feat(deep-scan): IR-parity port — refreshed status + counter, re-queue completed paths in deep mode, honest UX — Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

This commit is contained in:
2026-05-25 22:16:26 -04:00
parent c06cbc0abe
commit e6ededbe8e
11 changed files with 251 additions and 29 deletions
+17 -8
View File
@@ -59,16 +59,25 @@ def scan_directory(self, triggered_by: str = "manual",
session.flush()
batch_id = batch.id
# Skip-set: any source_path that already has a non-failed ImportTask
# row. Re-running scan_directory must not re-enqueue files the
# importer has already handled (or is currently handling); doing so
# creates duplicate work and inflates the queue. Failed prior tasks
# are eligible for retry.
# Skip-set behavior splits by mode (operator-flagged 2026-05-25):
#
# quick: any non-failed prior ImportTask (active OR finished) is
# skipped — quick scan only does new-file enqueue, so re-touching
# already-imported files is wasted work.
#
# deep: ONLY currently-in-flight tasks (pending/queued/processing)
# are skipped. Completed and skipped tasks ARE re-queued because
# deep scan exists precisely to re-touch already-imported files
# (refresh sidecar metadata, fill NULL phash, fill NULL artist
# via Importer._deep_rederive). Matches IR's deep-scan behavior.
active_statuses = ["pending", "queued", "processing"]
if mode == "deep":
skip_statuses = active_statuses
else:
skip_statuses = active_statuses + ["complete", "skipped"]
non_failed_existing = set(session.execute(
select(ImportTask.source_path).where(
ImportTask.status.in_(
["pending", "queued", "processing", "complete", "skipped"]
),
ImportTask.status.in_(skip_statuses),
)
).scalars().all())