andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-11 00:58:30 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Feat/individual react agent (#2483)

Browse Source 
* WIP

* WIP

* wip

* wip

* WIP

* More WIP

* Its working but needs a massive clean up

* output type works now

* Usage metrics fixed

* more testing

* WIP

* cleaning up

* Update logger

* 99% done. Need to make docs match new example

* cleanup

* drop hard coded examples

* docs

* Clean up

* Fix errors

* Trying to fix CI issues

* more type checker fixes

* More type checking fixes

* Update LiteAgent documentation for clarity and consistency; replace WebsiteSearchTool with SerperDevTool, and improve formatting in examples.

* fix fingerprinting issues

* fix type-checker

* Fix type-checker issue by adding type ignore comment for cache read in ToolUsage class

* Add optional agent parameter to CrewAgentParser and enhance action handling logic

* Remove unused parameters from ToolUsage instantiation in tests and clean up debug print statement in CrewAgentParser.

* Remove deprecated test files and examples for LiteAgent; add comprehensive tests for LiteAgent functionality, including tool usage and structured output handling.

* Remove unused variable 'result' from ToolUsage class to clean up code.

* Add initialization for 'result' variable in ToolUsage class to resolve type-checker warnings

* Refactor agent_utils.py by removing unused event imports and adding missing commas in function definitions. Update test_events.py to reflect changes in expected event counts and adjust assertions accordingly. Modify test_tools_emits_error_events.yaml to include new headers and update response content for consistency with recent API changes.

* Enhance tests in crew_test.py by verifying cache behavior in test_tools_with_custom_caching and ensuring proper agent initialization with added commas in test_crew_kickoff_for_each_works_with_manager_agent_copy.

* Update agent tests to reflect changes in expected call counts and improve response formatting in YAML cassette. Adjusted mock call count from 2 to 3 and refined interaction formats for clarity and consistency.

* Refactor agent tests to update model versions and improve response formatting in YAML cassettes. Changed model references from 'o1-preview' to 'o3-mini' and adjusted interaction formats for consistency. Enhanced error handling in context length tests and refined mock setups for better clarity.

* Update tool usage logging to ensure tool arguments are consistently formatted as strings. Adjust agent test cases to reflect changes in maximum iterations and expected outputs, enhancing clarity in assertions. Update YAML cassettes to align with new response formats and improve overall consistency across tests.

* Update YAML cassette for LLM tests to reflect changes in response structure and model version. Adjusted request and response headers, including updated content length and user agent. Enhanced token limits and request counts for improved testing accuracy.

* Update tool usage logging to store tool arguments as native types instead of strings, enhancing data integrity and usability.

* Refactor agent tests by removing outdated test cases and updating YAML cassettes to reflect changes in tool usage and response formats. Adjusted request and response headers, including user agent and content length, for improved accuracy in testing. Enhanced interaction formats for consistency across tests.

* Add Excalidraw diagram file for visual representation of input-output flow

Created a new Excalidraw file that includes a diagram illustrating the input box, database, and output box with connecting arrows. This visual aid enhances understanding of the data flow within the application.

* Remove redundant error handling for action and final answer in CrewAgentParser. Update tests to reflect this change by deleting the corresponding test case.

---------

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
This commit is contained in:
Brandon Hancock (bhancock_ai)
2025-04-02 11:54:46 -04:00
committed by GitHub
parent 9b51e1174c
commit efe27bd570
42 changed files with 21642 additions and 12531 deletions
Download Patch File Download Diff File Expand all files Collapse all files

351
tests/cassettes/test_agent_custom_max_iterations.yaml
View File

@@ -4,37 +4,35 @@ interactions:
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}'
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\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.\n\nThis is the expected 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:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1377'
- '1433'
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
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
@@ -44,35 +42,36 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
- 3.12.8
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
content: "{\n \"id\": \"chatcmpl-BHHw5WtswO316yaGO5yKxTcNv36eN\",\n \"object\":
\"chat.completion\",\n \"created\": 1743460221,\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"
tool to obtain the final answer as instructed.\\n\\nAction: get_final_answer\\nAction
Input: {}\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\": 31,\n
\ \"total_tokens\": 322,\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 \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_6dd05565ef\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fe67a03ce78ed83-ATL
- 92934a709920cecd-SJC
Connection:
- keep-alive
Content-Encoding:
@@ -80,14 +79,14 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 19:50:25 GMT
- Mon, 31 Mar 2025 22:30:22 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;
- __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4;
path=/; expires=Mon, 31-Mar-25 23:00:22 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=EYb4UftLm_C7qM4YT78IJt46hRSubZHKnfTXhFp6ZRU-1736279425874-0.0.1.1-604800000;
- _cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
@@ -97,71 +96,111 @@ interactions:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1218'
- '743'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '50000'
x-ratelimit-limit-tokens:
- '30000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '49999'
x-ratelimit-remaining-tokens:
- '29999681'
- '149999678'
x-ratelimit-reset-requests:
- 6ms
- 1ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_779992da2a3eb4a25f0b57905c9e8e41
- req_3bc6d00e79c88c43349084dec6d3161a
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtQBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSqwEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKUAQoQhmbMXvkscEn7a8wc0RdvihIIHFSkAKvHFKcqClRvb2wgVXNhZ2UwATmANCzE
1QMyGEGo00HE1QMyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSh8KCXRvb2xfbmFtZRIS
ChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '215'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.31.1
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 31 Mar 2025 22:30:22 GMT
status:
code: 200
message: OK
- 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}'
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\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 JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\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.\n\nThis is the expected 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": "42"}, {"role": "assistant",
"content": "Thought: I need to use the `get_final_answer` tool to obtain the
final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer`
tool to obtain the final answer as instructed.\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:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1743'
- '2033'
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
- __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4;
_cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
@@ -171,34 +210,35 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
- 3.12.8
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
content: "{\n \"id\": \"chatcmpl-BHHw65c6KgrmeCstyFwRSEyHyvlCI\",\n \"object\":
\"chat.completion\",\n \"created\": 1743460222,\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"
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 42\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 407,\n \"completion_tokens\": 15,\n
\ \"total_tokens\": 422,\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 \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_6dd05565ef\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fe67a0c4dbeed83-ATL
- 92934a761887cecd-SJC
Connection:
- keep-alive
Content-Encoding:
@@ -206,7 +246,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 07 Jan 2025 19:50:26 GMT
- Mon, 31 Mar 2025 22:30:23 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -217,28 +257,157 @@ interactions:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '434'
- '586'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '50000'
x-ratelimit-limit-tokens:
- '30000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '49999'
x-ratelimit-remaining-tokens:
- '29999598'
- '149999556'
x-ratelimit-reset-requests:
- 6ms
- 1ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1184308c5a4ed9130d397fe1645f317e
- req_5721f8ae85f6db2a8d622756c9c590e0
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\nIMPORTANT: Use the following format
in your response:\n\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 JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\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.\n\nThis is the expected 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": "42"}, {"role": "assistant",
"content": "Thought: I need to use the `get_final_answer` tool to obtain the
final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer`
tool to obtain the final answer as instructed.\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:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '2033'
content-type:
- application/json
cookie:
- __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4;
_cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BHHw7R16wjU2hKaUpPLQNnbUVZNg9\",\n \"object\":
\"chat.completion\",\n \"created\": 1743460223,\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: The final answer is 42.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 407,\n \"completion_tokens\":
20,\n \"total_tokens\": 427,\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 \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_6dd05565ef\"\n}\n"
headers:
CF-RAY:
- 92934a7a4d30cecd-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 22:30:23 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '649'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '50000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '49999'
x-ratelimit-remaining-tokens:
- '149999556'
x-ratelimit-reset-requests:
- 1ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_dd1a4cd09c8f157847d2a9d306d354ef
http_version: HTTP/1.1
status_code: 200
version: 1