fix(scans): Handle duplicated scan tasks (#7409)

Co-authored-by: Víctor Fernández Poyatos <victor@prowler.com>

api/CHANGELOG.md

@@ -4,6 +4,13 @@ All notable changes to the **Prowler API** are documented in this file.
 
 ---
 
+## [v1.5.3] (Prowler v5.4.3)
+
+### Fixed
+- Added duplicated scheduled scans handling ([#7401])(https://github.com/prowler-cloud/prowler/pull/7401).
+
+---
+
 ## [v1.5.2] (Prowler v5.4.2)
 
 ### Changed

api/pyproject.toml

@@ -8,7 +8,7 @@ description = "Prowler's API (Django/DRF)"
 license = "Apache-2.0"
 name = "prowler-api"
 package-mode = false
-version = "1.5.2"
+version = "1.5.3"
 
 [tool.poetry.dependencies]
 celery = {extras = ["pytest"], version = "^5.4.0"}

api/src/backend/api/specs/v1.yaml

@@ -1,7 +1,7 @@
 openapi: 3.0.3
 info:
   title: Prowler API
-  version: 1.5.2
+  version: 1.5.3
   description: |-
     Prowler API specification.
 

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

@@ -241,7 +241,7 @@ class SchemaView(SpectacularAPIView):
 
     def get(self, request, *args, **kwargs):
         spectacular_settings.TITLE = "Prowler API"
-        spectacular_settings.VERSION = "1.5.2"
+        spectacular_settings.VERSION = "1.5.3"
         spectacular_settings.DESCRIPTION = (
             "Prowler API specification.\n\nThis file is auto-generated."
         )

api/src/backend/tasks/tasks.py

@@ -1,3 +1,4 @@
+from datetime import datetime, timedelta, timezone
 from pathlib import Path
 from shutil import rmtree
 
@@ -21,6 +22,7 @@ from api.db_utils import rls_transaction
 from api.decorators import set_tenant
 from api.models import Finding, Provider, Scan, ScanSummary, StateChoices
 from api.utils import initialize_prowler_provider
+from api.v1.serializers import ScanTaskSerializer
 from prowler.lib.outputs.finding import Finding as FindingOutput
 
 logger = get_task_logger(__name__)
@@ -128,6 +130,43 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
         periodic_task_instance = PeriodicTask.objects.get(
             name=f"scan-perform-scheduled-{provider_id}"
         )
+
+        executed_scan = Scan.objects.filter(
+            tenant_id=tenant_id,
+            provider_id=provider_id,
+            task__task_runner_task__task_id=task_id,
+        ).order_by("completed_at")
+
+        if (
+            Scan.objects.filter(
+                tenant_id=tenant_id,
+                provider_id=provider_id,
+                trigger=Scan.TriggerChoices.SCHEDULED,
+                state=StateChoices.EXECUTING,
+                scheduler_task_id=periodic_task_instance.id,
+                scheduled_at__date=datetime.now(timezone.utc).date(),
+            ).exists()
+            or executed_scan.exists()
+        ):
+            # Duplicated task execution due to visibility timeout or scan is already running
+            logger.warning(f"Duplicated scheduled scan for provider {provider_id}.")
+            try:
+                affected_scan = executed_scan.first()
+                if not affected_scan:
+                    raise ValueError(
+                        "Error retrieving affected scan details after detecting duplicated scheduled "
+                        "scan."
+                    )
+                # Return the affected scan details to avoid losing data
+                serializer = ScanTaskSerializer(instance=affected_scan)
+            except Exception as duplicated_scan_exception:
+                logger.error(
+                    f"Duplicated scheduled scan for provider {provider_id}. Error retrieving affected scan details: "
+                    f"{str(duplicated_scan_exception)}"
+                )
+                raise duplicated_scan_exception
+            return serializer.data
+
         next_scan_datetime = get_next_execution_datetime(task_id, provider_id)
         scan_instance, _ = Scan.objects.get_or_create(
             tenant_id=tenant_id,
@@ -135,7 +174,11 @@ def perform_scheduled_scan_task(self, tenant_id: str, provider_id: str):
             trigger=Scan.TriggerChoices.SCHEDULED,
             state__in=(StateChoices.SCHEDULED, StateChoices.AVAILABLE),
             scheduler_task_id=periodic_task_instance.id,
-            defaults={"state": StateChoices.SCHEDULED},
+            defaults={
+                "state": StateChoices.SCHEDULED,
+                "name": "Daily scheduled scan",
+                "scheduled_at": next_scan_datetime - timedelta(days=1),
+            },
         )
 
         scan_instance.task_id = task_id