Fix Discogs cache — add field extractor, wire worker caching, browser UI

- Add _extract_discogs_fields to metadata cache — handles Discogs field
  names (title vs name, images array, Artist - Title format)
- Worker uses _fetch_and_cache_artist/_fetch_and_cache_album helpers
  that cache raw data while returning it for enrichment
- All search/lookup methods cache results for repeat queries
- Cache browser: Discogs stat pill, source filter, clear button, badge
- Fixes albums showing as 'Unknown' and artists missing images in cache

core/discogs_client.py

@@ -12,6 +12,7 @@ import re
 import time
 import threading
 import requests
+from core.metadata_cache import get_metadata_cache
 from typing import List, Dict, Any, Optional
 from dataclasses import dataclass
 from functools import wraps
@@ -372,6 +373,18 @@ class DiscogsClient:
 
     def search_artists(self, query: str, limit: int = 10) -> List[Artist]:
         """Search for artists on Discogs."""
+        cache = get_metadata_cache()
+        cached_results = cache.get_search_results('discogs', 'artist', query, limit)
+        if cached_results is not None:
+            artists = []
+            for raw in cached_results:
+                try:
+                    artists.append(Artist.from_discogs_artist(raw))
+                except Exception:
+                    pass
+            if artists:
+                return artists
+
         data = self._api_get('/database/search', {
             'q': query, 'type': 'artist', 'per_page': min(limit, 50),
         })
@@ -379,15 +392,36 @@ class DiscogsClient:
             return []
 
         artists = []
+        raw_items = []
         for item in data['results'][:limit]:
             try:
                 artists.append(Artist.from_discogs_artist(item))
+                raw_items.append(item)
             except Exception as e:
                 logger.debug(f"Error parsing Discogs artist: {e}")
+
+        if raw_items:
+            entries = [(str(r.get('id', '')), r) for r in raw_items if r.get('id')]
+            if entries:
+                cache.store_entities_bulk('discogs', 'artist', entries)
+                cache.store_search_results('discogs', 'artist', query, limit,
+                                           [str(r.get('id', '')) for r in raw_items if r.get('id')])
         return artists
 
     def search_albums(self, query: str, limit: int = 10) -> List[Album]:
         """Search for releases/albums on Discogs."""
+        cache = get_metadata_cache()
+        cached_results = cache.get_search_results('discogs', 'album', query, limit)
+        if cached_results is not None:
+            albums = []
+            for raw in cached_results:
+                try:
+                    albums.append(Album.from_discogs_release(raw))
+                except Exception:
+                    pass
+            if albums:
+                return albums
+
         data = self._api_get('/database/search', {
             'q': query, 'type': 'release', 'per_page': min(limit, 50),
         })
@@ -395,20 +429,28 @@ class DiscogsClient:
             return []
 
         albums = []
+        raw_items = []
         seen_titles = set()
         for item in data['results'][:limit * 2]:
             try:
                 album = Album.from_discogs_release(item)
-                # Deduplicate by title+artist (Discogs has many pressings of same album)
                 dedup_key = f"{album.name.lower()}|{album.artists[0].lower() if album.artists else ''}"
                 if dedup_key in seen_titles:
                     continue
                 seen_titles.add(dedup_key)
                 albums.append(album)
+                raw_items.append(item)
                 if len(albums) >= limit:
                     break
             except Exception as e:
                 logger.debug(f"Error parsing Discogs release: {e}")
+
+        if raw_items:
+            entries = [(str(r.get('id', '')), r) for r in raw_items if r.get('id')]
+            if entries:
+                cache.store_entities_bulk('discogs', 'album', entries, skip_if_exists=True)
+                cache.store_search_results('discogs', 'album', query, limit,
+                                           [str(r.get('id', '')) for r in raw_items if r.get('id')])
         return albums
 
     def search_tracks(self, query: str, limit: int = 10) -> List[Track]:
@@ -423,16 +465,23 @@ class DiscogsClient:
 
     def get_artist(self, artist_id: str) -> Optional[Dict[str, Any]]:
         """Get artist details by Discogs ID."""
-        data = self._api_get(f'/artists/{artist_id}')
-        if not data:
-            return None
+        cache = get_metadata_cache()
+        cached = cache.get_entity('discogs', 'artist', artist_id)
+        if cached and cached.get('name'):
+            # Rebuild normalized result from cached raw data
+            data = cached
+        else:
+            data = self._api_get(f'/artists/{artist_id}')
+            if not data:
+                return None
+            cache.store_entity('discogs', 'artist', artist_id, data)
 
         artist = Artist.from_discogs_artist(data)
 
         # Get profile/bio
         profile = data.get('profile', '')
 
-        return {
+        result = {
             'id': artist.id,
             'name': artist.name,
             'image_url': artist.image_url,
@@ -444,15 +493,22 @@ class DiscogsClient:
             'images': [{'url': artist.image_url}] if artist.image_url else [],
         }
 
+        return result
+
     def get_album(self, release_id: str, include_tracks: bool = True) -> Optional[Dict[str, Any]]:
         """Get release/album details by Discogs ID. Tries master first, falls back to release."""
-        # Try as master first (artist discography returns master IDs)
-        data = self._api_get(f'/masters/{release_id}')
-        if not data or not data.get('title'):
-            # Fall back to release
-            data = self._api_get(f'/releases/{release_id}')
-        if not data:
-            return None
+        cache = get_metadata_cache()
+        cached = cache.get_entity('discogs', 'album', release_id)
+        if cached and cached.get('title'):
+            data = cached
+        else:
+            # Try as master first (artist discography returns master IDs)
+            data = self._api_get(f'/masters/{release_id}')
+            if not data or not data.get('title'):
+                data = self._api_get(f'/releases/{release_id}')
+            if not data:
+                return None
+            cache.store_entity('discogs', 'album', release_id, data)
 
         album = Album.from_discogs_release(data)
 
@@ -560,10 +616,15 @@ class DiscogsClient:
 
     def get_album_tracks(self, release_id: str) -> Optional[Dict[str, Any]]:
         """Get album tracks by Discogs release or master ID. Returns Spotify-compatible format."""
+        cache = get_metadata_cache()
+        cache_key = f"{release_id}_tracks"
+        cached = cache.get_entity('discogs', 'album', cache_key)
+        if cached:
+            return cached
+
         # Try as master first (master IDs are used in artist discography)
         data = self._api_get(f'/masters/{release_id}')
         if not data or not data.get('tracklist'):
-            # Fall back to release
             data = self._api_get(f'/releases/{release_id}')
         if not data or not data.get('tracklist'):
             return None
@@ -630,13 +691,40 @@ class DiscogsClient:
                 '_source': 'discogs',
             })
 
-        return {
+        result = {
             'items': tracks,
             'total': len(tracks),
             'limit': len(tracks),
             'next': None,
         }
 
+        cache.store_entity('discogs', 'album', cache_key, result)
+        return result
+
+    def _fetch_and_cache_artist(self, artist_id: str) -> Optional[Dict]:
+        """Fetch raw artist data with cache. Used by enrichment worker."""
+        cache = get_metadata_cache()
+        cached = cache.get_entity('discogs', 'artist', str(artist_id))
+        if cached and cached.get('name'):
+            return cached
+        data = self._api_get(f'/artists/{artist_id}')
+        if data:
+            cache.store_entity('discogs', 'artist', str(artist_id), data)
+        return data
+
+    def _fetch_and_cache_album(self, release_id: str) -> Optional[Dict]:
+        """Fetch raw album/release data with cache. Used by enrichment worker."""
+        cache = get_metadata_cache()
+        cached = cache.get_entity('discogs', 'album', str(release_id))
+        if cached and cached.get('title'):
+            return cached
+        data = self._api_get(f'/masters/{release_id}')
+        if not data or not data.get('title'):
+            data = self._api_get(f'/releases/{release_id}')
+        if data:
+            cache.store_entity('discogs', 'album', str(release_id), data)
+        return data
+
     def _get_artist_image_from_albums(self, artist_id: str) -> Optional[str]:
         """Get artist image by fetching their first album's cover art.
         Used as fallback when artist has no direct image."""

core/discogs_worker.py

@@ -244,14 +244,14 @@ class DiscogsWorker:
             if existing_id:
                 try:
                     if item_type == 'artist':
-                        data = self.client._api_get(f'/artists/{existing_id}')
+                        data = self.client._fetch_and_cache_artist(existing_id)
                         if data:
                             self._update_artist(item_id, data)
                             self.stats['matched'] += 1
                             logger.info(f"Enriched artist '{item_name}' from existing Discogs ID: {existing_id}")
                             return
                     elif item_type == 'album':
-                        data = self.client._api_get(f'/releases/{existing_id}')
+                        data = self.client._fetch_and_cache_album(existing_id)
                         if data:
                             self._update_album(item_id, data)
                             self.stats['matched'] += 1
@@ -298,8 +298,8 @@ class DiscogsWorker:
         # Find best match by name similarity
         for result in results:
             if self._name_matches(artist_name, result.name):
-                # Fetch full artist detail
-                data = self.client._api_get(f'/artists/{result.id}')
+                # Fetch full artist detail (uses cache)
+                data = self.client._fetch_and_cache_artist(result.id)
                 if data:
                     self._update_artist(artist_id, data)
                     self.stats['matched'] += 1
@@ -322,8 +322,8 @@ class DiscogsWorker:
 
         for result in results:
             if self._name_matches(album_name, result.name):
-                # Fetch full release detail
-                data = self.client._api_get(f'/releases/{result.id}')
+                # Fetch full release detail (uses cache)
+                data = self.client._fetch_and_cache_album(result.id)
                 if data:
                     self._update_album(album_id, data)
                     self.stats['matched'] += 1

core/metadata_cache.py

@@ -489,9 +489,9 @@ class MetadataCache:
                 cursor = conn.cursor()
 
                 stats = {
-                    'artists': {'spotify': 0, 'itunes': 0, 'deezer': 0},
-                    'albums': {'spotify': 0, 'itunes': 0, 'deezer': 0},
-                    'tracks': {'spotify': 0, 'itunes': 0, 'deezer': 0},
+                    'artists': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
+                    'albums': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
+                    'tracks': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
                     'searches': 0,
                     'total_entries': 0,
                     'total_hits': 0,
@@ -541,9 +541,9 @@ class MetadataCache:
         except Exception as e:
             logger.error(f"Cache stats error: {e}")
             return {
-                'artists': {'spotify': 0, 'itunes': 0, 'deezer': 0},
-                'albums': {'spotify': 0, 'itunes': 0, 'deezer': 0},
-                'tracks': {'spotify': 0, 'itunes': 0, 'deezer': 0},
+                'artists': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
+                'albums': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
+                'tracks': {'spotify': 0, 'itunes': 0, 'deezer': 0, 'discogs': 0},
                 'searches': 0, 'total_entries': 0, 'total_hits': 0,
                 'oldest': None, 'newest': None,
             }
@@ -848,6 +848,8 @@ class MetadataCache:
             return self._extract_deezer_fields(entity_type, raw_data)
         elif source == 'beatport':
             return self._extract_beatport_fields(entity_type, raw_data)
+        elif source == 'discogs':
+            return self._extract_discogs_fields(entity_type, raw_data)
         return {'name': str(raw_data.get('name', raw_data.get('trackName', '')))}
 
     def _extract_spotify_fields(self, entity_type: str, data: dict) -> dict:
@@ -1043,6 +1045,56 @@ class MetadataCache:
 
         return fields
 
+    def _extract_discogs_fields(self, entity_type: str, data: dict) -> dict:
+        """Extract fields from Discogs API response."""
+        fields = {}
+
+        # Discogs uses 'name' for artists, 'title' for releases/masters
+        if entity_type == 'artist':
+            fields['name'] = data.get('name', data.get('title', ''))
+            fields['genres'] = json.dumps([])
+            fields['popularity'] = 0
+            fields['followers'] = 0
+            # Images array — prefer primary type
+            images = data.get('images', [])
+            if images:
+                primary = next((img for img in images if img.get('type') == 'primary'), None)
+                fields['image_url'] = (primary or images[0]).get('uri')
+            # Search results use cover_image/thumb
+            if not fields.get('image_url'):
+                img = data.get('cover_image') or data.get('thumb')
+                if img and 'spacer.gif' not in img:
+                    fields['image_url'] = img
+
+        elif entity_type == 'album':
+            # Handle "Artist - Title" format from search results
+            raw_title = data.get('title', '')
+            if data.get('artists'):
+                fields['name'] = raw_title
+                fields['artist_name'] = data['artists'][0].get('name', '')
+            elif ' - ' in raw_title:
+                parts = raw_title.split(' - ', 1)
+                fields['artist_name'] = parts[0].strip()
+                fields['name'] = parts[1].strip()
+            else:
+                fields['name'] = raw_title
+
+            fields['release_date'] = str(data.get('year', '')) if data.get('year') else ''
+            tracklist = data.get('tracklist', [])
+            fields['total_tracks'] = len(tracklist) if tracklist else 0
+            fields['genres'] = json.dumps(data.get('genres', []))
+
+            images = data.get('images', [])
+            if images:
+                primary = next((img for img in images if img.get('type') == 'primary'), None)
+                fields['image_url'] = (primary or images[0]).get('uri')
+            if not fields.get('image_url'):
+                img = data.get('cover_image') or data.get('thumb')
+                if img and 'spacer.gif' not in img:
+                    fields['image_url'] = img
+
+        return fields
+
     def _extract_beatport_fields(self, entity_type: str, data: dict) -> dict:
         """Extract fields from Beatport enriched track data."""
         fields = {}

webui/index.html

@@ -6625,6 +6625,7 @@
                             <button onclick="clearMetadataCacheBySource('beatport')"><span class="mcache-source-badge beatport" style="margin-right:6px">beatport</span>Clear Beatport</button>
                             <div style="border-top:1px solid rgba(255,255,255,0.08);margin:4px 0"></div>
                             <button onclick="clearMusicBrainzCache()"><span class="mcache-source-badge musicbrainz" style="margin-right:6px">musicbrainz</span>Clear MusicBrainz</button>
+                            <button onclick="clearMetadataCacheBySource('discogs')"><span class="mcache-source-badge discogs" style="margin-right:6px">discogs</span>Clear Discogs</button>
                             <button onclick="clearMusicBrainzCache(true)"><span class="mcache-source-badge musicbrainz" style="margin-right:6px;opacity:0.6">musicbrainz</span>Clear Failed MB Only</button>
                             <div style="border-top:1px solid rgba(255,255,255,0.08);margin:4px 0"></div>
                             <button onclick="clearMetadataCache()">Clear All</button>
@@ -6654,6 +6655,10 @@
                     <span class="mcache-stat-pill-label">MusicBrainz</span>
                     <span class="mcache-stat-pill-value" id="mcache-browse-musicbrainz-count">0</span>
                 </div>
+                <div class="mcache-stat-pill">
+                    <span class="mcache-stat-pill-label">Discogs</span>
+                    <span class="mcache-stat-pill-value" id="mcache-browse-discogs-count">0</span>
+                </div>
                 <div class="mcache-stat-pill">
                     <span class="mcache-stat-pill-label">Total Hits</span>
                     <span class="mcache-stat-pill-value" id="mcache-browse-hits">0</span>
@@ -6677,6 +6682,7 @@
                     <option value="deezer">Deezer</option>
                     <option value="beatport">Beatport</option>
                     <option value="musicbrainz">MusicBrainz</option>
+                    <option value="discogs">Discogs</option>
                 </select>
                 <select class="mcache-sort-filter" id="mcache-sort-filter" onchange="loadMetadataCacheBrowse()">
                     <option value="last_accessed_at">Recently Accessed</option>

webui/static/script.js

@@ -21642,6 +21642,8 @@ async function loadMetadataCacheBrowseStats() {
         el('mcache-browse-itunes-count', itunesTotal);
         el('mcache-browse-deezer-count', deezerTotal);
         el('mcache-browse-beatport-count', beatportTotal);
+        const discogsTotal = (stats.artists?.discogs || 0) + (stats.albums?.discogs || 0) + (stats.tracks?.discogs || 0);
+        el('mcache-browse-discogs-count', discogsTotal);
         el('mcache-browse-musicbrainz-count', stats.musicbrainz_total || 0);
         el('mcache-browse-hits', stats.total_hits || 0);
         el('mcache-browse-searches', stats.searches || 0);

webui/static/style.css

@@ -47303,6 +47303,11 @@ tr.tag-diff-same {
     color: #BA478F;
 }
 
+.mcache-source-badge.discogs {
+    background: rgba(212, 165, 116, 0.15);
+    color: #D4A574;
+}
+
 .mcache-card.mb-matched {
     border-left: 2px solid rgba(76, 175, 80, 0.5);
 }