Devin AI aa82ca5273 Fix Ollama models ValueError when response_format is used ...

- Add _is_ollama_model method to detect Ollama models consistently
- Skip response_format validation for Ollama models in _validate_call_params
- Filter out response_format parameter for Ollama models in _prepare_completion_params
- Add comprehensive tests for Ollama response_format handling
- Maintain backward compatibility for other LLM providers

Fixes #3082

Co-Authored-By: João <joao@crewai.com>

2025-06-28 21:32:30 +00:00

74 KiB

Raw Blame History

View Raw