feat(fc-cleanup): migration 0020 + LibraryAuditRun model — Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

alembic/versions/0020_library_audit_run.py

@@ -0,0 +1,65 @@
+"""fc-cleanup: library_audit_run table for async transparency/single_color audits
+
+Revision ID: 0020
+Revises: 0019
+Create Date: 2026-05-26
+
+The table backs the async audit lifecycle: rule + params snapshot, status
+state machine ('running' → 'ready' → 'applied'/'cancelled'/'error'), and
+the matched_ids JSONB array that the apply step deletes. Capped at 50k IDs
+per row by the scan task (oversize = rule too aggressive, operator narrows
+before re-running).
+"""
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+revision: str = "0020"
+down_revision: Union[str, None] = "0019"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "library_audit_run",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("rule", sa.String(32), nullable=False),
+        sa.Column("params", postgresql.JSONB(astext_type=sa.Text()), nullable=False),
+        sa.Column(
+            "status", sa.String(16),
+            nullable=False, server_default="running",
+        ),
+        sa.Column(
+            "started_at", sa.DateTime(timezone=True),
+            nullable=False, server_default=sa.func.now(),
+        ),
+        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column(
+            "scanned_count", sa.Integer(),
+            nullable=False, server_default="0",
+        ),
+        sa.Column(
+            "matched_count", sa.Integer(),
+            nullable=False, server_default="0",
+        ),
+        sa.Column(
+            "matched_ids", postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False, server_default=sa.text("'[]'::jsonb"),
+        ),
+        sa.Column("error", sa.Text(), nullable=True),
+    )
+    op.create_index(
+        "ix_library_audit_run_rule", "library_audit_run", ["rule"],
+    )
+    op.create_index(
+        "ix_library_audit_run_status", "library_audit_run", ["status"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("ix_library_audit_run_status", table_name="library_audit_run")
+    op.drop_index("ix_library_audit_run_rule", table_name="library_audit_run")
+    op.drop_table("library_audit_run")

backend/app/models/__init__.py

@@ -11,6 +11,7 @@ from .image_record import ImageRecord
 from .import_batch import ImportBatch
 from .import_settings import ImportSettings
 from .import_task import ImportTask
+from .library_audit_run import LibraryAuditRun
 from .migration_run import MigrationRun
 from .ml_settings import MLSettings
 from .post import Post
@@ -43,6 +44,7 @@ __all__ = [
     "ImportBatch",
     "ImportTask",
     "ImportSettings",
+    "LibraryAuditRun",
     "MLSettings",
     "MigrationRun",
     "TagAlias",

backend/app/models/library_audit_run.py

@@ -0,0 +1,37 @@
+"""LibraryAuditRun — async transparency / single_color audit lifecycle.
+
+State machine: running → ready → applied / cancelled / error.
+matched_ids JSONB is appended-to by scan_library_for_rule; apply_audit_run
+reads it and routes through cleanup_service.delete_images.
+"""
+
+from datetime import datetime
+from typing import Any
+
+from sqlalchemy import DateTime, Integer, String, Text, func
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class LibraryAuditRun(Base):
+    __tablename__ = "library_audit_run"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True)
+    rule: Mapped[str] = mapped_column(String(32), nullable=False, index=True)
+    params: Mapped[dict[str, Any]] = mapped_column(JSONB, nullable=False)
+    status: Mapped[str] = mapped_column(
+        String(16), nullable=False, default="running", index=True,
+    )
+    # running | ready | applied | cancelled | error
+    started_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now(),
+    )
+    finished_at: Mapped[datetime | None] = mapped_column(
+        DateTime(timezone=True), nullable=True,
+    )
+    scanned_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    matched_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    matched_ids: Mapped[list[int]] = mapped_column(JSONB, nullable=False, default=list)
+    error: Mapped[str | None] = mapped_column(Text, nullable=True)