feat(fc-cleanup): min-dimension service functions + tests — Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/app/services/cleanup_service.py

@@ -365,3 +365,47 @@ def prune_unused_tags(session: Session, *, dry_run: bool = False) -> dict:
         )
         session.commit()
     return {"deleted": len(ids), "sample_names": sample}
+
+
+# ---------------------------------------------------------------------------
+# FC-Cleanup additions (2026-05-26): retroactive audit of import-filter rules.
+# ---------------------------------------------------------------------------
+
+_MIN_DIM_SAMPLE_CAP = 50
+
+
+def project_min_dimension_violations(
+    session: Session, *, min_width: int, min_height: int,
+) -> dict:
+    """Return {count, sample_ids} for image_record rows with width or
+    height below the thresholds. Synchronous SQL — no PIL inspection
+    needed since width/height are stored columns."""
+    base = select(ImageRecord.id).where(
+        (ImageRecord.width < min_width) | (ImageRecord.height < min_height)
+    )
+    count = session.execute(
+        select(func.count()).select_from(base.subquery())
+    ).scalar_one()
+    sample_ids = session.execute(
+        base.order_by(ImageRecord.id).limit(_MIN_DIM_SAMPLE_CAP)
+    ).scalars().all()
+    return {"count": count, "sample_ids": list(sample_ids)}
+
+
+def delete_min_dimension_violations(
+    session: Session, *, min_width: int, min_height: int, images_root: Path,
+) -> int:
+    """Delete every image_record where width<min_w OR height<min_h.
+    Routes through delete_images so file-unlink + cascading FKs
+    (image_tag / image_provenance / etc.) are handled uniformly."""
+    ids = session.execute(
+        select(ImageRecord.id).where(
+            (ImageRecord.width < min_width) | (ImageRecord.height < min_height)
+        )
+    ).scalars().all()
+    if not ids:
+        return 0
+    result = delete_images(
+        session, image_ids=list(ids), images_root=images_root,
+    )
+    return result["images_deleted"]