fix: Handle orchestrated tasks without sub_tasks

Problem:
- Task #1 was stuck in 'in_progress' status
- TaskBeat expects 'sub_tasks' array for orchestrated tasks
- Tasks created via old API didn't have sub_tasks defined
- TaskBeat only processes 'pending' tasks, so in_progress tasks stay stuck

Solution:
- Added validation: if orchestrated task has no sub_tasks, mark as completed with error message
- Prevents infinite loop with stuck tasks
- Manually completed Task #1 in database

Note: This handles legacy tasks from deprecated /api/orchestrate endpoint.

app.py

@@ -1909,6 +1909,12 @@ def process_beat_tasks():
                     sub_tasks = task.get('sub_tasks', [])
                     available_agents = task.get('available_agents', list(AGENTS.keys()))
                     
+                    # Falls keine sub_tasks: Task ist fehlerhaft, markiere als completed
+                    if not sub_tasks:
+                        logger.warning("[TaskBeat] Task #%d hat keine sub_tasks - als completed markiert", task['id'])
+                        update_task_db(task['id'], status='completed', response='Fehler: Keine sub_tasks definiert. Dieser Task wurde wahrscheinlich über eine veraltete API erstellt.')
+                        continue
+                    
                     prompt = f"""Du bist der Master-Orchestrator. Analysiere folgende Tasks und weise sie den richtigen Agenten zu:
 
 Tasks: