feat(worker): per-seed discovery contributions so score sums across chunks/sweeps

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-13 15:18:30 +02:00
parent bdd8fe72e9
commit de052a4ef7
2 changed files with 149 additions and 34 deletions
@@ -96,6 +96,75 @@ def test_config_from_config_parses_and_defaults():
            d.albums_per_artist, d.min_score) == (False, 168, 5, 20, 1, 0.0)


+def _artist_score(conn, mbid):
+    with conn.cursor() as cur:
+        cur.execute('SELECT score, "seedCount" FROM "DiscoverySuggestion" WHERE "artistMbid" = %s', (mbid,))
+        return cur.fetchone()
+
+
+def test_score_sums_across_separate_chunks(conn):
+    # Two seeds, both eligible, forced into separate one-seed chunks by chunk_size=1.
+    insert_watched_artist(conn, mbid="s1", name="Seed One",
+                          last_discovered_sql="now() - interval '200 hours'")
+    insert_watched_artist(conn, mbid="s2", name="Seed Two",
+                          last_discovered_sql="now() - interval '190 hours'")
+    src = FakeSimilaritySource(similar={
+        "s1": [SimilarArtist("c1", "Shared", 0.6)],
+        "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
+    # replace-not-accumulate would leave 0.5/seedCount1; contributions give the sum.
+    assert _artist_score(conn, "c1") == (1.1, 2)
+
+
+def test_partial_sweep_preserves_other_seeds_contribution(conn):
+    # Full sweep: c1 gets s1(0.6)+s2(0.5)=1.1. Then only s1 is due again with a new
+    # score; s2's contribution must survive untouched.
+    insert_watched_artist(conn, mbid="s1", name="Seed One",
+                          last_discovered_sql="now() - interval '200 hours'")
+    insert_watched_artist(conn, mbid="s2", name="Seed Two",
+                          last_discovered_sql="now() - interval '200 hours'")
+    src = FakeSimilaritySource(similar={
+        "s1": [SimilarArtist("c1", "Shared", 0.6)],
+        "s2": [SimilarArtist("c1", "Shared", 0.5)],
+    })
+    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())  # both -> 1.1/2
+    assert _artist_score(conn, "c1") == (1.1, 2)
+
+    # s1 due again (older than interval), s2 fresh; s1 now scores c1 at 0.7.
+    with conn.cursor() as cur:
+        cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() - interval \'200 hours\' WHERE mbid = %s', ("s1",))
+        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())
+    assert _artist_score(conn, "c1") == (1.2, 2)  # 0.7 (new s1) + 0.5 (kept s2)
+
+
+def test_seed_dropoff_lowers_seedcount(conn):
+    insert_watched_artist(conn, mbid="s1", name="Seed One",
+                          last_discovered_sql="now() - interval '200 hours'")
+    insert_watched_artist(conn, mbid="s2", name="Seed Two",
+                          last_discovered_sql="now() - interval '200 hours'")
+    src = FakeSimilaritySource(similar={
+        "s1": [SimilarArtist("c1", "Shared", 0.6)],
+        "s2": [SimilarArtist("c1", "Shared", 0.5)],
+    })
+    run_discovery(conn, [src], FakeMbBrowser(), DiscoveryConfig())
+    assert _artist_score(conn, "c1") == (1.1, 2)
+
+    # s1 re-swept but no longer finds c1 -> its contribution is removed, c1 recomputed.
+    with conn.cursor() as cur:
+        cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() - interval \'200 hours\' WHERE mbid = %s', ("s1",))
+        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())
+    assert _artist_score(conn, "c1") == (0.5, 1)  # only s2 remains
+
+
 def test_run_discovery_processes_at_most_chunk_size_seeds(conn):
    from lyra_worker.discovery import DiscoveryConfig, run_discovery
    from lyra_worker.adapters.fakes import FakeMbBrowser, FakeSimilaritySource