fix: emit tool_call_end events for any finish_reason (Kimi K2 fix) #10236
+16
−6
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Outdated suggestions cannot be applied.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.
This PR attempts to address Issue #9551 regarding Kimi K2 Thinking native tool calls not working properly with OpenAI-compatible servers like ik_llama.cpp.
Problem
The original PR #9557 could not be applied to the current codebase because the code has been significantly refactored. Tool call handling now uses
NativeToolCallParserinstead of the originaltoolCallAccumulatorpattern.Solution
Modified
NativeToolCallParser.processFinishReason()to emittool_call_endevents when ANYfinish_reasonis present and there are tracked tool calls that have started, not just whenfinish_reason === "tool_calls".This ensures compatibility with various OpenAI-compatible servers including ik_llama.cpp that may send finish_reason values like
"stop"instead of"tool_calls"when tool calls are made.Changes
processFinishReason()insrc/core/assistant-message/NativeToolCallParser.tstracked.hasStartedto only emit end events for tool calls that have actually startedTesting
Feedback and guidance are welcome!