aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-02-10 00:34:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

Move task_complete command out of prompt (#3663)

Browse Source 
* feat: move task_complete command out of prompt

* fix: formatting fixes

* Add the shutdown command to the test agents

* tests: update test vcrs

---------

Co-authored-by: James Collins <collijk@uw.edu>
This commit is contained in:
Nicholas Tindle
2023-05-03 18:40:49 -05:00
committed by GitHub
parent e21917cc93
commit d74428057e
9 changed files with 1415 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
autogpt/app.py
View File

@@ -120,8 +120,6 @@ def execute_command(
# 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
elif command_name == "task_complete":
shutdown()
else:
for command in prompt.commands:
if (
@@ -171,12 +169,6 @@ def get_hyperlinks(url: str) -> Union[str, List[str]]:
return scrape_links(url)
def shutdown() -> NoReturn:
"""Shut down the program"""
logger.info("Shutting down...")
quit()
@command(
"start_agent",
"Start GPT Agent",

26
autogpt/commands/task_statuses.py Normal file
View File

@@ -0,0 +1,26 @@
"""Task Statuses module."""
from __future__ import annotations
from typing import NoReturn
from autogpt.commands.command import command
from autogpt.logs import logger
@command(
"task_complete",
"Task Complete (Shutdown)",
'"reason": "<reason>"',
)
def task_complete(reason: str) -> NoReturn:
"""
A function that takes in a string and exits the program
Parameters:
reason (str): The reason for shutting down.
Returns:
A result string from create chat completion. A list of suggestions to
improve the code.
"""
logger.info(title="Shutting down...\n", message=reason)
quit()

1
autogpt/main.py
View File

@@ -130,6 +130,7 @@ def run_auto_gpt(
command_registry.import_commands("autogpt.commands.web_selenium")
command_registry.import_commands("autogpt.commands.write_tests")
command_registry.import_commands("autogpt.app")
command_registry.import_commands("autogpt.commands.task_statuses")
ai_name = ""
ai_config = construct_main_ai_config()

9
autogpt/prompts/prompt.py
View File

@@ -41,15 +41,6 @@ def build_default_prompt_generator() -> PromptGenerator:
'Exclusively use the commands listed in double quotes e.g. "command name"'
)
# Define the command list
commands = [
("Task Complete (Shutdown)", "task_complete", {"reason": "<reason>"}),
]
# Add commands to the PromptGenerator object
for command_label, command_name, args in commands:
prompt_generator.add_command(command_label, command_name, args)
# Add resources to the PromptGenerator object
prompt_generator.add_resource(
"Internet access for searches and information gathering."

3
tests/integration/agent_factory.py
View File

@@ -45,6 +45,7 @@ def browser_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace
command_registry.import_commands("autogpt.commands.file_operations")
command_registry.import_commands("autogpt.commands.web_selenium")
command_registry.import_commands("autogpt.app")
command_registry.import_commands("autogpt.commands.task_statuses")
ai_config = AIConfig(
ai_name="browse_website-GPT",
@@ -80,6 +81,7 @@ def writer_agent(agent_test_config, memory_none: NoMemory, 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.task_statuses")
ai_config = AIConfig(
ai_name="write_to_file-GPT",
@@ -120,6 +122,7 @@ def memory_management_agent(
command_registry = CommandRegistry()
command_registry.import_commands("autogpt.commands.file_operations")
command_registry.import_commands("autogpt.app")
command_registry.import_commands("autogpt.commands.task_statuses")
ai_config = AIConfig(
ai_name="Follow-Instructions-GPT",

721
tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
View File

@@ -40,7 +40,7 @@ interactions:
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": 2763}'
"temperature": 0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -123,7 +123,7 @@ interactions:
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": null}'
"temperature": 0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -248,7 +248,7 @@ interactions:
{"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": 2549}'
0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -332,7 +332,7 @@ interactions:
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": null}'
new happened.\n\"\"\"\n"}], "temperature": 0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -469,7 +469,7 @@ interactions:
{\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": 2339}'
using the format specified above:"}], "temperature": 0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -554,7 +554,7 @@ interactions:
''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": null}'
"max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -704,7 +704,7 @@ interactions:
{"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": 2125}'
"temperature": 0, "max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -789,7 +789,7 @@ interactions:
''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": null}'
"max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -951,7 +951,7 @@ interactions:
{"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": 1912}'
"max_tokens": 0}'
headers:
Accept:
- '*/*'
@@ -1025,4 +1025,707 @@ 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": "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 |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:
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 |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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 |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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'
x-ratelimit-reset-requests:
- 17ms
x-ratelimit-reset-tokens:
- 2.36s
x-request-id:
- ecfa6ef54add3f6517ceb72c53d46f7d
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:"}, {"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}"},
{"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:
- '6448'
Content-Type:
- application/json
method: POST
uri: https://api.openai.com/v1/chat/completions
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=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 7c15cf155f914768-DFW
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 03 May 2023 04:37:38 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:
- '9744'
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:
- 9a91f5f1047315a3b543a4b85d42e4d3
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:"}, {"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}"},
{"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\":
\"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:
- '7415'
Content-Type:
- application/json
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 7c15cf5f5f494768-DFW
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 03 May 2023 04:37:47 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:
- significant-gravitas
openai-processing-ms:
- '6973'
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:
- 7cc602be91ae73e5f18b92f2743aef7d
status:
code: 200
message: OK
version: 1

423
tests/integration/goal_oriented/cassettes/test_browse_website/test_browse_website.yaml
View File

@@ -1334,4 +1334,427 @@ 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 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.
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:
- '3782'
Content-Type:
- application/json
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 7c15cf968c8f2e2d-DFW
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 03 May 2023 04:38:03 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:
- '14086'
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:
- 7d5960d2e736b510f90bce2462edc349
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 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.
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 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.\",\n \"plan\":
\"- Use the browse_website command to visit the website\\n- Search for the price
of the book\\n- Save 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 searching for the correct information on the website and
that I am saving the information to the correct file.\",\n \"speak\":
\"I will use the browse_website command to visit the website and search for
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. \\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:
- '5788'
Content-Type:
- application/json
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 7c15d0162f7e2e2d-DFW
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 03 May 2023 04:38:22 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:
- '12877'
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:
- '86484'
x-ratelimit-reset-requests:
- 17ms
x-ratelimit-reset-tokens:
- 2.344s
x-request-id:
- 3f98e6bc193fe721af8b1119040752cf
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 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.
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 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.\",\n \"plan\":
\"- Use the browse_website command to visit the website\\n- Search for the price
of the book\\n- Save 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 searching for the correct information on the website and
that I am saving the information to the correct file.\",\n \"speak\":
\"I will use the browse_website command to visit the website and search for
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. \\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.\",\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- Use the task_complete command to complete the task\",\n \"criticism\":
\"I need to ensure that I am writing the correct information 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:
- '6974'
Content-Type:
- application/json
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA6xSTY/TMBC98yusObtVq1Ja5QYIRJcLh0VaiaDKcaaJqT+CZ7LtUuW/o7RJ0w1c
WHH0m5k3743fCUwOCehSsXaVnazePT0ctbt7X+svxacPP399frjfuPu3H211p0FCyH6g5m5iqoOr
LLIJHiToiIoxh2T+Zr2Yrder2VKCCzlaSKCoeLKYLidcxyxMZovZHCTUpAqE5ARVDK7iLYc9eoJk
vlyuJAzkQ2H1WgIHVvYGWswbCboMRiNB8u0EDqknjsEiJKCIDLHy3MoMntG3Fk6pF0KIFLgMdVEy
pZCIDuwKeOQWTGEjPGIuOIiaUHCJghXtt51GFDo4p/y54Yr1XdMU5C1rREXBG1/01KV6xOtYfp0T
YSceDRk2vjiDB8zIMIp20SEOeBWNxra7fWQh7FsZSuyMReGVw1xkMRwItx3BlI8sBQWxEVr5/+Co
sspfzEzE139mG5Hp1pk25MaXR091bMcUDzcyNBBmuAsRRU39Yf6qYSyeKlT7ftfBWPuyg1woG9mH
qmv/I1Pth1y2PaMfiVKxGMfxNjzPkkO11ki0q619ugSmC9E4L4z+xXm5Ojy77MymvoFGws54Q+X2
Ig0SIA4VSDA+xyMks+Z78+o3AAAA//8DAOBHTyVoBAAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 7c15d07678622e2d-DFW
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 03 May 2023 04:38:36 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:
- '10949'
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:
- 176c6e9d4a6ec0fa8a0c8053a4f50218
status:
code: 200
message: OK
version: 1

249
tests/integration/goal_oriented/cassettes/test_write_file/test_write_file.yaml
View File

@@ -324,4 +324,253 @@ 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.\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 |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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 |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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
status:
code: 200
message: OK
version: 1

2
tests/integration/goal_oriented/test_browse_website.py
View File

@@ -11,7 +11,7 @@ from tests.utils import requires_api_key
def test_browse_website(browser_agent: Agent) -> None:
file_path = browser_agent.workspace.get_path("browse_website.txt")
try:
run_interaction_loop(browser_agent, 40)
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)