feat(P3): Docker健康检查 + Worker优雅重启 + 前端错误监控

backend/cmd/worker/main.go

@@ -17,6 +17,7 @@ import (
 	"time"
 
 	amqp "github.com/rabbitmq/amqp091-go"
+	"gorm.io/gorm"
 )
 
 const (
@@ -37,6 +38,21 @@ const (
 	popularityBindingKey = "video.popularity.*"
 )
 
+func connectWithRetry(name string, maxRetries int, fn func() error) {
+	for i := 0; i < maxRetries; i++ {
+		if err := fn(); err == nil {
+			return
+		}
+		wait := time.Duration(1<<i) * time.Second
+		if wait > 30*time.Second {
+			wait = 30 * time.Second
+		}
+		log.Printf("%s 不可用，%v 后重试 (%d/%d)...", name, wait, i+1, maxRetries)
+		time.Sleep(wait)
+	}
+	log.Fatalf("%s: 超过最大重试次数", name)
+}
+
 func main() {
 	// 加载配置
 	configPath := os.Getenv("CONFIG_PATH")
@@ -53,11 +69,13 @@ func main() {
 	} else {
 		log.Printf("Config loaded from file: %s", configPath)
 	}
-	// 连接数据库
-	sqlDB, err := db.NewDB(cfg.Database)
-	if err != nil {
-		log.Fatalf("Failed to connect database: %v", err)
-	}
+	// 连接数据库（带重试）
+	var sqlDB *gorm.DB
+	connectWithRetry("MySQL", 10, func() error {
+		var err error
+		sqlDB, err = db.NewDB(cfg.Database)
+		return err
+	})
 	defer db.CloseDB(sqlDB)
 
 	// 连接 Redis（用于流行度更新）
@@ -77,12 +95,14 @@ func main() {
 			log.Printf("Redis connected (popularity worker enabled)")
 		}
 	}
-	// 连接 RabbitMQ
+	// 连接 RabbitMQ（带重试）
 	url := "amqp://" + cfg.RabbitMQ.Username + ":" + cfg.RabbitMQ.Password + "@" + cfg.RabbitMQ.Host + ":" + strconv.Itoa(cfg.RabbitMQ.Port) + "/"
-	conn, err := amqp.Dial(url)
-	if err != nil {
-		log.Fatalf("Failed to connect rabbitmq: %v", err)
-	}
+	var conn *amqp.Connection
+	connectWithRetry("RabbitMQ", 10, func() error {
+		var err error
+		conn, err = amqp.Dial(url)
+		return err
+	})
 	defer conn.Close()
 	// 创建 RabbitMQ 通道
 	ch, err := conn.Channel()

docker-compose.yml

@@ -71,6 +71,11 @@ services:
         condition: service_healthy
       rabbitmq:
         condition: service_healthy
+    healthcheck:
+      test: ["CMD-SHELL", "wget -qO- --post-data='{}' --header='Content-Type: application/json' http://localhost:8080/account/findByID || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
 
   worker:
     build:
@@ -87,6 +92,11 @@ services:
         condition: service_healthy
       rabbitmq:
         condition: service_healthy
+    healthcheck:
+      test: ["CMD-SHELL", "pgrep worker || exit 1"]
+      interval: 15s
+      timeout: 5s
+      retries: 3
 
   frontend:
     build:
@@ -97,6 +107,11 @@ services:
       - "5173:80"
     depends_on:
       - backend
+    healthcheck:
+      test: ["CMD-SHELL", "wget -qO- http://localhost:80/ || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
 
 volumes:
   mysql_data:

frontend/src/api/client.ts

@@ -1,4 +1,5 @@
 import { useAuthStore } from '../stores/auth'
+import { reportError } from '../utils/error-reporter'
 
 export class ApiError extends Error {
   status: number
@@ -51,7 +52,9 @@ export async function postJson<T>(path: string, body: unknown, options?: { authR
       data && typeof data === 'object' && (data as ApiErrorBody).error
         ? String((data as ApiErrorBody).error)
         : `请求失败 (${res.status})`
-    throw new ApiError(msg, res.status, data)
+    const apiErr = new ApiError(msg, res.status, data)
+    reportError(apiErr, { path, status: res.status })
+    throw apiErr
   }
 
   return data as T
@@ -92,7 +95,9 @@ export async function postForm<T>(path: string, body: FormData, options?: { auth
       data && typeof data === 'object' && (data as ApiErrorBody).error
         ? String((data as ApiErrorBody).error)
         : `请求失败 (${res.status})`
-    throw new ApiError(msg, res.status, data)
+    const apiErr = new ApiError(msg, res.status, data)
+    reportError(apiErr, { path, status: res.status })
+    throw apiErr
   }
 
   return data as T

frontend/src/main.ts

@@ -3,8 +3,14 @@ import { createPinia } from 'pinia'
 import './style.css'
 import App from './App.vue'
 import router from './router'
+import { reportError } from './utils/error-reporter'
 
 const app = createApp(App)
 app.use(createPinia())
 app.use(router)
+
+app.config.errorHandler = (err, _instance, info) => {
+  reportError(err instanceof Error ? err : new Error(String(err)), { info })
+}
+
 app.mount('#app')

frontend/src/utils/error-reporter.ts

@@ -0,0 +1,18 @@
+export function reportError(error: Error, context?: Record<string, unknown>) {
+  if (import.meta.env.DEV) {
+    console.error('[ErrorReporter]', error.message, context)
+    return
+  }
+  fetch('/api/error-report', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({
+      message: error.message,
+      stack: error.stack,
+      context,
+      timestamp: new Date().toISOString(),
+    }),
+  }).catch(() => {
+    /* 静默失败，避免错误上报自身导致循环 */
+  })
+}