feat(enrichment): record status/errors and trust high-confidence AcoustID
Two related gaps surfaced from "uploaded a track, nothing changed / no status": - A track could stay stuck on `pending` forever (an unexpected worker error rolled back the run without recording anything), and `failed` carried no reason. Add `tracks.metadata_error` + `tracks.enriched_at` (migration), stamp the outcome in apply_enrichment, add TrackRepository.mark_enrichment_failed, wrap enrich_task to persist crashes as `failed` in a fresh session, and emit a human-readable no-match reason. Expose metadata_error/enriched_at in TrackOut. - The tag-first merge let junk embedded tags (e.g. "Music Track"/"Sound_13958") override even a 0.99-confidence AcoustID match. Add acoustid_trust_score (default 0.85): above it the acoustic identity wins for title/artist/album/ year, tags are fallback; below it, tag-first as before. Add a license-free real-file fixture (Scarlet Fire / Otis McDonald) whose junk tags AcoustID overrides, with an always-on tag-reader test plus fpcalc/AcoustID/ network-gated identity + full-pipeline tests (skip on host, run in the container). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -6,9 +6,10 @@
|
||||
imports/downloads stay idempotent (plan §4, §6.1).
|
||||
"""
|
||||
|
||||
import datetime as dt
|
||||
import uuid
|
||||
|
||||
from sqlalchemy import ForeignKey, Integer, String, UniqueConstraint
|
||||
from sqlalchemy import DateTime, ForeignKey, Integer, String, UniqueConstraint
|
||||
from sqlalchemy.orm import Mapped, mapped_column
|
||||
|
||||
from app.infrastructure.db.base import Base
|
||||
@@ -63,6 +64,16 @@ class TrackModel(UUIDPrimaryKeyMixin, TimestampMixin, Base):
|
||||
nullable=False,
|
||||
default=MetadataStatus.PENDING.value,
|
||||
)
|
||||
# Human-readable reason the last enrichment run set ``failed`` (no match, or
|
||||
# an unexpected worker error). ``None`` once a run succeeds. Surfaced in the
|
||||
# UI so a stuck/failed track is diagnosable, not silent.
|
||||
metadata_error: Mapped[str | None] = mapped_column(String(2048), nullable=True)
|
||||
# When the last enrichment run finished (success or failure). ``None`` while
|
||||
# still ``pending`` — lets the UI distinguish "queued/running" from "done".
|
||||
enriched_at: Mapped[dt.datetime | None] = mapped_column(
|
||||
DateTime(timezone=True),
|
||||
nullable=True,
|
||||
)
|
||||
|
||||
added_by: Mapped[uuid.UUID | None] = mapped_column(
|
||||
ForeignKey("users.id", ondelete="SET NULL"),
|
||||
|
||||
@@ -39,6 +39,8 @@ def _track_to_entity(row: TrackModel) -> Track:
|
||||
genre=row.genre,
|
||||
year=row.year,
|
||||
metadata_status=row.metadata_status,
|
||||
metadata_error=row.metadata_error,
|
||||
enriched_at=row.enriched_at,
|
||||
created_at=row.created_at,
|
||||
updated_at=row.updated_at,
|
||||
)
|
||||
|
||||
@@ -38,6 +38,8 @@ def _track_to_entity(row: TrackModel) -> Track:
|
||||
genre=row.genre,
|
||||
year=row.year,
|
||||
metadata_status=row.metadata_status,
|
||||
metadata_error=row.metadata_error,
|
||||
enriched_at=row.enriched_at,
|
||||
created_at=row.created_at,
|
||||
updated_at=row.updated_at,
|
||||
)
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
"""Track repository — adapter over ``AsyncSession``."""
|
||||
|
||||
import datetime as dt
|
||||
import uuid
|
||||
|
||||
from sqlalchemy import func, select
|
||||
@@ -26,6 +27,8 @@ def _to_entity(row: TrackModel) -> Track:
|
||||
genre=row.genre,
|
||||
year=row.year,
|
||||
metadata_status=row.metadata_status,
|
||||
metadata_error=row.metadata_error,
|
||||
enriched_at=row.enriched_at,
|
||||
created_at=row.created_at,
|
||||
updated_at=row.updated_at,
|
||||
)
|
||||
@@ -189,6 +192,7 @@ class SqlAlchemyTrackRepository:
|
||||
acoustid_fingerprint: str | None,
|
||||
musicbrainz_id: str | None,
|
||||
metadata_status: str,
|
||||
metadata_error: str | None = None,
|
||||
) -> Track:
|
||||
row = await self._session.get(TrackModel, track_id)
|
||||
if row is None:
|
||||
@@ -197,6 +201,10 @@ class SqlAlchemyTrackRepository:
|
||||
row.title = title
|
||||
row.artist_id = artist_id
|
||||
row.metadata_status = metadata_status
|
||||
# A finished run always stamps outcome: clear/set the reason and mark the
|
||||
# completion time so the UI can tell "still pending" from "done/failed".
|
||||
row.metadata_error = metadata_error
|
||||
row.enriched_at = dt.datetime.now(dt.UTC)
|
||||
# Nullable extras: fill gaps only — never erase data a prior run found.
|
||||
if album_id is not None:
|
||||
row.album_id = album_id
|
||||
@@ -217,3 +225,16 @@ class SqlAlchemyTrackRepository:
|
||||
await self._session.flush()
|
||||
await self._session.refresh(row)
|
||||
return _to_entity(row)
|
||||
|
||||
async def mark_enrichment_failed(self, track_id: uuid.UUID, *, error: str) -> None:
|
||||
"""Record that an enrichment run crashed (unexpected exception). Runs in
|
||||
its own session so the failure is persisted even though the run's own
|
||||
transaction rolled back. Never overwrites ``manual`` (a no-op then), and
|
||||
a missing track is a clean no-op."""
|
||||
row = await self._session.get(TrackModel, track_id)
|
||||
if row is None or row.metadata_status == "manual":
|
||||
return
|
||||
row.metadata_status = "failed"
|
||||
row.metadata_error = error
|
||||
row.enriched_at = dt.datetime.now(dt.UTC)
|
||||
await self._session.flush()
|
||||
|
||||
Reference in New Issue
Block a user