fix: reconcile and expose failed product cleanup

backend/tests/test_cleanup_service.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import json
 import os
+import sqlite3
 import sys
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
@@ -254,6 +255,62 @@ def test_failed_cleanup_product_can_be_restored_or_requeued(tmp_path, monkeypatc
     ]
 
 
+def test_stale_purging_claim_is_reconciled_to_failed_cleanup(tmp_path, monkeypatch):
+    service = make_cleanup_service(tmp_path)
+    product = create_pending_product(service, purge_after=NOW)
+    store = service.product_store
+
+    original_fail = store.fail_product_purge
+    calls = {"n": 0}
+
+    def flaky_fail(product_id, now=None):
+        calls["n"] += 1
+        if calls["n"] == 1:
+            raise sqlite3.OperationalError("simulated busy")
+        return original_fail(product_id, now=now)
+
+    monkeypatch.setattr(store, "fail_product_purge", flaky_fail)
+    monkeypatch.setattr(
+        "service.cleanup_service.shutil.rmtree",
+        lambda *_args, **_kwargs: (_ for _ in ()).throw(OSError("disk failure")),
+    )
+
+    with pytest.raises(sqlite3.OperationalError, match="simulated busy"):
+        service.apply(now=NOW)
+
+    stranded = store._fetchone(
+        "SELECT status, claimed_at FROM cleanup_records WHERE product_id = ?",
+        (product.product_id,),
+    )
+    assert stranded["status"] == "purging"
+    assert datetime.fromisoformat(stranded["claimed_at"]) == NOW
+
+    report = service.preview(now=NOW + timedelta(hours=2))
+
+    assert [item.product_id for item in report.failed_products] == [product.product_id]
+    assert store.get_product(product.product_id).status == "failed_cleanup"
+    assert store.due_product_cleanups(NOW + timedelta(days=1)) == []
+
+
+def test_cleanup_candidates_reports_failed_products(tmp_path, monkeypatch):
+    service = make_cleanup_service(tmp_path)
+    product = create_pending_product(service, purge_after=NOW)
+    store = service.product_store
+    store.claim_product_purge(product.product_id, NOW)
+    store.fail_product_purge(product.product_id, now=NOW)
+    monkeypatch.setattr(service_app, "cleanup_service", service, raising=False)
+    client = TestClient(service_app.app)
+
+    response = client.get("/api/maintenance/cleanup-candidates", headers=auth_header())
+
+    assert response.status_code == 200
+    data = response.json()
+    assert [item["product_id"] for item in data["failed_products"]] == [
+        product.product_id
+    ]
+    assert data["pending_products"] == []
+
+
 def test_apply_rechecks_archive_reference_immediately_before_job_deletion(tmp_path):
     service = make_cleanup_service(tmp_path)
     due_job = create_success_job(service, age_days=31)