Files
crewAI/lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml
Greyson LaLonde e134e5305b Gl/feat/a2a refactor (#3793)
* feat: agent metaclass, refactor a2a to wrappers

* feat: a2a schemas and utils

* chore: move agent class, update imports

* refactor: organize imports to avoid circularity, add a2a to console

* feat: pass response_model through call chain

* feat: add standard openapi spec serialization to tools and structured output

* feat: a2a events

* chore: add a2a to pyproject

* docs: minimal base for learn docs

* fix: adjust a2a conversation flow, allow llm to decide exit until max_retries

* fix: inject agent skills into initial prompt

* fix: format agent card as json in prompt

* refactor: simplify A2A agent prompt formatting and improve skill display

* chore: wide cleanup

* chore: cleanup logic, add auth cache, use json for messages in prompt

* chore: update docs

* fix: doc snippets formatting

* feat: optimize A2A agent card fetching and improve error reporting

* chore: move imports to top of file

* chore: refactor hasattr check

* chore: add httpx-auth, update lockfile

* feat: create base public api

* chore: cleanup modules, add docstrings, types

* fix: exclude extra fields in prompt

* chore: update docs

* tests: update to correct import

* chore: lint for ruff, add missing import

* fix: tweak openai streaming logic for response model

* tests: add reimport for test

* tests: add reimport for test

* fix: don't set a2a attr if not set

* fix: don't set a2a attr if not set

* chore: update cassettes

* tests: fix tests

* fix: use instructor and dont pass response_format for litellm

* chore: consolidate event listeners, add typing

* fix: address race condition in test, update cassettes

* tests: add correct mocks, rerun cassette for json

* tests: update cassette

* chore: regenerate cassette after new run

* fix: make token manager access-safe

* fix: make token manager access-safe

* merge

* chore: update test and cassete for output pydantic

* fix: tweak to disallow deadlock

* chore: linter

* fix: adjust event ordering for threading

* fix: use conditional for batch check

* tests: tweak for emission

* tests: simplify api + event check

* fix: ensure non-function calling llms see json formatted string

* tests: tweak message comparison

* fix: use internal instructor for litellm structure responses

---------

Co-authored-by: Mike Plachta <mike@crewai.com>
2025-10-31 18:42:03 -07:00

690 lines
30 KiB
YAML

interactions:
- request:
body: '{"trace_id": "e97144c4-2bdc-48ac-bbe5-59e4d9814c49", "execution_type":
"crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
"crew_name": "crew", "flow_name": null, "crewai_version": "1.2.1", "privacy_level":
"standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-31T07:44:22.182046+00:00"},
"ephemeral_trace_id": "e97144c4-2bdc-48ac-bbe5-59e4d9814c49"}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '488'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/1.2.1
X-Crewai-Organization-Id:
- 73c2b193-f579-422c-84c7-76a39a1da77f
X-Crewai-Version:
- 1.2.1
method: POST
uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches
response:
body:
string: '{"id":"dfc603d5-afb3-49bb-808c-dfae122dde9d","ephemeral_trace_id":"e97144c4-2bdc-48ac-bbe5-59e4d9814c49","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.2.1","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.2.1","privacy_level":"standard"},"created_at":"2025-10-31T07:44:22.756Z","updated_at":"2025-10-31T07:44:22.756Z","access_code":"TRACE-0d13ac15e6","user_identifier":null}'
headers:
Connection:
- keep-alive
Content-Length:
- '515'
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 31 Oct 2025 07:44:22 GMT
cache-control:
- no-store
content-security-policy:
- 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self''
''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts
https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com
https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/
https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net
https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net
https://js.hscollectedforms.net https://js.usemessages.com https://snap.licdn.com
https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com
https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com
app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data:
*.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com
https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com
https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com
https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com;
connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com
https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/*
https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io
https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com
https://api.hubspot.com https://forms.hscollectedforms.net https://api.hubapi.com
https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509
https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect
https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self''
*.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com
https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com
https://drive.google.com https://slides.google.com https://accounts.google.com
https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/
https://www.youtube.com https://share.descript.com'
etag:
- W/"c886631dcc4aae274f1bdcfb3b17fb01"
expires:
- '0'
permissions-policy:
- camera=(), microphone=(self), geolocation=()
pragma:
- no-cache
referrer-policy:
- strict-origin-when-cross-origin
strict-transport-security:
- max-age=63072000; includeSubDomains
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- 9b9d1dac-6f4b-455b-8be9-fa8bb0c85a4f
x-runtime:
- '0.073038'
x-xss-protection:
- 1; mode=block
status:
code: 201
message: Created
- request:
body: '{"messages":[{"role":"system","content":"You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
want them to do, and ALL necessary context to execute the task, they know nothing
about the task, so share absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolutely everything you know, don''t
reference things but instead explain them.\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 [Delegate work to coworker, Ask question
to coworker], 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: Give me an integer
score between 1-5 for the following title: ''The impact of AI in the future
of work''\n\nThis is the expected criteria for your final answer: The score
of the title.\nyou MUST return the actual complete content as the final answer,
not a summary.\nEnsure your final answer contains only the content in the following
format: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\":
\"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\":
\"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nEnsure
the final output does not include any code block markers like ```json or ```python.\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3379'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.109.1
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.10
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 997186dc6d3aea38-FCO
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 07:44:26 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=n45oVEbg4Ph05GBqJp2KyKI77cF1e_lNGmWrdQjbV20-1761896666-1.0.1.1-hTLlylCKTisapDYTpS63zm.2k2AGNs0DvyKGQ6MEtJHyYJBoXKqzsHRbsZN_dbtjm4Kj_5RG3J73ysTSs817q_9mvPtjHgZOvOPhDwGxV_M;
path=/; expires=Fri, 31-Oct-25 08:14:26 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=gOhnFtutoiWlRm84LU88kCfEmlv5P_3_ZJ_wlDnkYy4-1761896666288-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '3152'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '3196'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999195'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_5011a1ac60f3411f9164a03bedad1bc5
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent
Task: Evaluate and provide an integer score between 1-5 for the title ''The
impact of AI in the future of work''. Consider factors such as relevance, clarity,
engagement, and potential impact of the title.\n\nThis is the expected criteria
for your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nThis
score will be used to assess the quality of the title in terms of its relevance
and impact.\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-4.1-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1222'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.109.1
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.10
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 997186f4ef56dd1f-FCO
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 07:44:28 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=8qRmqHic3PKOkCdnlc5s2fTHlZ8fBzfDa2aJ.xrQBBg-1761896668-1.0.1.1-JIBosm31AwPEXmz19O636o_doSclt_nENWvAfvp_gbjWPtfO2e99BjAvWJsUWjHVZGRlO6DJILFTRbA7iKdYGQykSCe_mj9a9644nS5E6VA;
path=/; expires=Fri, 31-Oct-25 08:14:28 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=TlYX1UMlEMLrIXQ.QBUJAS4tT0N5uBkshUKYyJjd9.g-1761896668679-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '2019'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2126'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-tokens:
- '150000000'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-project-tokens:
- '149999720'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999720'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_019c6c76f5414041b69f973973952df4
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Crew Manager. You are
a seasoned manager with a knack for getting the best out of your team.\nYou
are also known for your ability to delegate work to the right people, and to
ask the right questions to get the best out of your team.\nEven though you don''t
perform tasks by yourself, you have a lot of experience in the field, which
allows you to properly evaluate the work of your team members.\nYour personal
goal is: Manage the team to complete the task in the best way possible.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate a specific task to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
want them to do, and ALL necessary context to execute the task, they know nothing
about the task, so share absolutely everything you know, don''t reference things
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
''str''}}\nTool Description: Ask a specific question to one of the following
coworkers: Scorer\nThe input to this tool should be the coworker, the question
you have for them, and ALL necessary context to ask the question properly, they
know nothing about the question, so share absolutely everything you know, don''t
reference things but instead explain them.\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 [Delegate work to coworker, Ask question
to coworker], 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: Give me an integer
score between 1-5 for the following title: ''The impact of AI in the future
of work''\n\nThis is the expected criteria for your final answer: The score
of the title.\nyou MUST return the actual complete content as the final answer,
not a summary.\nEnsure your final answer contains only the content in the following
format: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\":
\"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\":
\"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nEnsure
the final output does not include any code block markers like ```json or ```python.\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":"To
complete the task, I need to delegate the scoring of the title ''The impact
of AI in the future of work'' to the Scorer. \n\nAction: Delegate work to coworker\nAction
Input: {\"task\": \"Evaluate and provide an integer score between 1-5 for the
title ''The impact of AI in the future of work''. Consider factors such as relevance,
clarity, engagement, and potential impact of the title.\", \"context\": \"This
score will be used to assess the quality of the title in terms of its relevance
and impact.\", \"coworker\": \"Scorer\"}\nObservation: I would score the title
\"The impact of AI in the future of work\" a 4 out of 5. The title is highly
relevant given the increasing role of AI in shaping workplaces and job markets.
It is clear and straightforward in communicating the topic, making it easy for
audiences to understand the focus at a glance. The engagement level is solid,
as AI and future work dynamics attract broad interest across industries. However,
the title could be slightly more compelling by adding specifics or a provocative
element to enhance its potential impact, such as mentioning specific sectors
or challenges. Overall, it is a strong, relevant, and clear title with potential
for broad impact, hence a 4 instead of a perfect 5."}],"model":"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '4667'
content-type:
- application/json
cookie:
- __cf_bm=n45oVEbg4Ph05GBqJp2KyKI77cF1e_lNGmWrdQjbV20-1761896666-1.0.1.1-hTLlylCKTisapDYTpS63zm.2k2AGNs0DvyKGQ6MEtJHyYJBoXKqzsHRbsZN_dbtjm4Kj_5RG3J73ysTSs817q_9mvPtjHgZOvOPhDwGxV_M;
_cfuvid=gOhnFtutoiWlRm84LU88kCfEmlv5P_3_ZJ_wlDnkYy4-1761896666288-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.109.1
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.10
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 997187038d85ea38-FCO
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 07:44:29 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '740'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '772'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998885'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_5c525e6992a14138826044dd5a2becf9
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"Please convert the following text
into valid JSON.\n\nOutput ONLY the valid JSON and nothing else.\n\nThe JSON
must follow this schema exactly:\n```json\n{\n score: int\n}\n```"},{"role":"user","content":"{\n \"properties\":
{\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\":
[\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\":
false\n}"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '779'
content-type:
- application/json
cookie:
- __cf_bm=n45oVEbg4Ph05GBqJp2KyKI77cF1e_lNGmWrdQjbV20-1761896666-1.0.1.1-hTLlylCKTisapDYTpS63zm.2k2AGNs0DvyKGQ6MEtJHyYJBoXKqzsHRbsZN_dbtjm4Kj_5RG3J73ysTSs817q_9mvPtjHgZOvOPhDwGxV_M;
_cfuvid=gOhnFtutoiWlRm84LU88kCfEmlv5P_3_ZJ_wlDnkYy4-1761896666288-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-helper-method:
- chat.completions.parse
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.109.1
x-stainless-read-timeout:
- '600'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.10
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAAwAAAP//jJJBj9MwEIXv+RXWnBuUljZNc13BAXFDYgXsKnLtSWpwPJY9QUDV/46c
dJssLBIXH/zNG783nnMmBBgNtQB1kqx6b/O7eywP4dMv87548/mePn7A4a6qlHz91r0LsEoKOn5F
xU+qV4p6b5ENuQmrgJIxdV3vy3V1KMvyMIKeNNok6zznW8o3xWabF1VelFfhiYzCCLX4kgkhxHk8
k0Wn8QfUolg93fQYo+wQ6luREBDIphuQMZrI0jGsZqjIMbrR9fkBoqKAD1AXl2VNwHaIMll0g7UL
IJ0jlini6O7xSi43P5Y6H+gY/5BCa5yJpyagjOTS25HJw0gvmRCPY+7hWRTwgXrPDdM3HJ9bb/dT
P5gnPdPdlTGxtAvRbrN6oV2jkaWxcTE4UFKdUM/Secpy0IYWIFuE/tvMS72n4MZ1/9N+BkqhZ9SN
D6iNeh54LguY9vBfZbchj4YhYvhuFDZsMKSP0NjKwU4rAvFnZOyb1rgOgw9m2pPWN+rYrvfVblfu
IbtkvwEAAP//AwCH29h7MAMAAA==
headers:
CF-RAY:
- 997187099d02ea38-FCO
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 07:44:30 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '409'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '447'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-requests:
- '10000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-requests:
- '9999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999903'
x-ratelimit-reset-project-requests:
- 6ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c1d2e65ce5244e49bbc31969732c9b54
status:
code: 200
message: OK
version: 1