Changes Made

1. app/web/utils/validators.py - Added 'finalizing' to valid_statuses list
  2. app/web/models.py - Updated status field comment to document all valid statuses
  3. app/web/jobs/scan_job.py
  - Added transition to 'finalizing' status before output file generation
  - Sets current_phase = 'generating_outputs' during this phase
  - Wrapped output generation in try-except with proper error handling
  - If output generation fails, scan is marked 'completed' with warning message (scan data is still valid)

  4. app/web/api/scans.py
  - Added _recover_orphaned_scan() helper function for smart recovery
  - Modified stop_running_scan() to:
    - Allow stopping scans with status 'running' OR 'finalizing'
    - When scanner not in registry, perform smart recovery instead of returning 404
    - Smart recovery checks for output files and marks as 'completed' if found, 'cancelled' if not

  5. app/web/services/scan_service.py
  - Enhanced cleanup_orphaned_scans() with smart recovery logic
  - Now finds scans in both 'running' and 'finalizing' status
  - Returns dict with stats: {'recovered': N, 'failed': N, 'total': N}

  6. app/web/app.py - Updated caller to handle new dict return type from cleanup_orphaned_scans()

  Expected Behavior Now

  1. Normal scan flow: running → finalizing → completed
  2. Stop on active scan: Sends cancel signal, becomes 'cancelled'
  3. Stop on orphaned scan with files: Smart recovery → 'completed'
  4. Stop on orphaned scan without files: → 'cancelled'
  5. App restart with orphans: Startup cleanup uses smart recovery

app/web/jobs/scan_job.py

@@ -240,14 +240,47 @@ def execute_scan(scan_id: int, config_id: int, db_url: str = None):
         scan_duration = (end_time - start_time).total_seconds()
         logger.info(f"Scan {scan_id}: Scanner completed in {scan_duration:.2f} seconds")
 
-        # Generate output files (JSON, HTML, ZIP)
-        logger.info(f"Scan {scan_id}: Generating output files...")
-        output_paths = scanner.generate_outputs(report, timestamp)
+        # Transition to 'finalizing' status before output generation
+        try:
+            scan = session.query(Scan).filter_by(id=scan_id).first()
+            if scan:
+                scan.status = 'finalizing'
+                scan.current_phase = 'generating_outputs'
+                session.commit()
+                logger.info(f"Scan {scan_id}: Status changed to 'finalizing'")
+        except Exception as e:
+            logger.error(f"Scan {scan_id}: Failed to update status to finalizing: {e}")
+            session.rollback()
 
-        # Save results to database
-        logger.info(f"Scan {scan_id}: Saving results to database...")
-        scan_service = ScanService(session)
-        scan_service._save_scan_to_db(report, scan_id, status='completed', output_paths=output_paths)
+        # Generate output files (JSON, HTML, ZIP) with error handling
+        output_paths = {}
+        output_generation_failed = False
+        try:
+            logger.info(f"Scan {scan_id}: Generating output files...")
+            output_paths = scanner.generate_outputs(report, timestamp)
+        except Exception as e:
+            output_generation_failed = True
+            logger.error(f"Scan {scan_id}: Output generation failed: {str(e)}")
+            logger.error(f"Scan {scan_id}: Traceback:\n{traceback.format_exc()}")
+            # Still mark scan as completed with warning since scan data is valid
+            try:
+                scan = session.query(Scan).filter_by(id=scan_id).first()
+                if scan:
+                    scan.status = 'completed'
+                    scan.error_message = f"Scan completed but output file generation failed: {str(e)}"
+                    scan.completed_at = datetime.utcnow()
+                    if scan.started_at:
+                        scan.duration = (datetime.utcnow() - scan.started_at).total_seconds()
+                    session.commit()
+                    logger.info(f"Scan {scan_id}: Marked as completed with output generation warning")
+            except Exception as db_error:
+                logger.error(f"Scan {scan_id}: Failed to update status after output error: {db_error}")
+
+        # Save results to database (only if output generation succeeded)
+        if not output_generation_failed:
+            logger.info(f"Scan {scan_id}: Saving results to database...")
+            scan_service = ScanService(session)
+            scan_service._save_scan_to_db(report, scan_id, status='completed', output_paths=output_paths)
 
         # Evaluate alert rules
         logger.info(f"Scan {scan_id}: Evaluating alert rules...")