fix(worker): resolve MB to the original edition + loosen duration gate

Root cause of albums re-downloading forever despite completing (Linkin Park "Hybrid
Theory"): the MB resolver read the tracklist from an arbitrary releases[0], often a
later reissue/deluxe. HT resolved to a 2023 13-track reissue (~52 min); a complete
2000 12-track download (~38 min) then failed _download_problem's duration gate
(2267s < 2877s×0.85) and fell through peer after peer, never importing.

- _pick_release: choose the ORIGINAL standard edition (Official, earliest date)
  instead of releases[0], so completeness/duration are judged against the edition
  sources actually deliver.
- _DURATION_MIN_RATIO 0.85 -> 0.65: a source legitimately delivering a shorter
  edition than MB's release shouldn't be rejected; only genuinely truncated/preview
  downloads (a fraction of expected runtime) should be.

Together with the est-time peer ranking, this stops the download→reject→re-download
loop. 334 tests pass.

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

worker/lyra_worker/_musicbrainz.py

@@ -75,6 +75,23 @@ def _best_release_group(artist: str, album: str, groups: list) -> dict | None:
     return best
 
 
+def _pick_release(releases: list) -> dict | None:
+    """Choose which release of a release-group to read the tracklist from. MB returns them in an
+    arbitrary order and ``releases[0]`` is often a later reissue/deluxe/anniversary edition with
+    more tracks and a longer runtime than the standard album a source actually delivers — which
+    then makes a *complete* download fail the pipeline's track-count/duration completeness checks
+    and re-download forever (Linkin Park "Hybrid Theory": MB's arbitrary pick was a 2023 13-track
+    reissue at ~52 min vs the 2000 original's 12 tracks / ~38 min). Prefer the ORIGINAL standard
+    edition: an Official release, then the earliest date, then a dated one. Pure — unit-tested."""
+    if not releases:
+        return None
+    def _key(r: dict) -> tuple:
+        official = 0 if (r.get("status") == "Official") else 1  # official editions first
+        date = r.get("date") or ""
+        return (official, 0 if date else 1, date)  # then dated, then earliest date
+    return min(releases, key=_key)
+
+
 class MusicBrainzResolver:
     """Real MbResolver using the MusicBrainz webservice via musicbrainzngs.
 
@@ -119,9 +136,10 @@ class MusicBrainzResolver:
         if rgid:
             rgfull = _with_retry(lambda: musicbrainzngs.get_release_group_by_id(rgid, includes=["releases"]))
             releases = rgfull.get("release-group", {}).get("release-list", [])
-            if releases:
+            chosen = _pick_release(releases)
+            if chosen:
                 rel = _with_retry(
-                    lambda: musicbrainzngs.get_release_by_id(releases[0]["id"], includes=["recordings"])
+                    lambda: musicbrainzngs.get_release_by_id(chosen["id"], includes=["recordings"])
                 ).get("release", {})
                 tracks = []
                 for medium in rel.get("medium-list", []):

worker/lyra_worker/pipeline.py

@@ -22,8 +22,10 @@ _AUDIO_EXT = {".flac", ".mp3", ".m4a", ".opus", ".ogg", ".aac", ".wav"}
 # Reject a download whose total playtime falls below this fraction of MusicBrainz's expected
 # total — catches truncated files / preview clips substituted for real tracks that keep the
 # track COUNT right. Generous, so edition/encoding differences don't false-positive; bonus
-# tracks (over-long) are always fine.
+# tracks (over-long) are always fine. Kept well below 1.0 because a source legitimately delivers a
-_DURATION_MIN_RATIO = 0.85
+# different edition than MB's resolved release (shorter radio edits, no bonus/live tracks), and only
+# a genuinely truncated/preview-filled download (playtime a fraction of expected) should be caught.
+_DURATION_MIN_RATIO = 0.65
 # Cap how many ranked candidates a single job will actually download+verify before giving up.
 # Without this, the incomplete-download fall-through can grind through dozens of sources (a popular
 # album returns ~200 Soulseek candidates), each a slow attempt that also leaves an abandoned slskd

worker/tests/test_musicbrainz.py

@@ -1,7 +1,7 @@
 import musicbrainzngs
 import pytest
 
-from lyra_worker._musicbrainz import _best_release_group, _with_retry
+from lyra_worker._musicbrainz import _best_release_group, _pick_release, _with_retry
 
 # Offline unit tests for the pure release-group selection logic. The live resolve()
 # path (network) is covered by test_musicbrainz_live.py.
@@ -68,6 +68,30 @@ def test_prefers_credited_artist_over_same_titled_other_artist_album():
 # --- _with_retry: transient MusicBrainz failures (SSL EOF, 503 rate-limit) ---
 
 
+def test_pick_release_prefers_original_official_over_later_reissue():
+    # Real "Hybrid Theory" bug: MB's arbitrary releases[0] was a 2023 13-track reissue; the 2000
+    # original is what sources deliver, so completeness checks must reference it.
+    releases = [
+        {"id": "reissue", "status": "Official", "date": "2023-06-01"},
+        {"id": "original", "status": "Official", "date": "2000-10-24"},
+        {"id": "deluxe", "status": "Official", "date": "2020-10-09"},
+    ]
+    assert _pick_release(releases)["id"] == "original"
+
+
+def test_pick_release_skips_non_official_and_undated():
+    releases = [
+        {"id": "promo", "status": "Promotion", "date": "1999-01-01"},  # earliest but not official
+        {"id": "undated", "status": "Official", "date": ""},
+        {"id": "official", "status": "Official", "date": "2001-03-03"},
+    ]
+    assert _pick_release(releases)["id"] == "official"
+
+
+def test_pick_release_empty_is_none():
+    assert _pick_release([]) is None
+
+
 def test_retry_returns_value_without_backoff_when_first_call_succeeds():
     sleeps: list[float] = []
     calls = {"n": 0}