Change thought_in_content to False #1230
Open
Conversation
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
Update `thought_in_content` so it no longer affects tool call parsing.
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Outdated suggestions cannot be applied.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
According to Qwen-Agent’s README, the
thought_in_contentparameter affects tool-calling behavior.When testing Qwen3-4B-Think, I noticed that tool calls are returned as
<tool_call>tags embedded in the content rather than underapi_response["choices"][0]["message"]["tools"], as expected by_parse_query_response_FC(see reference).
Changes
Updated parsing logic to handle tool calls embedded in content.
Ensured compatibility when
thought_in_content=True.Prevented incorrect tool-call extraction for Qwen3-4B-Think responses.
Impact
Fixes leaderboard scoring for Qwen3-4B-Think.
Aligns parsing behavior with Qwen-Agent’s documented API.
Improves evaluation consistency across Qwen-Thinking models.
Testing
Verified with local benchmark runs using Qwen3-4B-Think.
Confirmed tool calls are correctly parsed and scored.