Files
crewAI/lib/crewai/tests/llms
Lorenze Jay 19ce56032c fix: improve output handling and response model integration in agents (#4307)
* fix: improve output handling and response model integration in agents

- Refactored output handling in the Agent class to ensure proper conversion and formatting of outputs, including support for BaseModel instances.
- Enhanced the AgentExecutor class to correctly utilize response models during execution, improving the handling of structured outputs.
- Updated the Gemini and Anthropic completion providers to ensure compatibility with new response model handling, including the addition of strict mode for function definitions.
- Improved the OpenAI completion provider to enforce strict adherence to function schemas.
- Adjusted translations to clarify instructions regarding output formatting and schema adherence.

* drop what was a print that didnt get deleted properly

* fixes gemini

* azure working

* bedrock works

* added tests

* adjust test

* fix tests and regen

* fix tests and regen

* refactor: ensure stop words are applied correctly in Azure, Gemini, and OpenAI completions; add tests to validate behavior with structured outputs

* linting
2026-01-30 12:27:46 -08:00
..
2025-12-01 18:56:56 -05:00
2025-10-20 14:10:19 -07:00