Files
crewAI/lib/crewai/tests/cassettes/test_output_pydantic_sequential.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

439 lines
15 KiB
YAML

interactions:
- 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 use 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: 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 expect criteria
for your final answer: The score of the title.\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '915'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_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-AB7frQCjT9BcDGcDj4QyiHzmwbFSt\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214471,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer\\nFinal
Answer: 4\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
186,\n \"completion_tokens\": 13,\n \"total_tokens\": 199,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9af4ef31cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:52 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:
- '170'
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:
- '29999781'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c024216dd5260be75d28056c46183b74
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON.\n\nThe json should have the
following structure, with the following keys:\n{\n score: int\n}"}], "model":
"gpt-4o", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
"tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
"Correctly extracted `ScoreOutput` with all the required parameters with correct
types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
"required": ["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '615'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_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-AB7fsjohZBgZL7M0zgaX4R7BxjHuT\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214472,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_MzP98lapLUxbi46aCd9gP0Mf\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n
\ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
100,\n \"completion_tokens\": 5,\n \"total_tokens\": 105,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f9b2fc671cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:47:52 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:
- '163'
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:
- '29999947'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d24b98d762df8198d3d365639be80fe4
http_version: HTTP/1.1
status_code: 200
- 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":"4"}],"model":"gpt-4.1-mini"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '277'
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 |
H4sIAAAAAAAAA4yST2+cMBDF73wKa85LBITsEm5VKvWUQ0/9RwReM7BOzdi1TbXVar97ZdgspE2l
XjjMb97w3nhOEWMgWygZiAP3YjAqfvj0+ajl7iM9dI9ff2w5T+Rx3+fvvjx+OL6HTVDo/TMK/6K6
EXowCr3UNGNhkXsMU9PdNi12t0lRTGDQLaog642P85s0HiTJOEuyuzjJ4zS/yA9aCnRQsm8RY4yd
pm8wSi0eoWTJ5qUyoHO8RyivTYyB1SpUgDsnnefkYbNAockjTd6bpnl2mio6VRRYBU5oixWULK/o
XFHTNGupxW50PPinUakV4ETa85B/Mv10IeerTaV7Y/Xe/SGFTpJ0h9oid5qCJee1gYmeI8aepnWM
rxKCsXowvvb6O06/y+/ncbC8wgLT2wv02nO11LfZ5o1pdYueS+VW6wTBxQHbRbnsno+t1CsQrTL/
beat2XNuSf3/jF+AEGg8trWx2ErxOvDSZjHc6L/arjueDIND+1MKrL1EG96hxY6Paj4ccL+cx6Hu
JPVojZXz9XSmzkVW3KVdsc0gOke/AQAA//8DAILgqohMAwAA
headers:
CF-RAY:
- 996f4750dfd259cb-MXP
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 01:11:28 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=NFLqe8oMW.d350lBeNJ9PQDQM.Rj0B9eCRBNNKM18qg-1761873088-1.0.1.1-Ipgawg95icfLAihgKfper9rYrjt3ZrKVSv_9lKRqJzx.FBfkZrcDqSW3Zt7TiktUIOSgO9JpX3Ia3Fu9g3DMTwWpaGJtoOj3u0I2USV9.qQ;
path=/; expires=Fri, 31-Oct-25 01:41:28 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=dQQqd3jb3DFD.LOIZmhxylJs2Rzp3rGIU3yFiaKkBls-1761873088861-0.0.1.1-604800000;
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:
- '481'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '570'
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:
- '149999952'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999955'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_1b331f2fb8d943249e9c336608e2f2cf
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":"4"}],"model":"gpt-4.1-mini","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:
- '541'
content-type:
- application/json
cookie:
- __cf_bm=NFLqe8oMW.d350lBeNJ9PQDQM.Rj0B9eCRBNNKM18qg-1761873088-1.0.1.1-Ipgawg95icfLAihgKfper9rYrjt3ZrKVSv_9lKRqJzx.FBfkZrcDqSW3Zt7TiktUIOSgO9JpX3Ia3Fu9g3DMTwWpaGJtoOj3u0I2USV9.qQ;
_cfuvid=dQQqd3jb3DFD.LOIZmhxylJs2Rzp3rGIU3yFiaKkBls-1761873088861-0.0.1.1-604800000
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//jFLLbtswELzrK4g9W4HlyI6sWx8IeuulQIs2gUCTK4kpRRLkKnBg+N8L
SrYl5wH0osPOznBmtIeEMVASSgai5SQ6p9MvP3/t3Tf6JFX79ffL04/b5+/Z/X672zT55x4WkWF3
TyjozLoRtnMaSVkzwsIjJ4yq2d0mK+5ul8V2ADorUUda4yjNb7K0U0alq+VqnS7zNMtP9NYqgQFK
9idhjLHD8I1GjcQ9lGy5OE86DIE3COVliTHwVscJ8BBUIG4IFhMorCE0g/fDAwRhPT5AmR/nOx7r
PvBo1PRazwBujCUegw7uHk/I8eJH28Z5uwuvqFAro0JbeeTBmvh2IOtgQI8JY49D7v4qCjhvO0cV
2b84PFesRzmY6p7AM0aWuJ7G21NV12KVROJKh1ltILhoUU7MqWPeS2VnQDKL/NbLe9pjbGWa/5Gf
ACHQEcrKeZRKXOed1jzGW/xo7VLxYBgC+mclsCKFPv4GiTXv9XggEF4CYVfVyjTonVfjldSuysWq
WGd1sVlBckz+AQAA//8DAKv/0dE0AwAA
headers:
CF-RAY:
- 996f4755989559cb-MXP
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 31 Oct 2025 01:11:29 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:
- '400'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '659'
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:
- '149999955'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999955'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7829900551634a0db8009042f31db7fc
status:
code: 200
message: OK
version: 1