feat(monitoring): add node/tunnel metrics, service monitors, and health checks

- Add NodeMetric/TunnelMetric/ServiceMonitor models and repository methods
- Implement metrics ingestion service with per-minute bucket aggregation
- Add health checker for node connectivity monitoring
- Wire node metrics from WebSocket SystemInfo messages
- Add tunnel metrics ingestion from flow upload endpoint
- Create monitoring REST API endpoints for nodes, tunnels, services
- Implement service monitor CRUD and execution (TCP/ICMP checks)
- Add MonitorPermission for non-admin access control
- Create frontend monitor page with node/tunnel/service views
- Add tunnel metrics ingestion from agent flow reports
- Include schema migration for tunnel_metric unique index
- Fix tunnel entry port conflict validation to use transaction

Entire-Checkpoint: 030821a7c8e3

go-backend/internal/http/handler/handler.go

@@ -16,17 +16,21 @@ import (
 	"time"
 
 	"go-backend/internal/auth"
+	"go-backend/internal/health"
 	"go-backend/internal/http/middleware"
 	"go-backend/internal/http/response"
+	"go-backend/internal/metrics"
 	"go-backend/internal/security"
 	"go-backend/internal/store/repo"
 	"go-backend/internal/ws"
 )
 
 type Handler struct {
-	repo      *repo.Repository
-	jwtSecret string
-	wsServer  *ws.Server
+	repo        *repo.Repository
+	jwtSecret   string
+	wsServer    *ws.Server
+	metrics     *metrics.IngestionService
+	healthCheck *health.Checker
 
 	captchaMu     sync.Mutex
 	captchaTokens map[string]int64
@@ -83,10 +87,31 @@ func New(repo *repo.Repository, jwtSecret string) *Handler {
 		repo:                   repo,
 		jwtSecret:              jwtSecret,
 		wsServer:               ws.NewServer(repo, jwtSecret),
+		metrics:                metrics.NewIngestionService(repo),
+		healthCheck:            nil,
 		captchaTokens:          make(map[string]int64),
 		pendingUpgradeRedeploy: make(map[int64]struct{}),
 	}
+	h.healthCheck = health.NewChecker(repo, h.wsServer)
 	h.wsServer.SetNodeOnlineHook(h.onNodeOnline)
+	h.wsServer.SetNodeMetricHook(func(nodeID int64, info ws.SystemInfo) {
+		metricInfo := metrics.SystemInfo{
+			Uptime:           info.Uptime,
+			BytesReceived:    info.BytesReceived,
+			BytesTransmitted: info.BytesTransmitted,
+			CPUUsage:         info.CPUUsage,
+			MemoryUsage:      info.MemoryUsage,
+			DiskUsage:        info.DiskUsage,
+			Load1:            info.Load1,
+			Load5:            info.Load5,
+			Load15:           info.Load15,
+			TCPConns:         info.TCPConns,
+			UDPConns:         info.UDPConns,
+			NetInSpeed:       info.NetInSpeed,
+			NetOutSpeed:      info.NetOutSpeed,
+		}
+		h.metrics.RecordNodeMetric(nodeID, metricInfo)
+	})
 	return h
 }
 
@@ -195,6 +220,23 @@ func (h *Handler) Register(mux *http.ServeMux) {
 	mux.HandleFunc("/api/v1/announcement/get", h.getAnnouncement)
 	mux.HandleFunc("/api/v1/announcement/update", h.updateAnnouncement)
 
+	mux.HandleFunc("/api/v1/monitor/access", h.monitorAccessHandler)
+	mux.HandleFunc("/api/v1/monitor/nodes/", h.monitorNodeMetricsHandler)
+	mux.HandleFunc("/api/v1/monitor/nodes", h.monitorNodeListHandler)
+	mux.HandleFunc("/api/v1/monitor/tunnels", h.monitorTunnelListHandler)
+	mux.HandleFunc("/api/v1/monitor/tunnels/", h.monitorTunnelMetrics)
+	mux.HandleFunc("/api/v1/monitor/services", h.monitorServiceListHandler)
+	mux.HandleFunc("/api/v1/monitor/services/create", h.monitorServiceCreate)
+	mux.HandleFunc("/api/v1/monitor/services/update", h.monitorServiceUpdate)
+	mux.HandleFunc("/api/v1/monitor/services/delete", h.monitorServiceDelete)
+	mux.HandleFunc("/api/v1/monitor/services/run", h.monitorServiceRun)
+	mux.HandleFunc("/api/v1/monitor/services/latest-results", h.monitorServiceLatestResultsHandler)
+	mux.HandleFunc("/api/v1/monitor/services/limits", h.monitorServiceLimitsHandler)
+	mux.HandleFunc("/api/v1/monitor/services/", h.monitorServiceResultsHandler)
+	mux.HandleFunc("/api/v1/monitor/permission/list", h.monitorPermissionList)
+	mux.HandleFunc("/api/v1/monitor/permission/assign", h.monitorPermissionAssign)
+	mux.HandleFunc("/api/v1/monitor/permission/remove", h.monitorPermissionRemove)
+
 	mux.HandleFunc("/flow/test", h.flowTest)
 	mux.HandleFunc("/flow/config", h.flowConfig)
 	mux.HandleFunc("/flow/upload", h.flowUpload)
@@ -723,6 +765,8 @@ func (h *Handler) flowUpload(w http.ResponseWriter, r *http.Request) {
 	if err == nil && strings.TrimSpace(raw) != "" {
 		var items []flowItem
 		if json.Unmarshal([]byte(raw), &items) == nil {
+			nowMs := time.Now().UnixMilli()
+			h.recordTunnelMetricsFromFlowItems(node.ID, items, nowMs)
 			for _, item := range items {
 				h.processFlowItem(node.ID, item)
 			}

go-backend/internal/http/handler/jobs.go

@@ -18,12 +18,14 @@ func (h *Handler) StartBackgroundJobs() {
 	ctx, cancel := context.WithCancel(context.Background())
 	h.jobsCancel = cancel
 	h.jobsStarted = true
-	h.jobsWG.Add(3)
+	h.jobsWG.Add(5)
 	h.jobsMu.Unlock()
 
 	go h.runHourlyStatsLoop(ctx)
 	go h.runDailyMaintenanceLoop(ctx)
 	go h.runNodeRenewalCycleLoop(ctx)
+	go h.runMetricsIngestion(ctx)
+	go h.runHealthChecks(ctx)
 }
 
 func (h *Handler) StopBackgroundJobs() {
@@ -47,6 +49,20 @@ func (h *Handler) StopBackgroundJobs() {
 	h.jobsWG.Wait()
 }
 
+func (h *Handler) runMetricsIngestion(ctx context.Context) {
+	defer h.jobsWG.Done()
+	if h.metrics != nil {
+		h.metrics.Start(ctx)
+	}
+}
+
+func (h *Handler) runHealthChecks(ctx context.Context) {
+	defer h.jobsWG.Done()
+	if h.healthCheck != nil {
+		h.healthCheck.Start(ctx)
+	}
+}
+
 func (h *Handler) runHourlyStatsLoop(ctx context.Context) {
 	defer h.jobsWG.Done()
 

go-backend/internal/http/handler/monitoring.go

@@ -0,0 +1,795 @@
+package handler
+
+import (
+	"log"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"go-backend/internal/http/response"
+	"go-backend/internal/monitoring"
+	"go-backend/internal/store/model"
+)
+
+const (
+	defaultMetricsRangeMs = int64(60 * 60 * 1000)      // 1h
+	maxMetricsRangeMs     = int64(24 * 60 * 60 * 1000) // 24h
+)
+
+func (h *Handler) resolveServiceMonitorLimits() monitoring.ServiceMonitorLimits {
+	defaults := monitoring.DefaultServiceMonitorLimits()
+	if h == nil || h.repo == nil {
+		return defaults
+	}
+	cfg, err := h.repo.GetConfigsByNames([]string{
+		monitoring.ConfigServiceMonitorCheckerScanIntervalSec,
+		monitoring.ConfigServiceMonitorWorkerLimit,
+		monitoring.ConfigServiceMonitorMinIntervalSec,
+		monitoring.ConfigServiceMonitorDefaultIntervalSec,
+		monitoring.ConfigServiceMonitorMinTimeoutSec,
+		monitoring.ConfigServiceMonitorDefaultTimeoutSec,
+		monitoring.ConfigServiceMonitorMaxTimeoutSec,
+	})
+	if err != nil {
+		return defaults
+	}
+	return monitoring.ServiceMonitorLimitsFromConfigMap(cfg)
+}
+
+func (h *Handler) monitorNodeMetricsHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	path := r.URL.Path
+	prefix := "/api/v1/monitor/nodes/"
+	if !strings.HasPrefix(path, prefix) {
+		response.WriteJSON(w, response.ErrDefault("无效的路径"))
+		return
+	}
+
+	rest := strings.TrimPrefix(path, prefix)
+	if strings.HasSuffix(rest, "/metrics/latest") {
+		h.handleNodeMetricsLatest(w, r, strings.TrimSuffix(rest, "/metrics/latest"))
+		return
+	}
+	if strings.HasSuffix(rest, "/metrics") {
+		h.handleNodeMetrics(w, r, strings.TrimSuffix(rest, "/metrics"))
+		return
+	}
+
+	response.WriteJSON(w, response.ErrDefault("无效的路径"))
+}
+
+type monitorNodeListItem struct {
+	ID          int64  `json:"id"`
+	Inx         int    `json:"inx"`
+	Name        string `json:"name"`
+	Status      int    `json:"status"`
+	UpdatedTime int64  `json:"updatedTime"`
+}
+
+func (h *Handler) monitorNodeListHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	nodes, err := h.repo.ListMonitorNodes()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	items := make([]monitorNodeListItem, 0, len(nodes))
+	for _, n := range nodes {
+		updated := int64(0)
+		if n.UpdatedTime.Valid {
+			updated = n.UpdatedTime.Int64
+		}
+		items = append(items, monitorNodeListItem{
+			ID:          n.ID,
+			Inx:         n.Inx,
+			Name:        n.Name,
+			Status:      n.Status,
+			UpdatedTime: updated,
+		})
+	}
+
+	response.WriteJSON(w, response.OK(items))
+}
+
+type monitorTunnelListItem struct {
+	ID          int64  `json:"id"`
+	Inx         int    `json:"inx"`
+	Name        string `json:"name"`
+	Status      int    `json:"status"`
+	UpdatedTime int64  `json:"updatedTime"`
+}
+
+func (h *Handler) monitorTunnelListHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	tunnels, err := h.repo.ListMonitorTunnels()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	items := make([]monitorTunnelListItem, 0, len(tunnels))
+	for _, t := range tunnels {
+		items = append(items, monitorTunnelListItem{
+			ID:          t.ID,
+			Inx:         t.Inx,
+			Name:        t.Name,
+			Status:      t.Status,
+			UpdatedTime: t.UpdatedTime,
+		})
+	}
+
+	response.WriteJSON(w, response.OK(items))
+}
+
+func (h *Handler) handleNodeMetrics(w http.ResponseWriter, r *http.Request, nodeIDStr string) {
+	nodeID, err := strconv.ParseInt(nodeIDStr, 10, 64)
+	if err != nil || nodeID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的节点ID"))
+		return
+	}
+
+	now := time.Now().UnixMilli()
+	startMs := now - defaultMetricsRangeMs
+	endMs := now
+
+	if s := r.URL.Query().Get("start"); s != "" {
+		if v, err := strconv.ParseInt(s, 10, 64); err == nil {
+			startMs = v
+		}
+	}
+	if e := r.URL.Query().Get("end"); e != "" {
+		if v, err := strconv.ParseInt(e, 10, 64); err == nil {
+			endMs = v
+		}
+	}
+	if startMs <= 0 || endMs <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的时间范围"))
+		return
+	}
+	if endMs < startMs {
+		response.WriteJSON(w, response.ErrDefault("无效的时间范围"))
+		return
+	}
+	if endMs-startMs > maxMetricsRangeMs {
+		response.WriteJSON(w, response.ErrDefault("时间范围过大"))
+		return
+	}
+
+	metrics, err := h.repo.GetNodeMetrics(nodeID, startMs, endMs)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(metrics))
+}
+
+func (h *Handler) handleNodeMetricsLatest(w http.ResponseWriter, _ *http.Request, nodeIDStr string) {
+	nodeID, err := strconv.ParseInt(nodeIDStr, 10, 64)
+	if err != nil || nodeID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的节点ID"))
+		return
+	}
+
+	metric, err := h.repo.GetLatestNodeMetric(nodeID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	if metric == nil {
+		response.WriteJSON(w, response.OK(nil))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(metric))
+}
+
+func (h *Handler) monitorTunnelMetrics(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	tunnelIDStr := extractPathParam(r.URL.Path, "/api/v1/monitor/tunnels/", "/metrics")
+	tunnelID, err := strconv.ParseInt(tunnelIDStr, 10, 64)
+	if err != nil || tunnelID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的隧道ID"))
+		return
+	}
+
+	now := time.Now().UnixMilli()
+	startMs := now - defaultMetricsRangeMs
+	endMs := now
+
+	if s := r.URL.Query().Get("start"); s != "" {
+		if v, err := strconv.ParseInt(s, 10, 64); err == nil {
+			startMs = v
+		}
+	}
+	if e := r.URL.Query().Get("end"); e != "" {
+		if v, err := strconv.ParseInt(e, 10, 64); err == nil {
+			endMs = v
+		}
+	}
+	if startMs <= 0 || endMs <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的时间范围"))
+		return
+	}
+	if endMs < startMs {
+		response.WriteJSON(w, response.ErrDefault("无效的时间范围"))
+		return
+	}
+	if endMs-startMs > maxMetricsRangeMs {
+		response.WriteJSON(w, response.ErrDefault("时间范围过大"))
+		return
+	}
+
+	metrics, err := h.repo.GetTunnelMetricsAggregated(tunnelID, startMs, endMs)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(metrics))
+}
+
+func (h *Handler) monitorServiceListHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	monitors, err := h.repo.ListServiceMonitors()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(monitors))
+}
+
+type createServiceMonitorRequest struct {
+	Name        string `json:"name"`
+	Type        string `json:"type"`
+	Target      string `json:"target"`
+	IntervalSec int    `json:"intervalSec"`
+	TimeoutSec  int    `json:"timeoutSec"`
+	NodeID      int64  `json:"nodeId"`
+	Enabled     *int   `json:"enabled"`
+}
+
+func (h *Handler) monitorServiceCreate(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	var req createServiceMonitorRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+
+	name := strings.TrimSpace(req.Name)
+	if name == "" {
+		response.WriteJSON(w, response.ErrDefault("名称不能为空"))
+		return
+	}
+
+	monitorType := strings.ToLower(strings.TrimSpace(req.Type))
+	if monitorType != "tcp" && monitorType != "icmp" {
+		response.WriteJSON(w, response.ErrDefault("类型必须是 tcp 或 icmp"))
+		return
+	}
+
+	target := strings.TrimSpace(req.Target)
+	if target == "" {
+		response.WriteJSON(w, response.ErrDefault("目标地址不能为空"))
+		return
+	}
+
+	limits := h.resolveServiceMonitorLimits()
+
+	intervalSec := req.IntervalSec
+	if intervalSec <= 0 {
+		intervalSec = limits.DefaultIntervalSec
+	}
+	if intervalSec < limits.MinIntervalSec {
+		intervalSec = limits.MinIntervalSec
+	}
+
+	timeoutSec := req.TimeoutSec
+	if timeoutSec <= 0 {
+		timeoutSec = limits.DefaultTimeoutSec
+	}
+	if timeoutSec < limits.MinTimeoutSec {
+		timeoutSec = limits.MinTimeoutSec
+	}
+	if timeoutSec > limits.MaxTimeoutSec {
+		timeoutSec = limits.MaxTimeoutSec
+	}
+
+	enabled := 1
+	if req.Enabled != nil {
+		if *req.Enabled == 0 || *req.Enabled == 1 {
+			enabled = *req.Enabled
+		}
+	}
+
+	now := time.Now().UnixMilli()
+	if req.NodeID > 0 {
+		n, err := h.repo.GetNodeByID(req.NodeID)
+		if err != nil {
+			response.WriteJSON(w, response.Err(-2, err.Error()))
+			return
+		}
+		if n == nil {
+			response.WriteJSON(w, response.ErrDefault("节点不存在"))
+			return
+		}
+	}
+	m := &model.ServiceMonitor{
+		Name:        name,
+		Type:        monitorType,
+		Target:      target,
+		IntervalSec: intervalSec,
+		TimeoutSec:  timeoutSec,
+		NodeID:      req.NodeID,
+		Enabled:     enabled,
+		CreatedTime: now,
+		UpdatedTime: now,
+	}
+	if m.Type == "icmp" && m.NodeID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("ICMP 监控必须选择执行节点"))
+		return
+	}
+	// enabled is already normalized above.
+
+	if err := h.repo.CreateServiceMonitor(m); err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(m))
+}
+
+type updateServiceMonitorRequest struct {
+	ID          int64  `json:"id"`
+	Name        string `json:"name"`
+	Type        string `json:"type"`
+	Target      string `json:"target"`
+	IntervalSec int    `json:"intervalSec"`
+	TimeoutSec  int    `json:"timeoutSec"`
+	NodeID      *int64 `json:"nodeId"`
+	Enabled     *int   `json:"enabled"`
+}
+
+func (h *Handler) monitorServiceUpdate(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	var req updateServiceMonitorRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+
+	if req.ID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的监控ID"))
+		return
+	}
+
+	existing, err := h.repo.GetServiceMonitor(req.ID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	if existing == nil {
+		response.WriteJSON(w, response.ErrDefault("监控不存在"))
+		return
+	}
+
+	name := strings.TrimSpace(req.Name)
+	if name != "" {
+		existing.Name = name
+	}
+
+	monitorType := strings.ToLower(strings.TrimSpace(req.Type))
+	if monitorType == "tcp" || monitorType == "icmp" {
+		existing.Type = monitorType
+	}
+
+	target := strings.TrimSpace(req.Target)
+	if target != "" {
+		existing.Target = target
+	}
+
+	limits := h.resolveServiceMonitorLimits()
+
+	if req.IntervalSec > 0 {
+		intervalSec := req.IntervalSec
+		if intervalSec < limits.MinIntervalSec {
+			intervalSec = limits.MinIntervalSec
+		}
+		existing.IntervalSec = intervalSec
+	}
+	if req.TimeoutSec > 0 {
+		timeoutSec := req.TimeoutSec
+		if timeoutSec < limits.MinTimeoutSec {
+			timeoutSec = limits.MinTimeoutSec
+		}
+		if timeoutSec > limits.MaxTimeoutSec {
+			timeoutSec = limits.MaxTimeoutSec
+		}
+		existing.TimeoutSec = timeoutSec
+	}
+
+	if req.NodeID != nil {
+		existing.NodeID = *req.NodeID
+	}
+	if req.Enabled != nil {
+		if *req.Enabled == 0 || *req.Enabled == 1 {
+			existing.Enabled = *req.Enabled
+		}
+	}
+
+	existing.UpdatedTime = time.Now().UnixMilli()
+	if existing.Type == "icmp" && existing.NodeID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("ICMP 监控必须选择执行节点"))
+		return
+	}
+	if existing.NodeID > 0 {
+		n, err := h.repo.GetNodeByID(existing.NodeID)
+		if err != nil {
+			response.WriteJSON(w, response.Err(-2, err.Error()))
+			return
+		}
+		if n == nil {
+			response.WriteJSON(w, response.ErrDefault("节点不存在"))
+			return
+		}
+	}
+
+	if err := h.repo.UpdateServiceMonitor(existing); err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(existing))
+}
+
+type deleteServiceMonitorRequest struct {
+	ID int64 `json:"id"`
+}
+
+func (h *Handler) monitorServiceDelete(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	var req deleteServiceMonitorRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+
+	if req.ID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的监控ID"))
+		return
+	}
+
+	if err := h.repo.DeleteServiceMonitor(req.ID); err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OKEmpty())
+}
+
+func (h *Handler) monitorServiceRun(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+	if h.healthCheck == nil {
+		response.WriteJSON(w, response.ErrDefault("监控服务不可用"))
+		return
+	}
+
+	var req deleteServiceMonitorRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+	if req.ID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的监控ID"))
+		return
+	}
+
+	m, err := h.repo.GetServiceMonitor(req.ID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	if m == nil {
+		response.WriteJSON(w, response.ErrDefault("监控不存在"))
+		return
+	}
+
+	res, err := h.healthCheck.RunOnce(m)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	if err := h.repo.InsertServiceMonitorResult(res); err != nil {
+		log.Printf("monitoring write failed op=service_monitor_result.manual_insert monitor_id=%d err=%v", res.MonitorID, err)
+	}
+	response.WriteJSON(w, response.OK(res))
+}
+
+func (h *Handler) monitorServiceResultsHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	monitorIDStr := extractPathParam(r.URL.Path, "/api/v1/monitor/services/", "/results")
+	monitorID, err := strconv.ParseInt(monitorIDStr, 10, 64)
+	if err != nil || monitorID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的监控ID"))
+		return
+	}
+
+	limit := 100
+	if l := r.URL.Query().Get("limit"); l != "" {
+		if v, err := strconv.Atoi(l); err == nil && v > 0 && v <= 1000 {
+			limit = v
+		}
+	}
+
+	results, err := h.repo.GetServiceMonitorResults(monitorID, limit)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(results))
+}
+
+func (h *Handler) monitorServiceLatestResultsHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+
+	results, err := h.repo.GetLatestServiceMonitorResults()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	response.WriteJSON(w, response.OK(results))
+}
+
+func (h *Handler) monitorServiceLimitsHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureMonitoringAccess(w, r) {
+		return
+	}
+	response.WriteJSON(w, response.OK(h.resolveServiceMonitorLimits()))
+}
+
+func extractPathParam(path, prefix, suffix string) string {
+	if !strings.HasPrefix(path, prefix) {
+		return ""
+	}
+	rest := strings.TrimPrefix(path, prefix)
+	if suffix != "" {
+		rest = strings.TrimSuffix(rest, suffix)
+	}
+	return rest
+}
+
+type monitorAccessData struct {
+	Allowed bool   `json:"allowed"`
+	Reason  string `json:"reason,omitempty"`
+}
+
+// monitorAccessHandler is a lightweight capability check for frontend navigation.
+// It does NOT replace authorization on the actual monitoring endpoints.
+func (h *Handler) monitorAccessHandler(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+
+	userID, roleID, err := userRoleFromRequest(r)
+	if err != nil {
+		response.WriteJSON(w, response.Err(401, "未登录或token已过期"))
+		return
+	}
+	if roleID == 0 {
+		response.WriteJSON(w, response.OK(monitorAccessData{Allowed: true}))
+		return
+	}
+
+	allowed, err := h.repo.HasMonitorPermission(userID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	data := monitorAccessData{Allowed: allowed}
+	if !allowed {
+		data.Reason = "need_admin_grant"
+	}
+	response.WriteJSON(w, response.OK(data))
+}
+
+func (h *Handler) ensureAdminAccess(w http.ResponseWriter, r *http.Request) bool {
+	_, roleID, err := userRoleFromRequest(r)
+	if err != nil {
+		response.WriteJSON(w, response.Err(401, "未登录或token已过期"))
+		return false
+	}
+	if roleID != 0 {
+		response.WriteJSON(w, response.Err(403, "权限不足，仅管理员可操作"))
+		return false
+	}
+	return true
+}
+
+func (h *Handler) ensureMonitoringAccess(w http.ResponseWriter, r *http.Request) bool {
+	userID, roleID, err := userRoleFromRequest(r)
+	if err != nil {
+		response.WriteJSON(w, response.Err(401, "未登录或token已过期"))
+		return false
+	}
+	if roleID == 0 {
+		return true
+	}
+	allowed, err := h.repo.HasMonitorPermission(userID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return false
+	}
+	if !allowed {
+		response.WriteJSON(w, response.Err(403, "权限不足：当前账户非管理员，且未被授予监控权限。请联系管理员在用户管理中授权监控权限。"))
+		return false
+	}
+	return true
+}
+
+func (h *Handler) monitorPermissionList(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureAdminAccess(w, r) {
+		return
+	}
+
+	items, err := h.repo.ListMonitorPermissions()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	response.WriteJSON(w, response.OK(items))
+}
+
+type monitorPermissionMutationRequest struct {
+	UserID int64 `json:"userId"`
+}
+
+func (h *Handler) monitorPermissionAssign(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureAdminAccess(w, r) {
+		return
+	}
+
+	var req monitorPermissionMutationRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+	if req.UserID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的用户ID"))
+		return
+	}
+
+	u, err := h.repo.GetUserByID(req.UserID)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	if u == nil {
+		response.WriteJSON(w, response.ErrDefault("用户不存在"))
+		return
+	}
+
+	if err := h.repo.InsertMonitorPermission(req.UserID, time.Now().UnixMilli()); err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	response.WriteJSON(w, response.OKEmpty())
+}
+
+func (h *Handler) monitorPermissionRemove(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		response.WriteJSON(w, response.ErrDefault("请求失败"))
+		return
+	}
+	if !h.ensureAdminAccess(w, r) {
+		return
+	}
+
+	var req monitorPermissionMutationRequest
+	if err := decodeJSON(r.Body, &req); err != nil {
+		response.WriteJSON(w, response.ErrDefault("请求参数错误"))
+		return
+	}
+	if req.UserID <= 0 {
+		response.WriteJSON(w, response.ErrDefault("无效的用户ID"))
+		return
+	}
+
+	if err := h.repo.DeleteMonitorPermission(req.UserID); err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+	response.WriteJSON(w, response.OKEmpty())
+}

go-backend/internal/http/handler/mutations.go

@@ -809,7 +809,7 @@ func (h *Handler) tunnelUpdate(w http.ResponseWriter, r *http.Request) {
 			newEntryNodeIDs = append(newEntryNodeIDs, in.NodeID)
 		}
 	}
-	if err := h.validateTunnelEntryPortConflictsForNewEntries(id, oldEntryNodeIDs, newEntryNodeIDs); err != nil {
+	if err := h.validateTunnelEntryPortConflictsForNewEntriesTx(tx, id, oldEntryNodeIDs, newEntryNodeIDs); err != nil {
 		response.WriteJSON(w, response.ErrDefault(err.Error()))
 		return
 	}
@@ -997,8 +997,22 @@ func (h *Handler) cleanupTunnelForwardRuntimesOnRemovedEntryNodes(tunnelID int64
 	}
 }
 
-func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tunnelID int64, oldEntryNodeIDs, newEntryNodeIDs []int64) error {
-	if h == nil || h.repo == nil || tunnelID <= 0 {
+func (h *Handler) validateForwardPortAvailabilityTx(tx *gorm.DB, node *nodeRecord, port int, currentForwardID int64) error {
+	if h == nil || h.repo == nil || tx == nil || node == nil || port <= 0 {
+		return nil
+	}
+	occupied, err := h.repo.HasOtherForwardOnNodePortTx(tx, node.ID, port, currentForwardID)
+	if err != nil {
+		return err
+	}
+	if occupied {
+		return fmt.Errorf("节点 %s 端口 %d 已被其他转发占用", node.Name, port)
+	}
+	return nil
+}
+
+func (h *Handler) validateTunnelEntryPortConflictsForNewEntriesTx(tx *gorm.DB, tunnelID int64, oldEntryNodeIDs, newEntryNodeIDs []int64) error {
+	if h == nil || h.repo == nil || tx == nil || tunnelID <= 0 {
 		return nil
 	}
 
@@ -1007,7 +1021,7 @@ func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tunnelID int64,
 		return nil
 	}
 
-	forwards, err := h.listForwardsByTunnel(tunnelID)
+	forwards, err := h.repo.ListForwardsByTunnelTx(tx, tunnelID)
 	if err != nil || len(forwards) == 0 {
 		return nil
 	}
@@ -1017,7 +1031,7 @@ func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tunnelID int64,
 		if f == nil {
 			continue
 		}
-		oldPorts, portsErr := h.listForwardPorts(f.ID)
+		oldPorts, portsErr := h.repo.ListForwardPortsTx(tx, f.ID)
 		if portsErr != nil {
 			continue
 		}
@@ -1027,14 +1041,11 @@ func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tunnelID int64,
 		}
 
 		for _, nodeID := range addedNodeIDs {
-			node, nodeErr := h.getNodeRecord(nodeID)
+			node, nodeErr := h.repo.GetNodeRecordTx(tx, nodeID)
 			if nodeErr != nil {
 				continue
 			}
-			if err := validateLocalNodePort(node, port); err != nil {
-				return fmt.Errorf("转发 %s 入口端口冲突: %w", f.Name, err)
-			}
-			if err := h.validateForwardPortAvailability(node, port, f.ID); err != nil {
+			if err := h.validateForwardPortAvailabilityTx(tx, node, port, f.ID); err != nil {
 				return fmt.Errorf("转发 %s 入口端口冲突: %w", f.Name, err)
 			}
 		}

go-backend/internal/http/handler/tunnel_metrics_ingestion.go

@@ -0,0 +1,111 @@
+package handler
+
+import (
+	"log"
+	"strings"
+	"time"
+
+	"go-backend/internal/store/model"
+)
+
+type tunnelTrafficDelta struct {
+	bytesIn  int64
+	bytesOut int64
+}
+
+func unixMilliBucketMinute(nowMs int64) int64 {
+	if nowMs <= 0 {
+		return 0
+	}
+	const minuteMs = int64(time.Minute / time.Millisecond)
+	return nowMs - (nowMs % minuteMs)
+}
+
+func (h *Handler) recordTunnelMetricsFromFlowItems(nodeID int64, items []flowItem, nowMs int64) {
+	if h == nil || h.repo == nil {
+		return
+	}
+	if nodeID <= 0 || len(items) == 0 {
+		return
+	}
+
+	bucketTs := unixMilliBucketMinute(nowMs)
+	if bucketTs <= 0 {
+		return
+	}
+
+	forwardDeltas := make(map[int64]tunnelTrafficDelta)
+	for _, item := range items {
+		name := strings.TrimSpace(item.N)
+		if name == "" || name == "web_api" {
+			continue
+		}
+		forwardID, _, _, ok := parseFlowServiceIDs(name)
+		if !ok {
+			continue
+		}
+		if item.D == 0 && item.U == 0 {
+			continue
+		}
+		d := forwardDeltas[forwardID]
+		d.bytesIn += item.D
+		d.bytesOut += item.U
+		forwardDeltas[forwardID] = d
+	}
+	if len(forwardDeltas) == 0 {
+		return
+	}
+
+	forwardIDs := make([]int64, 0, len(forwardDeltas))
+	for id := range forwardDeltas {
+		forwardIDs = append(forwardIDs, id)
+	}
+
+	forwardTunnelMap, err := h.repo.MapForwardIDsToTunnelIDs(forwardIDs)
+	if err != nil {
+		log.Printf("monitoring write skipped op=tunnel_metric.map_forward_to_tunnel node_id=%d err=%v", nodeID, err)
+		return
+	}
+	if len(forwardTunnelMap) == 0 {
+		return
+	}
+
+	tunnelAgg := make(map[int64]tunnelTrafficDelta)
+	for forwardID, delta := range forwardDeltas {
+		tunnelID := forwardTunnelMap[forwardID]
+		if tunnelID <= 0 {
+			continue
+		}
+		a := tunnelAgg[tunnelID]
+		a.bytesIn += delta.bytesIn
+		a.bytesOut += delta.bytesOut
+		tunnelAgg[tunnelID] = a
+	}
+	if len(tunnelAgg) == 0 {
+		return
+	}
+
+	metrics := make([]*model.TunnelMetric, 0, len(tunnelAgg))
+	for tunnelID, delta := range tunnelAgg {
+		if delta.bytesIn == 0 && delta.bytesOut == 0 {
+			continue
+		}
+		metrics = append(metrics, &model.TunnelMetric{
+			TunnelID:     tunnelID,
+			NodeID:       nodeID,
+			Timestamp:    bucketTs,
+			BytesIn:      delta.bytesIn,
+			BytesOut:     delta.bytesOut,
+			Connections:  0,
+			Errors:       0,
+			AvgLatencyMs: 0,
+		})
+	}
+	if len(metrics) == 0 {
+		return
+	}
+
+	if err := h.repo.UpsertTunnelMetricBuckets(metrics); err != nil {
+		log.Printf("monitoring write failed op=tunnel_metric.upsert_buckets node_id=%d bucket_ts=%d count=%d err=%v", nodeID, bucketTs, len(metrics), err)
+	}
+}

go-backend/internal/http/middleware/auth.go

@@ -101,6 +101,10 @@ func shouldSkip(path string) bool {
 }
 
 func requiresAdmin(path string) bool {
+	if strings.HasPrefix(path, "/api/v1/monitor/permission/") {
+		return true
+	}
+
 	if strings.HasPrefix(path, "/api/v1/group/") {
 		return true
 	}