Files
crewAI/tests/cassettes/test_agent_custom_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

245 lines
9.8 KiB
YAML

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.\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:
- '1377'
content-type:
- application/json
cookie:
- _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
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-An9sn6yimejzB3twOt8E2VAj4Bfmm\",\n \"object\":
\"chat.completion\",\n \"created\": 1736279425,\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 `get_final_answer`
tool to fulfill the current task requirement.\\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\":
273,\n \"completion_tokens\": 30,\n \"total_tokens\": 303,\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:
- 8fe67a03ce78ed83-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 19:50:25 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=PsMOhP_yeSFIMA.FfRlNbisoG88z4l9NSd0zfS5UrOQ-1736279425-1.0.1.1-mdXy_XDkelJX2.9BSuZsl5IsPRGBdcHgIMc_SRz83WcmGCYUkTm1j_f892xrJbOVheWWH9ULwCQrVESupV37Sg;
path=/; expires=Tue, 07-Jan-25 20:20:25 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=EYb4UftLm_C7qM4YT78IJt46hRSubZHKnfTXhFp6ZRU-1736279425874-0.0.1.1-604800000;
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:
- '1218'
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:
- '29999681'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_779992da2a3eb4a25f0b57905c9e8e41
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.\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 `get_final_answer` tool to fulfill the current task requirement.\n\nAction:
get_final_answer\nAction Input: {}\nObservation: 42\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:
- '1743'
content-type:
- application/json
cookie:
- _cfuvid=EYb4UftLm_C7qM4YT78IJt46hRSubZHKnfTXhFp6ZRU-1736279425874-0.0.1.1-604800000;
__cf_bm=PsMOhP_yeSFIMA.FfRlNbisoG88z4l9NSd0zfS5UrOQ-1736279425-1.0.1.1-mdXy_XDkelJX2.9BSuZsl5IsPRGBdcHgIMc_SRz83WcmGCYUkTm1j_f892xrJbOVheWWH9ULwCQrVESupV37Sg
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-An9soTDQVS0ANTzaTZeo6lYN44ZPR\",\n \"object\":
\"chat.completion\",\n \"created\": 1736279426,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now know the final answer.\\n\\nFinal
Answer: 42\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
344,\n \"completion_tokens\": 12,\n \"total_tokens\": 356,\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:
- 8fe67a0c4dbeed83-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 19:50:26 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:
- '434'
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:
- '29999598'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1184308c5a4ed9130d397fe1645f317e
http_version: HTTP/1.1
status_code: 200
version: 1