From 6eb13bce63b0b6ffe325b52734f54851b4090fb7 Mon Sep 17 00:00:00 2001
From: Claude <claude@anthropic.com>
Date: Fri, 20 Mar 2026 13:49:14 -0700
Subject: [PATCH] Remove progress throttle so every segment emits a progress
 update

Previously, progress messages were only sent every 5th segment due to
a `segment_count % 5` guard. This made the UI feel unresponsive for
short recordings with few segments. Now every segment emits a progress
update with a more descriptive message including the segment number
and audio percentage.

Adds a test verifying that all 8 mock segments produce progress
messages, not just every 5th.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 python/tests/test_transcribe.py              | 54 ++++++++++++++++++++
 python/voice_to_notes/services/transcribe.py | 16 +++---
 2 files changed, 61 insertions(+), 9 deletions(-)

diff --git a/python/tests/test_transcribe.py b/python/tests/test_transcribe.py
index b9e4220..67b4289 100644
--- a/python/tests/test_transcribe.py
+++ b/python/tests/test_transcribe.py
@@ -49,3 +49,57 @@ def test_result_to_payload_empty():
     assert payload["segments"] == []
     assert payload["language"] == ""
     assert payload["duration_ms"] == 0
+
+
+def test_progress_every_segment(monkeypatch):
+    """Verify a progress message is sent for every segment, not just every 5th."""
+    from unittest.mock import MagicMock, patch
+    from voice_to_notes.services.transcribe import TranscribeService
+
+    # Mock WhisperModel
+    mock_model = MagicMock()
+
+    # Create mock segments (8 of them to test > 5)
+    mock_segments = []
+    for i in range(8):
+        seg = MagicMock()
+        seg.start = i * 1.0
+        seg.end = (i + 1) * 1.0
+        seg.text = f"Segment {i}"
+        seg.words = []
+        mock_segments.append(seg)
+
+    # Mock info object
+    mock_info = MagicMock()
+    mock_info.language = "en"
+    mock_info.language_probability = 0.99
+    mock_info.duration = 8.0
+
+    mock_model.transcribe.return_value = (iter(mock_segments), mock_info)
+
+    # Track write_message calls
+    written_messages = []
+
+    def mock_write(msg):
+        written_messages.append(msg)
+
+    service = TranscribeService()
+    service._model = mock_model
+    service._current_model_name = "base"
+    service._current_device = "cpu"
+    service._current_compute_type = "int8"
+
+    with patch("voice_to_notes.services.transcribe.write_message", mock_write):
+        service.transcribe("req-1", "/fake/audio.wav")
+
+    # Filter for "transcribing" stage progress messages
+    transcribing_msgs = [
+        m for m in written_messages
+        if m.type == "progress" and m.payload.get("stage") == "transcribing"
+    ]
+
+    # Should have one per segment (8) + the initial "Starting transcription..." message
+    # The initial "Starting transcription..." is also stage "transcribing" — so 8 + 1 = 9
+    assert len(transcribing_msgs) >= 8, (
+        f"Expected at least 8 transcribing progress messages (one per segment), got {len(transcribing_msgs)}"
+    )
diff --git a/python/voice_to_notes/services/transcribe.py b/python/voice_to_notes/services/transcribe.py
index 2539cfc..19cf146 100644
--- a/python/voice_to_notes/services/transcribe.py
+++ b/python/voice_to_notes/services/transcribe.py
@@ -145,16 +145,14 @@ class TranscribeService:
                 )
             )
 
-            # Send progress every few segments
-            if segment_count % 5 == 0:
-                write_message(
-                    progress_message(
-                        request_id,
-                        progress_pct,
-                        "transcribing",
-                        f"Processed {segment_count} segments...",
-                    )
+            write_message(
+                progress_message(
+                    request_id,
+                    progress_pct,
+                    "transcribing",
+                    f"Transcribing segment {segment_count} ({progress_pct}% of audio)...",
                 )
+            )
 
         elapsed = time.time() - start_time
         print(