feat: add missing SDK fields to API findings and resources (#7318)

api/src/backend/api/migrations/0016_finding_compliance_resource_details_and_more.py

@@ -0,0 +1,32 @@
+# Generated by Django 5.1.5 on 2025-03-31 10:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("api", "0015_finding_muted"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="finding",
+            name="compliance",
+            field=models.JSONField(blank=True, default=dict, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="details",
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="metadata",
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="resource",
+            name="partition",
+            field=models.TextField(blank=True, null=True),
+        ),
+    ]

api/src/backend/api/models.py

@@ -518,6 +518,11 @@ class Resource(RowLevelSecurityProtectedModel):
         editable=False,
     )
 
+    metadata = models.TextField(blank=True, null=True)
+    details = models.TextField(blank=True, null=True)
+    partition = models.TextField(blank=True, null=True)
+
+    # Relationships
     tags = models.ManyToManyField(
         ResourceTag,
         verbose_name="Tags associated with the resource, by provider",
@@ -656,6 +661,7 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
     check_id = models.CharField(max_length=100, blank=False, null=False)
     check_metadata = models.JSONField(default=dict, null=False)
     muted = models.BooleanField(default=False, null=False)
+    compliance = models.JSONField(default=dict, null=True, blank=True)
 
     # Relationships
     scan = models.ForeignKey(to=Scan, related_name="findings", on_delete=models.CASCADE)

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

@@ -1,3 +1,4 @@
+import json
 import time
 from copy import deepcopy
 from datetime import datetime, timezone
@@ -6,6 +7,7 @@ from celery.utils.log import get_task_logger
 from config.settings.celery import CELERY_DEADLOCK_ATTEMPTS
 from django.db import IntegrityError, OperationalError
 from django.db.models import Case, Count, IntegerField, Sum, When
+from tasks.utils import CustomEncoder
 
 from api.compliance import (
     PROWLER_COMPLIANCE_OVERVIEW_TEMPLATE,
@@ -191,6 +193,17 @@ def perform_prowler_scan(
                         if resource_instance.type != finding.resource_type:
                             resource_instance.type = finding.resource_type
                             updated_fields.append("type")
+                        if resource_instance.metadata != finding.resource_metadata:
+                            resource_instance.metadata = json.dumps(
+                                finding.resource_metadata, cls=CustomEncoder
+                            )
+                            updated_fields.append("metadata")
+                        if resource_instance.details != finding.resource_details:
+                            resource_instance.details = finding.resource_details
+                            updated_fields.append("details")
+                        if resource_instance.partition != finding.partition:
+                            resource_instance.partition = finding.partition
+                            updated_fields.append("partition")
                         if updated_fields:
                             with rls_transaction(tenant_id):
                                 resource_instance.save(update_fields=updated_fields)
@@ -268,6 +281,7 @@ def perform_prowler_scan(
                         scan=scan_instance,
                         first_seen_at=last_first_seen_at,
                         muted=finding.muted,
+                        compliance=finding.compliance,
                     )
                     finding_instance.add_resources([resource_instance])
 

api/src/backend/tasks/tasks.py

@@ -246,6 +246,11 @@ def generate_outputs(scan_id: str, provider_id: str, tenant_id: str):
         scan_id (str): The scan identifier.
         provider_id (str): The provider_id id to be used in generating outputs.
     """
+    # Check if the scan has findings
+    if not ScanSummary.objects.filter(scan_id=scan_id).exists():
+        logger.info(f"No findings found for scan {scan_id}")
+        return {"upload": False}
+
     # Initialize the prowler provider
     prowler_provider = initialize_prowler_provider(Provider.objects.get(id=provider_id))
 

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

@@ -1,3 +1,4 @@
+import json
 import uuid
 from unittest.mock import MagicMock, patch
 
@@ -7,6 +8,7 @@ from tasks.jobs.scan import (
     _store_resources,
     perform_prowler_scan,
 )
+from tasks.utils import CustomEncoder
 
 from api.models import (
     Finding,
@@ -109,6 +111,11 @@ class TestPerformScan:
             finding.resource_tags = {"tag1": "value1", "tag2": "value2"}
             finding.muted = False
             finding.raw = {}
+            finding.resource_metadata = {"test": "metadata"}
+            finding.resource_details = {"details": "test"}
+            finding.partition = "partition"
+            finding.muted = True
+            finding.compliance = {"compliance1": "PASS"}
 
             # Mock the ProwlerScan instance
             mock_prowler_scan_instance = MagicMock()
@@ -146,6 +153,8 @@ class TestPerformScan:
         assert scan_finding.severity == finding.severity
         assert scan_finding.check_id == finding.check_id
         assert scan_finding.raw_result == finding.raw
+        assert scan_finding.muted
+        assert scan_finding.compliance == finding.compliance
 
         assert scan_resource.tenant == tenant
         assert scan_resource.uid == finding.resource_uid
@@ -153,6 +162,11 @@ class TestPerformScan:
         assert scan_resource.service == finding.service_name
         assert scan_resource.type == finding.resource_type
         assert scan_resource.name == finding.resource_name
+        assert scan_resource.metadata == json.dumps(
+            finding.resource_metadata, cls=CustomEncoder
+        )
+        assert scan_resource.details == f"{finding.resource_details}"
+        assert scan_resource.partition == finding.partition
 
         # Assert that the resource tags have been created and associated
         tags = scan_resource.tags.all()

api/src/backend/tasks/utils.py

@@ -1,9 +1,32 @@
+import json
 from datetime import datetime, timedelta, timezone
+from enum import Enum
 
 from django_celery_beat.models import PeriodicTask
 from django_celery_results.models import TaskResult
 
 
+class CustomEncoder(json.JSONEncoder):
+    def default(self, o):
+        # Enum serialization
+        if isinstance(o, Enum):
+            return o.value
+        # Datetime and timedelta serialization
+        if isinstance(o, datetime):
+            return o.isoformat(timespec="seconds")
+        if isinstance(o, timedelta):
+            return o.total_seconds()
+
+        # Custom object serialization
+        try:
+            return super().default(o)
+        except TypeError:
+            try:
+                return o.__dict__
+            except AttributeError:
+                return str(o)
+
+
 def get_next_execution_datetime(task_id: int, provider_id: str) -> datetime:
     task_instance = TaskResult.objects.get(task_id=task_id)
     try: