fix: handle Qwen models putting response in reasoning_content#84
Open
ihfazhillah wants to merge 1 commit into
Open
fix: handle Qwen models putting response in reasoning_content#84ihfazhillah wants to merge 1 commit into
ihfazhillah wants to merge 1 commit into
Conversation
When Qwen models run via llama.cpp without --reasoning, they put the entire response in reasoning_content with empty content field. Add fallback in both llm_loop.py and llm_client.py to treat reasoning_text as the actual response content when content is empty and no tool calls.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When Qwen models run via llama.cpp without --reasoning, they put the entire response in reasoning_content with an empty content field.
This adds a fallback in both llm_loop.py and llm_client.py to treat reasoning_text as the actual response content when:
This fixes silent failures where agents using certain Qwen models appear to not respond.