Implement self-healing system Phase 1: Error capture and logging

- Add SelfHealingSystem with error observation infrastructure
- Capture errors with full context: type, message, stack trace, intent, inputs
- Log to MEMORY.md with deduplication (max 3 attempts per error signature)
- Integrate error capture in agent, tools, runtime, and scheduler
- Non-invasive: preserves all existing error handling behavior
- Foundation for future diagnosis and auto-fixing capabilities

Phase 1 of 4-phase rollout - observation only, no auto-fixing yet.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

scheduled_tasks.py

@@ -345,6 +345,17 @@ class TaskScheduler:
             print(f"[Scheduler] Task failed: {task.name}")
             print(f"  Error: {e}")
             traceback.print_exc()
+            if self.agent and hasattr(self.agent, 'healing_system'):
+                self.agent.healing_system.capture_error(
+                    error=e,
+                    component="scheduled_tasks.py:_execute_task",
+                    intent=f"Executing scheduled task: {task.name}",
+                    context={
+                        "task_name": task.name,
+                        "schedule": task.schedule,
+                        "prompt": task.prompt[:100],
+                    },
+                )
 
     async def _send_to_platform(
         self, task: ScheduledTask, response: str