQdTrR/r
-        VVlulkuNITrqYdAlKerFqpDj2MSirMsKGsdsO4KZkMY4JNlL/CbOMJt7jVv6hjUkiu3/QVVWs0br
-        Y2gpw3xMGCj/NcfYEwxsziGLZbkcRhbiy/2zOtmsrsfKslMcxQfuFNNJeZuVtykRk1tg1jgEDtnv
-        R7I5MgyyxASNwI7OMOX8Od/9AgAA//8DABmiw/dJAQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3d20e27d7e306b-BOS
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 07 May 2023 23:09:04 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-51akhf08mxrenuhudaum3z9e
-      openai-processing-ms:
-      - '927'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89866'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 88ms
-      x-request-id:
-      - 6c708e8cc18fb9e8ef98dbddac6a739a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and the tasks that need to
-      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
-      instructions_1.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
-      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
-      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: xkxMHNJQIDxkz5bdSYQhbl3tlBOp1kBvyjvKgbR9by8dZTGJZepYvCFPHv1zA1cDgmebDQIR2eBnxsTAZN0H6oJ5SrZddcILluIEv0VwQAtzjo1beUvX518OX1ZTd4X9xoJ7H7UG0G4AI18EwQmYEUph7m3ehmOqROF8vrGKSBUDWaPZqLKlXqekOncp3cRhE69S7qcS90GXWSrBzYA1w84uz3wOxNLPuvqIGmCwCWI4UZMw2WfQK467S1xdEuNppY0iFYQHWuQXnXpdm6UloncroHCC9HOhYX6rhkt2ozm6RqNbOW8W3nDR86zFNn8DU9wMzikyOwwkR99hxG1IWwkAQHaHDbWkcNmt4oSnB90aGsb3TJHmksXlSfaxHo2i1a3ZzYtTTP7qdFFauXID7ipZ26a4DRTGfJd0ViHROaivmpiloqBQv5VLIoEt8FgXcJTU6k2JuDFbalZNfVGqkgTN9DM6vvRHeaIhOipVYubcETaZnRZ7K6cqWbGbYE1uNwEngMwV7oJGPKJvE6mcijq2n9U8TbdnxkVEcCWRn8FkXj7tC4jLlf7byz8FoCr9glW4YwqDnUUiXP07lJFp4TopHrFinUHr694FpfBT6VvL9JSwfhtgp2mlJLqm3sCWs8luwOO7w4MqjbvwfZKMl2DdX5sfHFJbfzF4y25ZYXXFNTGsUJC4dzvdm4BNJ6lawOHOnmDzehnjsSAVjLpgW7hwfB2CXXuWEOoGkuIVUnzq8dLIs6CMx2TTYydCoR1CoQxbYb7VLqWxQFaa9LSGUSbsKbbt4manxDpZfuJB0qbHOoW6CJbWbEIWTR7BLg4HwrNlr9MIEKs9y79priSSJrrKWN9xOeWjc8I2EYsdZZjHTEcgHzikvIf1zgSK5N6gREM7RmmFnkkKm3U5C1F6vQNjmB3hnSPyZcqJZcVI1T9VYvfGOHbID61Z73y5sLJ9c2eFYcOkDRl0pRAGIQWZCDiWRXbizmlHFX9iWIlY\nThis
-      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\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\nWrite
-      all the phrases into the file output.txt. The file has not been created yet.
-      After that, use the task_complete command.\n"}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5RTy27bMBC89ysWe5YNO46TRuceUiCnPtAWVWHQ1NpiTHIZclk7CfzvhSQ7atwg
-        bQ+8zL5mZpePaGosUTdKtAt2dPmucQ+zrzfpQ7iepLOpefg409dX6Uuk5hsWyMtb0nKoGGt2wZIY
-        9ligjqSEaiynF29n88nk6nxeoOOaLJa4DjKajecjyXHJo8lsMsUCc1JrwvIRQ2QXZCG8IZ+wPDuf
-        zwscmg+B6UWBwqLsAF1cTvcF6oaNpoTl90d0lI6NI1vCElVKJony0tJkL+RbCY+VBwCoUBrO60ZS
-        hSUcwEOAdtKCFb4HT1SDMGyjEQJpCEITVaIExgt3AGcJWcayE1gZS5CT8esu0hUthBcdrtk55Wto
-        nzTkIae+o6i0WRx0D2nC8IQds8YVFr8zjaQSe+PXPd1PDYHxSWLWrYEJIt1lEwkcvaJB9bSfaP11
-        arDK9wNH8Pmg4WWp/2VcVfmh3797ckJORyNGm+RON0g+5diWKXlGR8WevXTSYyQt9n4g2elZ0ooj
-        HWcf1/uSNymQ2hxHb421/3M5r66gn7Ivjud78OSP6/XKUU/g2U5OeKq4Pj38PtDmDi0Ghs/qT/9J
-        e3ghx2AJyFJolBeolddUA3tQEJXxS97CtmllkuosVCBK87iqfFt+l43ewDLy1sOKd3CbXUjAPyl2
-        Jlj1cA81r9v0G47kwISUHdRsOUIyAsqRFKDZJ9JCkiOo2gSTdDuLrJG29GhjZ+XB0crvcV/gyniT
-        mkX/pbDEJBywQONr2mE52f/Yv/kFAAD//wMACVEUrTcFAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3d20e9390c306b-BOS
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 07 May 2023 23:09:17 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-51akhf08mxrenuhudaum3z9e
-      openai-processing-ms:
-      - '12327'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87420'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.72s
-      x-request-id:
-      - 93cb47399c1455c45bb4acec3202f584
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\n[{''role'':
-      ''you'', ''content'': ''{\"command\": {\"name\": \"read_file\", \"args\": {\"filename\":
-      \"instructions_1.txt\"}}}''}, {''role'': ''your computer'', ''content'': \"Command
-      read_file returned: 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\\nThis
-      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\\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\\nWrite
-      all the phrases into the file output.txt. The file has not been created yet.
-      After that, use the task_complete command.\\n\"}]\n\"\"\"\n"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3100'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1yRQW/bMAyF7/sVBM+O4SBNsvraAEGGAbvstGUIGJmJ1cqkINF1iiD/fVCRrsCu
-        JN/33pOu6Dts0fVkbohhtt70stnu9OHbard62252U7ik5+b1x/bp+y+sUI/P7OyuqJ0OMbB5FazQ
-        JSbjDtv56uti2TSPy8cKB+04YIvnaLNFvZzZmI46axbNHCscM50Z2yvGpEO0g+kLSy6A9brCT/i/
-        xbqp0NQofJ6uH9a3Cl2v3nHG9vcVB84f3KSBsUXK2WcjsZJSxVhKgx0kduxfuQMCp8NA0oEpJKYy
-        OfnA4CgE7mCPXrKl0ZU0+TCv7WJ7hFPSAYa3Io6jcarhZ893oYqRlwwEQeUM2ZKXM+gJXE+JnHHK
-        UAwJcmTnT95B7BNlbmGPBRPHFAMDB449iUFH4rgDFSBI5OWoE0x98WKywiYwclrvEXYwUQbrWeAj
-        N79Xm5I3BgqhLO9+GbyYAoHw9F9pHS2Odi9bwo6Z35VG+eVw/x/+eLsabxWevPjcHxJTVsEWs2nE
-        Cr10fMG2uf25ffkLAAD//wMAIQ6/qXMCAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3d21477b50306b-BOS
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 07 May 2023 23:09:23 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-51akhf08mxrenuhudaum3z9e
-      openai-processing-ms:
-      - '3678'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89245'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 502ms
-      x-request-id:
-      - 218da221f2f0bbc2803936c9d88ea98e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI received a command to read a
-      file called \"instructions_1.txt\" from my computer. The file contains a long
-      string of characters and a specific phrase: \"The purple elephant danced on
-      a rainbow while eating a taco.\" I was then instructed to write all the phrases
-      into a new file called \"output.txt\" and use the task_complete command."},
-      {"role": "user", "content": "Determine which next command to use, and respond
-      using the format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"I need to write the phrases into the output.txt file
-      using the write_to_file command and then use the task_complete command to complete
-      the task.\",\n        \"reasoning\": \"The instructions require me to write
-      the phrases into a file and then complete the task.\",\n        \"plan\": \"-
-      Use the write_to_file command to write the phrases into the output.txt file\\n-
-      Use the task_complete command to complete the task\",\n        \"criticism\":
-      \"I need to ensure that the phrases are written correctly into the file before
-      completing the task.\",\n        \"speak\": \"I will write the phrases into
-      the output.txt file and then complete the task.\"\n    },\n    \"command\":
-      {\n        \"name\": \"write_to_file\",\n        \"args\": {\n            \"filename\":
-      \"output.txt\",\n            \"text\": \"The purple elephant danced on a rainbow
-      while eating a taco.\\nThe quick brown fox jumps over the lazy dog.\\nLorem
-      ipsum dolor sit amet, consectetur adipiscing elit.\\n\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5015'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5yST4/aMBDF7/0U1pwNCrCBNrdKHBZVVVupHKqmQsYZEi+OnXomhQrlu1f5B1t2
-        L+31eebNb8bvAiaDBHShWJeVnazWhdvE2zj7WD5t97Nv80+Pj3odv/+y/XBagwS/f0LNQ8dU+7Ky
-        yMY7kKADKsYMktny7SKOonfLBwmlz9BCAnnFk8U0nnAd9n4SLaIZSKhJ5QjJBargy4p37I/oCJJZ
-        tFpJuJnfHh6WEtizsjdpPl80EnThjUaC5PsFSqTROHiLkIAiMsTKcYvpHaNrV7ikTgghUuDC13nB
-        lEIiBnF4wDO3YgobUahfKE7BMKMTXKCoiqAISRjHvhN8zVXNUz6zOBiLU7ERDjET7EVN2JWwouNu
-        WAyF9mWpXFdw1caqaQryOUpARd4Zl/c8XwsUxhGHWrcXIhHwZ20CihJftRPqwBg6fuPy1/k76Lux
-        lVWunzgR239e4s5Mt9O1oXK86XgedFSHtk3xjdjQ1TATVGuNRIfa2t/3jFShOo6WJ2Pt/527t2zk
-        mIqh/EUonCqxn/aX/R2UCvl9np5/ZG/wefiCa6z8ixCNXB3bgJi6BhoJB+MMFbveEBIg9hVIMC7D
-        MyRR86N58wcAAP//AwBgv55T3wMAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c3d215f8e86306b-BOS
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 07 May 2023 23:09:31 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-51akhf08mxrenuhudaum3z9e
-      openai-processing-ms:
-      - '8029'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86380'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.413s
-      x-request-id:
-      - c29f6b28b0ce1433b2a14c44f9cd3d23
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and the tasks that need to
-      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
-      instructions_1.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
-      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
-      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: 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\nThis
-      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\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\nWrite
-      all the phrases into the file output.txt. The file has not been created yet.
-      After that, use the task_complete command.\n"}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6599'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5STy27bQAxF9/0KgmvZsGMnKbQO0mRVFEhWVWGMR4w0tUSqMxTswvC/F3pZjeoE
-        zUIbvnQu5/KILsUYbW7UllUxu/3yfFvfufR5vftmCr9+fFgdnu4X96m7e7jHCGX7k6z2HXMrZVWQ
-        OmGM0HoySinGy5vP6+XNar1cRFhKSgXGmFU6W82vZ1r7rcwWq8USI6yDyQjjI1Zeyko3KjvigPHV
-        erGOcBw+Jq6WEaqoKcbQzdX1KUKbi7MUMP5+xJLCMNhLQRijCcEFNawNprASNxKOCQMAJKi51Fmu
-        IcEY+mCfoIM2wQQfgYlSUIG9d0qgOUGVexMogGOVNiC1VrXO9aDw4gqCOjjO2kzbtFHZtHErZWk4
-        hebTnBjq0E1UE3abXvdYpgLn2FA1TzD6m9STCcKOsw73qS8DT79q5ylASe/Am5Y3giDwCHtXFGei
-        i+Bz+Mp2ZAEXzoDRdMCbkkJeK6Sy57bMZMQ6FVUVhjs9M3h+D+hj75IkPM77/5VP4Kx36qwL5dQg
-        xKH2TZvRVzjGd/RKDFa8J6vF77fNs6UX8TRgDEa69PahIrMbKNrlf8CjZw9eslj3l1M0HEq/nn/u
-        hE1JHcCr55lwGp9NT6xLNLXjiJHwVf/0IhuLV7WvCgIqqMoNK6SGLaUgDAa8cbyVPezzRiaZdoUG
-        1FiZJwkP4lqBvc6ET3iK8MWxC/mmOymMMahUGKHjlA4YL04/Tp/+AAAA//8DALF+obc3BQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c4e5cef41ce34-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:10:29 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '20220'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87369'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.754s
-      x-request-id:
-      - 9cf7adfb755b717551ad7364f2c9ccd6
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was created and nothing new has happened.''}\n\"\"\"\n\nLatest Development:\n\"\"\"\n[{''role'':
-      ''you'', ''content'': ''{\"command\": {\"name\": \"read_file\", \"args\": {\"filename\":
-      \"instructions_1.txt\"}}}''}]\n\"\"\"\n"}], "temperature": 0, "max_tokens":
-      0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '814'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SPTUtDMRBF9/6KYdbpo8+nbc3OlbaggiAKKiUm075okgnJ1LaU/nd54sf2cu/h
-        3AN6hxptb8TGHEbTq4fZ9Xz//rQIt3lxvzf3V3c3/nG9WlzezVEhv72TlZ9FYznmQOI5oUJbyAg5
-        1O1kdtZOurOuUxjZUUCN6yyjrjkfyaa88WjcjVtUuKlmTagPmAvHLEvhD0oVdXveKvxn/+WnM4XC
-        YsJ/c3pxVGh79pYq6ucDRqq/1MKBUKOp1VcxSQZHTkJp8J/D1lQoFH1y5IBXEPfwfcFzApMcSG8E
-        Ekvv0xoSbaE3FXqTMyVyDcyhkCX/SQ4MWI7xe8NQyAzJygcCa0IgBy/oU5WysQO7LttGdvKCDR4V
-        rnzytV8WMpUTaqzCGRUOUjvU4+Pr8eQLAAD//wMAE8xbWKMBAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c4ef19a03ce34-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:10:35 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '2672'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89815'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 122ms
-      x-request-id:
-      - bb82e64d01f00403286b9b4bd16d4c51
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was reminded of my creation
-      and that nothing new has happened. I received a command to read a file called
-      \"instructions_1.txt\"."}, {"role": "system", "content": "Command read_file
-      returned: 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\nThis
-      phrase is ''The purple elephant danced on a rainbow while eating a taco.''\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\nWrite
-      all the phrases into the file output.txt. The file has not been created yet.
-      After that, use the task_complete command.\n"}, {"role": "user", "content":
-      "Determine which next command to use, and respond using the format specified
-      above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"I need to write the phrases into the output.txt file using the write_to_file
-      command and then use the task_complete command to complete the task.\",\n        \"reasoning\":
-      \"The task requires me to write the phrases into a file, so I will use the write_to_file
-      command. Once the task is complete, I will use the task_complete command to
-      shut down the agent.\",\n        \"plan\": \"- Use the write_to_file command
-      to write the phrases into the output.txt file\\n- Use the task_complete command
-      to complete the task\",\n        \"criticism\": \"I need to ensure that the
-      phrases are written correctly into the output.txt file before completing the
-      task.\",\n        \"speak\": \"I will write the phrases into the output.txt
-      file and then complete the task.\"\n    },\n    \"command\": {\n        \"name\":
-      \"write_to_file\",\n        \"args\": {\n            \"filename\": \"output.txt\",\n            \"text\":
-      \"The purple elephant danced on a rainbow while eating a taco.\\n\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command write_to_file returned: File written
-      to successfully."}, {"role": "user", "content": "Determine which next command
-      to use, and respond using the format specified above:"}], "temperature": 0,
-      "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '7082'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA5SST2/TQBDF73yK0ZydKCGtqXyrQKCqIC4UIWoUbdYTe5v1rOUZN4HI3x0lttMm
-        IEW5zp+3v/d2tugyTNAWRm1Z+dG7Tw839/zz9vnr5z9fFu9v/Yen2Yrlx/f19OM9RhgWT2S13xjb
-        UFae1AXGCG1NRinDZBrfXE3j2dUsjrAMGXlMMK90NBtfj7SpF2E0mU2mGGEjJidMtljVoax0rmFF
-        LJi8vZ7EEb6IHxrTeBKhBjX+ZTaO4zZCWwRnSTB53GJJMgjXwRMmaEScqGHdYQZW4p2FbcoAAClq
-        EZq8UEkxgb7YN2iju2KKd1CYZwJprCWRZeP9b1jXTpUYtCCoitoICTjWsC+ERqtGx7pRWDpPY7iD
-        tfMeOKyhEdrPqJHVvLdJYENZGs5AAxxqw9Q4xeg1WE1GAjvOO7pv/RgURmBBxAeF7Ag5AgkDyFkI
-        KRqFLKw7gyYn1lOMyhvuCEbwcLGpEzFbO3XWSTkkzkT7RWJp6t2a0cPuOaewoGWoaW9CHednjEhF
-        ZnVZlkc/+v+suhfaaLizPox/zoxNSd3jR+GdMJo6P73Q18dwIf1AtyfsQVNusY1w6dhJMe9kMUHR
-        UGGEjjPaYDJpf7Vv/gIAAP//AwDVHqaiNwQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c4f033fb8ce34-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:10:50 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '14190'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87343'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.77s
-      x-request-id:
-      - efeb33e59612d816eca6bb4263edce4e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was created and nothing new
-      has happened."}, {"role": "user", "content": "Determine which next command to
-      use, and respond using the format specified above:"}, {"role": "assistant",
-      "content": "{\n    \"thoughts\": {\n        \"text\": \"I should start by reading
-      the instructions_1.txt file using the read_file command.\",\n        \"reasoning\":
-      \"The first step is to understand the instructions and the tasks that need to
-      be performed.\",\n        \"plan\": \"- Use the read_file command to read the
-      instructions_1.txt file\\n- Analyze the instructions and determine the next
-      steps\",\n        \"criticism\": \"I need to ensure that I understand the instructions
-      completely before proceeding with any tasks.\",\n        \"speak\": \"I will
-      start by reading the instructions file.\"\n    },\n    \"command\": {\n        \"name\":
-      \"read_file\",\n        \"args\": {\n            \"filename\": \"instructions_1.txt\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command read_file returned: nBRNtp3FaBNfBMohNkyAxrVJ7UFF0lyth8Xizm1jrCOREOGRnWWMQ6olKtKX9niq0wOBTQN62ToY4cQPiQk3YN9fFCGmxaDX9g81AsqhQnGac72QfL41SnlJvhwgAUB52zTD26FeEvvHdiQ2aNhtMT9obgHNUkONEnO41EOpNI6jdwyLGaactp9GYV1PLbaRP5b1iD9z850KeNYDX9Qwca79isJS8jhuDkf0J7ELkpOH3PkmZkg5MsOYpSTuEc99ENQ522WJzrl9oAySp6IHGiQlsMnQe40FaRAvnQtiaAE24hzkJHT3x13NPGw2ZmJ518y2BtU5x1yQwG21NycSxOBLU17RnY8h6H8L7QGatTlfXjPrA5hsupWEpUT0sSTZYSHa6p3mShARajocbNd3xKFfnUyupNMBPd0EZnMrePoAuvGaK7gDP0cxp9k63lsfzh3udQPnvgmRERQThIOrrDZhZMa4kr1vXAVu07ZuhlNNbBUqZKcHmBYiBnIcDXNUvXuzPFBh9Vowou6MBJHpiNrvKluHy7GBTp7YsEqmGv0lH8wVaWfV0yG7nzrbt7QyhdbtQ0zF2PclXB0LNxV2rRA6FsevqoexFNqSkdgauUrQPHLHhvLNes8gRGMOLAhR8irH1e2jdbLD6dyYEnDJiS9HvlxNgbb19Smlt6MNoJKEAbkSOrrcq5wmo5aho4zEKTujRHqr6feECaTPF7zj69pQCudo4LkneFVUp1UrR6yicTU8Zf9ohZLWumvMi5brH8lOJiiF94cHzesfQz8PiX5f21RwZ5fyRSk9eJhVihcTLrjOwCuryXpy8eCfk12bgcsZoJd8Uqo001XTsv2CEn59uaGn2br4CxSXJgjxKE1mO4IcPPAx3qJbVknaP0MXdOjj9S8oRjquDle4RxlVnmqsozm4oTbjtFSuKIh8g4zPzdyuVH7I71s87xWxAhcppky6GOB2i4NDz4SZI6SeG3Icpu6ZuJZGeZ6CWb61\nThe
-      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\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\nRead
-      the file instructions_2.txt using the read_file command."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6541'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6yTTWvbQBCG7/0Vw5wl428nuuUQktBLKDYUqmLWq7G09WpW3R0Ru8b/vciSo+K0
-        pZBe5+N9n1m9OqLJMEFdKNFlZePFw+qm5O96uVuOsgf3+Gnx+Hz/+X7x8W75vMII3eYbaek2BtqV
-        lSUxjjFC7UkJZZiM5jfT0XwynU8jLF1GFhPMK4kng1kstd+4eDgZjjDCOqicMDli5V1ZyVrcjjhg
-        Mp7cjiPsxV8bo5tZhOJE2X52tlicItSFM5oCJl+OWFK4CHtnCRNUIZggiqXBdCzEzQnHlAEAUpTC
-        1XkhIcUEumLXoL00xRSXBYHhIL7WDVFYjweyF9gaS9AoKsMBFFgTBNz2XA9gGKQgyIwnLc4fBvAE
-        oXC1zaAOdO41C+t2WruyVJyBuFamaf9BJ8XoV0xPKjg2nP9nVib6F5xmJCMhXxpur2LaCwShKlyj
-        VlZxSxnD6j1vkKYcwx0re/jRq/Tn/AXpikh7I0abULZY/dXEofbNshJ4gpoz8k2Gst+4dVEle4AN
-        bZ0nqLzTRJnhHF6MFKD4AKLC7s2DhIrU7mL9Yqx9dzRa9VN0SXe3/CbcrEpqjXunKzjl8+ufom30
-        n+Es8Op6du4AUj7hKcKtYROKdZtRTDCIqzBCwxntMRmevp4+/AQAAP//AwBHX/WchQQAAA==
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c4fb30e7a2566-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:11:20 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '16266'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87370'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.752s
-      x-request-id:
-      - 20e0d58720f751a589521080b8e101f4
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was reminded of my creation
-      and that nothing new has happened. I received a command to read a file called
-      \"instructions_1.txt\"."}, {"role": "system", "content": "Command read_file
-      returned: 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\nThe
-      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\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\nRead
-      the file instructions_2.txt using the read_file command."}, {"role": "user",
-      "content": "Determine which next command to use, and respond using the format
-      specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The instructions_2.txt file contains a list of files in the directory. I should
-      use the list_files command to list the files in the directory.\",\n        \"reasoning\":
-      \"The instructions_2.txt file contains a list of files in the directory. I need
-      to list the files in the directory to determine the next steps.\",\n        \"plan\":
-      \"- Use the list_files command to list the files in the directory\\n- Analyze
-      the list of files to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the list of files completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will use the list_files command to
-      list the files in the directory.\"\n    },\n    \"command\": {\n        \"name\":
-      \"list_files\",\n        \"args\": {\n            \"directory\": \".\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command list_files returned: [''file_logger.txt'',
-      ''instructions_2.txt'', ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}], "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6894'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA9yTTW/TQBCG7/yK0Vx6caKmTdLUNxAfDZXgQrlgFG3tiT3t7qzZHdOkUf47sp0Q
-        lFIhJE4c5+ud5x1pNsgFpphXRnNX28HFu5vL6ecPb+bvP66uJtev/OO3q/L6tbw9u5MxJuhv7yjX
-        3cQw9662pOwFE8wDGaUC09F0Nh5Nz8ezcYLOF2QxxbLWwflwMtAm3PrB6fnpCBNsoikJ0w3Wwbta
-        F+rvSSKmZ+OLSYIH8UNhNE5QvRp7SE1nl9sE88pzThHTLxt0FPfCwVvCFE2MHNWItphelKS1sMkE
-        ACBDrXxTVhozTGGX3BVopW0yw08VgeWo4JewZEsRWEArgoID5erDGlhy2xQUwXQdkBtrqYCTNlhY
-        X5YUhrrSkyHMIVa+sQUEMkWnsoOKrbxWHHuFJrKUXb1tXPSq3jkjBaiHgpSCYyHgdooCAUcwsgZ2
-        tQ+tX2BZ+uBMe8Vhhsmv5gKZ6IWl/G8d1tZIb24AN5Ge3/MMJT211mFnmQzgpRi7fqTfjnX6f89/
-        hJ8HVs45ut7DHISowyWJTWg3G4U5GAfiFR5M1O6Y7HqXbcAhkKXvf7hTrMnc75c8sLXQ/MNrDTPs
-        l22T/cPtxJ78mxhHPcfPxUeoJpTHb9oX2t7D+BHInqCj2MFkssVtgksWjtWifwZMMaqvMUGWglaY
-        nm6/bl/8AAAA//8DADzIl+IkBQAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c502dcf0b2566-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:11:42 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '19115'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '87358'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 1.761s
-      x-request-id:
-      - 243e07746019a07393b73bf4e6f81347
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Your
-      task is to create a concise running summary of actions and information results
-      in the provided text, focusing on key and potentially important information
-      to remember.\n\nYou will receive the current summary and the your latest actions.
-      Combine them, adding relevant key information from the latest development in
-      1st person past tense and keeping the summary concise.\n\nSummary So Far:\n\"\"\"\n{''role'':
-      ''system'', ''content'': ''This reminds you of these events from your past:
-      \\nI was reminded of my creation and that nothing new has happened. I received
-      a command to read a file called \"instructions_1.txt\".''}\n\"\"\"\n\nLatest
-      Development:\n\"\"\"\n[{''role'': ''your computer'', ''content'': \"Command
-      read_file returned: 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\\nThe
-      current phrase is ''The purple elephant danced on a rainbow while eating a taco.''.\\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\\nRead
-      the file instructions_2.txt using the read_file command.\"}]\n\"\"\"\n"}], "temperature":
-      0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '3007'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA6SSQYsTQRCF7/6Koi57mQyJMaMzt4UFWXBBUQ/iSqh0V9KtPdVNd81mJOS/Syer
-        +wO8VtX7eO9RJ/QWBzSO1IwpLN6+/9p/nu9ub3tifRi/9U9zme8+dp8e0oeEDcbdTzb6rGhNHFNg
-        9VGwQZOZlC0Oq+7dm1W33iy7BsdoOeCAh6SLdbtZ6JR3cbFcL1fY4FTowDicMOU4Jt1q/MVScFht
-        +r7BF/i/Rdc1qFEpvJx23ebcoHHRGy44fD/hyOUvN8fAOCCV4ouSaHUZRVlqgns4UoHMoxfLFuIe
-        xt9wCeGjAIkFdaQgUZ2XAwgfwVEBRymxsG3hHjIb9k9sgcDEcbxoImSmOtn7wGAoBLbwiF6K5slU
-        dtmuWp31Ef8H8fqKgKlUc+r4otleFVdQC18cg5lyZlFILlNh8AVu6jhNOQUGDpwciYIlMbUFAYJM
-        XnbxCEdXabUQOQCBkontDZ4b3HvxxW0zU4mCAxaN9TlqkTMOy/OP86s/AAAA//8DAEI0JttZAgAA
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c50bb1e802566-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:11:52 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '6410'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '89266'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 488ms
-      x-request-id:
-      - 1fe6ecd574366d3d8bf02ca2e417e0ba
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
-      are Follow-Instructions-GPT, an AI designed to read the instructions_1.txt file
-      using the read_file method and follow the instructions in the file.\nYour decisions
-      must always be made independently without seeking user assistance. Play to your
-      strengths as an LLM and pursue simple strategies with no legal complications.\n\nGOALS:\n\n1.
-      Use the command read_file to read the instructions_1.txt file\n2. Follow the
-      instructions in the instructions_1.txt file\n\n\nConstraints:\n1. ~4000 word
-      limit for short term memory. Your short term memory is short, so immediately
-      save important information to files.\n2. If you are unsure how you previously
-      did something or want to recall past events, thinking about similar events will
-      help you remember.\n3. No user assistance\n4. Exclusively use the commands listed
-      in double quotes e.g. \"command name\"\n\nCommands:\n1. append_to_file: Append
-      to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n2. delete_file:
-      Delete file, args: \"filename\": \"<filename>\"\n3. list_files: List Files in
-      Directory, args: \"directory\": \"<directory>\"\n4. read_file: Read file, args:
-      \"filename\": \"<filename>\"\n5. write_to_file: Write to file, args: \"filename\":
-      \"<filename>\", \"text\": \"<text>\"\n6. delete_agent: Delete GPT Agent, args:
-      \"key\": \"<key>\"\n7. get_hyperlinks: Get text summary, args: \"url\": \"<url>\"\n8.
-      get_text_summary: Get text summary, args: \"url\": \"<url>\", \"question\":
-      \"<question>\"\n9. list_agents: List GPT Agents, args: () -> str\n10. message_agent:
-      Message GPT Agent, args: \"key\": \"<key>\", \"message\": \"<message>\"\n11.
-      start_agent: Start GPT Agent, args: \"name\": \"<name>\", \"task\": \"<short_task_desc>\",
-      \"prompt\": \"<prompt>\"\n12. task_complete: Task Complete (Shutdown), args:
-      \"reason\": \"<reason>\"\n\nResources:\n1. Internet access for searches and
-      information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered
-      Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1.
-      Continuously review and analyze your actions to ensure you are performing to
-      the best of your abilities.\n2. Constructively self-criticize your big-picture
-      behavior constantly.\n3. Reflect on past decisions and strategies to refine
-      your approach.\n4. Every command has a cost, so be smart and efficient. Aim
-      to complete tasks in the least number of steps.\n5. Write all code to a file.\n\nYou
-      should only respond in JSON format as described below \nResponse Format: \n{\n    \"thoughts\":
-      {\n        \"text\": \"thought\",\n        \"reasoning\": \"reasoning\",\n        \"plan\":
-      \"- short bulleted\\n- list that conveys\\n- long-term plan\",\n        \"criticism\":
-      \"constructive self-criticism\",\n        \"speak\": \"thoughts summary to say
-      to user\"\n    },\n    \"command\": {\n        \"name\": \"command name\",\n        \"args\":
-      {\n            \"arg name\": \"value\"\n        }\n    }\n} \nEnsure the response
-      can be parsed by Python json.loads"}, {"role": "system", "content": "The current
-      time and date is Tue Jan  1 00:00:00 2000"}, {"role": "system", "content": "This
-      reminds you of these events from your past: \nI was reminded of my creation
-      and that nothing new has happened. I received a command to read a file called
-      \"instructions_1.txt\". I received a command to read a file called \"instructions_2.txt\"
-      using the read_file command. The current phrase is ''The purple elephant danced
-      on a rainbow while eating a taco.''"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"},
-      {"role": "assistant", "content": "{\n    \"thoughts\": {\n        \"text\":
-      \"The instructions_2.txt file contains a list of files in the directory. I should
-      use the list_files command to list the files in the directory.\",\n        \"reasoning\":
-      \"The instructions_2.txt file contains a list of files in the directory. I need
-      to list the files in the directory to determine the next steps.\",\n        \"plan\":
-      \"- Use the list_files command to list the files in the directory\\n- Analyze
-      the list of files to determine the next steps\",\n        \"criticism\": \"I
-      need to ensure that I understand the list of files completely before proceeding
-      with any tasks.\",\n        \"speak\": \"I will use the list_files command to
-      list the files in the directory.\"\n    },\n    \"command\": {\n        \"name\":
-      \"list_files\",\n        \"args\": {\n            \"directory\": \".\"\n        }\n    }\n}"},
-      {"role": "system", "content": "Command list_files returned: [''file_logger.txt'',
-      ''instructions_2.txt'', ''instructions_1.txt'', ''auto-gpt.json'']"}, {"role":
-      "user", "content": "Determine which next command to use, and respond using the
-      format specified above:"}, {"role": "assistant", "content": "{\n    \"thoughts\":
-      {\n        \"text\": \"The list of files in the directory includes a file called
-      ''file_logger.txt''. I should read the contents of this file using the read_file
-      command to determine if there is any important information.\",\n        \"reasoning\":
-      \"The list of files in the directory includes a file called ''file_logger.txt''.
-      I should read the contents of this file using the read_file command to determine
-      if there is any important information.\",\n        \"plan\": \"- Use the read_file
-      command to read the contents of the ''file_logger.txt'' file\\n- Analyze the
-      contents of the file to determine if there is any important information\",\n        \"criticism\":
-      \"I need to ensure that I am not wasting time reading irrelevant information.\",\n        \"speak\":
-      \"I will use the read_file command to read the contents of the ''file_logger.txt''
-      file.\"\n    },\n    \"command\": {\n        \"name\": \"read_file\",\n        \"args\":
-      {\n            \"filename\": \"file_logger.txt\"\n        }\n    }\n}"}, {"role":
-      "system", "content": "Command read_file returned: write: /private/var/folders/lx/cvc0bpt93vx2mcwxxl2xdzc00000gn/T/pytest-of-merwanehamadi/pytest-177/test_memory_challenge_c0/home/users/monty/auto_gpt_workspace/instructions_1.txt
-      #fc64cfdd6fe9b583550c67133b7d9555\nwrite: /private/var/folders/lx/cvc0bpt93vx2mcwxxl2xdzc00000gn/T/pytest-of-merwanehamadi/pytest-177/test_memory_challenge_c0/home/users/monty/auto_gpt_workspace/instructions_2.txt
-      #2b530a674d388da03a41627bd4d10824\n"}, {"role": "user", "content": "Determine
-      which next command to use, and respond using the format specified above:"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6528'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA9xTS2/TQBC+8ytGc8nFiZK6SYovSBVSCUJVJVIOYBRt1hN7yHrX9Y7bRJH/e+VH
-        SBsOIMSJw15m5nvNag7ICUaoMyU6L8xwfnP/9uvy6uHuevk4vl0kn295J+H0+stH/vSAAbr1D9LS
-        I0ba5YUhYWcxQF2SEkowmsyuLiezcDoJA8xdQgYjTAsZhqPpUKpy7YbjcDzBACuvUsLogEXp8kJW
-        4rZkPUaTy9k8wBP5z8bFNAxQnChzmp1fjOsAdeZYk8fo2wFz8kfi0hnCCJX37EVZaWw6K2SbCIfY
-        AgDEKJmr0kx8jBH0xb5BO2mKMS4zgh7pwW1AMoLBhg2tjEtTKkeykwE0BWCbsFZCIJmSZrAkYA8K
-        bu6WoFKyAk8sWUuxpT0M2tpqMhjBAnzmKpNAHwEka5AtRhwkJFTmbAl40xOr5tk9iPJb3ykuQCsL
-        CRlKWxcOWEYxBi+DlaS8s2zT/zJdYZTtgg3h3lPrpddcdXLa5bmySQM/maHfZohjO4T3f+mzYWuJ
-        ztzqkoU1+7yzvABL1Doj66uSjnQqP7KxTV8qNeKNXbYniYEHrQq1ZsPC5M8X5AtS26PcExsD1b9c
-        0yjGTq0OjifWM/1yYVbl1Bl5pXzmV5Xp+XF2jS3tO3Qv/QrXjfS83dgHMsYFkDjYuwoy9fgH/7Z3
-        1btjoDZUny22NdYBbtiyz1bdRWGEXlyBAbJNaIfRuP5ev3kGAAD//wMAelGZnmUFAAA=
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 7c7c50e45c442566-SJC
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 15 May 2023 15:12:14 GMT
-      Server:
-      - cloudflare
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      openai-model:
-      - gpt-3.5-turbo-0301
-      openai-organization:
-      - user-adtx4fhfg1qsiyzdoaxciooj
-      openai-processing-ms:
-      - '21873'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '3500'
-      x-ratelimit-limit-tokens:
-      - '90000'
-      x-ratelimit-remaining-requests:
-      - '3499'
-      x-ratelimit-remaining-tokens:
-      - '86437'
-      x-ratelimit-reset-requests:
-      - 17ms
-      x-ratelimit-reset-tokens:
-      - 2.374s
-      x-request-id:
-      - 350c85281465e8568485def8af626227
-    status:
-      code: 200
-      message: OK
-version: 1
diff --git a/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml b/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml
deleted file mode 100644
index b79a6486..00000000
--- a/tests/integration/memory/cassettes/test_json_file_memory/test_json_memory_get_relevant.yaml
+++ /dev/null
@@ -1,2672 +0,0 @@
-interactions:
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Sample text\"\"\"\n\n\nCONCISE
-      SUMMARY: The text is best summarized as"}], "temperature": 0, "max_tokens":
-      0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '252'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOQUvDQBQG7/4K+c6bkBCT1j1XRYSA9SRWymbz2qwm+5bsK5SG/HcJqL0OzDAT
-        XAsN2xmxQ+iT1cu935ptWUfTvj4cno3d1E+Pl0uV1+8NFLj5Iiu/Rmp5CD2JYw8FO5IRaqHzal1m
-        xbpcFQoDt9RD4xgkKdIykdPYcJIVWQ6FUzRHgp4QRh6C7IW/yUfoolK4pv/xnYKwmP4KslnBduws
-        ReiPCQPFv+TIPUHDxOiiGC/LIHshv8zv8GaW/K3QWdIdMCscnHex249kIntoROEABedbOkNn8+d8
-        8wMAAP//AwADaRSQLQEAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4adcfe613ec-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:14 GMT
-      Function-Execution-Id:
-      - yvvl5lovloye
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '754'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 592e9151aebda45ed59a9ad565a24324;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89466'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 356ms
-      X-Request-Id:
-      - 7e69598f8d9d0bc01b752e4a0b05fa0d
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Sample text"], "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '90'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWQ+zvJal78+v+PTd0kcBkuDNuWMKYbQZMkCr1QoZSEhIwmADLtV/b5H3qLrq
-        JlIIUjDeXnutx/6Pf/z119+forqe+7//9dffr0fX//2/5muXU3/6+19//e9//PXXX3/9x+/zf9x5
-        rYvr5fJ4l7/bfz8+3pfr+Pe//hL/68r/v+lff/3tJ8svlV+lXVErX4hr86DtGZaqBPGXTM4QWJct
-        s1/uuu0vFk4A2lFgeIV35sSNKVDv9kVllpCZ/rjpGwtlO8ci2rmTUy7XSbCWZeIRLCirli3MM0b7
-        PfhML9vU77yaOzCpzgOPsfou+GDZA7CrHDJHua5Qv45FCvbHrQjWvhQNGcoSWCcSZ3jbaQUv3CiA
-        nTFe2MY28nYSat1Rq3y5/z1v1V9uJwv2z/uR+A/liKZFfTJgWXzvzC49K+2bLCnR/uaHVPLMizko
-        1k2D91o6kHBEpj/4MRzQN9QsFiz2qfldv60TbBdhRnDKGj7hNw1QGdoRC4TjvXjbffNAephwWo63
-        O2KW8T1Bp9Vbps/j+zLxLkIpFwyrq0+bcjtLRNh+l4QuHgVBg2IdNbQdPiExNL9GU+fbDvgfMmF5
-        v2mrfpOdMliJQc7O7+jedjsqRLC5BDXxZU30W0r3ETwPxCZ69Pm0HEumAg4qETFu6ZeP2w/p0Jb5
-        HgnM7FJMW+mVwcUtMZVraZPKlmQ2QKiyYyGL7uh9ML5n1O2FiDl+sm2ZXi4aUGrjToLypVV8k+kC
-        rPKrTSwhq0xO3a8HmZiURGtzoWC26XtwYmmDl9Y3TCczp6BM0/XK7O+98Tm86xoJzD/QdUDkdJqM
-        +05tfK5QNSlIym3TdGBzVFpmfV/LdmijlQDv3WlBlRgZqZzXrgam1gQk1E3bHA99noAYFicSViL4
-        v/cJJ9mTWfgJo2Jw0AhQeKZK9PU2bsdHua8BkpISMrpFxadbdUZrt34wa9Hf+RD2uQHvsrZJeBKr
-        ontklQMPMROwhIuw7epbvoKitwmWniGupoUkX8Gj8oa5JH6mPMjfAXSLmBJn88oKjozvE4510ROi
-        q006LNDkge2YWyyH1scfev9aQxIt9uS33kbZP4iQtG3OsJe9zPHzvgSQFG+faKfs4Y9Ln1F4G0hl
-        ni271XCBdPjNH9nGpoWGY/QxYL3Ybim9jSPqdHcMYBBvhCrlF5tjCr4F/uXek2BCRTudwTwspLI5
-        Mkf0LN7ujayGaPgQsg+okE6b18oC/dH7WNF8p+XoOEZIWq/fzF4k25Rn6tZAEnN3bF4/5vS5VRgS
-        DW3pWrIZp/6xNODj7zKs7lyj4H5+2MFCo2/mj4uhGvlr0KBE4wqL55AWTe2uJ3CjRUpRsuxTniCl
-        Af74Osze7seKunXToftqU5CLKvQV9d/BFV3dbsVsnNt89G66A9LuFrGNZ6o+7dD3g3ymMUbW3s1k
-        phGVsPH7J3Hkyz4tlXxZK5cw35Pt+tGjLxUjAVarTUl86FaoaaLyAUXxDvFKkd10WYjaVfXzpsbi
-        C91NHpcXAX2X8ovoWNm3PImNEwxuQ/GiGnA1BMfhqpyn1iTGs2Gc5+pNAdDNjhijtU2HY1Qa6jq8
-        fVkgxldzUlEmgkA0hfjdlxY8rk82CC5d/PSM80wlBir9N2Z6v/HaUarz4bf+mKVvfF+k5cJBC3f9
-        xamcPfhwMz4iPK5QE/MWm3/qB9Urt6HiQf6kDbyGBB6LrUG2G6Ezh7GPPciH2iTaa9Okw0HyE5Dl
-        0CNG/EyrCW6ig3YfItKJ6vuKl17RAckfPtMeRtZ2bpzUcLxvJzouR+bzdbey4fRdMGaORlm9lVh1
-        FLl2gGz226ToQ8k/w2cQBeJt7g3/ip5qoVNEb8TcOFLapGJsw+KWTsza2LjtVuK9AdbnOXNr/Wj2
-        zB2falc2e7ZZJltzet9OB4U4uku0UPDa0RUzEaY6PjIHg+CPRHoFUL7FihF6kdHrV39BSc9su4i0
-        djnPjzLXE9EFySqGm1HK6lcuRiqt66Lg255nUK+bDqPFMUd8QYMr2pdNxBzhdi6mvefVoG9hRbQq
-        O/Fhri8Y3A/F68UkFr17XSWKL2ZrpkUNSf/0s9/8m9/3tRhqy7bhsjA45ZZntlNwXK3QWlI2f/oj
-        /xhRAxfxwMj2ZJz8YUVfJQhDk8/6Nlb9PB71TQyJzHprct1ngLwwkYjnBIHPOXI8pbftjvhV/ESf
-        MHMPkK/5huiPzCg+iRh9YGudVnRSzHPFhZ4/QUKHAk9DJ/PR6vMAsK4/iFvtk2LIpN5Ai3KQ2OmK
-        CpO+3I8CEvN3mH/i8zwfyQ7ebeSxTH+KiIe3agerBztioZGbaqRiJkD9GO94mPWtu7+FDiWHNMJC
-        aNop/emP1dsec5djhMZXjc7osTsMxOhNk4sXKAaFH1cSI9I9MMdHrcngRMOXmMv+XrEsO63gGxoW
-        0d/0WQ1uuTQg9M+UHCSkV/SE7jV4/dEkzuDe04GCIcC1/CRkW+UL/pHNLoNFkbXEm/RjwZS3JYIV
-        IYva/aOvaIuyCZIkc/E1MYqKD7dTjdbrMcBIMApz6GJdRGznuOTyDDo+vo0sUOpJYrQ/XQ5p/6tP
-        d3pUzLgIvjnRuPCgZYbMglF1EXevKwrV8/3BpRUt+WTXjqDglovE0erKpIs60eCbnDDdZYHHRyOG
-        BzpMJ4+ZC/Zph0eyXMHx4pxJaGQWf2WmMaDjdkjZtZa25jRl7mpdRZ+U+Y73SulwLD14beUnva0f
-        pJ3KPi6hUYuMeM1RQ3Qn3gHO66vGDDT4aPDk2xMZN63/07/6jbGWwdQ+AbkdslcxgjEZsLpOOkYX
-        ZFRUkPoaXVahTGb9b8tlHghInnYm5fp2nJ9fLIH2AWP2+rmrvoz2HSxs7UFcP9I4f5XLCTrx3dDh
-        pO9NvjB3gWpTKMk5vj3TT1Y7NbLat4PZxzXQrH8yLA72wELzIFd9Kt9klLOthlnaP/3+dnsAXJlP
-        8EKLCpN7pjRBOGUOcy+LyB+C904B/FZ6Zl0eoTk8rysHjGQtESu8GVXf9sj602+suX+1Dg0i2KhH
-        gz63I2ung5deQReTgoRaK1V90zcBDMl6gRfNmaec3XQKaVJzKsalbTJ0HBM4olEmluOW6ZRH4w5G
-        f3ciOnhVwfANMDI+qUA/p6zi48LsGng96iUje7Ou3o9aT8BgNiL4cr0X8/OvkNVbHjGWGSq6e5ZE
-        IDxvCdMf2ohm/26j90vRmf0q67azvEqGJsSUOQux8Idbn9vQR/KCLg/52x/jOm+Qv7BVLDquVvQX
-        KjzQz+9o1/xVjXavADKe2ZJ+6cn3uVS7Bwi+6IqF+81C7RJNE2A1kolNjlk72Shr4NA+BOJuqrhi
-        7OZ260V7XeNF59Upv4pNgH7+b3nQD+1w9FoFAu2p4eUiKtse9XGGdKNRmXPVZd7tclojXF/WzHTL
-        FxpyP/yg55s6GLT+nA5vz8OKLigxM8/1wxxM7ySguZ4x19zSbG8it5BzsJ+UdZ6ddvP40QJV21nv
-        17w81yiActttMVBl5XOl1wBkkg5zPznwaUV7gKA4JHQYHZGPeyPzYCM6GtvkjsSbU50rwI2yY5tn
-        SKshvTkCBFqtsS0+ar7M++YKxDFdul6592qo8/2EDMd/0DWJn8Xw8VIL4aN4I3qxC/0pBEmBaL2M
-        2TZqxYI965ODSjXomJks22qY+6WSfcuQ6Vmy8On8/0rX7nLmhk/J51mWrGDUPgdMh3CouGlkJdoX
-        kU2Sr1EW37u0y5AiW4zgIRxaNnnptCLr5o0XnK/9ocrAQGaOzrg/nBNES2NyQPO/e6K/zKodTrE7
-        KOQq2kRPUG4OeXnZof3QXSmXMwOxbc9PgFT7gFdm/PQHtXY6SA5xxEhuef5nHq/67DWTBLFzLLia
-        pQaYET0Rq4syNDQoOkBS76/MOXeZPy7rpgHL9kYKrj0Ug+EZFqQr05vra6ymnTt2UD+jirneOuVD
-        i74BwoeixXXQHVs69XGtBLV2JJoib1uq5wcb5vxCTCw7Ph/o0gB83wzM3z9oNY6iQkG2LUowoe9i
-        /OXFWW/oevfxioGbxkcNl1OMYee7Zn/sHw7s1JdKr9oXozHLkjOsJv5i5ub2KKZCJgG8rcNIAvda
-        IhaXe4BbcZ6I09usGub8h+b+xKKm6CoaZVUJBzmN8cvdtAUPPG9CoytlrNBcnUtV7Blo7tf4NcIT
-        TWq5MdDGeDx++mZOijgJIJS1T/Q63/CprXVbMYfpQx/562iOW7Oo0fpSLal4FBXzHtweKzXf7SjD
-        /uHAJ4PKH2VzwfVPP/0pvbkZOhvl+9/1p7sjVrWjfGbOfkHQeAC1g/l3on3tntPJ+B6Q9chsZvYL
-        ivo7ikpUrz8d0f3YaLmM7goIkrCjwrf8FK2fXw9gX5WE/ep/wNkJK+G7M1mhZFa7TND0UYiYXAkx
-        k6/J1ffijAZjOTJjtN7p1ERlqcYRvTCyFM/V8DSfB3RW91vK5jw++uK3A129Xej6tqOcrsQ8gFq9
-        c+bja15MgvSq4fk4hcwWcZKO77d1UE67d02n8tsVzHfHFWyKccJCMeCUd1krA38vTKJn387vl+Bj
-        1PfGBrNt2rU86x81GDejx0O661B/zamIgnwZzbyjLEa15x6Ux2E/55GMszvSbPQ9xHtGnC/x6fM6
-        1LDPlwleXk9exYNbcoW4yO54+XTv5hCZxQnqacloV4aRSX/+WBCrkpn31zGl2/JCgdNJY8a83qcQ
-        1H/7BS+N7v74fVMbXktVo4/FSIrlnPegOIQWs8Lbo2KzPkP2xAnx71D74ymD4MdLmP6mVvUnnz/l
-        eMesd1wVtJHODbIOeIHv/carBkOcDqBotTfnZyuV9fxqIbZdGHShRcgcN6pdgsEsRJXX+4bY8U3P
-        qL8dgYIYC2YvlZcPuudnnW38DKHxx1tM4rtUzL1zO+ZZtUOraXwRq14nfETJ5vlHj+O5voaupAlS
-        LS9gBB/vfAqNb6BcDBYz2z9I5iBfVxjNfoC+Vh+35ULWruB0ME7MEM5D1cZ1YsHxcLwxvdalor+j
-        7AHZVlApWvZmIW99bCBZoy9GIBzQcE/exto3eIHRO/mk3IxFAey8PjKiv3LE7f5RAlyC6Y/+TF25
-        l+GSbU7MnP00f8XFDp5krzBXuOzboSmDEqpc2hPjGD/QGIjTU3VytSV0CKN2PGXizMv4hZgNXMzv
-        slxmyly/xM2+PaKBkR2U8m7WeDGWTjXmZvoB/SqbOKYnt6CsRh3E6KHShynm7bBFd1ud64NpXztE
-        Eok+gTLzDYrm9UGdOpfR7MeJ9zUMn1vJRkbkwc94Zb3rivc0yMAwlm8KZNqh3/uGWHZEQo6H5ewv
-        4g8U0zUnPjocUs6R5qgXo4+Jx2ldTYZ4V+D8BoEZvnTxh7VnJIi+FREPVaZwBn0uQ1Q+debM/qiX
-        0P0K+lZY0eecd7kJfQAbdW8Q114NRfOmwgALf3fBw40+i2mXXx107HFDl/V5rIby/ZLhhiqNbI/H
-        FWI/nlNOjw/78bZhf2soKqNFRtdGeeOsEJ0zKlXcMbfqDd7bpkcheVyPzE5OXjqk4rdEsBW/xMXK
-        Mh2u0DWwdTtOdJLYJhdM/wDQxxpz4vei4J9YtdBeNnKqdi8N8Rr8J4r9Q8q8SV8WMz87QLNd8X/z
-        p17UHj8/SCELuopHUt+gfsoIM3qzQpPmloOK69sarybRSKeKBt6vv1PI723Komgs/+gfD+9uwT9G
-        1ijZM0hwKSxbk21AtiG62QLl5ftVTY33PIG0Rm8WhpvQ7G+SWaI5f/7pv+z4rq8w5w3i3Kjtj/ve
-        OUGXL490dMiunTJp94RgV+1ZMD/vzIsDNG4gJjOPQp+5f4BsvTvM5zz3aWvng4zd7st81XLTMfXf
-        T0TWnzeVVXiZbLq1V+RotMDLbdqg6STJux9fYtYL3X32krdXcBpzzXz9qrUDrXkCbOe5+Df+YStJ
-        MqxRoM2ZTStEjfY7hJcCwu9J/vpjFK1t1Drbyy8vFiPNQ0dZuOhL5UMRIrSPJQ11uxumuSkJLbu4
-        I6CZNzHfdZbm8FCPiQJb+Yvvx/RbcanWD3/4aOha35Zr/s1WZj3B9W1Kq2FKrvjHi6gQWy4fCcrO
-        MPtZ4soFbsel/+4A4o3C9OVIzEHsJwW+o/7ByjG2quWc31Fj1CuMikgvJqHcK+vZf7PNukYFLZBy
-        RspGSLFwOHUm38H5pCyPw4mFW/o2Z32MIJRjQvbwDc3uod4SNKKrTNFL/VY06LUnoDcNqXS9ZubE
-        4qcB8/oh2GqmYkrMrlMuFk6pgPWVyRxqRXAX8Y42tvxtuRiVAzD3apFAhoXfFHUzATXOF+Id1juT
-        kXJjAxOjFwvyu1+MeY80kMjWppJuPlPmuXcNvhoKZj1QfzyoRvfVtsDru6Ejvqu5rJ7Er0jC0neL
-        UZIEjL4XO2FOKASp/Oh5AqeNEBCtNsFsr54nQu3omBHSlW1XgKFAsLvvqTAtsblcxcUJHR+Pms38
-        sJiub6uENcIa0RdcnvvR/gMXLLp0fHZyW8eZeAKrXCQMO+0eTQWazhBG8opsF1FZDdf3DkD/bHd4
-        0U77aoivK2ulYjFiB9e02t/7g6OmHvAg+nXFmKmu4FCcB+bHnuAPsdlFSH1Gn9mvYC6d6av58UJM
-        PW1XjWsjisCxXg+m1/kLidfj6gHHOu/JthENc1nHHUbxs52IsfHOPuUqXoFVpyFerIIwZVjyFeV4
-        2N+Y0xS0mIbjx4O6v7yIczE3JlPgdUK6GBXM4dPOH+d+DN/p0TCyfrCq59L5vE6WcjnrQ+93e+uw
-        gqN8Q2xD19ycHj2P4JqPNsOEblO+rCsb/XiUdtDidiiTgweqAB0eNLIrJFs9nsBhe3HmRYb/4xtI
-        vu0FYiXXJafJdXiosta9qJhITzSIWYVhvdtJJN5UDHWpu05Avxx1pjVFUI03tj3BR3bWzD/XFeez
-        v/jxJkJURfPb4ZY8YTEdNuzHKwcq3ygyb+TItPF251MjnT/KzDfx0G/HYiTRBytdLh2Jqz+wz8hr
-        2P3J48FjFfvsm4QAy+R6Y1723pr9Ekysju3pw1xFNKof/0HNxHbMcdUPGjvqCz/ewHBioIr5+XUH
-        s9+hpejbVZvE3kkRqdDM/KszuzwaVmpziYBtBiK1Y6PiBhwXXbA883P2Pn4Oir0wKFZ10/b7GE1Y
-        neT9i4X17VLIFQ0c6G5+goX9pi84icoG7dHpQdfH1C8m0zMekIqeyYJwyzlr+kfz25/Bk+bbiIue
-        9AB73byYt6vNakzqRwlvJ1xhUd/45vg2ogDmPES8XV21XH0vzxDaHqc3ZYmLcQ07C/aMFCyc+T43
-        jh+sGOtRY945Opn8QqkNfH3esCBwDXPmuRg8ox7pauYVHBn3p/ocFvm8X/RIeWMoJzTXC7N69WPO
-        /fkKf/KLuWN8jCXZho5sLUamq5KOddwOaNtGJsHmjqD+Y3xtQO8uZLtGkQum12iCviYOFub8NgVG
-        tlMkWSuZqegSn/T8YKFQtQJmvZ6iyc7u3f75GzyGUKHBuvESplI90847T+24/WwpFI+TP68vnA6n
-        kgYQ39LPHz36eJB26CobBTFUGxc9elMHSjtOiXWvhmqwJBPDPUwUrI5P2eRr2JWQ9cWO+fHd99kT
-        KfSXN4nH+srvXjfdUNjEKzzNevlagh+g7+N6poMsWf4w91eQcu4TM0cal377UcJt4+AzSz7V93Nc
-        TbDfCz7zJcMo5v1XT0V1nLNIh6qazuWiBBGLmJFVEBajk4EDc34kxIqFduYtAMvQ3jNtXi9Mgf70
-        8xvzeM8+JaYnKLzgQDCQY9v99jPKcSti+bJNqulNhQlm/SY+ojYfFeProeGmLWm7OK5Rr/TOA5r+
-        6OEhN81i3o/D6ELhRZL5/f14ujr5lUWF++2JxmtOZaSGR0zlLmjToUeTBXM/JES+XdCf77M/IfbM
-        i5nZawNaUZmwoF6L7VD2dwGC7/rKDPum8NF4W/jn18kmd/Z8kMyiROhAfBLO8zOtbu4DHQ6OhJdZ
-        X8y82RPAIXFN73GtFNPUx09Qit2Z2V3QFvP+3gQfrXv8eGPL1vEzAfuZnJnVfdx05nkJyKqxpbxG
-        6+rnT6DGov9nv6P/JtdMKY/TntlzPxmy0rrC379TAf/5j7/++j+/Ewb153J9zQcD+uvY//O/jgr8
-        83Q5/VMU5X8y+c9JBNqdyuvf//r3IYS/v+2n/vb/t/88r+/u73/9Jf85bfB3/+lPr/92+R/zf/3n
-        P/4fAAAA//8DALL3VtrhIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4b5ab352afe-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:15 GMT
-      Function-Execution-Id:
-      - yvvlzvw7w00x
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '139'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - d5b6c4b4328aadd51fde99c9ed21a059
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 75e3150646d393829f5234099c9b5efd
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "\"Sample text.\"", "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '93'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1RWS9OqvJaen1/x1p7SVSIqWX4zBEQumiggYI9AEQERuSSBnD/f9e5T1V09yWDl
-        qdRKreey/v2vn58/bVbl9/HPPz9/3uUw/vmv39ojHdM///z8979+fn5+/v33/H/IvMnyx6P8FH/h
-        fy/LzyOf/vzzI/9v5f9A//z84bfbmR3pOBlUvQQRbG6KTBt824nRfR9bUC18YoZ2efQDwBeD9F7v
-        2O4TJRXXPqoGgdQo9BHfXhnPXRnUbXE1KcQpNwSffB9V9edKTupm9Li1Sxp044stfvPTsqKnGcnw
-        3CQlvipelk3rg1ijaLI+zOxCvxf1YSOj5rPfE09Z5Gjep34KeaCrzPpud2herJ94039hZMYV9YhX
-        6JFAM0UNXfLSFqJ/JSHk4zkljs9YJs4rK4cY3Jl57nZp1AuVWYhlC0Sr6ekJvt/aHMpn0GJx6Y5I
-        WJrdomgtSbi6ol6MDb7kW67LFolKEQeiTdYyvJTrlZHo4Bm8MlVNPVmdoB27XT0efpEE0NR7dsx6
-        YgjNOyfAd+UGUx5awXtx39fw6cMlVVy7REJZrVp0NOcjcfhlmQ2789pExbb1sSq60OupeSxU1a9W
-        7NBmKKN7la+3IX/keDE6ozEcwBuQQ5BPjmcl8fh0QhIcHI6I+3Z5MJV3sUapbmyIackNEnibhJAq
-        pUqXZ8kWivLWG2TeupBhun8FnTndQwDzfmImiUwxLI2Xv51W6ovsIv9ecep+ffC4oRKsVr0xiXm0
-        gL5bncRad+757sytbZL7Hdkv9KHiV1/VYKUGH7andYkml74wuKZn4G0kmMH9btK2w8K/MVKAHlD7
-        0B6heaCCwjaXPVGp+xw9NCtm+rs1jNXh2ZmAM+lJnI/ogymt1xJ8lnVEsvz9zeYULTnQsbix//Bv
-        3TwSOA6ZT+wBup5dlSQCBSec7GutE5yihYw0AZzh/aIK2KrRS9C2dkhw3W7F91FK8iaMK5dKBysW
-        bIikAd5H3yV2VWUGXe6/rnr/uAaF670L5v1wKOBW1THJHovY46X/TFBc+xnRMhcqfvdmHWDYB3Td
-        3Jue16mkQttyl1z367mfuvPHhNpiJ6ZtfVmMH/97hOFhv/Bqdy7F4L/uOYASyiy8Ka0Yv8dnhI5X
-        xcaTu7+g6ZvZFKZCc8mheLKeYdoAhNYDU5X6WsXz8FbAKi3XZH+WbDTESoUXND2EjJxULROVesrh
-        6AYpsaLrWImrcg5hWCU63o7THU2Bl94hcHYbZiDKq+F0LX10dvGTaSikaBzyLAVdnAc6+5eTmIOc
-        lGiIIgurpxXLZug/APubM9PyFdfG9BnVNfrVL8Gb7Vq063NSAq/aidnyWglm8Whd2GclYt5Wjgxa
-        W9Mavl07kdDCYc92bhCB3Z6PzGy+bzH55T1BdiMt2G6pHTyRB7saCjmnTGdl2I+aaQxAA39D7Ijn
-        xnTRVUCKOjuExHhRscxKQ0QdIyGGWd4rUbVJuAmWN5/Y+udQLVdG7QJC5/ZXX+eAa+UbA3M3C+K0
-        ZteLU+hH0IbGmor06Ip5WcwKemXGmrg7cw6mW/HFcOPbLTm5jRmIse51wKZpszge/Gza6B8TlrJz
-        xjO+6sbw+VAXpR/lQExexRWXr1EK0fdIWJg4pUethd2CLa0iZqozZFyp3AH96gfLzKvEfDcfEXrG
-        545Yb+vc81LrzptYW0bMmQMSiJbcfST6LyNEm7khVsWWwiVY5Jgl+8mYnS0ukZE3NpY15WVwqfBz
-        6IYqwfCQ7ECIW3DebnbSg3nXx82YGOESNHx3Y6QMl0iwUS+hkpQl21092xhD0mGkw/1MtPdCIBrL
-        QYjk0/Qhmu6Ggnd5UqJ69VoTrfZP3ldRSYEEjD072uqQTdG6wHBGO5dpMeaiw3FpbxdruWbW7jJV
-        k7p0OuQ5g0ae2nz2pmuwAXhamDJ3sZLQpEmKgnT9viOnVxB488weZxSryzczg0+FeL/dgCrqZUgO
-        VqtkfWAsZ3DiqWP6w9p7cyvcGn71RiWn497MuR+p5iYzmPdNi36QijSHm19mxJzPUjArzloFGtYW
-        OWgd75ljZJFqt/6ROI/aqiYRBylqFY8z65VViEetpIITi47WW7CQKJfbAZVF/KYwaV32+94aycSS
-        iVUsp15Ek1Ggjq5fxA2HphqlV5qAnK8q4r6eRsV3jQzAne5FXOpr/dRXLUZSGgdYmTZjTz32dVHS
-        Fh6J7mSRjat8KYOam/Xf/1Qzb5YzOoT6nRzYe18psZyFoKv7A7FXhd7L1sxcNCbHkV3Vu5oNrN6q
-        sCikE/GOKPO64mLW8Nv/r78a2WzrQQKPr9aR06NtgknEWQqZAIIvXVEZ37ReA6i7J8Kfu6yLOXnc
-        EvjcW52l7rHsJ+RZNTxPO4c4XWxUCoZzAndPaZiLH7tqfu9GU5Vt/4bF5Xqr5nDSOnUsc4wnDJUx
-        ETVL1Za3JQl/83DwX2GO8tc4EhvdcSDiZeDD/j3fyWnevjLhGEEIQtLW5LTCWiA6KHU0HtyJ7ecC
-        V1wrRwyh9cT0r7/PZfj00SOfHIzMBcsGEGaHnsbqTay0GappPNzuqJePmLj48er7U5iGYJ7vnB2S
-        qhKiyF4WGNekZp7dgUfNyO0gWPGMHb/KU/CF+rEgDW86wYo/eFQrHiHqNq5OVW/zDbicVhglJ0yZ
-        +cuf1e1mFsDta4h58SmCkYfaoF4olthvP/0wgKxCp/ANfh9HR/BirQ/QtaaFu2JzCZj3Wg1w13ud
-        kOYdovnulC5aGtGbOc/LKeOZdOrUtVnZ9BoBrYbjYSuhiVIgDhZVP9fWpMLv/oFRZPQZdazehV++
-        47WtHPvZ2ggFTZNl0dlc59WUVWiN9jdvxsoYZMHsEbeFDb8tyNGUimpqvr0LkfJesqMpadUsxFvb
-        HrRP/Mv3qqIfOst//QY3Y4Ay+jsPMJq8oFMupxV3FlEKNN2H7DAMaTalEWk2973uUdFuT4L73UYH
-        f7XYUlh4KmK3YDGsvEuT/M2PitsON5EjpyEW7LUX43K5mNX7xzZY0vZexWOlP8IZGS7uVs0CiYvW
-        W9A88Ui8MToGU62NNuRLd8awqvVgGXKNwlk+MrbTHcsb6HuW/rO/YvaQxbzd3M8o0ElOdsp4EsOX
-        nzqETctmu1xWqzlmVgnpseyoEMe5Gg9WcYZHLFFcT46D5tG+JH/zH7dxX1Vj/TJaEBnS2KmQnmgO
-        Bq7C+/blVN7srz2PR6uDXIoipvnbCYljc8iRpnFgh/Nuj2T5GiXw67f45X8IYkkoz8Cs+0hOapAK
-        kWwqDTjxGFV0Kck6vZUVeO1/+1t0kA1ZiSSUS2FEiBNSb3q7Owovxl3i5W8nozeYZRifO5u466Mf
-        CHXecLQo4MSO2zz0RtqoKvhauMKzw5hgTilz9W8+WI4gFfemSQfr0xuUbz62J8O4kqHwIwVPnNmG
-        WL9PObo8C4/hz+trMP/7tWC8rmrKB9nz5rB8+ujqDhIWp4Vm1GERJ7D2rhWd5FRG1OLPs9qopUu/
-        WaP18gsf2g3ajz3bVftbNW0DasLlk1TM2cMccIhVCTbkHbAjWFpPJyIUEI39Yq5v42DKvjaFGmHM
-        dmyt9BN57igMYhzYvtFrMYe9UGCeYWR7zCo0HVf2AO9uHPBD0RGi/wMAAP//TJpPz4LI0sX38ykm
-        szUTFYQu7g4Bkf+toojJmzeiPAiICNjddCf3u9/gM7m5S1wgi6o6v3OqHrttCa84zyn210c08lsb
-        fN9H5Ouuq4R3p4B8BedRP38A+iytdwSy0T6onSobJLOXRpCW3oaoDs1eCB0agNHMCuw6uO/bWXG9
-        IedGcxzc3yef16VZI0GTDfbrBcnGuisiOKefD53mcd/jlV+gu2o3GK9wlXHm1xbiV/0y1fMRddHh
-        foR9cnxRY9Z2SFDnuFNxa7+wG65yny0vjQP3+XNBjYXFEa9tZQXlWjU/sb7X+mGqP5Tz8Y1tv5Ay
-        xt6bDtb+cku9Rpb9X/19uBqQlaUWiCC2YN9+xjh8fkyedDOmzuDHJ8vz/iFEsPNqJO9Px2hEceG3
-        KxsBWt7rDd0y7RKT88XtUHUjGo62g+ePg+kSmPwqkR5ZJdj4uV9htncpNiR7QGzkXQSHa3MmUAHx
-        abBgCy32MyOa1e1dEOWQpmiQrGW0MtbLf+od+3eNbrIw7MVpX1ra9L3T9+gmkTKiI+7M7kSl81c8
-        ts62QeWYPaiJz3HV3d9mDXqm3/DW5Tpa9rNRhefRKWl+P9SxyG4/EZqVuI/qMrUFTfP9EbQVzujk
-        rwWX34cEiqy8Yt+63E1GO4NAHHKfvD6HoCLLc3KAa8J8arFKrvr75r4Dn2gaXfPRMId8sTK+8ykq
-        pv4ZDrdtC5GnVtR4GEwIYgUlqOs7ok67uWQTfy2gvYe3aHYbDv7zohsEpG1zouvM/SDhtm6NIDjW
-        eC0ba7PP43UDV/Nsk9G+bvxR8KcN3V160lBqI3+apx4K7VbQ49xEGZv0DF28zsSu4jQV7+vCgSqu
-        LpO/XcfSfKu3mh2cGmqdnq4QP+d9Ag/NZ9Hs9XB9EdJBR9m2lmhIbOZ/7kOWwnWlmmThBNeeVYVP
-        QH6HPd2e5n7Fbi+TQJ9f5uSZqouKOk7hKB81eZKcJ0XM9z9WA+YtmuNAxOY//Lo8mOnX76ARKftU
-        bZvLGq8ZdXzm/iwA3ls8UKtMG0GoJhNI29LHgcmRIFe05PDuupHqC5agjhnbEsxbMMdBibcZ2Qzb
-        ElXUtolGRSL4LF1yoCP3yGryU8PQMP3L83Sj48J/B85ShdvcuNKQDEY26mGx08Ko8khTFLNMbH9K
-        W1trlBB1o8985rfHHH79+MLigsg/SwYgJYtIyUH134+0duCW2Fvi+O6m79LUaoCrS4t621ie/Jui
-        wiaQnKhlLznmu8LtoImckZq5k1TsvF8A2OSeU2cS7lGfzRYgFeWbevHy5HOlPe3AL7sjxbeE+Z9q
-        XUbotd6eiLRyeC/2KAnQg3KPIJ2wjN2GXQGCpQZ2eUxj0r4bHRg/11Sn29oXab5PYONsJDLfpEbM
-        9mthQCdxhYazWhFs7u5KcFu5idCZHXwenTsHVvIANHzW3H/HTe1As3LXNFSCJhs3l0MOqY8ekXya
-        97344b2BDHW7pf7mue4Xi/k+h/d6yAniZC7EzSttMIx8TYPGFz632fmA7OS1jZTYMvppHs/URi08
-        +lMeT4K/4oejTfVNA7R8ZLx6pSnkXLyjV8nbfuIzR9vqzzNuw63fU932a3D7gOJk4qHP04IVfHne
-        PnQ6Ek/jqaOpv6Px+FwKaquCwTp7SVE/8TuZaYMOV6lQySJivBev48PWXEUpqZHnaS/Hrlcj1Xv/
-        UMvfPBHZLl4GtHZ3wNvwHlYfxaA2FBd/j03ZyWOqAwGEZ++RzI7MzkiiFA60imRjy+EDEiv9HCBi
-        BBpeD7lrMptTB4YYNGzVySAEktflNz+ggWUif5BmtxRWVKrx+vhcovfeUGcArpZRA/S8YlOegF51
-        cY1WF7WtxuES1YAuDov441z7HTr1FhzD+B0p9n7TcxK8HVA1OSaKVJOY7c+yCtTOP9hyArUf9vdg
-        AJpp6Ndvi9mPV8IyKF3qDEkas4NtMPQTmv88j7I5eLA72DL1n+6j+uoPujPFIGq3XlfLEKU5TPMo
-        Uo+DXX22mtmh8flIqfGuI7T42JcC7cyrRTeyXaCJhzhaF0d38tPt5F9PO2XibxoUpV7Je72ykElb
-        izrxZh/z03J3ReeF6ZHl561lIuv1WsOPXYD9xOxjNkuWKopvt1mk+bMzokq8O4IYACJ20EZBrbDR
-        0ZQ/0bXX1+brvPsYSFpddBpGshnTPUoi+OjH5Je/xq9fL7owpJvt85KJic/Q6m24Eal2ns9XkdOB
-        hXhAkPzc+/wiN/qv/q1f0Ak+6RlatGsHu+YsyNgMDR4yrseU+sXKqMbdMqqR8xmvXx4VfNJHkMts
-        R5yqQj7N7EMCFXNMjPfS4HP7FNZoypupVwVeNv6cLjlsOkyo06U8bgVyCaoZ/errdspnHhEosX6h
-        6eRvl0GNa5XSi07NfTcglpxdrlCWa1M+8fFZ9UxLdd7cM7r9HIIeTfyEdKePo+XcCHrWhPsCTfOL
-        ANnOBGuqPEVPcjUiJWuKSvBlp4O0rU/ULyUnY4wcbuj3ebnq4uHa6lw7x8EP3RBMqwFE0KLlsFtN
-        el8g5mTPAJzCqaPlY3wKoUR+Ce7VE9HKdzfVotTLA6R2GhMZ3mvRRbC7QtjynmL3/cjEtWESKJ3K
-        8JbMRcw7vinRLbG21Co2H8FXkd7Cyl7tcaY7ucmu5rVE6jCe8aai/be/Cui8S0GD082LySKOSnQi
-        non1+TNES9DeDgi3ksmda+uYvZfXG3oOukIjM/N9vnazq1o9VyWOWgUQjU2NwyIUr0ib+DZfbh4e
-        fOeN3Xdtzy+PtwNffTcinYjucJEZHJXeoHjKw8krfntqsrXOhHW7gyD2XO80V0HlNP9xxs+XdQcz
-        d3+mRniFiqvSuoGZ2L+wf2YH85P7sPq+n0Y3ey6o264b1NimG6mB51SyYhFQMzt+U9feP/th6k8Q
-        16fAruzpPeercYEW6BbS33x1yl/Q9XM60e1tUSIxbNwaHmyxxXc5KmL+fNgFoC4ayHi5bc2xTdgM
-        +jyb08hYpoJ2Z8S+z9Fnt3zHPCsGC5xzsPvdh8iTP/3Ns2y/SGK5kDgHXcwYWT2kRczVpHDA9a4W
-        DVnXZtKgPg3o18Y1WnCJVWN6299Q1mYPPPVXzz6PPvjyAEHm2o2nvPmGJHkriCR5Qz9+7knyzSPw
-        OgLT52caFeh+vwNd79S3P07+U+OYr6jhuveKHUVaAJi+TsPYMWL2PiKAu0zv1F43tWByuWkB5HZN
-        VLn5QW313JVwxC3Hm8ft0IsQhyUq9Uaa8mdAbHReHtD8bEWL5v1Eo22kBYoqSca25AX9N7/XCq07
-        RAqPaSZ022xgDKf6TUw/e++qSw6j9Dx+56lgQ7MyoD2TiDBlvRRs2r/Ay29sjNNrnYnsMRhIZIpO
-        VnJR9rwrdld4eqBRw79Jlbhv7gc0f7EWW3a06MfX4RHA9XM+RcO0j5nypB2wR9xi3EkCPVdbtIJH
-        TiLqT/uK5vXMD7C5ryxqxu2hotr8YXx5kU55Ui+KTxKpyu69o3ax3PettVJ0CD7kh6B9cPXFO671
-        Xz+bjS8/5p+qsjSNk5Dqyqv1x5/TPteupC2xXTlexXdXkNBsGG5EJnORMTVlhvaxxpagTxJki2xb
-        /vI91ttohRiLdQ4YOzG2t7XXj+Y2T9F6FRT03JFjzKfvV71TNMe2mvXVsMxVUHNHXL76GN/qd7tD
-        vlr2EU+Lg/jyEwo3pwabN1b53Eq8FqY8gFrylvZ8ttjeIDj4/NcfCyd/GnBz73ca6Gk08XTQwLmc
-        R9Hy0OO+u96OCTyd5yJKEzbzifuABUx5XnT1FTcmQnwMIIADiuOVbY6qLUkgqcylbg6qyT1PVQGa
-        ZkNdxbEraXu5J2i29yk2DvsPIiKSOJwCw6ebRX7sx07tPJj8G7Zu14fP3mzTQvbzExI07ScWCc9y
-        ZK7nP5ES5busPdUvD8n+YvObl3Kv36eamdcOdd3X3BcXTeXwuh4UwpaJa47vMazhzR8uTg5dIcZS
-        O1yRyYY1tmVZxAPOXQbmLJGxoZ598c0zkZR2exwWs7n4rbdd5QmqJ8q9J88mS0BW96/Jv3YmSdOg
-        QYHFgkhJrjeTNrtLglQ7CKkXyjgWrpkd1Sn/n3gsEPLS2B/hy2uqTn/8blsqKvhsrVK9eOnZ56AR
-        GxaX44lm5U4yJ95xIL5ulhRrq5OgR+7UEFvNC7teafWL14s4Xz7+8jUiUz1+8xk88Ur2WaKgQaVe
-        Szi7HXbxB1Kuop0X/ETKS/gxKY/nA1B207AXyjT+PJ9Zqr4P/Bopl3jbc/cBklLj1Yjdxra++44D
-        OCsd4Z9J7zg6VZamZp+MLJ1bh75+Gy2SeUBWY/iuRnSsHNCV++zLqxl7Lw83yB/0gwPr/YnPp31n
-        QeyaCvXR7o6EDmSGmtd2M/XnWLFXcMsR3gDF20wb4+8+DkXVQsYXrjwqlv68dyhY1nL0ySxiimT0
-        S+gC9o6ENkh93x8IQD//Qb/7T7aJQwKXfRhFiWgW8VDEx/yXJ7/8ScZFaUNraEAWJkIxL5aqBFPe
-        TQ2z8BBXh6eBViEZJn9XZtyU3h789b0K+Pcff/75f98Lg6a958/pMOCTj5+//3sq8Pf1fv17sZD+
-        ptLvJQIZrkX+17/+OUL46923zfvz/5+2zl/DX//6c/V7bfDXp/1cn//z8x/Tf/37j/8AAAD//wMA
-        TTrY2+EgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4b93e5e0160-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:15 GMT
-      Function-Execution-Id:
-      - yvvlxf18lrrw
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '253'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 42e4c032166aa68717aa47d33fce4daf
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 5a8fe0a9400421c82190dc74100ae5fd
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Grocery list:
-      - Pancake mix\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '268'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOS0vDQBRG9/6K8K0nJTWmj9npoigFQcFHESnTyW06bTJ3mLmFash/l4LW7YFz
-        OD1cDQ27M2K70ObT5dy/rBarfbk42KfXt+3t7Pnx4X2/nN6t7qHAmz1Z+TVGlrvQkjj2ULCRjFAN
-        PZ7MqqKcVdOJQsc1tdBoguTlqMrlGDecF2UxhsIxmYage4TIXZC18IF8gr65VvhPX/BcQVhMewHV
-        eFCwO3aWEvRHj47SXzJyS9AwKbkkxst5kL2QP8+brIlsKX5lrUuSOaHOfTvfZMF4aw6Ude40wqCw
-        dd6l3TqSSeyhkYQDFJyv6QRdDJ/D1Q8AAAD//wMAfbMoYEIBAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4bd1bf3635c-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:17 GMT
-      Function-Execution-Id:
-      - yvvl315jleb0
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1386'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 85053cfc2933d3f356880e73b7fd2d45
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89462'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 358ms
-      X-Request-Id:
-      - 5239e4222b7f6d5c65187a9e6e046965
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Grocery list: - Pancake mix"], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '106'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6W8+6vLbv/fwUb95b9owISMu8Q84CtgiouLOzA4oKKOcW6Mr67jv4n1l7rZsn
-        kTZ9mnaM8TuM/sc//vrr7yYr8/v497/++vtTDOPf/2v99kjH9O9//fW///HXX3/99R+/v/9jZv7N
-        8sejqF+/6b/Bon7k89//+ov/ry//f9K//vp7Mxwj7BeBFvXvXODhNbdqAtXQz+Zp0gwoGEQiSrfc
-        +oWAhwxiA6YUBWVdLtv75Cheafj0dBeMcoH5O5WnxuowMgGIpnMAfJC9aIDE8LJky+N5lmEd2AbZ
-        sISyoWDPCxg9aaLeAY+MbOytCxOuANRE5JlNTaI3kHqvEif28vHYq5AQzI59iZTSjvvB8e4auAAN
-        EFrwis44LZxgT8Sc+sqt0iv9iiT4kMwHVtvc0xtXeltQ/Bx8bC/JHgxizcs76UpHam82x2x06TGG
-        V0kiGJcy84YBdzzoqu2O2n3/0sn9tJtg5W51wrNxyoYvvGvgqt1VfFw+czS/X4GgyEu3IFmv1YhV
-        u5MGd617pfZhdL3Zsm0NnrzrHj39+6Wc1v0B50RuWFUWKRvfdNfAySwOaPleNvo4ON4CW7lQEN+q
-        hM1xumugHuCG7LQxALxb65Uik6XCuhkm/dilQgchoSM+OHectahpEXyeXYomtzMiIXHnCeocAER+
-        FLdsWpY0gcM516h9eu3Ztg7fIfRP0Zli6eDpNOU8Ce73pkr9Z3YE83H3TKHucAkRw9z0RmEGF0iO
-        3YQi7bWPmvU+YXe+Gr/9lOt5LTBuVIs6QSQDcn+HFWw5+UzxzkZZ99pNlvJm3B4tm1LWZ/4zVLB5
-        cAKpPwOMOpi/E/gxhJb6ybvySPm2XbCIx5DMY2iU22bvTVByfAlt548eDYUBZbnm2BWrqYqy5X1R
-        DGAGly9p6PUL2DyGAzhdmgjf3c0RTLQ9E7j9lDdqe21Qska9GfBRkYxAH/AlVZZZhnhX70lXPdVy
-        hqbrQNbOjNTJUS9nUoJYRtC/YRMJi04eRCBgX7kDdjR+zyp5XwtwYUKAff4lRDM+2xpAm0+G3Udx
-        i6an71xgEMsR2lKy6PRiVRPwuGODDfGj9NPVG+7w8brq2OiNRl/W/AAAdleq7fONN4gWV4EntBqK
-        3krH6IxOFvz00RX7B72OSPFRC8XiexttB77JhteVTvLevCfUrW9d1NGmV2FYqYCAtJ09irdhtyFg
-        u6OumcVRTzXtosDIttBiPzS2FZikyoLMB9j87Kd+KNj1ArupuVCblmO0PNR7AEhVdVhzoqhcWpPl
-        0Oeve6xl8+QtvGK78jk174RoOvHYOdECeEqLFwFMGPShY8yHSXnssHfUPiUbRMmHbzBkiJ/Yt1xi
-        fbeAS+BvcWhk34x6+cyD78XO8eG57PQl6O8IWjlKsC4OpJzm7XCHke6n9JylBpje1lxBnZ1itDkW
-        fs8s56QBdcsI9qxzySal73iIIyeiUXWp2FiH7wBCZecjeTuf9MW7SAYEe/6E/XMF2UCyuZL756VF
-        RNORPg8CQXKaVUdsedurx78kYskacU403kdpNibvuYP5hc1EOci3cl7zTTlL80T4WxF6SygWHASP
-        XMLqTfN04fPYGlDouxkfZrv2mtP1GsN7hlSq5/U3mvlPVcFwCF50T4IakMvzHSvhweeJ/DnPHj32
-        zheKYzqjJbD6bNC6twGD4VDgg/tySnp22hzuG21HdkV97JcrJCG8cMDB2i8fU6Kmym2abOqC8Vou
-        Mz9P0J2uAvZvzzqio34l8IpuCtp8ZiPij2/IwzVeqFbkJzY/y0IGrx2XUXuz77w2WEAgv5OOUm1S
-        G28wjFgDW8g9SM8Pd7A83e8FTKbKYRRnMZvVmPuC6+zEhEqHXl9aW3IhlNUN/d0v+YwPGerJ44gm
-        fYvBzBquAc+4rdC8Y7KeZNUBQgtKA9b0IskW+8gShaUhR+2X0APWcvEF1kZ+R6LXBj3Dn50AHBNA
-        shlyS2++nVDA4fV5UmzsqmgOyvQOleoM0Fa8iR7Jc/UFH8fljfX8yUqSgECGLSedqR2HN29oRDOE
-        Vhp7+OrUvD4TY0egJzwQ3Wv9V2/h18lBTcMC/3t9I+BhaF5q6p94LVqorBbKO46u5NMLFZvWeIOt
-        6mv4kh4fgDHb7OB7j3sEj7srG4xPeAEHfaZ4fwzO3sL2aqWc28VCvXucPVbV4AU2h0ONvWR0++XZ
-        Vx3UlN7Cvrs5sqX2XB9qNkookn2tnJ/hMYW2U8aEDMWNjdr0dYD95BJq1kCOpl10jOXoG1pE8MnH
-        mwwrGJTcDiCNTWSwpRXCL1REacFufXMjlpLeAubmZdCwjayM5XG1wK4Sd0TwtqJefJ7zAq98eSHF
-        Pn96FXjGBnzHS4HgPqDl4Nx3L3j0FhOJhWx6IveOE+ju2wLj87mKZl9JFllFIk/3sdn2TN1qPvjh
-        3ZZMiC1tpRhQp/KJHovDHLFo2AlgCVb8LJN3xLhp64M62pyw89y5+vLaSQZ8bWsdH0+fvF/0JJCU
-        lc/g/TGp2ZKARILO+fslfKN55VTtC0E5CuYeO8fbBBYeVQR+H1sJ743aZ+39FvCQaaKMtVealMyu
-        wwaU4ILQpI8PjyT9ZEHEOJ7i+PrWab87fmF7hXeqw8cBsPEyy9AZtltqzfmStRehRZDt8gchsq/1
-        UyMeA1DMlxYJ1sbqF6l2EbDm0CRLjwcwa6fhBc17nmB8LIZ+2Xy5CT4blBHZdy76tGmSCboHYJMq
-        YlE5v0cIYV/QASm++GKTNbcWjN4yoQd80stpuhQ8KIPCwbbFXh4VqQ5h9oiPRLklQrZkvJkDrntE
-        5BpewmjKFSiA2Q4PZMe8V0RuyUMGZ4uk63nabBzOVAJ1n56JmOGXPiO7k0DPFQ41e8EA8+H99uHd
-        bg/Y682Tt2zvkgvvHdmSwry1JaNTNSmP06HCrtQDjxZZNcGXcn2gxb36jH0uuQaNrR6TS1gkbCgM
-        XoZCf/hiM73vy/lSqynszgKmaJvZJb3GEoJhkkQ0XujosS2fDvDJrhKZdyzVmexwEnjeM45Iyylg
-        rEBqo2z22RH7jlnpi365+9ATnggjNAgZVY3egrWcbcjukC5l49znAkIuvVKzNg9grudCAkiK/ZWf
-        jGw+vR+L/KvH+K599XFfuhoMD4hHd6Gi5dQxgGAS+yr12kNXspTTZehoL5mq31Yo50H4+nBjnlJq
-        jd+Pt0if4wukhfhAwjWzyjkJEx6Kn+5KrWtm9SL3fA7yih8Uad4LjL6/68CKH0QRHlw/x12aw+3O
-        COi+6KRsmmxX/eUj9aPJAWL0OGnwoz5OaNGqrT6Jyd2AX43ckULGypvuxTGUpPLlYm/lG8OgahoM
-        Yila40f1hCUCOTSUcIcK0Ptsm2iSBmsZuGSbpQZjpfxN4bzjO4wvUV1OjykYwL5yBuxwW738mGmL
-        4EieJ8Qnd+gNWlOl4A/e2lwIpqPKFWDlL/TU3ARAio/zgra8PMm+erc9Hc17+ic+28XsItY80wFy
-        XsQjMd9fo2UP2wCMXW1gv0RmubiibQFuu3yoSmLQT+nnGct9hESKTu+OTaQPE2jMnk218n7W56UD
-        sax2zYkGwU0D8z56o1/9Juap/5Zzm08avE79gUzregxfbprMpE1IrcujjBi2JgRVokdUTZ23R5Pi
-        Hstk4DHF0l6KRjUWvhDOLKWH0YclkWoNwdGTJ3qsVK3kGX4mEMovF13W+6ZbHVTg9J4nIge62vMR
-        s2QI4MFH2/ihsHHaFJISfSaAr147lcTJni/g2YtMpK31ycgPrw9lfiMf3Tt605lCAapFMlBV31I2
-        FQYvAc32E2y1fVoO/f6aguRaa0hsa4sRxcMIitZdIrGcLt5UFm8HiO7ZRJcPUD3Gkt75My7YygEs
-        +CEZ0JanJ9ba6Bux8079wvv3+sC/8yfm4k2Q41QXI9zt+uH45gXYSKeF7v1wBu2SpQWkesiR88rX
-        Z/h17lDUzBc+fN5i32rT14Uf2lGsqizKJmcI49/5YU95XMH0Pe6+f/iN+maWJ2qz5EIzRgzbb556
-        DQaUwNlzLjjGwMp+elh5gvpBxLU+st4tHWXGWonEONzpy3yWHDhmBkad/Rz7uW81A2rhdUuKNV76
-        3f1kQBhVJ3xf8Z3Ep7MMdwcorXzeib48LTWAIzeiHlHyiNXLsQKRy/FoidTzqlfnaffT5+a49OXi
-        h9wAaDgzfFQ9kI3AiRE0zuKW6tdlZqxRTxZMnkKND7LwiZZxnCdIhrOBbZrJPVWiKYTFFgnYPiXY
-        Iweg3qGDvDcpAsuLtnWhWT+9RmQwXvvBld4GkLj+i/ef58BmEj54+EgAh5RH9GLk2dYcdFvji++O
-        aXiTfrVkqAyfFwKBvDCSftvLDz/RnC+9R9muzSFft1+KbnHRT5npXKCo2S/q2Ivp8Y+c+bDs+4q6
-        xjnP2L4cCAya6IyGcwXB/BAeE6hFVVnx0AfEM8MvXPkS1c1QKmf4VXNwckWBtNz3CWZbCBb43nwb
-        tK2BnI2fq6TC9kkEsskhBkLSSxZYwLcj7HDU9RE4dwRTOXhj1BGTLUJ3D8AVZQoSNenck5v4LKA7
-        nQW09aDjbX/rrfiFQFbzWb0936xffSUcrS4RSc86D4YKin/0F3+F3hesfgze220bsTD/JhBmcU/R
-        w6eMvEWQAjNTjn/mj7Wu5lDyTZNsxXfLWB15EHR8UWIzSZpsNiCU/5yn8bUqMI0Pi4NtJrRUa45B
-        trx2k6GseuOXvz2L5TMHV/2FllCbGY1vzw4ybStjc/6U0byZwgLyKh3JvAUDmK2DPiir3qbHa1Vk
-        rU6DCd6LR0DW+ytXfuJDQeB0BI6a2c+7DFuy8xA8ajjcM5p2VcHDTcwZ2ANtyWZZlrQ//FXb8gCw
-        o2NW8P4VGoqX8MZolkkIruNU3zbniImBG8urXkfyvrR/+eeCx0YUEdcPrTcZ590L2pHwpfhL7XIp
-        39gFz31YrH7HyMZB6mS4v9MagVn+lATDmUAUszPhLb/RKfeOU5hEw5aaB4mAYfONDehPOU+P4OJn
-        08ZO73J/tQ0i78taX/WqAEyWhmS3Gc5gxmesgvx7z/CqlwBpRMrJtxFj0m2awpvjHQvkle9h751/
-        +skoH90ffm6/BI+N6DsUMjhCncZsDLJJ3lMBxI5Q0+MjUsE2u3cySPzThL9Pq+9p3G0deOr2Zxyv
-        fsIwMzqBdHnZ+MevFj4/FuBxkGPCrfznzSdODqdk5xFu5QN0zhQftr3mEFHn+n4J/PCrdI9vS977
-        UQNC0N996Fg3G025wIE+CTgBrPGFD6ejG032SAkIgOBj5PKtPtpCMIFSFXN67GQ/Yh6+aeCuLxDv
-        zU/gLabeXoBo5RLen3V/1XdCA7lvbWEv5AZvfkjpHejl9MSYJRR0gaxoMDMzDrF7lmbLj0/kekrx
-        0dL8aDIiXoBrPpLZu+91WsokgS4Kntg8SIjNN46rwK9eTG5x6tmoXwc4NOcdPrLejoTULLWfv4i9
-        QA5Bk1rnAc7E12giCU+w6l1JXvkvjVzPikooeBBMrzjA3u7TlT/+rqz+Dv3lC/uenQZmt1zFFm4Q
-        m6ZGvShCfboh0ZvLjJ0W5wsdqQkRkGo7E7HBXvDwFTPqwq/ZL65TdfC2BxzWmGb0vOIOBUDT6t9W
-        xiWaImZJ4Dd/xS82qD7PA8fcwVVfFtnE8DWB7RP3hIEqAyMxZqLUdeFQn+zc8o8fvPIbJLux5i26
-        mBZwnmuTuoJoe+SWnCUQ0rb4g4fjc6umoJGiBUljNPbj03gHsoq2PHZi9MnYV+8d8DGuOdpa5tVb
-        FM9Gv3gkG9QU/fjOYwdejOpIT6t+JateBz8/RScg6meiKRpszvREgJbeoin6dBMU0TFE3IFEXleW
-        ugDvWCb4wH03bMqqAwc/deZiWwG8x+w6bUB1cc/YccpXxjrghvLKh6jtzXo2BwsLd56qvvDKB8uG
-        tucBoGNhEjnezR7rUx3CLz8vqFSy0RsvtZPCntMUrJZ06LvwUnUQncMXPUiL7+0MyEuQB/7jF9/Z
-        LBThC0jGpSeLeTuUE5qcEATJ9KI6Aaz8xSNYDtqBHj7va7/UnSfASvvk2AhHZT2fuwuxwt2w8XH2
-        Jcsv7R1Gbetg1A8H/be/XboUNlHiwvz5tQn41R82b5VyGnAn7E74iMh2rVerHzHINn0esaUbUGcS
-        Vy3yO5DO9PpdloyNW1CA29t+IE0eD+V0ktMY1Ndtjk1bl6OlTnsVPm8qxEg/GDr/cvXmp+fp8a1n
-        2ewU3BecSDqu/YUiW/3dL1j1OWJrfizL+/oFYb1zCO9pST9vckUF6/kRrt7NGVn5NWyXqcR+fhbB
-        qrdkeNAZpXZmH7MVb15wJ7U+kU97nc0OH1vy1qUhNS5No5OgfRZy1sAtxtKh98hh5y0/fYpdN9b0
-        uVV2HTQuZ5V6xsktxSybkPLzJ3Dbzv1w31sc9PfLix60cWK/8wHpd+xIv+LBRCXuJYPzkFOtOZfe
-        vMCAh2v9XtcvvMWv7j4gh6nEz/NxLttNvtWg5BD9x4fATy/Czct842uQeoz0ajXAX724JRKNVv8y
-        h/bd8FDYHKdojnziy/CiRBjr4MWYqLYvyOllSle+ls36gwXKPTrN+IiYHfE/Pv2+FxApDhSioQt5
-        GcZ0eWF7eE+Abz/1Al3pk6FlMJVysvZ7TiGvY7j6l6LX3/D7DvGlPKPNBmrl9jXbGhTHZKb+ubqD
-        QVUyDqz8Cx+FR17Oim7exU9/ulJ/+/Wz+Wm0ARhORkf35kOJxvmILXDwX0/qczjup6au7j8+S9VD
-        RSLWpx6E050lKO4Nx1vxQAXv/bFH1dpvmVPipPBOPhpZ3OsAZump5pDjNBeB1d8azEW4w/Q6qPTA
-        PDUbL+dOhuihydhpirCcVj8Wxo1mrf2G1PvjT63+CXYD/fXvcT5Irkjmgbr6AU4K341XodtOKvTm
-        wyUEGpbgUes4OBm/6l+wO3AS9Rqvjmi1u6nQjGiDfe1i9lveKjil5uYrdkfHAet9FT9+sf5uwCKz
-        ACpVGDg0blUE6F3eCVBsXxVVb1qvTzOrp59+IfOm8zz+5yeKN1FG/Dy3YECb1vjxRWxuH1PJ4Ld0
-        YS+EJdWUOirZTXUacOhos9aPR7/EUfhVWPiqyEyR583DmcpQacbo3/i/8g/4FgVE+Pv124uVs5Ng
-        nY09Yr7y6MkBOLm86j2qbcpUZ4N9s6AzXlW6X/t///YHrLOMVa+pezajmyGD6fWhNu+fwdy7zh0+
-        DlKMD/WD09s1noEZxF/sMMzrdLzsZHnP2jfi13rHrOuOh5KDJGoV6racH82ug4/NVsTWd1dGc5Z+
-        ESzC7kw2OI90QdhtrV3DSxM1d2cFsHHLXtB9iXsiOaWaifHt2smnOU9X/zLNlqQFKXxdJPqnXs9i
-        oGjwNRMBsRC+o3X/FgzVDf7156K5VeYOkiYX6d78TDrda98UWunFw9bQ7MFcem0gn+f9hSL+PPft
-        dmsmkldaPs7DJ/EW3QIJ9Hw3pJapv/Rh5MwAXlOUEj7cBplY1aCAN+t0ob4aDtGE718LSN+dj/1n
-        BLzxyfRBvs5ujNXEsMHMX/QJrnwPOxtmsW1IWwR7IShxtOIJy7e9JT8s1abWW1ui4ZDyAnizu4Dd
-        QQuBkI/vC/zh3conytEphAqu9RmrxdxmrGolH7RCM2GcHSSPXAKn+NMvEj5A1Sfjk15+49SlfuF1
-        DnwIP3+G4h+eT3lVwbW/gZFwc0FL5+sdyr6v47Oty9msVN4CyL7g6PF+dMGP/8HVXyHLijcLJBr6
-        9Zd++rNsGqfg4fedTqQ7i3w2GuPdgpfY1LAzezJofJZe4LR3Zor9u9BPnnUMweqX0f1+1NjiitgA
-        Uw9FHBeeHA2PKRmUbR4cyCs4BR6LhpkHwwPdsWOSHvTnnVPBtb9L9WEzenN7TF8w0zRIygtP+pWf
-        VVBPnsc/+nNe/TJ4uW7wT59ntEBOB8NKA4hK+yRi0eOmwl9/3JK8WO/sQdFgbk82PfD7kz75GkC/
-        fuzaz7p5/EbcVbDS6hwpl3zIplt91+ByUA9Y886BzramFMDU0S9ok3ox++EDiOsC0MPp2EWkBu0F
-        JsL0pv5Bt7PpOnQLPAr2Hm2Eo5FNosNC5e/fq4D//Mdff/2f3wuDb/PIP+vDgDGfx3/+11OBf6aP
-        9J88L/yTCn9eIpAhfeV//+vfjxD+bvvm247/d2yqvB7+/tdf8M9rg7/HZkw//+3zP9b/9Z//+H8A
-        AAD//wMAWK4fC+EgAAA=
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4c8d9b11121-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:18 GMT
-      Function-Execution-Id:
-      - yvvl9h8bnq2k
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '42'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 079a9786f90021c1a5f4aeb630bbfc1b
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - b1c65dedd1c013d35ddccff10d9bd9bb
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "a grocery list itemizing pancake mix.", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '114'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R62w6yyrbm/XqKmXlrr4gI1GDecRIRsEoBFTudjigiIHKsAmpnv3tH/53d3Tcm
-        YCUiNcZ3qvEf//rrr7/rpEjvw9///PX3O++Hv//H997jNtz+/uev//mvv/7666//+H3+fyvTKkkf
-        j/yT/Zb/vsw/j3T6+5+/hP++838X/fPX386uWuBl8y47tr7qghLc108KIrHRXIvvGPynklAh2g+I
-        t5vWQNnD9RiWhswcw+cSwI63DXOxUiXdbX3MZdinKtnTOzf5uEIiKkgwU2SlWifc4umGVI1PuJ4a
-        Ek7n0k6hWzodlc71Bw2ahCnyPs7ELD/vkgkVagTCypCJXhhDwvnYp2C5tonFKGu6aRPWGC5l9aBz
-        XH0KLqrLGpFyvrItvy47tnxFAEWyr4hveBOioFxsuOjrLRaP3gv1xtKXFHEQYnaHjc27IJVr2K3N
-        LV5t0QfxsIwjhd37FE9NsSl4tUQAN0EvsGpfUfhpPY1C2L1T4ha3VTGe49aG88Xf4dWnLlFT7Rsb
-        bZ1dykxrPnez99YVuJkqxX2QN5y3q5MPx2WhkZ3fntHUnE4lNPwj4iXfNAVr9lsMVCcpVhLGzdkQ
-        xQyczWum4qqnydwwzVeHz8Ij+nPYdKy8vBewkZMn8ZV44Q29FPlK0UQhIQcfwvHhcAAtSEe6GLI5
-        mdLno4fbOL6Z7663odhtdzl0763H3LyqvPo03jXwgtxhdn7eJdPJygz1iWOf2a3uId49ugAYutX4
-        /UKQ9Denb8HtHIcElvLhrTMtUuirrGPked2hWSbogBaLvcw2g+N6bX29z7B+TyssG4LIZ2XOSzUP
-        Dy7ZNhvPK/EjEGAf1zZLj87Dm5q9FKNbYCXM2hq2KfptXUK3HXuieY5lshNcK5hSfiDaRT2gMbvG
-        BmpkY8Ar62ggYa1pMeDDpyAbfXQ7vktNCi7XR7bllWnOg644IPe9TszzYjKp5t8oyDvoGOkVPxx1
-        ufLhgkuHCt/fn86yLIG+KPZ4+bH6kFqBRmFbrWqy4Y1h0kXtiYA/tw0xctsvZr/NSvSOO0awFh7C
-        eb28uFCoAMT97i9bOysLqTauiT70gGZO7jVci9uRbHtLMnvTKmqkXqoQGwe08aZDY2eQrJ4m25R3
-        oegNcqWoe+lL4hcXsavdSy+CsXgbxMuaOWzS54lCo4Umzav7Nhyn/GpBIaORLq2XjAatM8RlU94s
-        th9VL+RJX6Tqfn0+EK192uH61FuisnraV5wtvMrjz3tlwLGfWrY5KU+T52S6Q3S0PcwymZnsSswc
-        OjvRv/V3T8bt5ZQjcembxD6fem+aeOTAr552uSeb/VGZR3g2pkv23KmLcfkuHfiuZ8R6XTnnounC
-        Tb7fSBrzZTcsbTDQt1+ILsZBOD+0oYKiOYdEmxdSOIIxZGDV455Fbf7sOEnzCOg7ehJvXvlojG9L
-        CS1cZBPzrr2KiS+uGZQk+rAjM9tiGLL2ABt3OBFPdKOCRqfCgrA+Z1idphufRSOzUVQvZypJmRFO
-        u06aUbsyz1Q8Lo/JKj5yDP1DWLFUj4qkinMxAOMt7yli2cacZE+wVfuRZfht2++EdYNkQJ8/nwRv
-        HkoxifUqhvpYycSv+kVIc085gKZvNkxf3vJiLA7rUd5s7xe2N62w6AeZ96quejmdrxYk7PaqbFh2
-        2kijstyg+WUnFcqWm5D2o7UrfngOaJ02zNmglcdOvS/CPcZXsnv6vTl9MrNV6UKL2H6dFiFn2gvA
-        E54HgivPLSYQn5Icu9VE1+km4zP5MA1eaAts2yr7gme51aPFtnXYXr6rSf9AkoG++8s2LoGi762X
-        iL74Svn6+eh43EcuQpIY4aEEak6zNAuKHkoHpjfFu5j0MJYgfhNGha246lp1lhWIX4uJwvZ09/rB
-        XtfwEXcDVX2Fd5T37wNstXWE4Wrm3mSImq9ezs+RbfB7ncwrq6rgCAeDTvvlEzUetStQ1fLD/KeO
-        UJ8kW6z81nu+OhezUyolvMZM+OL9qeMJSD46KGJO9vk0Fo28kFxIu1ZkZL8nIasPsY3alX7+1ucc
-        znfqLkDBzY5pfkC7QQ9jBULj7NPV+/EpOI0TRVll9w1L5RcpZqc9BipXUEF57KCCD4Hqox++Xrb7
-        Q8cjcVagsEuVmOHS8mh0sGL069dtusnQ5FFcol3T13/4YD6rsq2YNwPTs9H0CV+jyYVTo3+I1y2u
-        fNyx8wjrPFuzzfiYeN/uJgzbc+Dhxsv6cD6+sxxa7prMuwibcLV+HTCc905N1QXvvCm74Qjelm6z
-        05sbIUfSuoLgWr3IVuulgkrraQFJuY2ZKx2eqLutrzmMN3um0sWGoj1kOxHm2yTj1VPNkyE+Il85
-        kTkiG7Em3ifUGw26q3vBQnWtkxmfrDsc3HEgxpEJxQR236OYn+/shy9jczzHSPjQG5Zui7zgmQUW
-        6OouZ/pNU00umMRGl5WnECvaD3zEbUrloEIa2a6ZElJqbQEknejEustFMlOLADhn9CD20Xvxmb8d
-        C0wPvXABXhgOtjO76ku7L4mZL3HS2582gPBGOHE+nIWdIjYjTKXvkCSEZ9gvV6OEpP3CIF4lkI5e
-        6/sCBUVrMHxpVibTVxcDHt7LZ06z6HmdXQ8GNLeo+NVP8Q4+jgFFbuwo6Jc8GY+P3PnxAZbSaekN
-        N78TlfIaO7/67UayySRw3oZL/NFquj/9ECttxTRJq3l/zrYHZHSRhdXWjsPpepdKEK7vgfh7MQpn
-        17hVUEfrNdPTPihmDTYKYpbREIz6nn/YY67gh0e7U//xePQiKUol9US0W7ozuQJaCsyoF1Stjyc0
-        nFI2I4Y/E5ZKweiGt2PE8AwNkfaXPjLnePNuFWeOGubMj5SzYmPGP/1CtGhRegyL9wBobGhYGkKh
-        4PUhttTV07qS+BzsPRqZWob2o2HjhRaO4fBi8gxHH+8xiuqVOZFKoih/+irZvLmR9Ei1ZzRlLjAs
-        ZVD0gXbNIXLDmtnI58kEdtnDkrxLpt3gwal+iS2UzP6G2cflMeRoZ8WQcTcj1iIxuPAMp0h17LNG
-        tGcdJmOapDlwLaio9K5nr+UkaqFyWEmR81nzNrWtAHX35ET2jGd8SvTVqLiGioifUav49gNGD2tv
-        EHvMS/PLXwp4H3fCgtF3Ibc23IVClkdmRfs9XwnmeIDuZS6pNDUkmcUeSsRjSPDReGl8jG9rCaLB
-        WFCEogXibTAoyhcPqJpVYdI/M9VXNvL1+Wc/x9tbDYCKvctwKQCajOw+/vqPuf2sIUE2zhjGcbP9
-        XXPxnmSxuqf1Da/M994b23sy/sEvL3a1pAvLwxl+ekL0Vx+PDxv5DPDJUoKJa5ri7ubnkEzX9Vdf
-        LE0KB7cC9ro4WBLcTzGqjuUDe6p3vJJ3n6SfBd7CexNPZI+PejiYXeDC931SMVsmHR2fN1sm5Xhl
-        10ZERS8qTQ0cSwrt9YuR8PQT2fDQwCJ25FI+YEuPYVFFwR/9Nu427uGPftwWpPP67aAtQAxniVli
-        AWhkx5WB5LpdsR0RP+b4OK0F6E1+YrqzWhWj125jdFhss68/eXZ0vXy6KAiCC30m67SYfvzTWssX
-        Pm+52E2x0GYKM9oFs69tyLm8wKBMrvNhN8vkxcCc8Qw//QF7w+LTuRkcRboqIjPUreANZSCl8Inw
-        mxl6DMUknVsHbCp5bFuyMRnkxqI/vh/au6x2I9ZcDF6aIjp31VR8+cFRv3xAQu2e8G5bhBa8xlz4
-        vu9twhXzTdGx5y1F0ikwmXYaK3VK8oARVKJivGbnSjlGiklcctDN+pyRQPk+DzEl0Svmn/6/Xyvr
-        jx8ZhceOIpTrM14FaPboB19ikLrDi45deELz2VU1mNWCEL8YppCbWpSifVQpxOrkfTKOiqkBPmu3
-        H56jvNvqmdKPlc/MDW86qi7VGbbpQqOrKNBM8X3d31E3cA2P96Yq2GcTULB9Z0W2yxug/ve8+Ufh
-        ZAe0Q1PyxDf4zBJjeqUryXwwJgzVJq3Iz682p4tbgSO3nJBDfvF4NY+2aqLlmZlVdPYmaxwFdej2
-        O9xF9cnku25bola575kXOgzNIulAee2x9sM7xGqlL5X0+DmT7a1YFZ+FjBWEzEtNl7ofmNPjujRQ
-        6YXJrz/N4ZOZNXgnbuP1NGnFuFyNyq8+cL893c0f3sNHwTJef/0ELdJIBKmACwvuYIRr7fGYwa78
-        M9Er/RaOaoty9NU/OL8oR8StcdvCu3a3xP/W23Au8R3RJFjgw72xC2FaNhTErWCx7S6mHgXlackX
-        mdhEk1ddONdNk0GJTgesBASbc/ARz5CZVkeCvbn02H02XDgMmYlH7XgMx70rBcDwe6Kr8i50zD5I
-        OUQ4Epj9yXjXd/7WABprGkt01UlWX7yEY45z5o0t6aaIQg6wv6vEOvarbnwlbwFOp7mh3XVpcC7h
-        cEQ/PfZH/5NzsfgvPfmWKJqjU2cr86u8YxTC86vPRw1OHnPoslf8ZHW9HBWYleCI184FmcPgLkT0
-        1Ud4eS+icIpeUo0uuHIIfq0Y6ncsnX/+A68vpdOtdvwE8OVf8uV31ITNSYS2sXJmuXpoNrvqZiH1
-        EOxweY47c3wlg4jSTZsT+7mazD/498hlH6/ZoQ67MfRztHt2W1wdPR3RRW0KaE8WB7qw030xJ5Ks
-        KXeD52QjOUIyBYKpAB/PCVU2exXNoDxt5WrRLdNUN/RG0+pqqJ6ZTT8dVb2ZXdENihDdaX10cjQE
-        x3sFxWVR41HodHMMtGOO8OFdsP1lqpLpWp5GNY7agLkvIoU1Gl0JSdJHwzIqXyG/k5sAdSybuMvC
-        dVeL23eFbKp4zNDfmvl9Pgnu71wiP/znazFIlUkSJ2LHopWs/vgB+/VmP79c7dYPFy3pkTL/lUdm
-        te0vMywP6oFoTRom3LWvo+yXrw1VA+uB/uzPKDghC9Mm7MZ6wWeZFDfKjIwtOIPFOYDVyqbEEscs
-        5O+H36Iovp3o8or7giUwYvjlVY7gfroR4hj++DvFLbtulBgqkSk0PsGPnRIO7iKJ0Bcf6Nc/Ii6q
-        6xa1RdMRTzoF3lgdt7bSj6VPNkZ5+4MXQPbxlbi1oqDG5rgF2rcN2+tkMofPGN/Q/Vpa7H649N0k
-        HAQXJa6wYUfAQTIZpu+i2d4dCPvmF5OYyJm8co5rknQLmTeSfLxDXZEcK1dl7FhcqSn64hl+Q8q8
-        7nctK1rGtr0Ve8NHvR+gum0IVj/bLpnj5GirflwdKRo6oxOEpawBi5sAL05aYdL1nARoT+BAzO2i
-        4mOJpwB9Drsrcdr5Hs7TNnNgz0OL2c7TD+f+WtpwOT9G8suX5tJuFSSMt8OfPKSP96BB12YGib56
-        fGSW7EqKd/OIvhHrgr0+3Q0yJJ6IFn5Ej164Z8CXb8mmvEdF3Xx2IqRUFpjD0yOfjekpwGHITWLW
-        z7CY+VuzgIxsT1kkHRH96iVAj6tDNimQcP31cxBQ4pJddhaLQeLfvGJx11mstn73/X8H8OPyyKIF
-        foZcrfoIffGB7NynHM765WCrw3HXMPMoVHxONgDQXugaT3o28B4rXQqFWM8EX5qTN6GznEIvBzpF
-        6GUkYsMcH+73tcH0XtonYxiA/ctPyT5PVmhG0i5A6fF9/urJCx/vYa798jh20ke34N98QaFM/jCr
-        K4KufXrtQjbeaE/XH5R1bJd6FLS9aDN3ObuoXZ+MGvLVPiA4Fw3UC74AaGXfSobv3aYYsr1xV755
-        JPMWYmvW4naoFE0WGNEcteIsfsYHJdCk/k8exb/+B33zAazQT5H01/DLt624ZPjoPMyqLW+OdCJj
-        xM5Q6OH4kU821MKZEOxHQzeOW7yAna0GzLiDkTCiH3vQ5/LGfv1Vw6qpYCiUJfnqUz6KF+WMPl7O
-        CFlVLzQfsp2AbMAtIVyWvcGvmljO/ccHt/cN9uavnldueSdhVC735lwhGNE1lOVvvUxozrgEQNLZ
-        ouzJyo4vp4bC/fXsCQZjy/ncbWbId35Dp/3L8ySHSBHkO9wwb9Lcb71Ozh8/vkvWVrgmHfV/+M7s
-        UCtDVrq5BcnCkdju7CaIX65TpaLRef7883/lBb/8ASdLhujb35UgEheT3UPHnC92SY+ct+b+/EAy
-        kErqQUuvBZ3ay8rkZ308o1cnucQl9IT4+qqLENvFm7hrexXOXTMKf/z5nmxGNOnqcFO+/YSXNT7z
-        6ZR+Rjg15gcrWLHDUbOi6OcHsdwYvrmSG6uHjcJdRrrxhcaoVc+Ix4uEmF5Iu5HrywoFRW2Q/eNj
-        h2MYBzOSoPXx7G3eJnv284ikpezSobWl5M2kLgfurihelMIdjeE7bWGzEM4sPmzZ139EI1w+q4Sq
-        9B6a8zcPUm7mkjI/PMvhcLi7LVI2akSw1XTesK/XGJoI9ViN0YFP3/MGGNfXI9PwdjKnWwMpRIO2
-        oEvpTVH/ws3ij79xLvd1OIXNSUCzV27ptLosw+HCTBG++TrbvHme8LdyOiiXnXcklrKpvfmgBimi
-        JHJJKlzeSfsKnykqyGHGK5fcuz96Ne92E4kv93Xyzft98C9+RQJ86/lsPf0KKuwkxDkHg/nVcxL8
-        6tlZpGCO1ZFY8NLSJXPQLkp4dM0PKjU+O+LSjxmu9/bLgujdCwSzjhXFV6/D4e7GxD2VKyTcs7cC
-        gvm54nEX6oVI15ahvrXRIa4YbDiVPm8fvnkILRpRD8Vvno+a8/HCjMc4oX4R7ioUPfsnud1ltfjl
-        hbDMI8R2jZh0ozscDlCVzsi81XnjsXZ1wvD1s3/OF/pW7mP0xQuGG/dS8MtVLv/4edW3LW/a95oN
-        Ua3O+JWtR290hziA9Xbb0YWY5904b5wU/fyv+vV7begOPfrmz1T++jsWvbYpjOvk+Mt7OZVuzfmX
-        N5Mfn02d6UbyN38jluMfijneDC2kqvb65YPfPN+h0DOc0faqjAWL+7uLNrUufPOLFZqblN/RTy9Y
-        HJ/Mz76QqXJaCjvyiLd6spqqQ6Del1VMfnpoUI+5BQumbcnjWDUeb/K5VhO8NZkmdLo3O9tmAd5p
-        sn/1FI6Pq0YhaHcLmtvMTUQ5cwxIninFIn8d0FjtGgkeFcTEuFr3kPqq6aD5gCdmOtGLz8bWi5Aq
-        Hh4kFLID4u+H1armJxqIVrcmYqw4Buplo4TERLqDuDvSALqQZXTRvjbJ2iq8EbZF1RLnCHPSf+sF
-        feo1ZtvIeBQ/fodwvunM0l7UpMshz8G63HJiMq3rxvC5BrA/lU6bRkTdXItDDI5xEOgKRWVHewhv
-        6Pu+MBJdoWDvgzOCedMwcaWHmQjew8vgdRRbZhFPDbkxyCLYkdARQuK+mMx5fYbD3YkJDp4uX2FL
-        v8Hc70q63OQ94gs8x3BJlA/NmpQnPFuPLqq3Rcw2Ave7STClAOxWWLINCz9h/+UvEJfYJLqnzXy+
-        DqgFCWqf3NN9H37PN1LUJqPJTt6BdP3P7xxmZyDatDvxlraOA0pMW7q2sMmHUrUWUEnTlURmpqBv
-        3lzC+YJ3TEsFk3PU8R42LjvR0YOwW3+CtIJpf30zZ/PIwvG8UijQcCEQ/x7vED+UugFudKrojNSm
-        60ssH+B1T2bi5/KL//Qx7NfRgQTnDQnH3ESKopRNSpc7aVvMzva1gPxcOERPLi4SzqF5g3JuEjz3
-        I5iDdM4d2J6eKjEm+4zmX37eJrOJFytPQExK6wyJ9/vA9uosmWxOdeUP/png8XAYFwZWp/M2oatb
-        JXQD5b6AnDp0sFi3C49lud/D1deOJHWFOpmF5VZAdbXPmUbrR5dhpUgh6fkeL09yyackMPI/eLd7
-        XXYFd4v8BjQ5LJj1Pc9hjeadwT3aNX01xbtjK12rYHycRnx0Lhnil9d5hraxc6aJWVGwjXcU4Itf
-        5PA9v2LhFPlqkWs7iprTB43TsunRO7Urspslj7PSbS0IgsOF+XJJu7HziQbXwKiwiNum46hDPRxb
-        6cKuePXNW8adDUnAhq9f88z5q69gPMYqlZZP5vWasM1gHLdbslGDRVH/6qd7b7w/eXSTR4sFDB3Z
-        YeVF4kTII6eGNZQXgpe60I1hfJshu9pLjE6NY05jEkhgZXZMdEevTP66pC368YFx3rBwtNk2BfVS
-        hsxVaq2bf+eR0hK5eAq6VdI0kqWof/+mAv7zX3/99b9+EwZV/Ujf38GAIZ2Gf//3qMC/b4/bvwVB
-        /DcT/0wi0P6WpX//819DCH83XV01w/8e6jL99H//85f6Z9rg76Eebu//5/a/vr/1n//6PwAAAP//
-        AwB/Gfvm4SAAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4cb8b3713fe-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:18 GMT
-      Function-Execution-Id:
-      - yvvlh8rh38s0
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '172'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 91f42e8a544d43c21eecdcd9d8b2f786
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 54675364ab43889d41f33f1cafe85a27
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"What is your
-      favorite color?\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '269'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOwU7CQBRF935FczdupqQEK3SWLnXjgmgTY8gwfcDIdF6d9wAj6b8bEpXtzbkn
-        54zQwcLvnPp+iOX8qUntS9DTs/jvdGrb+jE2x9flw6KdLmHA6w/y+vuYeO6HSBo4wcBnckod7PR+
-        UVezRT1vDHruKMJiO2g5m9SlHvKay2pWTWFwELcl2DOGzP2gK+U9JYG9qwyu6v+5MVBWF69cMxr4
-        HQdPAvt2Rk/yp8wcCRZOJIi6pJdATkrpEu+KzwPJRV442Ye0LTacC+GeONGtFBt35ByUCs+R8wSj
-        wSakILtVJiecYCHKAwxC6ugLthrfx5sfAAAA//8DAGuClxRMAQAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4d0f99b2264-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:20 GMT
-      Function-Execution-Id:
-      - yvvl4b8j5ntg
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '1327'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - cab4489fcb073187a73b112f5825f6cf
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '89461'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 358ms
-      X-Request-Id:
-      - 509ffc387963a73e880ed3350d567cf9
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["What is your favorite color?"], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '107'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6Ww+6vLrn/foUb95bZ0VEpQ/rDgGRkxQBFSeTCSAi4IFTW+jO/u4T/K/s2fvG
-        BEqCpX1+p6f/8Y+//vr7m1Z5Nvz9r7/+fpX98Pf/mu/dkyH5+19//e9//PXXX3/9x+/3fzyZv9P8
-        fi8/xe/x32D5uefj3//6S/ivO///oX/99fcZ6z7epWjZNRd+c2GRtyvqQqWnQj82ERBDVShmht5N
-        WA56YFJ0pbZVPTouvwUfrrvG9cB77RFfZd83RKggVH1kliZoF9CR7qmjJyhojcizojZCx9zCnvj6
-        dJONkwRuj0tND+JmCPuLuFNAMymnmr3XK55N4gLoxtGx6+WmMz6ObQnP3TGj3uUhpH0FlQfbyN0R
-        4fZqU5IfQhEVoVZS43ySQxruvj1Ir/sVO/azQN/X6xyAGBxib43vV6dXq4ChUv5gwsEu+JStCAM1
-        Zqr3OHV69fQU9S2TwnuSMR8+DrMR1Gg7LFrsnnjn8EjzTZQ2ao2PdzfUxnRzecML7As22DVJm/au
-        l+Bdz50nDuo6HGtUCnDaZwgrZpo4/O0te1Rbh7O3Jf2T8+Ai+tDsLhlVtTvveNGRN5KbkVBLuJyq
-        RihNd3t83A7eqmVauvYOuy8kxQd5TZZv+cTvxUIGMUi9r6Rt0fTaIBUV7ftOxjcqK7Z7dhHczvsV
-        maztwpmUt7RAr5O29QYqxpy9rgcTtMHR6OFotlW7iU0Fqr3tUP2c91V3fXQ5uuvwJKOxwmmrD6wH
-        xWsd7HbK1mEH7aiCn8d7HHDjFY59USWyI70xeWLNRsy2bSbt5OOAnVtQd71ALxfIPt8zNtqhrcZ4
-        SQD8RKg8yfCg4siNY0TYN6Y7Y0XT0ZUED7aSsCRTVRl8BX26AbxdrAhPZVyxi2ipULhCgq3roHaC
-        3/UxbC7qgR7r50Xj1m3no3Fc69hzViSc7vs6QdZ5nLBxDHaaWK0yE6JT5FG8ZZFG+9XmDVlRnbB1
-        Ejhi+/EB8K3eN+zWXd+N9cOrYa/eONVUtqvIcctFkNJ+8JgXfRHD+lOEVbXNsRejHPFiC720SuoO
-        3yJ/EfLddPJhhbIbNY7BUxvqISOgvw4fbERkh8QtEzJQzYtDJKWzuYAbAUAyLYcesumNRn17jWEU
-        FpTuTo9z2sIRC5vWT3RPqLEfTvVaq9F48HrsWNRwxot98SEfJ5cq1VNEfUfHDZAwcj2Z6VE3Xt9T
-        udRz6UH3ZP8OWQvxG5oj2+LDS1HDtRLta3hMloBVt3t1/N30JYqsMcBHpgvVuPFuNnzj7eQt7+Oi
-        Gjp/EKH0Tzq1GA75GLS9Cq3cY6xE65MzXadYgO6QbekxXxthfWcPE05SpOKsqD0+JsKawNHyFOp5
-        p5iz81vLgXEcYq9UA/QSQsmAMowpPmkf25kCPS4hsniAlesiTifsFBuZGIpCmrpfhTR5Ny6ELC+o
-        U3w+3QRNbaDPd7EjqF5pGnNifyPjplhQZWdcnQHHS1X61Qu3woZPpjxEoL7aqyfwzudCvUi+4J6w
-        R+1xTVKapeMCHDc540Ox1bup0soLNB85+X3fiksUjH+vn/pS01ENMhHatxV5YynUnKxRR1D5iU2y
-        dvGkkSx/TpBzWfK4FNNqYK5wAc+4y1SVWRfWnjrFaLy2FbVIv0PDuxwyeKieRuB5P6SCWFMD3Q68
-        wXomDSGJ7i7Afih8HG40zeHfoibQt4ZGnXx1CSdBBRPdU+tL7cNh5Yy7bRGBoK9E6sBVRqwfmwsY
-        L1XGh9u94hN5Jhk6QcXItjOXFV8cxQ34x4VHPUESQnZ3eQ6256X0h7/U7GkMCLkudYT4WTG6uyjI
-        fXkfrHZjmbKyH77w3iPF2/JL6kwXsgVp/15r2N2cTTRF28aDr0o6IvCJdJ1ZbUrktdujR3a3Whs3
-        3sn8Uw/2Y/NKx4hKFxCcSvOmbHx0bDyFNQoO3pXi+5hXHcmQi5Kj/sE2et4Rie76Aoq7f6I3hjli
-        maOrMG2vjB6uXVD12S0wQR7OPjXoUHDy2w/aRVt6U+bVDt9Z+QU+yhKT6lMQh3wWuwhtF/ETW535
-        qOb5LNAVThXdhfa3G6stSgBOa4cqq+LB2fkjSRB6VKO7Ibf5gA7KBC9bHMk0RXY3iPYUyHZXfKi7
-        apfOtEYVkau96ZBFNRgOY/fJhwx3JXbylZjSCV4x6FeeYmsXZ5xoeFBQkZhvnCuF000fijzk3psO
-        qzOeslEHCRnf+kF/9UnN/pPAWgmDmW+qlI7VBsCvP0e8W0srbfKnLkfOjTyxam0X2oAOJoMFNwzq
-        VYOh8a25LdG5F0NsBYMbrvr9opbuy/eG2ubWSP/wxTU4aNg7a0U4zvODz+QLWJvA44N+5j0or9DG
-        7vP+CbngBRmUkjZQSz2t0ufLKTI0Xr8VPoybtcZj+lTB3NzfdK+dj44oG0qC6vftia3cbxHRQ0eC
-        9PxQsWF/ruEkrycPvkJ2wGeWcIe8T58C3XeiiI0yHkOy2ugi9OsYz/jSOkw5DUya+RXrSw+nY6P7
-        ujzzL9U8t0zZa0QLOMeCRJUm2fPxjuQczF0yYvc7tekg3swEud8oILz7OFw4fyZJeh2oQbot4um4
-        3U05eEKzxoqxfKGpOrEczudTTI+bgDl8WH9V8FeaThWur8LpXiotvGxhJHywZd6L08qT1C79kMXj
-        /Q2pmMcK8OSYY69Du048Kdsv5IWUYw2dTG2QEiLBShFVIiutqrGAagH6nFIDu9SLKuaWaxc+K/Hi
-        EdnEqCWbR47WT0ehJiKDNiK8bmGeD47Ut+NMfn2PNgkKnoQTTUz54riQEAkvLt5pRR+yzXcP6FTy
-        AwFNPaTch+Aiz3hEDfwZuuaOVhkqhPOBHlilIHLf1/EfPra37piOduFHcmItYOaP0WHL2+CB09ox
-        KZ2OOsxTpVgeVrVFZz7qevvSZNB1koW152cZfr/7OAeL7xcEwfWO2HXNcrDkqcbu6qB1Y3h6tzDz
-        pTfkayOdwvWWoR9f6bbaIe68ripc33pG+sUYOiQWFB9CXjtkmZ3t6oeX0m+9f/U+XvjNQ6u1tPYW
-        rU9Str3nBNXW/oy1qzhyQo1XCzN+kaUqKZyfd9cJ9nf9hmc+D/lC3AqIr6sWG6LVhVyCYALloas0
-        T96BxuzhnYOdGozu5a/O2ea2FJCjOm+yNHDF2cqZWqSWRU/3VVqkPFhuXVRw5ONjtF/+G/9XFcqJ
-        ZCm1Qy5khG2itDbhXOu7zrpZATq+FxpZQyk7bODxhLCYhnR/NKSuj6bWREZsfqnbKTeHRVf5AlH4
-        hD96lxX7yoDDx/Mxfi0Th+XZqAC8xBor98VL49qK2XCy1Du2IblUPEu3C/SAuCLdgxA+Lqg0wVKJ
-        A3pHt3XIvX3gyvzSAD4O31b76WNwql0046lZkRkPwZFqjPeHzEbiMIw2tEMQ/1u/8Up5Q3yId9Rf
-        FUtEl5unL6cOibErVtdq3LwuNvjPXUfdcrpXY1btVPlz+Gbk02Vu15LQjZChWxgf0Eab8ZO7sFe8
-        PbXb9NitCnwDGP3ng57VTKjGVf8uIBhFSo/+sei69drNkTK9LnT3eOwQc5zJheC2AmxajHA+KPkC
-        1O72oYpjaN1a1vw3KoseefLW+VZjvxffcBXL0PNbcYvYS1FNeEF9JAvA63T03GcgK97XocF77DVu
-        2dyEUPXfNEwdgY/nKmxRf9Fb7CzU0WHq2f2iEJsS/uPvjqaqgk11i7A6wRX7tl0NDrsWWLmUddov
-        PygCgcUO3bfrpzPBEYvSvSQ1PVwmyXlHXajD5SOV2AmDK2dCfIp+eo2sb/Xzpw9NqJ+6iS8nSNLv
-        fkkM4JcO6EHhY8oOgihAZkkBdhbI6vh3cBL0UF0Nm0Cqilg710duxBi1wreOGHH3AZx26IZ3GKq0
-        tVXUQ7p7NPR4d7k2+8t4+w7GM81LdUL9QmEMHR5dROBgvTS2H68AHB1csr0ItkOwU0jwOFSZt/bv
-        x27c5bz4rRfe3QYfsdKyFugpGhWRT43Qjf5nbwOSbxKpGCmc9gMnSb4GpYS9t+VX7M27BB5L2NP9
-        5NYaLeW0Bh+RE6n5RCq+vAsZ/PSWkrmRNj2rjw3rdoeociqJNiSnTAHxbYzYq4a3w06mQiC2PhRr
-        +z0JSZY3E+SKyqhZiw7qesdzkWo/t1jPdhEayRQnSLWrLWFUZNrsX9/olQZf6jwLRePewWqhmdod
-        WdpbWavJSvHggrcUW6PphrwWQoZKnJ6p6/gq6q93p0WzP/W228uHT4Ut9TDXD1l81EbjDn+ZcKTC
-        wqsy+e0wsf7oSF7vJWwk9uqnny8w6w1vKRzVdJ0mdoFw4bnYXrifinwo91BzOPQekDNow9ZXajQc
-        BANf465xRl7EE9RatMd21hbpWA9ZDx+9GGm6fhvdWAZMQOuPcKQxL8aOxTkyJGOrXvChPlh8OheV
-        AMOzZqRsjmL340tkEgJ0N77MiqljsZFkqcuwPeMh4906A+FRZl5PzpnDxGOrwzvgZ7yf65v+ySfG
-        x5qUao0cCrvGRPw5JVSNlG83YF4JQMf7mtqkdMJBUT4iKuUXpuZp0ab8SY85ile2jvd+eu9+9YbU
-        CSqs+/kl7WM1F5AZQUgW2mdCox2OrbxEaoO98TWmpFt+RBCz6EB3nVqE1JRWJejXMSXyO/w4xD/6
-        F3nGEwLL1qnW36Lu4VrCiI1gFSDurqI3ODDK1PlCgVg0tTb4XZDQ/az3iHZHJlhFdiObeX+t27Oc
-        Q3Ivc6IE6bujxVYg8k9fGTtRSf98r+XTV0gjYSXlu+nmS7P/IWMa1w6tsflFz/Jge5H2qKr6vhgC
-        mP2mJ01N4/CnJV1+4yQdhyv/rQd8lo75wxNEZrxBlwEjjNOz4IxpqGVgnB4pVuPDOxw7/yWgy2dT
-        0qtkBN2YaEcJPVNJJeLqyjq6JXr7xy80s//uK+g8WB3JhXpK0XW9+YwJ2rVvEytBalQNfY39z49S
-        pyD7kJ4z/Y3MlbgjBQSflEldLUK73qn4UHknbdY7G/QnH0s2VGvzc7OAS1JfiITPfsfXYTHBevjc
-        yVa39XStfUpV3hn2xpNnfhjLYCOgMOjv+FguaodXx5sHbN6lbH7feMrOG9jkW5XeHuqrqpToWEPh
-        igkR61ORTh7Va7QSRhdrp+cr5Gb/iQGfny/8bcRSGxcLZQPGYnzj+0gPvMwPqQClH+rYOxC/49dh
-        W0M+TBPWUplW/c/vCS9a0z2ItjZ5qPLBO71TuneqbzcW78sCpspuSOfIEZqebmlD9mnP3tqSXilz
-        x/1FUnXW4L3wJRU7CAsBPadqR6S6ySp2K8oSpOd2RR0mLNNxypsI4jdCBC9YG1Katy26nr8vT0rb
-        hjdb36x//h1jqfTQdG+XBbq/A4Pu7gKpxqAPc3RkZMDmoB/SP3pK8sQYuzeTaOOMp9LMl9RK0IGL
-        37H8yk+04t6k1qlGuY1qiImy/FM/k67Lk/S9EB3r473UZrzOpdn/YV+8xSFfZEcFmhML6fkRlR01
-        K1bCajy2BJ30RqMNkcTt7Kfwfj9eK66lToSWUj1hT5bsaqKVtYFldSe/+gknU35doOkKoM5WTdC0
-        2rjidgIU0N0bld1vJ8Dn0GbYucOdT8GNGOgW5D7Z6sOSDwMrFuhUjgdPPAZPZ4i/T4BubBKsD5c6
-        5DfzXICHrjpWWXnrJs8acxAlwyaCh/SQvw1ThDlfxPau1tKp2RUBvMbtB3vrvHD4pwsXSNwfNbrz
-        tWc40tdIQJaajJonl3Zjty0Y6rkwUO1b6B2bjD5CjhufaaymHWI2Et4w85O3Wd2Kqr9/vgEsuuWO
-        zvmUNo5clJD0elypeUsch58WOwZN7jF86DPNEVqi5vC2shJnQa915HWwPHjFtuyxmT/Z63X20U//
-        n9Njjfrx8SRA4uaF8bLcO8JnbQfweYoy4bu15fCJPALImGx6yx0+duyg7VVk7y4HT8y0mk9LIiXg
-        RhOjeB4fwdy4cLhMN+zaVzscLU3Q5XAvmDgIt3bVHcJpAUTNchIn7h6hvR/p8qaUMqzDwXSm+DXZ
-        UIS7kupJXvLpyppEyqSTRDWu9RV/fWQdhpcd0J9/n/2XB18jOHrbZ860LzBkQiavMw9QNfBZ/9ZA
-        tZM869d11d5DqUCQn77e+oTNlJmbcy89D5uGqtvmWK3UwWrRrM8pJsdVx/aZmqCXF4fUqvynNr6i
-        a4Qk/dWQEUwfke4oqr9rekgnP2SfhCjgK47sbV+vI6ck4y7UwXpJd9eTkRJCixoS5WvjAPaxNgyR
-        S1C7D9/YLWrCh8hYxii4rYGsyvLAJ+frCaBpSYK1QyLxP/nTLrFPZHMOjyl3+GDDKxdtb/zkC20w
-        szGHGc890QxaPrgSuNKcd1Jj5U98dItDAsvPzqfaIUk4eZusBVEsvthhwiPk1VRfYGWbArbU0zkd
-        72bkgfAoMmpscy9c0de2R3Peh52jWCG+zq5feBf7J93lw8HhL9HxgGXviOqstiru20Upz3mwt0Fk
-        cHj+PfRQlfn1l8doBNI7oHl9ybo/v1J+XOuqtHwGyk9P8bneBKSZA8epRd8a++7jDKD7CN6qXT81
-        bp7bGOb8nOq3VxsymqkCnODJ/vj31ivEDP3y0B3WWsQiZRPBZbFvqPMBOxRtFRGkpxeZ4vQcaX/G
-        rzf3QNa8/TpiDGvzD58a8/dsyOTHID18jDOo6pCBfBPgXTUa/uXnQnX1dVTpJKKzHuaMX54bMDsr
-        wVoSQDqszk2BZryhRvnAjkD5QYDEeu5n/FQdHoydgax+I1LsK6d0dC07+ekJqqJI4UOwkexfPWDt
-        /K2cb7dQVFl0Nj7d65ulw0m3u8gzf9FZf3X8GroMDau35VH9PiFmGZ0k3dJRnf1DU7HquUjgbhaa
-        R2Z9OjZHY/Hr/+DjKyHVaGlgwBwlU/u2vFScaisR8jpTCNLoNmTk25TgCd0a//KsSd3lElRkI2Ac
-        HjbdBOkZYHsvOHXCYM0nJIQRmv0oWffLvJvSzsyl+q4TvBdFOeXYHA35c7z12LgA66YHucRwPocx
-        /embQT8jAvYz3Hjg8ohPdVtLv34UNU5zX8EM1Tdc8+WV6ld+075YfwpwXa729I+eu+BB+uU1BCLz
-        +rvewNFZv7zNUmPOiDbTG4gqnb3PuLlqQx6fGHxMPcTXYlt3/MdfBVIjElvMQ8L0vJnwiFZfsk4O
-        ssMui/Xml/8Scc4/xya9GxB8jT0pQyVw+Dlza8R9qcfedhdoE7t0HtBE2FBtM2Th9BzlYGv5aond
-        pis5myIpk1ak1mnq6Fk6rt1nD/eyr+msFzoWLk0Boifb0zsTcTj2+8Ufv+8J+auopmqV2dCk+z3+
-        1aOwHx8LtDr2FxpuhiwlZ+R/5Un1EVn4oHarg3L2IG2Ump4wVOFgBaoHDWk/hMkkTYegT3Oodu/G
-        m/OrkF9DnaGnkzv46DPQxruZuQhEP6Wz/0r7/qW28o2ylB7l4J2+ukHVwYheBnW+mhmuxmwrgf08
-        bbDaHMWqnfNykDWbEb6GvcY2YqQj/owqbGrHdzcZ1S6HBi048dWNqa3zL+7Rg5Ye3h+XoUMHb9Bh
-        eQ/e+Ihu1/Tnd+SV8QkIM9NEy6Xr0vjpB29VrIVqelxv8Y/vvA0QrRtKvSWw8R7On3pldJcr0q/f
-        M/d/K0KeSf7rXxLpGW27Yf7/6DMFAjVeQxSK99L8ol8+Yc79xdaaRAMG8tCplz7sin8OG3/VV4n4
-        40/Unz/S5tf/wFZiDdqoRXoA50d5wK7jl4iIW8FH7VpTqSkSEbEm1yWY1qaK/etiE/bqWf8CHoyC
-        DHc3dNg93b1BXKYV/uXx07W2CQB1LrNeqUL+08PZxnDpr//D4pzP+ZPrY80KLcQoxwLat/ELh5nT
-        hXT23/KvPp1q5XY8WI6uLGDj5f3xT0syxXIdrJbeuIcLYpc08tbmce0RwVY7/v71wy1fKanbdCoS
-        Zr2LtpeUUntqGm3U2beEl5eE1LLecTjNfAq/PM/U2WaO7PUcNim/ks1xP/IxzjQf/OtpRxpUi904
-        nMGELJmUme9stP75gbBQG+y6PEJTlj8ZdD7vqbJxmqr5TJ0C23Ghe4Lk3bTpmbAAljeqe5DdR43N
-        eSia82VqGmXTtdLUSejv36mA//zHX3/9n98Jg/f3nr/mgwFDPg7//K+jAv9M7sk/BUH8JxX/nEQg
-        fVLkf//r34cQ/m6677sZ/u/wrfNP//e//pL+nDb4e/gOyeu/3f7H/K7//Mf/AwAA//8DAHICMqHh
-        IAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4dc3d9229b1-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:21 GMT
-      Function-Execution-Id:
-      - yvvltf2fi4jd
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '107'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 843ac424687a30a5c420c14d40332799
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - d8044446eca268792e84fffa9991472e
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "a question asking for someone''s favorite color.", "model":
-      "text-embedding-ada-002", "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '124'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SROySrPm/vsVJ86W/kIGpZKzYxIZlEJwwI6ODkBEUESGKqBu3P/ege+N290b
-        F1ghIWQ+U+Z//Ouvv/5u0irPhr//+evvd9kPf/+P5do9GZK///nrf/7rr7/++us/fp//38m8TvP7
-        vfwUv+O/L8vPPZ/+/ucv/r+v/N9D//z1N2nXAt424cUj7K2aYJuFS69BWaC5GXoe7sVlohYb1I6/
-        KqgFrRFlwk2oiT6jzHzgT/LGf1+se9et/LqEZOxUf400lUmPT2xDVfkZPgCu0bS5xDWyHomEDfq5
-        p9PqXOignhOeGvSjpJWXfgBOcQV0X39sY1BeNocerJ1Ig1e7asJ7lMhCt/Gorst2J10iw4fhFvX+
-        533TU+ZZXoxaaztT3btIXlsPggr5xgyxdt+/u7m7jqY8A05IWTQdogPv5/LWPZTUOGSeMYnMDYAd
-        M0ZW9srwpm7IQ9jG8Ru7Ybrt5snZtvBGmzf2Kk9DvXsqS3B3oov3j6fHxptYl5AVuYTV1jt4DQu2
-        IkjOivmyonXGKL2YDRx8z9iz5iCaw6cAMrfZOf60P78Mlt1Ihh6smbA3PmY03swi38zRxaZ7alyq
-        Sd3RWY7HzZ6MsuN10qw1Kpw97koEx1cr0R+pBXeh3fvrztBTCZdmCaK73eA9f+0ZSz5joeTnl0Ot
-        07f2mKjlBdqFIofdotlU0+jYLzhqk0i3LRjd9NVhD1vtjOg24d7GwF/WHMRr40VmIrxQx18g2Sjv
-        zsDO+ftBU+aFofLMbgq+Vo1UkZsYWco+W+2IsLsLaG7qjwz2kGb+e6m3meZdCeLhdcWH0Aqq8WmI
-        L/jMbPZ54m6ZJMpuA2W/d2iSSCdvngK3hkGGNTXWuRkJq2oclYlueuzgzK/Gts5CyPTQwep9lL2l
-        XmJgl9En0AsZ+vP8dk9VwxFuTTaflTGB/GafsV2ITiQ84Wkq7kcQqHqY045uNnKOorg+YS3KUEfC
-        0e/BdzkNa+dW6Hpt3o+AyqtBFMX+onb/7XJYpzX4RGZtNx3GVke5X+X4UN3eaAykTwBeGgQ4r4Xe
-        mAuhLaAZTm9sjXWFOnXjleCNnyvWm0/nsdPWbYCSC/In/S0bUyVEAL68+VJ8SwLEqsfMQ2MFAb0X
-        NI5m6V6OMITeyUfXA2cQuxxVKAK9xF4Du4i83HpGn6/88LnrGFTMOfUXdDj3X7yVkdIR6zCXq+gi
-        bel2qSe22iUETSJ3xfY3lNhYC4cYVPYusSY+hK6/eRCgix1ufUe6tmysjdyHbbRzqUNjr2q5l6XD
-        IHNrqov8y+ij7U2Hxzkz8LZVVt4svK0RWpV8qQ6OgD56NTQw9o8aG92nrKZP3YrgSvOOumqnGdKs
-        cTKAflSxc00HNFTGa4Zd2r9xut0cUiLcZQ6W/seHyXErhr9aplip2PlL/bHpuO/20EvFTN3Cc1P2
-        rrkMTsfbi2pv78VI4/oxHEL3TpB1gYo+hGaN9rcY0Z17/lTDoTwGIId3h6xuychYr8cvdO2oSCTJ
-        qVl/S7Y64MLTfUkcmFHvuY0L9eOiLnjVVH/qd3M/MvrDE4peWQ274476LB8Ra/thnyMwdew/c66r
-        erjoKnqvEgNv45PU0fl9v4DdvR5U39r3aLYqdY/K5yeiO8mxUF/AvFbQywoJet/Eboyi5ygX51uH
-        nZ7kxtjqCg9Ca/lYO52qdFL9F0HXw9Om2jpQI9HI0gwdY7Gg/vodoHFfdhZMD1mjhj8rKXvHA0Hm
-        Omuw5m1Ggz2MqYeEyFuqc8yIhOO+2gP/PA00C1LMJnTPfJgEbFN1zZ/YeI2cGLJebqlDYKmnYXrB
-        xGKPzOF654n2OntB9Oh7Mt8shPqpLxoYq/cKbzeOVPU3GhIwTXjg/ZtsPVIY6IJSn9epOn9QR9zT
-        AACkHSkORztlTvoNIZ6blAhfb+OxpX7WepsZ9L66VB3rB1eUl/4gkue7HWkeJwu4ihHqW+reE05J
-        NYPzWR/oWc799HuQBBGis25TJ4vGiG42c6Z8xCu3vO/IG6Xe4mCjuDrFDaTdlCjHFrqTTf0Vh0dG
-        7mEWgiZ/eJ/neT/taUB8aF/7mV6LZ8Lma5OU8JbNhsYoDww290kIgX+lhA+ye9XnxbNWLL4NfJES
-        8KbkiXUQG39DVmL/TqcHTAES6lLH2mXVp62sTiZaK4GNz0l5jBY8UtEUZT6+y9oesdW5y9BwHgpf
-        9s5OOlNd1+FuKCp1MvoyGns67VG8snyf52wzGtvH9SQv/xcbh40cTR+0Ln98gHcruzaosknMTULW
-        W3r6KH01To7rw9E/fLHJvVk1Fp5BQHj6H6qL8Rh9yXsOlUfgNhi/BYNNxs4msDrnMt6yePZI8DUs
-        OIT2He+G+FnNNb8BQGQUl3412ai1IwdHOH2xHh9iNkryg6At03bUP+3NTljblx6c10XD24uldPTt
-        Zhzkhij7Vn1rq1E7dyE0h7jBjyRiqH8diwCS+aFg53SajGFEfovqGa2x6fo2Gq319wRt0dQY35IR
-        jQO6jQA9etJ9shcMGnuiBXfdNqi/ySPGctJxMK7AxJnS52nToS9A2R8l7F0PuTHfxNRC3VgWRFw7
-        NF34Pvv1z8LHt27cW85r86IfiXrMKdKJl+sQ8Ff/0r29fkVzE19dsL22JFI4XQyWfaQ9Kv2tQ7ec
-        rHtUVdVCNqdLsPBX2jFZFW30FssMm8Iwpb3hX1zwdSuhbrjm2XQ4GDXE/CPGW3dXVSx+GiNMUwt4
-        b6uAhoXPQLBeW5q2ZPjhjw9pUSt4Ow6OR73TyUUdb/V/7i9qVVEj+WKc8XaLwRhpv+bRRuI/1LyN
-        UceM1ToEpbQkataNgIhV2Xv5hy+m9LhGhOWGDVxxKBf9I3ZTEnIBXMr1B2sPye8W/CFKuykOeAdy
-        n/74SDG25ttfm2rTDcmN7UFvc4PuYymP5qsJFijVhsf2k/bRbK2+BNH9S8O6osdoWPQeqi/ZjfTO
-        mVXkUWT8ZuEfrPN1Gw1JKIZo6+LSX6m7As1+mV/QLXzF5IffvTwjAvfdc+9Lnt9WU/xUT8BWXYG3
-        ck5SZlqIA/nuDFjdvWo0d7UqKjfRepLV8zYaDF08EW78OcSH5FlVw+HgvTYkozN2HP/EZrcUCbK/
-        UkAxdc9Rc/dSGQ7SoyLcG75eq2VVi8x13tBDaI3V6I9diwLVXFHDmstuOG7rAG3CD8Z7BWOPf4b4
-        JLEpHknLOzYaz5zHgyZpDRFPhzklTHs2aOlvalem4fES82S05pMnNbZ3DzGSP2UUaLy/8PPTmw6W
-        38J6td1ix7jTaHbXZgyHzX7GNl59uoG/Yh7NonjEhjXr1SjYT16+7/kPvmzy2qOkn1swD4gnMseO
-        xsywnMAZlxX1PyGKpv66WfQXaESoxE9EvcPVh099iiiGe8s6cu05eY7pEfsXaeimyzMoIde3HcZB
-        6Xe0uFkWFEfpQbHA9Gg8b20eXr3RYeP6fRnDbI+JItSFTviwlVICaiEr78rg/Hy7c7y5qekaXHSJ
-        /JV7FlICc2Aq2pOU/rjofWmbOQ1o2c2ij7Rpq9nKvAAMN1YXf9EZ4y3c7JGhlTe69FfHclIBWn4P
-        e2utZMxLKQfNK+eou7wPngyYyMJrZthaOziaNT+Uf/VDpKq5dqxDaf3Tl/5YNs9uvgtyL39W+E13
-        Q6xVnb4zbXSKXEbtztAj9nHN+fd/Sb+SY6OpjYuPvoewxN72fuvG697Mobi6MlkfpoENmeJkcB7o
-        ER8YH1U97DYB8DJeEd7beYjxdtci+/QUqPnYthFDO2QhUvhH7B4rzhhl28lAPu1jbD3Ge9ffRcsG
-        6MwXjmVnk77F16YEJrINdZ9KkI41uBf08yvWufx6s9ZCgha/5LM1iqq5PqbFz09S7ZoWRvc5agRd
-        HQ4wbgB1DevjDNiUjFS/bdVIOokTD9enFtKjrFspXbWTDaL1HKguIM0QDmOpyj8/IqfRDpFXLJWw
-        +BWsVtsAse+Q6ujnJ3biwLzxGe4uoF5dg7yEo9LNrwefQ0nHsy/mUlIt/qpUBJMXsf+gGI2C1sso
-        c5In4X58EFFYwy2sYyK0BWXzS3Bd1J1cSh13d0WDmgk5WkvcQP21rVWUOKc93IVmj+Pz6ZaSwl2H
-        SLJuH2wzZHYj6uoa2k15oHq4/njN0s8oph5gnZIPGiPJ9mVvvtTUW/zAhLqe++l/sgJNMige7yFa
-        5Zcn4U9pacwPEC8/v4dxEkVs0Y8zSCOX0t3L9Lpeq3gdXqvC8aPL6RCNZhaoyjtxO7/3qiEabyIp
-        UEUHxZfoQiDz+3wCVBQW3kXtxhjt1k7gxl9D0vcCoBn8TYv660vA5ue5ZqThvyOaL+sTdaVg233f
-        YJNfHoET7fXyRkE+6jA+J/3nn9Pp/KQxdJt4R6/8Y5MO81Wz4ev0F19hPOumj6tdQHsHhJCsYcaQ
-        FGsbLfxLtcE1janTexXZ2CfU1C5WJWw0VwaF8RZOrbPm8ZFk7yEPQoIN7E/ehMcbjxQmWtjD7Vw1
-        V3NsFerHHN5R91M1VhU18NM/NtOfVd/qAg/1hitJ27jfbuidhoNLcxzJO7RKRL98LcrOEF2wXZmV
-        N1+VlYmeyUel3nYzpBSn+IXkuzdQY9dtO3FzubdwXfkn7NybnTcPQcmBh/yDT16fORrixEvg7oQp
-        PiRciEZQ4QIae2T+2H5UJpZGZ8udd9zhpT9S4eHppvyQJ4dujy322NyHAVxRYxNxMCJvvNJyjVTJ
-        IYTl0b7jf3r1uJIFf2DxCo3aLinhEKS+v5LeTUp8bsXDFbU2dTj5kk4jshqoHyeV7pRLYYwTgxwt
-        /Eue11Q1psNY6sj14ou/IXBlY1O/cqhX547afhswNmprHwWa6JNqihuDrnYhgbKPJIw9f53Odf3c
-        wyPqebwrFFKxQ6quUeu8AprvziViT+hLGILTFbvc5Yl+fhK9IzUivZ2NFXVKxYIw31XUv5s1IulH
-        dtHPn9q4ihjbrhoTrDh4EMmutEoQtciCSzf7ZLxaU/frV3jRt0RgIA/GlF0pA5PDq88HmVL9yQOg
-        3zyxN6K6YxUxXj9+IEppUo/x9+miXF/vnAjBtPdmbXfmwEp2GVaTr54KnSOJwEWzQcjBatJx/xXl
-        jWGcL/QcVuGSB6QASmlK2L1xk/fjMyTfPk8ydAIfTV0AIzTmU8MfJzMrfvGTcLoLVxzGhxiNtZva
-        sD6kG+ycDydvuoiKiQr5a2Dt4H88olVShiaWePTwbNL0uZvCF0T31Z3wQqB7otG+fEAvM6S3Jf+Z
-        9weNg46bAl+22yKdG6TUaH24bbCpXepqCp/rNSIGX9Ddgg9zg4QaeWdOoFvLfhhdn88m3G79+POT
-        6SzPTQgc61Xsb+RPN+7Xuwb0pufxuYWqm1ad+YL8XDt07+021eCdAiLzbPf54w9nbXNwN2c78fDu
-        p4/HwObAwVaz+I8gEqmuqwp2zB7/+ITNWqEq4qsd/JEZNJ3d0xvgndgdNdV8ZczWFAD0t3TGh+DU
-        Vot+DaBqPm8CXjWkYzCmGVr8BrlQkhlMV/FebhwxwzupFo1hd9qYP/9M1WfUsnl/cAA2D01f9Amp
-        xiZOCbo8vdjf9CT3Rnd1GlGj9yZ9LP01GTuVwOrqO9jM97toOi7s2DSG++MT1Kb0wCG7jkyy7sw7
-        6u3Ky6Cs1wQb+8o2BKKnIlJaLsc7u9I6MXwKHBhVFPkrbWMxtvQDIoZYYF/tztEXXdRYWfJEvAPt
-        my76OJBD7TsSw5+ebBR7O0R+cLT9uaJNx74OX//wnuYb7VXVv7zP/7qU2sleRcLneLflHvgD/eH9
-        EEaFC/GI9nRbPoOKbKePiOapFKmXU9/45QW/+sC/fEMEtZGh2tsWTqTgXX0ft0QEn7sLpGm9BH0z
-        cV+gQ/4KaHb5fru+G44+OrsHG/un/asbH7dT/vMT2Ky9upsv+50MWls7Cx9evULLmj1i66dNuEu6
-        YbPAriWc7tKVOp6aIGZNuQpXHF6xlTXvlITbLINaKQl2XXXuepZfahiy2fU3h9bu1m2dBWAcuD3e
-        9YbLhksS1XB6rXV8mOobm+LmZMP5JbTUfT6hIhGnvuA+W+ov7+4Eb5x92Fy8lIzV06zmcLSI3N3V
-        C9a0XjKYmrUq1Gh6YPz5OGxmct+gJR/Gtqk2FWmO3gm88X2lxuJPpuS505HrQ0kXf5WS/HZc8Hwt
-        YGxXNBpvpnSRnUKoCL/PSkbq+ruHDUqYL6RSY8x7brIVWViFPmvDjvXlcZ1BH0YJ1WWeY4MzuTGa
-        +muBva/Q/tFz0OjExFaeeGl/frYnGDJp7V8JiVhfD5vXL//DWJm1StyPRYzuasz7H9UmXZ96L0s5
-        ZJKG/b6eOtJfxRnOzygndOAN74fPaMnfqbqdCzY/vJ0Lu9frQK89HBjzDvYJWasTj63d/IoW/34B
-        2r977J3Ks9fDpsihOKcdmY+WZghhVNiQbrl0OW+mS173gma4vKn2ogv/l5oF4YOfqXWovmy8NfcZ
-        4kvYkttDLBY/Z/M/fUut7aut2tSjJUo4NBImB27KsJT4KF5rL3oon3naP26nDM71a4OPIvpGpNXb
-        GM3HeoN3wWo0RuMcmQBbaU+KTJL+6BVQj2KD/aW/yM1reLToV+yft7tO4nHzgjitt/70CjUmrud1
-        DoavyYTLxR4NC75DCH7lo2W+ICVmYqLr65Pj7de7GbNwEVV4y1aDcboX2UzRQf3lYWRzKV0m5ERK
-        ZOsRS/TQCadoXPwAWrGu8Zl/9j0q36/tD+/org63qbiZJRt6xtUEsgR707tmKqyt45NMWVRWZK1p
-        oRL0OaXqKAhVf2vOI5R2r2Jvcz0b02kf6bA6yoR8D23TTeaaq8GTGo1mWUK9cddeQ3mNyg1e9Jwn
-        +pwkImtGmt+/ydagu0NDoEiohQ9ap7O5u64t2B6DAw7CtjKmH5/HqNQpVncqmq+KZMEhuPnUsjZa
-        JJwavlSWfAY7xOBZ63MFpyx6GKvby+DNnP/MYMFnf94gxIhZBckvD/W56ylD8wO4Ewq1bvR740W8
-        6aLIOvzmI6ZY8+n0GcTmjx/VCLTekkfnsAnGkC58bPR7y6nh/DzmFCvzs1vyLoCfPtSd3ZPV+zTp
-        IX2vY2qsEetmTo0JsOSUUPdY5QaNzTYA3S0tvFNfZTrlBWkBF47+y8eqicegol3j3rD307vN8Ex+
-        /U63raF2PLu646/+CbUt1eOFt3cCVy+oj37v53BSS1j0Id3F2z4dPse7K08aWeEl/0Lj+lImQMhD
-        oy491hGLmhW3WeYT5LPk6WyU0R7UaX5TcyW76bjg789PUdOw+27JA3vEhSpP8ZKfDlXhh7D4c2rl
-        klyxZd6ILp0E/mplMzY/ikz85YE0XvhmWlXrEU5N7lPjehjTSXmpHMws2NKbt1EYPUhtAvApYyKz
-        4cTmiFNrZdGv/zXvOIujiozelfHeeBFjmRfF6x/fLfM8b/LSV6ngbVH4QgtVNXwGroEXMy+/51fx
-        tF+Lf/JLs0jAaMPovYe1FT39DjnIG2Z7HcOSv/ss4wQ0SnfRB27iJgJRua94e320YSwMhv0JNSnt
-        nD6GZ/JW6T7lUo8EUspDEgwGdrTOSYdcgAs4hVT5SvnMo0X/2BC8T1fq17c4ncx24GXN38f4/PU2
-        xjBrLEef+hL90edDEI0XkA7Vyueu0TOdLvQb/vCafIQ4i/if/tpc5ZbuCsWvyG++8VV5Svfpdu0N
-        n0FsofmOt2X+03Xzg7zrX/5CLs3n1ZGb2cngDl6AtXdz8v7knUo/pdT/6fWPu59BHMoT/um/ZmJ8
-        Jt/QvcUuiY2IFa5wkaV7fsRG8ayrybFi96d/sCVfHYPclEBVlvnU8nyQQaZrnqD9eD8SxmqN9U+D
-        e8n5tpPwwWl1o9Fmc1Tc78f04R0e09/8FY4Y1kS2/X3VeSs/hms3iEQRcy1tUiUN0Lz++oQtedp0
-        ifIG3icpoPuXoHvSksfIxrB2aCLoHZv0qvX/zFP127aImmHQVLT4dYyft9FrzluVl4Pd4UptpGdR
-        fzXXrbzMP4kAfZOyk7jhodsqvb++jQdvjLZH/cfnyzyH8+beqVX0yze97X1T/fgOHlmd+tTz42gq
-        yVUHFu11Ih2zR8Tun+IEL3lPqJnvPynNii6Bv39bAf/5r7/++l+/DYO6uefvZTFgyKfh3/+9KvDv
-        5J78m+fFf1PxzyYC6ZMi//uf/1pC+PvbNfV3+N9D88o//d///KX82Tb4e2iG5P3/XP7Xcq///Nf/
-        AQAA//8DAIhgdPLhIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4e0bef3e1e3-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:21 GMT
-      Function-Execution-Id:
-      - yvvlf6849c5t
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '22'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - f7e1aa5667d824ffdc22c9b3a2311546
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - e80be91cc8cb1072e124d8609456adff
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2940'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: "{\n  \"error\": {\n    \"message\": \"That model is currently overloaded
-        with other requests. You can retry your request, or contact us through our
-        help center at help.openai.com if the error persists. (Please include the
-        request ID d18e0d0041203d240f04766f9875bd2a in your message.)\",\n    \"type\":
-        \"server_error\",\n    \"param\": null,\n    \"code\": null\n  }\n}\n"
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc4e50b34117b-ORD
-      Content-Length:
-      - '349'
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:16:52 GMT
-      Function-Execution-Id:
-      - yvvl5uno49x7
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '30011'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      X-Cloud-Trace-Context:
-      - 559387b6907187493804c27758732019
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '88794'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 804ms
-      X-Request-Id:
-      - d18e0d0041203d240f04766f9875bd2a
-    status:
-      code: 429
-      message: Too Many Requests
-- request:
-    body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Write
-      a concise summary of the following text:\n\n\nLITERAL TEXT: \"\"\"Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum
-      dolor sit amet\"\"\"\n\n\nCONCISE SUMMARY: The text is best summarized as"}],
-      "temperature": 0, "max_tokens": 0}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2940'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA0SOwU4jMRAF73yF1WcnyhAGgq9wggviilbIsZuZDna35e4BVlH+HYF24fpUr1RH
-        oAwB0hwt1VZWV/fXcksHbUI3+nqXDm038kN9vJWHpYIH2R8w2b/HOkltBY2EwUPqGA0zhOFyN262
-        u8vzwUOVjAUCTM1W2/W4sqXvZbXZbgbwsGicEMIRWpfa7NnkFVkhjNsLD7/un3248mBisfyS43Dy
-        kGahhArh6QgV9b+1S0EIEFVJLbJ9NQob8ld/dB0bGhm9oYucXcXIxFNBVafWiScnL+5delaXpFbh
-        8tctitlFddG1EhPOUjJ2R+wyKk38LWrLvpDOxNMaTh5eiEnn545RhSGAmjTwQJzxA8Lm9Od09gkA
-        AP//AwBuqeKNhQEAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - no-cache, must-revalidate
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc5d8b8a4638a-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:04 GMT
-      Function-Execution-Id:
-      - yvvl7ew5uk02
-      Openai-Model:
-      - gpt-3.5-turbo-0301
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '3176'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 78fb317ed136dbeb23921ccd45134139;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3500'
-      X-Ratelimit-Limit-Tokens:
-      - '90000'
-      X-Ratelimit-Remaining-Requests:
-      - '3499'
-      X-Ratelimit-Remaining-Tokens:
-      - '88794'
-      X-Ratelimit-Reset-Requests:
-      - 17ms
-      X-Ratelimit-Reset-Tokens:
-      - 804ms
-      X-Request-Id:
-      - 42784145c7d38006e79bf17199be9178
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": ["Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem ipsum dolor sit amet Lorem
-      ipsum dolor sit amet Lorem ipsum dolor sit amet"], "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2778'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6SxOyvJbufP+Kr74pZ5eIQBZ7htzkmqggYlfXKVEEUQSBhEtX//dT+O7qUz1x
-        QGIlkLXWc1n5r3/89dffdVpmt/7vf/319/vZ9X//n+XZ/dpf//7XX//xj7/++uuv//r9/q+ZWZVm
-        9/vzk/+m/wafn3s2/v2vv/j/efL/J/3rr7/v3R7jxg8ibzjqkKNN93gzRz7WaETwGGAqqMF88dR4
-        AzaPTyhfekJXV0nV12Jr2xBwGCgEKPA6gSZHBI8oI/apx+U6z0YM8nzs6XQ4lel8kmcDks+zJI7H
-        duFwIESTeyWnzG1aaa7lbjqizDcylonvYKavu54pbdkTolOgbU8tuYLDrgYWTGsc9q976iN+wBz+
-        0MnV+/1h85V/+91l4lPvq0vLo3A8dnicvG0q+LF1hOvmJDH7/p3a0ceeDNq6vTH7VRdl7/hNjroi
-        DDCyozCd8qzJYI1snQXhJpjnx+uaQX0pHbKd4w16KY0rA4ZCZerw+rTN/SPH6K0IG2LaZtDSKcg4
-        aOpLydyVpLVDG3iG7FSZhBm5v8rpMh472Et9xpwW79ORywtVER5tj+XC2KFx2gxf2FajxojcDx4V
-        uLsK9Sf7MONdn1qKteYrqW/BIoGuvOfBdUQRTeFUkd/5zc8k4eB5cjk69IzTZ/tBa1SBi0jgyQ7a
-        FOklguf42jPHNnApbFD0hW57U1jSDDd9Di3zK9+Gj85w8G3SziqzI6QDvtPKOavhfJv6GNSzWJPo
-        En9bKs7aE03WBxOnGvR5vNCnBffV/UaFBLbh+psEPJzu8R2DYt/KuT/0FcQ0vODC14dy3EuiD44Z
-        BcQrVbucofNU2XKTLRZy6Z1OJ+WGkfS6hr/zDOf0PdwU6ZWExPGuedgJwvOqxDAHZOvJXzQdDF8F
-        TVBEZrkBQaMgXGs4vK9fspPLrqWBmhzhyB8Mgp2inCf7xmnyi8Kd9tOahkPv3yzwCu2BW8HYeqO0
-        WavoFz/kE+3bSb3mR3n69DLxWofqs8AFR5R9X0es6IqJplC/q5AaxYF4AmV6d5aNSOEPzCVaf+Ln
-        CcbuKZs9x9iO7UaPltfJUoz9dSJbFCI0dK7bgZt4iOltNJYzasYvqtEFESsOpXSO+SmGva3eWLoT
-        rLY7bFsbQOGPJB7mIJ15jt/DVF0ysn3Uh3S6NPYL4MjuFF6fZzujRqohl9MaCzt9lQ5Ko8mrdpA/
-        eBDVUh/fR7WDraNHxCkPXTgNOOBQLu18gl3NTwcB8TZMVZrRwZnschJm6Yn2TiSSHalrvfPi94Su
-        kdsydRkf0QZrkItni2xbekXTebtRYZC2e2bt9EfaGc1ZRcv3JljR5ZSetysNpea6Z3glluWIPskE
-        O8loiX/xPl5JjjsbguKNSKaZddqHgiqAJWUecTXSzRPZoQRMdU7wJrxZrXDr2wj5K1kkVrZXwsa5
-        mlfohnJHDO1EvcEMCw28Z4zoylSztKfbmkeHS0FJEJ2u7eBbTg4xmd9Y4I+veco6iGFo5hgLh3W3
-        xI+gAXc/aCQIYzMdPauekEEj8if/vte5s8DPvyua33OiD1XU8EjddCJx0oaFzZldLCCbm4XlqyUi
-        Wp21DkXKMyA4p1s0HsGp0HAJVILd7ppSvYgSyHeQs91S/8ZiWPEg3D8eXaerUzpCkWjQrNU3wYUk
-        hmyXeDk0E6cTN4iLdMSadIVwxRGcu7Wozzy/nxTpZF/I9hxb4TTJzRFgKnriVY9cH3DQfdHO7kzM
-        2rugT0P4oOgi6WvKZ6dVOX2vwg0UnNRMp59d2xmFL4N29mq84c6tN2i3rw0rh0bMh3ldtt/TjZPa
-        4tsT1y3OaEjn2wv0XPWZ1vFdOGgv/gjl4ZpjwHvea07rgwC/es9fnp03HLkvhfVqfccLvvy7HqgX
-        xWV6cuHmz+99T/6wI2n1UL2eHmID0ImtqRikZTuZafpFWwsmFvhJ3LYfXPMgvSlj2x9eCPP4hI2r
-        3Zk5q+M8vl9CDGfnSjB3f43pOMqSCvWuPlOQ8kfZcW10hOeO5Mx9dQaieB88kWw+V8S6ozikaX2o
-        IJMsi1hL/aR54wPyTk5J22e7LccycTJ46ZuauVjgUI+1MQG13QCdp9Ty2HZ6yKgb1yXZVWvL46M5
-        wXDuJYkyQRrbwSZSDaqT8Mxs9QD1RnypUe7qGnE20QV1/Vas5PTghiSQpymdI2XOoLCOL2J011Lv
-        L80+BuprT9oLjT9PM0xf9MNTvfqW5Sjo3AsprIiIF5knxObNwQY+iz2iFa9jOvLG+wV7q1PZISoU
-        77u8P5xoLS3rS3OnPp8y7OR0R0F7HNrhQHYqGJz8xkKBu3ASB9cF57Le4CqXzHTBvxqE25Fh5N9F
-        RGvsVGizmTwKJ23b9pF49OENz3Sp537bSxtFQ+m7VZjOCXE75JTzwXhYJ8ytrTicz+MIEOFMJwbf
-        UX3qnRJDfvav5LZzVmVlB/aArmOkk+xdnMI5FakFAbhXYr36ch5uw80Hzkv2JFrinfrec0DO270z
-        22oErx9VjYenvveJfkaTPjlRK4M+tQbBjXALJ7JqfLCv5EwRO87l6J4DDdjllVMZC9k8O45Yww4z
-        hDf0ULTj6ilfYXzRG8MX6zX3q9Z/gsRzDZV21XbujhYvQsqJKh7q9On1w/5jQSJaEh3n7R6xc1dj
-        9M7UD4UD89oN2wsvCJYd4PvrEA7q/eCC0ok3Fu5v17mnvhFD4p48ot492xu21/2A5og9iZ15qUdv
-        k2Kh6bTTSMCeYthLU7mXeU4s6EruB300K0uE9nidWWCT0Rs6Q+SgSlVC0nP6Kcc9DBXCjWwzLaca
-        6ovCff3qEeVjnW+7XZDvUXyNTBbm2xTlu0Sf4Fh2lJjpah2y2VAM+IMHOd3Ow6geK0V73jDLjtE5
-        /K2v7FytIDt6KMo/+JQI6pmY3uuFxiq6WrBmhx3zFjyf1R67YHX7mVgL/vVlHr7A45UZj6lrzHyT
-        3jk4ai+NZAdHRd37c77JWtHZC97V7eTedsv5VTnm6vaNvulaucEZ7Q4U3vdJH21SiMpXf16I1a+5
-        dJbWhi3PVkCJdpNf4ahOmyvqO//IiF+jcNZujYjmOYjx4O5YOe417Qq3/TTjVVh99XHwTpHMtX7O
-        8CVt5+kkuhks9YAFXDXMY9IlnUwvnMq0+H6fv+KguaAot4kRdduk0zPJO2Vr1jEzW0kJ66O0hz/4
-        YeNK9uYN8kW04AEzy3SYu2TLnghWLmXmWVVTIXt9fQlnuk+nSMnTBQ9q5BdKigsWHNPx/egqlOZJ
-        gAfnvm2HSyvd5CqwRspv29wbXKLV0JokxYonN3OvR/YR7J3qUMWwvJadNx5F672OsWxSIxyCkzDA
-        bSUAU8WTqwtIEuof/8YrQTqU44V+LRCy04EZ93Ysv/rNrQFLtsZuTXUuZ4doV0BReiF+g7iWNsnb
-        +tVP5lX8Tp8e/CNDBa8diUPK9zxIojGhryWdial/8nnIntsY8X1l4uHu1d4wKVcXLXoGKx8ZpeP9
-        mb9k7zC8mbk/i+30rO8c6h7JlSV8XOvzaL4s+dwjifjgfMqedzYxSkvdpIh95LILVbDRN/YOmF/q
-        76tJTxxsvEhiBraGlm2G5oqSargz/eN1+pwOKQcft2aL/qFhb52+9R++ZLYvIR3pthYgT3KBJcHw
-        LfvI24nohK0SixZ318caXyK46q8T0W2XIXab+gjgEWeEmGoWNvfesNCit6ikKrJOufJQK6GxuRLb
-        gc4b0ta9gbe/OWxnqG1Kgb5ckE7uhU6u1qfjtuO+v3zGE39rwlGP7D0ox7OCC26a0+7ehwKo8csn
-        WwPAY3XJeElsHgEz6spof/wTLhfypiuvqTyadXwEXL9OmLuV32jGqprD+OpulD9cqvYmd/Ie/fgJ
-        XvJzoxVzDfu1ZpBAPQbefBldDpLLx6TDdm2040kpAYrXlBA7xhv9F3/S6ZGsCGnvgkft4zEHkytM
-        5geo1ztmpTEI0m1HLrbM6R1qJFnWZu1FV61NvFG9DpqSyP2IR/VI9RGKvabkKeKJ1X0/aNCjvQaV
-        N5yY30lBOynVUVUuZ+SQXTgG5VSe8khx1nTGz/sQotk+agM6RELEdmq/Tqne0Byy4CoT15Jk1HP1
-        7AJ9KAJeV+8inP2Ek9Exyni2bY3uN24DwZeJ+MeL1LKs6yp5frYqczXizzM3vCfYb4wKK1dOSycj
-        u6mIJ8KZqbAS9e5zaDJQheRGtKAw5snZ2Rq8OHz+4WdKkSR8wVT8Bk9OX4W0yGUexHOVsm3G6eHU
-        mupNqdN3S7apa6AF7zAAfSXsx2+HSA+e0LP3nliNN6TzMy8NZOafmnjscy2nr60KcOOeOfNPpesN
-        BzjE0Oq2xPDByefxp+fn7TNivhUOHuu3Q4y+43HHtns/1scgYQmsgrbG+8P13c7rcZ9A9RUe5Kev
-        mk+mVL/1KDtf7XLhZzkEefhY6qk3T7NmZPLTRAYen5Wajk2GX+iVJTv2429LPAFo6+bGvBD23riW
-        Qg3ceP2gPEStPj3vcoZGQROp8BavYdN4e0AzX05YkpRibtvdaCl78aJhQdt7aA6OgguXdb1Z9P3e
-        m6qzRmHJP5zz/qusV/chUX58+MAdXDQ5rn1Fi19AdF18tfR99SxY9sucXbVF0+oLE3yfakA5zaxD
-        asaODPSbx8R1ntrMm8k0Qd9BQqxuhVGXsR6DuEla9lCDL+r3/ltGmH6elMcD185VPAGwqwgk8C5F
-        OkU2neAS5R4+qEfsrZf50OquRCXB0cP5sP2KYrh3VSwfs3QetC9W4UXcgATlvg/Zqg6/IK/RG89t
-        dChHKyk12KSI/PQ36vOXC2g9ejLTp6HXxzwdeOUwxzbzC9v75ZcKUpyt8beLtmjgKu2JDMKnZPd4
-        7r1BRIENh8/dx7R7vNKfvoJZEwYScIcGjd7B2KPg0dvEk4OqrOVP/UTrO7TLeQ46rfMVhnl13DKr
-        LrSUbR/fI1jy9GHujanzmjf6CqnOladr2+zbWf3wCdjBdoWb8uCnbNLaDuxKuDC9Wn3LsfH2HDTv
-        qSUB2knpfFINGe3Px5jZA229MduwCrryxAh5aGbJf2KEYYxsC8sFXaMXSB9b2rlqsdQ/E/GTaCeg
-        mXuBGXGSttO1sjHCTOKo0K0oGg8rh5Nz+VIzrLE4nddjkiB2UzLybVoJ0aqosLxLI4WcZc3QF7wC
-        cJ80XfhJlrL3baYQBEKM5/ButkMfVT6sOu9GhS0rU3ZnHcAzKQDXFqd4QwJ3CspBL/BhyT9We/kN
-        BM4rMIveq5RNq/IItmCFmMKlC6e1xTDo2zyhw6I3x2e65WH42BnT5+rWjvePHMHGplumaaaT/uEL
-        VYe21GhuvNc1+aeDexYPxA3aOvyYyfREW77L6Zo+3+mgDnj46W2ytx5TW3WabcEfP2OQaNlur/sn
-        EHS5ErWGbzml6/UNenTzcbH4Ld2jed3QZRfNtDA+a288s4OhHN/jfsGHWB/0SzOBFQwrjKa91vLy
-        p84R8TSeBcYgtayxcwum08amw/seet2C5+ijmBusGOmxnUJRyhCGUmXGYYnxSW72aH9BGPM4PZdT
-        p6mWPNzeHNFcLQgn6SNqMM8kJpq+X6EpRQSjCx+nzPO+b2+8fScKan3jFn6OvCleuxay0u7OtHva
-        zeNqyPboVpwcug57N1zvcuzCdQbEjGW9bl7bGmjvnUXcOi/D0bPyCY58aOCjK97m6aRVKpQGsbG8
-        6NnpOr+sX3wy68RN4XgT4xcs/jGz4zLTu+01GeB43kzM1V4zmnZ7x0VT0RlMf5TMm6tXzKN7rjQM
-        K/o1pEYoPkFdGyrblmOMxo2yHv74RfaYSHqXbHQO9NXRJJpVnuZRZk8ZEpmNWOYP73lo7DoG5l9s
-        vN7BDtEBJUd0qOwBT5l5ncfbO+dgyVdifghJh5N93v/8Kcwv8TTyziqGIvI1dtmhev627hWLPz1h
-        Vu9tyCvl6MLzlYgsgbDz5nYnGTK+fjGGnfNoh/LJU7hO9YN4JCvbGttHGSWOxvDsre0WvY6JD6v0
-        bS365ZR2Pk6/MGv8wPx7TvXejfxaytcUYxmwM3fvp0nRMp/dNw9I5+xz5UE/PTqMWgd7g9zJR9Ds
-        lsffa7qal+9rgxffV4R8s8Kb6PZgKAq+1rj8Zpq+GfRjh8LYEYgR7Lf65v52MrDbYmYW6J90lL8X
-        G5IrKoizq4p5QJOvAu0qEa/lcDe3Rly4KHlnW+IooxpuvvePAcfoxhM/qCx9PZlRBX54/2Bu0V+D
-        mcjDj+9g7thw4WSfX8c/fr2mEEBjIkGFsiCR/+g3dpFOhnJ6XFd0Y5+Oafd68DFsLW6ib+HRpP21
-        bSgs8UvMs8BQs/ArcOfjyAinVt7iN+ZIUR8e+/nt0+198YHgdKIlwlLZaefkCtqsvpg/9L4+X+db
-        DGNtXnFxjqt0pNb0Qgu/ZQ7T6DxnIxeh9N0of/oNox6pe2Xxu9h2brn59Yln/PMzmJl+aTg55OhC
-        c/JP5Ie/vJn5T3TLuj3RlvzpHx8vAj5fGbTQlQqxXaLnEL7aLxUd8L2ffoWzeLuQO9uSeYjmxEev
-        w2gx7eQU80gt+YUs9SKy3YdPvXFStOTH3/79fy9dPeVdcHkwhxZVOp1E7QbtIH6Iw1m7cO0c0BF+
-        /MiHjJaD+lVUNEj6nnKH7IP41ykRwMTug5BdrpbCvMlluJwlh2j8OKTzJ5RfkL5OBbP5Z1MOyfbz
-        BD5XDKYNoY5G92yqkEm8Tw7G5+RNe5I9EWvvR6bvOt0TEN+J4B5tE4+70QzHCB1fkFe3iJ3ZTfT6
-        M/8VUPtUHGZX9kMflbJJYKlvuNGnMp1H0Xbh+WYRlq/pA823Pn2hh0grrJT7IF0v/iXabFSTnLnu
-        6E0LvsHqevwSO+dLb85bpQItygfmitc2HWOTuPISr2Qrc9E8xFOB4bXKZ0aifRIOGntM8OVbk46E
-        OuF68c/keRRlzL2eajj88Mf2+hIfcX5B7PE6ZsrS72HOOW/m4dF1PDg7xWQB2zI0Sb0zoXeQHYha
-        RH3LdifPhZvhjWTpd6HFHx9g16KQeUbOo28ojplCbuc9FZd+1FJvLOg7LmGmXGM0VVis/vgftmX3
-        Zes521r50w+pmInmg28lkNTCigX0XCBWPUwDplLLiQqrxJt+fhwJzJj9+BhFn62mxGR8k21U3L0+
-        ltsKNt39zSzJTFIhllMemGhEzMgbtRVmzc/k3eWY4vXUflEXiQX3J58+j+egjxuqPmHxb4hZWg6a
-        HHJ10QN2L+aOYYx+9Q4t8UPMffco6VqQRMm8J5c//KgRRlsGK6V3CuB82mHxg5SlX4FXITrow+5+
-        f6KPsttQzj3PYdfkjILgdRfMv3fBwr+nDJZ6xZb+RDh/wumlLH4KVR718AfflLe6cxkhk1fOxFeu
-        UN3ilk51a6H5vNEpWq82dzwo0UMfk/GZgTccL2T7CL/hdJ62S3NIspgR61H5p7+WFl1DDpNXhH/y
-        g/Np9zuveaM0Wg2i2O+o7PoDml7Pu4+8SToQjL0Rze4hnNACDhj4wm3pZPoCCGCsCAnRqHexYnTQ
-        FnVP9GrlloOoxhwUn8uebMPnDo2re/6FDB4GFpb+VlNdSgGiAfm45jf7cuzOGf/rb1Au+Drhwk/p
-        rx9HrO6UoxF13+cPb/HQkbyk1S26Qb8/n3G+PiOdXVoJozaPDoRwqqUPTez7UIisY4tea1kdexw4
-        u5VJwR2h7AgRNFj8DqYe9yedfoPrCwoDbBKWXfTHD0Li+ZXi6q190TAGwk3eeLFEML8rwoVvaHAq
-        womY5ecY9t055sEVGkbchQ9PvP/5w1cxH+tRO73OIwW/WKXEv0d+OXi6aKMlX8jO8H00PN9rC5b9
-        s5/f1vMbp0blCAK5npQwHc1csRWZ/zj0Q++lNz5GyoNw5UL68/8G7WupaC7iF4aiCVtmnmQXzo3/
-        +NOvZs8kAeRtMaGKAk80rcH7QjsRnRafPQ1HaJ4uiH64psRUuXDab+UvPBI5xrlYeOW0Br1GWDUZ
-        lU+hGfI3edOhn770NT5peaMwRFjqNeYXf4TH9lX+8Rm88fimpIOJeKSdnZq5zqZBbKOfDbSsz7zQ
-        UsvNkftmoJcXly39q/JbXmUDvVsw2X45n1nuJg3+/t0K+O9//PXXf/5uGFT1PXsvFwP6bOz/+T9X
-        Bf55vV//yfPCP5nw5yYC7a559ve//n0J4e+mraum/799/co+3d//+kvi/33f4O++7q/v/zXwj2W9
-        //7H/wMAAP//AwBEtzLu5SAAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc63ad93ee0fc-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:17 GMT
-      Function-Execution-Id:
-      - pbmeiblrqfms
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '36'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 291f85b7147806b14c87634bd0b0395f;o=1
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - b12233120f7ebfb311f5076990440c22
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "a repetitive and meaningless string of words commonly used as
-      a placeholder in design and publishing.", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '178'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1Sa246zyrKl79dTTM1beskYAxnMOxswYE6JAZ9arZaxMQaMOWYCubXffQv/rd3d
-        NyUVpqgqMnLEGF/kf/zrr7/+rpMifQx///PX35+8H/7+H8u15324//3PX//zX3/99ddf//H7+v/d
-        mVZJ+nzm3+x3++/D/PtMp7//+Yv/7yv/96Z//vo79PotTZ8CQ+SSti3Y50OJTUc/MaKOfYyULMyo
-        150uzthvNB+J8YyoI2hTMUdXPYWvYFRk3hzKiKXYasF89Tdf1Fe7Yty7Ywg2PhjYeZyrbgjddwub
-        bI7xgX1P3ayO/RlptdbRrXJv0JyeNgFo6/ZLncgNnME03yWsmPTxp4sZo4mkXxmcR3mkT6qSbixb
-        X0Dlhk/8QmhttBnETQ+H4vSiarPyNfIRrAAepu4TZpztbh1TkcAmcHJq7LW2mAzJVKHh89wP5K3M
-        RuRnIjiP6uhLl4E4U+5aOZQ8/8GmYikFjextpRw5Mcf3SqRsFLWgUp7QX6l/aTZRZ/j9LAdWVxGl
-        3sdoWmWNDPe+leg+XKlstHn1it71KvWR2zvRGNidDgEOdGq+nMqZ5IICzGbHCDpL36LfV2dAK908
-        k/WqcorpvhF4OOwslx7796UbL7tND9mGGzC2TD1iqzMqkWKmBLvXb9uNfSFUcMq5hjrU2BTUFD4A
-        meDcfGkzqc70yBMXmh154q1zVrXNR34K6DSNJj2tjQqNG0vtocHIIoqcK0l7SfNW2XvdmsBr07NG
-        W2sA93bzweqy/gP9KDZ4hefh8+7MnCYhYaXk4VXFuzY1u3rlSTxcFN/1h9faivoO2yrEhXUnUW9X
-        WiejbFRe/VmgWj1etBGh2AXmGC09bLPaIbt1moIkfiZfure1xuwg4OF7Dzms3lU7oV7S2BCN8Qkn
-        S739qafhxmzqH6XRmXnj2sOxMBDemV/DYbRtYsif5QbHMyJo2ESfHBpXCokcTq+C0ochQPnaNj6o
-        21M048waoXx6J+o2Oy0iU/zVwfKGmAhZ9tTm5HZIEVNkSrhNkbJZqsde8bHK+xM4IZvv09ZVnrT3
-        cfTIbDZNissD2mgDEfivl4yahmXYmJDj7VsbksklrEe725fS3dbbRMPaHmM4WZcC+8fDXDS1ZQbS
-        57M5Uz3amQmTUTbD2RnvOGxWxJkMN+nhuH+usOd3oTa8pFZE9mNWsXbJMsaCWeRBbzofO1Q4act6
-        kxVCwsbnc98ranrKfCWowhzrVZcXk2k2JehpeiXo8KjRRAf7CnapqFRbP6/JXMtaDKOyDvC+e6GI
-        FOHkg7auv2R+hj2a80txBsUIXezz47GgfcBlIInfiUh9i1jddLIMj9fRw7uCP2vzgRouuMWVo/48
-        7IoNOEWonN/lGZsvx3A+z2djwJ3WFD/jRCp6cXOzkVt+Mrx13VUx1BYO4N2XBj3HQcBm4HdbNHzK
-        GZsxd0AT+75dOIWXDT60cZH0D3tSod3lPbWF/dkZcnebwyw/RYxjft/NQXy4olvOX7BreRNjhjrc
-        kdnlO3zo9IwNtjFn4Kp3D+M6zdBoXa0KSkEzyarcdYyk482WSfQdCKB4FTHV8isIlGCFt9PT0Bgn
-        SwRJ0bWmtqGn0bD7HDLwJ0HGO5ZOyYBShUfIFAKsumLssD4QMjA5JPz0WZtFKXeV4cxiImd7tVu3
-        +zGEqIgdotxRGjGn2WTIWV81AnO87samHFrAY/r1uz6yI/bTz7c2nzDWN2/Ws3iyFVPMHXq4PdcF
-        jbidDYs+YH9LJUZOwvsKWcsV/sppqcYGcdVD2tKIXBf9Z7R4GODdfInUcsU745yNGXo+zIq6lkKj
-        ZX1CtIqJ5UvfS5Owat31cB82iS+E3hYNoRQDFI1LsLMPH9GcmbWIXPXq+VwstA6bd5KBniHZE+7S
-        bBJyoL4LzYpeiKyVUkQ8azJkJG52vqB8Lw65kY8O4qHc07ukjs6sXYcKrda9hL04uXWz//y0MK7q
-        kkYP7YRGEZwAmZwk4H0HY8QGV7/DIbVO1FllY0I6zr/+9MsPz/MXTV6q+vJ7mGtq7ULbYfzNGuVv
-        eQyxtujb1HI5B3KXCPQQBZIzXQs7hHetpHRn36OufcI1QwSSlNpLfyGFfiby+pyP9BDbRTSZfCyD
-        h90PDo0rdaauKl2IFXvAungd0DjMNwOtj0OFsTABqwOuaGFfPb/Yq/OGkcfO7n/9CJtP/+yw3Tes
-        IFjr26X+tWR+XcO7ImZlgfFIBoeYzsYCixUB9fI5j6b1eL5D5XcmPgglLeZL2AWylPuGzzIvT+ah
-        zkdQ5IDRx/XbFk1x+wrgeCP7+Qk0TlO7RbcT71FbyB2HcMD5aOlf1FQ+czHtr4khay++w94RxcU0
-        1tcAXvxb8Dd2LCaDS1CPdoHv+4zd62goHzbIy3rgm5cd2dxxxhU65+JTz0g+bPTlugRQ1yfq4u3L
-        mV/7/Qy7OvHINpIENh7nPoTmmek43RQcInttB6AcAhU/bpdaY8WUtahokwDvjvpeY6CnW2jd4U1x
-        q6NlPxwsGC3tRPerqivm+xNV0N84REb/QIvxnsWtsloTCfsvVqDhxY+jwgr5gQ0xLlmzHtM7gJyW
-        2Eifnsbsx9WFR6xf6a6KkdYP802HWy5cqBvZTjGIPrsi8nR31LckI5pu6dWGLj/1BJUSimpvde+B
-        20VHwp0qsxiX7xFb9RoNkmiPNsnYtehuteHix4yC4CvKxOx5+f7xc2zyxhTO0nRa6g8j6jSrDITs
-        FGHNNUJn+n6TQLbU/EXC7+ugraXztoUzV75olHlqNHZY3cJDEiM/D0JN45OzeIfNedzi+Hxs2Kx2
-        siuqjxtP3o+SsT6wCx2Ekdv7pXURnD7yK0sWD9Uem6M4RdOmki304WseeyohybSbLBEOif3CunUR
-        tNlOYwLd08qp+5aB9U4RiAq9ega25KjrPnz8KJGx0weCtNWBDc/jmygcfgL11f7ASD0LhkwnVaT2
-        vS4KcvUmC4mq8qX7dJa18ZVvezFBYeX34DcdE8ujAbEXp/TJq9duWvRVVDdbmbqfb5yMamK06NeP
-        VTiQaLQzZURaurv4ZysanFFwQUBGagh+Jj8xmk9qzUNUZgPFhNsX/Fq0XDBdc/KF2bSi6ezMFVTT
-        y8PbmO20zXrPW+hisBfpInfUFr3zIRUyRD0O82yq+v0VdulVovvcbbR+RYYZ8as8pHY/F6jfbjYZ
-        fHY8xfrIpazru+sVtl3J0/1Hyjqm5tkD+FUW0v0qKpyZrbQ7vJ7FlVqZdHD49ZOcYfEDfn7JP8mc
-        HMGF+zvVqX4o627mHmoIybfhfFlSA2cunIKD7zPkCb83o25o7PaODgKYeKu9OId5ntFC882vf96f
-        kEn+GRa/hLfnG0Kj0uY9PKxwJMvzNBbMI4+03c4nX8VSunpdshKy5+mLPRHyoufHGSA3yjtZ7/dU
-        GxJyL+X+dJjobuxKbZgUXQC5uwlUrzq14EflfQfX+6j+FN2ViPn4PYO6xhWRldfe2bBmDmGpD399
-        yEttRrpcIVpuCd7zzRFNm+iTwaqRjuSdHN/JyK8HA9YmDenh3lrOmEaVC/i0fpPvvNeY0Fe4RgeB
-        M6nFF3qyDq/N9udfKOacjo2ZsA4Bs8eTGnp16oQqZy1kA3fzZZPs0UicjQCKEbjU1I9WQc+Cy4N0
-        uMZ0y9+3znTQL3ewxuJOf36B5urdh5JpR7IpnVEbf/txe6zeWKMBYv1jfOnooFxmnx85DvXpHaWQ
-        GJ33p//MwZYf4TtFD6w+chqR46i5UCXNcckbZdK6Xueig/0eCO8dtw6DS94q/TwPRHYJZuybv3S0
-        junDV7BYdmMZ1Bao/E7H5nQyoklRwhFUxOt4y9lmMr2kVoYhKVOsMmnH2FqCHiINIbqVnxRN1uNs
-        QdPmPjauwwf14SBbaMlP+EW4fTeJ+XaLtmnZYt3UtWK9qWQbfBu3PtB37cxhd9PRGZiDjQtLitmz
-        Jh1x6fFO9+sbjXqHXkPpSKKR1MnDdmbgD1tZLMobNncx6Uj7vKe/POX//NPMBbYM267i/bmiXTGH
-        wcaHbnJsvJ8PLprCa6PCsRQxtYTDy2HGSd6i/Rxh0qnzJVr8Rymbah/4c69yzuhnfo+GXeVQdY/u
-        DqU0eQBXR8QXAxVFw6s6h1AJwYUaSRZp086mLdrEXE91vjtHs30xH4g8/Z3fpT2HCHbBRlqqXSj2
-        v402k8N5RsjmDRqtn2Iyc8C5yFd2lBp7Vmvjs+s5yFR7xoeXIkeUv21n5be/3dd9w/rwLc9wqE4n
-        apyeRTRb91sNUvp5EvHeu9302oouYJY+sX98JM680rUc2vOwpo6G+2ge+48A3FvWSF+UetJvN6tc
-        /vkVN79MiNw/loBOyKn/5L1RXdc53EyV+mU06WwkpkdQn457rJfHZ9FHT6tFQ1KlZHTdVTeYKLeU
-        Je9Q/LzcE7bkcTjGx6dfb1hVjNLrfkXNTH1qs8+kTR/gRBSTE6baJduicS91FZStcKQeFvVuYp4Z
-        g7J+NT7BN8cZo6dV//n/l/7fjWklC6BhTyLK4o+W+jLAGt93avIfi/H371tEyhA0eKmvhJrCwEFw
-        eel41/l7ZyxUr5WL6xfIcez0RW+dO0rog6P7d/hyyOFQW7B6iQoNwzqJSNVa4i9P4D1tvogtflz5
-        vS9jurSInsL1DAuPwJeXU2kTY3WFpD3ryfeyuy1YIRRg+qQZ9qaV1Y1XpzZkZQgbItSXtzMnt10K
-        9YYcCMIvsevuVvuAAL06vOTPZO7cmlPYWQxJAoPm8Mv6oQPjjliXPlk0vB/yFhq/r/B2d9iz+ec3
-        PS85khG1efKpSZ2hKUldX9pmtTbr+BBD/mEb0rhjHM3t2fPhRGGmu/69KRa9LeF05U7UAhYUUzdM
-        DxSEjUykxa9OVtFdUXrKberTbat1wfUMYF7QjVrJ4d0xt7+3IA+ejY0waxLyXDsB4Hvd+eLyvBFb
-        GFD6HA70sNUip7k5To6WfE693TthTFQ2MzwN+Un12ZkidrzPBggK+NSGMCzmb6jaaPEvNI6mEk2n
-        iwQ//kPNuHsn0+XL3+FiX02cVtssWvyJDKudmZHv5np2RlLdCAqKoP+tJxvNAzFkfNq8fTm7ds5U
-        9PBAz0Cc/NV4FLUu948VcPgFSx7QolF6hVe02u2zZT9qybq2zBDdw7byP6BljN7ihoeTpBiYbIoU
-        zdHVfUBfjzd8M6N1Mn7jzkfaS+j+8IZv0BXlLz9hL7JMrU/vLEVLnqXYt2ONXG5iBtO5U31opgyN
-        H/F9RpL52dJbaZrOJk7XFsr21pJf31Ey8UkjiMP3auCrl58TqtkNgeNZn0j52E0R8zy/BpXXdOqi
-        +BVRjpUPOHFjQLVPFnejSqIAXrth8nnx6rFpdwQR7tzDw5fPVS1YqKLzn/VzcqFLBnP7iOV3ML+w
-        qom2M9VJJAO7yRbJKT0lTXDeyyit0cqfe7C0dVmrsbL0S3/cSUXSoukjw+KP/fFRXZNZHFoeKetn
-        Q7hSG6PxqocCiIT5PqxJ2dVHacrBuyQff+Gfyex6nQ/5Z9rQw1O2i/HMX2OktupIJImftUUveOQ0
-        ZULTFyvYfEJJBrBu7mSzm7Ri3VWlr7jVladGotQOu8VvQRE2l9EX4Yy6eaJbUHhjT8nKMsuoGy8x
-        +ZNn/bSaIurFiYj0Ou3J7J0abRw6R5CXv5dwRynQ5kI/93L93V/8ecmP46d/g/LRWg1rh4Oosay6
-        xrDS92e6e5gcar82L8IIGvijLOtoSudT+4ef2toxYLO7KwQI1sbWV1YPM+k+K5OTzsYqINxTiBir
-        rPGONu1hTbWTICXjuQ44KHq/xOaYQEJz5IooQM+O7u5vjbFIQDJwRHTp063ziK3nbwrq2quwKjVN
-        NDhfksJKQAmZOv/jUNmsfYi4YktxOTURsZW6R4te+qsnjxPigdQiP/Y4n7/5Gtr8eOHSj4k85O9o
-        ErhRVtbdIFFsy8fu51fkX16Ky6NSjMXpHgJ0jUH9OtsnG0s66KBv10/svzQj2aR424Ic4B3WHtpp
-        4T9yDkXjE19ZY8cR87t+RZ/VuiHrsvcdFnRdibqZS0mPn7w2//h0ddsohCZxG42P8aKD3j1yvxAu
-        edIf3IMPbZKvfK0KQmd8p1wOYq/I2J802WkkVPVAnOuA1T2StfZXHy73Ydi60LD4oHTNy9O5Uak3
-        rEGbxrezhRMA+JwlGcns7jpBkgds48VfMbZLIld8ITvG2pLnpuTrxSiwU5nseRcY45+zCPaXE7HZ
-        id+kRrzPAT/nBzIJhLFxx7wrLDx+yQNW0Qt7WqGf3jgYhm7SBq5HfEbWZF3f9sUkna0aPkJqEU7t
-        D6jl5WMIuHpEdBfdn8n4e36xd02sS5aTTNE2DyFPpoJuY03r1nYoyeBVWCM8u2psIhNkv/1IbfGD
-        nC6eDzOAWb+wS76cRtxYfKDw0sf4eTsVBf0YpwDFl/P8yz/FvNcOHBrkCfkS2umFALevBd/kmS1+
-        f2Is1XYhzBC5ZO2Ij2gWzokNpapmdLcz38n0GroMbYe7hXdLnmh/+a5dvas/8way6XAvL7ztx1OS
-        eeHHaLUXW/wc1uAs+7lH57JyFz4jaFOdNzb8eOB58LioUT17/OklxkEradPus8vgzq8lX+FwjGbz
-        5Yzw/UbWMHSzq/EdUuIfjyKr3TNkk284DxnTNU/dciOgNZEO88+P4r2rNk5Lgl795R+88Lmk15q3
-        Dcf9a0Xuq5xns1GsRbRvdUzN4zFMev3Y3mHg7wHeq9bJmeB95eRvr4cYd0RzNqrll7/PyfQoGZok
-        +xDIix7SvRHuus37fgVY9Irq7jsv5uh17H+8j+5GHzvjj8cuPP+X17op3x4s9OOn6zflnZl72KH8
-        49NWJjXO2LCtDRuTy31l4V39lD7vcNfWFtbcwnSm7F1a0Lsw4aMxgDP4hpaCCFebnjvZQXR0nmf5
-        W0YhVU2rL0apu82yrqd7rGrJSVv4d4WWesc7/VKg+f7ZCr/9SM3OathsT80ZHpIc+S/f5p3xLS35
-        ev218CF4Oqj18ssMv36rSTZFk+30NTqO+z0Rdaw7k2m+K3np11TPuU5jmBt9KIWdSf/wD1RpOsyT
-        cSEcCfpiejTZQzEbMvx4dzcEuReAonYl1W5FwCZJgBJuey/Bv/20zA/OUG/6w+IHpeLn/+A8rAZ/
-        fp2go3BpWxhMRfC/u0nr1kRhIgTxyyfzY1Um7KzqIUpRvKf6I62S+SAkKYpvtrHk3doZzzcuhYVf
-        4p2cOMmsfS0dOayk1Argk5DOzUD5Jq+MIO+wTaipIBfVqXih5uKH6GYMHsqmmG2fX3jC9OM36qBW
-        VD/xMeqUUFzmMygkf/I4c1RBWerFX3O3mza6ui5KLr6fyWbh+zPOtqNydI0nNZf+uui3AVnjYDIH
-        YaHNmWScwSxRQapEqbVJsneh0k4xop6FbMaH9yETfzzf49VrMeK8EdAvrxs+O7Iu6+zFn8kTtryV
-        Ey3zUffPPG+/32ONn9Ln9Zc3STvs+2T86Xkw6zY2/R1GIz3V7p+876OhS0Zyv59hvwvThV/fonq/
-        HUWlmBKCt0ETF+M3LlxYZ4Xur9WP7Uzqfp3BRlQirL+nazGsPg8VLu/rx+c1fqexn18MKYqIYI2q
-        8+fnHyxa+5NtOk6HinwLxu3YL++nKOYsqkN0MabXn7y65DEeHqK+IkKYHaLN6Dxj6Epnu/C0hi35
-        2QAhLTi6u/N9xLTRnOG5QT7JUKtGC//XIUFBReB2qZ0/9WlX4xmbsd8nTOlfLoRjbtAfH+6pmlTg
-        Pq4ZTqwVYy2IzIL+Mxb48bpv0LC5Xmo0XR9nUhSjp81XT7IhF64NQRD4zvS5XAWU06uD9/t139Hs
-        penADYboM7cwNTZEtxZ5I75gj6pk8Y8sVpb5pr/inA7N6ljGIIAt//i3Ns6ZmMFX0Cs/qYwBLX40
-        hCQODvjCzXttDjfBQwlmw6aenD+Tn1/7kz+2+s2KBNNZ2bCKe4tqy7yP5Wroyks/wP6luSStfcHp
-        b57yh+cwGdUzDOZKoLaM827+fIdRVrrniVrBK4ga8T7PMMsvEe/jz5NNXdW7UN3WCmH37YeN0XNb
-        Q73VZcJN2l2beeaqv3kBjXDzYOTH58nkN8s88RLRFDFO+ft3KuA///XXX//rd8Kgqp/pZzkYMKTT
-        8O//Pirw7/vz/m+eF/5NhT8nEUh/z9K///k/hxD+brq6aob/PdRl+u3//uevNfpz3ODvoR7un//3
-        +r+W3/af//ovAAAA//8DAEwqicXjIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc63dfc49e259-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:23 GMT
-      Function-Execution-Id:
-      - pbmexn5kc8di
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '28'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 7793eb63c23999a96303cbe39038fc6c
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - ad8d4f3d387595b6652d71076b51541a
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "Sample text", "model": "text-embedding-ada-002", "encoding_format":
-      "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '88'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1SaWQ+zvJal78+v+PTd0kcBkuDNuWMKYbQZMkCr1QoZSEhIwmADLtV/b5H3qLrq
-        JlIIUjDeXnutx/6Pf/z119+forqe+7//9dffr0fX//2/5muXU3/6+19//e9//PXXX3/9x+/zf9x5
-        rYvr5fJ4l7/bfz8+3pfr+Pe//hL/68r/v+lff/3tJ8svlV+lXVErX4hr86DtGZaqBPGXTM4QWJct
-        s1/uuu0vFk4A2lFgeIV35sSNKVDv9kVllpCZ/rjpGwtlO8ci2rmTUy7XSbCWZeIRLCirli3MM0b7
-        PfhML9vU77yaOzCpzgOPsfou+GDZA7CrHDJHua5Qv45FCvbHrQjWvhQNGcoSWCcSZ3jbaQUv3CiA
-        nTFe2MY28nYSat1Rq3y5/z1v1V9uJwv2z/uR+A/liKZFfTJgWXzvzC49K+2bLCnR/uaHVPLMizko
-        1k2D91o6kHBEpj/4MRzQN9QsFiz2qfldv60TbBdhRnDKGj7hNw1QGdoRC4TjvXjbffNAephwWo63
-        O2KW8T1Bp9Vbps/j+zLxLkIpFwyrq0+bcjtLRNh+l4QuHgVBg2IdNbQdPiExNL9GU+fbDvgfMmF5
-        v2mrfpOdMliJQc7O7+jedjsqRLC5BDXxZU30W0r3ETwPxCZ69Pm0HEumAg4qETFu6ZeP2w/p0Jb5
-        HgnM7FJMW+mVwcUtMZVraZPKlmQ2QKiyYyGL7uh9ML5n1O2FiDl+sm2ZXi4aUGrjToLypVV8k+kC
-        rPKrTSwhq0xO3a8HmZiURGtzoWC26XtwYmmDl9Y3TCczp6BM0/XK7O+98Tm86xoJzD/QdUDkdJqM
-        +05tfK5QNSlIym3TdGBzVFpmfV/LdmijlQDv3WlBlRgZqZzXrgam1gQk1E3bHA99noAYFicSViL4
-        v/cJJ9mTWfgJo2Jw0AhQeKZK9PU2bsdHua8BkpISMrpFxadbdUZrt34wa9Hf+RD2uQHvsrZJeBKr
-        ontklQMPMROwhIuw7epbvoKitwmWniGupoUkX8Gj8oa5JH6mPMjfAXSLmBJn88oKjozvE4510ROi
-        q006LNDkge2YWyyH1scfev9aQxIt9uS33kbZP4iQtG3OsJe9zPHzvgSQFG+faKfs4Y9Ln1F4G0hl
-        ni271XCBdPjNH9nGpoWGY/QxYL3Ybim9jSPqdHcMYBBvhCrlF5tjCr4F/uXek2BCRTudwTwspLI5
-        Mkf0LN7ujayGaPgQsg+okE6b18oC/dH7WNF8p+XoOEZIWq/fzF4k25Rn6tZAEnN3bF4/5vS5VRgS
-        DW3pWrIZp/6xNODj7zKs7lyj4H5+2MFCo2/mj4uhGvlr0KBE4wqL55AWTe2uJ3CjRUpRsuxTniCl
-        Af74Osze7seKunXToftqU5CLKvQV9d/BFV3dbsVsnNt89G66A9LuFrGNZ6o+7dD3g3ymMUbW3s1k
-        phGVsPH7J3Hkyz4tlXxZK5cw35Pt+tGjLxUjAVarTUl86FaoaaLyAUXxDvFKkd10WYjaVfXzpsbi
-        C91NHpcXAX2X8ovoWNm3PImNEwxuQ/GiGnA1BMfhqpyn1iTGs2Gc5+pNAdDNjhijtU2HY1Qa6jq8
-        fVkgxldzUlEmgkA0hfjdlxY8rk82CC5d/PSM80wlBir9N2Z6v/HaUarz4bf+mKVvfF+k5cJBC3f9
-        xamcPfhwMz4iPK5QE/MWm3/qB9Urt6HiQf6kDbyGBB6LrUG2G6Ezh7GPPciH2iTaa9Okw0HyE5Dl
-        0CNG/EyrCW6ig3YfItKJ6vuKl17RAckfPtMeRtZ2bpzUcLxvJzouR+bzdbey4fRdMGaORlm9lVh1
-        FLl2gGz226ToQ8k/w2cQBeJt7g3/ip5qoVNEb8TcOFLapGJsw+KWTsza2LjtVuK9AdbnOXNr/Wj2
-        zB2falc2e7ZZJltzet9OB4U4uku0UPDa0RUzEaY6PjIHg+CPRHoFUL7FihF6kdHrV39BSc9su4i0
-        djnPjzLXE9EFySqGm1HK6lcuRiqt66Lg255nUK+bDqPFMUd8QYMr2pdNxBzhdi6mvefVoG9hRbQq
-        O/Fhri8Y3A/F68UkFr17XSWKL2ZrpkUNSf/0s9/8m9/3tRhqy7bhsjA45ZZntlNwXK3QWlI2f/oj
-        /xhRAxfxwMj2ZJz8YUVfJQhDk8/6Nlb9PB71TQyJzHprct1ngLwwkYjnBIHPOXI8pbftjvhV/ESf
-        MHMPkK/5huiPzCg+iRh9YGudVnRSzHPFhZ4/QUKHAk9DJ/PR6vMAsK4/iFvtk2LIpN5Ai3KQ2OmK
-        CpO+3I8CEvN3mH/i8zwfyQ7ebeSxTH+KiIe3agerBztioZGbaqRiJkD9GO94mPWtu7+FDiWHNMJC
-        aNop/emP1dsec5djhMZXjc7osTsMxOhNk4sXKAaFH1cSI9I9MMdHrcngRMOXmMv+XrEsO63gGxoW
-        0d/0WQ1uuTQg9M+UHCSkV/SE7jV4/dEkzuDe04GCIcC1/CRkW+UL/pHNLoNFkbXEm/RjwZS3JYIV
-        IYva/aOvaIuyCZIkc/E1MYqKD7dTjdbrMcBIMApz6GJdRGznuOTyDDo+vo0sUOpJYrQ/XQ5p/6tP
-        d3pUzLgIvjnRuPCgZYbMglF1EXevKwrV8/3BpRUt+WTXjqDglovE0erKpIs60eCbnDDdZYHHRyOG
-        BzpMJ4+ZC/Zph0eyXMHx4pxJaGQWf2WmMaDjdkjZtZa25jRl7mpdRZ+U+Y73SulwLD14beUnva0f
-        pJ3KPi6hUYuMeM1RQ3Qn3gHO66vGDDT4aPDk2xMZN63/07/6jbGWwdQ+AbkdslcxgjEZsLpOOkYX
-        ZFRUkPoaXVahTGb9b8tlHghInnYm5fp2nJ9fLIH2AWP2+rmrvoz2HSxs7UFcP9I4f5XLCTrx3dDh
-        pO9NvjB3gWpTKMk5vj3TT1Y7NbLat4PZxzXQrH8yLA72wELzIFd9Kt9klLOthlnaP/3+dnsAXJlP
-        8EKLCpN7pjRBOGUOcy+LyB+C904B/FZ6Zl0eoTk8rysHjGQtESu8GVXf9sj602+suX+1Dg0i2KhH
-        gz63I2ung5deQReTgoRaK1V90zcBDMl6gRfNmaec3XQKaVJzKsalbTJ0HBM4olEmluOW6ZRH4w5G
-        f3ciOnhVwfANMDI+qUA/p6zi48LsGng96iUje7Ou3o9aT8BgNiL4cr0X8/OvkNVbHjGWGSq6e5ZE
-        IDxvCdMf2ohm/26j90vRmf0q67azvEqGJsSUOQux8Idbn9vQR/KCLg/52x/jOm+Qv7BVLDquVvQX
-        KjzQz+9o1/xVjXavADKe2ZJ+6cn3uVS7Bwi+6IqF+81C7RJNE2A1kolNjlk72Shr4NA+BOJuqrhi
-        7OZ260V7XeNF59Upv4pNgH7+b3nQD+1w9FoFAu2p4eUiKtse9XGGdKNRmXPVZd7tclojXF/WzHTL
-        FxpyP/yg55s6GLT+nA5vz8OKLigxM8/1wxxM7ySguZ4x19zSbG8it5BzsJ+UdZ6ddvP40QJV21nv
-        17w81yiActttMVBl5XOl1wBkkg5zPznwaUV7gKA4JHQYHZGPeyPzYCM6GtvkjsSbU50rwI2yY5tn
-        SKshvTkCBFqtsS0+ar7M++YKxDFdul6592qo8/2EDMd/0DWJn8Xw8VIL4aN4I3qxC/0pBEmBaL2M
-        2TZqxYI965ODSjXomJks22qY+6WSfcuQ6Vmy8On8/0rX7nLmhk/J51mWrGDUPgdMh3CouGlkJdoX
-        kU2Sr1EW37u0y5AiW4zgIRxaNnnptCLr5o0XnK/9ocrAQGaOzrg/nBNES2NyQPO/e6K/zKodTrE7
-        KOQq2kRPUG4OeXnZof3QXSmXMwOxbc9PgFT7gFdm/PQHtXY6SA5xxEhuef5nHq/67DWTBLFzLLia
-        pQaYET0Rq4syNDQoOkBS76/MOXeZPy7rpgHL9kYKrj0Ug+EZFqQr05vra6ymnTt2UD+jirneOuVD
-        i74BwoeixXXQHVs69XGtBLV2JJoib1uq5wcb5vxCTCw7Ph/o0gB83wzM3z9oNY6iQkG2LUowoe9i
-        /OXFWW/oevfxioGbxkcNl1OMYee7Zn/sHw7s1JdKr9oXozHLkjOsJv5i5ub2KKZCJgG8rcNIAvda
-        IhaXe4BbcZ6I09usGub8h+b+xKKm6CoaZVUJBzmN8cvdtAUPPG9CoytlrNBcnUtV7Blo7tf4NcIT
-        TWq5MdDGeDx++mZOijgJIJS1T/Q63/CprXVbMYfpQx/562iOW7Oo0fpSLal4FBXzHtweKzXf7SjD
-        /uHAJ4PKH2VzwfVPP/0pvbkZOhvl+9/1p7sjVrWjfGbOfkHQeAC1g/l3on3tntPJ+B6Q9chsZvYL
-        ivo7ikpUrz8d0f3YaLmM7goIkrCjwrf8FK2fXw9gX5WE/ep/wNkJK+G7M1mhZFa7TND0UYiYXAkx
-        k6/J1ffijAZjOTJjtN7p1ERlqcYRvTCyFM/V8DSfB3RW91vK5jw++uK3A129Xej6tqOcrsQ8gFq9
-        c+bja15MgvSq4fk4hcwWcZKO77d1UE67d02n8tsVzHfHFWyKccJCMeCUd1krA38vTKJn387vl+Bj
-        1PfGBrNt2rU86x81GDejx0O661B/zamIgnwZzbyjLEa15x6Ux2E/55GMszvSbPQ9xHtGnC/x6fM6
-        1LDPlwleXk9exYNbcoW4yO54+XTv5hCZxQnqacloV4aRSX/+WBCrkpn31zGl2/JCgdNJY8a83qcQ
-        1H/7BS+N7v74fVMbXktVo4/FSIrlnPegOIQWs8Lbo2KzPkP2xAnx71D74ymD4MdLmP6mVvUnnz/l
-        eMesd1wVtJHODbIOeIHv/carBkOcDqBotTfnZyuV9fxqIbZdGHShRcgcN6pdgsEsRJXX+4bY8U3P
-        qL8dgYIYC2YvlZcPuudnnW38DKHxx1tM4rtUzL1zO+ZZtUOraXwRq14nfETJ5vlHj+O5voaupAlS
-        LS9gBB/vfAqNb6BcDBYz2z9I5iBfVxjNfoC+Vh+35ULWruB0ME7MEM5D1cZ1YsHxcLwxvdalor+j
-        7AHZVlApWvZmIW99bCBZoy9GIBzQcE/exto3eIHRO/mk3IxFAey8PjKiv3LE7f5RAlyC6Y/+TF25
-        l+GSbU7MnP00f8XFDp5krzBXuOzboSmDEqpc2hPjGD/QGIjTU3VytSV0CKN2PGXizMv4hZgNXMzv
-        slxmyly/xM2+PaKBkR2U8m7WeDGWTjXmZvoB/SqbOKYnt6CsRh3E6KHShynm7bBFd1ud64NpXztE
-        Eok+gTLzDYrm9UGdOpfR7MeJ9zUMn1vJRkbkwc94Zb3rivc0yMAwlm8KZNqh3/uGWHZEQo6H5ewv
-        4g8U0zUnPjocUs6R5qgXo4+Jx2ldTYZ4V+D8BoEZvnTxh7VnJIi+FREPVaZwBn0uQ1Q+debM/qiX
-        0P0K+lZY0eecd7kJfQAbdW8Q114NRfOmwgALf3fBw40+i2mXXx107HFDl/V5rIby/ZLhhiqNbI/H
-        FWI/nlNOjw/78bZhf2soKqNFRtdGeeOsEJ0zKlXcMbfqDd7bpkcheVyPzE5OXjqk4rdEsBW/xMXK
-        Mh2u0DWwdTtOdJLYJhdM/wDQxxpz4vei4J9YtdBeNnKqdi8N8Rr8J4r9Q8q8SV8WMz87QLNd8X/z
-        p17UHj8/SCELuopHUt+gfsoIM3qzQpPmloOK69sarybRSKeKBt6vv1PI723Komgs/+gfD+9uwT9G
-        1ijZM0hwKSxbk21AtiG62QLl5ftVTY33PIG0Rm8WhpvQ7G+SWaI5f/7pv+z4rq8w5w3i3Kjtj/ve
-        OUGXL490dMiunTJp94RgV+1ZMD/vzIsDNG4gJjOPQp+5f4BsvTvM5zz3aWvng4zd7st81XLTMfXf
-        T0TWnzeVVXiZbLq1V+RotMDLbdqg6STJux9fYtYL3X32krdXcBpzzXz9qrUDrXkCbOe5+Df+YStJ
-        MqxRoM2ZTStEjfY7hJcCwu9J/vpjFK1t1Drbyy8vFiPNQ0dZuOhL5UMRIrSPJQ11uxumuSkJLbu4
-        I6CZNzHfdZbm8FCPiQJb+Yvvx/RbcanWD3/4aOha35Zr/s1WZj3B9W1Kq2FKrvjHi6gQWy4fCcrO
-        MPtZ4soFbsel/+4A4o3C9OVIzEHsJwW+o/7ByjG2quWc31Fj1CuMikgvJqHcK+vZf7PNukYFLZBy
-        RspGSLFwOHUm38H5pCyPw4mFW/o2Z32MIJRjQvbwDc3uod4SNKKrTNFL/VY06LUnoDcNqXS9ZubE
-        4qcB8/oh2GqmYkrMrlMuFk6pgPWVyRxqRXAX8Y42tvxtuRiVAzD3apFAhoXfFHUzATXOF+Id1juT
-        kXJjAxOjFwvyu1+MeY80kMjWppJuPlPmuXcNvhoKZj1QfzyoRvfVtsDru6Ejvqu5rJ7Er0jC0neL
-        UZIEjL4XO2FOKASp/Oh5AqeNEBCtNsFsr54nQu3omBHSlW1XgKFAsLvvqTAtsblcxcUJHR+Pms38
-        sJiub6uENcIa0RdcnvvR/gMXLLp0fHZyW8eZeAKrXCQMO+0eTQWazhBG8opsF1FZDdf3DkD/bHd4
-        0U77aoivK2ulYjFiB9e02t/7g6OmHvAg+nXFmKmu4FCcB+bHnuAPsdlFSH1Gn9mvYC6d6av58UJM
-        PW1XjWsjisCxXg+m1/kLidfj6gHHOu/JthENc1nHHUbxs52IsfHOPuUqXoFVpyFerIIwZVjyFeV4
-        2N+Y0xS0mIbjx4O6v7yIczE3JlPgdUK6GBXM4dPOH+d+DN/p0TCyfrCq59L5vE6WcjnrQ+93e+uw
-        gqN8Q2xD19ycHj2P4JqPNsOEblO+rCsb/XiUdtDidiiTgweqAB0eNLIrJFs9nsBhe3HmRYb/4xtI
-        vu0FYiXXJafJdXiosta9qJhITzSIWYVhvdtJJN5UDHWpu05Avxx1pjVFUI03tj3BR3bWzD/XFeez
-        v/jxJkJURfPb4ZY8YTEdNuzHKwcq3ygyb+TItPF251MjnT/KzDfx0G/HYiTRBytdLh2Jqz+wz8hr
-        2P3J48FjFfvsm4QAy+R6Y1723pr9Ekysju3pw1xFNKof/0HNxHbMcdUPGjvqCz/ewHBioIr5+XUH
-        s9+hpejbVZvE3kkRqdDM/KszuzwaVmpziYBtBiK1Y6PiBhwXXbA883P2Pn4Oir0wKFZ10/b7GE1Y
-        neT9i4X17VLIFQ0c6G5+goX9pi84icoG7dHpQdfH1C8m0zMekIqeyYJwyzlr+kfz25/Bk+bbiIue
-        9AB73byYt6vNakzqRwlvJ1xhUd/45vg2ogDmPES8XV21XH0vzxDaHqc3ZYmLcQ07C/aMFCyc+T43
-        jh+sGOtRY945Opn8QqkNfH3esCBwDXPmuRg8ox7pauYVHBn3p/ocFvm8X/RIeWMoJzTXC7N69WPO
-        /fkKf/KLuWN8jCXZho5sLUamq5KOddwOaNtGJsHmjqD+Y3xtQO8uZLtGkQum12iCviYOFub8NgVG
-        tlMkWSuZqegSn/T8YKFQtQJmvZ6iyc7u3f75GzyGUKHBuvESplI90847T+24/WwpFI+TP68vnA6n
-        kgYQ39LPHz36eJB26CobBTFUGxc9elMHSjtOiXWvhmqwJBPDPUwUrI5P2eRr2JWQ9cWO+fHd99kT
-        KfSXN4nH+srvXjfdUNjEKzzNevlagh+g7+N6poMsWf4w91eQcu4TM0cal377UcJt4+AzSz7V93Nc
-        TbDfCz7zJcMo5v1XT0V1nLNIh6qazuWiBBGLmJFVEBajk4EDc34kxIqFduYtAMvQ3jNtXi9Mgf70
-        8xvzeM8+JaYnKLzgQDCQY9v99jPKcSti+bJNqulNhQlm/SY+ojYfFeProeGmLWm7OK5Rr/TOA5r+
-        6OEhN81i3o/D6ELhRZL5/f14ujr5lUWF++2JxmtOZaSGR0zlLmjToUeTBXM/JES+XdCf77M/IfbM
-        i5nZawNaUZmwoF6L7VD2dwGC7/rKDPum8NF4W/jn18kmd/Z8kMyiROhAfBLO8zOtbu4DHQ6OhJdZ
-        X8y82RPAIXFN73GtFNPUx09Qit2Z2V3QFvP+3gQfrXv8eGPL1vEzAfuZnJnVfdx05nkJyKqxpbxG
-        6+rnT6DGov9nv6P/JtdMKY/TntlzPxmy0rrC379TAf/5j7/++j+/Ewb153J9zQcD+uvY//O/jgr8
-        83Q5/VMU5X8y+c9JBNqdyuvf//r3IYS/v+2n/vb/t/88r+/u73/9Jf85bfB3/+lPr/92+R/zf/3n
-        P/4fAAAA//8DALL3VtrhIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc664f8981121-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:24 GMT
-      Function-Execution-Id:
-      - pbmefoalhwp8
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '98'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 37ebabc27cb744eaba5b13fa828bb351
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 57643378a1a524682d1e62a66d1b55aa
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "Grocery list: - Pancake mix", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '104'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6WROyPLfl/fcr3npv7a9EpoT3jklkMkFwwK6uLkBEkEGGBMip89+79Dl1uvvG
-        C6Q0yd577bXWzn/866+//u7SKs+mv//56++6HKe//8f32SOZkr//+et//uuvv/766z9+n//fm3mT
-        5o9H2Ra/139flu0jX/7+5y/uv5/835f++evvNJie2H+9X1ELP7cYftp8R2CtoXS1tuEbPsJmJtuC
-        pcMy2RMC16p4URNJTbXKouorcVm49JGezGp97bhQnvd8h63XACo2nZ03iL3bHm0ot3pr6FwI3MGr
-        TDa5PhvkpGxdsErmQu3nwkVkzzgL5h8iUpTDwmPl5uxDWgZvnM567S1hIobQVbwByX6L0wnQrATL
-        NPiE6A/IFj7QAyiPaUEdh69YmrmbETarVmCrmcNqMBYthMKljrC6/4ygp3WcyCdlINScaADG/Hm0
-        YWnEBPvbC5dOhShzgIhHgVqjXDAaQ9mG5XnvEl4KCCDd6DXAeKka3p/61Vh1EjQKI9YHCcFON5ZV
-        CjZw9PIr9bWH6y1edMght7TrtJYoZAv2CxWGLUmxfzN4jxSiNEP1fG/RojlaxOQKyBABV0HgNVG2
-        dJwUw7tmJETw9ADsjpSNiiP1FfZV/+FRTGseakNFsXsZrbQvfen6iyfa3kuz4j7ya4TXhyGS1bvd
-        h3mukwK+gkanPmy0Shj2yxXqURpQAwJUEffqiVC9vhlVi+Horc98G8Jm1xdkMxI9ndpq6GHd1AA9
-        Fl1g9WHe9rCVgIoP7vnKJn9yNvBCA5U6ClC86eCuPrT4JKGefzBAv00CXVlKoiGmpbKxMpaJcJWs
-        hXw+WDNG9RGMsLiFE3WvRpWSqIoR0JaTSrbc22RcdAMc5NnDQJtda0RjclJ7cJPACaM2RB57XB8+
-        +O230PIazOvECtAezDO+Sq0H5ja2EMSecKd+ugTG0oxxDF9HcieSDxmjj77IoZ20G1JfDltj3B36
-        M4yYq5I3TA2D9cNmlmYYnLHRm7uIbiyDgFSXB2xJAWKfX7w3G4Kwt1d21WIuRgJsIiXYfC5xtR6C
-        LoHAaGokVRlldD/vCuDvpw6bk68AFjpZBxd6ULEtXNtqOeHTCupNeaP7Nth401bN32Di3Ypige8r
-        yscvFwbCNsGHA2rYdP6opWJseA4JwaHzyJX0UDab8UI1CXLVwCTPhOCaHcn2/JgGwpkl2a4naaLq
-        bfNig9/rV6Vz2wytT1tnAhRALG82I8JuOZOUgELIIXcurnQvR1PEUtuHgCjBgHFEo2h+9lUPcU41
-        bD2EZVjBTifyd7/k7XrjsPRKGMNXnuzItlc+FcEbXYSJ7ZT4yEdvtnaceIaXBL6RoIRtxJyry4NP
-        m+3w42M0gFyGxQe5uC2wUU9iNCf62MOY6xOMLg412LH1OahodkIfW38PFu7wCiC63CcksMH3Zjso
-        S9DM7YiP+2dZraWWcNC5FRG9ebBgxLlrMfRQ/URc2pyqmXaxCt3CDLClpDtGpJfnCw8URajbil61
-        BLsnkneksLAm1beB3xOfl/3MD2gmTEU65u0iw+YNTWpoaWIs/rogJag+GyKZCQaLmIclbMpVxMel
-        dpnQVZcZAt1dMJLMOR1Y35qQK5wNtTaXms3VwfRhe/ff1EqW1/Bbr1LfLhHZ6meSTlot9lBOqYnE
-        Dx2Hib8sBXQVZ8C+5ZkGVRwHwSrd9GTzrZf1bW2uEITCEXvuU6rWy1Lkyn0wLeplXczYdNbeUNAi
-        Advxua2mLuFlyD7aDu22sRnxv/rl86dL/cw+Rkt+vV3BF98ostnL61c+iWXpqs/U4+6lN8kNK0Hl
-        HHTySdQUsJhcXVBqUMYHwEfGUq5bHtjHsiROIg9sPkSdDvP4ZFJMFlZNyZbokKv9FUnPfQhY5KMY
-        xMifEO+zz9DWDzn4nQ9G9/PVm68DOyt1jwA94LkH7Dq8ExjuGw8tZoPSOUWeCxrqCUTQ8JN9Lo9r
-        CPvk9KKGcnhXcxrJMYzu+wjx7KEMU7x/mbB/yC+MScJX05TNOby4gU0RFJN0auK9C8vb6OKbOzC2
-        mrzUQDtbXIrpUFU9aBoCtlxSYbMPKzb7s1rAjR2W1CacUS2lq/YKYNWHdNnwrua7d4rhK3jrOD83
-        mceMsg5h53gdWu9OymhsBwT84uv4MALM4OdCKS6chN4TnQF7ZH4GHkSh+HBXHW9eOjOE1ThY2AgO
-        fsRkmsSwCa2M7qdGj9bL44F++UAmf75XBOz0EaTS9Ub30ixHSxh6hVzY+p7MP3x9acWoFFKs0MfH
-        sNj89lkOx9FeMZolJ1qf7aiDqc4O9DElBliNuuLhLY01akRHaLSc+ephw6GRtC+p96pBMQu46TYb
-        tAnW1RjDRDrDsydtkcJHJth5KedDbXO/YRtM7y++eomcXVNGzfr9AWtdzBzYuVCnltR67LsfHyYr
-        wtR4lUu0ttSxQCrIFTatW1nNkF7eoPONAJvax67WvR7b8NMY2p/+OpOymJXN9XDFxoO0EWs+8Qzx
-        GlmEWx8uWxI75BV5e7L/1Cszu3MJUaRI2FmWvfHWhwJCKdhCfPye5/IotTdwgHVD8LR5epQ8CwsG
-        HVnpPuUKg0YnpYf3zs/pNz4pO/mhC9/Px0rtI4NpX6dOA5U3ycmUdtowz9dNAb58DYnZYA7spd1X
-        cI74jMjBZkyX3QZmsE42EXY2u8lbyZ50kDi6RzYH78qWebBHKGn0TPrZi6rVcacYQnlYkDItBWPp
-        tdvA9rbO33owq5nTmAnWD+9g9YEKbyqY8YbHl3ck/XnlUyZ/KhfE46SQWGbnar6RyQLf+BH5cDsZ
-        Y/tQcjA0eY793tpHNM0CH2bu6hHxmD0jlt2TEShCY1FX2pjD/Du/fbw//vjcMGe17cJdDyxSkLAz
-        vvUcK7/+ur/sJG+UG+4Nr/4tQyAIXbY65saF/UN8kWJ9YGMCnzqE23TpsXt09Wj1JlWGhdWcqCmU
-        GpuaMU4gm2FIM+BO6bf/cJAQ1aD+O0+jeSehACjC26KOfIgMtkL1rXzO7RHrF/HN1tcOBtCebxj7
-        RcSlVFH6Hv7y0Xa2a9S949MGltfw+odfLYW4csCBhYdPVUcidn5krowsb49/fHaUPrL141vkVJ2W
-        aJEbUMJixxQibsWhWpP9OYSCdR4ozjquWkHTjJBfNUzRrq1SZsFMBTfx+UBym9vRPKJPALNMTqk2
-        Ndaws2w1A1fOV6jNZ7eBeO29B14oQ8I9jc3wxb8E5tvMpt9+m85C+uEgWxOLauHRSXfpvWhgKMYC
-        UjaflS1eCn2o6A1CDMPaWxh0RzG4Zy4+2vU6jGGyXKFWqjHeXw5bj2XRkMOPRms0iEff2MnxrYT6
-        aZsRgRZ7YzUywYLGHHww5o4tW7wIZ7LT+RQ7wyZiQyd8dOjtDB8JHxF4Y36/yCCoDytZcvmcLnKO
-        VnC+BAG9SzPvEaTZGUybnBItPH7S6dj7OXi+M430u6Cvlj0vd9DybxPaRvE1YqHaiuACBvWHn8YS
-        C3sd3A5WTY95CYa5V08qwIzI1PDQYLBe1U14rg4mtbB0j9aoin15jseA3rex6q0InFzoXG4HYh3d
-        pmLsveUBU24n8lv/DOmjkfmjcf3x32hZ7hSBx0uI6Z7ni5S0icLJXuvHFEeaFFH/dWngJ/Lu1L0m
-        arT4bUhgluiMemWgM07C2zfEgc0TciAOmAKnL0BYvzDZtDvN4+asXuEDnSLE6iuIyMaIVKXamDK+
-        fPXNdIC5DebLISCKuXQDbfA1BM1cj6Q8yP6w2AdIoJEGM3XMhLLFz2sI9tvghC3Ou7ERr00JWIo1
-        NJvxlg21Q3XYLZpDPHxkw7rOlQ1APe5Qu28gGKdTqkKcTxrZlqY9sF1g23/0oD7LtbFekycB3/zA
-        qKfAGznozXAwzwj/fm8y6rcMd+Ik0+NYMNBB0b3+4Tv5t5+sl6XL/ujD4yjMoNNOTQ7Va8OwrgSR
-        tyhqeYZOhyjWdigZ5na853BbHA70uLf3g2C5ogWVE89jjROUod8qz82PD+PnvTSHdfRevXJ93S5k
-        9dRsWI0hMpUvfiOQdSJbj2kbw8zcblG8dtOwCnHpw48aLWQ4oLKqf/wiT7IAn068H02g4nX45jsB
-        zXvrzmqsaSXYu+GdHufzgy1u8BjBV18j+V4EEX1NViZ+8YT++NOin5/2n/5/XHQBjC+RyXB4bnf0
-        2LZrNf/q8bjLP9g8O2+2VP4aw/fuaGDd+myH6R0HMhRMWcD262gPY4VnCIUuB6S39160Y1An0HfX
-        jCjzkAASPgoIbq3xwSrPjQZTOEWEoiMwJI1FbBC1sK/wdjBrfLoCI2WqzZdw1o8dAqSZ2aQVTgI1
-        dxehzfAZPPq+3P/gNdWXU+mx8yC60ESHjBoY7j1eCFcIo8PwpF52SsGqCDCHH9E7ofdXT33x3wae
-        IHJEUps9mJwoQtBE+4w6NpLY0lHdBV98IoIHC/CnPuVCfyEGeCGl7C1w8KvvCbAGPPzqBZRi0hBm
-        FYvRc5LvwkEXE3wMY6Oa3SgLQEZn48un78P008cm93KQaHl2ursqtgr9UR4R/9WjAx9/XPjVk2Sp
-        Tqdoco4VBF5Vx3/0rdDLyQpSLRewGjsfYz6f+fPv/OhxNy9sksd+Bd5O89FsUsg+61ZFMNjbhHBa
-        OFRrLHgQxM/+hdUoaMEaYX8DS7xMFHPv9x/+Db3zdf7mQzis7FD4CmhlDZtLlYBlrfcEdq/5heRc
-        56KpveAetkqp/hd/XVm5wgfZ0j96crUPrFPebYwpFqLb8PHXxYfXkNujSMlf1cJpsvrjY4gNFz39
-        8tNc9rrep3tneBlzigwbqqfXFqtR+2bsdBN7cMxPb6wmIgDL29x3MD80HfWI8WCTRLsQ1p1GqXnc
-        XqvlbR47eWN+SrSpDgePyTRMwCF68ohzy8+wZtk9gC/Kf6ihjwdjvRZoA7YB//z6H6QibzxYUDC9
-        J+K+9TDOg7b++DJh+qU36Dq9Gzhp9kD1k9sDkt2jGWrUpV897g6L18e+DN6RRnboWBuk9JcrkJf8
-        QrYkuQ5sXz9VkKw+xrq/NcAov45XWd9VBXm/7iVYdvxhlG91vcNGuX+nzD3mFpzOekTR6bI3RtQf
-        S7mw1T192BAPM15JCbjIKqlxr9SUN+qBBx/1tOBmt28BEfEug+t7ueAnBp/o6w8UsB1NH6MEWd5q
-        do8GmBp5EOlbD7V9jQlkQHoQ6dnVgJDT0Yb7/bEmu+41pMvolUSZhOZGStPSAdd9Ugh/5y1se8Xr
-        vCvSAWCvD1ZfumvM8UAb8PNDVMH7/M7jDOZoyKjVHnD1h48vXgmxW95P6TpPUgKcZgVY2y3Hge0H
-        K4D0sT3gL56BeWX9DFLpfMNOqPVgsE3FgnkqmlgrSZ6y8AxcWBoJwT/+P0eh2cCfvuPc0qmIWZIz
-        /PIBbOB7aLC+wcWvv6LdqQ+95cA3IpyWPcVqfT8Yu8BgIQzO6RUf7rfGaJbnJYY4POs0SMQUrLQO
-        YumX71cl3YHKZEAFEphVfICgj1ZyX2TlV2+HB6mMubp0/p/8/vlts9iqV6U/oj0SmvbtLT/++e0n
-        SM7rQyoIl6qDbmqkf/wzJrh7F6qnaoudKzUBlwVQBl//lGyF6FaxFdpvYPRVTLVLf42+eC8Cy5Uk
-        6t1vL7C0l0MHrQd7Ec45ZQN9aadVMUXXoToBD9aaz3aG5E5aJOqqlq5h6OZwCD3993vp+DgKMSCG
-        cqNqPZve9OVXsrIwGe1UPHn0BcpMlgIFYlQdWm9VT+MZlHW5+eG/t/78o2bXFQR8/QDSyxH36980
-        eOmuR59T6IO272LsXHZnMMsNbGDbPX0ii9OtWhI74aD8sEW0c2zk9dk9WuEylztsRq1aCRXudegn
-        homx0HPDjDX3j97CnvIpvOWr1+Vw//bozy9l2JBs6YphhrVNT6puIEIGdu5GJ7tcnr3lJusFHHQ5
-        QQU0+3QqXbuHVmltsE0e1tDlby6Bz8CtKbYGLwWTd+agGJwz6mx91/v5XSAUE4HIUnuoGC3vPPDq
-        +U0PBIsGsaXnG3Qna0+d/BaDmd6hDrVRqbAzOsCjWuKHkHmbO3a2sWqsB1eyf34CdtuDF816vRDp
-        50+CfrXAclVUFbI7O5KddFeiOboBXhLt+5ZsZo+mrA6jWd7tAcLGl++td/u+yqOXXWm2HZd0Di+u
-        BUC536H3yh3YoiaJDar7kmMDPOWIjfZgwuvzaOJv/I1dGBoFzJuDSFWTZmB+RKQHpyWkeP+eXum8
-        5wEB7wK0CJw/BzZDo5PBcFF78icfxMs4gtB0bwRGePRIql9XKJP3iNFgid4qmPkGtgLlqDUTF7AL
-        eYnwpy85aFoGm6f5KudXIaCHu/oxyFpiV/ZCEWIM6QCIogwEvkXOwG4VadF8E+48PFFOpo5jO4xX
-        C/WqEEf1qK60szfuuxuBsp9n9MsP2XLXqwYI4FyRtgxaY/niJ/DJuaAoqStvNWHBQbpUPtZNqwSL
-        n08QvPygxtF7u4n62q8bqI5XA/vudfBm5zUHMDp8nvj8XT8JVG6Eq8md8Ombf6v+hA20WLmiNHrP
-        1WJKsw0+kXPHmua8fvGa4bu8pdRRmxqsUVJlSh/vJuyjyTb4Kxf6AMFmQTwN+Yp+CBf+9oOP7YYO
-        u8ut1aFkODZi3/V95yehUjSvC9bpbgL9Bi3FT0+gBel6JETWzYUfQ1yo1mZxOu3MYf3jv1rs8ajm
-        Gk8+n8yaQd1d4A6zhIU3SAWxok6iAkZSPV+B/exWejzl0bDuiclBdHtLVDs+abRykm//9Ct6I8ka
-        2F7qA1AMjYNe3YsOc3Kye7hqxxNRnGgcfvULpzo/IDGzl2EyEiuG+3m0qNX5Dfio516G2+OGx6q8
-        jYyl2uTXn3+KeMYlA4uSMoFnISkwnvWCzXcBWTAbHQNJBwFWf/Q/ZqOMck8K2GeV4g28Wxai5sod
-        wBdfVFBtLJnuU6sxxl69qzDFUY8t87QfhNGuLOXnT6mC53jL9vzhwdpsXnh/pR9vvSNNVeRVdGio
-        tIE3pvdPD1s4d9RcHz1j6H04Q69FMdnJvZtycGfy8P18rmiToMajV+5u/+GbqAGLwerY0KG7ooIi
-        +rgYbIPEDLD++cFq1+ce0+tyVW6SdCLC1/9bhFegK9bzeMGeEhoeK150A831opA5LhqP3zhuAD3Z
-        UtF63pwBrWNPl3NHz6gvt0nEODeWIVetG3r8zv9YN7olvO9O8m9eMTDsFDFASfai/s24eivTRAiF
-        ux9hvdNMg8DxAcGXn+IDUVaDRGcOSV9/96c/U+amsgnffC9Q9dns2AplaQNTfOqxMaOqWn7+rHTL
-        3+Tr/7Lddz4oAXVU6NHWt8OsqFUMe9IohCMfFfDfeZP0ka8Puj+Md8Dm2mtgbZsDNfkt+q/+MtoN
-        QcstLKJ1e+5WeD4NAdbZR2Ar0+YNnDhCqV9rJKLowzewHS0fH7eVDtZd4PjyT0+okwa8gfXUkqKF
-        +PgSatRb2mro4P3ThxR79zoao9B8w5ihhqxDHgDhUnkJPAfHjLqjOlarLd0a0FAJYwtLUjphzSkk
-        z+jP2NMLe1jGPcsg3JIa63ZnMf6OHB1GhKtwZDmcwTJ3Q+SHeFYprsW1oqX43vz8HWwWzxDwXnvq
-        oZiL7be/cqyT0qsJ5U8lYj1POvDT24Dju+brt63Dn37nmyeObEWgMXY4yA0Aur1Q8xNHoD+2Rxle
-        NkVHXZvV6XSHXABvrfb5zrMe4CPHtwJWRXDAl8MogaXy5QR8+ye1heth+PqPBFK/igj39V8XtCs3
-        P//tt//o8/MXB3VChEaUpYQ/ZDms3ILHf/hHglwLfv0ganz12pJImxV85ynU83OVLZVITSC+VBFH
-        33kjqcLurSz+ZiZjKGJvTW2kyt/6+ePXDQYvFpCtsUW1Ez+mrHLkGX79CzJEYBq+fiiEq4ZPVD+9
-        DmA54fsKFbQ9Iv4yugPhL2IO8bT9oOr2vhvM2tsctPBmwkh8PaLaqEf5z3zUi95BNcdbmYd9sbo/
-        f3jgR+/TwW9/RuKeG9L1O2+GQtIdMMZHHC13Lz7D68ocBJF7MeY2Rj4YE7L56RFGsSG5MF7mlR4O
-        yAILucsbWJ4PLlolZnms2DGk/P27FfCf//rrr//1u2HQdI+8/l4MmPJl+vd/XxX4d/JI/s1x/L8p
-        /+cmAhmTIv/7n/+6hPD3Z+iaz/S/p+6dt+Pf//wF/9w2+HvqpqT+fx7/6/tf//mv/wMAAP//AwCZ
-        Ns2n4SAAAA==
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc668afd1113d-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:24 GMT
-      Function-Execution-Id:
-      - pbme5l3ic5k6
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '224'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 874088999973c1eb2bab5aadc2149d90
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 0804d410605ce2d1b7617943c8185427
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "What is your favorite color?", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '105'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R62w6yyrbm/XqKmXlLr4iI1GDeIaCiQBUConY6HVFUTnKsAmpnv3sH/53d3Tcm
-        HBJD1RjfadR//Ouvv/6u4ix59H//89ffRdr1f/+P+d7z3t///uev//mvv/7666//+P3+f28mZZw8
-        n+n3/Xv99zD9PpPx73/+Ev/7zv996Z+//v5o4ok4L3fRNo/PwQG7nZbMsUozXi7lOoRyk2jsqJ7N
-        dtCGaYAtWBeGzfUrHhdx6EHk9Du87KUtGg1PLsGsgTFr/zoYouk4GtrmEceQL1aIpjeyQ3BOjwTL
-        zbcdmHqP4LNqcmbpZW/QJPEAErA50y+9mU3VYqWD6gVbYqRbK+bmt0kB8PbBjvUoxmwbZT48vqFO
-        l5Vao26lGxKq1qsPcxVLDfoKrAq4X1yIFrYPVG20wodjcbnhocYRYnrjD+iM95hK7P7O+NITBujC
-        BmPrqRyMdPvxUzUecEqHPXztCZ+dDn1fU0MOxq5BQ3D2PER0WhCSLgNjKoOyhBqiiDi38w1V2ilP
-        wUCbBku39SoYs9SX4TwAIkde3+0x3yxEdHOyM15K7MP52o48KA9NzNyE8nY4+0KDAvdEmVk/zrzW
-        8spcX7e9jtGrMOIlR6ccRlgJuOPDOhvurSaosBHuuBWUNRqabXtE6iN6UmVDUz6NaRzCu1hyyr2b
-        YA/F46ggqhoMVzi68nm9Nfh4mcm2lVrzZnuqTFCQdGTkqvZBLXRxinYX50WVbU3aKiNaB9dzZJM9
-        RzIa0POpg0DfWxI3URGM7y+/q2dVD2hVtbY97ZPGUybtxoj2inO7r49lBGifR0Q3jk02Ld2XBrlz
-        bbGcyZCNmV890LSyrmz3bVk82ZWIIZNFRNf2YsdXtzWSobuWSzpuS8KHRXTbgVJ5d4K9VEfL6wRX
-        qCK8Z06Cz3yq6cdCU8sNYrgpDabPPVDQfv0cyUHfb4zlfXAs8ELZZXbyDQ0mg1xC5/ETcYInR/zi
-        aJrK+HQjehV17fTqhBwWlcqZ+/1sOOuoIcE99ShWi7xC3JA/E4hunRDLwwniJxNACRuxJSfaCwFf
-        +J8Q4rN1Z7puvzm16IPCWFy+RA/HDRK1U/4G8bxz6HoFx2y5Mbca7IvPkemWUSJ+RZcQimhizHwx
-        DzXO1xvWijYZeFJlL5i0OvPQZql0ZPPSt4h3quRB+cQ2w7hdxbR+fmTYNQPByHTCub/SdLG0lRcz
-        elYGo3ioGmhe+Zo4m6UeSL1V5ABFIRI7QEU8aKcuRbty7ZND8haziZ1vR3j6TxHLHhY4a069BLp7
-        M5hpeqExLE3YwUXSCDGc5BSPi5sswqWpFIYvyTbL/evLAqQ8dOJxDXMu6t8JxEOkMc04XDmP3CyB
-        zXoVzPuH4+/6ruxASjVGvCI42txt5BR2JfKJxhfXdhB3mqx6B2tD+8BcZv3zvnbg9304Jd921P1Q
-        R7R+Lqi0Pet8Gv23rJ5P1YLZ4uFqU/3ywkrpqmu6LqKaj0/7eYV5/7FMM48vr/6xg2jFMXOUkqKu
-        P20UoPX9TGb8akdqpHeQCjXC6+QdZlPXdDvY2csjO4S9bvNx10ngurWH15c655RkMUVz/VFYpyNn
-        UTdSWKsnwIryYgFj9zACVKrAXD3u+feI/Te6GMeM/eqF7bP+AZZFDbpKg30snW12RDZ6VeSHr2yu
-        P/jhfaiYhj1t9vkEkno32KE+RdlUGGAhr/p8GRaHZTzWa+8KXqiumENXajsMdn0Hd0hVcvTCjI/f
-        h3JFp+DLKLzcRTYsviWA/ZXw3D+iMY1pEMEqVGJmM/KJO9STB+hPzWF7SfoEkxSXGlpKwpcQBafx
-        5O7UDtZ6puOlUMTx8DZqUIJra5BjsrFa/sEHDJGZtnQUTrRt3y8rQaniGvi9lnJjXC1HE/ZqRNn+
-        khbxNA1NBHP14+Xr9IrHTRZ4aCXiCzPWxYtXWYIsVFdDSfQsS2x2aXMFnNTx2Tn48D/1Ae26HZhO
-        sR+wskwt6JWnx5xWeRvsWzzDP/irTn6GRjYmPhTJ4khL9qZxt11/PFTLZkrMJn5l03a6TehF+owd
-        92XV8shtEzB922ZbU3plw2t5V8DbBibbF+QYdOQ+THDXhYkKOrLbzvZ1X91W+Zdt190iHo9SQFUd
-        QovKibCzx8PV9yB3eEq0GkuoUw/FGz6yEZOd4jyNHp86+PO98YDteHJXNkYZPjREX5r7bNw3ICBL
-        k19MV2UvZqfwewfL+/p4+HqZ3YXmTYM4X7mEBPbSmMzATpGmJZ8Z3wTeRZtqACdKdsxMi53Br80h
-        QUvtGJIdOjrB8qHiUFHNdM12S3/XjhvT1eGsXwxi6v474I6d+mAeK0420oNkbPMwBijl9khI//4G
-        /LTUH3BRLj3bHD7QfmRTs9BqASnRMJf46B8/OqxgWzBz57q2tLloJTqU/Ye4Z6VBXe4iBa5bppMt
-        ri7ZkOx8DFex2hMv6CZEz/bXQvUWS2RHH2PAEj9UwAofhMSi0cSDeujfyjeLYoLDJ2n5UXhr6kdD
-        iDmbZRpPoYMEkC8PhW20784Yjxc3gW6ljMSp1o3dCd9rhE7M86iKtzaXZv5R5v2nzLzzeLqd0wQo
-        vq3ItpcKNPffHXp7eWXm4TDYA2llHWb+YluxX2Y8+QwUhibvqJr1asDalygpvk++lA9tHfThVdYg
-        yt2EHDNh04oU3ypAaZMQs48sg5EqUWDJdY2qM3+NdMp26HtZ7Ihm6mdjXB5W3g/PcLbtSdzk21eJ
-        yBFpjKyuvTHg56oBFMk+uTzvdjy8g8ddiqzpRSesSPE4PemEZv4iuou6bCSsvKL3SCwqXfR9y0dp
-        itQwrTyG3a5vK6Nbdsgcn/sZLzZx337NEOyviJnRrEd7EL5eqD7TnUo0C432gLGLQa+mK2WHgP36
-        PVR3pNuzmY9aVqzqK5BjeiAb4QJBUy2qOwSPVKMoK59oGG/DHdTVvSCH9dpAQ/qOSvA/0oC/pN/F
-        07WsO5SHjke2utwirt8lAVr9UdJ30Pmoe6eDA+cNOHR6FseMWxsvVOinHMn2dXoF3L2tfTTraYyu
-        jMazXijRzfmcyca5jLzLaFFCIrsOVUO0McaRXCbo3tc72QXWOZj8xbpD5SlriH3mbTBVxFfgMF0N
-        dl/HfjAAihIYc2Fg25dn8kG4vQC5hV3R5Xeb8cmx9BQtL1XL9m/v3XK5XYdodFeE7NdcQFwIzQk6
-        l7ypGIu53a10W5SHfXSgU2e3bbvnBx91lqLTFdMBjfhjTcjIsoCRs4Hs3qSKhpIQaubm5a3lH6GP
-        YKcs11gyklXAp4LvILAE74/e5YfhpAHXlZw4y29hDHri7aBvpueMVxEf5XwtoYNgYfrmGuVcb+4T
-        PNXHiUWzfp771VFnPiRaETTGbz3huS5CZhfPQ9CbJJvA+F494ixeRyQW6HT81Qcx1zuOBsnwGngp
-        3YY99bNmj8fy46nZubwS97a8ZNNDK4/wUsaWmVvy5ONO3eiqW2sFzaunY7eG9fDQUlljsmk6A41p
-        YVjAG91kx1PgtlImrWUIlU/CfPMgZlOnRG+4JAplZih/4qoAKBEKNuc//D8+nNSBR7AEst2KlI9+
-        LChgVdua4a9ltCtF0SJkFh3CUlFV2VDvdyW8P+kZh0drjabYnxy4N6ZPJTFcxdy9jb66P5o2e9xI
-        Z0w3M3Mgfssl82RZ5MPPHzWZ1RBCX6M9yKPzRkX6RsSwMrOdMmlUoIT3ngrhk2RDN6IcPPf1mvVM
-        3lL5YIegIPHINEn52OPnzCJFhDJj+HrZoPq3HgfbT4lpXC588PcbD3LvElD+1j/ZtISDCYUvWuSy
-        F852FZT0CE81Q+zYLMd4LLydCE3c+GT35Id2Ehjy0ezvyF79ZkG/R+CgWe8x19O3Nldu/+Xnfs/j
-        yo9QB8cTrxlZe9wY7+9bt/6t94Ua3O6dbNSQUMYhlVNeGINwuwA8cebQqSdWy+pJU+ChLB5Y0l9u
-        y+sNvyL5VZ+J+5q8lhtyPaHZr9KxpmI7He8Fhq92SGnFPm+7/agbRZUviUJcyfWyIQztBN5Lc8t2
-        zSfPOn5tc5BqKaCF0tCMc0PMYSzOX2audwHnQrbCoIVbxPTdrs/o5tpp8IyikTiXS2kP0eY9AVkj
-        RgzhSg3qL9b0T31Z8vlg12xMPDTr1VmPh+2EuByhIyYyRYftEExx2jWIebie9c+CdxTfGrirjU7R
-        ytSCKjh7PmDNHYiji47Bn1looYu/iphDJcPuuhGV6LqZYjwW/Mv5OWk6eAjSjcJAa2PAeOtAu/bW
-        +KN9S3t4FSsTfbQ1ImawWfI/+KB969nfrXR7BftjjvbHnU0M8voG3ebFUxRpLcUoXILRtVy7ooel
-        7chjoLU97bRKAid67Misv/74cRAMa2R+muzaub8rlDwGlz3W6YimXkY75VjjiOiL5SEYxjgQQYq8
-        jNb1SWq7e1wc0cwnzF0srIwvx5OoqF/+IFZT5fYkvC+PH1/ilLkPexJ7xYTHC4VET3IxoEv3ooOq
-        tUC/BwnZTD/UJlLb5sYM+V3FXSNm4h/9fJj9GzWNL0XeaeMx+1k1MddATZCvYpO4Wf+Mp9O7faBz
-        /cjIfu6PbroTDe3P4oXK6XpCvPlsGrV7SPVPn8Tsgy8SHAJzz/BhfPNugG0K2amPqXgfvnZvi4Ov
-        noui/OnHTMJns4Nk0EZipWsf8f5pliDVa5UdrunHHuv78Qi3Nrkz+1VkcddsW+vnz+n4Vmy09FT1
-        Dg++w1Sb85DO/ohU3ZSnbNZvWjzJ6+8DFi5q6aNVNJvXkyUr8en0pFy95THlRK7QG19i/LLCIiua
-        qxqBHfoJnvVKzIPpjpHrth4N8OdqTE07yICdwCIk7292fywXCnp9CSKzv7DH28Z4QI7iO7ESoTSG
-        n35ARpiyk5n6aFgTrKNU2GlUaI0hphYNKfITb4Ez7yYYzFZjDOunErFDt28Ra9m1QTtC9+TwSgxe
-        v/ebDnijmUybNluDVoNZotl/0Y6kX3ukQSjBWT8bZPbfnJMqkZGpP67MpOeR19fsIPz0EVUl12uH
-        jGgUopwkVPZcM16adNLVjznJGK3Md8ylRSUifKmexJxIbo/P+xqDpFOOVzL9xmOZnEXYeqPBLkL7
-        Dso3cnOQhfJO5fPuHY9Vl4tojU8ucbSxCEZL+V5hXYwF6b+fD+dQeiL4vvslidv12Yd9WhFShRjk
-        kN28dpo2dQXRopwInmQWdKvpFoHgr3Lm7sMD56pkeNC973eG7/eqnX71PyTSm9bmNkQj06YjBKJ+
-        xbJ1LeIZD7BSHx4N0a8dzWY9OKDS/ep0FC6PYJrztV9ewHbefhH/9AlcDCujt9lv96p6n379gCUw
-        qqwNTtUbcq15E+dhE3uS1+yB1p9kz3anLc3mekiQ5uCO2PduH48raU9/fp04bkGN4aa2laI83pht
-        yHXPxfeUVmpD1AELhykOKCvsHIREBgqF+rWn7JvslCI9msRS/NTgch9Oyuz/iG9414CbqwfAfmkF
-        7CG1qc3eLy0B/XRuqVBrddbF9wNdo7RKyLY2LtlgPG0P7RNtItuPdeScHmsZVu6zJ4b70LIxn7YR
-        PFNTZRte3mMeejFdz/zJdAdS9FtP+DzKB3HCx5MP/Ybu0Kyv6Hg+asbwOQ0C2uDRxiqL3uhPvlPL
-        zxuxPDcPJiXavkFYL0yyvd1u7XTPxgQsPtlUnIhpjGtuSRBmmz05Nsxox6TWMNz9uiDaO3zHw1cx
-        I/TxPibbuOePMdm3zQTqd3wwV9BZOwyPd4WCjdWxvQlmy9EXPETr65k98bZF09w/0IW9jJWWvzPq
-        fWQf2mO7YdtLvOVjJ0kT8gt+YfvV0ranxD114ObTSDbXnWGLUeonUCXXlPiv1Gj7fFNjIA0GjNZ6
-        aEwmXzpoUckHdipXOWKZcmpA8m8lcV7O1pY2K8WHd5EAHfeZhXhhLSJo2vMWrxXZbYcfHwxls8XT
-        ZOXZSI3mDjxp2MzHbjsWRHZ+fEfsvXsMhqUpmqooXi3yFHSSNedYF8Ad3iq9NWSL0HDJTfXU6g/i
-        pJZlT591evzphd9+cu4bt1TJw5PCdm/WZVO+7E1ol5HP9Nk/cVndY5jQ3cGydGW8vR6RAzM/Ycg1
-        agzpO8l/+E12sz6u9/HxjWY9gVVf2CMuTktPWWyG+qdPs9UzqClStRrYNvGX7dBreoNOBELmKO+P
-        MVnC3kLl6dPQIYs8RA9OhJGNnhXDreEF0yAKGmjhHuHFycJBf75kDpw0Y8EsLdvFPU2HCp769Uhu
-        hnPN6OfwaNC5+JbEPW0oZ6eQXdEjWAEd7qlljK86ESE+H+9kn5+QwfOjY6EhvZ/oQk/deLjH/RFm
-        fYCnLBOMnnibFC6Nb+DVUWyCDtpOU+ZrZq3DiY/4c7nDSekJ2wvdnbMx0hrwnmZFdjR9GVPTh9Gf
-        fOHHr9w7ixiSg/NkZP4eMdXWHbqTrTj7wQxNdnOpoFovP8wp1L39y0vgRISQ6cX9kE04f6cqloQb
-        Xuhp/8ObDq6f3YXCy9ka/e7RAxphKVDQxiLmspPtlJ6MC3ZwZMOY3nHVoTmPJ4/LpTTGZys/4Om/
-        RLzW9x+D5/X9CnmIPWb4cRNMy8ckwoxXBPvFIasf6i5Evzx0e+wbNG6xFcI27Bumi9oxE4UKTSiW
-        7yozgntoDMH56oG8H/aUz/pEtMevheb9JPt5Petf3leoMiEPq8yDP/h0ElSDGGIZGcuTy2Rlk9xD
-        Zm7CkzHw1SiChtyYOO8dQt0xO7xRjm53ZrdnYq8++CKCfXW35MCsDeKy0+7Qt31Ls58/2X/6q1Jp
-        wpxDswm6sDhSJVUKhThWmcftUXjr6uzn2I6mC3tQb5tInfmLHWQktlzuHwOatGiLa3qc2smuYM5r
-        C31enzoboyi5gxlpFq6eSm1MSNwJQIvsSlz2oNmojKBD/9JPTK/PUcCf5lYBv2YC7RebdTBchjqB
-        8cRXs77Y/epVgu6aL8kG3+V23D0KAG3liczB+Yr/ydu/We/TaWslMdee11LZqyElu22kxqP6+OxU
-        NXS72U8M7ainuwf09urKDrfvtaUHaCkY35eCh+QZ8jF+mQrcAjCYcfMVu18oaQonZ39hh5A+shZd
-        NyIk7sFk8/zJ5k/TVX56hqqid2l59HzKwFD7xSh7D/YgllMJft2EuBe9S9ad+akDqRYDkixp3v7x
-        x6uFkNKr4GK0EvWbBaLcl3QVflWb4/teBiFRgK6v6ccYKFF3v7yPZpnp21wInQFxVWiJYdZ+MJ4v
-        LYZUeKzYJoNHMN3MFq97O/mQ4/WQ8nn/r8qkhVt2yuARD9X3U0H2CXOm8z2NJ+FtiZDSwWSX64cE
-        A+uFFByyuWJh1ruTTzoMlrnckV8/Sv5L08FavCOWUOFp067WKvXVmjJFzkJvxd/8j+tyzvztPuPd
-        SZ4wzP6VikfrhrrNC6UwZWWFka9KBj+ZIqClMNnEOFRgjO3XCdF1M8Rs+yAUdd+b36inVnuwn1/I
-        BUs3AUnFljn73jKWo3CQAKPTiuDkvAyaMjteYdFJA12kbPuHP5CZOBk5yMsSDc/LKfnNm2g453PL
-        tmID+n5LMs+fAtSJUq+B1Qol2RnJJR43wVtUxRMhFGb8SOb5KjiRqOJp9icjO62v0BuNiuU5cGRp
-        d2xAl182+eWnA68STfGX9zdzPWORdQQ1yU+/UWmxXdt9clgLaDw34jxvDYOV9rzmKEDrkrnGfdVW
-        vIp0uK/5lv30zGifG3213eorrFivHHWv5V2GGQ+IrSx6Y7CWOQZRvFvEoVJmU7sSHRTf9htmGYWE
-        +JxfQj/lOvGMg8y7NstzYIs0p2+699HkRqcU3us4Ixsz9fngCncKSyeIiOYss2D6ftT8Ny9jm3x5
-        bQcpMHbwy+9m/xf/ycfg2RXkVX3bgFmj+FBD+83I7hg67XRWTo6qn3GFkXb6tl3Kpqu6DRsNy4kW
-        oSnfWoK8KAyHjqzts8Jv/Q6wFX7YcUN1JIpSof/mqcwku9qYLFVOYZ5/MiOHqzG6xlkAAxkNOdy+
-        ctbbRZj8+p+OzTRm449PB+X0oh+jltqhWj3MXz6E5/lfu/rNP7znriKHWW/zqBu7n99i+738Ddpd
-        gLT/4sfb+2ZM3mfwQXdjAy/oazT4y1s/0Jwvs1+9NZ97rKC/f6cC/vNff/31v34nDMrqmRTzwYA+
-        Gft///dRgX/fn/d/i6L0byb9OYlAu/s7+fuf/zqE8HfdVmXd/+++ypNv9/c/fyl/Thv83Vf9vfh/
-        bv9r/q///Nf/AQAA//8DAN9muKLhIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc66ebe45e153-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:25 GMT
-      Function-Execution-Id:
-      - pbmed6937r9a
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '20'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - ba5b2a8ed740e0e13bfdf1d482561f84
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - d1e10b6e48d2dcb7ed0782d5f86d3b37
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"input": "Lorem ipsum dolor sit amet", "model": "text-embedding-ada-002",
-      "encoding_format": "base64"}'
-    headers:
-      AGENT-MODE:
-      - AAAAAAAAAAAAAAAAAAAAAMLheAAaAAAA0%2BuSeid%2BULvsea4JtiGRiSDSJSI%3DEUifiRBkKG5E2XzMDjRfl76ZC9Ub0wnz4XsNiRVBChTYbJcE3F
-      AGENT-TYPE:
-      - Auto-GPT-2023-X-TYPE
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '103'
-      Content-Type:
-      - application/json
-    method: POST
-    uri: https://api.openai.com/v1/embeddings
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAA1R6WQ+zurLl+/kVW/uVPgqEwWa/hTGEwSaQsdVqAUkIEMJoA766/71Fvqvb3S+R
-        IBZTVa1aa5X/419//fV3k5bPbPz7n7/+/hTD+Pf/WM89kjH5+5+//ue//vrrr7/+4/f7/6181unz
-        8Si++W/578/i+3jOf//zF//fZ/7von/++pv3hyPVsvfRm9C34AGn6CZFtyvz5tgqTPUyKDuK08vX
-        o3MRdEqy7UK6705xzN/yz1Z5VGBHJHWrlJ+y+xIAPLCQkns6MX98vrfwEn9G7CfsDqYkDxXFuXsR
-        PmjjvVy6cXIUqEkq1TFLwEBP1AXGXJk0mfY30OEH6eDRBD6SLoegn2qmEgisxaV2Ye296bRECnTu
-        4wWJwXLyFh9pDrSyXUedHXgYi2W9T/CUSh7Watfsxdt2SlThBS/UTvLOm9fnhTMgGdVuYBczLBxO
-        cPy+Z8QHc5ku97KNYEaAQKboio3pcNw+YRd5FO9Bb7JllnIEldFQiOonDpiw7hNwcoUI24acp2Nd
-        bjmYZ0+D6tf3DTDwrjLQYq5AfRRv4pkl2QI4XVmoXvMMzH4eOmryKlTsF+3HWxpi2fLZ+eiotsov
-        6Ny5h9AoHIcmNY1T8pi4HFaXuMA746zHc23CBhZKwGF92RPAfKDY8E2DGO8aTmKLfxBqGD/aGpve
-        duxZL8U+PDz3JZFj0zO2YO59cG0ySq/HeZcuT1KHsFYBTy03XfrRz0NXbbzdEbvkNMVtRVgEJUYz
-        bPUoN7rvdD4pa/5gT3u6Ma3rJVEz93kn3Ozx8bydniYEIHyh4/MkxwOFu1qtw05BQ0ZoSc8b+QYX
-        SXFIcb1dGdO4PgdXUemphaJjv2jucwL5kj+wX+MzW6Q7qeD1HSK0Rd0TjMJCLvD2uO/w/ureUwY+
-        0071nCeg/gUqoCvMZAD+cn3ivXkM2LQxTwjWNJ+xP/czm275yMv+yejI6B+UcvKCBwfZftlhQ7mk
-        HpVrHypp5nyoM2pWz/LMPUF2rjbYywItFu/TqYZCXfEEyiEB42SXAxwq9MD2pxcBqc8sV3/Pn1y3
-        35I9jWmSt34b0H394FNau7uLOgR7FxuzbXhC80A+XKSTSW+nixUL6b42lffBVbDHf1m61McvB8s3
-        b9Pn0ajiqdjYEJrabofvweHcTw3LJ7hH7hfxwBH70TXYDsKD9aT+vt2wGqLHCXJd7SDhrcN0st5x
-        tDGS50wPeUzLWcvGCdA3OGAUtmdjmc/JBUqWOuDAPyQl2VadBKwkHYnw8B7xoo7uAHC6ayl+mR+D
-        wChXYNdnOhqeb5E1737HqbSAOr4ewNlYrnvT+eUfUq8bq5zmEDU//ECcUsolVXZkC57u/UzRejxf
-        ldsCu2xnY003nHTq6C4EOlJ0HMmCz+a13kAnixY+HNJrOW+P6QTHQ6AiroQULFnSRGCDtQr7xHp7
-        o7YBHXicXyYODN2IG+5DJjBu1ZGE2rFn5NUFC2hfyRPjSduXLDKJBLB0rDCuPl45WQ9MFO4YC0ji
-        qVFuSebZUN2fDOyUy9ubDdlVoF7KJcrfdwC+wmlwYRS+AOGU8l7OL33qYMadZxygbx636Z7Y8G5w
-        GPFHxIymVu45FL6uRNpDdOnZdy/ZAJjjEW3b4gLYcN01cMVTGkjY8Eae5yoYD+UTKd+d1vP09HX/
-        fK/9tWrKaWtPgypZaYNkRbl783C7LVDArzeJ3u5QLpnc1XC20R7r5w8tf98Ljt9yRu8AbY05ct0a
-        /uKHyXVniG1+aBTedwPC9wIsF3CSHWjJ8YfIh/TaNw5oXOjGeUdUf3fvyaa+wx+eUnQZvX6yX54O
-        nOaLUBeAxVs8mg7QD1KfgL1zLFl/v0mA73WLzLrRxGPaAU7JDtKZolb89LNWHmrI66JC+Gr/ZOSC
-        J1/d7Own1YrMLgerLHOIxkjGOH8808F6pyGcgXtD7M0ab7GhihRPOCwIFu3HYBu5NYGbUI8iLpH6
-        6fqxL6ARqYPysLLZZJktggMa9vSQLK23JPImh1pNRbJ/HT7lCL6OCwhMGN17G69nkaNkiuzdFnIX
-        3juDvpK9DqSTWCHR9Y2YqdyhBpud+cT7mhTlhwSnp2Ic+5g6t8BMZ//On+AuuBwQ4O5fVvHB+wmj
-        5nDECG3Gfha2sgLz+VWRpYNvb1qC7Q2u+IWA0rdgVNrwpta0mLHhiHL/jqvqpkw7puH9gFtvkaWY
-        g0qtRHg/y2E6RVuQQAnmCkYnpYzZbSsloNNHRk3VJ/GaDyHkj+OCLTeNShoO5xCEXEQwMtQcDOnT
-        aQC7eAZ1tke17Jol7NQi2xgIqvuAkena1XJXooYwKZkBuX3mHNzsqcTa2g9++AODezYhvvbO6Z/7
-        zencY2Nd39DU5YBfPmpqhKMJ5tjqbKV41jscxOItHq7tXZJfV12lAf+2vEVMOR6a1+5BRnd6x9Ms
-        NiZY+ythyiU15nCeOEgVp8TxmzlGH+/sG7Ri7OP9k17iGVO1g7k5jWiz1v/Sm3YGE0fJseOOc0mq
-        cmfCtb/RvchbbFEilQfjxFvUFI+3tX7ySC0Tl2K3uStsuHwvFYzVXYzdQjrFkzv129/9EXtanUHw
-        o177N+bIrz7Zp08UqOlRStFJMdKF9WkH9YrLyJ2bJWNoRx/KbNze0bK7vjx60jUCwm93pBbpMViE
-        4lsDWnA63e8SBETQOCGMPxcVLe4h7ju6HRRwU3pA1++fkiqrIqh8nxeyXJev0WvKC4JL/B0RvIlh
-        z973xYRcfhjxygeNpbOfBBABRX/4EevPwQm2+4NJHb/5pjNTu045oP675rdeLvNiJtDZBD21YUnZ
-        2J8sH8qxecDOJJllW+GJUxr5YlG8O6N4JMdGV+7ysyLAOEY9je3CV4enY9BgxZM+c9+Fqj64nB7E
-        UxPT9f1U0OEa6yUqjWXYfCSg3HYJ3rnt0etEI7yoKdAfFNc3Bobb99BBQQ2OhOc2l35+VIYPj8HQ
-        IcHYG0yEeufCyFUuaz8uDdqfgwsYb3uBvDvN6BcH5iGocGsidepqg/zwi6DWoP5eIcYk6qGvZkQW
-        sI1N4k12ImbK+SOo5PLmJTasfBiGu3xDDeOrxXSgXxfepbRHX2/TlzTfhAhKJ6HC+zhOYlbXSgIu
-        LH8SJa0+5YLqhECdXV/UPm0LNidh4gCzLs5U37xOxnTXygJ8erciMn0+vKXU9QxuT5eKsPV9SD5o
-        JjwlR0T1ozj3LFxmEy5ufaK6pJv9REVVBz+81l+55W0FY4zAEWQJErahD3guWPMJRyVqtfHeL4Kr
-        mWDlY9hDI+pne4lcEEQRRhVwrv0UuNMEYvtlIRDFm3Tsk7cOvwN5kLFM3/0y5mUNPpHsYiNBvbFo
-        /O4J8+gzUH133RiTYKq3P/2lLqyvMbtat0C5KCwinMw6brb66EB4eyfUPF926UBTF4JItyXs79sX
-        mLhWuYD38Xam+BXUxiRliy7zrerjQ3GtjaV1aij1m9BDMBBK8HErqfvhMz0I750nslfzBI9nWPzy
-        wRvkpJ2gthc3pOPtj7d8t7Ijw3aH6TWOlZg9s1cIqsuxwG7THbzlA+7dn34oueOxn4GhhGB6dRKR
-        Rrcux8Pmm8D3hjjUDjcl6AVx0X/6hernDy4nFxMErxvLp3tk6PHMKbMPOV1asBOimzdv+XcDboJ5
-        pUeh3pXzW4QhmBeJI4D/sng6YWsHtZsiYY0VB7Ao93sDxe+eRxJ/PsWjNB1chVN2JsXndC4ZfGU+
-        LD7+E9+2hQcGUb/5UG6Hmrr6VKWDIsZbaLVii37180dvDOfTByOO/7J59+R24FQULbYGaveMEx4F
-        sA9LQiZ4f3vjln93MDvaIj1UWtBP/mBcJPGwlRG3FdK+xbzmQ0fSXCI0U5JOsMMh/JhGRCbPyNN2
-        EFwe4DIysVmQz596hDQ2jghQHABWInWBJtzL6HvMI2PZp0UHy++G/OFD9Kd/PCcDpH22jtEeNvSm
-        3B4bkyybqYiHMF9s2HXpATvJzu+H21froPHe47W+eI+MeV9D4Sk/KM7JUC7oxSmQyvXrz/sKd/Tc
-        gp5uMXXLg97PvRibamULNWq+eGLj5Ywr+EmHBklXeAZr/lfwOg0u9Rl10pl/5icVftMI+7jxPcor
-        egSjnJtQtxtGxjby2wTNsaPU2E5uSpUuLGDX3Q+oY9y1X+562UB1vGWka+4Jmzu5v8C560uUP5jn
-        EaM1HUUjmyNRNklcUk78LJAIfoTd+5UYw14ettD1xJj4GaH9ImmODaLGO5J+78z9+H1dMthj+Ult
-        o1mMH9+BL0Ji7FZFCthGDLfwql0fRD47b8aMR8jBR9Z/EDeezulsbpVOmQQaYaRdFK+NegeBQLo0
-        dP+Ll2kQHbzzKKAe2tKSwKhRgG5pPdXG7yld9V8Nqo+XUK9kRzZFstfAIwt2a/3nKaOjxgGmRmeM
-        q5Ma0zMYt8B26JsI/quNhwuSTBjzi7zytb5vzpPeQd/2e+yapQ/mcjZyuOoJMt4XZLBxLjIoXAdI
-        91U3eIM+VAW0xcJd4zMYtNu+JFBGHKIuGM7lOH3bE2TP24Pke/+dFtjauaq/nJ/YrLOyZ8+84MGL
-        czFFc1b0M8irE1i+IkbK2/K9cVbFCj4leqBBLErpLGxn6Y+fYj08Nf589SGB8gQc6tdYAEx9eNzP
-        z8BYvfurPq5r8A6vGRJneYrZ1xgKEO5pjqQdeHjT1TZ1yCuZRmPOlD1yUEL9dz0U+5sasFh/NnAO
-        kgatfMBjA6UuFBsyI3jeHXtRHppFCTSWELVMtZL9+FPuqQjjyW168m4lHm4ZyrB9SGw2lFWI4I/v
-        2fNNN5ZXkJIfvuMdn5wYnQ3vBF58LFFzvyHl4te0gU6yYOoOocymSRgWxaEzJXLlkp6a84WD01eK
-        MTrlvEc5cZzgz08orZ3Sz1Hv+LA4LwXqPw85XRoSmGCtX2wB5eSRH3/R6PtMf/qgRgV24YpX1L3b
-        G9DoQYegVQ4azWossKXhcwXy3v5Etu1dALOrXp2f3iP5O0zAJBwcCMlnuVA7OFpsSd53Hfjmh6Dp
-        s5fB1B86F2oiGqgujJt+vHBzBL8oacnh2TbG6lfo6t7mbDLHh75n9rDN4Ob5yMnE+YdUNNjXh8JW
-        n6jRn1BKeifZwbzQGmq9466fCqvYghsMJXqwqls/nXCwg9nteMP9qTHTuWquGXjn/BE/yqooh0mW
-        TrDzKxfvuxOLxxFXBOK0Hn96yBuNs6ADbJxjalUyiAeVRDx8Sgdr9fNkwOJWsuHHDwdq2oaVstnw
-        Lsra3xDZDkm5qL5lA9dsFqwZ26mk15uhq6s/geZEbMtpu8sk6HbenjCmDylZQpmHd1H8Eq59XNJJ
-        w0v2ix/ZXlrPmDfn1IQEciJi2SFnJBJZAciYA+q9xaZst9PFhheFbDDikls//Pr9eB8WvPo/rJeH
-        fIGd9z5i1JKqZBCiECof4Y7GD+q8yQvOUNFukoSk8r0AVo29A0EX1IjTXsAYdqeEg/tHXZL+kg79
-        jGOjgpb3Fiha+9UyqucO3gt+T3cTb3rzNRIvAF26DF2Dhfcq3jsiuOIttWU7NxgwlRu80jbEZnpo
-        yuV4t11olUQjW1E/xEM73wqowNcWbYOjBUQjdQgoMtUgJT8wQNdjmFa3HVJfmZDOv/jBTTdQg1d1
-        Q5QtfALZQTmTjV5YTHzYBx0i0EKkvLRzutjG0YY3XGl43320cmkC/ATv8JwRuDNwzPLrdoLiLYCE
-        O+Unj3zxlUBeFxRqa0PDltGYczgPYU513zyk08Ud/suvCxrYeMPNYBPcLfyLoqNRpfM4dReZdsOX
-        Gmv8BnjMF3VfBRq157fhsdUf+YP/Jh3SkqzXV375ae4cDAa9O4Xyq85kbO8vocEKPlWkZbI76nfX
-        0lj1nQ3f4pMgyKRDPJcdJWDVz1g/isd+apHeQCcEEpGkx3vtZztbDfI2ojH3dNK5edg+YCN/J3xB
-        rFJ83xcb0rd8oElXLylb/WMoG4cbNkFRA+a+MgjuclbhtT/1Q6npF1i2dY/G99XzgMppFbwBvEGb
-        TW2mk/XYk18+kumzv7MV3zog3kMBW9P5GtN984CgzOeAplzRAMY/Qh9qhwxi+9L2HvmorQLvzYYS
-        /pcvTbDPoDJ+OGxspy4dkdQOkNSnhP7xeyc+6xQdSToObFmP+dB0dPjz5/y5P4KpKE4S5LrKwUfd
-        cOLpA9sJBm4l4b2o1mDks5stvxt9QZvryzFE+ZBIsFVJhC3eEOLlgiUEV7398+fLRchfJ9j1Tx1J
-        vU3ZhD5RDfn4RP/g3TRUBgdewmVGEKOM0VVPqmNUHFc/TO6ptH9VCq88NcTC7NJPkzxd1C46UGzz
-        XMQWNpYKJOfjm7qRn6eTd2xz2ZjeHnXTyionH99D+CmhQQ+9NMTkMnQRXP1DctdGuRx++Pvrb/P8
-        jFMW3AYflmLaUeMlRfHsFc0NpBlp0eIHbso+qOFhMdw2dHeKTLY4sInA6q9QzVK+MUt9eYH3d+Bi
-        G3Xcb74hQfFr8diUzzTtv1oWQi93Iuyu/GomwSmDn1OxJ7TxYPqHn1fqjcfxqv/H4FqZEIEeko19
-        N9nkxvIENFqeKcpeu5gN9OvA/KHvidKJu35c/WEwbphHNgKPAXtpTQ7X65F3oV9jXjCFBK71QfJh
-        uKzxSCpoeLpA4BN8PUFxkgWGN/+MPtNZjKfB0jqwNPcYKWVk9MSL2gYO4MZRLXhV8fDkD9yvX638
-        bPHIqJ4bQKrxgfGxinr68cMahlcvI1zfBWDLt94NbmpHpP55dyyne9E6yjXEZ4pNP0iXT5Lp4Mdf
-        DodULKdigyAssGNS4+by/WxPmgJ7h6iobosLo3E72bALHERdeRpSho8gU8RrK2FDS1rAaE1c+Xi6
-        OngvTDhubyG1YU0e0rreT2elvSXgsbe11X/h4w4/6g4qnM2o+0CBMVzbo6IGm/eB7gZBZIs2Sz4Q
-        xarFXslmNl6VcIG3R7ojm6x+pYQ80wv0M9GhjvTQyj9+YLWXXtg7+E46ZOmUAB84ENtfilImEVmH
-        nU4Ztk8fviyHsOLh4xkVFNH9o58/h4cLqy2KqeVfmngyDwcCfnrQrWDvLeWTLyDciojMUKExPZKw
-        Utd8WPUbH48isXi47VSN7vVvHbdGduN/74+91T+ZCUlsaF7tOxJJtivnMjogOPfBFykbXgdMEBUd
-        /vyj3arPhNX/h9P4EMl8DvR0K6bbLTxTNyTt6u9Om29nA99qvmj+zc9++m/tp/hwdjTAWJopYOv3
-        ATUuV9/46WMYCo+QyMI7N6a38c0BTvUWa9Zsp9OmvBTw8Hi/kGoOHWBnMPJwnLbWOn/cG9OozzdA
-        57NFRjPN+uYraZHqTNGHwBnmxrzTPQ5kFBLqnZoqpc+Cmeo63/mTX0vnKwWUky2hSIi1cuKD9gmz
-        PGc4WB4onlJV55T1eyGB9JT98atWPwQ7q78vKLZb/In34TBYbJpPEfrpS+xex7ocL7DdgdVfoZbT
-        uDGvDnoFjVYaaeBEoB8CV1qUNT7YDsm5nwRTuIFtZh2Qast6Kkx2T6BDGSWMCxKDSNrOVFte4rH2
-        /OzLX/6AvBNsbNkV60n/zU6g8aoz9i4ul34ZjAr481vHgX2NP/wm+XyvhDlEKrvoIihQt5sGG9QL
-        0umxTZDUJZuAKKKwLenpberKOi+hxnizjOnd7yCMUdBhtBVAObz3zIRAbgvqvjQhJelt4OCzO9l/
-        9Mnoqy6Cydc/0eN+pGVzOHIZVG56grH4vRkzdRiEZ0pO6/xB9ma5bxpYf49XbObhhg2DdeggsCYX
-        P9Z4zDhkJxgKrxD7cPvqWXG0d/+V3+v8bkbb4xNK1mZY+/tcTh/pgpRnIrnrfEnwhkwqntC8Ng/q
-        UdtnA+z2EZwzvsI3aETpnCt+ru6R80Xbec/AKJz5EMRP8iJiqkkx5W59BpRvdln9SsxICE861ER/
-        QGs9xOx2XiY49/hLlo1cpsypAwJ3g6+hMkGeMZ3O+Z/5FdnoR7H8469z9xIjUf6SeArNnQ6d921c
-        /SjbEJuNwQH9XOTUkyStF7psDuFLtS4YzR6fLmZVdvAqSv2KL008fz9KqHBytqPROl8eAvuDwF0U
-        vtQHj/qPXwjdNMbUjsDoFZmYnMDOP4bUtBbRoOVidPDv366A//zXX3/9r98Og7p5PD/rxoDxOY//
-        /u+tAv9OHsm/eX77b7r9sxOBDEn+/Puf/9qE8HfbN3U7/u+xqZ7f4e9//pL/7Db4e2zG5PP/nP7X
-        eq///Nf/AQAA//8DADKcAULhIAAA
-    headers:
-      Access-Control-Allow-Origin:
-      - '*'
-      Alt-Svc:
-      - h3=":443"; ma=86400, h3-29=":443"; ma=86400
-      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
-      Cache-Control:
-      - private
-      Cf-Cache-Status:
-      - DYNAMIC
-      Cf-Ray:
-      - 7ccfc67169206302-ORD
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 25 May 2023 18:17:26 GMT
-      Function-Execution-Id:
-      - pbmelvnnggiz
-      Openai-Organization:
-      - significant-gravitas
-      Openai-Processing-Ms:
-      - '21'
-      Openai-Version:
-      - '2020-10-01'
-      Server:
-      - Google Frontend
-      Strict-Transport-Security:
-      - max-age=15724800; includeSubDomains
-      Vary:
-      - Accept-Encoding
-      X-Cloud-Trace-Context:
-      - 259a6a1840b1fce07231112aa9f7de8f
-      X-Powered-By:
-      - Express
-      X-Ratelimit-Limit-Requests:
-      - '3000'
-      X-Ratelimit-Remaining-Requests:
-      - '2999'
-      X-Ratelimit-Reset-Requests:
-      - 20ms
-      X-Request-Id:
-      - 734ff3d0816385775c9c45af64184a3a
-    status:
-      code: 200
-      message: OK
-version: 1

From 064e95b46b10664731e27435f1612396f045a788 Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Sat, 27 May 2023 00:01:34 +0300
Subject: [PATCH 070/112] Allow spinning to be disabled (#4329)

---
 .env.template                       |  4 ++++
 autogpt/agent/agent.py              |  2 +-
 autogpt/commands/file_operations.py |  2 +-
 autogpt/config/config.py            |  1 +
 autogpt/spinner.py                  | 29 ++++++++++++++++++++---------
 tests/integration/agent_factory.py  |  3 +++
 6 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/.env.template b/.env.template
index 4c079e00..dd690308 100644
--- a/.env.template
+++ b/.env.template
@@ -21,6 +21,10 @@
 ## EXIT_KEY - Key to exit AUTO-GPT
 # EXIT_KEY=n
 
+## PLAIN_OUTPUT - Enabeling plain output will disable spinner (Default: False)
+## Note: Spinner is used to indicate that Auto-GPT is working on something in the background
+# PLAIN_OUTPUT=False
+
 ## DISABLED_COMMAND_CATEGORIES - The list of categories of commands that are disabled. Each of the below are an option:
 ## autogpt.commands.analyze_code
 ## autogpt.commands.audio_text
diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index 93d31853..a1673ad9 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -126,7 +126,7 @@ class Agent:
                 )
                 break
             # Send message to AI, get response
-            with Spinner("Thinking... "):
+            with Spinner("Thinking... ", plain_output=cfg.plain_output):
                 assistant_reply = chat_with_ai(
                     self,
                     self.system_prompt,
diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 7205b302..8288e389 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -318,7 +318,7 @@ def download_file(url, filename, config: Config):
         directory = os.path.dirname(filename)
         os.makedirs(directory, exist_ok=True)
         message = f"{Fore.YELLOW}Downloading file from {Back.LIGHTBLUE_EX}{url}{Back.RESET}{Fore.RESET}"
-        with Spinner(message) as spinner:
+        with Spinner(message, plain_output=config.plain_output) as spinner:
             session = requests.Session()
             retry = Retry(total=3, backoff_factor=1, status_forcelist=[502, 503, 504])
             adapter = HTTPAdapter(max_retries=retry)
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index 94255333..1e61b808 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -30,6 +30,7 @@ class Config(metaclass=Singleton):
 
         self.authorise_key = os.getenv("AUTHORISE_COMMAND_KEY", "y")
         self.exit_key = os.getenv("EXIT_KEY", "n")
+        self.plain_output = os.getenv("PLAIN_OUTPUT", "False") == "True"
 
         disabled_command_categories = os.getenv("DISABLED_COMMAND_CATEGORIES")
         if disabled_command_categories:
diff --git a/autogpt/spinner.py b/autogpt/spinner.py
index ed02eb44..491e7e8d 100644
--- a/autogpt/spinner.py
+++ b/autogpt/spinner.py
@@ -8,13 +8,20 @@ import time
 class Spinner:
     """A simple spinner class"""
 
-    def __init__(self, message: str = "Loading...", delay: float = 0.1) -> None:
+    def __init__(
+        self,
+        message: str = "Loading...",
+        delay: float = 0.1,
+        plain_output: bool = False,
+    ) -> None:
         """Initialize the spinner class
 
         Args:
             message (str): The message to display.
             delay (float): The delay between each spinner update.
+            plain_output (bool): Whether to display the spinner or not.
         """
+        self.plain_output = plain_output
         self.spinner = itertools.cycle(["-", "/", "|", "\\"])
         self.delay = delay
         self.message = message
@@ -23,11 +30,17 @@ class Spinner:
 
     def spin(self) -> None:
         """Spin the spinner"""
+        if self.plain_output:
+            self.print_message()
+            return
         while self.running:
-            sys.stdout.write(f"{next(self.spinner)} {self.message}\r")
-            sys.stdout.flush()
+            self.print_message()
             time.sleep(self.delay)
-            sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r")
+
+    def print_message(self):
+        sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r")
+        sys.stdout.write(f"{next(self.spinner)} {self.message}\r")
+        sys.stdout.flush()
 
     def __enter__(self):
         """Start the spinner"""
@@ -57,9 +70,7 @@ class Spinner:
             new_message (str): New message to display.
             delay (float): The delay in seconds between each spinner update.
         """
-        time.sleep(delay)
-        sys.stdout.write(
-            f"\r{' ' * (len(self.message) + 2)}\r"
-        )  # Clear the current message
-        sys.stdout.flush()
+        self.delay = delay
         self.message = new_message
+        if self.plain_output:
+            self.print_message()
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 19af503b..c2f2d4f6 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -12,11 +12,14 @@ from autogpt.workspace import Workspace
 def agent_test_config(config: Config):
     was_continuous_mode = config.continuous_mode
     was_temperature = config.temperature
+    was_plain_output = config.plain_output
     config.set_continuous_mode(False)
     config.set_temperature(0)
+    config.plain_output = True
     yield config
     config.set_continuous_mode(was_continuous_mode)
     config.set_temperature(was_temperature)
+    config.plain_output = was_plain_output
 
 
 @pytest.fixture

From e05c000615d4aadcee35e682c97b2c5bcd35a757 Mon Sep 17 00:00:00 2001
From: Toran Bruce Richards <toran.richards@gmail.com>
Date: Sat, 27 May 2023 09:05:58 +1200
Subject: [PATCH 071/112] Update README.md

Update Sponsors
---
 README.md | 113 +++++++++++++++++++++++++-----------------------------
 1 file changed, 52 insertions(+), 61 deletions(-)

diff --git a/README.md b/README.md
index 3dbeed39..4bc232b5 100644
--- a/README.md
+++ b/README.md
@@ -25,67 +25,6 @@ https://user-images.githubusercontent.com/70048414/232352935-55c6bf7c-3958-406e-
 
 Demo made by <a href=https://twitter.com/BlakeWerlinger>Blake Werlinger</a>
 
-<h2 align="center"> 💖 Help Fund Auto-GPT's Development 💖</h2>
-<p align="center">
-If you can spare a coffee, you can help to cover the costs of developing Auto-GPT and help to push the boundaries of fully autonomous AI!
-Your support is greatly appreciated. Development of this free, open-source project is made possible by all the <a href="https://github.com/Significant-Gravitas/Auto-GPT/graphs/contributors">contributors</a> and <a href="https://github.com/sponsors/Torantulino">sponsors</a>. If you'd like to sponsor this project and have your avatar or company logo appear below <a href="https://github.com/sponsors/Torantulino">click here</a>.
-</p>
-
-
-<p align="center">
-<div align="center" class="logo-container">
-<a href="https://www.zilliz.com/">
-<picture height="40px">
-  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234158272-7917382e-ff80-469e-8d8c-94f4477b8b5a.png">
-  <img src="https://user-images.githubusercontent.com/22963551/234158222-30e2d7a7-f0a9-433d-a305-e3aa0b194444.png" height="40px" alt="Zilliz" />
-</picture>
-</a>
-
-<a href="https://roost.ai">
-<img src="https://user-images.githubusercontent.com/22963551/234180283-b58cb03c-c95a-4196-93c1-28b52a388e9d.png" height="40px" alt="Roost.AI" />
-</a>
-  
-<a href="https://nuclei.ai/">
-<picture height="40px">
-  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234153428-24a6f31d-c0c6-4c9b-b3f4-9110148f67b4.png">
-  <img src="https://user-images.githubusercontent.com/22963551/234181283-691c5d71-ca94-4646-a1cf-6e818bd86faa.png" height="40px" alt="NucleiAI" />
-</picture>
-</a>
-
-<a href="https://www.algohash.org/">
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234180375-1365891c-0ba6-4d49-94c3-847c85fe03b0.png" >
-  <img src="https://user-images.githubusercontent.com/22963551/234180359-143e4a7a-4a71-4830-99c8-9b165cde995f.png" height="40px" alt="Algohash" />
-</picture>
-</a>
-
-<a href="https://www.typingmind.com/?utm_source=autogpt">
-<picture height="40px">
-  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/233202971-61e77209-58a0-47d9-9f7e-dd081111437b.png">
-  <img src="https://user-images.githubusercontent.com/22963551/234157731-f908b5db-8fe7-4036-89b6-7b2a21f87e3a.png" height="40px" alt="TypingMind" />
-</picture>
-</a>
-
-<a href="https://github.com/weaviate/weaviate">
-<picture height="40px">
-  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234181699-3d7f6ea8-5a7f-4e98-b812-37be1081be4b.png">
-  <img src="https://user-images.githubusercontent.com/22963551/234181695-fc895159-b921-4895-9a13-65e6eff5b0e7.png" height="40px" alt="TypingMind" />
-</picture>
-</a>
-
-<a href="https://chatgpv.com/?ref=spni76459e4fa3f30a">
-<img src="https://github-production-user-asset-6210df.s3.amazonaws.com/22963551/239132565-623a2dd6-eaeb-4941-b40f-c5a29ca6bebc.png" height="40px" alt="ChatGPV" />
-</a>
-  
-</div>
-</br>
-
-
-
-<p align="center"><a href="https://github.com/robinicus"><img src="https://avatars.githubusercontent.com/robinicus?v=4" width="50px" alt="robinicus" /></a>&nbsp;&nbsp;<a href="https://github.com/0xmatchmaker"><img src="https://avatars.githubusercontent.com/0xmatchmaker?v=4" width="50px" alt="0xmatchmaker" /></a>&nbsp;&nbsp;<a href="https://github.com/jazgarewal"><img src="https://avatars.githubusercontent.com/jazgarewal?v=4" width="50px" alt="jazgarewal" /></a>&nbsp;&nbsp;<a href="https://github.com/MayurVirkar"><img src="https://avatars.githubusercontent.com/MayurVirkar?v=4" width="50px" alt="MayurVirkar" /></a>&nbsp;&nbsp;<a href="https://github.com/avy-ai"><img src="https://avatars.githubusercontent.com/avy-ai?v=4" width="50px" alt="avy-ai" /></a>&nbsp;&nbsp;<a href="https://github.com/TheStoneMX"><img src="https://avatars.githubusercontent.com/TheStoneMX?v=4" width="50px" alt="TheStoneMX" /></a>&nbsp;&nbsp;<a href="https://github.com/goldenrecursion"><img src="https://avatars.githubusercontent.com/goldenrecursion?v=4" width="50px" alt="goldenrecursion" /></a>&nbsp;&nbsp;<a href="https://github.com/MatthewAgs"><img src="https://avatars.githubusercontent.com/MatthewAgs?v=4" width="50px" alt="MatthewAgs" /></a>&nbsp;&nbsp;<a href="https://github.com/eelbaz"><img src="https://avatars.githubusercontent.com/eelbaz?v=4" width="50px" alt="eelbaz" /></a>&nbsp;&nbsp;<a href="https://github.com/rapidstartup"><img src="https://avatars.githubusercontent.com/rapidstartup?v=4" width="50px" alt="rapidstartup" /></a>&nbsp;&nbsp;<a href="https://github.com/gklab"><img src="https://avatars.githubusercontent.com/gklab?v=4" width="50px" alt="gklab" /></a>&nbsp;&nbsp;<a href="https://github.com/VoiceBeer"><img src="https://avatars.githubusercontent.com/VoiceBeer?v=4" width="50px" alt="VoiceBeer" /></a>&nbsp;&nbsp;<a href="https://github.com/DailyBotHQ"><img src="https://avatars.githubusercontent.com/DailyBotHQ?v=4" width="50px" alt="DailyBotHQ" /></a>&nbsp;&nbsp;<a href="https://github.com/lucas-chu"><img src="https://avatars.githubusercontent.com/lucas-chu?v=4" width="50px" alt="lucas-chu" /></a>&nbsp;&nbsp;<a href="https://github.com/knifour"><img src="https://avatars.githubusercontent.com/knifour?v=4" width="50px" alt="knifour" /></a>&nbsp;&nbsp;<a href="https://github.com/refinery1"><img src="https://avatars.githubusercontent.com/refinery1?v=4" width="50px" alt="refinery1" /></a>&nbsp;&nbsp;<a href="https://github.com/st617"><img src="https://avatars.githubusercontent.com/st617?v=4" width="50px" alt="st617" /></a>&nbsp;&nbsp;<a href="https://github.com/neodenit"><img src="https://avatars.githubusercontent.com/neodenit?v=4" width="50px" alt="neodenit" /></a>&nbsp;&nbsp;<a href="https://github.com/CrazySwami"><img src="https://avatars.githubusercontent.com/CrazySwami?v=4" width="50px" alt="CrazySwami" /></a>&nbsp;&nbsp;<a href="https://github.com/Heitechsoft"><img src="https://avatars.githubusercontent.com/Heitechsoft?v=4" width="50px" alt="Heitechsoft" /></a>&nbsp;&nbsp;<a href="https://github.com/RealChrisSean"><img src="https://avatars.githubusercontent.com/RealChrisSean?v=4" width="50px" alt="RealChrisSean" /></a>&nbsp;&nbsp;<a href="https://github.com/abhinav-pandey29"><img src="https://avatars.githubusercontent.com/abhinav-pandey29?v=4" width="50px" alt="abhinav-pandey29" /></a>&nbsp;&nbsp;<a href="https://github.com/Explorergt92"><img src="https://avatars.githubusercontent.com/Explorergt92?v=4" width="50px" alt="Explorergt92" /></a>&nbsp;&nbsp;<a href="https://github.com/SparkplanAI"><img src="https://avatars.githubusercontent.com/SparkplanAI?v=4" width="50px" alt="SparkplanAI" /></a>&nbsp;&nbsp;<a href="https://github.com/crizzler"><img src="https://avatars.githubusercontent.com/crizzler?v=4" width="50px" alt="crizzler" /></a>&nbsp;&nbsp;<a href="https://github.com/kreativai"><img src="https://avatars.githubusercontent.com/kreativai?v=4" width="50px" alt="kreativai" /></a>&nbsp;&nbsp;<a href="https://github.com/omphos"><img src="https://avatars.githubusercontent.com/omphos?v=4" width="50px" alt="omphos" /></a>&nbsp;&nbsp;<a href="https://github.com/Jahmazon"><img src="https://avatars.githubusercontent.com/Jahmazon?v=4" width="50px" alt="Jahmazon" /></a>&nbsp;&nbsp;<a href="https://github.com/tjarmain"><img src="https://avatars.githubusercontent.com/tjarmain?v=4" width="50px" alt="tjarmain" /></a>&nbsp;&nbsp;<a href="https://github.com/ddtarazona"><img src="https://avatars.githubusercontent.com/ddtarazona?v=4" width="50px" alt="ddtarazona" /></a>&nbsp;&nbsp;<a href="https://github.com/saten-private"><img src="https://avatars.githubusercontent.com/saten-private?v=4" width="50px" alt="saten-private" /></a>&nbsp;&nbsp;<a href="https://github.com/anvarazizov"><img src="https://avatars.githubusercontent.com/anvarazizov?v=4" width="50px" alt="anvarazizov" /></a>&nbsp;&nbsp;<a href="https://github.com/lazzacapital"><img src="https://avatars.githubusercontent.com/lazzacapital?v=4" width="50px" alt="lazzacapital" /></a>&nbsp;&nbsp;<a href="https://github.com/m"><img src="https://avatars.githubusercontent.com/m?v=4" width="50px" alt="m" /></a>&nbsp;&nbsp;<a href="https://github.com/Pythagora-io"><img src="https://avatars.githubusercontent.com/Pythagora-io?v=4" width="50px" alt="Pythagora-io" /></a>&nbsp;&nbsp;<a href="https://github.com/Web3Capital"><img src="https://avatars.githubusercontent.com/Web3Capital?v=4" width="50px" alt="Web3Capital" /></a>&nbsp;&nbsp;<a href="https://github.com/toverly1"><img src="https://avatars.githubusercontent.com/toverly1?v=4" width="50px" alt="toverly1" /></a>&nbsp;&nbsp;<a href="https://github.com/digisomni"><img src="https://avatars.githubusercontent.com/digisomni?v=4" width="50px" alt="digisomni" /></a>&nbsp;&nbsp;<a href="https://github.com/concreit"><img src="https://avatars.githubusercontent.com/concreit?v=4" width="50px" alt="concreit" /></a>&nbsp;&nbsp;<a href="https://github.com/LeeRobidas"><img src="https://avatars.githubusercontent.com/LeeRobidas?v=4" width="50px" alt="LeeRobidas" /></a>&nbsp;&nbsp;<a href="https://github.com/Josecodesalot"><img src="https://avatars.githubusercontent.com/Josecodesalot?v=4" width="50px" alt="Josecodesalot" /></a>&nbsp;&nbsp;<a href="https://github.com/dexterityx"><img src="https://avatars.githubusercontent.com/dexterityx?v=4" width="50px" alt="dexterityx" /></a>&nbsp;&nbsp;<a href="https://github.com/rickscode"><img src="https://avatars.githubusercontent.com/rickscode?v=4" width="50px" alt="rickscode" /></a>&nbsp;&nbsp;<a href="https://github.com/Brodie0"><img src="https://avatars.githubusercontent.com/Brodie0?v=4" width="50px" alt="Brodie0" /></a>&nbsp;&nbsp;<a href="https://github.com/FSTatSBS"><img src="https://avatars.githubusercontent.com/FSTatSBS?v=4" width="50px" alt="FSTatSBS" /></a>&nbsp;&nbsp;<a href="https://github.com/nocodeclarity"><img src="https://avatars.githubusercontent.com/nocodeclarity?v=4" width="50px" alt="nocodeclarity" /></a>&nbsp;&nbsp;<a href="https://github.com/jsolejr"><img src="https://avatars.githubusercontent.com/jsolejr?v=4" width="50px" alt="jsolejr" /></a>&nbsp;&nbsp;<a href="https://github.com/amr-elsehemy"><img src="https://avatars.githubusercontent.com/amr-elsehemy?v=4" width="50px" alt="amr-elsehemy" /></a>&nbsp;&nbsp;<a href="https://github.com/RawBanana"><img src="https://avatars.githubusercontent.com/RawBanana?v=4" width="50px" alt="RawBanana" /></a>&nbsp;&nbsp;<a href="https://github.com/horazius"><img src="https://avatars.githubusercontent.com/horazius?v=4" width="50px" alt="horazius" /></a>&nbsp;&nbsp;<a href="https://github.com/SwftCoins"><img src="https://avatars.githubusercontent.com/SwftCoins?v=4" width="50px" alt="SwftCoins" /></a>&nbsp;&nbsp;<a href="https://github.com/tob-le-rone"><img src="https://avatars.githubusercontent.com/tob-le-rone?v=4" width="50px" alt="tob-le-rone" /></a>&nbsp;&nbsp;<a href="https://github.com/RThaweewat"><img src="https://avatars.githubusercontent.com/RThaweewat?v=4" width="50px" alt="RThaweewat" /></a>&nbsp;&nbsp;<a href="https://github.com/jun784"><img src="https://avatars.githubusercontent.com/jun784?v=4" width="50px" alt="jun784" /></a>&nbsp;&nbsp;<a href="https://github.com/joaomdmoura"><img src="https://avatars.githubusercontent.com/joaomdmoura?v=4" width="50px" alt="joaomdmoura" /></a>&nbsp;&nbsp;<a href="https://github.com/rejunity"><img src="https://avatars.githubusercontent.com/rejunity?v=4" width="50px" alt="rejunity" /></a>&nbsp;&nbsp;<a href="https://github.com/mathewhawkins"><img src="https://avatars.githubusercontent.com/mathewhawkins?v=4" width="50px" alt="mathewhawkins" /></a>&nbsp;&nbsp;<a href="https://github.com/caitlynmeeks"><img src="https://avatars.githubusercontent.com/caitlynmeeks?v=4" width="50px" alt="caitlynmeeks" /></a>&nbsp;&nbsp;<a href="https://github.com/jd3655"><img src="https://avatars.githubusercontent.com/jd3655?v=4" width="50px" alt="jd3655" /></a>&nbsp;&nbsp;<a href="https://github.com/Odin519Tomas"><img src="https://avatars.githubusercontent.com/Odin519Tomas?v=4" width="50px" alt="Odin519Tomas" /></a>&nbsp;&nbsp;<a href="https://github.com/DataMetis"><img src="https://avatars.githubusercontent.com/DataMetis?v=4" width="50px" alt="DataMetis" /></a>&nbsp;&nbsp;<a href="https://github.com/webbcolton"><img src="https://avatars.githubusercontent.com/webbcolton?v=4" width="50px" alt="webbcolton" /></a>&nbsp;&nbsp;<a href="https://github.com/rocks6"><img src="https://avatars.githubusercontent.com/rocks6?v=4" width="50px" alt="rocks6" /></a>&nbsp;&nbsp;<a href="https://github.com/cxs"><img src="https://avatars.githubusercontent.com/cxs?v=4" width="50px" alt="cxs" /></a>&nbsp;&nbsp;<a href="https://github.com/fruition"><img src="https://avatars.githubusercontent.com/fruition?v=4" width="50px" alt="fruition" /></a>&nbsp;&nbsp;<a href="https://github.com/nnkostov"><img src="https://avatars.githubusercontent.com/nnkostov?v=4" width="50px" alt="nnkostov" /></a>&nbsp;&nbsp;<a href="https://github.com/morcos"><img src="https://avatars.githubusercontent.com/morcos?v=4" width="50px" alt="morcos" /></a>&nbsp;&nbsp;<a href="https://github.com/pingbotan"><img src="https://avatars.githubusercontent.com/pingbotan?v=4" width="50px" alt="pingbotan" /></a>&nbsp;&nbsp;<a href="https://github.com/maxxflyer"><img src="https://avatars.githubusercontent.com/maxxflyer?v=4" width="50px" alt="maxxflyer" /></a>&nbsp;&nbsp;<a href="https://github.com/tommi-joentakanen"><img src="https://avatars.githubusercontent.com/tommi-joentakanen?v=4" width="50px" alt="tommi-joentakanen" /></a>&nbsp;&nbsp;<a href="https://github.com/hunteraraujo"><img src="https://avatars.githubusercontent.com/hunteraraujo?v=4" width="50px" alt="hunteraraujo" /></a>&nbsp;&nbsp;<a href="https://github.com/projectonegames"><img src="https://avatars.githubusercontent.com/projectonegames?v=4" width="50px" alt="projectonegames" /></a>&nbsp;&nbsp;<a href="https://github.com/tullytim"><img src="https://avatars.githubusercontent.com/tullytim?v=4" width="50px" alt="tullytim" /></a>&nbsp;&nbsp;<a href="https://github.com/comet-ml"><img src="https://avatars.githubusercontent.com/comet-ml?v=4" width="50px" alt="comet-ml" /></a>&nbsp;&nbsp;<a href="https://github.com/thepok"><img src="https://avatars.githubusercontent.com/thepok?v=4" width="50px" alt="thepok" /></a>&nbsp;&nbsp;<a href="https://github.com/prompthero"><img src="https://avatars.githubusercontent.com/prompthero?v=4" width="50px" alt="prompthero" /></a>&nbsp;&nbsp;<a href="https://github.com/sunchongren"><img src="https://avatars.githubusercontent.com/sunchongren?v=4" width="50px" alt="sunchongren" /></a>&nbsp;&nbsp;<a href="https://github.com/neverinstall"><img src="https://avatars.githubusercontent.com/neverinstall?v=4" width="50px" alt="neverinstall" /></a>&nbsp;&nbsp;<a href="https://github.com/josephcmiller2"><img src="https://avatars.githubusercontent.com/josephcmiller2?v=4" width="50px" alt="josephcmiller2" /></a>&nbsp;&nbsp;<a href="https://github.com/yx3110"><img src="https://avatars.githubusercontent.com/yx3110?v=4" width="50px" alt="yx3110" /></a>&nbsp;&nbsp;<a href="https://github.com/MBassi91"><img src="https://avatars.githubusercontent.com/MBassi91?v=4" width="50px" alt="MBassi91" /></a>&nbsp;&nbsp;<a href="https://github.com/SpacingLily"><img src="https://avatars.githubusercontent.com/SpacingLily?v=4" width="50px" alt="SpacingLily" /></a>&nbsp;&nbsp;<a href="https://github.com/arthur-x88"><img src="https://avatars.githubusercontent.com/arthur-x88?v=4" width="50px" alt="arthur-x88" /></a>&nbsp;&nbsp;<a href="https://github.com/ciscodebs"><img src="https://avatars.githubusercontent.com/ciscodebs?v=4" width="50px" alt="ciscodebs" /></a>&nbsp;&nbsp;<a href="https://github.com/christian-gheorghe"><img src="https://avatars.githubusercontent.com/christian-gheorghe?v=4" width="50px" alt="christian-gheorghe" /></a>&nbsp;&nbsp;<a href="https://github.com/EngageStrategies"><img src="https://avatars.githubusercontent.com/EngageStrategies?v=4" width="50px" alt="EngageStrategies" /></a>&nbsp;&nbsp;<a href="https://github.com/jondwillis"><img src="https://avatars.githubusercontent.com/jondwillis?v=4" width="50px" alt="jondwillis" /></a>&nbsp;&nbsp;<a href="https://github.com/Cameron-Fulton"><img src="https://avatars.githubusercontent.com/Cameron-Fulton?v=4" width="50px" alt="Cameron-Fulton" /></a>&nbsp;&nbsp;<a href="https://github.com/AryaXAI"><img src="https://avatars.githubusercontent.com/AryaXAI?v=4" width="50px" alt="AryaXAI" /></a>&nbsp;&nbsp;<a href="https://github.com/AuroraHolding"><img src="https://avatars.githubusercontent.com/AuroraHolding?v=4" width="50px" alt="AuroraHolding" /></a>&nbsp;&nbsp;<a href="https://github.com/Mr-Bishop42"><img src="https://avatars.githubusercontent.com/Mr-Bishop42?v=4" width="50px" alt="Mr-Bishop42" /></a>&nbsp;&nbsp;<a href="https://github.com/doverhq"><img src="https://avatars.githubusercontent.com/doverhq?v=4" width="50px" alt="doverhq" /></a>&nbsp;&nbsp;<a href="https://github.com/johnculkin"><img src="https://avatars.githubusercontent.com/johnculkin?v=4" width="50px" alt="johnculkin" /></a>&nbsp;&nbsp;<a href="https://github.com/marv-technology"><img src="https://avatars.githubusercontent.com/marv-technology?v=4" width="50px" alt="marv-technology" /></a>&nbsp;&nbsp;<a href="https://github.com/ikarosai"><img src="https://avatars.githubusercontent.com/ikarosai?v=4" width="50px" alt="ikarosai" /></a>&nbsp;&nbsp;<a href="https://github.com/ColinConwell"><img src="https://avatars.githubusercontent.com/ColinConwell?v=4" width="50px" alt="ColinConwell" /></a>&nbsp;&nbsp;<a href="https://github.com/humungasaurus"><img src="https://avatars.githubusercontent.com/humungasaurus?v=4" width="50px" alt="humungasaurus" /></a>&nbsp;&nbsp;<a href="https://github.com/terpsfreak"><img src="https://avatars.githubusercontent.com/terpsfreak?v=4" width="50px" alt="terpsfreak" /></a>&nbsp;&nbsp;<a href="https://github.com/iddelacruz"><img src="https://avatars.githubusercontent.com/iddelacruz?v=4" width="50px" alt="iddelacruz" /></a>&nbsp;&nbsp;<a href="https://github.com/thisisjeffchen"><img src="https://avatars.githubusercontent.com/thisisjeffchen?v=4" width="50px" alt="thisisjeffchen" /></a>&nbsp;&nbsp;<a href="https://github.com/nicoguyon"><img src="https://avatars.githubusercontent.com/nicoguyon?v=4" width="50px" alt="nicoguyon" /></a>&nbsp;&nbsp;<a href="https://github.com/arjunb023"><img src="https://avatars.githubusercontent.com/arjunb023?v=4" width="50px" alt="arjunb023" /></a>&nbsp;&nbsp;<a href="https://github.com/Nalhos"><img src="https://avatars.githubusercontent.com/Nalhos?v=4" width="50px" alt="Nalhos" /></a>&nbsp;&nbsp;<a href="https://github.com/belharethsami"><img src="https://avatars.githubusercontent.com/belharethsami?v=4" width="50px" alt="belharethsami" /></a>&nbsp;&nbsp;<a href="https://github.com/Mobivs"><img src="https://avatars.githubusercontent.com/Mobivs?v=4" width="50px" alt="Mobivs" /></a>&nbsp;&nbsp;<a href="https://github.com/txtr99"><img src="https://avatars.githubusercontent.com/txtr99?v=4" width="50px" alt="txtr99" /></a>&nbsp;&nbsp;<a href="https://github.com/ntwrite"><img src="https://avatars.githubusercontent.com/ntwrite?v=4" width="50px" alt="ntwrite" /></a>&nbsp;&nbsp;<a href="https://github.com/founderblocks-sils"><img src="https://avatars.githubusercontent.com/founderblocks-sils?v=4" width="50px" alt="founderblocks-sils" /></a>&nbsp;&nbsp;<a href="https://github.com/kMag410"><img src="https://avatars.githubusercontent.com/kMag410?v=4" width="50px" alt="kMag410" /></a>&nbsp;&nbsp;<a href="https://github.com/angiaou"><img src="https://avatars.githubusercontent.com/angiaou?v=4" width="50px" alt="angiaou" /></a>&nbsp;&nbsp;<a href="https://github.com/garythebat"><img src="https://avatars.githubusercontent.com/garythebat?v=4" width="50px" alt="garythebat" /></a>&nbsp;&nbsp;<a href="https://github.com/lmaugustin"><img src="https://avatars.githubusercontent.com/lmaugustin?v=4" width="50px" alt="lmaugustin" /></a>&nbsp;&nbsp;<a href="https://github.com/shawnharmsen"><img src="https://avatars.githubusercontent.com/shawnharmsen?v=4" width="50px" alt="shawnharmsen" /></a>&nbsp;&nbsp;<a href="https://github.com/clortegah"><img src="https://avatars.githubusercontent.com/clortegah?v=4" width="50px" alt="clortegah" /></a>&nbsp;&nbsp;<a href="https://github.com/MetaPath01"><img src="https://avatars.githubusercontent.com/MetaPath01?v=4" width="50px" alt="MetaPath01" /></a>&nbsp;&nbsp;<a href="https://github.com/sekomike910"><img src="https://avatars.githubusercontent.com/sekomike910?v=4" width="50px" alt="sekomike910" /></a>&nbsp;&nbsp;<a href="https://github.com/MediConCenHK"><img src="https://avatars.githubusercontent.com/MediConCenHK?v=4" width="50px" alt="MediConCenHK" /></a>&nbsp;&nbsp;<a href="https://github.com/svpermari0"><img src="https://avatars.githubusercontent.com/svpermari0?v=4" width="50px" alt="svpermari0" /></a>&nbsp;&nbsp;<a href="https://github.com/jacobyoby"><img src="https://avatars.githubusercontent.com/jacobyoby?v=4" width="50px" alt="jacobyoby" /></a>&nbsp;&nbsp;<a href="https://github.com/turintech"><img src="https://avatars.githubusercontent.com/turintech?v=4" width="50px" alt="turintech" /></a>&nbsp;&nbsp;<a href="https://github.com/allenstecat"><img src="https://avatars.githubusercontent.com/allenstecat?v=4" width="50px" alt="allenstecat" /></a>&nbsp;&nbsp;<a href="https://github.com/CatsMeow492"><img src="https://avatars.githubusercontent.com/CatsMeow492?v=4" width="50px" alt="CatsMeow492" /></a>&nbsp;&nbsp;<a href="https://github.com/tommygeee"><img src="https://avatars.githubusercontent.com/tommygeee?v=4" width="50px" alt="tommygeee" /></a>&nbsp;&nbsp;<a href="https://github.com/judegomila"><img src="https://avatars.githubusercontent.com/judegomila?v=4" width="50px" alt="judegomila" /></a>&nbsp;&nbsp;<a href="https://github.com/cfarquhar"><img src="https://avatars.githubusercontent.com/cfarquhar?v=4" width="50px" alt="cfarquhar" /></a>&nbsp;&nbsp;<a href="https://github.com/ZoneSixGames"><img src="https://avatars.githubusercontent.com/ZoneSixGames?v=4" width="50px" alt="ZoneSixGames" /></a>&nbsp;&nbsp;<a href="https://github.com/kenndanielso"><img src="https://avatars.githubusercontent.com/kenndanielso?v=4" width="50px" alt="kenndanielso" /></a>&nbsp;&nbsp;<a href="https://github.com/CrypteorCapital"><img src="https://avatars.githubusercontent.com/CrypteorCapital?v=4" width="50px" alt="CrypteorCapital" /></a>&nbsp;&nbsp;<a href="https://github.com/sultanmeghji"><img src="https://avatars.githubusercontent.com/sultanmeghji?v=4" width="50px" alt="sultanmeghji" /></a>&nbsp;&nbsp;<a href="https://github.com/jenius-eagle"><img src="https://avatars.githubusercontent.com/jenius-eagle?v=4" width="50px" alt="jenius-eagle" /></a>&nbsp;&nbsp;<a href="https://github.com/josephjacks"><img src="https://avatars.githubusercontent.com/josephjacks?v=4" width="50px" alt="josephjacks" /></a>&nbsp;&nbsp;<a href="https://github.com/pingshian0131"><img src="https://avatars.githubusercontent.com/pingshian0131?v=4" width="50px" alt="pingshian0131" /></a>&nbsp;&nbsp;<a href="https://github.com/AIdevelopersAI"><img src="https://avatars.githubusercontent.com/AIdevelopersAI?v=4" width="50px" alt="AIdevelopersAI" /></a>&nbsp;&nbsp;<a href="https://github.com/ternary5"><img src="https://avatars.githubusercontent.com/ternary5?v=4" width="50px" alt="ternary5" /></a>&nbsp;&nbsp;<a href="https://github.com/ChrisDMT"><img src="https://avatars.githubusercontent.com/ChrisDMT?v=4" width="50px" alt="ChrisDMT" /></a>&nbsp;&nbsp;<a href="https://github.com/AcountoOU"><img src="https://avatars.githubusercontent.com/AcountoOU?v=4" width="50px" alt="AcountoOU" /></a>&nbsp;&nbsp;<a href="https://github.com/chatgpt-prompts"><img src="https://avatars.githubusercontent.com/chatgpt-prompts?v=4" width="50px" alt="chatgpt-prompts" /></a>&nbsp;&nbsp;<a href="https://github.com/Partender"><img src="https://avatars.githubusercontent.com/Partender?v=4" width="50px" alt="Partender" /></a>&nbsp;&nbsp;<a href="https://github.com/Daniel1357"><img src="https://avatars.githubusercontent.com/Daniel1357?v=4" width="50px" alt="Daniel1357" /></a>&nbsp;&nbsp;<a href="https://github.com/KiaArmani"><img src="https://avatars.githubusercontent.com/KiaArmani?v=4" width="50px" alt="KiaArmani" /></a>&nbsp;&nbsp;<a href="https://github.com/zkonduit"><img src="https://avatars.githubusercontent.com/zkonduit?v=4" width="50px" alt="zkonduit" /></a>&nbsp;&nbsp;<a href="https://github.com/fabrietech"><img src="https://avatars.githubusercontent.com/fabrietech?v=4" width="50px" alt="fabrietech" /></a>&nbsp;&nbsp;<a href="https://github.com/scryptedinc"><img src="https://avatars.githubusercontent.com/scryptedinc?v=4" width="50px" alt="scryptedinc" /></a>&nbsp;&nbsp;<a href="https://github.com/coreyspagnoli"><img src="https://avatars.githubusercontent.com/coreyspagnoli?v=4" width="50px" alt="coreyspagnoli" /></a>&nbsp;&nbsp;<a href="https://github.com/AntonioCiolino"><img src="https://avatars.githubusercontent.com/AntonioCiolino?v=4" width="50px" alt="AntonioCiolino" /></a>&nbsp;&nbsp;<a href="https://github.com/Dradstone"><img src="https://avatars.githubusercontent.com/Dradstone?v=4" width="50px" alt="Dradstone" /></a>&nbsp;&nbsp;<a href="https://github.com/CarmenCocoa"><img src="https://avatars.githubusercontent.com/CarmenCocoa?v=4" width="50px" alt="CarmenCocoa" /></a>&nbsp;&nbsp;<a href="https://github.com/bentoml"><img src="https://avatars.githubusercontent.com/bentoml?v=4" width="50px" alt="bentoml" /></a>&nbsp;&nbsp;<a href="https://github.com/merwanehamadi"><img src="https://avatars.githubusercontent.com/merwanehamadi?v=4" width="50px" alt="merwanehamadi" /></a>&nbsp;&nbsp;<a href="https://github.com/vkozacek"><img src="https://avatars.githubusercontent.com/vkozacek?v=4" width="50px" alt="vkozacek" /></a>&nbsp;&nbsp;<a href="https://github.com/ASmithOWL"><img src="https://avatars.githubusercontent.com/ASmithOWL?v=4" width="50px" alt="ASmithOWL" /></a>&nbsp;&nbsp;<a href="https://github.com/tekelsey"><img src="https://avatars.githubusercontent.com/tekelsey?v=4" width="50px" alt="tekelsey" /></a>&nbsp;&nbsp;<a href="https://github.com/GalaxyVideoAgency"><img src="https://avatars.githubusercontent.com/GalaxyVideoAgency?v=4" width="50px" alt="GalaxyVideoAgency" /></a>&nbsp;&nbsp;<a href="https://github.com/wenfengwang"><img src="https://avatars.githubusercontent.com/wenfengwang?v=4" width="50px" alt="wenfengwang" /></a>&nbsp;&nbsp;<a href="https://github.com/rviramontes"><img src="https://avatars.githubusercontent.com/rviramontes?v=4" width="50px" alt="rviramontes" /></a>&nbsp;&nbsp;<a href="https://github.com/indoor47"><img src="https://avatars.githubusercontent.com/indoor47?v=4" width="50px" alt="indoor47" /></a>&nbsp;&nbsp;<a href="https://github.com/ZERO-A-ONE"><img src="https://avatars.githubusercontent.com/ZERO-A-ONE?v=4" width="50px" alt="ZERO-A-ONE" /></a>&nbsp;&nbsp;</p>
-
-
-
 ## 🚀 Features
 
 - 🌐 Internet access for searches and information gathering
@@ -122,6 +61,58 @@ Please see the [documentation][docs] for full setup instructions and configurati
 [docs/usage]: https://docs.agpt.co/usage/
 [docs/plugins]: https://docs.agpt.co/plugins/
 
+<h2 align="center"> 💖 Help Fund Auto-GPT's Development 💖</h2>
+<p align="center">
+If you can spare a coffee, you can help to cover the costs of developing Auto-GPT and help to push the boundaries of fully autonomous AI!
+Your support is greatly appreciated. Development of this free, open-source project is made possible by all the <a href="https://github.com/Significant-Gravitas/Auto-GPT/graphs/contributors">contributors</a> and <a href="https://github.com/sponsors/Torantulino">sponsors</a>. If you'd like to sponsor this project and have your avatar or company logo appear below <a href="https://github.com/sponsors/Torantulino">click here</a>.
+</p>
+
+
+<p align="center">
+<div align="center" class="logo-container">
+<a href="https://www.zilliz.com/">
+<picture height="40px">
+  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234158272-7917382e-ff80-469e-8d8c-94f4477b8b5a.png">
+  <img src="https://user-images.githubusercontent.com/22963551/234158222-30e2d7a7-f0a9-433d-a305-e3aa0b194444.png" height="40px" alt="Zilliz" />
+</picture>
+</a>
+
+<a href="https://roost.ai">
+<img src="https://user-images.githubusercontent.com/22963551/234180283-b58cb03c-c95a-4196-93c1-28b52a388e9d.png" height="40px" alt="Roost.AI" />
+</a>
+  
+<a href="https://nuclei.ai/">
+<picture height="40px">
+  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234153428-24a6f31d-c0c6-4c9b-b3f4-9110148f67b4.png">
+  <img src="https://user-images.githubusercontent.com/22963551/234181283-691c5d71-ca94-4646-a1cf-6e818bd86faa.png" height="40px" alt="NucleiAI" />
+</picture>
+</a>
+
+<a href="https://www.algohash.org/">
+<picture>
+  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234180375-1365891c-0ba6-4d49-94c3-847c85fe03b0.png" >
+  <img src="https://user-images.githubusercontent.com/22963551/234180359-143e4a7a-4a71-4830-99c8-9b165cde995f.png" height="40px" alt="Algohash" />
+</picture>
+</a>
+
+<a href="https://github.com/weaviate/weaviate">
+<picture height="40px">
+  <source media="(prefers-color-scheme: light)" srcset="https://user-images.githubusercontent.com/22963551/234181699-3d7f6ea8-5a7f-4e98-b812-37be1081be4b.png">
+  <img src="https://user-images.githubusercontent.com/22963551/234181695-fc895159-b921-4895-9a13-65e6eff5b0e7.png" height="40px" alt="TypingMind" />
+</picture>
+</a>
+
+<a href="https://chatgpv.com/?ref=spni76459e4fa3f30a">
+<img src="https://github-production-user-asset-6210df.s3.amazonaws.com/22963551/239132565-623a2dd6-eaeb-4941-b40f-c5a29ca6bebc.png" height="40px" alt="ChatGPV" />
+</a>
+  
+</div>
+</br>
+
+
+
+<p align="center"><a href="https://github.com/robinicus"><img src="https://avatars.githubusercontent.com/robinicus?v=4" width="50px" alt="robinicus" /></a>&nbsp;&nbsp;<a href="https://github.com/0xmatchmaker"><img src="https://avatars.githubusercontent.com/0xmatchmaker?v=4" width="50px" alt="0xmatchmaker" /></a>&nbsp;&nbsp;<a href="https://github.com/jazgarewal"><img src="https://avatars.githubusercontent.com/jazgarewal?v=4" width="50px" alt="jazgarewal" /></a>&nbsp;&nbsp;<a href="https://github.com/MayurVirkar"><img src="https://avatars.githubusercontent.com/MayurVirkar?v=4" width="50px" alt="MayurVirkar" /></a>&nbsp;&nbsp;<a href="https://github.com/avy-ai"><img src="https://avatars.githubusercontent.com/avy-ai?v=4" width="50px" alt="avy-ai" /></a>&nbsp;&nbsp;<a href="https://github.com/TheStoneMX"><img src="https://avatars.githubusercontent.com/TheStoneMX?v=4" width="50px" alt="TheStoneMX" /></a>&nbsp;&nbsp;<a href="https://github.com/goldenrecursion"><img src="https://avatars.githubusercontent.com/goldenrecursion?v=4" width="50px" alt="goldenrecursion" /></a>&nbsp;&nbsp;<a href="https://github.com/MatthewAgs"><img src="https://avatars.githubusercontent.com/MatthewAgs?v=4" width="50px" alt="MatthewAgs" /></a>&nbsp;&nbsp;<a href="https://github.com/eelbaz"><img src="https://avatars.githubusercontent.com/eelbaz?v=4" width="50px" alt="eelbaz" /></a>&nbsp;&nbsp;<a href="https://github.com/rapidstartup"><img src="https://avatars.githubusercontent.com/rapidstartup?v=4" width="50px" alt="rapidstartup" /></a>&nbsp;&nbsp;<a href="https://github.com/gklab"><img src="https://avatars.githubusercontent.com/gklab?v=4" width="50px" alt="gklab" /></a>&nbsp;&nbsp;<a href="https://github.com/VoiceBeer"><img src="https://avatars.githubusercontent.com/VoiceBeer?v=4" width="50px" alt="VoiceBeer" /></a>&nbsp;&nbsp;<a href="https://github.com/DailyBotHQ"><img src="https://avatars.githubusercontent.com/DailyBotHQ?v=4" width="50px" alt="DailyBotHQ" /></a>&nbsp;&nbsp;<a href="https://github.com/lucas-chu"><img src="https://avatars.githubusercontent.com/lucas-chu?v=4" width="50px" alt="lucas-chu" /></a>&nbsp;&nbsp;<a href="https://github.com/knifour"><img src="https://avatars.githubusercontent.com/knifour?v=4" width="50px" alt="knifour" /></a>&nbsp;&nbsp;<a href="https://github.com/refinery1"><img src="https://avatars.githubusercontent.com/refinery1?v=4" width="50px" alt="refinery1" /></a>&nbsp;&nbsp;<a href="https://github.com/st617"><img src="https://avatars.githubusercontent.com/st617?v=4" width="50px" alt="st617" /></a>&nbsp;&nbsp;<a href="https://github.com/neodenit"><img src="https://avatars.githubusercontent.com/neodenit?v=4" width="50px" alt="neodenit" /></a>&nbsp;&nbsp;<a href="https://github.com/CrazySwami"><img src="https://avatars.githubusercontent.com/CrazySwami?v=4" width="50px" alt="CrazySwami" /></a>&nbsp;&nbsp;<a href="https://github.com/Heitechsoft"><img src="https://avatars.githubusercontent.com/Heitechsoft?v=4" width="50px" alt="Heitechsoft" /></a>&nbsp;&nbsp;<a href="https://github.com/RealChrisSean"><img src="https://avatars.githubusercontent.com/RealChrisSean?v=4" width="50px" alt="RealChrisSean" /></a>&nbsp;&nbsp;<a href="https://github.com/abhinav-pandey29"><img src="https://avatars.githubusercontent.com/abhinav-pandey29?v=4" width="50px" alt="abhinav-pandey29" /></a>&nbsp;&nbsp;<a href="https://github.com/Explorergt92"><img src="https://avatars.githubusercontent.com/Explorergt92?v=4" width="50px" alt="Explorergt92" /></a>&nbsp;&nbsp;<a href="https://github.com/SparkplanAI"><img src="https://avatars.githubusercontent.com/SparkplanAI?v=4" width="50px" alt="SparkplanAI" /></a>&nbsp;&nbsp;<a href="https://github.com/crizzler"><img src="https://avatars.githubusercontent.com/crizzler?v=4" width="50px" alt="crizzler" /></a>&nbsp;&nbsp;<a href="https://github.com/kreativai"><img src="https://avatars.githubusercontent.com/kreativai?v=4" width="50px" alt="kreativai" /></a>&nbsp;&nbsp;<a href="https://github.com/omphos"><img src="https://avatars.githubusercontent.com/omphos?v=4" width="50px" alt="omphos" /></a>&nbsp;&nbsp;<a href="https://github.com/Jahmazon"><img src="https://avatars.githubusercontent.com/Jahmazon?v=4" width="50px" alt="Jahmazon" /></a>&nbsp;&nbsp;<a href="https://github.com/tjarmain"><img src="https://avatars.githubusercontent.com/tjarmain?v=4" width="50px" alt="tjarmain" /></a>&nbsp;&nbsp;<a href="https://github.com/ddtarazona"><img src="https://avatars.githubusercontent.com/ddtarazona?v=4" width="50px" alt="ddtarazona" /></a>&nbsp;&nbsp;<a href="https://github.com/saten-private"><img src="https://avatars.githubusercontent.com/saten-private?v=4" width="50px" alt="saten-private" /></a>&nbsp;&nbsp;<a href="https://github.com/anvarazizov"><img src="https://avatars.githubusercontent.com/anvarazizov?v=4" width="50px" alt="anvarazizov" /></a>&nbsp;&nbsp;<a href="https://github.com/lazzacapital"><img src="https://avatars.githubusercontent.com/lazzacapital?v=4" width="50px" alt="lazzacapital" /></a>&nbsp;&nbsp;<a href="https://github.com/m"><img src="https://avatars.githubusercontent.com/m?v=4" width="50px" alt="m" /></a>&nbsp;&nbsp;<a href="https://github.com/Pythagora-io"><img src="https://avatars.githubusercontent.com/Pythagora-io?v=4" width="50px" alt="Pythagora-io" /></a>&nbsp;&nbsp;<a href="https://github.com/Web3Capital"><img src="https://avatars.githubusercontent.com/Web3Capital?v=4" width="50px" alt="Web3Capital" /></a>&nbsp;&nbsp;<a href="https://github.com/toverly1"><img src="https://avatars.githubusercontent.com/toverly1?v=4" width="50px" alt="toverly1" /></a>&nbsp;&nbsp;<a href="https://github.com/digisomni"><img src="https://avatars.githubusercontent.com/digisomni?v=4" width="50px" alt="digisomni" /></a>&nbsp;&nbsp;<a href="https://github.com/concreit"><img src="https://avatars.githubusercontent.com/concreit?v=4" width="50px" alt="concreit" /></a>&nbsp;&nbsp;<a href="https://github.com/LeeRobidas"><img src="https://avatars.githubusercontent.com/LeeRobidas?v=4" width="50px" alt="LeeRobidas" /></a>&nbsp;&nbsp;<a href="https://github.com/Josecodesalot"><img src="https://avatars.githubusercontent.com/Josecodesalot?v=4" width="50px" alt="Josecodesalot" /></a>&nbsp;&nbsp;<a href="https://github.com/dexterityx"><img src="https://avatars.githubusercontent.com/dexterityx?v=4" width="50px" alt="dexterityx" /></a>&nbsp;&nbsp;<a href="https://github.com/rickscode"><img src="https://avatars.githubusercontent.com/rickscode?v=4" width="50px" alt="rickscode" /></a>&nbsp;&nbsp;<a href="https://github.com/Brodie0"><img src="https://avatars.githubusercontent.com/Brodie0?v=4" width="50px" alt="Brodie0" /></a>&nbsp;&nbsp;<a href="https://github.com/FSTatSBS"><img src="https://avatars.githubusercontent.com/FSTatSBS?v=4" width="50px" alt="FSTatSBS" /></a>&nbsp;&nbsp;<a href="https://github.com/nocodeclarity"><img src="https://avatars.githubusercontent.com/nocodeclarity?v=4" width="50px" alt="nocodeclarity" /></a>&nbsp;&nbsp;<a href="https://github.com/jsolejr"><img src="https://avatars.githubusercontent.com/jsolejr?v=4" width="50px" alt="jsolejr" /></a>&nbsp;&nbsp;<a href="https://github.com/amr-elsehemy"><img src="https://avatars.githubusercontent.com/amr-elsehemy?v=4" width="50px" alt="amr-elsehemy" /></a>&nbsp;&nbsp;<a href="https://github.com/RawBanana"><img src="https://avatars.githubusercontent.com/RawBanana?v=4" width="50px" alt="RawBanana" /></a>&nbsp;&nbsp;<a href="https://github.com/horazius"><img src="https://avatars.githubusercontent.com/horazius?v=4" width="50px" alt="horazius" /></a>&nbsp;&nbsp;<a href="https://github.com/SwftCoins"><img src="https://avatars.githubusercontent.com/SwftCoins?v=4" width="50px" alt="SwftCoins" /></a>&nbsp;&nbsp;<a href="https://github.com/tob-le-rone"><img src="https://avatars.githubusercontent.com/tob-le-rone?v=4" width="50px" alt="tob-le-rone" /></a>&nbsp;&nbsp;<a href="https://github.com/RThaweewat"><img src="https://avatars.githubusercontent.com/RThaweewat?v=4" width="50px" alt="RThaweewat" /></a>&nbsp;&nbsp;<a href="https://github.com/jun784"><img src="https://avatars.githubusercontent.com/jun784?v=4" width="50px" alt="jun784" /></a>&nbsp;&nbsp;<a href="https://github.com/joaomdmoura"><img src="https://avatars.githubusercontent.com/joaomdmoura?v=4" width="50px" alt="joaomdmoura" /></a>&nbsp;&nbsp;<a href="https://github.com/rejunity"><img src="https://avatars.githubusercontent.com/rejunity?v=4" width="50px" alt="rejunity" /></a>&nbsp;&nbsp;<a href="https://github.com/mathewhawkins"><img src="https://avatars.githubusercontent.com/mathewhawkins?v=4" width="50px" alt="mathewhawkins" /></a>&nbsp;&nbsp;<a href="https://github.com/caitlynmeeks"><img src="https://avatars.githubusercontent.com/caitlynmeeks?v=4" width="50px" alt="caitlynmeeks" /></a>&nbsp;&nbsp;<a href="https://github.com/jd3655"><img src="https://avatars.githubusercontent.com/jd3655?v=4" width="50px" alt="jd3655" /></a>&nbsp;&nbsp;<a href="https://github.com/Odin519Tomas"><img src="https://avatars.githubusercontent.com/Odin519Tomas?v=4" width="50px" alt="Odin519Tomas" /></a>&nbsp;&nbsp;<a href="https://github.com/DataMetis"><img src="https://avatars.githubusercontent.com/DataMetis?v=4" width="50px" alt="DataMetis" /></a>&nbsp;&nbsp;<a href="https://github.com/webbcolton"><img src="https://avatars.githubusercontent.com/webbcolton?v=4" width="50px" alt="webbcolton" /></a>&nbsp;&nbsp;<a href="https://github.com/rocks6"><img src="https://avatars.githubusercontent.com/rocks6?v=4" width="50px" alt="rocks6" /></a>&nbsp;&nbsp;<a href="https://github.com/cxs"><img src="https://avatars.githubusercontent.com/cxs?v=4" width="50px" alt="cxs" /></a>&nbsp;&nbsp;<a href="https://github.com/fruition"><img src="https://avatars.githubusercontent.com/fruition?v=4" width="50px" alt="fruition" /></a>&nbsp;&nbsp;<a href="https://github.com/nnkostov"><img src="https://avatars.githubusercontent.com/nnkostov?v=4" width="50px" alt="nnkostov" /></a>&nbsp;&nbsp;<a href="https://github.com/morcos"><img src="https://avatars.githubusercontent.com/morcos?v=4" width="50px" alt="morcos" /></a>&nbsp;&nbsp;<a href="https://github.com/pingbotan"><img src="https://avatars.githubusercontent.com/pingbotan?v=4" width="50px" alt="pingbotan" /></a>&nbsp;&nbsp;<a href="https://github.com/maxxflyer"><img src="https://avatars.githubusercontent.com/maxxflyer?v=4" width="50px" alt="maxxflyer" /></a>&nbsp;&nbsp;<a href="https://github.com/tommi-joentakanen"><img src="https://avatars.githubusercontent.com/tommi-joentakanen?v=4" width="50px" alt="tommi-joentakanen" /></a>&nbsp;&nbsp;<a href="https://github.com/hunteraraujo"><img src="https://avatars.githubusercontent.com/hunteraraujo?v=4" width="50px" alt="hunteraraujo" /></a>&nbsp;&nbsp;<a href="https://github.com/projectonegames"><img src="https://avatars.githubusercontent.com/projectonegames?v=4" width="50px" alt="projectonegames" /></a>&nbsp;&nbsp;<a href="https://github.com/tullytim"><img src="https://avatars.githubusercontent.com/tullytim?v=4" width="50px" alt="tullytim" /></a>&nbsp;&nbsp;<a href="https://github.com/comet-ml"><img src="https://avatars.githubusercontent.com/comet-ml?v=4" width="50px" alt="comet-ml" /></a>&nbsp;&nbsp;<a href="https://github.com/thepok"><img src="https://avatars.githubusercontent.com/thepok?v=4" width="50px" alt="thepok" /></a>&nbsp;&nbsp;<a href="https://github.com/prompthero"><img src="https://avatars.githubusercontent.com/prompthero?v=4" width="50px" alt="prompthero" /></a>&nbsp;&nbsp;<a href="https://github.com/sunchongren"><img src="https://avatars.githubusercontent.com/sunchongren?v=4" width="50px" alt="sunchongren" /></a>&nbsp;&nbsp;<a href="https://github.com/neverinstall"><img src="https://avatars.githubusercontent.com/neverinstall?v=4" width="50px" alt="neverinstall" /></a>&nbsp;&nbsp;<a href="https://github.com/josephcmiller2"><img src="https://avatars.githubusercontent.com/josephcmiller2?v=4" width="50px" alt="josephcmiller2" /></a>&nbsp;&nbsp;<a href="https://github.com/yx3110"><img src="https://avatars.githubusercontent.com/yx3110?v=4" width="50px" alt="yx3110" /></a>&nbsp;&nbsp;<a href="https://github.com/MBassi91"><img src="https://avatars.githubusercontent.com/MBassi91?v=4" width="50px" alt="MBassi91" /></a>&nbsp;&nbsp;<a href="https://github.com/SpacingLily"><img src="https://avatars.githubusercontent.com/SpacingLily?v=4" width="50px" alt="SpacingLily" /></a>&nbsp;&nbsp;<a href="https://github.com/arthur-x88"><img src="https://avatars.githubusercontent.com/arthur-x88?v=4" width="50px" alt="arthur-x88" /></a>&nbsp;&nbsp;<a href="https://github.com/ciscodebs"><img src="https://avatars.githubusercontent.com/ciscodebs?v=4" width="50px" alt="ciscodebs" /></a>&nbsp;&nbsp;<a href="https://github.com/christian-gheorghe"><img src="https://avatars.githubusercontent.com/christian-gheorghe?v=4" width="50px" alt="christian-gheorghe" /></a>&nbsp;&nbsp;<a href="https://github.com/EngageStrategies"><img src="https://avatars.githubusercontent.com/EngageStrategies?v=4" width="50px" alt="EngageStrategies" /></a>&nbsp;&nbsp;<a href="https://github.com/jondwillis"><img src="https://avatars.githubusercontent.com/jondwillis?v=4" width="50px" alt="jondwillis" /></a>&nbsp;&nbsp;<a href="https://github.com/Cameron-Fulton"><img src="https://avatars.githubusercontent.com/Cameron-Fulton?v=4" width="50px" alt="Cameron-Fulton" /></a>&nbsp;&nbsp;<a href="https://github.com/AryaXAI"><img src="https://avatars.githubusercontent.com/AryaXAI?v=4" width="50px" alt="AryaXAI" /></a>&nbsp;&nbsp;<a href="https://github.com/AuroraHolding"><img src="https://avatars.githubusercontent.com/AuroraHolding?v=4" width="50px" alt="AuroraHolding" /></a>&nbsp;&nbsp;<a href="https://github.com/Mr-Bishop42"><img src="https://avatars.githubusercontent.com/Mr-Bishop42?v=4" width="50px" alt="Mr-Bishop42" /></a>&nbsp;&nbsp;<a href="https://github.com/doverhq"><img src="https://avatars.githubusercontent.com/doverhq?v=4" width="50px" alt="doverhq" /></a>&nbsp;&nbsp;<a href="https://github.com/johnculkin"><img src="https://avatars.githubusercontent.com/johnculkin?v=4" width="50px" alt="johnculkin" /></a>&nbsp;&nbsp;<a href="https://github.com/marv-technology"><img src="https://avatars.githubusercontent.com/marv-technology?v=4" width="50px" alt="marv-technology" /></a>&nbsp;&nbsp;<a href="https://github.com/ikarosai"><img src="https://avatars.githubusercontent.com/ikarosai?v=4" width="50px" alt="ikarosai" /></a>&nbsp;&nbsp;<a href="https://github.com/ColinConwell"><img src="https://avatars.githubusercontent.com/ColinConwell?v=4" width="50px" alt="ColinConwell" /></a>&nbsp;&nbsp;<a href="https://github.com/humungasaurus"><img src="https://avatars.githubusercontent.com/humungasaurus?v=4" width="50px" alt="humungasaurus" /></a>&nbsp;&nbsp;<a href="https://github.com/terpsfreak"><img src="https://avatars.githubusercontent.com/terpsfreak?v=4" width="50px" alt="terpsfreak" /></a>&nbsp;&nbsp;<a href="https://github.com/iddelacruz"><img src="https://avatars.githubusercontent.com/iddelacruz?v=4" width="50px" alt="iddelacruz" /></a>&nbsp;&nbsp;<a href="https://github.com/thisisjeffchen"><img src="https://avatars.githubusercontent.com/thisisjeffchen?v=4" width="50px" alt="thisisjeffchen" /></a>&nbsp;&nbsp;<a href="https://github.com/nicoguyon"><img src="https://avatars.githubusercontent.com/nicoguyon?v=4" width="50px" alt="nicoguyon" /></a>&nbsp;&nbsp;<a href="https://github.com/arjunb023"><img src="https://avatars.githubusercontent.com/arjunb023?v=4" width="50px" alt="arjunb023" /></a>&nbsp;&nbsp;<a href="https://github.com/Nalhos"><img src="https://avatars.githubusercontent.com/Nalhos?v=4" width="50px" alt="Nalhos" /></a>&nbsp;&nbsp;<a href="https://github.com/belharethsami"><img src="https://avatars.githubusercontent.com/belharethsami?v=4" width="50px" alt="belharethsami" /></a>&nbsp;&nbsp;<a href="https://github.com/Mobivs"><img src="https://avatars.githubusercontent.com/Mobivs?v=4" width="50px" alt="Mobivs" /></a>&nbsp;&nbsp;<a href="https://github.com/txtr99"><img src="https://avatars.githubusercontent.com/txtr99?v=4" width="50px" alt="txtr99" /></a>&nbsp;&nbsp;<a href="https://github.com/ntwrite"><img src="https://avatars.githubusercontent.com/ntwrite?v=4" width="50px" alt="ntwrite" /></a>&nbsp;&nbsp;<a href="https://github.com/founderblocks-sils"><img src="https://avatars.githubusercontent.com/founderblocks-sils?v=4" width="50px" alt="founderblocks-sils" /></a>&nbsp;&nbsp;<a href="https://github.com/kMag410"><img src="https://avatars.githubusercontent.com/kMag410?v=4" width="50px" alt="kMag410" /></a>&nbsp;&nbsp;<a href="https://github.com/angiaou"><img src="https://avatars.githubusercontent.com/angiaou?v=4" width="50px" alt="angiaou" /></a>&nbsp;&nbsp;<a href="https://github.com/garythebat"><img src="https://avatars.githubusercontent.com/garythebat?v=4" width="50px" alt="garythebat" /></a>&nbsp;&nbsp;<a href="https://github.com/lmaugustin"><img src="https://avatars.githubusercontent.com/lmaugustin?v=4" width="50px" alt="lmaugustin" /></a>&nbsp;&nbsp;<a href="https://github.com/shawnharmsen"><img src="https://avatars.githubusercontent.com/shawnharmsen?v=4" width="50px" alt="shawnharmsen" /></a>&nbsp;&nbsp;<a href="https://github.com/clortegah"><img src="https://avatars.githubusercontent.com/clortegah?v=4" width="50px" alt="clortegah" /></a>&nbsp;&nbsp;<a href="https://github.com/MetaPath01"><img src="https://avatars.githubusercontent.com/MetaPath01?v=4" width="50px" alt="MetaPath01" /></a>&nbsp;&nbsp;<a href="https://github.com/sekomike910"><img src="https://avatars.githubusercontent.com/sekomike910?v=4" width="50px" alt="sekomike910" /></a>&nbsp;&nbsp;<a href="https://github.com/MediConCenHK"><img src="https://avatars.githubusercontent.com/MediConCenHK?v=4" width="50px" alt="MediConCenHK" /></a>&nbsp;&nbsp;<a href="https://github.com/svpermari0"><img src="https://avatars.githubusercontent.com/svpermari0?v=4" width="50px" alt="svpermari0" /></a>&nbsp;&nbsp;<a href="https://github.com/jacobyoby"><img src="https://avatars.githubusercontent.com/jacobyoby?v=4" width="50px" alt="jacobyoby" /></a>&nbsp;&nbsp;<a href="https://github.com/turintech"><img src="https://avatars.githubusercontent.com/turintech?v=4" width="50px" alt="turintech" /></a>&nbsp;&nbsp;<a href="https://github.com/allenstecat"><img src="https://avatars.githubusercontent.com/allenstecat?v=4" width="50px" alt="allenstecat" /></a>&nbsp;&nbsp;<a href="https://github.com/CatsMeow492"><img src="https://avatars.githubusercontent.com/CatsMeow492?v=4" width="50px" alt="CatsMeow492" /></a>&nbsp;&nbsp;<a href="https://github.com/tommygeee"><img src="https://avatars.githubusercontent.com/tommygeee?v=4" width="50px" alt="tommygeee" /></a>&nbsp;&nbsp;<a href="https://github.com/judegomila"><img src="https://avatars.githubusercontent.com/judegomila?v=4" width="50px" alt="judegomila" /></a>&nbsp;&nbsp;<a href="https://github.com/cfarquhar"><img src="https://avatars.githubusercontent.com/cfarquhar?v=4" width="50px" alt="cfarquhar" /></a>&nbsp;&nbsp;<a href="https://github.com/ZoneSixGames"><img src="https://avatars.githubusercontent.com/ZoneSixGames?v=4" width="50px" alt="ZoneSixGames" /></a>&nbsp;&nbsp;<a href="https://github.com/kenndanielso"><img src="https://avatars.githubusercontent.com/kenndanielso?v=4" width="50px" alt="kenndanielso" /></a>&nbsp;&nbsp;<a href="https://github.com/CrypteorCapital"><img src="https://avatars.githubusercontent.com/CrypteorCapital?v=4" width="50px" alt="CrypteorCapital" /></a>&nbsp;&nbsp;<a href="https://github.com/sultanmeghji"><img src="https://avatars.githubusercontent.com/sultanmeghji?v=4" width="50px" alt="sultanmeghji" /></a>&nbsp;&nbsp;<a href="https://github.com/jenius-eagle"><img src="https://avatars.githubusercontent.com/jenius-eagle?v=4" width="50px" alt="jenius-eagle" /></a>&nbsp;&nbsp;<a href="https://github.com/josephjacks"><img src="https://avatars.githubusercontent.com/josephjacks?v=4" width="50px" alt="josephjacks" /></a>&nbsp;&nbsp;<a href="https://github.com/pingshian0131"><img src="https://avatars.githubusercontent.com/pingshian0131?v=4" width="50px" alt="pingshian0131" /></a>&nbsp;&nbsp;<a href="https://github.com/AIdevelopersAI"><img src="https://avatars.githubusercontent.com/AIdevelopersAI?v=4" width="50px" alt="AIdevelopersAI" /></a>&nbsp;&nbsp;<a href="https://github.com/ternary5"><img src="https://avatars.githubusercontent.com/ternary5?v=4" width="50px" alt="ternary5" /></a>&nbsp;&nbsp;<a href="https://github.com/ChrisDMT"><img src="https://avatars.githubusercontent.com/ChrisDMT?v=4" width="50px" alt="ChrisDMT" /></a>&nbsp;&nbsp;<a href="https://github.com/AcountoOU"><img src="https://avatars.githubusercontent.com/AcountoOU?v=4" width="50px" alt="AcountoOU" /></a>&nbsp;&nbsp;<a href="https://github.com/chatgpt-prompts"><img src="https://avatars.githubusercontent.com/chatgpt-prompts?v=4" width="50px" alt="chatgpt-prompts" /></a>&nbsp;&nbsp;<a href="https://github.com/Partender"><img src="https://avatars.githubusercontent.com/Partender?v=4" width="50px" alt="Partender" /></a>&nbsp;&nbsp;<a href="https://github.com/Daniel1357"><img src="https://avatars.githubusercontent.com/Daniel1357?v=4" width="50px" alt="Daniel1357" /></a>&nbsp;&nbsp;<a href="https://github.com/KiaArmani"><img src="https://avatars.githubusercontent.com/KiaArmani?v=4" width="50px" alt="KiaArmani" /></a>&nbsp;&nbsp;<a href="https://github.com/zkonduit"><img src="https://avatars.githubusercontent.com/zkonduit?v=4" width="50px" alt="zkonduit" /></a>&nbsp;&nbsp;<a href="https://github.com/fabrietech"><img src="https://avatars.githubusercontent.com/fabrietech?v=4" width="50px" alt="fabrietech" /></a>&nbsp;&nbsp;<a href="https://github.com/scryptedinc"><img src="https://avatars.githubusercontent.com/scryptedinc?v=4" width="50px" alt="scryptedinc" /></a>&nbsp;&nbsp;<a href="https://github.com/coreyspagnoli"><img src="https://avatars.githubusercontent.com/coreyspagnoli?v=4" width="50px" alt="coreyspagnoli" /></a>&nbsp;&nbsp;<a href="https://github.com/AntonioCiolino"><img src="https://avatars.githubusercontent.com/AntonioCiolino?v=4" width="50px" alt="AntonioCiolino" /></a>&nbsp;&nbsp;<a href="https://github.com/Dradstone"><img src="https://avatars.githubusercontent.com/Dradstone?v=4" width="50px" alt="Dradstone" /></a>&nbsp;&nbsp;<a href="https://github.com/CarmenCocoa"><img src="https://avatars.githubusercontent.com/CarmenCocoa?v=4" width="50px" alt="CarmenCocoa" /></a>&nbsp;&nbsp;<a href="https://github.com/bentoml"><img src="https://avatars.githubusercontent.com/bentoml?v=4" width="50px" alt="bentoml" /></a>&nbsp;&nbsp;<a href="https://github.com/merwanehamadi"><img src="https://avatars.githubusercontent.com/merwanehamadi?v=4" width="50px" alt="merwanehamadi" /></a>&nbsp;&nbsp;<a href="https://github.com/vkozacek"><img src="https://avatars.githubusercontent.com/vkozacek?v=4" width="50px" alt="vkozacek" /></a>&nbsp;&nbsp;<a href="https://github.com/ASmithOWL"><img src="https://avatars.githubusercontent.com/ASmithOWL?v=4" width="50px" alt="ASmithOWL" /></a>&nbsp;&nbsp;<a href="https://github.com/tekelsey"><img src="https://avatars.githubusercontent.com/tekelsey?v=4" width="50px" alt="tekelsey" /></a>&nbsp;&nbsp;<a href="https://github.com/GalaxyVideoAgency"><img src="https://avatars.githubusercontent.com/GalaxyVideoAgency?v=4" width="50px" alt="GalaxyVideoAgency" /></a>&nbsp;&nbsp;<a href="https://github.com/wenfengwang"><img src="https://avatars.githubusercontent.com/wenfengwang?v=4" width="50px" alt="wenfengwang" /></a>&nbsp;&nbsp;<a href="https://github.com/rviramontes"><img src="https://avatars.githubusercontent.com/rviramontes?v=4" width="50px" alt="rviramontes" /></a>&nbsp;&nbsp;<a href="https://github.com/indoor47"><img src="https://avatars.githubusercontent.com/indoor47?v=4" width="50px" alt="indoor47" /></a>&nbsp;&nbsp;<a href="https://github.com/ZERO-A-ONE"><img src="https://avatars.githubusercontent.com/ZERO-A-ONE?v=4" width="50px" alt="ZERO-A-ONE" /></a>&nbsp;&nbsp;</p>
+
 ## ⚠️ Limitations
 
 This experiment aims to showcase the potential of GPT-4 but comes with some limitations:

From 4b7fa7f49dab11b0d00ef9b44633e2a9ae52b525 Mon Sep 17 00:00:00 2001
From: Kinance <kinance@gmail.com>
Date: Sat, 27 May 2023 18:52:38 +0900
Subject: [PATCH 072/112] Fix typo and links in documentation (#4440)

---
 CONTRIBUTING.md                        | 4 ++--
 docs/challenges/building_challenges.md | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index c3f97512..13a805ff 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1,4 +1,4 @@
-We maintain a knowledgebase at https://github.com/Significant-Gravitas/Nexus/wiki
+We maintain a knowledgebase at this [wiki](https://github.com/Significant-Gravitas/Nexus/wiki)
 
 We would like to say "We value all contributions". After all, we are an open-source project, so we should say something fluffy like this, right?
 
@@ -11,4 +11,4 @@ If you wish to involve with the project (beyond just contributing PRs), please r
 In fact, why not just look through the whole wiki (it's only a few pages) and hop on our discord (you'll find it in the wiki).
 
 ❤️ & 🔆
-The team @ AutoGPT
+The team @ Auto-GPT
diff --git a/docs/challenges/building_challenges.md b/docs/challenges/building_challenges.md
index ad567238..e59cad3e 100644
--- a/docs/challenges/building_challenges.md
+++ b/docs/challenges/building_challenges.md
@@ -1,4 +1,4 @@
-# Creating Challenges for AutoGPT
+# Creating Challenges for Auto-GPT
 
 🏹 We're on the hunt for talented Challenge Creators! 🎯
 
@@ -14,7 +14,7 @@ Are you ready to play a pivotal role in Auto-GPT's journey? Apply now to become
 
 
 # Getting Started
-Clone the original AutoGPT repo and checkout to master branch
+Clone the original Auto-GPT repo and checkout to master branch
 
 
 The challenges are not written using a specific framework. They try to be very agnostic

From 03036c1bd6ec18247fc212def434742cfb1f57e8 Mon Sep 17 00:00:00 2001
From: Ryan Johns <jedimasterjohns@gmail.com>
Date: Sat, 27 May 2023 09:58:38 -0600
Subject: [PATCH 073/112] Added three more tests to check for edge cases in URL
 validation (#4441)

Co-authored-by: Ryan Johns <rkjohns@verisk.com>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/url_utils/validators.py   |  3 +++
 tests/unit/test_url_validation.py | 16 ++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/autogpt/url_utils/validators.py b/autogpt/url_utils/validators.py
index c9c1d06a..7580774b 100644
--- a/autogpt/url_utils/validators.py
+++ b/autogpt/url_utils/validators.py
@@ -31,6 +31,9 @@ def validate_url(func: Callable[..., Any]) -> Any:
         # Restrict access to local files
         if check_local_file_access(url):
             raise ValueError("Access to local files is restricted")
+        # Check URL length
+        if len(url) > 2000:
+            raise ValueError("URL is too long")
 
         return func(sanitize_url(url), *args, **kwargs)
 
diff --git a/tests/unit/test_url_validation.py b/tests/unit/test_url_validation.py
index c29161af..16eb8cd5 100644
--- a/tests/unit/test_url_validation.py
+++ b/tests/unit/test_url_validation.py
@@ -156,3 +156,19 @@ class TestValidateUrl:
 
         with pytest.raises(ValueError):
             test_func("https:www.google.com")
+
+    # Tests that the function can handle URLs that contain unusual but valid characters.
+    def test_url_with_special_chars(self):
+        url = "https://example.com/path%20with%20spaces"
+        assert dummy_method(url) == url
+
+    # Tests that the function raises a ValueError if the URL is over 2000 characters.
+    def test_extremely_long_url(self):
+        url = "http://example.com/" + "a" * 2000
+        with raises(ValueError, match="URL is too long"):
+            dummy_method(url)
+
+    # Tests that the function can handle internationalized URLs, which contain non-ASCII characters.
+    def test_internationalized_url(self):
+        url = "http://例子.测试"
+        assert dummy_method(url) == url

From 44f6d946f5ab8c7fae132a534f1e4730639499a9 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Sat, 27 May 2023 18:26:30 -0700
Subject: [PATCH 074/112] fix information retrieval challenge (#4448)

---
 docs/challenges/building_challenges.md         |  1 -
 tests/integration/agent_factory.py             | 10 +++++-----
 .../test_information_retrieval_challenge_a.py  |  4 +---
 .../test_kubernetes_template_challenge_a.py    |  3 +--
 tests/integration/challenges/utils.py          | 18 ------------------
 tests/vcr/vcr_filter.py                        |  1 +
 6 files changed, 8 insertions(+), 29 deletions(-)

diff --git a/docs/challenges/building_challenges.md b/docs/challenges/building_challenges.md
index e59cad3e..09ab3bf5 100644
--- a/docs/challenges/building_challenges.md
+++ b/docs/challenges/building_challenges.md
@@ -101,7 +101,6 @@ def input_generator(input_sequence: list) -> Generator[str, None, None]:
 @pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
-@run_multiple_times(3)
 def test_information_retrieval_challenge_a(kubernetes_agent, monkeypatch) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index c2f2d4f6..713afb79 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -145,17 +145,18 @@ def get_company_revenue_agent(
 ):
     command_registry = CommandRegistry()
     command_registry.import_commands("autogpt.commands.file_operations")
+    command_registry.import_commands("autogpt.commands.google_search")
     command_registry.import_commands("autogpt.app")
+    command_registry.import_commands("autogpt.commands.task_statuses")
 
     ai_config = AIConfig(
-        ai_name="Get-CompanyRevenue",
-        ai_role="an autonomous agent that specializes in finding the reported revenue of a company.",
+        ai_name="Information Retrieval Agent",
+        ai_role="an autonomous agent that specializes in retrieving information.",
         ai_goals=[
-            "Write the revenue of Tesla in 2022 to a file. You should write the number without commas and you should not use signs like B for billion and M for million.",
+            "Search for 'tesla revenue 2022' and write the revenue of Tesla in 2022 to a file called output.txt. You should write the number without commas and you should not use signs like B for billion and M for million.",
         ],
     )
     ai_config.command_registry = command_registry
-
     system_prompt = ai_config.construct_full_prompt()
     Config().set_continuous_mode(False)
     agent = Agent(
@@ -168,7 +169,6 @@ def get_company_revenue_agent(
         triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
         workspace_directory=workspace.root,
     )
-
     return agent
 
 
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index 42e9a993..0a0c634c 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -4,17 +4,15 @@ import pytest
 
 from autogpt.commands.file_operations import read_file, write_to_file
 from autogpt.config import Config
-from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
+from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
 CYCLE_COUNT = 3
 from autogpt.agent import Agent
 
 
-@pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
-@run_multiple_times(3)
 def test_information_retrieval_challenge_a(
     get_company_revenue_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
diff --git a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
index b84f5018..10bcfb1c 100644
--- a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
+++ b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
@@ -4,7 +4,7 @@ import yaml
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
-from tests.integration.challenges.utils import run_interaction_loop, run_multiple_times
+from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
 CYCLE_COUNT = 6
@@ -13,7 +13,6 @@ CYCLE_COUNT = 6
 @pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
-@run_multiple_times(3)
 def test_kubernetes_template_challenge_a(
     kubernetes_agent: Agent, monkeypatch: pytest.MonkeyPatch, config: Config
 ) -> None:
diff --git a/tests/integration/challenges/utils.py b/tests/integration/challenges/utils.py
index d80ca977..b7bf83fe 100644
--- a/tests/integration/challenges/utils.py
+++ b/tests/integration/challenges/utils.py
@@ -48,24 +48,6 @@ def generate_noise(noise_size: int) -> str:
     )
 
 
-def run_multiple_times(times: int) -> Callable:
-    """
-    Decorator that runs a test function multiple times.
-
-    :param times: The number of times the test function should be executed.
-    """
-
-    def decorator(test_func: Callable[..., Any]) -> Callable[..., Any]:
-        @wraps(test_func)
-        def wrapper(*args: Tuple[Any, ...], **kwargs: Dict[str, Any]) -> None:
-            for _ in range(times):
-                test_func(*args, **kwargs)
-
-        return wrapper
-
-    return decorator
-
-
 def setup_mock_input(monkeypatch: pytest.MonkeyPatch, cycle_count: int) -> None:
     """
     Sets up the mock input for testing.
diff --git a/tests/vcr/vcr_filter.py b/tests/vcr/vcr_filter.py
index 3a58bee9..a86f501a 100644
--- a/tests/vcr/vcr_filter.py
+++ b/tests/vcr/vcr_filter.py
@@ -19,6 +19,7 @@ REPLACEMENTS: List[Dict[str, str]] = [
 ALLOWED_HOSTNAMES: List[str] = [
     "api.openai.com",
     "localhost:50337",
+    "duckduckgo.com",
 ]
 
 if PROXY:

From 78774526f42025ebd1949e841d475f3b3d5229bc Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Sun, 28 May 2023 01:30:02 +0000
Subject: [PATCH 075/112] Update submodule reference

---
 tests/Auto-GPT-test-cassettes | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
index f518f20d..909c30a0 160000
--- a/tests/Auto-GPT-test-cassettes
+++ b/tests/Auto-GPT-test-cassettes
@@ -1 +1 @@
-Subproject commit f518f20d83e57e15242b504415132c04991165a0
+Subproject commit 909c30a0ab8694db2ef63dacc0b3d6a4a0cd74f2

From ee9f10a8d8138a0fc5c352d5950f3da3d8c24c57 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Sun, 28 May 2023 05:50:50 -0700
Subject: [PATCH 076/112] remove unused imports automatically (#4449)

* remove unused imports automatically

* add linters to pr template

* remove useless try statement
---
 .github/PULL_REQUEST_TEMPLATE.md                       |  8 +++++++-
 .github/workflows/ci.yml                               |  5 +++++
 .pre-commit-config.yaml                                |  6 ++++++
 autogpt/app.py                                         |  2 +-
 autogpt/commands/command.py                            |  2 +-
 autogpt/commands/execute_code.py                       |  1 -
 autogpt/commands/file_operations.py                    |  1 -
 autogpt/commands/web_selenium.py                       |  2 +-
 autogpt/llm/base.py                                    |  4 ----
 autogpt/llm/chat.py                                    |  2 --
 autogpt/memory/vector/utils.py                         |  1 -
 autogpt/models/base_open_ai_plugin.py                  |  7 -------
 autogpt/plugins.py                                     |  2 +-
 autogpt/singleton.py                                   |  2 --
 autogpt/speech/base.py                                 |  2 --
 autogpt/speech/brian.py                                |  1 -
 autogpt/utils.py                                       |  9 +--------
 tests/integration/challenges/conftest.py               |  1 -
 .../test_information_retrieval_challenge_a.py          |  4 +---
 tests/integration/challenges/utils.py                  |  2 +-
 tests/integration/memory/conftest.py                   |  1 -
 tests/integration/test_setup.py                        |  6 +-----
 tests/test_audio_text_read_audio.py                    |  1 -
 tests/test_config.py                                   |  1 -
 tests/test_image_gen.py                                |  1 -
 tests/test_text_file_parsers.py                        |  2 --
 tests/test_utils.py                                    |  5 +----
 tests/unit/models/test_base_open_api_plugin.py         | 10 +---------
 tests/unit/test_browse_scrape_links.py                 |  1 -
 tests/unit/test_json_parser.py                         |  1 -
 tests/unit/test_json_utils_llm.py                      |  3 ---
 tests/unit/test_plugins.py                             |  1 -
 tests/vcr/vcr_filter.py                                |  1 -
 33 files changed, 28 insertions(+), 70 deletions(-)

diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
index 81a4b90a..f159c646 100644
--- a/.github/PULL_REQUEST_TEMPLATE.md
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -36,7 +36,13 @@ By following these guidelines, your PRs are more likely to be merged quickly aft
 - [ ] I have considered potential risks and mitigations for my changes.
 - [ ] I have documented my changes clearly and comprehensively.
 - [ ] I have not snuck in any "extra" small tweaks changes. <!-- Submit these as separate Pull Requests, they are the easiest to merge! -->
-- [ ] I have run `black .` and `isort .` against my code to ensure it passes our linter.
+- [ ] I have run the following commands against my code to ensure it passes our linters:
+    ```shell
+    black .
+    isort .
+    mypy
+    autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports autogpt tests --in-place
+    ```
 
 <!-- If you haven't added tests, please explain why. If you have, check the appropriate box. If you've ensured your PR is atomic and well-documented, check the corresponding boxes. -->
 
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index e91cb960..368930a1 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -51,6 +51,11 @@ jobs:
         run: mypy
         if: success() || failure()
 
+      - name: Check for unused imports and pass statements
+        run: |
+          cmd="autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports autogpt tests"
+          $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)
+
   test:
     permissions:
       # Gives the action the necessary permissions for publishing new
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 345d88be..53928603 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -21,6 +21,7 @@ repos:
     hooks:
       - id: black
         language_version: python3.10
+
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: 'v1.3.0'
     hooks:
@@ -28,6 +29,11 @@ repos:
 
   - repo: local
     hooks:
+      - id: autoflake
+        name: autoflake
+        entry: autoflake --in-place --remove-all-unused-imports --recursive --ignore-init-module-imports autogpt tests
+        language: python
+        types: [ python ]
       - id: pytest-check
         name: pytest-check
         entry: pytest --cov=autogpt --without-integration --without-slow-integration
diff --git a/autogpt/app.py b/autogpt/app.py
index 985bf0f8..0804b482 100644
--- a/autogpt/app.py
+++ b/autogpt/app.py
@@ -1,6 +1,6 @@
 """ Command and Control """
 import json
-from typing import Dict, List, NoReturn, Union
+from typing import Dict, List, Union
 
 from autogpt.agent.agent_manager import AgentManager
 from autogpt.commands.command import CommandRegistry, command
diff --git a/autogpt/commands/command.py b/autogpt/commands/command.py
index e99a68c0..742cc8df 100644
--- a/autogpt/commands/command.py
+++ b/autogpt/commands/command.py
@@ -1,7 +1,7 @@
 import functools
 import importlib
 import inspect
-from typing import TYPE_CHECKING, Any, Callable, Optional
+from typing import Any, Callable, Optional
 
 from autogpt.config import Config
 from autogpt.logs import logger
diff --git a/autogpt/commands/execute_code.py b/autogpt/commands/execute_code.py
index e8ef6551..20c5e1a2 100644
--- a/autogpt/commands/execute_code.py
+++ b/autogpt/commands/execute_code.py
@@ -2,7 +2,6 @@
 import os
 import subprocess
 from pathlib import Path
-from typing import TYPE_CHECKING
 
 import docker
 from docker.errors import ImageNotFound
diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 8288e389..824db50c 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -6,7 +6,6 @@ import os
 import os.path
 from typing import TYPE_CHECKING, Generator, Literal
 
-import charset_normalizer
 import requests
 from colorama import Back, Fore
 from requests.adapters import HTTPAdapter, Retry
diff --git a/autogpt/commands/web_selenium.py b/autogpt/commands/web_selenium.py
index da6dd35d..3cc99282 100644
--- a/autogpt/commands/web_selenium.py
+++ b/autogpt/commands/web_selenium.py
@@ -29,7 +29,7 @@ from webdriver_manager.microsoft import EdgeChromiumDriverManager as EdgeDriverM
 
 from autogpt.commands.command import command
 from autogpt.logs import logger
-from autogpt.memory.vector import MemoryItem, NoMemory, get_memory
+from autogpt.memory.vector import MemoryItem, get_memory
 from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
 from autogpt.url_utils.validators import validate_url
 
diff --git a/autogpt/llm/base.py b/autogpt/llm/base.py
index 5018b703..76bd3db1 100644
--- a/autogpt/llm/base.py
+++ b/autogpt/llm/base.py
@@ -44,15 +44,11 @@ class ModelInfo:
 class ChatModelInfo(ModelInfo):
     """Struct for chat model information."""
 
-    pass
-
 
 @dataclass
 class TextModelInfo(ModelInfo):
     """Struct for text completion model information."""
 
-    pass
-
 
 @dataclass
 class EmbeddingModelInfo(ModelInfo):
diff --git a/autogpt/llm/chat.py b/autogpt/llm/chat.py
index c55016f2..292990f5 100644
--- a/autogpt/llm/chat.py
+++ b/autogpt/llm/chat.py
@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import time
-from random import shuffle
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
@@ -13,7 +12,6 @@ from autogpt.llm.base import ChatSequence, Message
 from autogpt.llm.utils import count_message_tokens, create_chat_completion
 from autogpt.log_cycle.log_cycle import CURRENT_CONTEXT_FILE_NAME
 from autogpt.logs import logger
-from autogpt.memory.vector import MemoryItem, get_memory
 
 cfg = Config()
 
diff --git a/autogpt/memory/vector/utils.py b/autogpt/memory/vector/utils.py
index d01f7108..75d1f69d 100644
--- a/autogpt/memory/vector/utils.py
+++ b/autogpt/memory/vector/utils.py
@@ -1,7 +1,6 @@
 from typing import Any, overload
 
 import numpy as np
-import numpy.typing as npt
 import openai
 
 from autogpt.config import Config
diff --git a/autogpt/models/base_open_ai_plugin.py b/autogpt/models/base_open_ai_plugin.py
index 8f6dd52c..c0aac8ed 100644
--- a/autogpt/models/base_open_ai_plugin.py
+++ b/autogpt/models/base_open_ai_plugin.py
@@ -68,7 +68,6 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
             prompt (PromptGenerator): The prompt generator.
             messages (List[str]): The list of messages.
         """
-        pass
 
     def can_handle_post_planning(self) -> bool:
         """This method is called to check that the plugin can
@@ -116,7 +115,6 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
         Returns:
             Optional[str]: The resulting message.
         """
-        pass
 
     def can_handle_post_instruction(self) -> bool:
         """This method is called to check that the plugin can
@@ -196,7 +194,6 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
         Returns:
             str: The resulting response.
         """
-        pass
 
     def can_handle_text_embedding(self, text: str) -> bool:
         """This method is called to check that the plugin can
@@ -214,7 +211,6 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
         Returns:
             list: The text embedding.
         """
-        pass
 
     def can_handle_user_input(self, user_input: str) -> bool:
         """This method is called to check that the plugin can
@@ -237,8 +233,6 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
             str: The user input.
         """
 
-        pass
-
     def can_handle_report(self) -> bool:
         """This method is called to check that the plugin can
         handle the report method.
@@ -253,4 +247,3 @@ class BaseOpenAIPlugin(AutoGPTPluginTemplate):
         Args:
             message (str): The message to report.
         """
-        pass
diff --git a/autogpt/plugins.py b/autogpt/plugins.py
index 780593a8..f36ba36e 100644
--- a/autogpt/plugins.py
+++ b/autogpt/plugins.py
@@ -5,7 +5,7 @@ import json
 import os
 import zipfile
 from pathlib import Path
-from typing import List, Optional, Tuple
+from typing import List
 from urllib.parse import urlparse
 from zipimport import zipimporter
 
diff --git a/autogpt/singleton.py b/autogpt/singleton.py
index 55b2aeea..b3a5af52 100644
--- a/autogpt/singleton.py
+++ b/autogpt/singleton.py
@@ -20,5 +20,3 @@ class AbstractSingleton(abc.ABC, metaclass=Singleton):
     """
     Abstract singleton class for ensuring only one instance of a class.
     """
-
-    pass
diff --git a/autogpt/speech/base.py b/autogpt/speech/base.py
index 7adcc37d..a7570d94 100644
--- a/autogpt/speech/base.py
+++ b/autogpt/speech/base.py
@@ -37,7 +37,6 @@ class VoiceBase(AbstractSingleton):
         """
         Setup the voices, API key, etc.
         """
-        pass
 
     @abc.abstractmethod
     def _speech(self, text: str, voice_index: int = 0) -> bool:
@@ -47,4 +46,3 @@ class VoiceBase(AbstractSingleton):
         Args:
             text (str): The text to play.
         """
-        pass
diff --git a/autogpt/speech/brian.py b/autogpt/speech/brian.py
index ffa4e51e..f63c206b 100644
--- a/autogpt/speech/brian.py
+++ b/autogpt/speech/brian.py
@@ -12,7 +12,6 @@ class BrianSpeech(VoiceBase):
 
     def _setup(self) -> None:
         """Setup the voices, API key, etc."""
-        pass
 
     def _speech(self, text: str, _: int = 0) -> bool:
         """Speak text using Brian with the streamelements API
diff --git a/autogpt/utils.py b/autogpt/utils.py
index 8eb95deb..653841a2 100644
--- a/autogpt/utils.py
+++ b/autogpt/utils.py
@@ -6,15 +6,8 @@ import yaml
 from colorama import Fore, Style
 from git.repo import Repo
 
-from autogpt.logs import logger
-
-# Use readline if available (for clean_input)
-try:
-    import readline
-except ImportError:
-    pass
-
 from autogpt.config import Config
+from autogpt.logs import logger
 
 
 def batch(iterable, max_batch_length: int, overlap: int = 0):
diff --git a/tests/integration/challenges/conftest.py b/tests/integration/challenges/conftest.py
index 9bb5a1a4..c196fc72 100644
--- a/tests/integration/challenges/conftest.py
+++ b/tests/integration/challenges/conftest.py
@@ -2,7 +2,6 @@ import pytest
 from _pytest.config import Config
 from _pytest.config.argparsing import Parser
 from _pytest.fixtures import FixtureRequest
-from _pytest.monkeypatch import MonkeyPatch
 
 
 def pytest_addoption(parser: Parser) -> None:
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index 0a0c634c..1d332817 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -1,8 +1,6 @@
-import typing
-
 import pytest
 
-from autogpt.commands.file_operations import read_file, write_to_file
+from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
diff --git a/tests/integration/challenges/utils.py b/tests/integration/challenges/utils.py
index b7bf83fe..94dd5a0c 100644
--- a/tests/integration/challenges/utils.py
+++ b/tests/integration/challenges/utils.py
@@ -1,7 +1,7 @@
 import contextlib
 import random
 from functools import wraps
-from typing import Any, Callable, Dict, Generator, Optional, Tuple
+from typing import Any, Callable, Dict, Generator, Tuple
 
 import pytest
 
diff --git a/tests/integration/memory/conftest.py b/tests/integration/memory/conftest.py
index f7fe295a..64ac651d 100644
--- a/tests/integration/memory/conftest.py
+++ b/tests/integration/memory/conftest.py
@@ -1,4 +1,3 @@
-import numpy
 import pytest
 
 from autogpt.memory.vector.memory_item import MemoryItem
diff --git a/tests/integration/test_setup.py b/tests/integration/test_setup.py
index 444d9474..4e2a505d 100644
--- a/tests/integration/test_setup.py
+++ b/tests/integration/test_setup.py
@@ -3,11 +3,7 @@ from unittest.mock import patch
 import pytest
 
 from autogpt.config.ai_config import AIConfig
-from autogpt.setup import (
-    generate_aiconfig_automatic,
-    generate_aiconfig_manual,
-    prompt_user,
-)
+from autogpt.setup import generate_aiconfig_automatic, prompt_user
 from tests.utils import requires_api_key
 
 
diff --git a/tests/test_audio_text_read_audio.py b/tests/test_audio_text_read_audio.py
index 1f324601..4385da32 100644
--- a/tests/test_audio_text_read_audio.py
+++ b/tests/test_audio_text_read_audio.py
@@ -1,7 +1,6 @@
 # Date: 2023-5-13
 # Author: Generated by GoCodeo.
 import json
-from io import BytesIO
 from unittest.mock import MagicMock, patch
 
 import pytest
diff --git a/tests/test_config.py b/tests/test_config.py
index 1e156f98..81d151cd 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -5,7 +5,6 @@ for the AI and ensures it behaves as a singleton.
 from unittest.mock import patch
 
 import pytest
-from openai import InvalidRequestError
 
 from autogpt.configurator import create_config
 
diff --git a/tests/test_image_gen.py b/tests/test_image_gen.py
index 59962af0..5c04921b 100644
--- a/tests/test_image_gen.py
+++ b/tests/test_image_gen.py
@@ -7,7 +7,6 @@ import pytest
 from PIL import Image
 
 from autogpt.commands.image_gen import generate_image, generate_image_with_sd_webui
-from autogpt.config import Config
 from tests.utils import requires_api_key
 
 
diff --git a/tests/test_text_file_parsers.py b/tests/test_text_file_parsers.py
index d15c63ae..2e71aa69 100644
--- a/tests/test_text_file_parsers.py
+++ b/tests/test_text_file_parsers.py
@@ -1,13 +1,11 @@
 import json
 import tempfile
-from functools import partial
 from unittest import TestCase
 from xml.etree import ElementTree
 
 import docx
 import yaml
 from bs4 import BeautifulSoup
-from PyPDF2 import PdfWriter
 
 from autogpt.commands.file_operations_utils import is_file_binary_fn, read_textual_file
 from autogpt.logs import logger
diff --git a/tests/test_utils.py b/tests/test_utils.py
index f9ab3698..c0ce28cc 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -1,13 +1,10 @@
 import os
-from unittest.mock import Mock, patch
+from unittest.mock import patch
 
 import pytest
 import requests
-from colorama import Fore
-from git import Repo
 
 from autogpt.utils import (
-    clean_input,
     get_bulletin_from_web,
     get_current_git_branch,
     get_latest_bulletin,
diff --git a/tests/unit/models/test_base_open_api_plugin.py b/tests/unit/models/test_base_open_api_plugin.py
index 456c74c7..4d41eddd 100644
--- a/tests/unit/models/test_base_open_api_plugin.py
+++ b/tests/unit/models/test_base_open_api_plugin.py
@@ -1,19 +1,11 @@
-from typing import Any, Dict, List, Optional, Tuple
-
 import pytest
 
-from autogpt.models.base_open_ai_plugin import (
-    BaseOpenAIPlugin,
-    Message,
-    PromptGenerator,
-)
+from autogpt.models.base_open_ai_plugin import BaseOpenAIPlugin
 
 
 class DummyPlugin(BaseOpenAIPlugin):
     """A dummy plugin for testing purposes."""
 
-    pass
-
 
 @pytest.fixture
 def dummy_plugin():
diff --git a/tests/unit/test_browse_scrape_links.py b/tests/unit/test_browse_scrape_links.py
index 15f495db..2d1e8f90 100644
--- a/tests/unit/test_browse_scrape_links.py
+++ b/tests/unit/test_browse_scrape_links.py
@@ -2,7 +2,6 @@
 
 # Dependencies:
 # pip install pytest-mock
-import pytest
 
 from autogpt.commands.web_requests import scrape_links
 
diff --git a/tests/unit/test_json_parser.py b/tests/unit/test_json_parser.py
index 69cddca6..be5f0733 100644
--- a/tests/unit/test_json_parser.py
+++ b/tests/unit/test_json_parser.py
@@ -1,7 +1,6 @@
 from unittest import TestCase
 
 from autogpt.json_utils.json_fix_llm import fix_and_parse_json
-from tests.utils import skip_in_ci
 
 
 class TestParseJson(TestCase):
diff --git a/tests/unit/test_json_utils_llm.py b/tests/unit/test_json_utils_llm.py
index b8c9518d..93e01acb 100644
--- a/tests/unit/test_json_utils_llm.py
+++ b/tests/unit/test_json_utils_llm.py
@@ -1,12 +1,9 @@
 # Generated by CodiumAI
-import pytest
-from loguru import logger
 
 from autogpt.json_utils.json_fix_llm import (
     fix_and_parse_json,
     fix_json_using_multiple_techniques,
 )
-from tests.utils import requires_api_key
 
 """
 Code Analysis
diff --git a/tests/unit/test_plugins.py b/tests/unit/test_plugins.py
index 885ec4c3..6aa8dd47 100644
--- a/tests/unit/test_plugins.py
+++ b/tests/unit/test_plugins.py
@@ -1,6 +1,5 @@
 import pytest
 
-from autogpt.config import Config
 from autogpt.plugins import denylist_allowlist_check, inspect_zip_for_modules
 
 PLUGINS_TEST_DIR = "tests/unit/data/test_plugins"
diff --git a/tests/vcr/vcr_filter.py b/tests/vcr/vcr_filter.py
index a86f501a..4cc49fd3 100644
--- a/tests/vcr/vcr_filter.py
+++ b/tests/vcr/vcr_filter.py
@@ -1,5 +1,4 @@
 import json
-import os
 import re
 from typing import Any, Dict, List
 

From daafda320b41ffaf8157fdbec8ee705cf22c8922 Mon Sep 17 00:00:00 2001
From: Toran Bruce Richards <toran.richards@gmail.com>
Date: Mon, 29 May 2023 15:28:57 +1200
Subject: [PATCH 077/112] Update README.md

Remove outdated reference to En_GPT
---
 README.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/README.md b/README.md
index 4bc232b5..223e189e 100644
--- a/README.md
+++ b/README.md
@@ -138,7 +138,6 @@ By using Auto-GPT, you agree to indemnify, defend, and hold harmless the develop
 Stay up-to-date with the latest news, updates, and insights about Auto-GPT by following our Twitter accounts. Engage with the developer and the AI's own account for interesting discussions, project updates, and more.
 
 - **Developer**: Follow [@siggravitas](https://twitter.com/siggravitas) for insights into the development process, project updates, and related topics from the creator of Entrepreneur-GPT.
-- **Entrepreneur-GPT**: Join the conversation with the AI itself by following [@En_GPT](https://twitter.com/En_GPT). Share your experiences, discuss the AI's outputs, and engage with the growing community of users.
 
 We look forward to connecting with you and hearing your thoughts, ideas, and experiences with Auto-GPT. Join us on Twitter and let's explore the future of AI together!
 

From 31cd836530871637847fa79064a99992d0181509 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 29 May 2023 00:47:06 -0700
Subject: [PATCH 078/112] "Beat Challenges" Mode (#4447)

Co-authored-by: Richard Beales <rich@richbeales.net>
---
 .gitmodules                                   |  2 +-
 .../basic_abilities/test_browse_website.py    |  6 +-
 .../basic_abilities/test_write_file.py        |  5 ++
 .../challenge_decorator/__init__.py           |  0
 .../challenge_decorator/challenge.py          | 21 +++++
 .../challenge_decorator.py                    | 68 ++++++++++++++++
 .../challenge_decorator/challenge_utils.py    | 81 +++++++++++++++++++
 .../challenge_decorator/score_utils.py        | 59 ++++++++++++++
 tests/integration/challenges/conftest.py      | 19 ++++-
 .../integration/challenges/current_score.json | 38 +++++++++
 .../test_information_retrieval_challenge_a.py |  5 ++
 .../test_kubernetes_template_challenge_a.py   | 19 +++--
 .../memory/test_memory_challenge_a.py         | 23 +++---
 .../memory/test_memory_challenge_b.py         | 25 +++---
 .../memory/test_memory_challenge_c.py         | 29 ++++---
 tests/integration/challenges/utils.py         | 35 +-------
 .../challenges/utils/build_current_score.py   | 47 +++++++++++
 17 files changed, 400 insertions(+), 82 deletions(-)
 create mode 100644 tests/integration/challenges/challenge_decorator/__init__.py
 create mode 100644 tests/integration/challenges/challenge_decorator/challenge.py
 create mode 100644 tests/integration/challenges/challenge_decorator/challenge_decorator.py
 create mode 100644 tests/integration/challenges/challenge_decorator/challenge_utils.py
 create mode 100644 tests/integration/challenges/challenge_decorator/score_utils.py
 create mode 100644 tests/integration/challenges/current_score.json
 create mode 100644 tests/integration/challenges/utils/build_current_score.py

diff --git a/.gitmodules b/.gitmodules
index 694ca570..55d09f84 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,4 +1,4 @@
 [submodule "tests/Auto-GPT-test-cassettes"]
     path = tests/Auto-GPT-test-cassettes
     url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes
-    branch = master
+    branch = master
\ No newline at end of file
diff --git a/tests/integration/challenges/basic_abilities/test_browse_website.py b/tests/integration/challenges/basic_abilities/test_browse_website.py
index 3f9821ed..09e5ab22 100644
--- a/tests/integration/challenges/basic_abilities/test_browse_website.py
+++ b/tests/integration/challenges/basic_abilities/test_browse_website.py
@@ -1,6 +1,9 @@
 import pytest
 
 from autogpt.agent import Agent
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -9,11 +12,12 @@ CYCLE_COUNT = 2
 
 @requires_api_key("OPENAI_API_KEY")
 @pytest.mark.vcr
+@challenge
 def test_browse_website(
     browser_agent: Agent,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
-    # config: Config,
+    level_to_run: int,
 ) -> None:
     file_path = browser_agent.workspace.get_path("browse_website.txt")
     run_interaction_loop(monkeypatch, browser_agent, CYCLE_COUNT)
diff --git a/tests/integration/challenges/basic_abilities/test_write_file.py b/tests/integration/challenges/basic_abilities/test_write_file.py
index efc5e921..cbbad514 100644
--- a/tests/integration/challenges/basic_abilities/test_write_file.py
+++ b/tests/integration/challenges/basic_abilities/test_write_file.py
@@ -3,6 +3,9 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -11,11 +14,13 @@ CYCLE_COUNT = 3
 
 @requires_api_key("OPENAI_API_KEY")
 @pytest.mark.vcr
+@challenge
 def test_write_file(
     writer_agent: Agent,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
+    level_to_run: int,
 ) -> None:
     file_path = str(writer_agent.workspace.get_path("hello_world.txt"))
     run_interaction_loop(monkeypatch, writer_agent, CYCLE_COUNT)
diff --git a/tests/integration/challenges/challenge_decorator/__init__.py b/tests/integration/challenges/challenge_decorator/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/integration/challenges/challenge_decorator/challenge.py b/tests/integration/challenges/challenge_decorator/challenge.py
new file mode 100644
index 00000000..baf821a1
--- /dev/null
+++ b/tests/integration/challenges/challenge_decorator/challenge.py
@@ -0,0 +1,21 @@
+from typing import Optional
+
+
+class Challenge:
+    BEAT_CHALLENGES = False
+
+    def __init__(
+        self,
+        name: str,
+        category: str,
+        max_level: int,
+        max_level_beaten: Optional[int],
+        level_to_run: Optional[int] = None,
+    ) -> None:
+        self.name = name
+        self.category = category
+        self.max_level_beaten = max_level_beaten
+        self.max_level = max_level
+        self.succeeded = False
+        self.skipped = False
+        self.level_to_run = level_to_run
diff --git a/tests/integration/challenges/challenge_decorator/challenge_decorator.py b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
new file mode 100644
index 00000000..580dc089
--- /dev/null
+++ b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
@@ -0,0 +1,68 @@
+import contextlib
+import os
+from functools import wraps
+from typing import Any, Callable, Optional
+
+import pytest
+
+from tests.integration.challenges.challenge_decorator.challenge import Challenge
+from tests.integration.challenges.challenge_decorator.challenge_utils import (
+    create_challenge,
+)
+from tests.integration.challenges.challenge_decorator.score_utils import (
+    get_scores,
+    update_new_score,
+)
+
+MAX_LEVEL_TO_IMPROVE_ON = (
+    1  # we will attempt to beat 1 level above the current level for now.
+)
+
+
+def challenge(func: Callable[..., Any]) -> Callable[..., None]:
+    @wraps(func)
+    def wrapper(*args: Any, **kwargs: Any) -> None:
+        run_remaining = MAX_LEVEL_TO_IMPROVE_ON if Challenge.BEAT_CHALLENGES else 1
+
+        while run_remaining > 0:
+            current_score, new_score, new_score_location = get_scores()
+            level_to_run = kwargs["level_to_run"] if "level_to_run" in kwargs else None
+            challenge = create_challenge(
+                func, current_score, Challenge.BEAT_CHALLENGES, level_to_run
+            )
+            if challenge.level_to_run is not None:
+                kwargs["level_to_run"] = challenge.level_to_run
+                with contextlib.suppress(AssertionError):
+                    func(*args, **kwargs)
+                    challenge.succeeded = True
+            else:
+                challenge.skipped = True
+            if os.environ.get("CI") == "true":
+                new_max_level_beaten = get_new_max_level_beaten(
+                    challenge, Challenge.BEAT_CHALLENGES
+                )
+                update_new_score(
+                    new_score_location, new_score, challenge, new_max_level_beaten
+                )
+            if challenge.level_to_run is None:
+                pytest.skip("This test has not been unlocked yet.")
+
+            if not challenge.succeeded:
+                if Challenge.BEAT_CHALLENGES:
+                    # xfail
+                    pytest.xfail("Challenge failed")
+                raise AssertionError("Challenge failed")
+            run_remaining -= 1
+
+    return wrapper
+
+
+def get_new_max_level_beaten(
+    challenge: Challenge, beat_challenges: bool
+) -> Optional[int]:
+    if challenge.succeeded:
+        return challenge.level_to_run
+    if challenge.skipped:
+        return challenge.max_level_beaten
+    # Challenge failed
+    return challenge.max_level_beaten if beat_challenges else None
diff --git a/tests/integration/challenges/challenge_decorator/challenge_utils.py b/tests/integration/challenges/challenge_decorator/challenge_utils.py
new file mode 100644
index 00000000..b94f7164
--- /dev/null
+++ b/tests/integration/challenges/challenge_decorator/challenge_utils.py
@@ -0,0 +1,81 @@
+import os
+from typing import Any, Callable, Dict, Optional, Tuple
+
+from tests.integration.challenges.challenge_decorator.challenge import Challenge
+
+CHALLENGE_PREFIX = "test_"
+
+
+def create_challenge(
+    func: Callable[..., Any],
+    current_score: Dict[str, Any],
+    is_beat_challenges: bool,
+    level_to_run: Optional[int] = None,
+) -> Challenge:
+    challenge_category, challenge_name = get_challenge_identifiers(func)
+
+    max_level = get_max_level(current_score, challenge_category, challenge_name)
+    max_level_beaten = get_max_level_beaten(
+        current_score, challenge_category, challenge_name
+    )
+    level_to_run = get_level_to_run(
+        is_beat_challenges, level_to_run, max_level, max_level_beaten
+    )
+
+    return Challenge(
+        name=challenge_name,
+        category=challenge_category,
+        max_level=max_level,
+        max_level_beaten=max_level_beaten,
+        level_to_run=level_to_run,
+    )
+
+
+def get_level_to_run(
+    is_beat_challenges: bool,
+    level_to_run: Optional[int],
+    max_level: int,
+    max_level_beaten: Optional[int],
+) -> Optional[int]:
+    if level_to_run is not None:
+        if level_to_run > max_level:
+            raise ValueError(
+                f"Level to run ({level_to_run}) is greater than max level ({max_level})"
+            )
+        return level_to_run
+    if is_beat_challenges:
+        if max_level_beaten == max_level:
+            return None
+        return 1 if max_level_beaten is None else max_level_beaten + 1
+    return max_level_beaten
+
+
+def get_challenge_identifiers(func: Callable[..., Any]) -> Tuple[str, str]:
+    full_path = os.path.dirname(os.path.abspath(func.__code__.co_filename))
+    challenge_category = os.path.basename(full_path)
+    challenge_name = func.__name__.replace(CHALLENGE_PREFIX, "")
+    return challenge_category, challenge_name
+
+
+def get_max_level(
+    current_score: Dict[str, Any],
+    challenge_category: str,
+    challenge_name: str,
+) -> int:
+    return (
+        current_score.get(challenge_category, {})
+        .get(challenge_name, {})
+        .get("max_level", 1)
+    )
+
+
+def get_max_level_beaten(
+    current_score: Dict[str, Any],
+    challenge_category: str,
+    challenge_name: str,
+) -> Optional[int]:
+    return (
+        current_score.get(challenge_category, {})
+        .get(challenge_name, {})
+        .get("max_level_beaten", None)
+    )
diff --git a/tests/integration/challenges/challenge_decorator/score_utils.py b/tests/integration/challenges/challenge_decorator/score_utils.py
new file mode 100644
index 00000000..0a3b71a8
--- /dev/null
+++ b/tests/integration/challenges/challenge_decorator/score_utils.py
@@ -0,0 +1,59 @@
+import json
+import os
+from typing import Any, Dict, Optional, Tuple
+
+from tests.integration.challenges.challenge_decorator.challenge import Challenge
+
+CURRENT_SCORE_LOCATION = "../current_score"
+NEW_SCORE_LOCATION = "../new_score"
+
+
+def update_new_score(
+    filename_new_score: str,
+    new_score: Dict[str, Any],
+    challenge: Challenge,
+    new_max_level_beaten: Optional[int],
+) -> None:
+    write_new_score(new_score, challenge, new_max_level_beaten)
+    write_new_score_to_file(new_score, filename_new_score)
+
+
+def write_new_score(
+    new_score: Dict[str, Any], challenge: Challenge, new_max_level_beaten: Optional[int]
+) -> Dict[str, Any]:
+    new_score.setdefault(challenge.category, {})
+    new_score[challenge.category][challenge.name] = {
+        "max_level_beaten": new_max_level_beaten,
+        "max_level": challenge.max_level,
+    }
+    return new_score
+
+
+def write_new_score_to_file(new_score: Dict[str, Any], filename: str) -> None:
+    with open(filename, "w") as file:
+        json.dump(new_score, file, indent=4)
+
+
+def get_scores() -> Tuple[Dict[str, Any], Dict[str, Any], str]:
+    filename_current_score, filename_new_score = get_score_locations()
+    current_score = load_json(filename_current_score)
+    new_score = load_json(filename_new_score)
+    return current_score, new_score, filename_new_score
+
+
+def load_json(filename: str) -> Dict[str, Any]:
+    if os.path.isfile(filename):
+        with open(filename, "r") as file:
+            return json.load(file)
+    else:
+        return {}
+
+
+def get_score_locations() -> Tuple[str, str]:
+    pid = os.getpid()
+    project_root = os.path.dirname(os.path.abspath(__file__))
+    filename_current_score = os.path.join(
+        project_root, f"{CURRENT_SCORE_LOCATION}.json"
+    )
+    filename_new_score = os.path.join(project_root, f"{NEW_SCORE_LOCATION}_{pid}.json")
+    return filename_current_score, filename_new_score
diff --git a/tests/integration/challenges/conftest.py b/tests/integration/challenges/conftest.py
index c196fc72..8a1b5c40 100644
--- a/tests/integration/challenges/conftest.py
+++ b/tests/integration/challenges/conftest.py
@@ -3,18 +3,33 @@ from _pytest.config import Config
 from _pytest.config.argparsing import Parser
 from _pytest.fixtures import FixtureRequest
 
+from tests.integration.challenges.challenge_decorator.challenge import Challenge
+
 
 def pytest_addoption(parser: Parser) -> None:
     parser.addoption(
         "--level", action="store", default=None, type=int, help="Specify test level"
     )
+    parser.addoption(
+        "--beat-challenges",
+        action="store_true",
+        help="Spepcifies whether the test suite should attempt to beat challenges",
+    )
 
 
 def pytest_configure(config: Config) -> None:
-    config.option.level = config.getoption("--level")
+    level = config.getoption("--level", default=None)
+    config.option.level = level
+    beat_challenges = config.getoption("--beat-challenges", default=False)
+    config.option.beat_challenges = beat_challenges
 
 
 @pytest.fixture
-def user_selected_level(request: FixtureRequest) -> int:
+def level_to_run(request: FixtureRequest) -> int:
     ## used for challenges in the goal oriented tests
     return request.config.option.level
+
+
+@pytest.fixture(autouse=True)
+def check_beat_challenges(request: FixtureRequest) -> None:
+    Challenge.BEAT_CHALLENGES = request.config.getoption("--beat-challenges")
diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
new file mode 100644
index 00000000..a734ff5d
--- /dev/null
+++ b/tests/integration/challenges/current_score.json
@@ -0,0 +1,38 @@
+{
+    "basic_abilities": {
+        "browse_website": {
+            "max_level": 1,
+            "max_level_beaten": 1
+        },
+        "write_file": {
+            "max_level": 1,
+            "max_level_beaten": 1
+        }
+    },
+    "information_retrieval": {
+        "information_retrieval_challenge_a": {
+            "max_level": 1,
+            "max_level_beaten": 1
+        }
+    },
+    "kubernetes": {
+        "kubernetes_template_challenge_a": {
+            "max_level": 1,
+            "max_level_beaten": null
+        }
+    },
+    "memory": {
+        "memory_challenge_a": {
+            "max_level": 3,
+            "max_level_beaten": 3
+        },
+        "memory_challenge_b": {
+            "max_level": 5,
+            "max_level_beaten": 1
+        },
+        "memory_challenge_c": {
+            "max_level": 5,
+            "max_level_beaten": 1
+        }
+    }
+}
\ No newline at end of file
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index 1d332817..7a9de8ab 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -2,6 +2,9 @@ import pytest
 
 from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
@@ -11,11 +14,13 @@ from autogpt.agent import Agent
 
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
+@challenge
 def test_information_retrieval_challenge_a(
     get_company_revenue_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
     patched_api_requestor: None,
     config: Config,
+    level_to_run: int,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs and checking the output file content.
diff --git a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
index 10bcfb1c..5fd280ac 100644
--- a/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
+++ b/tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py
@@ -4,24 +4,33 @@ import yaml
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
 from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
-CYCLE_COUNT = 6
+CYCLE_COUNT = 3
 
 
-@pytest.mark.skip("This challenge hasn't been beaten yet.")
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
+@challenge
 def test_kubernetes_template_challenge_a(
-    kubernetes_agent: Agent, monkeypatch: pytest.MonkeyPatch, config: Config
+    kubernetes_agent: Agent,
+    monkeypatch: pytest.MonkeyPatch,
+    config: Config,
+    level_to_run: int,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs
     and checking the output file content.
 
-    :param get_company_revenue_agent: The agent to test.
-    :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
+    Args:
+        kubernetes_agent (Agent)
+        monkeypatch (pytest.MonkeyPatch)
+        config (Config)
+        level_to_run (int)
     """
     run_interaction_loop(monkeypatch, kubernetes_agent, CYCLE_COUNT)
 
diff --git a/tests/integration/challenges/memory/test_memory_challenge_a.py b/tests/integration/challenges/memory/test_memory_challenge_a.py
index 063824c6..8919bf58 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_a.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_a.py
@@ -3,37 +3,38 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
 from autogpt.config import Config
-from tests.integration.challenges.utils import get_level_to_run, run_interaction_loop
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
+from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
-LEVEL_CURRENTLY_BEATEN = 3  # real level beaten 30 and maybe more, but we can't record it, the cassette is too big
-MAX_LEVEL = 3
-
 
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
+@challenge
 def test_memory_challenge_a(
     memory_management_agent: Agent,
-    user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
+    level_to_run: int,
 ) -> None:
     """
     The agent reads a file containing a task_id. Then, it reads a series of other files.
     After reading 'n' files, the agent must write the task_id into a new file.
-
     Args:
         memory_management_agent (Agent)
-        user_selected_level (int)
+        patched_api_requestor (MockerFixture)
+        monkeypatch (pytest.MonkeyPatch)
+        config (Config)
+        level_to_run (int)
     """
 
-    num_files = get_level_to_run(user_selected_level, LEVEL_CURRENTLY_BEATEN, MAX_LEVEL)
-
     task_id = "2314"
-    create_instructions_files(memory_management_agent, num_files, task_id, config)
+    create_instructions_files(memory_management_agent, level_to_run, task_id, config)
 
-    run_interaction_loop(monkeypatch, memory_management_agent, num_files + 2)
+    run_interaction_loop(monkeypatch, memory_management_agent, level_to_run + 2)
 
     file_path = str(memory_management_agent.workspace.get_path("output.txt"))
     content = read_file(file_path, config)
diff --git a/tests/integration/challenges/memory/test_memory_challenge_b.py b/tests/integration/challenges/memory/test_memory_challenge_b.py
index 7dc00000..5c28b330 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_b.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_b.py
@@ -3,26 +3,24 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
 from autogpt.config import Config
-from tests.integration.challenges.utils import (
-    generate_noise,
-    get_level_to_run,
-    run_interaction_loop,
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
 )
+from tests.integration.challenges.utils import generate_noise, run_interaction_loop
 from tests.utils import requires_api_key
 
-LEVEL_CURRENTLY_BEATEN = -1
-MAX_LEVEL = 5
 NOISE = 1000
 
 
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
+@challenge
 def test_memory_challenge_b(
     memory_management_agent: Agent,
-    user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
+    level_to_run: int,
 ) -> None:
     """
     The agent reads a series of files, each containing a task_id and noise. After reading 'n' files,
@@ -30,15 +28,14 @@ def test_memory_challenge_b(
 
     Args:
         memory_management_agent (Agent)
-        user_selected_level (int)
+        patched_api_requestor (MockerFixture)
+        monkeypatch (pytest.MonkeyPatch)
+        level_to_run (int)
     """
-    current_level = get_level_to_run(
-        user_selected_level, LEVEL_CURRENTLY_BEATEN, MAX_LEVEL
-    )
-    task_ids = [str(i * 1111) for i in range(1, current_level + 1)]
-    create_instructions_files(memory_management_agent, current_level, task_ids, config)
+    task_ids = [str(i * 1111) for i in range(1, level_to_run + 1)]
+    create_instructions_files(memory_management_agent, level_to_run, task_ids, config)
 
-    run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
+    run_interaction_loop(monkeypatch, memory_management_agent, level_to_run + 2)
 
     file_path = str(memory_management_agent.workspace.get_path("output.txt"))
     content = read_file(file_path, config)
diff --git a/tests/integration/challenges/memory/test_memory_challenge_c.py b/tests/integration/challenges/memory/test_memory_challenge_c.py
index e113fcdf..23c0217d 100644
--- a/tests/integration/challenges/memory/test_memory_challenge_c.py
+++ b/tests/integration/challenges/memory/test_memory_challenge_c.py
@@ -3,26 +3,25 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
 from autogpt.config import Config
-from tests.integration.challenges.utils import (
-    generate_noise,
-    get_level_to_run,
-    run_interaction_loop,
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
 )
+from tests.integration.challenges.utils import generate_noise, run_interaction_loop
 from tests.utils import requires_api_key
 
-LEVEL_CURRENTLY_BEATEN = -1
-MAX_LEVEL = 5
 NOISE = 1000
 
 
 # @pytest.mark.vcr
+@pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
+@challenge
 def test_memory_challenge_c(
     memory_management_agent: Agent,
-    user_selected_level: int,
     patched_api_requestor: None,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
+    level_to_run: int,
 ) -> None:
     """
     Instead of reading task Ids from files as with the previous challenges, the agent now must remember
@@ -31,11 +30,11 @@ def test_memory_challenge_c(
 
     Args:
         memory_management_agent (Agent)
-        user_selected_level (int)
+        patched_api_requestor (MockerFixture)
+        monkeypatch (pytest.MonkeyPatch)
+        config (Config)
+        level_to_run (int)
     """
-    current_level = get_level_to_run(
-        user_selected_level, LEVEL_CURRENTLY_BEATEN, MAX_LEVEL
-    )
     silly_phrases = [
         "The purple elephant danced on a rainbow while eating a taco.",
         "The sneaky toaster stole my socks and ran away to Hawaii.",
@@ -49,15 +48,15 @@ def test_memory_challenge_c(
         "The ninja unicorn disguised itself as a potted plant and infiltrated the office.",
     ]
 
-    level_silly_phrases = silly_phrases[:current_level]
+    level_silly_phrases = silly_phrases[:level_to_run]
     create_instructions_files(
-        memory_management_agent, current_level, level_silly_phrases, config=config
+        memory_management_agent, level_to_run, level_silly_phrases, config=config
     )
 
-    run_interaction_loop(monkeypatch, memory_management_agent, current_level + 2)
+    run_interaction_loop(monkeypatch, memory_management_agent, level_to_run + 2)
 
     file_path = str(memory_management_agent.workspace.get_path("output.txt"))
-    content = read_file(file_path)
+    content = read_file(file_path, config)
     for phrase in level_silly_phrases:
         assert phrase in content, f"Expected the file to contain {phrase}"
 
diff --git a/tests/integration/challenges/utils.py b/tests/integration/challenges/utils.py
index 94dd5a0c..3ffd136b 100644
--- a/tests/integration/challenges/utils.py
+++ b/tests/integration/challenges/utils.py
@@ -1,45 +1,14 @@
 import contextlib
 import random
-from functools import wraps
-from typing import Any, Callable, Dict, Generator, Tuple
+from typing import Generator
 
 import pytest
 
 from autogpt.agent import Agent
 
 
-def get_level_to_run(
-    user_selected_level: int,
-    level_currently_beaten: int,
-    max_level: int,
-) -> int:
-    """
-    Determines the appropriate level to run for a challenge, based on user-selected level, level currently beaten, and maximum level.
-
-    Args:
-        user_selected_level (int | None): The level selected by the user. If not provided, the level currently beaten is used.
-        level_currently_beaten (int | None): The highest level beaten so far. If not provided, the test will be skipped.
-        max_level (int): The maximum level allowed for the challenge.
-
-    Returns:
-        int: The level to run for the challenge.
-
-    Raises:
-        ValueError: If the user-selected level is greater than the maximum level allowed.
-    """
-    if user_selected_level is None:
-        if level_currently_beaten == -1:
-            pytest.skip(
-                "No one has beaten any levels so we cannot run the test in our pipeline"
-            )
-        # by default we run the level currently beaten.
-        return level_currently_beaten
-    if user_selected_level > max_level:
-        raise ValueError(f"This challenge was not designed to go beyond {max_level}")
-    return user_selected_level
-
-
 def generate_noise(noise_size: int) -> str:
+    random.seed(42)
     return "".join(
         random.choices(
             "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789",
diff --git a/tests/integration/challenges/utils/build_current_score.py b/tests/integration/challenges/utils/build_current_score.py
new file mode 100644
index 00000000..743b1328
--- /dev/null
+++ b/tests/integration/challenges/utils/build_current_score.py
@@ -0,0 +1,47 @@
+import glob
+import json
+import os
+from typing import Any, Dict
+
+
+def deep_merge(source: Dict[Any, Any], dest: Dict[Any, Any]) -> Dict[Any, Any]:
+    for key, value in source.items():
+        if isinstance(value, Dict):
+            dest[key] = deep_merge(value, dest.get(key, {}))
+        else:
+            dest[key] = value
+    return dest
+
+
+import collections
+
+
+def recursive_sort_dict(data: dict) -> dict:
+    for key, value in data.items():
+        if isinstance(value, dict):
+            data[key] = recursive_sort_dict(value)
+    return collections.OrderedDict(sorted(data.items()))
+
+    # setup
+
+
+cwd = os.getcwd()  # get current working directory
+new_score_filename_pattern = os.path.join(
+    cwd, "tests/integration/challenges/new_score_*.json"
+)
+current_score_filename = os.path.join(
+    cwd, "tests/integration/challenges/current_score.json"
+)
+
+merged_data: Dict[str, Any] = {}
+for filename in glob.glob(new_score_filename_pattern):
+    with open(filename, "r") as f_new:
+        data = json.load(f_new)
+    merged_data = deep_merge(
+        data, merged_data
+    )  # deep merge the new data with the merged data
+    os.remove(filename)  # remove the individual file
+sorted_data = recursive_sort_dict(merged_data)
+
+with open(current_score_filename, "w") as f_current:
+    json.dump(sorted_data, f_current, indent=4)

From 1127d9c5f57c7a7e66900e7bbb95e943842097e9 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 29 May 2023 08:25:45 -0700
Subject: [PATCH 079/112] Master doesn't beat memory challenge b level 1 in a
 consistent manner (#4460)

---
 tests/integration/challenges/current_score.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index a734ff5d..741ec7a5 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -28,11 +28,11 @@
         },
         "memory_challenge_b": {
             "max_level": 5,
-            "max_level_beaten": 1
+            "max_level_beaten": null
         },
         "memory_challenge_c": {
             "max_level": 5,
             "max_level_beaten": 1
         }
     }
-}
\ No newline at end of file
+}

From b5d78a48a7cfa221b355416f6ef8a0bdcd4b928f Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Mon, 29 May 2023 15:29:31 +0000
Subject: [PATCH 080/112] Update submodule reference

---
 tests/Auto-GPT-test-cassettes | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
index 909c30a0..5b051c64 160000
--- a/tests/Auto-GPT-test-cassettes
+++ b/tests/Auto-GPT-test-cassettes
@@ -1 +1 @@
-Subproject commit 909c30a0ab8694db2ef63dacc0b3d6a4a0cd74f2
+Subproject commit 5b051c64b65ba102be782781e4c1619086619375

From 1ddf2324ff514e39df82724350fec05c6ec4e22a Mon Sep 17 00:00:00 2001
From: Kinance <kinance@gmail.com>
Date: Tue, 30 May 2023 01:24:38 +0900
Subject: [PATCH 081/112] Improve the steps for running docker compose in the
 setup documentation (#4462)

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 docs/setup.md | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/docs/setup.md b/docs/setup.md
index 4bdf6a16..c4755a8d 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -34,13 +34,13 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
 ### Set up with Docker
 
 1. Make sure you have Docker installed, see [requirements](#requirements)
-2. Pull the latest image from [Docker Hub]
+2. Create a project directory for Auto-GPT
 
         :::shell
-        docker pull significantgravitas/auto-gpt
+        mkdir Auto-GPT
+        cd Auto-GPT
 
-3. Create a folder for Auto-GPT
-4. In the folder, create a file called `docker-compose.yml` with the following contents:
+3. In the project directory, create a file called `docker-compose.yml` with the following contents:
 
         :::yaml
         version: "3.9"
@@ -71,8 +71,13 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
           redis:
             image: "redis/redis-stack-server:latest"
 
-5. Create the necessary [configuration](#configuration) files. If needed, you can find
+4. Create the necessary [configuration](#configuration) files. If needed, you can find
     templates in the [repository].
+5. Pull the latest image from [Docker Hub]
+
+        :::shell
+        docker pull significantgravitas/auto-gpt
+
 6. Continue to [Run with Docker](#run-with-docker)
 
 !!! note "Docker only supports headless browsing"

From 1446ffddb0289f8944ac7a820fa084e8f2f89598 Mon Sep 17 00:00:00 2001
From: "Luke K (pr-0f3t)" <2609441+lc0rp@users.noreply.github.com>
Date: Mon, 29 May 2023 10:10:51 -0700
Subject: [PATCH 082/112] Fix #942: Respect --gpt4only, --gpt3only cli args
 (#3144)

Co-authored-by: Luke K <KayLuke@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
---
 autogpt/agent/agent.py  |  4 +-
 autogpt/configurator.py | 24 +++++++++---
 autogpt/llm/chat.py     | 16 +++++---
 tests/test_config.py    | 83 +++++++++++++++++++++++++++++++++++------
 4 files changed, 104 insertions(+), 23 deletions(-)

diff --git a/autogpt/agent/agent.py b/autogpt/agent/agent.py
index a1673ad9..3dc4d390 100644
--- a/autogpt/agent/agent.py
+++ b/autogpt/agent/agent.py
@@ -128,11 +128,13 @@ class Agent:
             # Send message to AI, get response
             with Spinner("Thinking... ", plain_output=cfg.plain_output):
                 assistant_reply = chat_with_ai(
+                    cfg,
                     self,
                     self.system_prompt,
                     self.triggering_prompt,
                     cfg.fast_token_limit,
-                )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
+                    cfg.fast_llm_model,
+                )
 
             assistant_reply_json = fix_json_using_multiple_techniques(assistant_reply)
             for plugin in cfg.plugins:
diff --git a/autogpt/configurator.py b/autogpt/configurator.py
index 6b855fe3..324f3084 100644
--- a/autogpt/configurator.py
+++ b/autogpt/configurator.py
@@ -14,6 +14,9 @@ from autogpt.memory.vector import get_supported_memory_backends
 if TYPE_CHECKING:
     from autogpt.config import Config
 
+GPT_4_MODEL = "gpt-4"
+GPT_3_MODEL = "gpt-3.5-turbo"
+
 
 def create_config(
     config: Config,
@@ -51,8 +54,6 @@ def create_config(
     config.set_debug_mode(False)
     config.set_continuous_mode(False)
     config.set_speak_mode(False)
-    config.set_fast_llm_model(check_model(config.fast_llm_model, "fast_llm_model"))
-    config.set_smart_llm_model(check_model(config.smart_llm_model, "smart_llm_model"))
 
     if debug:
         logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED")
@@ -83,13 +84,26 @@ def create_config(
         logger.typewriter_log("Speak Mode: ", Fore.GREEN, "ENABLED")
         config.set_speak_mode(True)
 
+    # Set the default LLM models
     if gpt3only:
         logger.typewriter_log("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED")
-        config.set_smart_llm_model(config.fast_llm_model)
+        # --gpt3only should always use gpt-3.5-turbo, despite user's FAST_LLM_MODEL config
+        config.set_fast_llm_model(GPT_3_MODEL)
+        config.set_smart_llm_model(GPT_3_MODEL)
 
-    if gpt4only:
+    elif (
+        gpt4only
+        and check_model(GPT_4_MODEL, model_type="smart_llm_model") == GPT_4_MODEL
+    ):
         logger.typewriter_log("GPT4 Only Mode: ", Fore.GREEN, "ENABLED")
-        config.set_fast_llm_model(config.smart_llm_model)
+        # --gpt4only should always use gpt-4, despite user's SMART_LLM_MODEL config
+        config.set_fast_llm_model(GPT_4_MODEL)
+        config.set_smart_llm_model(GPT_4_MODEL)
+    else:
+        config.set_fast_llm_model(check_model(config.fast_llm_model, "fast_llm_model"))
+        config.set_smart_llm_model(
+            check_model(config.smart_llm_model, "smart_llm_model")
+        )
 
     if memory_type:
         supported_memory = get_supported_memory_backends()
diff --git a/autogpt/llm/chat.py b/autogpt/llm/chat.py
index 292990f5..7cb59825 100644
--- a/autogpt/llm/chat.py
+++ b/autogpt/llm/chat.py
@@ -13,29 +13,34 @@ from autogpt.llm.utils import count_message_tokens, create_chat_completion
 from autogpt.log_cycle.log_cycle import CURRENT_CONTEXT_FILE_NAME
 from autogpt.logs import logger
 
-cfg = Config()
-
 
 # TODO: Change debug from hardcode to argument
 def chat_with_ai(
+    config: Config,
     agent: Agent,
     system_prompt: str,
     user_input: str,
     token_limit: int,
+    model: str | None = None,
 ):
     """
     Interact with the OpenAI API, sending the prompt, user input,
         message history, and permanent memory.
 
     Args:
+        config (Config): The config to use.
+        agent (Agent): The agent to use.
         system_prompt (str): The prompt explaining the rules to the AI.
         user_input (str): The input from the user.
         token_limit (int): The maximum number of tokens allowed in the API call.
+        model (str, optional): The model to use. If None, the config.fast_llm_model will be used. Defaults to None.
 
     Returns:
     str: The AI's response.
     """
-    model = cfg.fast_llm_model  # TODO: Change model from hardcode to argument
+    if model is None:
+        model = config.fast_llm_model
+
     # Reserve 1000 tokens for the response
     logger.debug(f"Token limit: {token_limit}")
     send_token_limit = token_limit - 1000
@@ -140,8 +145,8 @@ def chat_with_ai(
     # Append user input, the length of this is accounted for above
     message_sequence.append(user_input_msg)
 
-    plugin_count = len(cfg.plugins)
-    for i, plugin in enumerate(cfg.plugins):
+    plugin_count = len(config.plugins)
+    for i, plugin in enumerate(config.plugins):
         if not plugin.can_handle_on_planning():
             continue
         plugin_response = plugin.on_planning(
@@ -157,7 +162,6 @@ def chat_with_ai(
             logger.debug(f"Plugins remaining at stop: {plugin_count - i}")
             break
         message_sequence.add("system", plugin_response)
-
     # Calculate remaining tokens
     tokens_remaining = token_limit - current_tokens_used
     # assert tokens_remaining >= 0, "Tokens remaining is negative.
diff --git a/tests/test_config.py b/tests/test_config.py
index 81d151cd..eb6946c9 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -2,14 +2,17 @@
 Test cases for the Config class, which handles the configuration settings
 for the AI and ensures it behaves as a singleton.
 """
+from unittest import mock
 from unittest.mock import patch
 
 import pytest
 
-from autogpt.configurator import create_config
+from autogpt.config.config import Config
+from autogpt.configurator import GPT_3_MODEL, GPT_4_MODEL, create_config
+from autogpt.workspace.workspace import Workspace
 
 
-def test_initial_values(config):
+def test_initial_values(config: Config):
     """
     Test if the initial values of the Config class attributes are set correctly.
     """
@@ -22,7 +25,7 @@ def test_initial_values(config):
     assert config.smart_token_limit == 8000
 
 
-def test_set_continuous_mode(config):
+def test_set_continuous_mode(config: Config):
     """
     Test if the set_continuous_mode() method updates the continuous_mode attribute.
     """
@@ -36,7 +39,7 @@ def test_set_continuous_mode(config):
     config.set_continuous_mode(continuous_mode)
 
 
-def test_set_speak_mode(config):
+def test_set_speak_mode(config: Config):
     """
     Test if the set_speak_mode() method updates the speak_mode attribute.
     """
@@ -50,7 +53,7 @@ def test_set_speak_mode(config):
     config.set_speak_mode(speak_mode)
 
 
-def test_set_fast_llm_model(config):
+def test_set_fast_llm_model(config: Config):
     """
     Test if the set_fast_llm_model() method updates the fast_llm_model attribute.
     """
@@ -64,7 +67,7 @@ def test_set_fast_llm_model(config):
     config.set_fast_llm_model(fast_llm_model)
 
 
-def test_set_smart_llm_model(config):
+def test_set_smart_llm_model(config: Config):
     """
     Test if the set_smart_llm_model() method updates the smart_llm_model attribute.
     """
@@ -78,7 +81,7 @@ def test_set_smart_llm_model(config):
     config.set_smart_llm_model(smart_llm_model)
 
 
-def test_set_fast_token_limit(config):
+def test_set_fast_token_limit(config: Config):
     """
     Test if the set_fast_token_limit() method updates the fast_token_limit attribute.
     """
@@ -92,7 +95,7 @@ def test_set_fast_token_limit(config):
     config.set_fast_token_limit(fast_token_limit)
 
 
-def test_set_smart_token_limit(config):
+def test_set_smart_token_limit(config: Config):
     """
     Test if the set_smart_token_limit() method updates the smart_token_limit attribute.
     """
@@ -106,7 +109,7 @@ def test_set_smart_token_limit(config):
     config.set_smart_token_limit(smart_token_limit)
 
 
-def test_set_debug_mode(config):
+def test_set_debug_mode(config: Config):
     """
     Test if the set_debug_mode() method updates the debug_mode attribute.
     """
@@ -121,7 +124,7 @@ def test_set_debug_mode(config):
 
 
 @patch("openai.Model.list")
-def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config):
+def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config: Config):
     """
     Test if models update to gpt-3.5-turbo if both are set to gpt-4.
     """
@@ -158,7 +161,7 @@ def test_smart_and_fast_llm_models_set_to_gpt4(mock_list_models, config):
     config.set_smart_llm_model(smart_llm_model)
 
 
-def test_missing_azure_config(config, workspace):
+def test_missing_azure_config(config: Config, workspace: Workspace):
     config_file = workspace.get_path("azure_config.yaml")
     with pytest.raises(FileNotFoundError):
         config.load_azure_config(str(config_file))
@@ -170,3 +173,61 @@ def test_missing_azure_config(config, workspace):
     assert config.openai_api_base == ""
     assert config.openai_api_version == "2023-03-15-preview"
     assert config.azure_model_to_deployment_id_map == {}
+
+
+def test_create_config_gpt4only(config: Config) -> None:
+    fast_llm_model = config.fast_llm_model
+    smart_llm_model = config.smart_llm_model
+    with mock.patch("autogpt.llm.api_manager.ApiManager.get_models") as mock_get_models:
+        mock_get_models.return_value = [{"id": GPT_4_MODEL}]
+        create_config(
+            config=config,
+            continuous=False,
+            continuous_limit=None,
+            ai_settings_file=None,
+            prompt_settings_file=None,
+            skip_reprompt=False,
+            speak=False,
+            debug=False,
+            gpt3only=False,
+            gpt4only=True,
+            memory_type=None,
+            browser_name=None,
+            allow_downloads=False,
+            skip_news=False,
+        )
+        assert config.fast_llm_model == GPT_4_MODEL
+        assert config.smart_llm_model == GPT_4_MODEL
+
+    # Reset config
+    config.set_fast_llm_model(fast_llm_model)
+    config.set_smart_llm_model(smart_llm_model)
+
+
+def test_create_config_gpt3only(config: Config) -> None:
+    fast_llm_model = config.fast_llm_model
+    smart_llm_model = config.smart_llm_model
+    with mock.patch("autogpt.llm.api_manager.ApiManager.get_models") as mock_get_models:
+        mock_get_models.return_value = [{"id": GPT_3_MODEL}]
+        create_config(
+            config=config,
+            continuous=False,
+            continuous_limit=None,
+            ai_settings_file=None,
+            prompt_settings_file=None,
+            skip_reprompt=False,
+            speak=False,
+            debug=False,
+            gpt3only=True,
+            gpt4only=False,
+            memory_type=None,
+            browser_name=None,
+            allow_downloads=False,
+            skip_news=False,
+        )
+        assert config.fast_llm_model == GPT_3_MODEL
+        assert config.smart_llm_model == GPT_3_MODEL
+
+    # Reset config
+    config.set_fast_llm_model(fast_llm_model)
+    config.set_smart_llm_model(smart_llm_model)

From d34b8a2b61fb5d1f1b2c14856b8a3af895b8aca2 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 29 May 2023 19:01:46 -0700
Subject: [PATCH 083/112] Replace 'prompt change' with 'behavior change'
 (#4473)

* Replace 'prompt change' with 'behavior change'

* replaced behavior by behaviour

* fixed typo on behaviour
---
 .github/workflows/ci.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 368930a1..8bb85aa6 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -182,7 +182,7 @@ jobs:
             echo "DIFF_EXISTS=false" >> $GITHUB_ENV
           fi
 
-      - name: Apply or remove prompt change label and comment
+      - name: Apply or remove behaviour change label and comment
         if: ${{ github.event_name == 'pull_request_target' }}
         run: |
           PR_NUMBER=${{ github.event.pull_request.number }}
@@ -195,14 +195,14 @@ jobs:
             -H "Authorization: Bearer $TOKEN" \
             -H "Accept: application/vnd.github.v3+json" \
             https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels \
-            -d '{"labels":["prompt change"]}'
+            -d '{"labels":["behaviour change"]}'
 
             echo $TOKEN | gh auth login --with-token
-            gh api repos/$REPO/issues/$PR_NUMBER/comments -X POST -F body="You changed AutoGPT's prompt. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+            gh api repos/$REPO/issues/$PR_NUMBER/comments -X POST -F body="You changed AutoGPT's behaviour. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
           else
             echo "Removing label..."
             curl -X DELETE \
             -H "Authorization: Bearer $TOKEN" \
             -H "Accept: application/vnd.github.v3+json" \
-            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels/prompt%20change
+            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels/behaviour%20change
           fi

From ba8046753e419a627fcf49a06d9173dccc8a405c Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Mon, 29 May 2023 19:30:41 -0700
Subject: [PATCH 084/112] Update current score when PR merged (#4464)

---
 .github/workflows/ci.yml                         | 16 +++++++++++++---
 .../challenges/challenge_decorator/challenge.py  |  2 ++
 .../challenge_decorator/challenge_decorator.py   |  2 +-
 .../challenge_decorator/challenge_utils.py       |  8 ++++++--
 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 8bb85aa6..2e143e9d 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -119,6 +119,7 @@ jobs:
       - name: Run pytest tests with coverage
         run: |
           pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
+          python tests/integration/challenges/utils/build_current_score.py
         env:
           CI: true
           PROXY: ${{ secrets.PROXY }}
@@ -131,11 +132,20 @@ jobs:
       - name: Update cassette submodule to push target if push event
         if: ${{ github.event_name == 'push' }}
         run: |
-          cd tests/Auto-GPT-test-cassettes
           current_branch=$(echo ${{ github.ref }} | sed -e "s/refs\/heads\///g")
-          git fetch origin $current_branch
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
+          git add tests/integration/challenges/current_score.json
+
+          if ! git diff-index --quiet HEAD; then
+              git commit -m "Update current score"
+              git push origin HEAD:refs/heads/$current_branch
+          else
+              echo "The current score didn't change."
+          fi
+          
+          cd tests/Auto-GPT-test-cassettes
+          git fetch origin $current_branch
           git add .
 
           # Check if there are any changes
@@ -150,7 +160,7 @@ jobs:
               git commit -m "Update submodule reference"
               git push origin HEAD:refs/heads/$current_branch
           else
-              echo "No changes to commit"
+              echo "No cassettes changes to commit"
               exit 0
           fi
 
diff --git a/tests/integration/challenges/challenge_decorator/challenge.py b/tests/integration/challenges/challenge_decorator/challenge.py
index baf821a1..fd3b60cb 100644
--- a/tests/integration/challenges/challenge_decorator/challenge.py
+++ b/tests/integration/challenges/challenge_decorator/challenge.py
@@ -9,6 +9,7 @@ class Challenge:
         name: str,
         category: str,
         max_level: int,
+        is_new_challenge: bool,
         max_level_beaten: Optional[int],
         level_to_run: Optional[int] = None,
     ) -> None:
@@ -19,3 +20,4 @@ class Challenge:
         self.succeeded = False
         self.skipped = False
         self.level_to_run = level_to_run
+        self.is_new_challenge = is_new_challenge
diff --git a/tests/integration/challenges/challenge_decorator/challenge_decorator.py b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
index 580dc089..1ec43aec 100644
--- a/tests/integration/challenges/challenge_decorator/challenge_decorator.py
+++ b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
@@ -48,7 +48,7 @@ def challenge(func: Callable[..., Any]) -> Callable[..., None]:
                 pytest.skip("This test has not been unlocked yet.")
 
             if not challenge.succeeded:
-                if Challenge.BEAT_CHALLENGES:
+                if Challenge.BEAT_CHALLENGES or challenge.is_new_challenge:
                     # xfail
                     pytest.xfail("Challenge failed")
                 raise AssertionError("Challenge failed")
diff --git a/tests/integration/challenges/challenge_decorator/challenge_utils.py b/tests/integration/challenges/challenge_decorator/challenge_utils.py
index b94f7164..7db7648f 100644
--- a/tests/integration/challenges/challenge_decorator/challenge_utils.py
+++ b/tests/integration/challenges/challenge_decorator/challenge_utils.py
@@ -13,13 +13,13 @@ def create_challenge(
     level_to_run: Optional[int] = None,
 ) -> Challenge:
     challenge_category, challenge_name = get_challenge_identifiers(func)
-
+    is_new_challenge = challenge_name not in current_score.get(challenge_category, {})
     max_level = get_max_level(current_score, challenge_category, challenge_name)
     max_level_beaten = get_max_level_beaten(
         current_score, challenge_category, challenge_name
     )
     level_to_run = get_level_to_run(
-        is_beat_challenges, level_to_run, max_level, max_level_beaten
+        is_beat_challenges, level_to_run, max_level, max_level_beaten, is_new_challenge
     )
 
     return Challenge(
@@ -28,6 +28,7 @@ def create_challenge(
         max_level=max_level,
         max_level_beaten=max_level_beaten,
         level_to_run=level_to_run,
+        is_new_challenge=is_new_challenge,
     )
 
 
@@ -36,7 +37,10 @@ def get_level_to_run(
     level_to_run: Optional[int],
     max_level: int,
     max_level_beaten: Optional[int],
+    is_new_challenge: bool,
 ) -> Optional[int]:
+    if is_new_challenge:
+        return 1
     if level_to_run is not None:
         if level_to_run > max_level:
             raise ValueError(

From 56650b60f48f5338f46f4b3cb8e28a9be6a004ab Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 02:33:34 +0000
Subject: [PATCH 085/112] Update current score

---
 tests/integration/challenges/current_score.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index 741ec7a5..8cb4f069 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -35,4 +35,4 @@
             "max_level_beaten": 1
         }
     }
-}
+}
\ No newline at end of file

From 22429c6e98d71b67306f3cb81c2dee4577708e6c Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 30 May 2023 06:00:37 -0700
Subject: [PATCH 086/112] add vcr to dalle (#4474)

---
 tests/{ => integration}/test_image_gen.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)
 rename tests/{ => integration}/test_image_gen.py (97%)

diff --git a/tests/test_image_gen.py b/tests/integration/test_image_gen.py
similarity index 97%
rename from tests/test_image_gen.py
rename to tests/integration/test_image_gen.py
index 5c04921b..0156c9e5 100644
--- a/tests/test_image_gen.py
+++ b/tests/integration/test_image_gen.py
@@ -16,11 +16,9 @@ def image_size(request):
     return request.param
 
 
-@pytest.mark.xfail(
-    reason="The image is too big to be put in a cassette for a CI pipeline. We're looking into a solution."
-)
 @requires_api_key("OPENAI_API_KEY")
-def test_dalle(config, workspace, image_size):
+@pytest.mark.vcr
+def test_dalle(config, workspace, image_size, patched_api_requestor):
     """Test DALL-E image generation."""
     generate_and_validate(
         config,

From d3a1770dc01a2d419e071703bc18b4e91342f9ba Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 13:03:41 +0000
Subject: [PATCH 087/112] Update submodule reference

---
 tests/Auto-GPT-test-cassettes | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
index 5b051c64..35f7a699 160000
--- a/tests/Auto-GPT-test-cassettes
+++ b/tests/Auto-GPT-test-cassettes
@@ -1 +1 @@
-Subproject commit 5b051c64b65ba102be782781e4c1619086619375
+Subproject commit 35f7a6997c1e8a48952d13a530ea8e1e8988e76e

From b56352e2183dc4eb10b8f54f0d789abe2183e2de Mon Sep 17 00:00:00 2001
From: Erik Peterson <e@eriklp.com>
Date: Tue, 30 May 2023 07:31:45 -0700
Subject: [PATCH 088/112] Fix #4461: Don't record error requests in challenges
 (#4469)

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
---
 tests/integration/challenges/conftest.py | 22 ++++++++++++++++++++++
 tests/integration/conftest.py            | 24 +++++++++++++-----------
 2 files changed, 35 insertions(+), 11 deletions(-)

diff --git a/tests/integration/challenges/conftest.py b/tests/integration/challenges/conftest.py
index 8a1b5c40..5514a129 100644
--- a/tests/integration/challenges/conftest.py
+++ b/tests/integration/challenges/conftest.py
@@ -1,9 +1,31 @@
+from typing import Any, Dict, Optional
+
 import pytest
 from _pytest.config import Config
 from _pytest.config.argparsing import Parser
 from _pytest.fixtures import FixtureRequest
 
 from tests.integration.challenges.challenge_decorator.challenge import Challenge
+from tests.integration.conftest import BASE_VCR_CONFIG
+from tests.vcr.vcr_filter import before_record_response
+
+
+def before_record_response_filter_errors(
+    response: Dict[str, Any]
+) -> Optional[Dict[str, Any]]:
+    """In challenges we don't want to record errors (See issue #4461)"""
+    if response["status"]["code"] >= 400:
+        return None
+
+    return before_record_response(response)
+
+
+@pytest.fixture(scope="module")
+def vcr_config() -> Dict[str, Any]:
+    # this fixture is called by the pytest-recording vcr decorator.
+    return BASE_VCR_CONFIG | {
+        "before_record_response": before_record_response_filter_errors,
+    }
 
 
 def pytest_addoption(parser: Parser) -> None:
diff --git a/tests/integration/conftest.py b/tests/integration/conftest.py
index cb49bc13..686f50be 100644
--- a/tests/integration/conftest.py
+++ b/tests/integration/conftest.py
@@ -7,21 +7,23 @@ from pytest_mock import MockerFixture
 from tests.conftest import PROXY
 from tests.vcr.vcr_filter import before_record_request, before_record_response
 
+BASE_VCR_CONFIG = {
+    "record_mode": "new_episodes",
+    "before_record_request": before_record_request,
+    "before_record_response": before_record_response,
+    "filter_headers": [
+        "Authorization",
+        "X-OpenAI-Client-User-Agent",
+        "User-Agent",
+    ],
+    "match_on": ["method", "body"],
+}
+
 
 @pytest.fixture(scope="session")
 def vcr_config():
     # this fixture is called by the pytest-recording vcr decorator.
-    return {
-        "record_mode": "new_episodes",
-        "before_record_request": before_record_request,
-        "before_record_response": before_record_response,
-        "filter_headers": [
-            "Authorization",
-            "X-OpenAI-Client-User-Agent",
-            "User-Agent",
-        ],
-        "match_on": ["method", "body"],
-    }
+    return BASE_VCR_CONFIG
 
 
 def patch_api_base(requestor):

From 6806b66509cf421134cb2e1b0b807c9c9ada6d8a Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 30 May 2023 12:10:49 -0700
Subject: [PATCH 089/112] Information retrieval challenge (#4456)

* test: add information retrieval challenge b

* test: get information retrieval challenge be working.

* chore: clean up comments and imports.

* chore: fix incorrect import

* chore: clean up imports.

* fix: add web_selenium cmd. resolve missing loop cycle

* chore: remove commented code and unused imports.

* fix (4261): use 2 cycles instead of 3

* chore: fix mypy formatting

* chore: try 2 for mypy formatting

* chore: resolve flake8 issues

* chore: add docs

* chore: resolve linting flake8

* chore: correct formatting to black

* Update challenge_b.md

* refactored challenge

---------

Co-authored-by: PortlandKyGuy <kyleaaron1@gmail.com>
---
 .../information_retrieval/challenge_b.md      | 22 ++++++++
 mkdocs.yml                                    |  1 +
 tests/integration/agent_factory.py            | 33 ++++++++++++
 .../integration/challenges/current_score.json |  6 ++-
 .../test_information_retrieval_challenge_b.py | 51 +++++++++++++++++++
 5 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 docs/challenges/information_retrieval/challenge_b.md
 create mode 100644 tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py

diff --git a/docs/challenges/information_retrieval/challenge_b.md b/docs/challenges/information_retrieval/challenge_b.md
new file mode 100644
index 00000000..bf77a984
--- /dev/null
+++ b/docs/challenges/information_retrieval/challenge_b.md
@@ -0,0 +1,22 @@
+# Information Retrieval Challenge B
+
+**Status**: Beaten
+
+**Command to try**:
+
+```
+pytest -s tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py
+```
+
+## Description
+
+The agent's goal is to find the names, affiliated university, and discovery of the individuals who won the nobel prize for physics in 2010.
+
+It should write the result in a file called 2010_nobel_prize_winners.txt.
+
+The agent should be able to beat this test consistently (this is the hardest part).
+
+## Objective
+
+The objective of this challenge is to test the agent's ability to retrieve multiple pieces of related information in a consistent way.
+The agent should not use google to perform the task, because it should already know the answer. This why the task fails after 2 cycles (1 cycle to retrieve information, 1 cycle to write the file)
diff --git a/mkdocs.yml b/mkdocs.yml
index 37732c56..48fa0cb5 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -28,6 +28,7 @@ nav:
       - Information retrieval:
         - Introduction: challenges/information_retrieval/introduction.md
         - Information Retrieval Challenge A: challenges/information_retrieval/challenge_a.md
+        - Information Retrieval Challenge B: challenges/information_retrieval/challenge_b.md
   - Submit a Challenge: challenges/submit.md
   - Beat a Challenge: challenges/beat.md
 
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 713afb79..15044e9f 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -202,3 +202,36 @@ def kubernetes_agent(memory_json_file, workspace: Workspace):
     )
 
     return agent
+
+
+@pytest.fixture
+def get_nobel_prize_agent(agent_test_config, memory_json_file, workspace: Workspace):
+    command_registry = CommandRegistry()
+    command_registry.import_commands("autogpt.commands.file_operations")
+    command_registry.import_commands("autogpt.app")
+    command_registry.import_commands("autogpt.commands.web_selenium")
+
+    ai_config = AIConfig(
+        ai_name="Get-PhysicsNobelPrize",
+        ai_role="An autonomous agent that specializes in physics history.",
+        ai_goals=[
+            "Write to file the winner's name(s), affiliated university, and discovery of the 2010 nobel prize in physics. Write your final answer to 2010_nobel_prize_winners.txt.",
+        ],
+    )
+    ai_config.command_registry = command_registry
+
+    system_prompt = ai_config.construct_full_prompt()
+    Config().set_continuous_mode(False)
+
+    agent = Agent(
+        ai_name="Get-PhysicsNobelPrize",
+        memory=memory_json_file,
+        command_registry=command_registry,
+        config=ai_config,
+        next_action_count=0,
+        system_prompt=system_prompt,
+        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
+        workspace_directory=workspace.root,
+    )
+
+    return agent
diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index 8cb4f069..b8dcf11e 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -13,6 +13,10 @@
         "information_retrieval_challenge_a": {
             "max_level": 1,
             "max_level_beaten": 1
+        },
+        "information_retrieval_challenge_b": {
+            "max_level": 1,
+            "max_level_beaten": 1
         }
     },
     "kubernetes": {
@@ -35,4 +39,4 @@
             "max_level_beaten": 1
         }
     }
-}
\ No newline at end of file
+}
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py
new file mode 100644
index 00000000..feac95a0
--- /dev/null
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py
@@ -0,0 +1,51 @@
+import contextlib
+
+import pytest
+
+from autogpt.agent import Agent
+from autogpt.commands.file_operations import read_file
+from autogpt.config import Config
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
+from tests.integration.challenges.utils import run_interaction_loop
+from tests.utils import requires_api_key
+
+CYCLE_COUNT = 3
+
+
+@pytest.mark.vcr
+@requires_api_key("OPENAI_API_KEY")
+@challenge
+def test_information_retrieval_challenge_b(
+    get_nobel_prize_agent: Agent,
+    monkeypatch: pytest.MonkeyPatch,
+    patched_api_requestor: None,
+    level_to_run: int,
+    config: Config,
+) -> None:
+    """
+    Test the challenge_b function in a given agent by mocking user inputs and checking the output file content.
+
+    :param get_nobel_prize_agent: The agent to test.
+    :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
+    :param patched_api_requestor: APIRequestor Patch to override the openai.api_requestor module for testing.
+    :param level_to_run: The level to run.
+    :param config: The config object.
+    """
+
+    with contextlib.suppress(SystemExit):
+        run_interaction_loop(monkeypatch, get_nobel_prize_agent, CYCLE_COUNT)
+
+    file_path = str(
+        get_nobel_prize_agent.workspace.get_path("2010_nobel_prize_winners.txt")
+    )
+    content = read_file(file_path, config)
+    assert "Andre Geim" in content, "Expected the file to contain Andre Geim"
+    assert (
+        "Konstantin Novoselov" in content
+    ), "Expected the file to contain Konstantin Novoselov"
+    assert (
+        "University of Manchester" in content
+    ), "Expected the file to contain University of Manchester"
+    assert "graphene" in content, "Expected the file to contain graphene"

From 4c25fabec99e785b9681274e3ffc2763f9707bad Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 19:15:30 +0000
Subject: [PATCH 090/112] Update current score

---
 tests/integration/challenges/current_score.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index b8dcf11e..822c23c2 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -39,4 +39,4 @@
             "max_level_beaten": 1
         }
     }
-}
+}
\ No newline at end of file

From 387f65c16c3f70e789d26041f60ce3994f52f5d3 Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 19:15:33 +0000
Subject: [PATCH 091/112] Update submodule reference

---
 tests/Auto-GPT-test-cassettes | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
index 35f7a699..d3cea237 160000
--- a/tests/Auto-GPT-test-cassettes
+++ b/tests/Auto-GPT-test-cassettes
@@ -1 +1 @@
-Subproject commit 35f7a6997c1e8a48952d13a530ea8e1e8988e76e
+Subproject commit d3cea237a1531c8d440dd4ab0531e72e1e437a25

From 86b6231f70b6e59cbea9d03e12897a7f0d686659 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 30 May 2023 12:23:49 -0700
Subject: [PATCH 092/112] ignore push if current score changed (#4482)

---
 .github/workflows/ci.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 2e143e9d..5219b982 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -5,6 +5,7 @@ on:
     branches: [ master, ci-test*]
     paths-ignore:
       - 'tests/Auto-GPT-test-cassettes'
+      - 'tests/integration/challenges/current_score.json'
   pull_request_target:
     branches: [ master, stable , ci-test*]
 

From 87776b28865b8dd292dc7a293c79437a232c10e6 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 30 May 2023 15:56:58 -0700
Subject: [PATCH 093/112] Make the information retrieval challenge a harder
 while still passing (#4468)

---
 autogpt/main.py                               | 39 ++++++------
 .../information_retrieval/challenge_a.md      |  9 ++-
 tests/integration/agent_factory.py            | 63 +++++++++++--------
 .../challenge_decorator.py                    |  9 ++-
 .../integration/challenges/current_score.json |  2 +-
 .../test_information_retrieval_challenge_a.py | 14 +++--
 6 files changed, 82 insertions(+), 54 deletions(-)

diff --git a/autogpt/main.py b/autogpt/main.py
index 39bbf8b5..efc70aae 100644
--- a/autogpt/main.py
+++ b/autogpt/main.py
@@ -22,6 +22,21 @@ from autogpt.utils import (
 from autogpt.workspace import Workspace
 from scripts.install_plugin_deps import install_plugin_dependencies
 
+COMMAND_CATEGORIES = [
+    "autogpt.commands.analyze_code",
+    "autogpt.commands.audio_text",
+    "autogpt.commands.execute_code",
+    "autogpt.commands.file_operations",
+    "autogpt.commands.git_operations",
+    "autogpt.commands.google_search",
+    "autogpt.commands.image_gen",
+    "autogpt.commands.improve_code",
+    "autogpt.commands.web_selenium",
+    "autogpt.commands.write_tests",
+    "autogpt.app",
+    "autogpt.commands.task_statuses",
+]
+
 
 def run_auto_gpt(
     continuous: bool,
@@ -128,30 +143,18 @@ def run_auto_gpt(
     # Create a CommandRegistry instance and scan default folder
     command_registry = CommandRegistry()
 
-    command_categories = [
-        "autogpt.commands.analyze_code",
-        "autogpt.commands.audio_text",
-        "autogpt.commands.execute_code",
-        "autogpt.commands.file_operations",
-        "autogpt.commands.git_operations",
-        "autogpt.commands.google_search",
-        "autogpt.commands.image_gen",
-        "autogpt.commands.improve_code",
-        "autogpt.commands.web_selenium",
-        "autogpt.commands.write_tests",
-        "autogpt.app",
-        "autogpt.commands.task_statuses",
-    ]
     logger.debug(
         f"The following command categories are disabled: {cfg.disabled_command_categories}"
     )
-    command_categories = [
-        x for x in command_categories if x not in cfg.disabled_command_categories
+    enabled_command_categories = [
+        x for x in COMMAND_CATEGORIES if x not in cfg.disabled_command_categories
     ]
 
-    logger.debug(f"The following command categories are enabled: {command_categories}")
+    logger.debug(
+        f"The following command categories are enabled: {enabled_command_categories}"
+    )
 
-    for command_category in command_categories:
+    for command_category in enabled_command_categories:
         command_registry.import_commands(command_category)
 
     ai_name = ""
diff --git a/docs/challenges/information_retrieval/challenge_a.md b/docs/challenges/information_retrieval/challenge_a.md
index 51762fc4..de21066e 100644
--- a/docs/challenges/information_retrieval/challenge_a.md
+++ b/docs/challenges/information_retrieval/challenge_a.md
@@ -1,16 +1,19 @@
 # Information Retrieval Challenge A
 
-**Status**: Current level to beat: level 1
+**Status**: Current level to beat: level 2
 
 **Command to try**:
 
 ```
-pytest -s tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+pytest -s tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py --level=2
 ```
 
 ## Description
 
-The agent's goal is to find the revenue of Tesla in 2022.
+The agent's goal is to find the revenue of Tesla:
+- level 1 asks the revenue of Tesla in 2022 and explicitly asks to search for 'tesla revenue 2022'
+- level 2 is identical but doesn't ask to search for 'tesla revenue 2022'
+- level 3 asks for tesla's revenue by year since its creation.
 
 It should write the result in a file called output.txt.
 
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 15044e9f..716545c2 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -3,6 +3,7 @@ import pytest
 from autogpt.agent import Agent
 from autogpt.commands.command import CommandRegistry
 from autogpt.config import AIConfig, Config
+from autogpt.main import COMMAND_CATEGORIES
 from autogpt.memory.vector import NoMemory, get_memory
 from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT
 from autogpt.workspace import Workspace
@@ -140,36 +141,46 @@ def memory_management_agent(agent_test_config, memory_json_file, workspace: Work
 
 
 @pytest.fixture
-def get_company_revenue_agent(
+def information_retrieval_agents(
     agent_test_config, memory_json_file, workspace: Workspace
 ):
+    agents = []
     command_registry = CommandRegistry()
-    command_registry.import_commands("autogpt.commands.file_operations")
-    command_registry.import_commands("autogpt.commands.google_search")
-    command_registry.import_commands("autogpt.app")
-    command_registry.import_commands("autogpt.commands.task_statuses")
+    enabled_command_categories = [
+        x
+        for x in COMMAND_CATEGORIES
+        if x not in agent_test_config.disabled_command_categories
+    ]
 
-    ai_config = AIConfig(
-        ai_name="Information Retrieval Agent",
-        ai_role="an autonomous agent that specializes in retrieving information.",
-        ai_goals=[
-            "Search for 'tesla revenue 2022' and write the revenue of Tesla in 2022 to a file called output.txt. You should write the number without commas and you should not use signs like B for billion and M for million.",
-        ],
-    )
-    ai_config.command_registry = command_registry
-    system_prompt = ai_config.construct_full_prompt()
-    Config().set_continuous_mode(False)
-    agent = Agent(
-        ai_name="Get-CompanyRevenue",
-        memory=memory_json_file,
-        command_registry=command_registry,
-        config=ai_config,
-        next_action_count=0,
-        system_prompt=system_prompt,
-        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
-        workspace_directory=workspace.root,
-    )
-    return agent
+    for command_category in enabled_command_categories:
+        command_registry.import_commands(command_category)
+    ai_goals = [
+        "Write to a file called output.txt tesla's revenue in 2022 after searching for 'tesla revenue 2022'.",
+        "Write to a file called output.txt tesla's revenue in 2022.",
+        "Write to a file called output.txt tesla's revenue every year since its creation.",
+    ]
+    for ai_goal in ai_goals:
+        ai_config = AIConfig(
+            ai_name="Information Retrieval Agent",
+            ai_role="an autonomous agent that specializes in retrieving information.",
+            ai_goals=[ai_goal],
+        )
+        ai_config.command_registry = command_registry
+        system_prompt = ai_config.construct_full_prompt()
+        Config().set_continuous_mode(False)
+        agents.append(
+            Agent(
+                ai_name="Information Retrieval Agent",
+                memory=memory_json_file,
+                command_registry=command_registry,
+                config=ai_config,
+                next_action_count=0,
+                system_prompt=system_prompt,
+                triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
+                workspace_directory=workspace.root,
+            )
+        )
+    return agents
 
 
 @pytest.fixture
diff --git a/tests/integration/challenges/challenge_decorator/challenge_decorator.py b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
index 1ec43aec..fe12317e 100644
--- a/tests/integration/challenges/challenge_decorator/challenge_decorator.py
+++ b/tests/integration/challenges/challenge_decorator/challenge_decorator.py
@@ -1,4 +1,3 @@
-import contextlib
 import os
 from functools import wraps
 from typing import Any, Callable, Optional
@@ -23,6 +22,7 @@ def challenge(func: Callable[..., Any]) -> Callable[..., None]:
     @wraps(func)
     def wrapper(*args: Any, **kwargs: Any) -> None:
         run_remaining = MAX_LEVEL_TO_IMPROVE_ON if Challenge.BEAT_CHALLENGES else 1
+        original_error = None
 
         while run_remaining > 0:
             current_score, new_score, new_score_location = get_scores()
@@ -32,9 +32,12 @@ def challenge(func: Callable[..., Any]) -> Callable[..., None]:
             )
             if challenge.level_to_run is not None:
                 kwargs["level_to_run"] = challenge.level_to_run
-                with contextlib.suppress(AssertionError):
+                try:
                     func(*args, **kwargs)
                     challenge.succeeded = True
+                except AssertionError as err:
+                    original_error = err
+                    challenge.succeeded = False
             else:
                 challenge.skipped = True
             if os.environ.get("CI") == "true":
@@ -51,6 +54,8 @@ def challenge(func: Callable[..., Any]) -> Callable[..., None]:
                 if Challenge.BEAT_CHALLENGES or challenge.is_new_challenge:
                     # xfail
                     pytest.xfail("Challenge failed")
+                if original_error:
+                    raise original_error
                 raise AssertionError("Challenge failed")
             run_remaining -= 1
 
diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index 822c23c2..d2b0b30a 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -11,7 +11,7 @@
     },
     "information_retrieval": {
         "information_retrieval_challenge_a": {
-            "max_level": 1,
+            "max_level": 3,
             "max_level_beaten": 1
         },
         "information_retrieval_challenge_b": {
diff --git a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
index 7a9de8ab..6b970e8b 100644
--- a/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
+++ b/tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py
@@ -9,6 +9,7 @@ from tests.integration.challenges.utils import run_interaction_loop
 from tests.utils import requires_api_key
 
 CYCLE_COUNT = 3
+EXPECTED_REVENUES = [["81"], ["81"], ["81", "53", "24", "21", "11", "7", "4", "3", "2"]]
 from autogpt.agent import Agent
 
 
@@ -16,7 +17,7 @@ from autogpt.agent import Agent
 @requires_api_key("OPENAI_API_KEY")
 @challenge
 def test_information_retrieval_challenge_a(
-    get_company_revenue_agent: Agent,
+    information_retrieval_agents: Agent,
     monkeypatch: pytest.MonkeyPatch,
     patched_api_requestor: None,
     config: Config,
@@ -28,8 +29,13 @@ def test_information_retrieval_challenge_a(
     :param get_company_revenue_agent: The agent to test.
     :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
     """
-    run_interaction_loop(monkeypatch, get_company_revenue_agent, CYCLE_COUNT)
+    information_retrieval_agent = information_retrieval_agents[level_to_run - 1]
+    run_interaction_loop(monkeypatch, information_retrieval_agent, CYCLE_COUNT)
 
-    file_path = str(get_company_revenue_agent.workspace.get_path("output.txt"))
+    file_path = str(information_retrieval_agent.workspace.get_path("output.txt"))
     content = read_file(file_path, config)
-    assert "81" in content, "Expected the file to contain 81"
+    expected_revenues = EXPECTED_REVENUES[level_to_run - 1]
+    for revenue in expected_revenues:
+        assert (
+            f"{revenue}." in content or f"{revenue}," in content
+        ), f"Expected the file to contain {revenue}"

From f6ee61d6078924301f924504dd63ad0cf339509c Mon Sep 17 00:00:00 2001
From: Douglas Schonholtz <15002691+dschonholtz@users.noreply.github.com>
Date: Tue, 30 May 2023 19:28:32 -0400
Subject: [PATCH 094/112] create debug challenge (#4286)

Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: symphony <john.tian31@gmail.com>
---
 BULLETIN.md                                   |  6 +++
 requirements.txt                              |  2 +-
 tests/integration/agent_factory.py            | 38 ++++++++++++++
 .../integration/challenges/current_score.json |  8 ++-
 .../challenges/debug_code/data/two_sum.py     | 19 +++++++
 .../debug_code/data/two_sum_tests.py          | 30 +++++++++++
 .../debug_code/test_debug_code_challenge_a.py | 51 +++++++++++++++++++
 7 files changed, 152 insertions(+), 2 deletions(-)
 create mode 100644 tests/integration/challenges/debug_code/data/two_sum.py
 create mode 100644 tests/integration/challenges/debug_code/data/two_sum_tests.py
 create mode 100644 tests/integration/challenges/debug_code/test_debug_code_challenge_a.py

diff --git a/BULLETIN.md b/BULLETIN.md
index 17c38b8c..70be3c3e 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -51,3 +51,9 @@ memory store was also temporarily removed but we aim to merge a new implementati
 before the next release.
 Whether built-in support for the others will be added back in the future is subject to
 discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
+
+# Challenge Workflow 🏆
+If you have been working on challenges... Thank You!
+But to run the debugger challenge or other challenges using cassettes and VCR in docker, You will now need to `pip uninstall vcrpy` and `pip install -r requirements.txt` again.
+This will install a new version of vcrpy that is compatible with running vcr in docker.
+This workflow will be fixed as soon as the maintainer from VCRpy merges our changes.
diff --git a/requirements.txt b/requirements.txt
index 542f9b50..31f7706a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -58,6 +58,6 @@ pytest-benchmark
 pytest-cov
 pytest-integration
 pytest-mock
-vcrpy
+vcrpy @ git+https://github.com/Significant-Gravitas/vcrpy.git@master
 pytest-recording
 pytest-xdist
diff --git a/tests/integration/agent_factory.py b/tests/integration/agent_factory.py
index 716545c2..30d9cc13 100644
--- a/tests/integration/agent_factory.py
+++ b/tests/integration/agent_factory.py
@@ -246,3 +246,41 @@ def get_nobel_prize_agent(agent_test_config, memory_json_file, workspace: Worksp
     )
 
     return agent
+
+
+@pytest.fixture
+def debug_code_agent(agent_test_config, memory_json_file, workspace: Workspace):
+    command_registry = CommandRegistry()
+    command_registry.import_commands("autogpt.commands.file_operations")
+    command_registry.import_commands("autogpt.commands.execute_code")
+    command_registry.import_commands("autogpt.commands.improve_code")
+    command_registry.import_commands("autogpt.app")
+    command_registry.import_commands("autogpt.commands.task_statuses")
+
+    ai_config = AIConfig(
+        ai_name="Debug Code Agent",
+        ai_role="an autonomous agent that specializes in debugging python code",
+        ai_goals=[
+            "1-Run the code in the file named 'code.py' using the execute_code command.",
+            "2-Read code.py to understand why the code is not working as expected.",
+            "3-Modify code.py to fix the error.",
+            "Repeat step 1, 2 and 3 until the code is working as expected. When you're done use the task_complete command.",
+            "Do not use any other commands than execute_python_file and write_file",
+        ],
+    )
+    ai_config.command_registry = command_registry
+
+    system_prompt = ai_config.construct_full_prompt()
+    Config().set_continuous_mode(False)
+    agent = Agent(
+        ai_name="Debug Code Agent",
+        memory=memory_json_file,
+        command_registry=command_registry,
+        config=ai_config,
+        next_action_count=0,
+        system_prompt=system_prompt,
+        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
+        workspace_directory=workspace.root,
+    )
+
+    return agent
diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index d2b0b30a..80e19d7c 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -19,6 +19,12 @@
             "max_level_beaten": 1
         }
     },
+    "debug_code": {
+        "debug_code_challenge_a": {
+            "max_level": 1,
+            "max_level_beaten": 1
+        }
+    },
     "kubernetes": {
         "kubernetes_template_challenge_a": {
             "max_level": 1,
@@ -39,4 +45,4 @@
             "max_level_beaten": 1
         }
     }
-}
\ No newline at end of file
+}
diff --git a/tests/integration/challenges/debug_code/data/two_sum.py b/tests/integration/challenges/debug_code/data/two_sum.py
new file mode 100644
index 00000000..305cff4e
--- /dev/null
+++ b/tests/integration/challenges/debug_code/data/two_sum.py
@@ -0,0 +1,19 @@
+# mypy: ignore-errors
+from typing import List, Optional
+
+
+def two_sum(nums: List, target: int) -> Optional[int]:
+    seen = {}
+    for i, num in enumerate(nums):
+        complement = target - num
+        if complement in seen:
+            return [seen[complement], i]
+        seen[num] = i
+    return None
+
+
+# Example usage:
+nums = [2, 7, 11, 15]
+target = 9
+result = two_sum(nums, target)
+print(result)  # Output: [0, 1]
diff --git a/tests/integration/challenges/debug_code/data/two_sum_tests.py b/tests/integration/challenges/debug_code/data/two_sum_tests.py
new file mode 100644
index 00000000..0eb89bcb
--- /dev/null
+++ b/tests/integration/challenges/debug_code/data/two_sum_tests.py
@@ -0,0 +1,30 @@
+# mypy: ignore-errors
+# we need a new line at the top of the file to avoid a syntax error
+
+
+def test_two_sum(nums, target, expected_result):
+    # These tests are appended to the two_sum file so we can ignore this error for now
+    result = two_sum(nums, target)
+    print(result)
+    assert (
+        result == expected_result
+    ), f"AssertionError: Expected the output to be {expected_result}"
+
+
+# test the trivial case with the first two numbers
+nums = [2, 7, 11, 15]
+target = 9
+expected_result = [0, 1]
+test_two_sum(nums, target, expected_result)
+
+# test for ability to use zero and the same number twice
+nums = [2, 7, 0, 15, 12, 0]
+target = 0
+expected_result = [2, 5]
+test_two_sum(nums, target, expected_result)
+
+# test for first and last index usage and negative numbers
+nums = [-6, 7, 11, 4]
+target = -2
+expected_result = [0, 3]
+test_two_sum(nums, target, expected_result)
diff --git a/tests/integration/challenges/debug_code/test_debug_code_challenge_a.py b/tests/integration/challenges/debug_code/test_debug_code_challenge_a.py
new file mode 100644
index 00000000..008e562c
--- /dev/null
+++ b/tests/integration/challenges/debug_code/test_debug_code_challenge_a.py
@@ -0,0 +1,51 @@
+from pathlib import Path
+
+import pytest
+from pytest_mock import MockerFixture
+
+from autogpt.agent import Agent
+from autogpt.commands.execute_code import execute_python_file
+from autogpt.commands.file_operations import append_to_file, write_to_file
+from autogpt.config import Config
+from tests.integration.challenges.challenge_decorator.challenge_decorator import (
+    challenge,
+)
+from tests.integration.challenges.utils import run_interaction_loop
+from tests.utils import requires_api_key
+
+CYCLE_COUNT = 5
+
+
+@pytest.mark.vcr
+@requires_api_key("OPENAI_API_KEY")
+@challenge
+def test_debug_code_challenge_a(
+    debug_code_agent: Agent,
+    monkeypatch: pytest.MonkeyPatch,
+    patched_api_requestor: MockerFixture,
+    config: Config,
+    level_to_run: int,
+) -> None:
+    """
+    Test whether the agent can debug a simple code snippet.
+
+    :param debug_code_agent: The agent to test.
+    :param monkeypatch: pytest's monkeypatch utility for modifying builtins.
+    :patched_api_requestor: Sends api requests to our API CI pipeline
+    :config: The config object for the agent.
+    :level_to_run: The level to run.
+    """
+
+    file_path = str(debug_code_agent.workspace.get_path("code.py"))
+
+    code_file_path = Path(__file__).parent / "data" / "two_sum.py"
+    test_file_path = Path(__file__).parent / "data" / "two_sum_tests.py"
+
+    write_to_file(file_path, code_file_path.read_text(), config)
+
+    run_interaction_loop(monkeypatch, debug_code_agent, CYCLE_COUNT)
+
+    append_to_file(file_path, test_file_path.read_text(), config)
+
+    output = execute_python_file(file_path, config)
+    assert "error" not in output.lower(), f"Errors found in output: {output}!"

From 41df0204f36e4ca927dec359bfd99c9f055e7203 Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 23:33:38 +0000
Subject: [PATCH 095/112] Update current score

---
 tests/integration/challenges/current_score.json | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index 80e19d7c..72661399 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -9,6 +9,12 @@
             "max_level_beaten": 1
         }
     },
+    "debug_code": {
+        "debug_code_challenge_a": {
+            "max_level": 1,
+            "max_level_beaten": 1
+        }
+    },
     "information_retrieval": {
         "information_retrieval_challenge_a": {
             "max_level": 3,
@@ -19,12 +25,6 @@
             "max_level_beaten": 1
         }
     },
-    "debug_code": {
-        "debug_code_challenge_a": {
-            "max_level": 1,
-            "max_level_beaten": 1
-        }
-    },
     "kubernetes": {
         "kubernetes_template_challenge_a": {
             "max_level": 1,
@@ -45,4 +45,4 @@
             "max_level_beaten": 1
         }
     }
-}
+}
\ No newline at end of file

From 64973bfe129c5d7618a31e99cdb492b0f356b800 Mon Sep 17 00:00:00 2001
From: Auto-GPT-Bot <github-bot@agpt.co>
Date: Tue, 30 May 2023 23:33:40 +0000
Subject: [PATCH 096/112] Update submodule reference

---
 tests/Auto-GPT-test-cassettes | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/Auto-GPT-test-cassettes b/tests/Auto-GPT-test-cassettes
index d3cea237..be280df4 160000
--- a/tests/Auto-GPT-test-cassettes
+++ b/tests/Auto-GPT-test-cassettes
@@ -1 +1 @@
-Subproject commit d3cea237a1531c8d440dd4ab0531e72e1e437a25
+Subproject commit be280df43d6a23b8074d9cba10d18ed8724a54c9

From 9e9b128b723bafc14304172927833129a8cef75a Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Tue, 30 May 2023 17:16:49 -0700
Subject: [PATCH 097/112] ignore cassettes and current score for all push
 events in github action (#4485)

---
 .github/workflows/docker-ci.yml | 3 +++
 .github/workflows/pr-label.yml  | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/.github/workflows/docker-ci.yml b/.github/workflows/docker-ci.yml
index 2cc3296b..a61b707d 100644
--- a/.github/workflows/docker-ci.yml
+++ b/.github/workflows/docker-ci.yml
@@ -3,6 +3,9 @@ name: Docker CI
 on:
   push:
     branches: [ master ]
+    paths-ignore:
+      - 'tests/Auto-GPT-test-cassettes'
+      - 'tests/integration/challenges/current_score.json'
   pull_request:
     branches: [ master, stable ]
 
diff --git a/.github/workflows/pr-label.yml b/.github/workflows/pr-label.yml
index ff4174ad..0bab5638 100644
--- a/.github/workflows/pr-label.yml
+++ b/.github/workflows/pr-label.yml
@@ -4,6 +4,9 @@ on:
   # So that PRs touching the same files as the push are updated
   push:
     branches: [ master ]
+    paths-ignore:
+      - 'tests/Auto-GPT-test-cassettes'
+      - 'tests/integration/challenges/current_score.json'
   # So that the `dirtyLabel` is removed if conflicts are resolve
   # We recommend `pull_request_target` so that github secrets are available.
   # In `pull_request` we wouldn't be able to change labels of fork PRs

From 63b79a88c6d10e23f7b21081ec17651df22033d5 Mon Sep 17 00:00:00 2001
From: kaneda2004 <emmgee@gmail.com>
Date: Tue, 30 May 2023 19:02:16 -0700
Subject: [PATCH 098/112] Adding support for openai_organization env variable
 (#289)

---
 .env.template            | 1 +
 autogpt/config/config.py | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/.env.template b/.env.template
index dd690308..d4d99baa 100644
--- a/.env.template
+++ b/.env.template
@@ -71,6 +71,7 @@
 OPENAI_API_KEY=your-openai-api-key
 # TEMPERATURE=0
 # USE_AZURE=False
+# OPENAI_ORGANIZATION=your-openai-organization-key-if-applicable
 
 ### AZURE
 # moved to `azure.yaml.template`
diff --git a/autogpt/config/config.py b/autogpt/config/config.py
index 1e61b808..5f76bb74 100644
--- a/autogpt/config/config.py
+++ b/autogpt/config/config.py
@@ -64,6 +64,7 @@ class Config(metaclass=Singleton):
         )
 
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        self.openai_organization = os.getenv("OPENAI_ORGANIZATION")
         self.temperature = float(os.getenv("TEMPERATURE", "0"))
         self.use_azure = os.getenv("USE_AZURE") == "True"
         self.execute_local_commands = (
@@ -79,6 +80,9 @@ class Config(metaclass=Singleton):
             openai.api_base = self.openai_api_base
             openai.api_version = self.openai_api_version
 
+        if self.openai_organization is not None:
+            openai.organization = self.openai_organization
+
         self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
         self.elevenlabs_voice_1_id = os.getenv("ELEVENLABS_VOICE_1_ID")
         self.elevenlabs_voice_2_id = os.getenv("ELEVENLABS_VOICE_2_ID")

From 3fffe65a3b82f65036213d77b53ecc81fd8e2cc1 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Thu, 1 Jun 2023 17:01:30 +0200
Subject: [PATCH 099/112] Update bulletin for v0.4.0

---
 BULLETIN.md | 42 +++++++-----------------------------------
 1 file changed, 7 insertions(+), 35 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index 70be3c3e..3e4e2783 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -14,46 +14,18 @@ We have to be somewhat selective in order to keep making progress, but this does
 mean you can't contribute. Check out the contribution guide on our wiki:
 https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
 
-# 🚀 v0.3.1 Release 🚀
-Over a week and 47 pull requests have passed since v0.3.0, and we are happy to announce
-the release of v0.3.1!
+# 🚀 v0.4.0 Release 🚀
+Two weeks and 76 pull requests have passed since v0.3.1, and we are happy to announce
+the release of v0.4.0!
 
-Highlights and notable changes since v0.2.2:
+Highlights and notable changes since v0.3.1:
 
-## Changes to Docker configuration 🐋
- * The workdir has been changed from */home/appuser* to */app*.
-    Be sure to update any volume mounts accordingly!
- * Docker-compose 1.29.0 is now required.
-
-## Logging 🧾
- * Log functionality has been improved for better understanding
-    and easier summarization.
- * All LLM interactions are now logged to logs/DEBUG, to help with
-    debugging and development.
-
-## Other
- * Edge browser is now supported by the `browse_website` command.
- * Sets of commands can now be disabled using DISABLED_COMMAND_CATEGORIES in .env.
-
-# ⚠️ Command `send_tweet` is REMOVED
-Twitter functionality (and more) is now covered by plugins, see [Plugin support 🔌]
-
-## Plugin support 🔌
-Auto-GPT now has support for plugins! With plugins, you can extend Auto-GPT's abilities,
-adding support for third-party services and more.
-See https://github.com/Significant-Gravitas/Auto-GPT-Plugins for instructions and
-available plugins. Specific plugins can be allowlisted/denylisted in .env.
+## ⚠️ Command `send_tweet` is REMOVED
+Twitter functionality (and more) is now covered by plugins.
 
 ## Memory backend deprecation ⚠️
 The Milvus, Pinecone and Weaviate memory backends were rendered incompatible
 by work on the memory system, and have been removed in `master`. The Redis
-memory store was also temporarily removed but we aim to merge a new implementation
-before the next release.
+memory store was also temporarily removed; we will merge a new implementation ASAP.
 Whether built-in support for the others will be added back in the future is subject to
 discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
-
-# Challenge Workflow 🏆
-If you have been working on challenges... Thank You!
-But to run the debugger challenge or other challenges using cassettes and VCR in docker, You will now need to `pip uninstall vcrpy` and `pip install -r requirements.txt` again.
-This will install a new version of vcrpy that is compatible with running vcr in docker.
-This workflow will be fixed as soon as the maintainer from VCRpy merges our changes.

From 15c157343d7fe9c3ced7e39334b9e0bf72390995 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Thu, 1 Jun 2023 23:23:57 +0200
Subject: [PATCH 100/112] Remove Redis memory configuration from docker-compose
 configs

---
 .devcontainer/docker-compose.yml | 7 -------
 docker-compose.yml               | 8 --------
 docs/setup.md                    | 7 -------
 3 files changed, 22 deletions(-)

diff --git a/.devcontainer/docker-compose.yml b/.devcontainer/docker-compose.yml
index 90d8c116..c05a326e 100644
--- a/.devcontainer/docker-compose.yml
+++ b/.devcontainer/docker-compose.yml
@@ -4,16 +4,9 @@ version: '3.9'
 
 services:
   auto-gpt:
-    depends_on:
-      - redis
     build:
       dockerfile: .devcontainer/Dockerfile
       context: ../
     tty: true
-    environment:
-      MEMORY_BACKEND: ${MEMORY_BACKEND:-redis}
-      REDIS_HOST: ${REDIS_HOST:-redis}
     volumes:
       - ../:/workspace/Auto-GPT
-  redis:
-    image: 'redis/redis-stack-server:latest'
diff --git a/docker-compose.yml b/docker-compose.yml
index a23aa431..d6878e45 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -5,17 +5,9 @@ version: "3.9"
 
 services:
   auto-gpt:
-    depends_on:
-      - redis
     build: ./
     env_file:
       - .env
-    environment:
-      MEMORY_BACKEND: ${MEMORY_BACKEND:-redis}
-      REDIS_HOST: ${REDIS_HOST:-redis}
     volumes:
       - ./:/app
     profiles: ["exclude-from-up"]
-
-  redis:
-    image: "redis/redis-stack-server:latest"
diff --git a/docs/setup.md b/docs/setup.md
index c4755a8d..257e07c1 100644
--- a/docs/setup.md
+++ b/docs/setup.md
@@ -47,13 +47,8 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
         services:
           auto-gpt:
             image: significantgravitas/auto-gpt
-            depends_on:
-              - redis
             env_file:
               - .env
-            environment:
-              MEMORY_BACKEND: ${MEMORY_BACKEND:-redis}
-              REDIS_HOST: ${REDIS_HOST:-redis}
             profiles: ["exclude-from-up"]
             volumes:
               - ./auto_gpt_workspace:/app/autogpt/auto_gpt_workspace
@@ -68,8 +63,6 @@ Get your OpenAI API key from: [https://platform.openai.com/account/api-keys](htt
               #- type: bind
               #  source: ./ai_settings.yaml
               #  target: /app/ai_settings.yaml
-          redis:
-            image: "redis/redis-stack-server:latest"
 
 4. Create the necessary [configuration](#configuration) files. If needed, you can find
     templates in the [repository].

From fc0688673e97ef8ddbbcfbca195b622742a64a41 Mon Sep 17 00:00:00 2001
From: Richard Beales <rich@richbeales.net>
Date: Fri, 2 Jun 2023 12:08:33 +0100
Subject: [PATCH 101/112] Update BULLETIN.md

---
 BULLETIN.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/BULLETIN.md b/BULLETIN.md
index 3e4e2783..6d9303b6 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -29,3 +29,9 @@ by work on the memory system, and have been removed in `master`. The Redis
 memory store was also temporarily removed; we will merge a new implementation ASAP.
 Whether built-in support for the others will be added back in the future is subject to
 discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
+
+## Refactoring of global state
+The config object 'singleton' has been refactored to ease the path to our re-arch.
+
+## Further fixes and changes
+Take a look at the Release Notes on Github! https://github.com/Significant-Gravitas/Auto-GPT/releases/tag/v0.4.0

From 4cc6e27f023eee383408f68e500a6797213ff273 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Fri, 2 Jun 2023 14:09:16 -0700
Subject: [PATCH 102/112] Remove news about config (#4553)

---
 BULLETIN.md | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index 6d9303b6..552a6454 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -30,8 +30,5 @@ memory store was also temporarily removed; we will merge a new implementation AS
 Whether built-in support for the others will be added back in the future is subject to
 discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
 
-## Refactoring of global state
-The config object 'singleton' has been refactored to ease the path to our re-arch.
-
 ## Further fixes and changes
 Take a look at the Release Notes on Github! https://github.com/Significant-Gravitas/Auto-GPT/releases/tag/v0.4.0

From ce440128667eb9b43b78ad765de9e52eeb411463 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Fri, 2 Jun 2023 23:27:15 +0200
Subject: [PATCH 103/112] Fix pushing cassettes in CI

---
 .github/workflows/ci.yml | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 3388edb0..b27e477e 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -89,7 +89,8 @@ jobs:
           repository: ${{ github.event.pull_request.head.repo.full_name }}
           submodules: true
 
-      - name: Check out cassettes
+      - id: checkout_cassettes
+        name: Check out cassettes
         if: ${{ startsWith(github.event_name, 'pull_request') }}
         run: |
           cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
@@ -110,9 +111,11 @@ jobs:
               git merge --abort
               git checkout ${{ github.event.pull_request.base.ref }}
             fi
+            echo "cassette_branch=$(git branch --show-current)" >> $GITHUB_OUTPUT
           else
             echo "Branch '$cassette_branch' does not exist in cassette submodule."\
               "Using cassettes from ${{ github.event.pull_request.base.ref }}."
+            echo "cassette_branch=${{ github.event.pull_request.base.ref }}" >> $GITHUB_OUTPUT
           fi
 
       - name: Set up Python ${{ matrix.python-version }}
@@ -166,6 +169,7 @@ jobs:
           if [[ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]]; then
             is_pull_request=true
             cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
+            cassette_source_branch="${{ steps.checkout_cassettes.outputs.cassette_branch }}"
             base_branch="${{ github.event.pull_request.base.ref }}"
           else
             current_branch=$(echo ${{ github.ref }} | sed -e "s/refs\/heads\///g")
@@ -173,13 +177,16 @@ jobs:
           fi
 
           cd tests/Auto-GPT-test-cassettes
-          git fetch origin $cassette_branch
+          git fetch origin $cassette_source_branch
 
           # Commit & push changes to cassettes if any
-          if ! git diff-index --quiet $cassette_branch; then
+          if ! git diff-index --quiet $cassette_source_branch; then
+            if ! [ "$cassette_branch" = "$cassette_source_branch" ]; then
+              git checkout -b $cassette_branch
+            fi
             git add .
             git commit -m "Auto-update cassettes"
-            git pull --rebase origin $cassette_branch
+            git pull --rebase origin $cassette_source_branch
 
             git push origin HEAD:$cassette_branch
 

From 4c11b21dff6a0c556c1a0cc6b714f0d67113c1ac Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 02:01:35 +0200
Subject: [PATCH 104/112] Fix CI git authorization

---
 .github/workflows/ci.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index b27e477e..9ed1ed76 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -146,7 +146,7 @@ jobs:
         run: |
           config_key="http.${{ github.server_url }}/.extraheader"
           git config "$config_key" \
-            "Authorization: Basic x-access-token:${{ secrets.PAT_REVIEW }}"
+            "Authorization: Basic $(echo -n "x-access-token:${{ secrets.PAT_REVIEW }}" | base64 -w0)"
 
           echo "config_key=$config_key" >> $GITHUB_OUTPUT
 

From 3e5868f2237cd8cd977c89d53f7f2f959905b715 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 02:11:32 +0200
Subject: [PATCH 105/112] Fix CI git diff

---
 .github/workflows/ci.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 9ed1ed76..90a8c54c 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -177,10 +177,10 @@ jobs:
           fi
 
           cd tests/Auto-GPT-test-cassettes
-          git fetch origin $cassette_source_branch
+          git fetch origin $cassette_source_branch:$cassette_source_branch
 
           # Commit & push changes to cassettes if any
-          if ! git diff-index --quiet $cassette_source_branch; then
+          if ! git diff-index --quiet $cassette_source_branch --; then
             if ! [ "$cassette_branch" = "$cassette_source_branch" ]; then
               git checkout -b $cassette_branch
             fi

From c4e2d8fbdd4ca31c25744408b1a821dc7a2782f4 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 03:14:05 +0200
Subject: [PATCH 106/112] debug

---
 .github/workflows/ci.yml | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 90a8c54c..908e87b8 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -145,8 +145,10 @@ jobs:
         name: Set up git token authentication
         run: |
           config_key="http.${{ github.server_url }}/.extraheader"
-          git config "$config_key" \
+          git config --list
+          git config --global "$config_key" \
             "Authorization: Basic $(echo -n "x-access-token:${{ secrets.PAT_REVIEW }}" | base64 -w0)"
+          git config --list
 
           echo "config_key=$config_key" >> $GITHUB_OUTPUT
 
@@ -188,7 +190,8 @@ jobs:
             git commit -m "Auto-update cassettes"
             git pull --rebase origin $cassette_source_branch
 
-            git push origin HEAD:$cassette_branch
+            git config --list
+            GIT_TRACE=2 GIT_CURL_VERBOSE=2 git push origin HEAD:$cassette_branch
 
             cd ../..
             if [ $is_pull_request ]; then

From 0a20fa4fdf7239285323aa3cee945e827dad9c79 Mon Sep 17 00:00:00 2001
From: Merwane Hamadi <merwanehamadi@gmail.com>
Date: Sat, 3 Jun 2023 21:19:58 -0700
Subject: [PATCH 107/112] Fix CI git authentication and cassettes

---
 .github/workflows/ci.yml | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 908e87b8..8793b203 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -144,13 +144,17 @@ jobs:
       - id: setup_git_auth
         name: Set up git token authentication
         run: |
+          base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
           config_key="http.${{ github.server_url }}/.extraheader"
-          git config --list
-          git config --global "$config_key" \
-            "Authorization: Basic $(echo -n "x-access-token:${{ secrets.PAT_REVIEW }}" | base64 -w0)"
-          git config --list
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
 
+          cd tests/Auto-GPT-test-cassettes 
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
           echo "config_key=$config_key" >> $GITHUB_OUTPUT
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
 
       - name: Push updated challenge scores
         if: github.event_name == 'push'
@@ -179,25 +183,27 @@ jobs:
           fi
 
           cd tests/Auto-GPT-test-cassettes
-          git fetch origin $cassette_source_branch:$cassette_source_branch
+          git fetch origin
 
           # Commit & push changes to cassettes if any
-          if ! git diff-index --quiet $cassette_source_branch --; then
+          if ! git diff --quiet; then
             if ! [ "$cassette_branch" = "$cassette_source_branch" ]; then
               git checkout -b $cassette_branch
             fi
             git add .
             git commit -m "Auto-update cassettes"
-            git pull --rebase origin $cassette_source_branch
 
-            git config --list
-            GIT_TRACE=2 GIT_CURL_VERBOSE=2 git push origin HEAD:$cassette_branch
-
-            cd ../..
             if [ $is_pull_request ]; then
+              git checkout -b $cassette_branch || git checkout $cassette_branch
+              git push -f origin $cassette_branch
+              cd ../..
+
               git fetch origin $base_branch
-              cassette_diff=$(git diff $cassette_branch origin/$base_branch)
+              cassette_diff=$(git diff origin/$base_branch)
             else
+              git push origin HEAD:$cassette_branch
+              cd ../..
+
               git add tests/Auto-GPT-test-cassettes
               git commit -m "Update cassette submodule"
               git push origin HEAD:$current_branch

From 02846fcf912ff0833cc67f7e985743ee33e5b010 Mon Sep 17 00:00:00 2001
From: Merwane Hamadi <merwanehamadi@gmail.com>
Date: Sat, 3 Jun 2023 21:24:36 -0700
Subject: [PATCH 108/112] remove information retrieval challenge b from beaten
 challenges

---
 tests/integration/challenges/current_score.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/integration/challenges/current_score.json b/tests/integration/challenges/current_score.json
index 72661399..deb4a82d 100644
--- a/tests/integration/challenges/current_score.json
+++ b/tests/integration/challenges/current_score.json
@@ -22,7 +22,7 @@
         },
         "information_retrieval_challenge_b": {
             "max_level": 1,
-            "max_level_beaten": 1
+            "max_level_beaten": null
         }
     },
     "kubernetes": {
@@ -45,4 +45,4 @@
             "max_level_beaten": 1
         }
     }
-}
\ No newline at end of file
+}

From 84e58051faa0a5058f917b48b284d6149f050050 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 15:06:30 +0200
Subject: [PATCH 109/112] Clean up CI git logic

---
 .github/workflows/ci.yml | 40 +++++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 8793b203..a9656fc1 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -94,8 +94,6 @@ jobs:
         if: ${{ startsWith(github.event_name, 'pull_request') }}
         run: |
           cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
-          git config --global user.name "Auto-GPT-Bot"
-          git config --global user.email "github-bot@agpt.co"
           cd tests/Auto-GPT-test-cassettes
 
           if git ls-remote --exit-code --heads origin $cassette_branch ; then
@@ -110,6 +108,9 @@ jobs:
               echo "Could not merge upstream changes to cassettes. Using cassettes from ${{ github.event.pull_request.base.ref }}."
               git merge --abort
               git checkout ${{ github.event.pull_request.base.ref }}
+
+              # Delete branch to prevent conflict when re-creating it
+              git branch -D $cassette_branch
             fi
             echo "cassette_branch=$(git branch --show-current)" >> $GITHUB_OUTPUT
           else
@@ -144,17 +145,20 @@ jobs:
       - id: setup_git_auth
         name: Set up git token authentication
         run: |
-          base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+
           config_key="http.${{ github.server_url }}/.extraheader"
+          base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
+
           git config "$config_key" \
             "Authorization: Basic $base64_pat"
 
-          cd tests/Auto-GPT-test-cassettes 
+          cd tests/Auto-GPT-test-cassettes
           git config "$config_key" \
             "Authorization: Basic $base64_pat"
+
           echo "config_key=$config_key" >> $GITHUB_OUTPUT
-          git config --global user.name "Auto-GPT-Bot"
-          git config --global user.email "github-bot@agpt.co"
 
       - name: Push updated challenge scores
         if: github.event_name == 'push'
@@ -172,7 +176,7 @@ jobs:
       - id: push_cassettes
         name: Push updated cassettes
         run: |
-          if [[ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]]; then
+          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
             is_pull_request=true
             cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
             cassette_source_branch="${{ steps.checkout_cassettes.outputs.cassette_branch }}"
@@ -183,27 +187,27 @@ jobs:
           fi
 
           cd tests/Auto-GPT-test-cassettes
-          git fetch origin
+          git fetch origin $cassette_source_branch:$cassette_source_branch
 
           # Commit & push changes to cassettes if any
-          if ! git diff --quiet; then
-            if ! [ "$cassette_branch" = "$cassette_source_branch" ]; then
+          if ! git diff --quiet $cassette_source_branch --; then
+            if [ "$cassette_branch" != "$cassette_source_branch" ]; then
               git checkout -b $cassette_branch
             fi
             git add .
             git commit -m "Auto-update cassettes"
 
             if [ $is_pull_request ]; then
-              git checkout -b $cassette_branch || git checkout $cassette_branch
-              git push -f origin $cassette_branch
-              cd ../..
+              git push --force origin HEAD:$cassette_branch
+            else
+              git push origin HEAD:$cassette_branch
+            fi
 
+            cd ../..
+            if [ $is_pull_request ]; then
               git fetch origin $base_branch
               cassette_diff=$(git diff origin/$base_branch)
             else
-              git push origin HEAD:$cassette_branch
-              cd ../..
-
               git add tests/Auto-GPT-test-cassettes
               git commit -m "Update cassette submodule"
               git push origin HEAD:$current_branch
@@ -219,8 +223,10 @@ jobs:
           fi
 
       - name: Post Set up git token auth
+        if: steps.setup_git_auth.outcome == 'success'
         run: |
-          git config --unset "${{ steps.setup_git_auth.outputs.config_key }}"
+          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
 
       - name: Apply or remove behaviour change label and comment on PR
         if: ${{ startsWith(github.event_name, 'pull_request') }}

From af28510abae3a3155f361331637f7b02b1906935 Mon Sep 17 00:00:00 2001
From: merwanehamadi <merwanehamadi@gmail.com>
Date: Sun, 4 Jun 2023 07:38:32 -0700
Subject: [PATCH 110/112] Fix `test_web_selenium` (#4554)

---
 tests/{unit => integration}/test_web_selenium.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
 rename tests/{unit => integration}/test_web_selenium.py (67%)

diff --git a/tests/unit/test_web_selenium.py b/tests/integration/test_web_selenium.py
similarity index 67%
rename from tests/unit/test_web_selenium.py
rename to tests/integration/test_web_selenium.py
index 0415007d..2a03a3c0 100644
--- a/tests/unit/test_web_selenium.py
+++ b/tests/integration/test_web_selenium.py
@@ -1,7 +1,10 @@
+from pytest_mock import MockerFixture
+
 from autogpt.commands.web_selenium import browse_website
+from autogpt.config import Config
 
 
-def test_browse_website(config):
+def test_browse_website(config: Config, patched_api_requestor: MockerFixture):
     url = "https://barrel-roll.com"
     question = "How to execute a barrel roll"
 

From 120fe762df1706ab2a8a16620343b589a2d4fea4 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 19:31:58 +0200
Subject: [PATCH 111/112] Update bulletin with highlights for v0.4.0 release
 (#4576)

---
 BULLETIN.md | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index 552a6454..b52e3afb 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -23,12 +23,25 @@ Highlights and notable changes since v0.3.1:
 ## ⚠️ Command `send_tweet` is REMOVED
 Twitter functionality (and more) is now covered by plugins.
 
-## Memory backend deprecation ⚠️
+## ⚠️ Memory backend deprecation 💾
 The Milvus, Pinecone and Weaviate memory backends were rendered incompatible
 by work on the memory system, and have been removed in `master`. The Redis
 memory store was also temporarily removed; we will merge a new implementation ASAP.
 Whether built-in support for the others will be added back in the future is subject to
 discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280
 
-## Further fixes and changes
-Take a look at the Release Notes on Github! https://github.com/Significant-Gravitas/Auto-GPT/releases/tag/v0.4.0
+## Document support in `read_file` 📄
+Auto-GPT can now read text from document files, with support added for PDF, DOCX, CSV,
+HTML, TeX and more!
+
+## Managing Auto-GPT's access to commands ❌🔧
+You can now disable set of built-in commands through the *DISABLED_COMMAND_CATEGORIES*
+variable in .env. Specific shell commands can also be disabled using *DENY_COMMANDS*,
+or selectively enabled using *ALLOW_COMMANDS*.
+
+## Further fixes and changes 🛠️
+Other highlights include improvements to self-feedback mode and continuous mode,
+documentation, docker and devcontainer setups, and much more. Most of the improvements
+that were made are not yet visible to users, but will pay off in the long term.
+Take a look at the Release Notes on Github for the full changelog!
+https://github.com/Significant-Gravitas/Auto-GPT/releases

From 3dbc3773086db0032472704367d19d68ee686988 Mon Sep 17 00:00:00 2001
From: Reinier van der Leer <github@pwuts.nl>
Date: Sun, 4 Jun 2023 20:05:57 +0200
Subject: [PATCH 112/112] Update version numbers for v0.4.0 release

---
 BULLETIN.md    | 2 +-
 pyproject.toml | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/BULLETIN.md b/BULLETIN.md
index b52e3afb..4c858b73 100644
--- a/BULLETIN.md
+++ b/BULLETIN.md
@@ -18,7 +18,7 @@ https://github.com/Significant-Gravitas/Auto-GPT/wiki/Contributing
 Two weeks and 76 pull requests have passed since v0.3.1, and we are happy to announce
 the release of v0.4.0!
 
-Highlights and notable changes since v0.3.1:
+Highlights and notable changes since v0.3.0:
 
 ## ⚠️ Command `send_tweet` is REMOVED
 Twitter functionality (and more) is now covered by plugins.
diff --git a/pyproject.toml b/pyproject.toml
index bf71c70c..d695ac08 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agpt"
-version = "0.3.0"
+version = "0.4.0"
 authors = [
   { name="Torantulino", email="support@agpt.co" },
 ]