andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-01 23:32:39 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

fix: map output_pydantic/output_json to native structured output
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Details
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Details
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Details
Build uv cache / build-cache (3.10) (push) Has been cancelled
Details
Build uv cache / build-cache (3.11) (push) Has been cancelled
Details
Build uv cache / build-cache (3.12) (push) Has been cancelled
Details
Build uv cache / build-cache (3.13) (push) Has been cancelled
Details
Mark stale issues and pull requests / stale (push) Has been cancelled
Details

Browse Source 
* fix: map output_pydantic/output_json to native structured output

* test: add crew+tools+structured output integration test for Gemini

* fix: re-record stale cassette for test_crew_testing_function

* fix: re-record remaining stale cassettes for native structured output

* fix: enable native structured output for lite agent and fix mypy errors
This commit is contained in:
Greyson LaLonde
2026-02-25 17:13:34 -05:00
committed by GitHub
parent 017189db78
commit b371f97a2f
25 changed files with 3433 additions and 2173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
lib/crewai/tests/test_task.py
View File

@@ -759,11 +759,11 @@ def test_custom_converter_cls():
crew = Crew(agents=[scorer], tasks=[task])
with patch.object(
ScoreConverter, "to_pydantic", return_value=ScoreOutput(score=5)
) as mock_to_pydantic:
crew.kickoff()
mock_to_pydantic.assert_called_once()
# With native structured output, the LLM returns a BaseModel directly,
# so the converter is bypassed. Verify the output is valid instead.
result = crew.kickoff()
assert isinstance(result.pydantic, ScoreOutput)
assert isinstance(result.pydantic.score, int)
@pytest.mark.vcr()