aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-26 10:24:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update get_hyperlinks description (#4122)

Browse Source 
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>
This commit is contained in:
Sicong Zhao
2023-05-23 09:47:58 -04:00
committed by GitHub
parent 9c7f5671e6
commit a8af3313c1
4 changed files with 1462 additions and 1284 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
autogpt/app.py
View File

@@ -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

678
tests/integration/challenges/basic_abilities/cassettes/test_browse_website/test_browse_website.yaml
View File

@@ -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 |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H4sIAAAAAAAAA6RTS0/bQBC+91eM5sLFcRISSORLb5UoFWoRCLV1Fa3XE3tre9fsjglSlP+O1g9I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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 |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H4sIAAAAAAAAA7yUz27aQBDG732K0Vy4GAtDgNRvQKW0akVzqStrvR7sDfauszsOSMhP0zfpk1X+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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 |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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 |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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 |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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

471
tests/integration/challenges/basic_abilities/cassettes/test_write_file/test_write_file.yaml
View File

@@ -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 |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H4sIAAAAAAAAA7STTY/TMBCG7/yK0Vx6SauW0m7JDa1A9MCFBbGIoMjrTBtTxxPsCS2q8t9X+ehX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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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=
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 |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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 |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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 |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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

1595
tests/integration/challenges/memory/cassettes/test_memory_challenge_a/test_memory_challenge_a.yaml
View File

File diff suppressed because it is too large Load Diff