feat: add item_id to UserInputTranscribedEvent for per-utterance dedup#6247
Open
C1-BA-B1-F3 wants to merge 1 commit into
Open
feat: add item_id to UserInputTranscribedEvent for per-utterance dedup#6247C1-BA-B1-F3 wants to merge 1 commit into
C1-BA-B1-F3 wants to merge 1 commit into
Conversation
Add an optional `item_id` field to `UserInputTranscribedEvent` so callers can group interim and final transcription results belonging to the same utterance. - For realtime models: populated from `InputTranscriptionCompleted.item_id` - For STT pipelines: populated from `SpeechEvent.request_id` - Defaults to `None` when no upstream identifier is available Fixes livekit#6109
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
UserInputTranscribedEventdoesn't include any identifier for the utterance being transcribed. This makes it impossible for callers to deduplicate interim transcription results or correlate a final transcript back to its preceding interim updates.Fixes #6109
Solution
Add an optional
item_idfield toUserInputTranscribedEvent:InputTranscriptionCompleted.item_idSpeechEvent.request_idNonewhen no upstream identifier is available (e.g. IVR, speech-stopped events)Changes
events.py: Additem_id: str | None = Nonefield with docstringagent_activity.py: Populateitem_idin all three event creation sitesTesting
All 78 existing tests pass.