fix(dflash): expose qwen reasoning in streaming and non-streaming response#124
Merged
davide221 merged 1 commit intoLuce-Org:mainfrom May 8, 2026
Merged
Conversation
…sponses Parse <think>...</think> tags from Qwen model output and expose reasoning separately: - OpenAI: reasoning_content field on the message / streaming delta - Anthropic: thinking content blocks with thinking_delta events Streaming uses a sliding-window state machine (consume_stream_piece) to detect tag boundaries across token boundaries. Respects chat_template_kwargs.enable_thinking — when disabled, tokens stream as plain content without tag parsing.
jkyamog
changed the title
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
Contributor
|
@jkyamog thanks for your first contribution 🚀 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
First off thank you for making this project. I have been using for the past week, in particular on open-webui. I noticed the opening tag is missing. I did ask codex and reviewed by claude to implement a fix. I guess the streaming implementation is a bit more complex that its a state machine.
Here is the summary of the implementation: