meeting-assistant/openspec/changes/archive/2026-05-28-harden-speaker-samples-and-pyannote-validation/tasks.md

1. Specification

• Add requirements for minimum uninterrupted speaker samples.
• Add requirements for optional pyannote secondary validation.

2. Tests

• Cover sample collection waiting for the configured minimum uninterrupted speech duration.
• Cover sample collection resetting when another speaker interrupts.
• Cover pyannote sample validation rejecting multi-speaker samples.
• Cover pyannote match validation rejecting an Azure-confirmed match.
• Update existing live matching tests to configure short samples where they intentionally exercise fast matching.

3. Implementation

• Add speaker identification configuration for minimum sample duration and pyannote validation.
• Refactor live sample collection to accumulate continuous same-speaker spans.
• Add pyannote diarization reuse for speaker identity validation.
• Add secondary validation into the identity matching pipeline.

4. Verification

• Run focused speaker/transcription tests.
• Run openspec validate harden-speaker-samples-and-pyannote-validation --strict.