fix(discover): drop suggestions for non-artists (no core discography)

ListenBrainz surfaces producers/session players/band members (Max Martin,
Dominic Howard) that co-occur in listens but have no releases of their own —
they showed as bare rows with an empty page. _derive_albums now drops a
surfaced artist (deletes their pending suggestion) when their MB discography
has no core release-group (Album/Single/EP, no secondary type), catching both
empty discographies and soundtrack/production-only credits, while keeping real
singles/EP-only artists. On browse failure the suggestion is kept.

Test fake browser gains default_core so scoring tests keep surfacing candidates.
worker 249 tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

worker/lyra_worker/adapters/fakes.py

@@ -72,17 +72,24 @@ class FailingAdapter(_BaseFake):
 
 
 class FakeMbBrowser:
-    """In-memory MbBrowser for tests. `releases` maps artist mbid -> [ReleaseGroupInfo]."""
+    """In-memory MbBrowser for tests. `releases` maps artist mbid -> [ReleaseGroupInfo].
+    `default_core=True` returns a synthetic core Album for any artist not in `releases`, so
+    scoring tests don't trip the "no core discography → drop the suggestion" filter."""
 
-    def __init__(self, artists=None, releases=None):
+    def __init__(self, artists=None, releases=None, default_core=False):
         self._artists = list(artists or [])
         self._releases = dict(releases or {})
+        self._default_core = default_core
 
     def search_artist(self, name: str) -> list[ArtistHit]:
         return list(self._artists)
 
     def browse_release_groups(self, artist_mbid: str) -> list[ReleaseGroupInfo]:
-        return list(self._releases.get(artist_mbid, []))
+        if artist_mbid in self._releases:
+            return list(self._releases[artist_mbid])
+        if self._default_core:
+            return [ReleaseGroupInfo(f"rg-{artist_mbid}", "Album", "Album", (), "2000-01-01")]
+        return []
 
 
 class FakeAudioProbe:

worker/lyra_worker/discovery.py

@@ -204,6 +204,16 @@ def _derive_albums(conn: psycopg.Connection, browser: MbBrowser, surfaced: list[
         except Exception as e:  # one artist's browse failure must not abort the sweep
             print(f"worker: discovery album browse failed for {artist['mbid']}: {e}", flush=True)
             continue
+        # Drop suggestions for "artists" with no real discography of their own — producers,
+        # session players, band members, soundtrack-only credits. ListenBrainz surfaces them
+        # (they co-occur in listens) but they have no core release-group to follow or want, and
+        # their page is empty. Require at least one core release (Album/Single/EP, no secondary
+        # type); on browse failure we keep the suggestion rather than drop a real artist.
+        if not any(is_core_release(g.primary_type, g.secondary_types) for g in groups):
+            with conn.cursor() as cur:
+                cur.execute("DELETE FROM \"DiscoverySuggestion\" WHERE status = 'pending' "
+                            'AND "artistMbid" = %s', (artist["mbid"],))
+            continue
         core = [g for g in groups
                 if _album_kind_ok(g, cfg.albums_only) and g.rg_mbid not in have]
         core.sort(key=lambda g: g.first_release_date or "", reverse=True)

worker/tests/test_discovery.py

@@ -26,7 +26,7 @@ def test_seeds_discovery_from_owned_album_artists(conn):
     # An artist you own an album by but don't follow becomes a discovery seed.
     _insert_library_item(conn, "Owned Artist", "lib-seed")
     src = FakeSimilaritySource(similar={"lib-seed": [SimilarArtist("c1", "New Find", 0.9)]})
-    result = run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    result = run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert result.seeds == 1
     assert [r[0] for r in _artist_rows(conn)] == ["c1"]  # surfaced from the library seed
     with conn.cursor() as cur:  # library seed throttled via DiscoverySeed, not WatchedArtist
@@ -37,7 +37,7 @@ def test_seeds_discovery_from_owned_album_artists(conn):
 def test_library_seeding_can_be_disabled(conn):
     _insert_library_item(conn, "Owned Artist", "lib-seed")
     src = FakeSimilaritySource(similar={"lib-seed": [SimilarArtist("c1", "New Find", 0.9)]})
-    result = run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig(seed_from_library=False))
+    result = run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig(seed_from_library=False))
     assert result.seeds == 0 and _artist_rows(conn) == []  # library not seeded
 
 
@@ -49,7 +49,7 @@ def test_owned_artist_is_not_suggested_as_a_candidate(conn):
         "s1": [SimilarArtist("c1", "Owned", 0.9), SimilarArtist("c2", "New", 0.8)],
         "c1": [],  # the library seed itself finds nothing new here
     })
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert [r[0] for r in _artist_rows(conn)] == ["c2"]  # c1 excluded (already owned)
 
 
@@ -60,7 +60,7 @@ def test_aggregates_scores_across_seeds(conn):
         "s1": [SimilarArtist("c1", "Shared", 0.6), SimilarArtist("c2", "Only1", 0.4)],
         "s2": [SimilarArtist("c1", "Shared", 0.5)],
     })
-    result = run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    result = run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert result.artists == 2
     rows = _artist_rows(conn)
     # c1 recommended by both seeds; each seed max-normalizes its top score to 1.0, so
@@ -81,7 +81,7 @@ def test_normalizes_across_sources_of_different_scales(conn):
     lfm = FakeSimilaritySource(similar={"s1": [
         SimilarArtist("c_lfm", "LFM Only", 0.9), SimilarArtist("c_shared", "Shared", 0.5)]})
     lfm.name = "lastfm"
-    run_discovery(conn, [lb, lfm], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [lb, lfm], FakeMbBrowser(default_core=True), DiscoveryConfig())
 
     lb_only = _artist_score(conn, "c_lb")[0]    # 5000/5000 = 1.0
     lfm_only = _artist_score(conn, "c_lfm")[0]  # 0.9/0.9  = 1.0
@@ -95,7 +95,7 @@ def test_skips_already_followed_artists(conn):
     insert_watched_artist(conn, mbid="c1", name="Already Followed")
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "X", 0.9),
                                                 SimilarArtist("c2", "New", 0.8)]})
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert [r[0] for r in _artist_rows(conn)] == ["c2"]  # c1 filtered (followed)
 
 
@@ -103,7 +103,7 @@ def test_min_score_filters_weak_candidates(conn):
     insert_watched_artist(conn, mbid="s1", name="Seed")
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "Strong", 0.9),
                                                 SimilarArtist("c2", "Weak", 0.1)]})
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig(min_score=0.5))
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig(min_score=0.5))
     assert [r[0] for r in _artist_rows(conn)] == ["c1"]
 
 
@@ -111,7 +111,7 @@ def test_dismissed_suggestion_is_never_revived(conn):
     insert_watched_artist(conn, mbid="s1", name="Seed")
     insert_discovery_suggestion(conn, kind="artist", artist_mbid="c1", status="dismissed", score=0.0)
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "X", 0.9)]})
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     with conn.cursor() as cur:
         cur.execute('SELECT status::text, score FROM "DiscoverySuggestion" WHERE "artistMbid" = %s', ("c1",))
         assert cur.fetchone() == ("dismissed", 0.0)  # untouched — WHERE status='pending' blocked the update
@@ -120,18 +120,18 @@ def test_dismissed_suggestion_is_never_revived(conn):
 def test_stamps_last_discovered_and_throttles(conn):
     insert_watched_artist(conn, mbid="s1", name="Seed")
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "X", 0.9)]})
-    assert run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig()).artists == 1
+    assert run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig()).artists == 1
     with conn.cursor() as cur:
         cur.execute('SELECT "lastDiscoveredAt" IS NOT NULL FROM "WatchedArtist" WHERE mbid = %s', ("s1",))
         assert cur.fetchone()[0] is True
     # second run: seed not due (lastDiscoveredAt recent) -> no seeds -> nothing new
-    assert run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig()).artists == 0
+    assert run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig()).artists == 0
 
 
 def test_unhealthy_source_contributes_nothing(conn):
     insert_watched_artist(conn, mbid="s1", name="Seed")
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "X", 0.9)]}, healthy=False)
-    assert run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig()).artists == 0
+    assert run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig()).artists == 0
     assert _artist_rows(conn) == []
 
 
@@ -146,7 +146,7 @@ def test_source_with_raising_health_is_skipped_not_fatal(conn):
             return []
 
     good = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "X", 0.9)]})
-    result = run_discovery(conn, [BoomSource(), good], FakeMbBrowser(), DiscoveryConfig())
+    result = run_discovery(conn, [BoomSource(), good], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert result.artists == 1  # good source still processed; boom skipped, no crash
 
 
@@ -176,8 +176,8 @@ def test_score_sums_across_separate_chunks(conn):
         "s2": [SimilarArtist("c1", "Shared", 0.5)],
     })
     cfg = DiscoveryConfig(chunk_size=1)
-    run_discovery(conn, [src], FakeMbBrowser(), cfg)   # processes s1 (older)
-    run_discovery(conn, [src], FakeMbBrowser(), cfg)   # processes s2
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), cfg)   # processes s1 (older)
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), cfg)   # processes s2
     # replace-not-accumulate would leave 0.5/seedCount1; contributions give the sum.
     assert _artist_score(conn, "c1") == (2.0, 2)  # each seed max-normalizes to 1.0
 
@@ -193,7 +193,7 @@ def test_partial_sweep_preserves_other_seeds_contribution(conn):
         "s1": [SimilarArtist("c1", "Shared", 0.6)],
         "s2": [SimilarArtist("c1", "Shared", 0.5)],
     })
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())  # both -> 1.1/2
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())  # both -> 1.1/2
     assert _artist_score(conn, "c1") == (2.0, 2)  # each seed max-normalizes to 1.0
 
     # s1 due again (older than interval), s2 fresh; s1 now scores c1 at 0.7.
@@ -202,7 +202,7 @@ def test_partial_sweep_preserves_other_seeds_contribution(conn):
         cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() WHERE mbid = %s', ("s2",))
     conn.commit()
     src2 = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "Shared", 0.7)]})
-    run_discovery(conn, [src2], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src2], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert _artist_score(conn, "c1") == (2.0, 2)  # 1.0 (new s1) + 1.0 (kept s2), max-normalized
 
 
@@ -215,7 +215,7 @@ def test_seed_dropoff_lowers_seedcount(conn):
         "s1": [SimilarArtist("c1", "Shared", 0.6)],
         "s2": [SimilarArtist("c1", "Shared", 0.5)],
     })
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert _artist_score(conn, "c1") == (2.0, 2)  # each seed max-normalizes to 1.0
 
     # s1 re-swept but no longer finds c1 -> its contribution is removed, c1 recomputed.
@@ -224,7 +224,7 @@ def test_seed_dropoff_lowers_seedcount(conn):
         cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() WHERE mbid = %s', ("s2",))
     conn.commit()
     src2 = FakeSimilaritySource(similar={"s1": [SimilarArtist("c9", "Other", 0.9)]})
-    run_discovery(conn, [src2], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src2], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert _artist_score(conn, "c1") == (1.0, 1)  # only s2 remains (max-normalized to 1.0)
 
 
@@ -241,7 +241,7 @@ def test_evicts_contributions_from_removed_seed(conn):
         "s1": [SimilarArtist("c1", "Shared", 0.6)],
         "s2": [SimilarArtist("c1", "Shared", 0.5)],
     })
-    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src], FakeMbBrowser(default_core=True), DiscoveryConfig())
     assert _artist_score(conn, "c1") == (2.0, 2)  # each seed max-normalizes to 1.0
 
     # Unfollow s1 (no FK cascade on DiscoverySeedContribution).
@@ -254,7 +254,7 @@ def test_evicts_contributions_from_removed_seed(conn):
         cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() - interval \'200 hours\' WHERE mbid = %s', ("s2",))
     conn.commit()
     src2 = FakeSimilaritySource(similar={"s2": [SimilarArtist("c1", "Shared", 0.5)]})
-    run_discovery(conn, [src2], FakeMbBrowser(), DiscoveryConfig())
+    run_discovery(conn, [src2], FakeMbBrowser(default_core=True), DiscoveryConfig())
 
     assert _artist_score(conn, "c1") == (1.0, 1)  # s1's stale contribution evicted; s2 alone -> 1.0
     with conn.cursor() as cur:
@@ -271,7 +271,7 @@ def test_run_discovery_processes_at_most_chunk_size_seeds(conn):
         insert_watched_artist(conn, mbid=f"s{i}", name=f"Seed{i}")
     src = FakeSimilaritySource(similar={f"s{i}": [SimilarArtist(f"c{i}", f"Cand{i}", 0.9)] for i in range(4)})
     cfg = DiscoveryConfig.from_config({"discover.chunkSize": "2"})
-    result = run_discovery(conn, [src], FakeMbBrowser(), cfg)
+    result = run_discovery(conn, [src], FakeMbBrowser(default_core=True), cfg)
     assert result.seeds == 2          # only chunk_size seeds this call
     # exactly 2 seeds now have lastDiscoveredAt set
     with conn.cursor() as cur:

worker/tests/test_discovery_albums.py

@@ -12,6 +12,13 @@ def _album_rows(conn):
         return cur.fetchall()
 
 
+def _artist_rows(conn):
+    with conn.cursor() as cur:
+        cur.execute("SELECT \"artistMbid\" FROM \"DiscoverySuggestion\" "
+                    "WHERE kind = 'artist' AND status = 'pending' ORDER BY \"artistMbid\"")
+        return cur.fetchall()
+
+
 def _reasons(conn):
     with conn.cursor() as cur:
         cur.execute('SELECT "rgMbid", "albumReason" FROM "DiscoverySuggestion" '
@@ -120,6 +127,28 @@ def test_rederiving_keeps_wanted_album_suggestions(conn):
         assert cur.fetchone()[0] == 1
 
 
+def test_drops_artist_with_no_core_discography(conn):
+    # Two candidates: one real (has a core album), one a "producer" whose only release is a
+    # secondary-typed soundtrack (like Max Martin's & Juliet) — the latter must be dropped.
+    insert_watched_artist(conn, mbid="s1", name="Seed")
+    src = FakeSimilaritySource(similar={"s1": [
+        SimilarArtist("real", "Real Artist", 0.9), SimilarArtist("producer", "Producer", 0.8)]})
+    browser = FakeMbBrowser(releases={
+        "real": [ReleaseGroupInfo("rg-r", "Record", "Album", (), "2020-01-01")],
+        "producer": [ReleaseGroupInfo("rg-st", "A Musical", "Album", ("Soundtrack",), "2019-01-01")],
+    })
+    run_discovery(conn, [src], browser, DiscoveryConfig(albums_per_artist=1))
+    assert [r[0] for r in _artist_rows(conn)] == ["real"]  # producer dropped
+
+
+def test_drops_artist_with_empty_discography(conn):
+    insert_watched_artist(conn, mbid="s1", name="Seed")
+    src = FakeSimilaritySource(similar={"s1": [SimilarArtist("member", "Band Member", 0.9)]})
+    browser = FakeMbBrowser(releases={"member": []})  # no release groups at all
+    run_discovery(conn, [src], browser, DiscoveryConfig(albums_per_artist=1))
+    assert _artist_rows(conn) == []
+
+
 def test_no_popularity_provider_yields_newest_only(conn):
     insert_watched_artist(conn, mbid="s1", name="Seed")
     src = FakeSimilaritySource(similar={"s1": [SimilarArtist("c1", "Cand", 0.9)]})