fix(attack-paths): clear Neo4j database cache after scan and queries (#9878)

Co-authored-by: Josema Camacho <josema@prowler.com>

api/CHANGELOG.md

@@ -14,6 +14,7 @@ All notable changes to the **Prowler API** are documented in this file.
 - Use `Findings.all_objects` to avoid the `ActiveProviderPartitionedManager` [(#9869)](https://github.com/prowler-cloud/prowler/pull/9869)
 - Lazy load Neo4j driver for workers only [(#9872)](https://github.com/prowler-cloud/prowler/pull/9872)
 - Improve Cypher query for inserting Findings into Attack Paths scan graphs [(#9874)](https://github.com/prowler-cloud/prowler/pull/9874)
+- Clear Neo4j database cache after Attack Paths scan and each API query [(#9877)](https://github.com/prowler-cloud/prowler/pull/9877)
 
 ## [1.18.0] (Prowler v5.17.0)
 

api/src/backend/api/attack_paths/database.py

@@ -125,6 +125,17 @@ def drop_subgraph(database: str, root_node_label: str, root_node_id: str) -> int
             return 0  # As there are no nodes to delete, the result is empty
 
 
+def clear_cache(database: str) -> None:
+    query = "CALL db.clearQueryCaches()"
+
+    try:
+        with get_session(database) as session:
+            session.run(query)
+
+    except GraphDatabaseQueryException as exc:
+        logging.warning(f"Failed to clear query cache for database `{database}`: {exc}")
+
+
 # Neo4j functions related to Prowler + Cartography
 DATABASE_NAME_TEMPLATE = "db-{attack_paths_scan_id}"
 

api/src/backend/api/attack_paths/retryable_session.py

@@ -64,9 +64,9 @@ class RetryableSession:
                 return method(*args, **kwargs)
 
             except (
-                neo4j.exceptions.ServiceUnavailable,
-                ConnectionResetError,
                 BrokenPipeError,
+                ConnectionResetError,
+                neo4j.exceptions.ServiceUnavailable,
             ) as exc:  # pragma: no cover - depends on infra
                 last_exc = exc
                 attempt += 1

api/src/backend/api/tests/test_views.py

@@ -3867,6 +3867,7 @@ class TestAttackPathsScanViewSet:
                 "api.v1.views.attack_paths_views_helpers.execute_attack_paths_query",
                 return_value=graph_payload,
             ) as mock_execute,
+            patch("api.v1.views.graph_database.clear_cache") as mock_clear_cache,
         ):
             response = authenticated_client.post(
                 reverse(
@@ -3889,6 +3890,7 @@ class TestAttackPathsScanViewSet:
             query_definition,
             prepared_parameters,
         )
+        mock_clear_cache.assert_called_once_with(attack_paths_scan.graph_database)
         result = response.json()["data"]
         attributes = result["attributes"]
         assert attributes["nodes"] == graph_payload["nodes"]
@@ -4000,6 +4002,7 @@ class TestAttackPathsScanViewSet:
                 "api.v1.views.attack_paths_views_helpers.execute_attack_paths_query",
                 return_value={"nodes": [], "relationships": []},
             ),
+            patch("api.v1.views.graph_database.clear_cache"),
         ):
             response = authenticated_client.post(
                 reverse(

api/src/backend/api/v1/views.py

@@ -77,6 +77,7 @@ from rest_framework_json_api.views import RelationshipView, Response
 from rest_framework_simplejwt.exceptions import InvalidToken, TokenError
 
 from api.attack_paths import (
+    database as graph_database,
     get_queries_for_provider,
     get_query_by_id,
     views_helpers as attack_paths_views_helpers,
@@ -2435,6 +2436,7 @@ class AttackPathsScanViewSet(BaseRLSViewSet):
         graph = attack_paths_views_helpers.execute_attack_paths_query(
             attack_paths_scan, query_definition, parameters
         )
+        graph_database.clear_cache(attack_paths_scan.graph_database)
 
         status_code = status.HTTP_200_OK
         if not graph.get("nodes"):

api/src/backend/tasks/jobs/attack_paths/scan.py

@@ -137,6 +137,11 @@ def run(tenant_id: str, scan_id: str, task_id: str) -> dict[str, Any]:
                 neo4j_session, prowler_api_provider, scan_id, cartography_config
             )
 
+        logger.info(
+            f"Clearing Neo4j cache for database {cartography_config.neo4j_database}"
+        )
+        graph_database.clear_cache(cartography_config.neo4j_database)
+
         logger.info(
             f"Completed Cartography ({attack_paths_scan.id}) for "
             f"{prowler_api_provider.provider.upper()} provider {prowler_api_provider.id}"

api/src/backend/tasks/tests/test_attack_paths_scan.py

@@ -68,6 +68,7 @@ class TestAttackPathsRun:
                 "tasks.jobs.attack_paths.scan.graph_database.get_session",
                 return_value=session_ctx,
             ) as mock_get_session,
+            patch("tasks.jobs.attack_paths.scan.graph_database.clear_cache"),
             patch(
                 "tasks.jobs.attack_paths.scan.cartography_create_indexes.run"
             ) as mock_cartography_indexes,