diff --git a/API_DOCUMENTATION.md b/API_DOCUMENTATION.md
index f24f03c..4992936 100644
--- a/API_DOCUMENTATION.md
+++ b/API_DOCUMENTATION.md
@@ -164,7 +164,7 @@ curl http://localhost:8000/agents?template=echo_agent
 
 ### 3. 获取 Agent 状态
 
-获取指定 Agent 的详细状态信息。
+获取指定 Agent 的详细状态信息，包括 Pod 状态、容器健康状态、资源配额等。
 
 **请求**
 
@@ -178,23 +178,168 @@ GET /agents/{agent_name}/status
 |------|------|------|
 | agent_name | string | Agent 名称 |
 
-**响应**
+**响应 - 健康状态**
 
 ```json
 {
   "name": "alice-echo",
   "namespace": "ai-agents",
   "status": "Running",
-  "pod_ip": "10.244.2.24",
-  "node_name": "aks-node-123",
+  "health_status": "healthy",
+  "template": "echo_agent",
   "created_at": "2026-01-05T07:35:00+00:00",
-  "labels": {
-    "user-id": "alice",
-    "template": "echo_agent"
-  }
+  "node": "aks-node-123",
+  "pod_ip": "10.244.2.24",
+  "containers": [
+    {
+      "name": "alice-echo",
+      "ready": true,
+      "restart_count": 0,
+      "state": "running",
+      "started_at": "2026-01-05T07:35:15+00:00"
+    }
+  ],
+  "resources": {
+    "requests": {
+      "cpu": "100m",
+      "memory": "128Mi"
+    },
+    "limits": {
+      "cpu": "500m",
+      "memory": "512Mi"
+    },
+    "usage": {
+      "cpu": "14502n",
+      "memory": "8704Ki",
+      "available": true
+    }
+  },
+  "service_port": 8080,
+  "access_url": "http://10.244.2.24:8080",
+  "endpoints": {
+    "root": "http://10.244.2.24:8080/",
+    "health": "http://10.244.2.24:8080/health"
+  },
+  "conditions": [
+    {
+      "type": "Ready",
+      "status": "True",
+      "reason": null
+    },
+    {
+      "type": "ContainersReady",
+      "status": "True",
+      "reason": null
+    }
+  ]
 }
 ```
 
+**响应 - 崩溃状态**
+
+```json
+{
+  "name": "my-mysql-agent",
+  "namespace": "ai-agents",
+  "status": "Waiting",
+  "health_status": "unhealthy",
+  "template": "mysql_agent",
+  "created_at": "2026-01-04T06:40:38+00:00",
+  "node": "aks-node-123",
+  "pod_ip": "10.244.1.53",
+  "containers": [
+    {
+      "name": "my-mysql-agent",
+      "ready": false,
+      "restart_count": 599,
+      "state": "waiting",
+      "reason": "CrashLoopBackOff",
+      "message": "back-off 5m0s restarting failed container=my-mysql-agent pod=my-mysql-agent_ai-agents(...)"
+    }
+  ],
+  "resources": {
+    "requests": {
+      "cpu": "100m",
+      "memory": "128Mi"
+    },
+    "limits": {
+      "cpu": "500m",
+      "memory": "512Mi"
+    },
+    "usage": {
+      "cpu": null,
+      "memory": null,
+      "available": false,
+      "reason": "metrics-server未安装或Pod不存在"
+    }
+  },
+  "conditions": [
+    {
+      "type": "Ready",
+      "status": "False",
+      "reason": "ContainersNotReady"
+    },
+    {
+      "type": "ContainersReady",
+      "status": "False",
+      "reason": "ContainersNotReady"
+    }
+  ]
+}
+```
+
+**字段说明**
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| name | string | Agent 名称 |
+| namespace | string | 命名空间 |
+| status | string | Pod 状态 (Running/Pending/Waiting/Terminated/Failed) |
+| **health_status** | string | **健康状态** (healthy/unhealthy/degraded) |
+| template | string | 使用的模板 |
+| created_at | string | 创建时间 (ISO 8601) |
+| node | string | 运行的节点 |
+| pod_ip | string | Pod IP 地址 |
+| **containers** | array | **容器详细状态** |
+| resources | object | 资源配额和使用情况 |
+| service_port | int \| null | 服务端口 |
+| access_url | string \| null | 访问地址 |
+| endpoints | object \| null | API 端点 |
+| conditions | array | Pod 条件状态 |
+
+**健康状态说明**
+
+| 状态 | 说明 |
+|------|------|
+| `healthy` | 所有容器运行正常且就绪 |
+| `unhealthy` | 容器崩溃、终止或未就绪 |
+| `degraded` | 容器重启次数过多 (>5次) |
+
+**容器状态字段**
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| name | string | 容器名称 |
+| ready | boolean | 是否就绪 |
+| restart_count | int | 重启次数 |
+| state | string | 状态 (running/waiting/terminated) |
+| reason | string \| null | 状态原因 (如 CrashLoopBackOff) |
+| message | string \| null | 详细消息 |
+| exit_code | int \| null | 退出码 (terminated 状态) |
+| started_at | string \| null | 启动时间 (running 状态) |
+| finished_at | string \| null | 结束时间 (terminated 状态) |
+
+**Pod 状态类型**
+
+| 状态 | 说明 |
+|------|------|
+| Running | Pod 正在运行 |
+| Pending | Pod 等待调度 |
+| Waiting | 容器等待启动 |
+| Terminated | 容器已终止 |
+| Failed | Pod 失败 |
+| Succeeded | Pod 成功完成 |
+
 **状态码**
 
 - `200` - 成功
@@ -204,9 +349,20 @@ GET /agents/{agent_name}/status
 **示例**
 
 ```bash
+# 查询健康的 Agent
 curl http://localhost:8000/agents/alice-echo/status
+
+# 查询崩溃的 Agent
+curl http://localhost:8000/agents/my-mysql-agent/status
 ```
 
+**使用建议**
+
+1. **监控告警**：使用 `health_status` 字段而非 `status` 进行健康监控
+2. **故障排查**：检查 `containers` 数组获取容器崩溃原因和重启次数
+3. **自动化运维**：根据 `health_status` 自动触发重启或告警
+4. **日志分析**：结合 `restart_count` 和 `reason` 定位问题
+
 ---
 
 ### 4. 获取 Agent 资源使用情况
diff --git a/HEALTH_CHECK_FIX.md b/HEALTH_CHECK_FIX.md
new file mode 100644
index 0000000..0b8643b
--- /dev/null
+++ b/HEALTH_CHECK_FIX.md
@@ -0,0 +1,158 @@
+# 健康检查修复说明
+
+## 问题描述
+
+之前的健康检查实现存在一个严重问题：即使 agent 的容器已经崩溃（crashed），查询状态时仍然会显示为健康（healthy）。
+
+### 根本原因
+
+原实现只检查了 Pod 的 `phase`（如 Running、Pending 等），但没有检查容器的实际状态。即使容器崩溃或处于等待/终止状态，Pod 的 phase 可能仍然是 "Running"。
+
+## 修复内容
+
+### 1. 修改 `k8s_manager.py` 的 `get_pod_status` 方法
+
+**主要改进：**
+- ✅ 检查容器实际状态（running、waiting、terminated）
+- ✅ 检查容器就绪状态（ready）
+- ✅ 检查容器重启次数
+- ✅ 新增 `health_status` 字段，返回真实健康状态
+
+**健康状态分类：**
+- `healthy`: 所有容器运行正常且就绪
+- `unhealthy`: 容器崩溃、终止或未就绪
+- `degraded`: 容器重启次数过多（>5次）
+
+**新增字段：**
+- `health_status`: 真实健康状态
+- `containers`: 容器详细信息数组，包含：
+  - `name`: 容器名称
+  - `ready`: 是否就绪
+  - `restart_count`: 重启次数
+  - `state`: 当前状态（running/waiting/terminated）
+  - `reason`: 状态原因（如果有）
+  - `exit_code`: 退出码（如果已终止）
+
+### 2. 修改 `k8s_manager_new.py` 的 `get_deployment_status` 方法
+
+对于基于 Deployment 的实现，同样增加了对底层 Pod 容器的健康检查。
+
+### 3. 更新 `app.py` 的 `PodStatusResponse` 模型
+
+添加了新字段以支持响应中的健康状态信息。
+
+## 使用方法
+
+### 查询 Agent 状态
+
+```bash
+curl http://localhost:8000/agents/my-mysql-agenty/status
+```
+
+### 示例响应（健康状态）
+
+```json
+{
+  "name": "my-mysql-agenty",
+  "namespace": "ai-agents",
+  "status": "Running",
+  "health_status": "healthy",
+  "containers": [
+    {
+      "name": "mysql-agent",
+      "ready": true,
+      "restart_count": 0,
+      "state": "running",
+      "started_at": "2026-01-06T10:00:00Z"
+    }
+  ],
+  ...
+}
+```
+
+### 示例响应（崩溃状态）
+
+```json
+{
+  "name": "my-mysql-agenty",
+  "namespace": "ai-agents",
+  "status": "Terminated",
+  "health_status": "unhealthy",
+  "containers": [
+    {
+      "name": "mysql-agent",
+      "ready": false,
+      "restart_count": 3,
+      "state": "terminated",
+      "reason": "Error",
+      "exit_code": 1,
+      "message": "Connection refused",
+      "finished_at": "2026-01-06T10:30:00Z"
+    }
+  ],
+  ...
+}
+```
+
+### 示例响应（等待状态）
+
+```json
+{
+  "name": "my-mysql-agenty",
+  "namespace": "ai-agents",
+  "status": "Waiting",
+  "health_status": "unhealthy",
+  "containers": [
+    {
+      "name": "mysql-agent",
+      "ready": false,
+      "restart_count": 2,
+      "state": "waiting",
+      "reason": "CrashLoopBackOff",
+      "message": "Back-off restarting failed container"
+    }
+  ],
+  ...
+}
+```
+
+## 测试
+
+运行测试脚本验证修复：
+
+```bash
+# 设置环境变量
+export API_URL="http://localhost:8000"
+export AGENT_NAME="my-mysql-agenty"
+
+# 运行测试
+./test_health_check.sh
+```
+
+## 重启服务
+
+修复后需要重启 agent-manager 服务以应用更改：
+
+```bash
+# 如果使用 systemd
+sudo systemctl restart agent-manager
+
+# 或者如果直接运行
+pkill -f "uvicorn.*app:app"
+uvicorn app:app --host 0.0.0.0 --port 8000 --reload
+```
+
+## 注意事项
+
+1. **向后兼容性**: 
+   - 原有的 `status` 字段保持不变
+   - 新增的 `health_status` 字段不会影响现有客户端
+   
+2. **建议**:
+   - 在监控和告警系统中使用 `health_status` 而非 `status`
+   - 检查 `containers` 数组获取详细的失败原因
+
+3. **健康状态判断优先级**:
+   - 任何容器 unhealthy → 整体 unhealthy
+   - 任何容器 degraded（且无 unhealthy）→ 整体 degraded
+   - 所有容器 healthy → 整体 healthy
diff --git a/app.py b/app.py
index cf74908..1c3ed03 100644
--- a/app.py
+++ b/app.py
@@ -209,10 +209,12 @@ class PodStatusResponse(BaseModel):
     name: str
     namespace: str
     status: str
+    health_status: Optional[str] = None  # 新增：健康状态 (healthy, unhealthy, degraded)
     template: Optional[str] = None
     created_at: Optional[str] = None
     node: Optional[str] = None
     pod_ip: Optional[str] = None
+    containers: Optional[List[Dict]] = None  # 新增：容器详细信息
     resources: Optional[ResourceInfo] = None
     service_port: Optional[int] = None
     access_url: Optional[str] = None
diff --git a/k8s_manager.py b/k8s_manager.py
index 275b5f4..091a2ba 100644
--- a/k8s_manager.py
+++ b/k8s_manager.py
@@ -322,14 +322,68 @@ class K8sManager:
             # 尝试获取实际资源使用情况（需要metrics-server）
             resource_usage = self._get_pod_resource_usage(pod_name)
             
+            # 获取容器实际状态 - 检查是否崩溃或异常
+            container_statuses = pod.status.container_statuses or []
+            actual_status = pod.status.phase  # 默认使用Pod阶段
+            health_status = "healthy"
+            container_info = []
+            
+            for container_status in container_statuses:
+                container_state = {}
+                restart_count = container_status.restart_count
+                
+                # 检查容器状态
+                if container_status.state.running:
+                    container_state = {
+                        "state": "running",
+                        "started_at": container_status.state.running.started_at.isoformat() if container_status.state.running.started_at else None
+                    }
+                elif container_status.state.waiting:
+                    container_state = {
+                        "state": "waiting",
+                        "reason": container_status.state.waiting.reason,
+                        "message": container_status.state.waiting.message
+                    }
+                    # 容器在等待状态，标记为不健康
+                    health_status = "unhealthy"
+                    actual_status = "Waiting"
+                elif container_status.state.terminated:
+                    container_state = {
+                        "state": "terminated",
+                        "reason": container_status.state.terminated.reason,
+                        "exit_code": container_status.state.terminated.exit_code,
+                        "message": container_status.state.terminated.message,
+                        "finished_at": container_status.state.terminated.finished_at.isoformat() if container_status.state.terminated.finished_at else None
+                    }
+                    # 容器已终止，标记为不健康
+                    health_status = "unhealthy"
+                    actual_status = "Terminated"
+                    
+                # 检查容器是否就绪
+                if not container_status.ready:
+                    health_status = "unhealthy"
+                    
+                # 如果重启次数过多，也标记为不健康
+                if restart_count > 5:
+                    health_status = "degraded"
+                    
+                container_info.append({
+                    "name": container_status.name,
+                    "ready": container_status.ready,
+                    "restart_count": restart_count,
+                    **container_state
+                })
+            
             result = {
                 "name": pod.metadata.name,
                 "namespace": pod.metadata.namespace,
-                "status": pod.status.phase,
+                "status": actual_status,
+                "health_status": health_status,  # 新增：真实健康状态
                 "template": template,
                 "created_at": pod.metadata.creation_timestamp.isoformat() if pod.metadata.creation_timestamp else None,
                 "node": pod.spec.node_name,
                 "pod_ip": pod_ip,
+                "containers": container_info,  # 新增：容器详细信息
                 "resources": {
                     "requests": resource_requests,
                     "limits": resource_limits,
diff --git a/k8s_manager_new.py b/k8s_manager_new.py
index 187dbe3..9edd8ac 100644
--- a/k8s_manager_new.py
+++ b/k8s_manager_new.py
@@ -473,12 +473,71 @@ class K8sManager:
                 deployment_name, self.namespace
             )
             
+            # 获取 Deployment 对应的 Pods 实际状态
+            label_selector = f"app={deployment_name.replace('-deployment', '')}"
+            pods = self.core_v1.list_namespaced_pod(
+                self.namespace,
+                label_selector=label_selector
+            )
+            
+            # 检查 Pod 的健康状态
+            health_status = "healthy"
+            pod_details = []
+            
+            for pod in pods.items:
+                pod_health = "healthy"
+                container_statuses = pod.status.container_statuses or []
+                
+                for container_status in container_statuses:
+                    container_info = {
+                        "name": container_status.name,
+                        "ready": container_status.ready,
+                        "restart_count": container_status.restart_count
+                    }
+                    
+                    # 检查容器状态
+                    if container_status.state.waiting:
+                        container_info["state"] = "waiting"
+                        container_info["reason"] = container_status.state.waiting.reason
+                        pod_health = "unhealthy"
+                    elif container_status.state.terminated:
+                        container_info["state"] = "terminated"
+                        container_info["reason"] = container_status.state.terminated.reason
+                        container_info["exit_code"] = container_status.state.terminated.exit_code
+                        pod_health = "unhealthy"
+                    elif container_status.state.running:
+                        container_info["state"] = "running"
+                    
+                    # 检查是否就绪
+                    if not container_status.ready:
+                        pod_health = "unhealthy"
+                    
+                    # 检查重启次数
+                    if container_status.restart_count > 5:
+                        pod_health = "degraded"
+                
+                pod_details.append({
+                    "name": pod.metadata.name,
+                    "phase": pod.status.phase,
+                    "health": pod_health,
+                    "containers": [container_info]
+                })
+                
+                # 更新整体健康状态
+                if pod_health == "unhealthy":
+                    health_status = "unhealthy"
+                elif pod_health == "degraded" and health_status != "unhealthy":
+                    health_status = "degraded"
+            
             return {
                 "name": deployment_name,
                 "namespace": self.namespace,
+                "status": "Running" if deployment.status.available_replicas else "Pending",
+                "health_status": health_status,  # 新增：真实健康状态
                 "replicas": deployment.status.replicas or 0,
                 "ready_replicas": deployment.status.ready_replicas or 0,
                 "available_replicas": deployment.status.available_replicas or 0,
+                "pods": pod_details,  # 新增：Pod详细信息
                 "conditions": [
                     {
                         "type": c.type,
diff --git a/test_health_check.sh b/test_health_check.sh
new file mode 100755
index 0000000..5b743b7
--- /dev/null
+++ b/test_health_check.sh
@@ -0,0 +1,85 @@
+#!/bin/bash
+
+# 测试健康检查修复
+# 验证崩溃的 agent 是否能正确识别为 unhealthy
+
+API_URL="${API_URL:-http://localhost:8000}"
+AGENT_NAME="${AGENT_NAME:-my-mysql-agenty}"
+
+echo "========================================"
+echo "测试 Agent 健康状态检查"
+echo "========================================"
+echo "API URL: $API_URL"
+echo "Agent Name: $AGENT_NAME"
+echo ""
+
+# 获取 agent 状态
+echo "📊 获取 Agent 状态..."
+response=$(curl -s -w "\nHTTP_STATUS:%{http_code}" "$API_URL/agents/$AGENT_NAME/status")
+
+http_status=$(echo "$response" | grep "HTTP_STATUS" | cut -d':' -f2)
+body=$(echo "$response" | sed '/HTTP_STATUS/d')
+
+echo "HTTP Status: $http_status"
+echo ""
+
+if [ "$http_status" = "200" ]; then
+    echo "✅ 成功获取状态"
+    echo ""
+    echo "响应内容:"
+    echo "$body" | python3 -m json.tool 2>/dev/null || echo "$body"
+    echo ""
+    
+    # 提取健康状态
+    health_status=$(echo "$body" | python3 -c "import sys, json; data=json.load(sys.stdin); print(data.get('health_status', 'N/A'))" 2>/dev/null || echo "无法解析")
+    status=$(echo "$body" | python3 -c "import sys, json; data=json.load(sys.stdin); print(data.get('status', 'N/A'))" 2>/dev/null || echo "无法解析")
+    
+    echo "========================================"
+    echo "状态摘要:"
+    echo "  Pod Status: $status"
+    echo "  Health Status: $health_status"
+    echo "========================================"
+    echo ""
+    
+    if [ "$health_status" = "unhealthy" ]; then
+        echo "✅ 正确识别为不健康状态 (unhealthy)"
+        
+        # 显示容器信息
+        echo ""
+        echo "📦 容器详情:"
+        echo "$body" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+containers = data.get('containers', [])
+for c in containers:
+    print(f\"  容器: {c.get('name', 'N/A')}\")
+    print(f\"    状态: {c.get('state', 'N/A')}\")
+    print(f\"    就绪: {c.get('ready', 'N/A')}\")
+    print(f\"    重启次数: {c.get('restart_count', 0)}\")
+    if c.get('reason'):
+        print(f\"    原因: {c.get('reason')}\")
+    if c.get('exit_code') is not None:
+        print(f\"    退出码: {c.get('exit_code')}\")
+    print()
+" 2>/dev/null || echo "  无法解析容器信息"
+    elif [ "$health_status" = "healthy" ]; then
+        echo "⚠️  仍然显示为健康状态 (healthy) - 可能是 agent 确实在运行"
+        echo "   请检查容器详细信息确认"
+    elif [ "$health_status" = "degraded" ]; then
+        echo "⚠️  显示为降级状态 (degraded) - 容器可能频繁重启"
+    else
+        echo "⚠️  未知健康状态: $health_status"
+    fi
+    
+elif [ "$http_status" = "404" ]; then
+    echo "❌ Agent 不存在"
+    echo "$body"
+else
+    echo "❌ 获取状态失败"
+    echo "$body"
+fi
+
+echo ""
+echo "========================================"
+echo "测试完成"
+echo "========================================"