feat(fc-cleanup): audit lifecycle service functions (start/apply/cancel) + tests — Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/app/services/cleanup_service.py

@@ -12,12 +12,14 @@ re-exports from this module and then delete the wrapper.
 """
 from __future__ import annotations
 
+from datetime import UTC, datetime
 from pathlib import Path
+from typing import Any
 
-from sqlalchemy import func, select
+from sqlalchemy import func, select, update
 from sqlalchemy.orm import Session
 
-from ..models import Artist, ImageRecord, Tag
+from ..models import Artist, ImageRecord, LibraryAuditRun, Tag
 from ..models.series_page import SeriesPage
 from ..models.tag import image_tag
 
@@ -409,3 +411,98 @@ def delete_min_dimension_violations(
         session, image_ids=list(ids), images_root=images_root,
     )
     return result["images_deleted"]
+
+
+# ---------------------------------------------------------------------------
+# Audit lifecycle (transparency + single_color async scans).
+# ---------------------------------------------------------------------------
+
+
+class AuditAlreadyRunning(Exception):
+    """Another audit_run is currently in status='running' — wait or
+    cancel it before starting a new one. Surfaces as HTTP 409 in the
+    /api/cleanup/audit POST endpoint."""
+
+
+class AuditNotReady(Exception):
+    """apply_audit_run called on an audit whose status is not 'ready'."""
+
+
+class ConfirmTokenMismatch(Exception):
+    """Operator-supplied confirm token did not match server-recomputed token."""
+
+
+_VALID_RULES = ("transparency", "single_color")
+
+
+def start_audit_run(
+    session: Session, *, rule: str, params: dict[str, Any],
+) -> int:
+    """Create a LibraryAuditRun row in status='running' and dispatch the
+    scan_library_for_rule Celery task. Returns the new audit_id.
+
+    Concurrent-runs guard: raises AuditAlreadyRunning if any audit_run
+    has status='running'. Operator must cancel or wait."""
+    if rule not in _VALID_RULES:
+        raise ValueError(f"unknown rule {rule!r}; expected one of {_VALID_RULES}")
+    existing = session.execute(
+        select(LibraryAuditRun.id).where(LibraryAuditRun.status == "running")
+    ).scalar_one_or_none()
+    if existing is not None:
+        raise AuditAlreadyRunning(existing)
+    audit = LibraryAuditRun(
+        rule=rule,
+        params=params,
+        status="running",
+        scanned_count=0,
+        matched_count=0,
+        matched_ids=[],
+    )
+    session.add(audit)
+    session.flush()
+    audit_id = audit.id
+    # Dispatch after flush so audit_id is populated; commit happens in
+    # the API handler so the audit row + dispatch are visible together.
+    from ..tasks.library_audit import scan_library_for_rule
+    scan_library_for_rule.delay(audit_id)
+    return audit_id
+
+
+def apply_audit_run(
+    session: Session, *, audit_id: int, confirm_token: str, images_root: Path,
+) -> int:
+    """Delete all images in audit_run.matched_ids after confirming token.
+    Marks audit status='applied'. Routes through delete_images so files
+    + cascading FK rows are handled uniformly."""
+    audit = session.execute(
+        select(LibraryAuditRun).where(LibraryAuditRun.id == audit_id)
+    ).scalar_one_or_none()
+    if audit is None:
+        raise ValueError(f"audit_run {audit_id} not found")
+    if audit.status != "ready":
+        raise AuditNotReady(audit.status)
+    expected = f"apply-audit-{audit_id}"
+    if confirm_token != expected:
+        raise ConfirmTokenMismatch(expected)
+    ids = list(audit.matched_ids or [])
+    deleted = 0
+    if ids:
+        result = delete_images(session, image_ids=ids, images_root=images_root)
+        deleted = result["images_deleted"]
+    session.execute(
+        update(LibraryAuditRun)
+        .where(LibraryAuditRun.id == audit_id)
+        .values(status="applied", finished_at=datetime.now(UTC))
+    )
+    return deleted
+
+
+def cancel_audit_run(session: Session, *, audit_id: int) -> None:
+    """Flip a running audit_run to 'cancelled'. The scan task checks
+    for status=='cancelled' between batches and exits cleanly."""
+    session.execute(
+        update(LibraryAuditRun)
+        .where(LibraryAuditRun.id == audit_id)
+        .where(LibraryAuditRun.status == "running")
+        .values(status="cancelled", finished_at=datetime.now(UTC))
+    )

tests/test_cleanup_service_audit.py

@@ -74,3 +74,99 @@ def test_delete_min_dimension_violations_unlinks_and_cascades(db_sync, tmp_path)
     ).scalars().all()
     assert remaining_ids == [rec_big.id]
     assert not small_path.exists()  # file unlinked
+
+
+# --- Audit lifecycle tests (Task 5) ---
+
+import backend.app.tasks.library_audit  # noqa: F401, E402 — celery registration
+
+
+def test_start_audit_run_creates_row_and_dispatches(db_sync, monkeypatch):
+    dispatched = []
+    from backend.app.tasks import library_audit as la_mod
+    monkeypatch.setattr(
+        la_mod.scan_library_for_rule, "delay",
+        lambda audit_id: dispatched.append(audit_id),
+    )
+    audit_id = cleanup_service.start_audit_run(
+        db_sync, rule="transparency", params={"threshold": 0.9},
+    )
+    db_sync.commit()
+    row_status = db_sync.execute(
+        select(LibraryAuditRun.status).where(LibraryAuditRun.id == audit_id)
+    ).scalar_one()
+    assert row_status == "running"
+    assert dispatched == [audit_id]
+
+
+def test_start_audit_run_rejects_when_another_is_running(db_sync, monkeypatch):
+    from backend.app.tasks import library_audit as la_mod
+    monkeypatch.setattr(
+        la_mod.scan_library_for_rule, "delay", lambda audit_id: None,
+    )
+    cleanup_service.start_audit_run(
+        db_sync, rule="transparency", params={"threshold": 0.9},
+    )
+    db_sync.commit()
+    with pytest.raises(cleanup_service.AuditAlreadyRunning):
+        cleanup_service.start_audit_run(
+            db_sync, rule="single_color",
+            params={"threshold": 0.95, "tolerance": 30},
+        )
+
+
+def test_apply_audit_run_with_correct_token_deletes_matched(db_sync, tmp_path):
+    rec = _make_image_record(
+        db_sync, tmp_path, width=100, height=100, color=(60, 0, 0),
+    )
+    db_sync.flush()
+    audit = LibraryAuditRun(
+        rule="transparency", params={"threshold": 0.9},
+        status="ready", scanned_count=1, matched_count=1,
+        matched_ids=[rec.id],
+    )
+    db_sync.add(audit)
+    db_sync.commit()
+
+    deleted = cleanup_service.apply_audit_run(
+        db_sync, audit_id=audit.id,
+        confirm_token=f"apply-audit-{audit.id}",
+        images_root=tmp_path,
+    )
+    assert deleted == 1
+    remaining_count = db_sync.execute(
+        select(func.count()).select_from(ImageRecord)
+    ).scalar_one()
+    assert remaining_count == 0
+    new_status = db_sync.execute(
+        select(LibraryAuditRun.status).where(LibraryAuditRun.id == audit.id)
+    ).scalar_one()
+    assert new_status == "applied"
+
+
+def test_apply_audit_run_with_wrong_token_raises(db_sync, tmp_path):
+    audit = LibraryAuditRun(
+        rule="transparency", params={"threshold": 0.9},
+        status="ready", matched_ids=[],
+    )
+    db_sync.add(audit)
+    db_sync.commit()
+    with pytest.raises(cleanup_service.ConfirmTokenMismatch):
+        cleanup_service.apply_audit_run(
+            db_sync, audit_id=audit.id,
+            confirm_token="wrong-token", images_root=tmp_path,
+        )
+
+
+def test_cancel_audit_run_flips_status(db_sync):
+    audit = LibraryAuditRun(
+        rule="transparency", params={"threshold": 0.9},
+        status="running", matched_ids=[],
+    )
+    db_sync.add(audit)
+    db_sync.commit()
+    cleanup_service.cancel_audit_run(db_sync, audit_id=audit.id)
+    new_status = db_sync.execute(
+        select(LibraryAuditRun.status).where(LibraryAuditRun.id == audit.id)
+    ).scalar_one()
+    assert new_status == "cancelled"