fix(core): reset user away timer on final STT transcript AGT-3149#6478
Merged
chenghao-mou merged 1 commit intoJul 18, 2026
Merged
Conversation
When VAD misses speech, STT can still emit a final transcript while the user stays listening; refresh the away timeout without changing state. Co-authored-by: Cursor <cursoragent@cursor.com>
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
theomonnom
approved these changes
Jul 18, 2026
chenghao-mou
deleted the
chenghao/agt-3149-reset-away-on-final-transcript
branch
July 18, 2026 20:45
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
VAD can miss speech while STT still emits a final transcript. In that case the user stays
listening, so the away timer kept counting down and could fire despite recent STT activity. Observed from a user session where short utterance was ignored by the timer.On a final transcript when the user is not already speaking, refresh
user_away_timeoutwithout changing user state. The existingaway→listeningrecovery path is unchanged.Made with Cursor