Public Access
Preserve recovery transcripts and add user-approved agent requests
PR and Push Build/Test / build-and-test (push) Successful in 12m0s
PR and Push Build/Test / build-and-test (push) Successful in 12m0s
Append successful offline recovery with a duplicate-warning marker and retain failed replay sources. Offer newly available microphones through confirmation notifications. Add project discovery metadata and blocking association approval, plus nonblocking workflow requests that start a separate settings-agent conversation. Include regression tests, OpenSpec changes, and verified local Release startup.
This commit is contained in:
@@ -139,7 +139,11 @@ When Azure Speech is still unavailable after recording stops and transcription c
|
||||
|
||||
When a stopped meeting is persisted to the durable transcription backlog, Meeting Assistant SHALL release the active recording slot so another meeting can be recorded while the stopped meeting waits for Azure Speech to become available.
|
||||
|
||||
When Azure Speech becomes available again, Meeting Assistant SHALL retry durable backlog items, rewrite the transcript from the recorded WAV, run the normal post-transcription meeting completion and summary flow, and remove the backlog item after successful completion.
|
||||
When Azure Speech becomes available again, Meeting Assistant SHALL retry durable backlog items, append the recovered transcript from the recorded WAV without replacing the existing transcript body, run the normal post-transcription meeting completion and summary flow, and remove the backlog item after successful completion.
|
||||
|
||||
Before appending recovered lines, Meeting Assistant SHALL insert a visible recovery marker explaining that the following section was recovered by replaying the entire recording and may duplicate earlier transcript passages. The marker SHALL tell the summarizer to treat repeated passages as the same discussion. The marker and appended lines SHALL be available to the summary agent together with the preserved earlier transcript. Existing transcript text, speaker labels, and user edits SHALL remain unchanged.
|
||||
|
||||
An offline replay that returns no speech segments with non-blank text SHALL be treated as an unsuccessful attempt. This includes empty results, blank speech segments, and results containing only status markers. Meeting Assistant SHALL preserve the existing transcript and meeting artifacts unchanged, SHALL skip meeting completion and summarization, and SHALL retain the durable backlog item and its WAV for a later retry.
|
||||
|
||||
When Meeting Assistant starts, it SHALL preserve WAV files that are referenced by durable transcription backlog items instead of deleting them as stale temporary recordings.
|
||||
|
||||
@@ -185,10 +189,28 @@ When Meeting Assistant starts, it SHALL preserve WAV files that are referenced b
|
||||
#### Scenario: Durable Azure backlog resumes after connectivity returns
|
||||
- **GIVEN** a stopped Azure meeting exists in the durable transcription backlog
|
||||
- **WHEN** Azure Speech can transcribe the recorded WAV
|
||||
- **THEN** Meeting Assistant rewrites the transcript from the recorded WAV
|
||||
- **THEN** Meeting Assistant preserves the existing transcript body and appends a recovery marker followed by the transcript from the recorded WAV
|
||||
- **AND** the marker explains the recovery and possible duplicates to the summary agent
|
||||
- **AND** runs meeting completion and summarization
|
||||
- **AND** removes the durable backlog item and its temporary WAV after successful completion
|
||||
|
||||
#### Scenario: Empty offline replay preserves the live transcript and recovery files
|
||||
- **GIVEN** a stopped Azure meeting has an existing live transcript and a durable backlog item referencing its WAV
|
||||
- **WHEN** the offline replay returns no transcript segments
|
||||
- **THEN** Meeting Assistant leaves the transcript and meeting artifacts unchanged
|
||||
- **AND** does not run meeting completion or summarization
|
||||
- **AND** retains the backlog item and WAV for the next retry
|
||||
- **WHEN** a later retry produces a transcript from the WAV
|
||||
- **THEN** Meeting Assistant appends the recovery marker and recovered transcript without replacing earlier content and completes the meeting normally
|
||||
- **AND** removes the backlog item and WAV only after that successful completion
|
||||
|
||||
#### Scenario: Offline status markers or blank speech do not count as successful transcription
|
||||
- **GIVEN** a stopped Azure meeting has an existing live transcript and a durable backlog item referencing its WAV
|
||||
- **WHEN** the offline replay returns only status markers or speech segments with blank text
|
||||
- **THEN** Meeting Assistant preserves the existing transcript and meeting artifacts
|
||||
- **AND** skips meeting completion and summarization
|
||||
- **AND** retains the backlog item and WAV for another retry
|
||||
|
||||
### Requirement: FunASR can provide speaker-attributed streaming transcription
|
||||
Meeting Assistant SHALL provide a FunASR speech recognition pipeline that streams PCM audio to a configured FunASR WebSocket endpoint.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user