feat(worker): discovery chunk_size + seed-count in result (retire max_seeds)

Reconciled the pre-existing test_config_from_config_parses_and_defaults
test in test_discovery.py, which referenced max_seeds/maxSeeds and would
otherwise have broken.

worker/lyra_worker/discovery.py

@@ -13,7 +13,7 @@ _TRUE = {"1", "true", "yes", "on"}
 class DiscoveryConfig:
     enabled: bool = False
     interval_hours: int = 168
-    max_seeds: int = 50
+    chunk_size: int = 5
     similar_per_seed: int = 20
     albums_per_artist: int = 1
     min_score: float = 0.0
@@ -35,7 +35,7 @@ class DiscoveryConfig:
         return cls(
             enabled=str(config.get("discover.enabled", "")).strip().lower() in _TRUE,
             interval_hours=_int("discover.intervalHours", 168),
-            max_seeds=_int("discover.maxSeeds", 50),
+            chunk_size=_int("discover.chunkSize", 5),
             similar_per_seed=_int("discover.similarPerSeed", 20),
             albums_per_artist=_int("discover.albumsPerArtist", 1),
             min_score=_float("discover.minScore", 0.0),
@@ -46,6 +46,7 @@ class DiscoveryConfig:
 class DiscoveryResult:
     artists: int
     albums: int
+    seeds: int = 0
 
 
 def _healthy_sources(sources):
@@ -68,7 +69,7 @@ def _seed_artists(conn: psycopg.Connection, cfg: DiscoveryConfig):
             'WHERE "lastDiscoveredAt" IS NULL '
             '   OR "lastDiscoveredAt" < now() - make_interval(hours => %s) '
             'ORDER BY "lastDiscoveredAt" ASC NULLS FIRST LIMIT %s',
-            (cfg.interval_hours, cfg.max_seeds),
+            (cfg.interval_hours, cfg.chunk_size),
         )
         return cur.fetchall()
 
@@ -190,4 +191,4 @@ def run_discovery(conn: psycopg.Connection, sources: list[SimilaritySource],
             cur.execute('UPDATE "WatchedArtist" SET "lastDiscoveredAt" = now() WHERE mbid = %s',
                         (seed_mbid,))
     conn.commit()
-    return DiscoveryResult(artists=artists, albums=albums)
+    return DiscoveryResult(artists=artists, albums=albums, seeds=len(seeds))

worker/tests/test_discovery.py

@@ -88,9 +88,26 @@ def test_source_with_raising_health_is_skipped_not_fatal(conn):
 
 
 def test_config_from_config_parses_and_defaults():
-    cfg = DiscoveryConfig.from_config({"discover.enabled": "true", "discover.maxSeeds": "10",
+    cfg = DiscoveryConfig.from_config({"discover.enabled": "true", "discover.chunkSize": "10",
                                        "discover.minScore": "0.3"})
-    assert cfg.enabled is True and cfg.max_seeds == 10 and cfg.min_score == 0.3
+    assert cfg.enabled is True and cfg.chunk_size == 10 and cfg.min_score == 0.3
     d = DiscoveryConfig.from_config({})
-    assert (d.enabled, d.interval_hours, d.max_seeds, d.similar_per_seed,
+    assert (d.enabled, d.interval_hours, d.chunk_size, d.similar_per_seed,
-            d.albums_per_artist, d.min_score) == (False, 168, 50, 20, 1, 0.0)
+            d.albums_per_artist, d.min_score) == (False, 168, 5, 20, 1, 0.0)
+
+
+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
+    from lyra_worker.similarity.base import SimilarArtist
+    from tests.conftest import insert_watched_artist
+    for i in range(4):
+        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)
+    assert result.seeds == 2          # only chunk_size seeds this call
+    # exactly 2 seeds now have lastDiscoveredAt set
+    with conn.cursor() as cur:
+        cur.execute('SELECT count(*) FROM "WatchedArtist" WHERE "lastDiscoveredAt" IS NOT NULL')
+        assert cur.fetchone()[0] == 2