Fix: Apply additional_drop_params filtering across all LLM providers

[devin-ai-integration]

Fix: Apply additional_drop_params filtering across all LLM providers

Summary

Fixes issue #3814 where the additional_drop_params parameter was being ignored when LLM was used within an Agent. This parameter is critical for reasoning models (o1-mini, o4-mini) that don't support certain parameters like "stop".

Root cause: The parameter filtering logic was missing from _prepare_completion_params() methods across all LLM providers (LiteLLM fallback path and native providers for OpenAI, Azure, Anthropic).

Solution:

• Added centralized _apply_additional_drop_params() helper method in BaseLLM class
• Applied filtering consistently in all provider implementations
• Maintained backwards compatibility with misspelled drop_additionnal_params parameter

Review & Testing Checklist for Human

⚠️ Critical - Manual testing needed with actual API calls:

• Test with a reasoning model (e.g., o1-mini) that rejects the "stop" parameter, both with and without additional_drop_params=["stop"]
• Verify the fix works specifically when LLM is used within an Agent (the original bug scenario from issue [BUG] drop_additionnal_params parameter ignored when working with agents #3814)
• Test that normal (non-reasoning) models still work correctly and aren't affected by this change
• Confirm backwards compatibility: verify that drop_additionnal_params (misspelled variant) still works if it's being used in production

Why manual testing is important: The automated tests use extensive mocking and don't make actual API calls, so they verify the filtering logic but not end-to-end behavior with real LLM providers.

Notes

• CI checks all passed (tests, type-checker, lint)
• Added 4 comprehensive unit tests covering different scenarios
• The helper method creates a copy of params before filtering to avoid mutation issues
• Link to Devin session: https://app.devin.ai/sessions/e78611892fa144358e558d23c4a5feac
• Requested by: João (joao@crewai.com)

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring