Merge perf/diarize-threading: diarization progress via background thread

This commit is contained in:
Claude
2026-03-20 13:52:59 -07:00
3 changed files with 113 additions and 6 deletions

View File

@@ -1,7 +1,13 @@
"""Tests for diarization service data structures and payload conversion."""
import time
from unittest.mock import MagicMock, patch
import pytest
from voice_to_notes.services.diarize import (
DiarizationResult,
DiarizeService,
SpeakerSegment,
diarization_to_payload,
)
@@ -31,3 +37,73 @@ def test_diarization_to_payload_empty():
assert payload["num_speakers"] == 0
assert payload["speaker_segments"] == []
assert payload["speakers"] == []
def test_diarize_threading_progress(monkeypatch):
"""Test that diarization emits progress while running in background thread."""
# Track written messages
written_messages = []
def mock_write(msg):
written_messages.append(msg)
# Mock pipeline that takes ~5 seconds
def slow_pipeline(file_path, **kwargs):
time.sleep(5)
# Return a mock diarization result
mock_result = MagicMock()
mock_track = MagicMock()
mock_track.start = 0.0
mock_track.end = 5.0
mock_result.itertracks = MagicMock(return_value=[(mock_track, None, "SPEAKER_00")])
return mock_result
mock_pipeline_obj = MagicMock()
mock_pipeline_obj.side_effect = slow_pipeline
service = DiarizeService()
service._pipeline = mock_pipeline_obj
with patch("voice_to_notes.services.diarize.write_message", mock_write):
result = service.diarize(
request_id="req-1",
file_path="/fake/audio.wav",
audio_duration_sec=60.0,
)
# Filter for diarizing progress messages (not loading_diarization or done)
diarizing_msgs = [
m for m in written_messages
if m.type == "progress" and m.payload.get("stage") == "diarizing"
and "elapsed" in m.payload.get("message", "")
]
# Should have at least 1 progress message (5s sleep / 2s interval = ~2 messages)
assert len(diarizing_msgs) >= 1, (
f"Expected at least 1 diarizing progress message, got {len(diarizing_msgs)}"
)
# Progress percent should be between 20 and 85
for msg in diarizing_msgs:
pct = msg.payload["percent"]
assert 20 <= pct <= 85, f"Progress {pct} out of expected range 20-85"
# Result should be valid
assert result.num_speakers == 1
assert result.speakers == ["SPEAKER_00"]
def test_diarize_threading_error_propagation(monkeypatch):
"""Test that errors from the background thread are properly raised."""
mock_pipeline_obj = MagicMock()
mock_pipeline_obj.side_effect = RuntimeError("Pipeline crashed")
service = DiarizeService()
service._pipeline = mock_pipeline_obj
with patch("voice_to_notes.services.diarize.write_message", lambda m: None):
with pytest.raises(RuntimeError, match="Pipeline crashed"):
service.diarize(
request_id="req-1",
file_path="/fake/audio.wav",
audio_duration_sec=30.0,
)