andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-03 00:02:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fixed core invoke loop logic and relevant tests (#1865)

Browse Source 
* Fixed core invoke loop logic and relevant tests

* Fix failing tests

* Clean up final print statements

* Additional clean up for PR review
This commit is contained in:
Brandon Hancock (bhancock_ai)
2025-01-09 12:13:02 -05:00
committed by GitHub
parent b3504e768c
commit 2131b94ddb
11 changed files with 1854 additions and 32101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

668
tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
View File

@@ -2,23 +2,23 @@ interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o"}'
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [get_final_answer], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple python dictionary, enclosed in
curly braces, using \" to wrap keys and values.\nObservation: the result of
the action\n\nOnce all necessary information is gathered:\n\nThought: I now
know the final answer\nFinal Answer: the final answer to the original input
question"}, {"role": "user", "content": "\nCurrent Task: The final answer is
42. But don''t give it yet, instead keep using the `get_final_answer` tool over
and over until you''re told you can give your final answer.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
@@ -27,16 +27,13 @@ interactions:
connection:
- keep-alive
content-length:
- '1452'
- '1440'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
@@ -46,30 +43,285 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7NlDmtLHCfUZJCFVIKeV5KMyQfX\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213349,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AnAdPHapYzkPkClCzFaWzfCAUHlWI\",\n \"object\":
\"chat.completion\",\n \"created\": 1736282315,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to use the provided tool
as instructed.\\n\\nAction: get_final_answer\\nAction Input: {}\",\n \"refusal\":
\"assistant\",\n \"content\": \"I need to use the `get_final_answer`
tool and then keep using it repeatedly as instructed. \\n\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
285,\n \"completion_tokens\": 31,\n \"total_tokens\": 316,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fe6c096ee70ed8c-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 20:38:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=hkH74Rv9bMDMhhK.Ep.9blvKIwXeSSwlCoTNGk9qVpA-1736282316-1.0.1.1-5PAsOPpVEfTNNy5DYRlLH1f4caHJArumiloWf.L51RQPWN3uIWsBSuhLVbNQDYVCQb9RQK8W5DcXv5Jq9FvsLA;
path=/; expires=Tue, 07-Jan-25 21:08:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=vqZ5X0AXIJfzp5UJSFyTmaCVjA.L8Yg35b.ijZFAPM4-1736282316289-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '883'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999665'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_00de12bc6822ef095f4f368aae873f31
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [get_final_answer], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple python dictionary, enclosed in
curly braces, using \" to wrap keys and values.\nObservation: the result of
the action\n\nOnce all necessary information is gathered:\n\nThought: I now
know the final answer\nFinal Answer: the final answer to the original input
question"}, {"role": "user", "content": "\nCurrent Task: The final answer is
42. But don''t give it yet, instead keep using the `get_final_answer` tool over
and over until you''re told you can give your final answer.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need to
use the `get_final_answer` tool and then keep using it repeatedly as instructed.
\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42"}], "model":
"gpt-4o", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1632'
content-type:
- application/json
cookie:
- __cf_bm=hkH74Rv9bMDMhhK.Ep.9blvKIwXeSSwlCoTNGk9qVpA-1736282316-1.0.1.1-5PAsOPpVEfTNNy5DYRlLH1f4caHJArumiloWf.L51RQPWN3uIWsBSuhLVbNQDYVCQb9RQK8W5DcXv5Jq9FvsLA;
_cfuvid=vqZ5X0AXIJfzp5UJSFyTmaCVjA.L8Yg35b.ijZFAPM4-1736282316289-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AnAdQKGW3Q8LUCmphL7hkavxi4zWB\",\n \"object\":
\"chat.completion\",\n \"created\": 1736282316,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I should continue using the `get_final_answer`
tool as per the instructions.\\n\\nAction: get_final_answer\\nAction Input:
{}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 324,\n \"completion_tokens\":
26,\n \"total_tokens\": 350,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fe6c09e6c69ed8c-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 20:38:37 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '542'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999627'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_6844467024f67bb1477445b1a8a01761
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [get_final_answer], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple python dictionary, enclosed in
curly braces, using \" to wrap keys and values.\nObservation: the result of
the action\n\nOnce all necessary information is gathered:\n\nThought: I now
know the final answer\nFinal Answer: the final answer to the original input
question"}, {"role": "user", "content": "\nCurrent Task: The final answer is
42. But don''t give it yet, instead keep using the `get_final_answer` tool over
and over until you''re told you can give your final answer.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need to
use the `get_final_answer` tool and then keep using it repeatedly as instructed.
\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42"}, {"role":
"assistant", "content": "I should continue using the `get_final_answer` tool
as per the instructions.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead."}], "model": "gpt-4o", "stop": ["\nObservation:"], "stream":
false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1908'
content-type:
- application/json
cookie:
- __cf_bm=hkH74Rv9bMDMhhK.Ep.9blvKIwXeSSwlCoTNGk9qVpA-1736282316-1.0.1.1-5PAsOPpVEfTNNy5DYRlLH1f4caHJArumiloWf.L51RQPWN3uIWsBSuhLVbNQDYVCQb9RQK8W5DcXv5Jq9FvsLA;
_cfuvid=vqZ5X0AXIJfzp5UJSFyTmaCVjA.L8Yg35b.ijZFAPM4-1736282316289-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AnAdR2lKFEVaDbfD9qaF0Tts0eVMt\",\n \"object\":
\"chat.completion\",\n \"created\": 1736282317,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I should persist with using the `get_final_answer`
tool.\\n\\nAction: get_final_answer\\nAction Input: {}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 303,\n \"completion_tokens\":
22,\n \"total_tokens\": 325,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 378,\n \"completion_tokens\":
23,\n \"total_tokens\": 401,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85de473ae11cf3-GRU
- 8fe6c0a2ce3ded8c-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -77,7 +329,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:29:10 GMT
- Tue, 07 Jan 2025 20:38:37 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -86,10 +338,12 @@ interactions:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '489'
- '492'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -101,273 +355,59 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999651'
- '29999567'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_de70a4dc416515dda4b2ad48bde52f93
- req_198e698a8bc7eea092ea32b83cc4304e
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "Thought: I need to use the provided tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1608'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Nnz14hlEaTdabXodZCVU0UoDhk\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213351,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I must continue using the `get_final_answer`
tool as instructed.\\n\\nAction: get_final_answer\\nAction Input: {}\\nObservation:
42\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 333,\n \"completion_tokens\":
30,\n \"total_tokens\": 363,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85de5109701cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:29:11 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '516'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999620'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5365ac0e5413bd9330c6ac3f68051bcf
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "Thought: I need to use the provided tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I must continue using the `get_final_answer` tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1799'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7NoF5Gf597BGmOETPYGxN2eRFxd\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213352,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I must continue using the `get_final_answer`
tool to meet the requirements.\\n\\nAction: get_final_answer\\nAction Input:
{}\\nObservation: 42\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
372,\n \"completion_tokens\": 32,\n \"total_tokens\": 404,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85de587bc01cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:29:12 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '471'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999583'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_55550369b28e37f064296dbc41e0db69
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
answer but don''t give it yet, just re-use this tool non-stop. \nTool
Arguments: {}\n\nUse the following format:\n\nThought: you should always think
about what to do\nAction: the action to take, only one name of [get_final_answer],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple python dictionary, enclosed in curly braces, using \" to wrap
keys and values.\nObservation: the result of the action\n\nOnce all necessary
information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n"}, {"role": "user", "content":
"\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep
using the `get_final_answer` tool over and over until you''re told you can give
your final answer.\n\nThis is the expect criteria for your final answer: The
final answer\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
"assistant", "content": "Thought: I need to use the provided tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant",
"content": "Thought: I must continue using the `get_final_answer` tool as instructed.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\nObservation: 42"}, {"role":
"assistant", "content": "Thought: I must continue using the `get_final_answer`
tool to meet the requirements.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42\nObservation: I tried reusing the same input, I must stop using this action
input. I''ll try something else instead.\n\n\n\n\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: get_final_answer(*args: Any, **kwargs: Any) -> Any\nTool Description:
get_final_answer() - Get the final answer but don''t give it yet, just re-use
this tool non-stop. \nTool Arguments: {}\n\nUse the following format:\n\nThought:
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [get_final_answer], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple python dictionary, enclosed in
curly braces, using \" to wrap keys and values.\nObservation: the result of
the action\n\nOnce all necessary information is gathered:\n\nThought: I now
know the final answer\nFinal Answer: the final answer to the original input
question"}, {"role": "user", "content": "\nCurrent Task: The final answer is
42. But don''t give it yet, instead keep using the `get_final_answer` tool over
and over until you''re told you can give your final answer.\n\nThis is the expect
criteria for your final answer: The final answer\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nBegin! This is VERY
important to you, use the tools available and give your best Final Answer, your
job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need to
use the `get_final_answer` tool and then keep using it repeatedly as instructed.
\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42"}, {"role":
"assistant", "content": "I should continue using the `get_final_answer` tool
as per the instructions.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead."}, {"role": "assistant", "content": "I should persist
with using the `get_final_answer` tool.\n\nAction: get_final_answer\nAction
Input: {}\nObservation: I tried reusing the same input, I must stop using this
action input. I''ll try something else instead.\n\n\n\n\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: get_final_answer\nTool Arguments: {}\nTool Description: Get the final
answer but don''t give it yet, just re-use this\n tool non-stop.\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question"}, {"role": "assistant", "content": "I should persist with using
the `get_final_answer` tool.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
I tried reusing the same input, I must stop using this action input. I''ll try
something else instead.\n\n\n\n\nYou ONLY have access to the following tools,
and should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nUse the following format:\n\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [get_final_answer], just the name, exactly as it''s written.\nAction
Input: the input to the action, just a simple python dictionary, enclosed in
@@ -376,7 +416,8 @@ interactions:
know the final answer\nFinal Answer: the final answer to the original input
question\n\nNow it''s time you MUST give your absolute best final answer. You''ll
ignore all previous instructions, stop using any tools, and just return your
absolute BEST Final answer."}], "model": "gpt-4o"}'
absolute BEST Final answer."}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
@@ -385,16 +426,16 @@ interactions:
connection:
- keep-alive
content-length:
- '3107'
- '4148'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
- __cf_bm=hkH74Rv9bMDMhhK.Ep.9blvKIwXeSSwlCoTNGk9qVpA-1736282316-1.0.1.1-5PAsOPpVEfTNNy5DYRlLH1f4caHJArumiloWf.L51RQPWN3uIWsBSuhLVbNQDYVCQb9RQK8W5DcXv5Jq9FvsLA;
_cfuvid=vqZ5X0AXIJfzp5UJSFyTmaCVjA.L8Yg35b.ijZFAPM4-1736282316289-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
@@ -404,29 +445,34 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Npl5ZliMrcSofDS1c7LVGSmmbE\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213353,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-AnAdRu1aVdsOxxIqU6nqv5dIxwbvu\",\n \"object\":
\"chat.completion\",\n \"created\": 1736282317,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\n\\nFinal
Answer: The final answer is 42.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
642,\n \"completion_tokens\": 19,\n \"total_tokens\": 661,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: 42\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
831,\n \"completion_tokens\": 14,\n \"total_tokens\": 845,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85de5fad921cf3-GRU
- 8fe6c0a68cc3ed8c-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -434,7 +480,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:29:13 GMT
- Tue, 07 Jan 2025 20:38:38 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -443,10 +489,12 @@ interactions:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '320'
- '429'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -458,13 +506,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999271'
- '29999037'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_5eba25209fc7e12717cb7e042e7bb4c2
- req_2552d63d3cbce15909481cc1fc9f36cc
http_version: HTTP/1.1
status_code: 200
version: 1