integrity: don't quarantine longer masters/versions as 'truncated' (#937)

the duration-agreement check used abs() drift, so a file running LONGER than the metadata
(a remaster with a longer outro, an extended cut) was rejected the same as a truncated one —
e.g. A-Ha 'Take on Me' remaster at 228.5s vs 225.0s expected, quarantined for +3.5s.

but a longer file is the OPPOSITE of truncated. make the auto tolerance asymmetric: keep the
tight 3s/5s bound for SHORTER files (the truncation case the check exists for), allow up to
15s in the LONGER direction for version/master differences. a wrong song still trips it (off
by far more than 15s), and a user-pinned tolerance is honoured symmetrically. direction-aware
rejection message too. 4 new tests; 274 integrity/import tests green.

core/imports/file_integrity.py

@@ -52,6 +52,14 @@ _DEFAULT_LENGTH_TOLERANCE_S = 3.0
 _LENGTH_TOLERANCE_LONG_TRACK_S = 5.0
 _LONG_TRACK_THRESHOLD_S = 600.0  # 10 minutes
 
+# A file that runs LONGER than the expected metadata is the opposite of a truncated
+# download — it's almost always a different master/version (a remaster with a longer
+# outro, an extended fade, an album cut vs the radio edit). The duration check exists to
+# catch TRUNCATION (short files) and wildly-wrong matches, so on the auto default we allow
+# more drift in the longer direction and keep the tight bound for short files. A wrong-song
+# match still trips this — it's usually off by far more than 15s. (#937)
+_LONGER_VERSION_TOLERANCE_S = 15.0
+
 # Upper bound for the user-configurable override. Anything past 60s
 # means the check is effectively off — cap defends against accidental
 # nonsense like 9999 making logs misleading. Users who genuinely want
@@ -242,18 +250,32 @@ def check_audio_integrity(
             if expected_length_s > _LONG_TRACK_THRESHOLD_S
             else _DEFAULT_LENGTH_TOLERANCE_S
         )
+        user_pinned_tolerance = False
+    else:
+        user_pinned_tolerance = True
     checks["length_tolerance_s"] = length_tolerance_s
 
-    drift_s = abs(actual_length_s - expected_length_s)
+    # Positive drift = the file runs LONGER than expected (not truncation). On the auto
+    # default, give the longer direction more room so legit longer masters/versions aren't
+    # quarantined (#937); a user-pinned tolerance is honoured symmetrically.
+    signed_drift_s = actual_length_s - expected_length_s
+    drift_s = abs(signed_drift_s)
     checks["length_drift_s"] = drift_s
+    effective_tolerance_s = length_tolerance_s
+    if signed_drift_s > 0 and not user_pinned_tolerance:
+        effective_tolerance_s = max(length_tolerance_s, _LONGER_VERSION_TOLERANCE_S)
+    checks["effective_tolerance_s"] = effective_tolerance_s
 
-    if drift_s > length_tolerance_s:
+    if drift_s > effective_tolerance_s:
+        runs_long = signed_drift_s > 0
         return IntegrityResult(
             ok=False,
             reason=f"Duration mismatch: file is {actual_length_s:.1f}s, "
                    f"expected {expected_length_s:.1f}s "
-                   f"(drift {drift_s:.1f}s > tolerance {length_tolerance_s:.1f}s) — "
+                   f"(drift {drift_s:.1f}s > tolerance {effective_tolerance_s:.1f}s) — "
-                   "likely truncated download or wrong file matched",
+                   + ("runs longer than expected — likely a different version/master or wrong file"
+                      if runs_long
+                      else "likely truncated download or wrong file matched"),
             checks=checks,
         )
 

tests/imports/test_file_integrity.py

@@ -201,6 +201,60 @@ def test_rejects_truncated_file(tmp_path: Path) -> None:
     assert result.checks["length_drift_s"] > 3.0
 
 
+# ── #937: a file that runs LONGER than expected is a version/master difference, not
+#    truncation — it gets more leeway, while SHORTER files stay tight. ──
+
+def test_accepts_longer_master_beyond_short_tolerance(tmp_path: Path) -> None:
+    """The reported case (A-Ha remaster): file runs ~3.5s LONGER than the metadata.
+    Past the 3s short-tolerance but a remaster, not a bad download — must pass."""
+    f = tmp_path / "remaster.wav"
+    _write_minimal_wav(f, duration_s=9.0)   # 9.0s file vs 5.5s expected → +3.5s longer
+
+    result = file_integrity.check_audio_integrity(str(f), expected_duration_ms=5500)
+
+    assert result.ok is True
+    assert result.checks["length_check"] == "passed"
+    assert result.checks["effective_tolerance_s"] == pytest.approx(15.0)
+
+
+def test_shorter_file_still_tight_after_longer_loosening(tmp_path: Path) -> None:
+    """Loosening the LONGER direction must not loosen truncation detection — a file
+    3.5s SHORTER than expected is still rejected at the 3s tolerance."""
+    f = tmp_path / "short.wav"
+    _write_minimal_wav(f, duration_s=5.5)   # 5.5s vs 9.0s expected → -3.5s shorter
+
+    result = file_integrity.check_audio_integrity(str(f), expected_duration_ms=9000)
+
+    assert result.ok is False
+    assert "truncated" in result.reason.lower()
+    assert result.checks["effective_tolerance_s"] == pytest.approx(3.0)
+
+
+def test_wildly_longer_file_still_rejected(tmp_path: Path) -> None:
+    """A different/wrong song that happens to run long is still caught — +25s blows
+    past even the 15s longer-tolerance."""
+    f = tmp_path / "wronglong.wav"
+    _write_minimal_wav(f, duration_s=30.0)  # 30s vs 5s expected → +25s
+
+    result = file_integrity.check_audio_integrity(str(f), expected_duration_ms=5000)
+
+    assert result.ok is False
+    assert "longer than expected" in result.reason.lower()
+
+
+def test_user_pinned_tolerance_is_symmetric(tmp_path: Path) -> None:
+    """An explicit user tolerance is honoured in BOTH directions — the longer-direction
+    loosening only applies to the auto default, not a value the user pinned."""
+    f = tmp_path / "long.wav"
+    _write_minimal_wav(f, duration_s=9.0)   # +4s longer
+
+    result = file_integrity.check_audio_integrity(
+        str(f), expected_duration_ms=5000, length_tolerance_s=2.0)
+
+    assert result.ok is False
+    assert result.checks["effective_tolerance_s"] == pytest.approx(2.0)
+
+
 def test_rejects_wrong_file_substituted(tmp_path: Path) -> None:
     """A 10-second clip masquerading as a 3-minute album track. slskd
     matched on a similar filename but the actual content is a snippet."""