class MonitoredAgent:
    """Agent wrapper that collects metrics on every invocation."""
    
    def __init__(self, agent, agent_name: str, metrics_client):
        self.agent = agent
        self.agent_name = agent_name
        self.metrics = metrics_client
    
    async def run(self, task: str) -> str:
        start_time = time.time()
        step_count = 0
        token_usage = 0
        
        try:
            result = await self.agent.run(task)
            
            # Collect metrics
            duration = time.time() - start_time
            self.metrics.timing(f"agent.{self.agent_name}.latency", duration)
            self.metrics.increment(f"agent.{self.agent_name}.invocations")
            self.metrics.increment(f"agent.{self.agent_name}.success")
            self.metrics.gauge(f"agent.{self.agent_name}.steps", step_count)
            
            return result
            
        except Exception as e:
            duration = time.time() - start_time
            self.metrics.increment(f"agent.{self.agent_name}.errors")
            self.metrics.timing(f"agent.{self.agent_name}.error_latency", duration)
            raise

class AgentHealthProbe:
    """Kubernetes-style health probes for AI agents."""
    
    async def liveness_check(self, agent) -> bool:
        """Is the agent process alive and responding?"""
        try:
            result = await asyncio.wait_for(
                agent.run("Respond with: OK"),
                timeout=5.0
            )
            return "OK" in result
        except (asyncio.TimeoutError, Exception):
            return False
    
    async def readiness_check(self, agent) -> dict:
        """Is the agent ready to accept tasks?"""
        checks = {
            "model_available": await self._check_model(agent),
            "tools_available": await self._check_tools(agent),
            "memory_available": await self._check_memory(agent),
            "context_capacity": await self._check_context(agent),
        }
        return {
            "ready": all(checks.values()),
            "checks": checks
        }
    
    async def deep_check(self, agent) -> dict:
        """Full diagnostic: run a test task and validate output."""
        test_task = agent.config.test_prompt
        result = await agent.run(test_task)
        return {
            "passed": self._validate_output(result),
            "output_preview": result[:200],
            "latency_ms": self._last_latency
        }

class AnomalyDetector:
    """Detect unusual agent behavior using statistical methods."""

    def __init__(self, window_size: int = 100):
        self.window_size = window_size
        self.metrics_history = defaultdict(list)

    def record(self, agent_name: str, metric: str, value: float):
        self.metrics_history[f"{agent_name}:{metric}"].append(value)
        
        # Keep rolling window
        history = self.metrics_history[f"{agent_name}:{metric}"]
        if len(history) > self.window_size:
            history.pop(0)

    def is_anomalous(self, agent_name: str, metric: str, value: float, 
                     z_threshold: float = 3.0) -> tuple[bool, float]:
        """Check if a value is anomalous using z-score."""
        history = self.metrics_history.get(f"{agent_name}:{metric}", [])
        if len(history) < 10:
            return False, 0.0  # Not enough data
        
        mean = statistics.mean(history)
        stdev = statistics.stdev(history)
        if stdev == 0:
            return False, 0.0
        
        z_score = (value - mean) / stdev
        return abs(z_score) > z_threshold, z_score

class AlertManager:
    """Route alerts to the right channels based on severity."""
    
    def __init__(self):
        self.channels = {
            "p0": ["pagerduty", "slack-critical", "phone"],
            "p1": ["slack-critical", "email"],
            "p2": ["slack-warn", "email"],
            "p3": ["dashboard", "weekly-report"],
        }
    
    async def alert(self, severity: str, title: str, message: str, 
                    context: dict = None):
        """Send an alert through the appropriate channels."""
        channels = self.channels.get(severity, self.channels["p3"])
        
        for channel in channels:
            await self._send(channel, {
                "severity": severity,
                "title": title,
                "message": message,
                "context": context,
                "timestamp": datetime.now().isoformat()
            })

# alert-rules.yaml
rules:
  - name: agent_down
    condition: liveness_check == false
    for: 30s
    severity: P0
    message: "Agent {name} is unresponsive"

  - name: high_error_rate
    condition: error_rate > 0.20
    for: 5m
    severity: P1
    message: "Agent {name} error rate is {error_rate:.0%}"

  - name: latency_spike
    condition: p99_latency > 30s
    for: 3m
    severity: P1
    message: "Agent {name} p99 latency is {latency:.1f}s"

  - name: looping_detected
    condition: step_count > max_steps * 0.8
    for: 1m
    severity: P2
    message: "Agent {name} approaching step limit on {task_count} tasks"

  - name: budget_anomaly
    condition: token_usage > daily_budget * 0.5
    for: 1h
    severity: P2
    message: "Agent {name} used {usage} tokens in last hour (50% of daily budget)"