Normalize metadata payloads around source

- remove legacy _source/provider emission from the new metadata path
- update import, discovery, wishlist, and repair consumers to read source
- refresh the affected tests to match the new contract

core/discovery/playlist.py

@@ -184,7 +184,7 @@ def run_playlist_discovery_worker(playlists, automation_id=None, deps: PlaylistD
                     if cached_match and deps.validate_discovery_cache_artist(artist_name, cached_match):
                         extra_data = {
                             'discovered': True,
-                            'provider': discovery_source,
+                            'source': discovery_source,
                             'confidence': cached_match.get('confidence', 0.85),
                             'matched_data': cached_match,
                         }
@@ -309,7 +309,7 @@ def run_playlist_discovery_worker(playlists, automation_id=None, deps: PlaylistD
 
                     extra_data = {
                         'discovered': True,
-                        'provider': discovery_source,
+                        'source': discovery_source,
                         'confidence': best_confidence,
                         'matched_data': matched_data,
                     }
@@ -337,7 +337,7 @@ def run_playlist_discovery_worker(playlists, automation_id=None, deps: PlaylistD
                     stub = deps.build_discovery_wing_it_stub(track_name, artist_name, duration_ms)
                     extra_data = {
                         'discovered': True,
-                        'provider': 'wing_it_fallback',
+                        'source': 'wing_it_fallback',
                         'confidence': 0,
                         'wing_it_fallback': True,
                         'matched_data': stub,

core/discovery/quality_scanner.py

@@ -243,7 +243,6 @@ def _normalize_track_match(track_item: Any, provider: str) -> dict:
         'preview_url': _extract_lookup_value(track_item, 'preview_url', default=None),
         'external_urls': _extract_lookup_value(track_item, 'external_urls', default={}) or {},
         'popularity': _extract_lookup_value(track_item, 'popularity', default=0) or 0,
-        'provider': provider,
         'source': provider,
     }
     if not track_data['image_url']:
@@ -612,7 +611,7 @@ def run_quality_scanner(scope='watchlist', profile_id=1, deps: QualityScannerDep
                         'bitrate': bitrate,
                         'matched': matched,
                         'match_id': matched_track_data['id'] if matched_track_data else None,
-                        'provider': best_source if matched else None,
+                        'source': best_source if matched else None,
                         'spotify_id': matched_track_data['id'] if matched_track_data else None,
                     }
 

core/discovery/youtube.py

@@ -349,7 +349,7 @@ def run_youtube_discovery_worker(url_hash, deps: YoutubeDiscoveryDeps):
                     if result.get('status_class') in ('found', 'wing-it') and result.get('matched_data'):
                         extra_data = {
                             'discovered': True,
-                            'provider': result.get('discovery_source', discovery_source),
+                            'source': result.get('discovery_source', discovery_source),
                             'confidence': result.get('confidence', 0),
                             'matched_data': result['matched_data'],
                         }
@@ -357,13 +357,13 @@ def run_youtube_discovery_worker(url_hash, deps: YoutubeDiscoveryDeps):
                             extra_data['manual_match'] = True
                         if result.get('wing_it_fallback'):
                             extra_data['wing_it_fallback'] = True
-                            extra_data['provider'] = 'wing_it_fallback'
+                            extra_data['source'] = 'wing_it_fallback'
                         db.update_mirrored_track_extra_data(db_track_id, extra_data)
                     else:
                         extra_data = {
                             'discovered': False,
                             'discovery_attempted': True,
-                            'provider': discovery_source,
+                            'source': discovery_source,
                         }
                         db.update_mirrored_track_extra_data(db_track_id, extra_data)
                 logger.info(f"Wrote discovery results to DB for {url_hash}")

core/imports/album.py

@@ -96,16 +96,6 @@ def _normalize_album_source(album: Dict[str, Any], source: str = "") -> str:
     return str(album_source).strip().lower()
 
 
-def _strip_legacy_source_fields(payload: Any) -> Any:
-    if not isinstance(payload, dict):
-        return payload
-
-    cleaned = dict(payload)
-    cleaned.pop("_source", None)
-    cleaned.pop("provider", None)
-    return cleaned
-
-
 def _extract_track_artist_name(track: Dict[str, Any]) -> str:
     artists = track.get("artists") or []
     if isinstance(artists, (str, bytes)):
@@ -138,8 +128,6 @@ def _coerce_track_int(value: Any, default: int = 1) -> int:
 
 def _normalize_match_track(track: Dict[str, Any], source: str, album: Dict[str, Any]) -> Dict[str, Any]:
     track_album = track.get("album") if isinstance(track.get("album"), dict) else album
-    if isinstance(track_album, dict):
-        track_album = _strip_legacy_source_fields(track_album)
     track_source = _normalize_album_source(track, source)
     track_artists = _normalize_artist_entries(track.get("artists") or [])
 
@@ -284,7 +272,6 @@ def build_album_import_context(
     else:
         artist_ctx = resolve_album_artist_context(album, source)
 
-    artist_ctx = _strip_legacy_source_fields(artist_ctx)
     artist_ctx.setdefault("genres", [])
     artist_ctx.setdefault("source", source)
     artist_ctx["genres"] = artist_ctx.get("genres") or []
@@ -382,10 +369,6 @@ def build_album_import_context(
     }
 
     normalized_context = normalize_import_context(context)
-    normalized_context["artist"] = _strip_legacy_source_fields(normalized_context.get("artist"))
-    normalized_context["album"] = _strip_legacy_source_fields(normalized_context.get("album"))
-    normalized_context["track_info"] = _strip_legacy_source_fields(normalized_context.get("track_info"))
-    normalized_context["original_search_result"] = _strip_legacy_source_fields(normalized_context.get("original_search_result"))
     return normalized_context
 
 
@@ -405,7 +388,7 @@ def build_album_import_match_payload(
         source=source,
     )
 
-    album = _strip_legacy_source_fields(dict(album_response.get("album") or {}))
+    album = dict(album_response.get("album") or {})
     source = _normalize_album_source(album, album_response.get("source") or source or "")
     tracks = list(album_response.get("tracks") or [])
     if not album_response.get("success") or not tracks:

core/imports/context.py

@@ -55,11 +55,11 @@ def extract_artist_name(artist: Any) -> str:
 
 
 def normalize_import_context(context: Optional[Dict[str, Any]]) -> Dict[str, Any]:
-    """Normalize an import context to neutral fields in place and drop legacy aliases."""
+    """Normalize an import context to neutral fields in place."""
     if not isinstance(context, dict):
         return {}
 
-    source = context.get("source") or context.get("_source") or ""
+    source = context.get("source") or ""
     artist = _as_dict(context.get("artist") or context.get("spotify_artist"))
     album = _as_dict(context.get("album") or context.get("spotify_album"))
     track_info = _as_dict(context.get("track_info"))
@@ -73,7 +73,6 @@ def normalize_import_context(context: Optional[Dict[str, Any]]) -> Dict[str, Any
     context["album"] = album
     context["track_info"] = track_info
     context["original_search_result"] = normalized_search
-    context.pop("_source", None)
     context.pop("spotify_artist", None)
     context.pop("spotify_album", None)
 

core/imports/resolution.py

@@ -251,7 +251,7 @@ def _build_single_import_context_payload(
         'album_id': album_id,
         'album_type': album_type,
         'release_date': release_date,
-        '_source': source or '',
+        'source': source or '',
     }
 
     album_payload = {
@@ -263,14 +263,14 @@ def _build_single_import_context_payload(
         'image_url': album_image_url,
         'images': album_images,
         'artists': album_artists,
-        '_source': source or '',
+        'source': source or '',
     }
 
     artist_payload = {
         'id': primary_artist_id,
         'name': primary_artist_name,
         'genres': [],
-        '_source': source or '',
+        'source': source or '',
     }
 
     original_search = {
@@ -285,7 +285,7 @@ def _build_single_import_context_payload(
         'artists': track_info['artists'],
         'duration_ms': track_info['duration_ms'],
         'id': track_id,
-        '_source': source or '',
+        'source': source or '',
     }
 
     return {
@@ -322,7 +322,7 @@ def _build_single_import_fallback_context(
                 'id': '',
                 'name': artist_name,
                 'genres': [],
-                '_source': '',
+                'source': '',
             },
             'album': {
                 'id': '',
@@ -333,7 +333,7 @@ def _build_single_import_fallback_context(
                 'image_url': '',
                 'images': [],
                 'artists': [],
-                '_source': '',
+                'source': '',
             },
             'track_info': {
                 'id': '',
@@ -347,7 +347,7 @@ def _build_single_import_fallback_context(
                 'album_id': '',
                 'album_type': 'album',
                 'release_date': '',
-                '_source': '',
+                'source': '',
             },
             'original_search_result': {
                 'title': title,
@@ -361,7 +361,7 @@ def _build_single_import_fallback_context(
                 'artists': [{'name': artist_name}],
                 'duration_ms': 0,
                 'id': '',
-                '_source': '',
+                'source': '',
             },
             'is_album_download': False,
             'has_clean_metadata': False,

core/library/redownload.py

@@ -95,7 +95,7 @@ def redownload_start(track_id):
 
         # Fetch full track details from the metadata source for pipeline parity
         # This gives us track_number, disc_number, full album data
-        meta_source = metadata.get('_source', '')
+        meta_source = metadata.get('source', '')
         meta_id = metadata.get('id', '')
         full_track_details = None
         full_album_data = None

core/metadata/album_tracks.py

@@ -342,8 +342,6 @@ def _build_album_track_entry(track_item: Any, album_info: Dict[str, Any], source
         'uri': _extract_lookup_value(track_item, 'uri', default='') or '',
         'album': album_info,
         'source': source,
-        'provider': source,
-        '_source': source,
     }
 
 
@@ -360,8 +358,6 @@ def _build_album_tracks_payload(
         album_name=album_name, artist_name=artist_name, source=source,
     )
     album_info['source'] = source
-    album_info['_source'] = source
-    album_info['provider'] = source
     track_items = _extract_album_track_items(album_data, tracks_data)
     tracks = [_build_album_track_entry(track, album_info, source) for track in track_items]
 

core/playlists/explorer.py

@@ -105,8 +105,8 @@ def playlist_explorer_build_tree(deps: PlaylistExplorerDeps):
 
             # Only use discovery data if it matches the active metadata source
             is_discovered = extra.get('discovered', False)
-            provider = (extra.get('provider') or '').lower()
+            source = (extra.get('source') or '').lower()
-            source_matches = provider == source_name or (provider in ('itunes', 'apple') and source_name == 'itunes')
+            source_matches = source == source_name or (source in ('itunes', 'apple') and source_name == 'itunes')
 
             matched = extra.get('matched_data', {}) if (is_discovered and source_matches) else {}
             artists_list = matched.get('artists', [])
@@ -359,5 +359,3 @@ def playlist_explorer_build_tree(deps: PlaylistExplorerDeps):
         import traceback
         traceback.print_exc()
         return deps.flask_jsonify({"success": False, "error": str(e)}), 500
-
-

core/repair_jobs/album_completeness.py

@@ -365,7 +365,7 @@ class AlbumCompletenessJob(RepairJob):
                     'track_number': tn,
                     'name': item.get('name', ''),
                     'disc_number': item.get('disc_number', 1),
-                    'source': item.get('_source', primary_source),
+                    'source': item.get('source', primary_source),
                     'source_track_id': item.get('id', ''),
                     'track_id': item.get('id', ''),
                     'spotify_track_id': item.get('id', ''),

core/wishlist/service.py

@@ -193,11 +193,7 @@ class WishlistService:
                     "track_name": track_name,
                     "artist_name": artist_name,
                     "album_name": album_name,
-                    "provider": (
+                    "source": track_data.get("source") if isinstance(track_data, dict) else None,
-                        track_data.get("provider") or track_data.get("source")
-                        if isinstance(track_data, dict)
-                        else None
-                    ),
                     "spotify_track_id": wishlist_track["spotify_track_id"],
                     "spotify_data": track_data,
                     "failure_reason": wishlist_track["failure_reason"],

tests/discovery/test_discovery_playlist.py

@@ -270,7 +270,7 @@ def test_match_above_threshold_writes_extra_data():
     assert len(deps._db.extra_data_writes) == 1
     _, extra = deps._db.extra_data_writes[0]
     assert extra['discovered'] is True
-    assert extra['provider'] == 'spotify'
+    assert extra['source'] == 'spotify'
     assert extra['confidence'] == 0.92
     assert deps._db.cache_saves  # saved to cache
 
@@ -289,7 +289,7 @@ def test_match_below_threshold_falls_back_to_wing_it():
 
     assert len(deps._db.extra_data_writes) == 1
     _, extra = deps._db.extra_data_writes[0]
-    assert extra['provider'] == 'wing_it_fallback'
+    assert extra['source'] == 'wing_it_fallback'
     assert extra['wing_it_fallback'] is True
 
 

tests/discovery/test_discovery_quality_scanner.py

@@ -326,7 +326,6 @@ def test_low_quality_tracks_follow_source_priority(mock_db_and_wishlist):
     assert spotify_client.search_calls == []
     assert len(ws.added) == 1
     add_args = ws.added[0]
-    assert add_args['track_data']['provider'] == 'deezer'
     assert add_args['track_data']['source'] == 'deezer'
 
 

tests/imports/test_import_context.py

@@ -64,9 +64,9 @@ def test_normalize_import_context_promotes_neutral_fields_without_legacy_aliases
     assert get_import_has_full_metadata(normalized) is False
 
 
-def test_normalize_import_context_promotes_legacy_source_alias():
+def test_normalize_import_context_keeps_source_field():
     context = {
-        "_source": "spotify",
+        "source": "spotify",
         "artist": {"name": "Artist One", "id": "artist-1"},
         "album": {"name": "Album One", "id": "album-1"},
         "track_info": {"name": "Song One", "id": "track-1"},
@@ -76,7 +76,6 @@ def test_normalize_import_context_promotes_legacy_source_alias():
     normalized = normalize_import_context(context)
 
     assert normalized["source"] == "spotify"
-    assert "_source" not in normalized
     assert get_import_source(normalized) == "spotify"
 
 

tests/playlists/test_explorer.py

@@ -269,7 +269,7 @@ def test_discovered_artist_grouping_uses_matched_data():
                 'album_name': 'Local Album',
                 'extra_data': json.dumps({
                     'discovered': True,
-                    'provider': 'spotify',
+                    'source': 'spotify',
                     'matched_data': {
                         'artists': [{'name': 'Discovered Artist', 'id': 'sp-aid'}],
                         'album': {'name': 'Discovered Album'},
@@ -306,7 +306,7 @@ def test_provider_mismatch_falls_back_to_raw_track_name():
                 'album_name': 'Raw Album',
                 'extra_data': json.dumps({
                     'discovered': True,
-                    'provider': 'itunes',  # mismatch
+                    'source': 'itunes',  # mismatch
                     'matched_data': {
                         'artists': [{'name': 'iTunes Artist'}],
                     },

tests/wishlist/test_service.py

@@ -163,7 +163,7 @@ def test_get_wishlist_tracks_for_download_formats_modal_shape():
             "track_name": "Song One",
             "artist_name": "Artist One",
             "album_name": "Album One",
-            "provider": None,
+            "source": None,
             "spotify_data": {
                 "id": "sp-1",
                 "name": "Song One",