Merged
Conversation
- Add separate Qwen thinking filter (insideThinking=false, detects <think> opening tag) - Always apply thinking filter for models that may generate thinking (Qwen, DeepSeek, Gemma 4) - Strip ThinkingResponse when isThinking=false - Add Qwen3 thinking support to README and model config - Bump version to 0.13.5
- Rewrite DeepSeek and Qwen stream filters with buffer pattern (like Gemma 4) - Handle partial <think>/</think> tags split across token boundaries - Add unit tests for partial tag split cases (DeepSeek + Qwen) - Add Qwen2.5 passthrough test (no thinking tags)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
<think>blocks by default — now stripped whenisThinking: falseinsideThinking=false, detects opening<think>tag) — safe for Qwen2.5 which doesn't generate thinkingThinkingResponsewhen user didn't request itTested on 6 models × 2 modes = 12 tests passed (Qwen3, Qwen2.5, Gemma4 E2B, Gemma3 1B, Gemma3n E2B, FunctionGemma 270M)
Closes #224