Run pyannote diarization in background thread with progress reporting

Move the blocking pipeline() call to a daemon thread and emit estimated
progress messages every 2 seconds from the main thread. The progress
estimate uses audio duration to calibrate the expected total time.
Also pass audio_duration_sec from PipelineService to DiarizeService.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

python/voice_to_notes/services/diarize.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import sys
+import threading
 import time
 from dataclasses import dataclass, field
 from typing import Any
@@ -82,6 +83,8 @@ class DiarizeService:
         num_speakers: int | None = None,
         min_speakers: int | None = None,
         max_speakers: int | None = None,
+        hf_token: str | None = None,
+        audio_duration_sec: float | None = None,
     ) -> DiarizationResult:
         """Run speaker diarization on an audio file.
 
@@ -116,8 +119,36 @@ class DiarizeService:
         if max_speakers is not None:
             kwargs["max_speakers"] = max_speakers
 
-        # Run diarization
-        diarization = pipeline(file_path, **kwargs)
+        # Run diarization in background thread for progress reporting
+        result_holder: list = [None]
+        error_holder: list[Exception | None] = [None]
+        done_event = threading.Event()
+
+        def _run():
+            try:
+                result_holder[0] = pipeline(file_path, **kwargs)
+            except Exception as e:
+                error_holder[0] = e
+            finally:
+                done_event.set()
+
+        thread = threading.Thread(target=_run, daemon=True)
+        thread.start()
+
+        elapsed = 0.0
+        estimated_total = max(audio_duration_sec * 0.5, 30.0) if audio_duration_sec else 120.0
+        while not done_event.wait(timeout=2.0):
+            elapsed += 2.0
+            pct = min(20 + int((elapsed / estimated_total) * 65), 85)
+            write_message(progress_message(
+                request_id, pct, "diarizing",
+                f"Analyzing speakers ({int(elapsed)}s elapsed)..."))
+
+        thread.join()
+
+        if error_holder[0] is not None:
+            raise error_holder[0]
+        diarization = result_holder[0]
 
         # Convert pyannote output to our format
         result = DiarizationResult()

python/voice_to_notes/services/pipeline.py

@@ -121,6 +121,7 @@ class PipelineService:
             num_speakers=num_speakers,
             min_speakers=min_speakers,
             max_speakers=max_speakers,
+            audio_duration_sec=transcription.duration_ms / 1000.0,
         )
 
         # Step 3: Merge