Repository navigation
feat(meeting): room microphone switch, summary without who-said-what - #44
Merged
Merged
Conversation
A meeting room often shares one microphone among several people, so the summary put everything they said under one member. A control-bar switch marks this microphone as the room's (participant attribute meet.room_mic, remembered per browser); the summary service labels its lines 會議室. The summary now describes what was discussed and names a person only for a task the transcript assigns to them. Chunk-level diarization was tried first and dropped: on 25 s room chunks the transcriber returns one long segment, so it never saw two voices. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
A meeting room often shares one microphone among several people. The live summary labeled each line with the microphone's account, so everything said in the room went under one member.
What
meet.room_mic; the browser remembers it for the next meeting. The join token now grantscanUpdateOwnMetadata.會議室, read per chunk so the switch can change mid-meeting.Tried and dropped
Chunk-level diarization (diarize=true on each 25 s chunk): on 3 real room chunks the transcriber returned one long segment, so it never saw a second voice, and it added 4 to 7 s per chunk.
Verify
typecheck, lint, format, tokens, actions, build and summary tests pass on the sandbox.
🤖 Generated with Claude Code