Fix provider reasoning follow-ups for Anthropic, Gemini, and OpenRouter#269
Merged
Fix provider reasoning follow-ups for Anthropic, Gemini, and OpenRouter#269
Conversation
OpenAI follow-up work uncovered provider-specific drift elsewhere: OpenRouter could leak reasoning_effort at the wrong request level, Anthropic thinking requests still sent incompatible parameters, and Gemini was not preserving native thought summaries or function-call signatures. This change keeps provider-native thinking visible without faking normal progress as reasoning. Constraint: Preserve visible execution text as content and only surface provider-native reasoning as thinking. Rejected: Faking progress text as thinking; silently dropping Gemini function-call signatures. Confidence: medium-high. Scope-risk: medium. Reversibility: revert the commit. Directive: align OpenRouter, Anthropic, and Gemini reasoning/thinking handling with current provider APIs. Tested: PYTHONPATH=C:\Users\Ricky\Documents\Project\XSpoonAi\core .venv\Scripts\python.exe -m pytest core/tests/test_tool_streaming_output.py -q; PYTHONPATH=C:\Users\Ricky\Documents\Project\XSpoonAi\core .venv\Scripts\python.exe -m pytest core/tests/test_agent_llm_integration.py -k "preserves_tool_call_metadata_in_memory or forwards_reasoning_effort_to_llm or run_signatures_accept_reasoning_kwargs" -q. Not-tested: live Anthropic/Gemini network calls. Related: spoon-bot reasoning-effort config/gateway PR.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Verification
PYTHONPATH=C:\Users\Ricky\Documents\Project\XSpoonAi\core .venv\Scripts\python.exe -m pytest core/tests/test_tool_streaming_output.py -qPYTHONPATH=C:\Users\Ricky\Documents\Project\XSpoonAi\core .venv\Scripts\python.exe -m pytest core/tests/test_agent_llm_integration.py -k "preserves_tool_call_metadata_in_memory or forwards_reasoning_effort_to_llm or run_signatures_accept_reasoning_kwargs" -qNotes