feat(基础设施): 添加运维监控功能的基础配置和依赖

- 更新 .gitignore 排除临时文件
- 添加 ops 监控相关配置项到 config.yaml
- 更新 Go 依赖包（go.mod/go.sum）
- 扩展 config.go 支持 ops 监控配置
- 新增上下文键定义（ClientRequestID）

.gitignore

@@ -123,6 +123,4 @@ backend/cmd/server/server
 deploy/docker-compose.override.yml
 .gocache/
 vite.config.js
-!docs/
 docs/*
-!docs/dependency-security.md

backend/go.mod

@@ -8,9 +8,11 @@ require (
 	github.com/golang-jwt/jwt/v5 v5.2.2
 	github.com/google/uuid v1.6.0
 	github.com/google/wire v0.7.0
+	github.com/gorilla/websocket v1.5.3
 	github.com/imroc/req/v3 v3.57.0
 	github.com/lib/pq v1.10.9
 	github.com/redis/go-redis/v9 v9.17.2
+	github.com/shirou/gopsutil/v4 v4.25.6
 	github.com/spf13/viper v1.18.2
 	github.com/stretchr/testify v1.11.1
 	github.com/testcontainers/testcontainers-go/modules/postgres v0.40.0
@@ -104,9 +106,9 @@ require (
 	github.com/quic-go/quic-go v0.57.1 // indirect
 	github.com/refraction-networking/utls v1.8.1 // indirect
 	github.com/rivo/uniseg v0.2.0 // indirect
+	github.com/robfig/cron/v3 v3.0.1 // indirect
 	github.com/sagikazarmark/locafero v0.4.0 // indirect
 	github.com/sagikazarmark/slog-shim v0.1.0 // indirect
-	github.com/shirou/gopsutil/v4 v4.25.6 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
 	github.com/sourcegraph/conc v0.3.0 // indirect
 	github.com/spaolacci/murmur3 v1.1.0 // indirect

backend/go.sum

@@ -113,6 +113,8 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/wire v0.7.0 h1:JxUKI6+CVBgCO2WToKy/nQk0sS+amI9z9EjVmdaocj4=
 github.com/google/wire v0.7.0/go.mod h1:n6YbUQD9cPKTnHXEBN2DXlOp/mVADhVErcMFb0v3J18=
+github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
+github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.3 h1:NmZ1PKzSTQbuGHw9DGPFomqkkLWMC+vZCkfs+FHv1Vg=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.3/go.mod h1:zQrxl1YP88HQlA6i9c63DSVPFklWpGX4OWAc9bFuaH4=
 github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
@@ -220,6 +222,8 @@ github.com/refraction-networking/utls v1.8.1 h1:yNY1kapmQU8JeM1sSw2H2asfTIwWxIkr
 github.com/refraction-networking/utls v1.8.1/go.mod h1:jkSOEkLqn+S/jtpEHPOsVv/4V4EVnelwbMQl4vCWXAM=
 github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
+github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
+github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
 github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII=
 github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=

backend/internal/config/config.go

@@ -42,6 +42,7 @@ type Config struct {
 	Turnstile    TurnstileConfig    `mapstructure:"turnstile"`
 	Database     DatabaseConfig     `mapstructure:"database"`
 	Redis        RedisConfig        `mapstructure:"redis"`
+	Ops          OpsConfig          `mapstructure:"ops"`
 	JWT          JWTConfig          `mapstructure:"jwt"`
 	Default      DefaultConfig      `mapstructure:"default"`
 	RateLimit    RateLimitConfig    `mapstructure:"rate_limit"`
@@ -304,6 +305,47 @@ func (r *RedisConfig) Address() string {
 	return fmt.Sprintf("%s:%d", r.Host, r.Port)
 }
 
+type OpsConfig struct {
+	// Enabled controls whether ops features should run.
+	//
+	// NOTE: vNext still has a DB-backed feature flag (ops_monitoring_enabled) for runtime on/off.
+	// This config flag is the "hard switch" for deployments that want to disable ops completely.
+	Enabled bool `mapstructure:"enabled"`
+
+	// UsePreaggregatedTables prefers ops_metrics_hourly/daily for long-window dashboard queries.
+	UsePreaggregatedTables bool `mapstructure:"use_preaggregated_tables"`
+
+	// Cleanup controls periodic deletion of old ops data to prevent unbounded growth.
+	Cleanup OpsCleanupConfig `mapstructure:"cleanup"`
+
+	// MetricsCollectorCache controls Redis caching for expensive per-window collector queries.
+	MetricsCollectorCache OpsMetricsCollectorCacheConfig `mapstructure:"metrics_collector_cache"`
+
+	// Pre-aggregation configuration.
+	Aggregation OpsAggregationConfig `mapstructure:"aggregation"`
+}
+
+type OpsCleanupConfig struct {
+	Enabled  bool   `mapstructure:"enabled"`
+	Schedule string `mapstructure:"schedule"`
+
+	// Retention days (0 disables that cleanup target).
+	//
+	// vNext requirement: default 30 days across ops datasets.
+	ErrorLogRetentionDays      int `mapstructure:"error_log_retention_days"`
+	MinuteMetricsRetentionDays int `mapstructure:"minute_metrics_retention_days"`
+	HourlyMetricsRetentionDays int `mapstructure:"hourly_metrics_retention_days"`
+}
+
+type OpsAggregationConfig struct {
+	Enabled bool `mapstructure:"enabled"`
+}
+
+type OpsMetricsCollectorCacheConfig struct {
+	Enabled bool          `mapstructure:"enabled"`
+	TTL     time.Duration `mapstructure:"ttl"`
+}
+
 type JWTConfig struct {
 	Secret     string `mapstructure:"secret"`
 	ExpireHour int    `mapstructure:"expire_hour"`
@@ -489,6 +531,20 @@ func setDefaults() {
 	viper.SetDefault("redis.pool_size", 128)
 	viper.SetDefault("redis.min_idle_conns", 10)
 
+	// Ops (vNext)
+	viper.SetDefault("ops.enabled", true)
+	viper.SetDefault("ops.use_preaggregated_tables", false)
+	viper.SetDefault("ops.cleanup.enabled", true)
+	viper.SetDefault("ops.cleanup.schedule", "0 2 * * *")
+	// Retention days: vNext defaults to 30 days across ops datasets.
+	viper.SetDefault("ops.cleanup.error_log_retention_days", 30)
+	viper.SetDefault("ops.cleanup.minute_metrics_retention_days", 30)
+	viper.SetDefault("ops.cleanup.hourly_metrics_retention_days", 30)
+	viper.SetDefault("ops.aggregation.enabled", true)
+	viper.SetDefault("ops.metrics_collector_cache.enabled", true)
+	// TTL should be slightly larger than collection interval (1m) to maximize cross-replica cache hits.
+	viper.SetDefault("ops.metrics_collector_cache.ttl", 65*time.Second)
+
 	// JWT
 	viper.SetDefault("jwt.secret", "")
 	viper.SetDefault("jwt.expire_hour", 24)
@@ -687,6 +743,21 @@ func (c *Config) Validate() error {
 	if c.Gateway.Scheduling.SlotCleanupInterval < 0 {
 		return fmt.Errorf("gateway.scheduling.slot_cleanup_interval must be non-negative")
 	}
+	if c.Ops.MetricsCollectorCache.TTL < 0 {
+		return fmt.Errorf("ops.metrics_collector_cache.ttl must be non-negative")
+	}
+	if c.Ops.Cleanup.ErrorLogRetentionDays < 0 {
+		return fmt.Errorf("ops.cleanup.error_log_retention_days must be non-negative")
+	}
+	if c.Ops.Cleanup.MinuteMetricsRetentionDays < 0 {
+		return fmt.Errorf("ops.cleanup.minute_metrics_retention_days must be non-negative")
+	}
+	if c.Ops.Cleanup.HourlyMetricsRetentionDays < 0 {
+		return fmt.Errorf("ops.cleanup.hourly_metrics_retention_days must be non-negative")
+	}
+	if c.Ops.Cleanup.Enabled && strings.TrimSpace(c.Ops.Cleanup.Schedule) == "" {
+		return fmt.Errorf("ops.cleanup.schedule is required when ops.cleanup.enabled=true")
+	}
 	if c.Concurrency.PingInterval < 5 || c.Concurrency.PingInterval > 30 {
 		return fmt.Errorf("concurrency.ping_interval must be between 5-30 seconds")
 	}

backend/internal/pkg/ctxkey/ctxkey.go

@@ -7,4 +7,10 @@ type Key string
 const (
 	// ForcePlatform 强制平台（用于 /antigravity 路由），由 middleware.ForcePlatform 设置
 	ForcePlatform Key = "ctx_force_platform"
+
+	// ClientRequestID 客户端请求的唯一标识，用于追踪请求全生命周期（用于 Ops 监控与排障）。
+	ClientRequestID Key = "ctx_client_request_id"
+
+	// RetryCount 表示当前请求在网关层的重试次数（用于 Ops 记录与排障）。
+	RetryCount Key = "ctx_retry_count"
 )

config.yaml

@@ -221,6 +221,41 @@ redis:
   # 数据库编号（0-15）
   db: 0
 
+# =============================================================================
+# Ops Monitoring (Optional)
+# 运维监控 (可选)
+# =============================================================================
+ops:
+  # Hard switch: disable all ops background jobs and APIs when false
+  # 硬开关：为 false 时禁用所有 Ops 后台任务与接口
+  enabled: true
+
+  # Prefer pre-aggregated tables (ops_metrics_hourly/ops_metrics_daily) for long-window dashboard queries.
+  # 优先使用预聚合表（用于长时间窗口查询性能）
+  use_preaggregated_tables: false
+
+  # Data cleanup configuration
+  # 数据清理配置（vNext 默认统一保留 30 天）
+  cleanup:
+    enabled: true
+    # Cron expression (minute hour dom month dow), e.g. "0 2 * * *" = daily at 2 AM
+    # Cron 表达式（分 时 日 月 周），例如 "0 2 * * *" = 每天凌晨 2 点
+    schedule: "0 2 * * *"
+    error_log_retention_days: 30
+    minute_metrics_retention_days: 30
+    hourly_metrics_retention_days: 30
+
+  # Pre-aggregation configuration
+  # 预聚合任务配置
+  aggregation:
+    enabled: true
+
+  # OpsMetricsCollector Redis cache (reduces duplicate expensive window aggregation in multi-replica deployments)
+  # 指标采集 Redis 缓存（多副本部署时减少重复计算）
+  metrics_collector_cache:
+    enabled: true
+    ttl: 65s
+
 # =============================================================================
 # JWT Configuration
 # JWT 配置