Speed up music scan by deferring tag reads to import time

Reading embedded ID3/MP4 tags for every file during the scan itself was
taking minutes even for a small (146-track) library, since each mutagen
open is a slow round trip over the CIFS-mounted NAS share. Scan now uses
fast filename/path parsing only; tag reads happen once, only for the
tracks actually selected for import.

backend/library_scan.py

@@ -132,7 +132,10 @@ def _read_tags(path: Path) -> Dict:
 
 
 def scan_music() -> List[Dict]:
-    """Music/<Artist>/<Album>/<NN Title.ext>. Prefers embedded tags, falls back to path/filename."""
+    """Music/<Artist>/<Album>/<NN Title.ext>. Filename/path-derived only — no file reads, so this
+    stays fast even over a network share with a large library. Embedded tags (better titles, real
+    duration) are read later, only for the tracks actually selected for import — see tags_for_file().
+    """
     if not MUSIC_DIR.is_dir():
         return []
     out = []
@@ -145,23 +148,24 @@ def scan_music() -> List[Dict]:
             for f in sorted(album_dir.iterdir()):
                 if not f.is_file() or f.suffix.lower() not in AUDIO_EXTS:
                     continue
-                tags = _read_tags(f)
-                track_number = tags["track_number"]
-                title = tags["title"]
-                if not title:
+                track_number = None
+                title = f.stem
                 fm = _TRACK_NUM_RE.match(f.stem)
                 if fm:
-                        track_number = track_number or int(fm.group(1))
+                    track_number = int(fm.group(1))
                     title = fm.group(2)
-                    else:
-                        title = f.stem
                 out.append({
-                    "artist": tags["artist"] or artist_dir.name,
-                    "album": tags["album"] or album_dir.name,
+                    "artist": artist_dir.name,
+                    "album": album_dir.name,
                     "title": _clean_title(title) or title,
                     "track_number": track_number,
-                    "duration_seconds": round(tags["duration"], 1),
+                    "duration_seconds": 0,
                     "storage_path": str(f),
                     "size_bytes": f.stat().st_size,
                 })
     return out
+
+
+def tags_for_file(path_str: str) -> Dict:
+    """Embedded-tag lookup for a single file — used at import time, not during scan."""
+    return _read_tags(Path(path_str))

backend/server.py

@@ -1431,10 +1431,13 @@ async def scan_import(payload: dict, user: dict = Depends(require_admin)):
         for it in items:
             if await db.tracks.find_one({"storage_path": it["storage_path"]}, {"_id": 1}):
                 continue
+            tags = await asyncio.to_thread(library_scan.tags_for_file, it["storage_path"])
             track = Track(
-                title=it.get("title") or "Untitled", artist=it.get("artist") or "Unknown Artist",
-                album=it.get("album") or "Unknown Album", track_number=it.get("track_number"),
-                duration_seconds=it.get("duration_seconds") or 0, storage_path=it["storage_path"],
+                title=tags.get("title") or it.get("title") or "Untitled",
+                artist=tags.get("artist") or it.get("artist") or "Unknown Artist",
+                album=tags.get("album") or it.get("album") or "Unknown Album",
+                track_number=tags.get("track_number") or it.get("track_number"),
+                duration_seconds=round(tags.get("duration") or 0, 1), storage_path=it["storage_path"],
             ).model_dump()
             await db.tracks.insert_one(track)
             created += 1