fix: handle thinking model responses in /api/chat endpoint#764
Merged
Lightheartdevs merged 1 commit intoLight-Heart-Labs:mainfrom Apr 3, 2026
Merged
Conversation
Increase max_tokens from 256 to 2048 so thinking models (Qwen3.5) have enough tokens to complete their reasoning phase and produce actual content. Strip <think>...</think> tags from response text. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Fix
/api/chatreturning empty responses when a thinking model (e.g., Qwen3.5) is loaded.Why
Thinking models generate
<think>...</think>blocks before producing actual content. Withmax_tokens: 256, the model exhausts its token budget on the reasoning phase and never produces visible output —contentis always empty string.How
max_tokensfrom 256 to 2048 (bounded by existing 30s HTTP timeout)<think>...</think>tags from response text via regex (safe, no ReDoS risk — fixed delimiters with lazy quantifier)Testing
python -m py_compilepassesPlatform Impact
🤖 Generated with Claude Code