feat(discovery): ListenBrainz similarity source

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

worker/lyra_worker/similarity/_listenbrainz.py

@@ -0,0 +1,49 @@
+import requests
+
+from lyra_worker.similarity.base import SimilarArtist
+
+_DEFAULT_URL = "https://labs.api.listenbrainz.org"
+# ListenBrainz Labs similar-artists dataset requires an algorithm parameter.
+# NOTE: confirm this string + response field names against the live API during
+# manual verification; parsing below is defensive if the shape shifts.
+_DEFAULT_ALGORITHM = (
+    "session_based_days_7500_session_300_contribution_5_threshold_15_limit_50_filter_True_skip_30"
+)
+
+
+class ListenBrainzSource:
+    """SimilaritySource backed by the (unauthenticated) ListenBrainz Labs API."""
+
+    name = "listenbrainz"
+
+    def __init__(self, base_url: str = _DEFAULT_URL, algorithm: str = _DEFAULT_ALGORITHM,
+                 timeout: float = 15.0):
+        self._base = (base_url or _DEFAULT_URL).rstrip("/")
+        self._algorithm = algorithm
+        self._timeout = timeout
+
+    def health(self) -> bool:
+        try:
+            res = requests.get(self._base + "/", timeout=self._timeout)
+            return res.status_code < 500
+        except requests.RequestException:
+            return False
+
+    def similar_artists(self, mbid: str) -> list[SimilarArtist]:
+        res = requests.get(
+            self._base + "/similar-artists/json",
+            params={"artist_mbids": mbid, "algorithm": self._algorithm},
+            timeout=self._timeout,
+        )
+        res.raise_for_status()
+        out: list[SimilarArtist] = []
+        for row in res.json() or []:
+            ambid = row.get("artist_mbid")
+            if not ambid or ambid == mbid:
+                continue
+            out.append(SimilarArtist(
+                mbid=ambid,
+                name=row.get("name") or row.get("comment") or "",
+                score=float(row.get("score") or 0),
+            ))
+        return out

worker/tests/test_listenbrainz.py

@@ -0,0 +1,43 @@
+from unittest.mock import MagicMock, patch
+
+import requests
+
+from lyra_worker.similarity._listenbrainz import ListenBrainzSource
+from lyra_worker.similarity.base import SimilarArtist
+
+
+def _resp(payload, status=200):
+    r = MagicMock()
+    r.status_code = status
+    r.json.return_value = payload
+    r.raise_for_status.side_effect = (
+        None if status < 400 else requests.HTTPError(f"{status}"))
+    return r
+
+
+def test_similar_artists_parses_and_drops_self():
+    payload = [
+        {"artist_mbid": "seed", "name": "Seed", "score": 100},
+        {"artist_mbid": "c1", "name": "Cand One", "score": 42},
+        {"artist_mbid": "c2", "name": "Cand Two", "score": 7},
+    ]
+    with patch("lyra_worker.similarity._listenbrainz.requests.get", return_value=_resp(payload)):
+        out = ListenBrainzSource().similar_artists("seed")
+    assert out == [SimilarArtist("c1", "Cand One", 42.0), SimilarArtist("c2", "Cand Two", 7.0)]
+
+
+def test_similar_artists_raises_on_http_error():
+    with patch("lyra_worker.similarity._listenbrainz.requests.get", return_value=_resp([], status=500)):
+        try:
+            ListenBrainzSource().similar_artists("seed")
+            assert False, "expected HTTPError"
+        except requests.HTTPError:
+            pass
+
+
+def test_health_true_on_2xx_false_on_exception():
+    with patch("lyra_worker.similarity._listenbrainz.requests.get", return_value=_resp([], status=200)):
+        assert ListenBrainzSource().health() is True
+    with patch("lyra_worker.similarity._listenbrainz.requests.get",
+               side_effect=requests.ConnectionError("down")):
+        assert ListenBrainzSource().health() is False