fix(voice): preserve held STT turn boundaries - #2319
Open
Thytu wants to merge 1 commit into
Open
Conversation
🦋 Changeset detectedLatest commit: 67385f7 The changes in this PR will be included in the next version bump. This PR includes changesets to release 39 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Preserve an accepted STT turn boundary when agent speech starts between the final transcript and its
END_OF_SPEECHsentinel.The final transcript is accepted before agent speech, but the following sentinel is buffered while the agent is speaking. During the later flush, the sentinel has no transcript alternatives, so it cannot set
shouldFlushand is discarded. The user turn remains uncommitted and can be merged with later speech.Changes Made
END_OF_SPEECHwhen STT has accepted transcript text for an uncommitted turn.@livekit/agents.Pre-Review Checklist
Testing
mainwithuserTurnCommitted === falsepnpm test agents/src— 136 files passed; 2,248 tests passed; 5 skippedpnpm buildpnpm typecheckpnpm format:checkpnpm -w lint:fixAdditional Notes
The unscoped test command also runs provider/example integration tests. Locally those reported unrelated missing
OPENAI_API_KEY/CEREBRAS_API_KEY, Hugging Face download timeouts, and one FishAudio assertion. The completeagents/srcsuite passes.