andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
0af6b05e1646377d66d5465b5b49d1f028d057da
crewAI/tests/cassettes/test_agent_moved_on_after_max_iterations.yaml
Brandon Hancock (bhancock_ai) 2131b94ddb Fixed core invoke loop logic and relevant tests (#1865) 
* Fixed core invoke loop logic and relevant tests

* Fix failing tests

* Clean up final print statements

* Additional clean up for PR review
2025-01-09 12:13:02 -05:00

519 lines
22 KiB
YAML
Raw Blame History

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\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
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1440'
content-type:
- application/json
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-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\": \"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\": 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:
- 8fe6c0a2ce3ded8c-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:
- '492'
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:
- '29999567'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- 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\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
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\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", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4148'
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-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.\\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:
- 8fe6c0a68cc3ed8c-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 20:38:38 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:
- '429'
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:
- '29999037'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_2552d63d3cbce15909481cc1fc9f36cc
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink