fix(serve): filter <think> output and support speaking interruption#132
Merged
fix(serve): filter <think> output and support speaking interruption#132
Conversation
Filter model <think> blocks from streamed output before appending assistant text or sending sentence chunks to TTS, so reasoning text is never spoken.\n\nKeep speech recognition active during assistant speaking and add turn-id guards to prevent stale async turns from restoring an incorrect state. This allows reliable barge-in interruption and avoids getting stuck in speaking.\n\nAlso add a demo-page regression assertion for think filtering.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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>...</think>content from assistant visible text and TTS sentence chunksspeakingso users can barge in while assistant audio is playingspeakingstateValidation
cargo test serve::tests -- --nocapture<think>):第一句。/第二句。to WS (no think text){"type":"cancel"}and starts second LLM call (LLM_CALLS=2)listening…User-visible Fixes