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
+21 -6
View File
@@ -51,7 +51,14 @@ class SkipReason(StrEnum):
@dataclass(frozen=True)
class ImportResult:
status: str # 'imported'|'skipped'|'failed'|'superseded'|'attached'
# 'imported' — new ImageRecord row created
# 'superseded' — existing ImageRecord row got the new file (larger) + sidecar
# 'attached' — non-media saved as PostAttachment
# 'refreshed' — deep scan re-applied sidecar / filled NULL phash / NULL
# artist on an already-imported row (no new ImageRecord)
# 'skipped' — no work done (true duplicate, too small, etc.)
# 'failed' — pipeline error
status: str
image_id: int | None = None
skip_reason: SkipReason | None = None
error: str | None = None
@@ -417,7 +424,18 @@ class Importer:
) -> ImportResult:
"""Deep scan: backfill phash/provenance/artist on an
already-imported record. METADATA ONLY — never re-runs the pHash
near-dup / supersede path. NULL-only, idempotent."""
near-dup / supersede path. NULL-only on phash/artist, additive on
sidecar Post/Source/ImageProvenance (via _apply_sidecar).
Idempotent: a second deep-scan over the same file finds nothing
to refresh and is a no-op.
Returns status="refreshed" so the UI can surface the work done
instead of the prior misleading "skipped/duplicate_hash" reading.
Operator-flagged 2026-05-25 — IR has had this; FC inherited it
as a no-op skip during the original port and the UI showed deep
scan as "completed with no changes" even when sidecar metadata
actually got re-applied to N existing rows.
"""
if existing.phash is None and not is_video(source):
try:
with Image.open(source) as im:
@@ -436,10 +454,7 @@ class Importer:
self._apply_sidecar(existing, attribution_path, artist)
self.session.commit()
return ImportResult(
status="skipped", skip_reason=SkipReason.duplicate_hash,
image_id=existing.id, error="deep: re-derived",
)
return ImportResult(status="refreshed", image_id=existing.id)
def attach_in_place(
self,