fix: quarantine failed product cleanups in failed_cleanup state

backend/service/cleanup_service.py

@@ -126,7 +126,9 @@ class CleanupService:
                 if product_dir.exists():
                     shutil.rmtree(product_dir)
             except Exception:
-                self.product_store.release_product_purge(product.product_id)
+                # rmtree may have removed only part of the archive. Quarantine
+                # the record for manual inspection instead of retrying it.
+                self.product_store.fail_product_purge(product.product_id)
                 raise
             self.product_store.finalize_product_purge(product.product_id, now=now_utc)
             report.deleted_product_ids.append(product.product_id)

backend/service/product_archive_service.py

@@ -21,7 +21,7 @@ from .schemas import ProductVersionRecord
 
 
 class ProductPendingCleanupError(ValueError):
-    """Raised when a soft-deleted product is changed before restoration."""
+    """Raised when a pending or failed-cleanup product is changed before recovery."""
 
 
 class ProductArchiveService:
@@ -83,7 +83,7 @@ class ProductArchiveService:
         if not isinstance(document, dict):
             raise ValueError("document must be a JSON object")
         product = self.store.get_product(product_id)
-        if product.status == "pending_cleanup":
+        if product.status in ("pending_cleanup", "failed_cleanup"):
             raise ProductPendingCleanupError("product is pending cleanup")
         if product.status != "active":
             raise ValueError("product is not active")

backend/service/product_archive_store.py

@@ -318,7 +318,9 @@ class ProductArchiveStore:
             raise ValueError(f"unknown version_id for product: {version_id}")
 
     def mark_pending_cleanup(self, product_id: str, now: datetime) -> ProductRecord:
-        self.get_product(product_id)
+        product = self.get_product(product_id)
+        if product.status not in ("active", "failed_cleanup"):
+            raise ValueError("product cannot be marked pending cleanup")
         purge_after = now + timedelta(days=30)
         self._execute(
             "UPDATE products SET status = ?, purge_after = ?, updated_at = ? WHERE product_id = ?",
@@ -355,8 +357,8 @@ class ProductArchiveStore:
             )
             conn.execute(
                 """UPDATE cleanup_records SET status = ?, completed_at = ?
-                   WHERE product_id = ? AND status = ?""",
-                ("restored", restored_at.isoformat(), product_id, "pending_cleanup"),
+                   WHERE product_id = ? AND status IN ('pending_cleanup', 'failed_cleanup')""",
+                ("restored", restored_at.isoformat(), product_id),
             )
         return self.get_product(product_id)
 
@@ -405,13 +407,29 @@ class ProductArchiveStore:
                 return None
             return self._product_from_row(row)
 
-    def release_product_purge(self, product_id: str) -> None:
-        """Return a failed physical deletion claim to its pending state."""
-        self._execute(
-            """UPDATE cleanup_records SET status = 'pending_cleanup'
-               WHERE product_id = ? AND status = 'purging'""",
-            (product_id,),
-        )
+    def fail_product_purge(self, product_id: str) -> ProductRecord:
+        """Quarantine a purge whose physical deletion failed mid-way."""
+        with self._lock, self._connect() as conn:
+            conn.execute("BEGIN IMMEDIATE")
+            claim = conn.execute(
+                """SELECT 1 FROM cleanup_records
+                   WHERE product_id = ? AND status = 'purging' LIMIT 1""",
+                (product_id,),
+            ).fetchone()
+            if claim is None:
+                raise ValueError("product purge is not claimed")
+            updated = conn.execute(
+                """UPDATE cleanup_records SET status = 'failed_cleanup'
+                   WHERE product_id = ? AND status = 'purging'""",
+                (product_id,),
+            )
+            if updated.rowcount != 1:
+                raise ValueError("product purge is not claimed")
+            conn.execute(
+                "UPDATE products SET status = 'failed_cleanup', updated_at = ? WHERE product_id = ?",
+                (_now().isoformat(), product_id),
+            )
+        return self.get_product(product_id)
 
     def finalize_product_purge(self, product_id: str, now: datetime) -> ProductRecord:
         """Atomically mark a claimed product purged after file removal."""

backend/service/schemas.py

@@ -43,7 +43,7 @@ class ProductRecord(BaseModel):
     name: str
     sku: str = ""
     specification: str = ""
-    status: Literal["active", "pending_cleanup", "purged"] = "active"
+    status: Literal["active", "pending_cleanup", "failed_cleanup", "purged"] = "active"
     created_at: datetime
     updated_at: datetime
     purge_after: datetime | None = None