feat(monitoring): add node/tunnel metrics, service monitors, and health checks (#331)

## Summary
- Add comprehensive monitoring system with
NodeMetric/TunnelMetric/ServiceMonitor models
- Implement metrics ingestion service with per-minute bucket aggregation
and upsert support
- Add health checker for node connectivity monitoring with configurable
intervals
- Wire node metrics from WebSocket SystemInfo messages to metrics
service
- Add tunnel metrics ingestion from flow upload endpoint with
transaction support
- Create monitoring REST API endpoints for nodes, tunnels, and services
- Implement service monitor CRUD and execution (TCP/ICMP health checks)
- Add MonitorPermission model for non-admin access control to monitoring
features
- Create frontend monitor page with node/tunnel/service views
- Include schema migration (v6) for tunnel_metric unique index and
deduplication
- Fix tunnel entry port conflict validation to use transaction (Tx
variants)

.gitignore

@@ -62,6 +62,9 @@ go-gost/ss/
 .classpath
 .project
 .settings/
+
+# OpenCode session metadata
+.entire/
 bin/
 tmp/
 *.swp

AGENTS.md

@@ -1,9 +1,9 @@
 # PROJECT KNOWLEDGE BASE
 
-**Generated:** Thu Feb 26 2026
-**Commit:** 21008cc
+**Generated:** Wed Mar 18 2026
+**Commit:** ea21a7d
 **Branch:** main
-**Tag:** 2.1.5-rc15
+**Tag:** 2.1.8
 
 ## OVERVIEW
 FLVX (formerly Flux Panel) is a traffic forwarding management system built on a forked GOST v3 stack. It ships as a Go-based admin API (SQLite/PostgreSQL) + Vite/React UI + Go forwarding agent, with optional mobile WebView wrappers.

go-backend/internal/health/checker.go

@@ -0,0 +1,360 @@
+package health
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"log"
+	"net"
+	"strings"
+	"sync"
+	"time"
+
+	"go-backend/internal/monitoring"
+	"go-backend/internal/store/model"
+	"go-backend/internal/store/repo"
+	"go-backend/internal/ws"
+)
+
+type nodeCommander interface {
+	SendCommand(nodeID int64, cmdType string, data interface{}, timeout time.Duration) (ws.CommandResult, error)
+}
+
+type Checker struct {
+	repo      *repo.Repository
+	commander nodeCommander
+	lastRun   map[int64]int64
+	inFlight  map[int64]struct{}
+
+	mu     sync.RWMutex
+	cancel context.CancelFunc
+	wg     sync.WaitGroup
+}
+
+func NewChecker(repo *repo.Repository, commander nodeCommander) *Checker {
+	return &Checker{
+		repo:      repo,
+		commander: commander,
+		lastRun:   make(map[int64]int64),
+		inFlight:  make(map[int64]struct{}),
+	}
+}
+
+func (c *Checker) Start(ctx context.Context) {
+	c.mu.Lock()
+	ctx, cancel := context.WithCancel(ctx)
+	c.cancel = cancel
+	c.mu.Unlock()
+
+	c.runChecks(ctx)
+
+	for {
+		limits := c.loadServiceMonitorLimits()
+		scanInterval := time.Duration(limits.CheckerScanIntervalSec) * time.Second
+		if scanInterval <= 0 {
+			scanInterval = 30 * time.Second
+		}
+
+		timer := time.NewTimer(scanInterval)
+		select {
+		case <-ctx.Done():
+			timer.Stop()
+			return
+		case <-timer.C:
+			c.runChecks(ctx)
+		}
+	}
+}
+
+func (c *Checker) Stop() {
+	c.mu.Lock()
+	if c.cancel != nil {
+		c.cancel()
+	}
+	c.mu.Unlock()
+	c.wg.Wait()
+}
+
+func (c *Checker) RunOnce(m *model.ServiceMonitor) (*model.ServiceMonitorResult, error) {
+	if c == nil {
+		return nil, errors.New("checker not initialized")
+	}
+	if m == nil {
+		return nil, errors.New("monitor is nil")
+	}
+	limits := c.loadServiceMonitorLimits()
+	return c.executeCheck(m, time.Now().UnixMilli(), limits), nil
+}
+
+func (c *Checker) runChecks(ctx context.Context) {
+	if c == nil || c.repo == nil {
+		return
+	}
+
+	limits := c.loadServiceMonitorLimits()
+	monitors, err := c.repo.ListEnabledServiceMonitors()
+	if err != nil {
+		log.Printf("service monitor scheduler failed op=list_enabled err=%v", err)
+		return
+	}
+	if len(monitors) == 0 {
+		return
+	}
+
+	// Use persisted result timestamps to avoid restart bursts.
+	latest, err := c.repo.GetLatestServiceMonitorResults()
+	if err != nil {
+		log.Printf("service monitor scheduler failed op=get_latest_results err=%v", err)
+		latest = nil
+	}
+	persistedLast := make(map[int64]int64, len(latest))
+	for _, r := range latest {
+		if r.MonitorID <= 0 || r.Timestamp <= 0 {
+			continue
+		}
+		persistedLast[r.MonitorID] = r.Timestamp
+	}
+
+	now := time.Now().UnixMilli()
+	due := make([]model.ServiceMonitor, 0, len(monitors))
+	for _, m := range monitors {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+		}
+
+		intervalSec := m.IntervalSec
+		if intervalSec <= 0 {
+			intervalSec = limits.DefaultIntervalSec
+		}
+		if intervalSec < limits.MinIntervalSec {
+			intervalSec = limits.MinIntervalSec
+		}
+		intervalMs := int64(intervalSec) * 1000
+
+		c.mu.Lock()
+		if _, ok := c.inFlight[m.ID]; ok {
+			c.mu.Unlock()
+			continue
+		}
+
+		lastSeen := persistedLast[m.ID]
+		if v := c.lastRun[m.ID]; v > lastSeen {
+			lastSeen = v
+		}
+		if lastSeen > 0 && intervalMs > 0 && now-lastSeen < intervalMs {
+			c.mu.Unlock()
+			continue
+		}
+
+		c.inFlight[m.ID] = struct{}{}
+		// Use now as a best-effort guard against overlapping scans; the final
+		// timestamp is updated again when the result is persisted.
+		c.lastRun[m.ID] = now
+		c.mu.Unlock()
+
+		due = append(due, m)
+	}
+	if len(due) == 0 {
+		return
+	}
+
+	workerLimit := limits.WorkerLimit
+	if workerLimit <= 0 {
+		workerLimit = 1
+	}
+	if workerLimit > len(due) {
+		workerLimit = len(due)
+	}
+
+	jobs := make(chan model.ServiceMonitor, len(due))
+	for _, m := range due {
+		jobs <- m
+	}
+	close(jobs)
+
+	for i := 0; i < workerLimit; i++ {
+		c.wg.Add(1)
+		go func() {
+			defer c.wg.Done()
+			for {
+				select {
+				case <-ctx.Done():
+					return
+				case m, ok := <-jobs:
+					if !ok {
+						return
+					}
+					ts := time.Now().UnixMilli()
+					result := c.executeCheck(&m, ts, limits)
+					if err := c.repo.InsertServiceMonitorResult(result); err != nil {
+						log.Printf("monitoring write failed op=service_monitor_result.insert monitor_id=%d err=%v", result.MonitorID, err)
+					}
+
+					c.mu.Lock()
+					c.lastRun[m.ID] = result.Timestamp
+					delete(c.inFlight, m.ID)
+					c.mu.Unlock()
+				}
+			}
+		}()
+	}
+}
+
+func (c *Checker) executeCheck(m *model.ServiceMonitor, timestamp int64, limits monitoring.ServiceMonitorLimits) *model.ServiceMonitorResult {
+	result := &model.ServiceMonitorResult{
+		MonitorID: m.ID,
+		NodeID:    m.NodeID,
+		Timestamp: timestamp,
+	}
+
+	timeoutSec := m.TimeoutSec
+	if timeoutSec <= 0 {
+		timeoutSec = limits.DefaultTimeoutSec
+	}
+	if timeoutSec < limits.MinTimeoutSec {
+		timeoutSec = limits.MinTimeoutSec
+	}
+	if timeoutSec > limits.MaxTimeoutSec {
+		timeoutSec = limits.MaxTimeoutSec
+	}
+
+	timeout := time.Duration(timeoutSec) * time.Second
+
+	// When nodeId is set, run checks on the specified node.
+	if m.NodeID > 0 {
+		c.checkOnNode(m, timeoutSec, timeout, result)
+		return result
+	}
+
+	switch strings.ToLower(strings.TrimSpace(m.Type)) {
+	case "tcp":
+		c.checkTCP(m.Target, timeout, result)
+	case "icmp":
+		result.Success = 0
+		result.ErrorMessage = "ICMP 监控必须指定执行节点"
+	default:
+		result.Success = 0
+		result.ErrorMessage = fmt.Sprintf("不支持的检查类型: %s", m.Type)
+	}
+
+	return result
+}
+
+func (c *Checker) loadServiceMonitorLimits() monitoring.ServiceMonitorLimits {
+	defaults := monitoring.DefaultServiceMonitorLimits()
+	if c == nil || c.repo == nil {
+		return defaults
+	}
+	cfg, err := c.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)
+}
+
+type serviceMonitorCheckRequest struct {
+	MonitorID  int64  `json:"monitorId"`
+	Type       string `json:"type"`
+	Target     string `json:"target"`
+	TimeoutSec int    `json:"timeoutSec"`
+}
+
+func (c *Checker) checkOnNode(m *model.ServiceMonitor, timeoutSec int, timeout time.Duration, result *model.ServiceMonitorResult) {
+	if c == nil || m == nil || result == nil {
+		return
+	}
+	if c.commander == nil {
+		result.Success = 0
+		result.ErrorMessage = "节点检查不可用"
+		return
+	}
+
+	checkType := strings.ToLower(strings.TrimSpace(m.Type))
+	if checkType != "tcp" && checkType != "icmp" {
+		result.Success = 0
+		result.ErrorMessage = fmt.Sprintf("不支持的检查类型: %s", m.Type)
+		return
+	}
+	if strings.TrimSpace(m.Target) == "" {
+		result.Success = 0
+		result.ErrorMessage = "检查目标为空"
+		return
+	}
+
+	req := serviceMonitorCheckRequest{
+		MonitorID:  m.ID,
+		Type:       checkType,
+		Target:     m.Target,
+		TimeoutSec: timeoutSec,
+	}
+
+	cmdTimeout := timeout
+	if cmdTimeout < 2*time.Second {
+		cmdTimeout = 2 * time.Second
+	}
+	cmdTimeout = cmdTimeout + 2*time.Second
+
+	cmdRes, err := c.commander.SendCommand(m.NodeID, "ServiceMonitorCheck", req, cmdTimeout)
+	if err != nil {
+		result.Success = 0
+		result.ErrorMessage = err.Error()
+		return
+	}
+	if cmdRes.Data == nil {
+		result.Success = 0
+		result.ErrorMessage = "节点返回为空"
+		return
+	}
+
+	if v, ok := cmdRes.Data["success"]; ok {
+		if b, ok := v.(bool); ok {
+			if b {
+				result.Success = 1
+			} else {
+				result.Success = 0
+			}
+		}
+	}
+	if v, ok := cmdRes.Data["latencyMs"]; ok {
+		if f, ok := v.(float64); ok {
+			result.LatencyMs = f
+		}
+	}
+	if v, ok := cmdRes.Data["statusCode"]; ok {
+		if f, ok := v.(float64); ok {
+			result.StatusCode = int(f)
+		}
+	}
+	if v, ok := cmdRes.Data["errorMessage"]; ok {
+		if s, ok := v.(string); ok {
+			result.ErrorMessage = s
+		}
+	}
+}
+
+func (c *Checker) checkTCP(target string, timeout time.Duration, result *model.ServiceMonitorResult) {
+	start := time.Now()
+
+	conn, err := net.DialTimeout("tcp", target, timeout)
+	latency := time.Since(start)
+
+	result.LatencyMs = float64(latency.Milliseconds())
+
+	if err != nil {
+		result.Success = 0
+		result.ErrorMessage = err.Error()
+		return
+	}
+	_ = conn.Close()
+	result.Success = 1
+}

go-backend/internal/health/checker_test.go

@@ -0,0 +1,477 @@
+package health
+
+import (
+	"context"
+	"net"
+	"testing"
+	"time"
+
+	"go-backend/internal/monitoring"
+	"go-backend/internal/store/model"
+	"go-backend/internal/store/repo"
+	"go-backend/internal/ws"
+)
+
+type fakeCommander struct {
+	lastNodeID int64
+	lastType   string
+	lastData   interface{}
+	res        ws.CommandResult
+	err        error
+}
+
+type delayedCommander struct {
+	delayByMonitorID map[int64]time.Duration
+}
+
+func (d *delayedCommander) SendCommand(nodeID int64, cmdType string, data interface{}, _ time.Duration) (ws.CommandResult, error) {
+	_ = nodeID
+	_ = cmdType
+	if req, ok := data.(serviceMonitorCheckRequest); ok {
+		if delay := d.delayByMonitorID[req.MonitorID]; delay > 0 {
+			time.Sleep(delay)
+		}
+	}
+	return ws.CommandResult{
+		Success: true,
+		Data: map[string]interface{}{
+			"success":   true,
+			"latencyMs": float64(1),
+		},
+	}, nil
+}
+
+func (f *fakeCommander) SendCommand(nodeID int64, cmdType string, data interface{}, _ time.Duration) (ws.CommandResult, error) {
+	f.lastNodeID = nodeID
+	f.lastType = cmdType
+	f.lastData = data
+	return f.res, f.err
+}
+
+func TestTCPHealthCheckViaMonitor(t *testing.T) {
+	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+	defer listener.Close()
+	addr := listener.Addr().String()
+
+	go func() {
+		for {
+			conn, err := listener.Accept()
+			if err != nil {
+				return
+			}
+			conn.Close()
+		}
+	}()
+
+	t.Run("successful tcp check", func(t *testing.T) {
+		checker := NewChecker(nil, nil)
+		limits := checker.loadServiceMonitorLimits()
+		now := time.Now().UnixMilli()
+		monitor := &model.ServiceMonitor{
+			Type:       "tcp",
+			Target:     addr,
+			TimeoutSec: 5,
+		}
+		result := checker.executeCheck(monitor, now, limits)
+		if result.Success != 1 {
+			t.Fatalf("expected success, got error: %s", result.ErrorMessage)
+		}
+		if result.LatencyMs < 0 {
+			t.Fatalf("expected non-negative latency, got %f", result.LatencyMs)
+		}
+	})
+
+	t.Run("failed tcp check - connection refused", func(t *testing.T) {
+		checker := NewChecker(nil, nil)
+		limits := checker.loadServiceMonitorLimits()
+		now := time.Now().UnixMilli()
+		monitor := &model.ServiceMonitor{
+			Type:       "tcp",
+			Target:     "127.0.0.1:1",
+			TimeoutSec: 1,
+		}
+		result := checker.executeCheck(monitor, now, limits)
+		if result.Success == 1 {
+			t.Fatalf("expected failure for connection refused")
+		}
+		if result.ErrorMessage == "" {
+			t.Fatalf("expected error message")
+		}
+	})
+}
+
+func TestCheckerRunChecks(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+	defer listener.Close()
+	tcpAddr := listener.Addr().String()
+
+	go func() {
+		for {
+			conn, err := listener.Accept()
+			if err != nil {
+				return
+			}
+			conn.Close()
+		}
+	}()
+
+	now := time.Now().UnixMilli()
+
+	monitors := []*model.ServiceMonitor{
+		{
+			Name:        "TCP Monitor",
+			Type:        "tcp",
+			Target:      tcpAddr,
+			IntervalSec: 60,
+			TimeoutSec:  5,
+			NodeID:      0,
+			Enabled:     1,
+			CreatedTime: now,
+			UpdatedTime: now,
+		},
+		{
+			Name:        "TCP Monitor 2",
+			Type:        "tcp",
+			Target:      tcpAddr,
+			IntervalSec: 60,
+			TimeoutSec:  5,
+			NodeID:      0,
+			Enabled:     1,
+			CreatedTime: now,
+			UpdatedTime: now,
+		},
+		{
+			Name:        "Disabled Monitor",
+			Type:        "tcp",
+			Target:      "127.0.0.1:1",
+			IntervalSec: 60,
+			TimeoutSec:  5,
+			NodeID:      0,
+			Enabled:     0,
+			CreatedTime: now,
+			UpdatedTime: now,
+		},
+	}
+
+	for _, m := range monitors {
+		if err := r.CreateServiceMonitor(m); err != nil {
+			t.Fatalf("create monitor: %v", err)
+		}
+	}
+
+	monitors[2].Enabled = 0
+	if err := r.UpdateServiceMonitor(monitors[2]); err != nil {
+		t.Fatalf("update disabled monitor: %v", err)
+	}
+
+	enabledMonitors, err := r.ListEnabledServiceMonitors()
+	if err != nil {
+		t.Fatalf("list enabled monitors: %v", err)
+	}
+	if len(enabledMonitors) != 2 {
+		t.Fatalf("expected 2 enabled monitors, got %d", len(enabledMonitors))
+	}
+
+	checker := NewChecker(r, nil)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+	defer cancel()
+
+	go checker.Start(ctx)
+	time.Sleep(500 * time.Millisecond)
+
+	results, err := r.GetServiceMonitorResults(monitors[0].ID, 10)
+	if err != nil {
+		t.Fatalf("get tcp results: %v", err)
+	}
+	if len(results) == 0 {
+		t.Fatalf("expected at least one result for tcp monitor")
+	}
+	for _, res := range results {
+		if res.Success != 1 {
+			t.Fatalf("expected success for tcp monitor, got failure: %s", res.ErrorMessage)
+		}
+	}
+
+	results2, err := r.GetServiceMonitorResults(monitors[1].ID, 10)
+	if err != nil {
+		t.Fatalf("get tcp results 2: %v", err)
+	}
+	if len(results2) == 0 {
+		t.Fatalf("expected at least one result for tcp monitor 2")
+	}
+	for _, res := range results2 {
+		if res.Success != 1 {
+			t.Fatalf("expected success for tcp monitor 2, got failure: %s", res.ErrorMessage)
+		}
+	}
+
+	disabledResults, err := r.GetServiceMonitorResults(monitors[2].ID, 10)
+	if err != nil {
+		t.Fatalf("get disabled results: %v", err)
+	}
+	if len(disabledResults) != 0 {
+		t.Fatalf("expected no results for disabled monitor, got %d", len(disabledResults))
+	}
+}
+
+func TestCheckerUnsupportedType(t *testing.T) {
+	checker := NewChecker(nil, nil)
+	limits := checker.loadServiceMonitorLimits()
+	now := time.Now().UnixMilli()
+	monitor := &model.ServiceMonitor{
+		Type:       "http",
+		Target:     "https://example.com",
+		TimeoutSec: 5,
+	}
+	result := checker.executeCheck(monitor, now, limits)
+	if result.Success == 1 {
+		t.Fatalf("expected failure for unsupported type")
+	}
+	if result.ErrorMessage == "" {
+		t.Fatalf("expected error message for unsupported type")
+	}
+}
+
+func TestCheckerDefaultTimeout(t *testing.T) {
+	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+	defer listener.Close()
+	addr := listener.Addr().String()
+
+	go func() {
+		for {
+			conn, err := listener.Accept()
+			if err != nil {
+				return
+			}
+			conn.Close()
+		}
+	}()
+
+	checker := NewChecker(nil, nil)
+	limits := checker.loadServiceMonitorLimits()
+	now := time.Now().UnixMilli()
+	monitor := &model.ServiceMonitor{
+		Type:       "tcp",
+		Target:     addr,
+		TimeoutSec: 0,
+	}
+	result := checker.executeCheck(monitor, now, limits)
+	if result.Success != 1 {
+		t.Fatalf("expected success with default timeout, got error: %s", result.ErrorMessage)
+	}
+}
+
+func TestCheckerStop(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+	defer listener.Close()
+
+	go func() {
+		for {
+			conn, err := listener.Accept()
+			if err != nil {
+				return
+			}
+			conn.Close()
+		}
+	}()
+
+	now := time.Now().UnixMilli()
+	monitor := &model.ServiceMonitor{
+		Name:        "Test Monitor",
+		Type:        "tcp",
+		Target:      listener.Addr().String(),
+		IntervalSec: 60,
+		TimeoutSec:  5,
+		NodeID:      0,
+		Enabled:     1,
+		CreatedTime: now,
+		UpdatedTime: now,
+	}
+	if err := r.CreateServiceMonitor(monitor); err != nil {
+		t.Fatalf("create monitor: %v", err)
+	}
+
+	checker := NewChecker(r, nil)
+
+	ctx := context.Background()
+	go checker.Start(ctx)
+
+	time.Sleep(100 * time.Millisecond)
+	checker.Stop()
+
+	results, err := r.GetServiceMonitorResults(monitor.ID, 10)
+	if err != nil {
+		t.Fatalf("get results: %v", err)
+	}
+	if len(results) == 0 {
+		t.Fatalf("expected at least one result before stop")
+	}
+}
+
+func TestCheckerRunsOnNodeWhenNodeIDSet(t *testing.T) {
+	fake := &fakeCommander{
+		res: ws.CommandResult{
+			Success: true,
+			Data: map[string]interface{}{
+				"success":      false,
+				"latencyMs":    float64(12),
+				"errorMessage": "unreachable",
+			},
+		},
+	}
+	checker := NewChecker(nil, fake)
+	limits := checker.loadServiceMonitorLimits()
+	now := time.Now().UnixMilli()
+	monitor := &model.ServiceMonitor{
+		ID:         99,
+		Type:       "icmp",
+		Target:     "8.8.8.8",
+		TimeoutSec: 2,
+		NodeID:     123,
+	}
+	res := checker.executeCheck(monitor, now, limits)
+	if fake.lastNodeID != 123 {
+		t.Fatalf("expected command to be sent to node 123, got %d", fake.lastNodeID)
+	}
+	if fake.lastType != "ServiceMonitorCheck" {
+		t.Fatalf("expected ServiceMonitorCheck command, got %s", fake.lastType)
+	}
+	if res.Success != 0 {
+		t.Fatalf("expected failed result from node check")
+	}
+	if res.ErrorMessage != "unreachable" {
+		t.Fatalf("expected errorMessage unreachable, got %q", res.ErrorMessage)
+	}
+}
+
+func TestCheckerDoesNotBurstOnRestartWhenRecentResultsExist(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	now := time.Now().UnixMilli()
+	monitor := &model.ServiceMonitor{
+		Name:        "recent-monitor",
+		Type:        "tcp",
+		Target:      "127.0.0.1:1",
+		IntervalSec: 60,
+		TimeoutSec:  1,
+		NodeID:      0,
+		Enabled:     1,
+		CreatedTime: now,
+		UpdatedTime: now,
+	}
+	if err := r.CreateServiceMonitor(monitor); err != nil {
+		t.Fatalf("create monitor: %v", err)
+	}
+	if err := r.InsertServiceMonitorResult(&model.ServiceMonitorResult{
+		MonitorID: monitor.ID,
+		NodeID:    0,
+		Timestamp: now - 10_000,
+		Success:   1,
+	}); err != nil {
+		t.Fatalf("seed recent result: %v", err)
+	}
+
+	checker := NewChecker(r, nil)
+	ctx, cancel := context.WithCancel(context.Background())
+	go checker.Start(ctx)
+	// Give the initial scan a chance to run.
+	time.Sleep(200 * time.Millisecond)
+	cancel()
+	checker.Stop()
+
+	results, err := r.GetServiceMonitorResults(monitor.ID, 10)
+	if err != nil {
+		t.Fatalf("get results: %v", err)
+	}
+	if len(results) != 1 {
+		t.Fatalf("expected no immediate rerun (1 result), got %d", len(results))
+	}
+}
+
+func TestCheckerConcurrencyPreventsSlowMonitorBlockingOthers(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	now := time.Now().UnixMilli()
+	// Force worker limit to at least 2 for this test.
+	_ = r.UpsertConfig(monitoring.ConfigServiceMonitorWorkerLimit, "2", now)
+
+	slow := &model.ServiceMonitor{
+		Name:        "slow",
+		Type:        "icmp",
+		Target:      "8.8.8.8",
+		IntervalSec: 60,
+		TimeoutSec:  1,
+		NodeID:      123,
+		Enabled:     1,
+		CreatedTime: now,
+		UpdatedTime: now,
+	}
+	if err := r.CreateServiceMonitor(slow); err != nil {
+		t.Fatalf("create slow monitor: %v", err)
+	}
+	fast := &model.ServiceMonitor{
+		Name:        "fast",
+		Type:        "icmp",
+		Target:      "1.1.1.1",
+		IntervalSec: 60,
+		TimeoutSec:  1,
+		NodeID:      123,
+		Enabled:     1,
+		CreatedTime: now,
+		UpdatedTime: now,
+	}
+	if err := r.CreateServiceMonitor(fast); err != nil {
+		t.Fatalf("create fast monitor: %v", err)
+	}
+
+	cmd := &delayedCommander{delayByMonitorID: map[int64]time.Duration{slow.ID: 800 * time.Millisecond}}
+	checker := NewChecker(r, cmd)
+	ctx, cancel := context.WithCancel(context.Background())
+	go checker.Start(ctx)
+
+	// Fast monitor should complete even while slow one is still running.
+	time.Sleep(250 * time.Millisecond)
+	results, err := r.GetServiceMonitorResults(fast.ID, 10)
+	if err != nil {
+		t.Fatalf("get fast results: %v", err)
+	}
+	if len(results) == 0 {
+		t.Fatalf("expected fast monitor to have results without waiting for slow")
+	}
+
+	cancel()
+	checker.Stop()
+}

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
 }
 
@@ -200,6 +225,23 @@ 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)
@@ -728,6 +770,8 @@ 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

@@ -832,7 +832,7 @@ func (h *Handler) tunnelUpdate(w http.ResponseWriter, r *http.Request) {
 			newEntryNodeIDs = append(newEntryNodeIDs, in.NodeID)
 		}
 	}
-	if err := h.validateTunnelEntryPortConflictsForNewEntries(tx, id, oldEntryNodeIDs, newEntryNodeIDs); err != nil {
+	if err := h.validateTunnelEntryPortConflictsForNewEntriesTx(tx, id, oldEntryNodeIDs, newEntryNodeIDs); err != nil {
 		response.WriteJSON(w, response.ErrDefault(err.Error()))
 		return
 	}
@@ -1020,7 +1020,21 @@ func (h *Handler) cleanupTunnelForwardRuntimesOnRemovedEntryNodes(tunnelID int64
 	}
 }
 
-func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tx *gorm.DB, tunnelID int64, oldEntryNodeIDs, newEntryNodeIDs []int64) error {
+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
 	}
@@ -1054,9 +1068,7 @@ func (h *Handler) validateTunnelEntryPortConflictsForNewEntries(tx *gorm.DB, tun
 			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.validateForwardPortAvailabilityTx(tx, node, port, f.ID); err != nil {
 				return fmt.Errorf("转发 %s 入口端口冲突: %w", f.Name, err)
 			}
@@ -4153,20 +4165,6 @@ func (h *Handler) validateForwardPortAvailability(node *nodeRecord, port int, cu
 	return nil
 }
 
-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 parsePortRangeMinMax(input string) (int, int) {
 	input = strings.TrimSpace(input)
 	if input == "" {

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

@@ -83,7 +83,7 @@ func TestValidateTunnelEntryPortConflictsForNewEntriesDoesNotBlockOnSQLiteTx(t *
 	doneCh := make(chan struct{})
 	go func() {
 		defer close(doneCh)
-		errCh <- h.validateTunnelEntryPortConflictsForNewEntries(tx, tunnelID, []int64{oldEntryID}, []int64{oldEntryID, newEntryID})
+		errCh <- h.validateTunnelEntryPortConflictsForNewEntriesTx(tx, tunnelID, []int64{oldEntryID}, []int64{oldEntryID, newEntryID})
 	}()
 
 	select {

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
 	}

go-backend/internal/metrics/ingestion.go

@@ -0,0 +1,135 @@
+package metrics
+
+import (
+	"context"
+	"log"
+	"sync"
+	"time"
+
+	"go-backend/internal/store/model"
+	"go-backend/internal/store/repo"
+)
+
+type SystemInfo struct {
+	Uptime           uint64  `json:"uptime"`
+	BytesReceived    uint64  `json:"bytes_received"`
+	BytesTransmitted uint64  `json:"bytes_transmitted"`
+	CPUUsage         float64 `json:"cpu_usage"`
+	MemoryUsage      float64 `json:"memory_usage"`
+	DiskUsage        float64 `json:"disk_usage"`
+	Load1            float64 `json:"load1"`
+	Load5            float64 `json:"load5"`
+	Load15           float64 `json:"load15"`
+	TCPConns         int64   `json:"tcp_conns"`
+	UDPConns         int64   `json:"udp_conns"`
+	NetInSpeed       int64   `json:"net_in_speed"`
+	NetOutSpeed      int64   `json:"net_out_speed"`
+}
+
+type IngestionService struct {
+	repo          *repo.Repository
+	nodeBuffer    []*model.NodeMetric
+	nodeBufferMu  sync.Mutex
+	flushInterval time.Duration
+	retentionDays int
+}
+
+func NewIngestionService(repo *repo.Repository) *IngestionService {
+	return &IngestionService{
+		repo:          repo,
+		nodeBuffer:    make([]*model.NodeMetric, 0, 500),
+		flushInterval: 30 * time.Second,
+		retentionDays: 7,
+	}
+}
+
+func (s *IngestionService) Start(ctx context.Context) {
+	flushTicker := time.NewTicker(s.flushInterval)
+	defer flushTicker.Stop()
+
+	pruneTicker := time.NewTicker(1 * time.Hour)
+	defer pruneTicker.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			s.flushNodeMetrics()
+			return
+		case <-flushTicker.C:
+			s.flushNodeMetrics()
+		case <-pruneTicker.C:
+			s.pruneMetrics()
+		}
+	}
+}
+
+func (s *IngestionService) RecordNodeMetric(nodeID int64, info SystemInfo) {
+	m := &model.NodeMetric{
+		NodeID:      nodeID,
+		Timestamp:   time.Now().UnixMilli(),
+		CPUUsage:    info.CPUUsage,
+		MemUsage:    info.MemoryUsage,
+		DiskUsage:   info.DiskUsage,
+		NetInBytes:  int64(info.BytesReceived),
+		NetOutBytes: int64(info.BytesTransmitted),
+		NetInSpeed:  info.NetInSpeed,
+		NetOutSpeed: info.NetOutSpeed,
+		Load1:       info.Load1,
+		Load5:       info.Load5,
+		Load15:      info.Load15,
+		TCPConns:    info.TCPConns,
+		UDPConns:    info.UDPConns,
+		Uptime:      int64(info.Uptime),
+	}
+
+	s.nodeBufferMu.Lock()
+	s.nodeBuffer = append(s.nodeBuffer, m)
+	shouldFlush := len(s.nodeBuffer) >= 200
+	s.nodeBufferMu.Unlock()
+
+	if shouldFlush {
+		go s.flushNodeMetrics()
+	}
+}
+
+func (s *IngestionService) flushNodeMetrics() {
+	s.nodeBufferMu.Lock()
+	if len(s.nodeBuffer) == 0 {
+		s.nodeBufferMu.Unlock()
+		return
+	}
+	buffer := s.nodeBuffer
+	s.nodeBuffer = make([]*model.NodeMetric, 0, 500)
+	s.nodeBufferMu.Unlock()
+
+	if s.repo == nil {
+		return
+	}
+	if err := s.repo.InsertNodeMetricBatch(buffer); err != nil {
+		log.Printf("monitoring write failed op=node_metric.flush count=%d err=%v", len(buffer), err)
+	}
+}
+
+func (s *IngestionService) pruneMetrics() {
+	cutoff := time.Now().Add(-time.Duration(s.retentionDays) * 24 * time.Hour).UnixMilli()
+	if s.repo == nil {
+		return
+	}
+	if err := s.repo.PruneNodeMetrics(cutoff); err != nil {
+		log.Printf("monitoring prune failed op=node_metric cutoff=%d err=%v", cutoff, err)
+	}
+	if err := s.repo.PruneTunnelMetrics(cutoff); err != nil {
+		log.Printf("monitoring prune failed op=tunnel_metric cutoff=%d err=%v", cutoff, err)
+	}
+	if err := s.repo.PruneServiceMonitorResults(cutoff); err != nil {
+		log.Printf("monitoring prune failed op=service_monitor_result cutoff=%d err=%v", cutoff, err)
+	}
+}
+
+func (s *IngestionService) GetLatestMetric(nodeID int64) (*model.NodeMetric, error) {
+	return s.repo.GetLatestNodeMetric(nodeID)
+}
+
+func (s *IngestionService) GetMetrics(nodeID int64, startMs, endMs int64) ([]model.NodeMetric, error) {
+	return s.repo.GetNodeMetrics(nodeID, startMs, endMs)
+}

go-backend/internal/metrics/ingestion_test.go

@@ -0,0 +1,294 @@
+package metrics
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"go-backend/internal/store/repo"
+)
+
+func TestRecordNodeMetric(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	info := SystemInfo{
+		Uptime:           86400,
+		BytesReceived:    1024000,
+		BytesTransmitted: 2048000,
+		CPUUsage:         45.5,
+		MemoryUsage:      60.2,
+		DiskUsage:        30.1,
+		Load1:            1.5,
+		Load5:            1.2,
+		Load15:           0.9,
+		TCPConns:         100,
+		UDPConns:         50,
+		NetInSpeed:       51200,
+		NetOutSpeed:      102400,
+	}
+
+	svc.RecordNodeMetric(1, info)
+	svc.flushNodeMetrics()
+
+	metrics, err := r.GetNodeMetrics(1, 0, time.Now().UnixMilli()+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) != 1 {
+		t.Fatalf("expected 1 metric, got %d", len(metrics))
+	}
+
+	m := metrics[0]
+	if m.CPUUsage != 45.5 {
+		t.Fatalf("expected CPUUsage 45.5, got %f", m.CPUUsage)
+	}
+	if m.MemUsage != 60.2 {
+		t.Fatalf("expected MemUsage 60.2, got %f", m.MemUsage)
+	}
+	if m.DiskUsage != 30.1 {
+		t.Fatalf("expected DiskUsage 30.1, got %f", m.DiskUsage)
+	}
+	if m.Load1 != 1.5 {
+		t.Fatalf("expected Load1 1.5, got %f", m.Load1)
+	}
+	if m.TCPConns != 100 {
+		t.Fatalf("expected TCPConns 100, got %d", m.TCPConns)
+	}
+	if m.UDPConns != 50 {
+		t.Fatalf("expected UDPConns 50, got %d", m.UDPConns)
+	}
+}
+
+func TestRecordNodeMetricAutoFlush(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	info := SystemInfo{
+		CPUUsage:    50.0,
+		MemoryUsage: 60.0,
+		DiskUsage:   30.0,
+	}
+
+	for i := 0; i < 250; i++ {
+		svc.RecordNodeMetric(1, info)
+	}
+
+	time.Sleep(100 * time.Millisecond)
+
+	metrics, err := r.GetNodeMetrics(1, 0, time.Now().UnixMilli()+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) < 200 {
+		t.Fatalf("expected at least 200 metrics after auto-flush, got %d", len(metrics))
+	}
+}
+
+func TestIngestionServiceStart(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+	svc.flushInterval = 100 * time.Millisecond
+
+	ctx, cancel := context.WithTimeout(context.Background(), 500*time.Millisecond)
+	defer cancel()
+
+	info := SystemInfo{
+		CPUUsage:    45.0,
+		MemoryUsage: 55.0,
+		DiskUsage:   35.0,
+	}
+
+	go svc.Start(ctx)
+
+	for i := 0; i < 10; i++ {
+		svc.RecordNodeMetric(1, info)
+		time.Sleep(50 * time.Millisecond)
+	}
+
+	<-ctx.Done()
+
+	metrics, err := r.GetNodeMetrics(1, 0, time.Now().UnixMilli()+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) == 0 {
+		t.Fatalf("expected metrics after service run")
+	}
+}
+
+func TestGetLatestMetric(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	now := time.Now().UnixMilli()
+
+	info1 := SystemInfo{CPUUsage: 40.0, MemoryUsage: 50.0, DiskUsage: 30.0}
+	svc.RecordNodeMetric(1, info1)
+
+	time.Sleep(5 * time.Millisecond)
+
+	info2 := SystemInfo{CPUUsage: 60.0, MemoryUsage: 70.0, DiskUsage: 40.0}
+	svc.RecordNodeMetric(1, info2)
+
+	svc.flushNodeMetrics()
+
+	latest, err := svc.GetLatestMetric(1)
+	if err != nil {
+		t.Fatalf("get latest: %v", err)
+	}
+	if latest == nil {
+		t.Fatalf("expected latest metric")
+	}
+	if latest.CPUUsage != 60.0 {
+		t.Fatalf("expected latest CPUUsage 60.0, got %f", latest.CPUUsage)
+	}
+
+	_ = now
+
+	latestNone, err := svc.GetLatestMetric(999)
+	if err != nil {
+		t.Fatalf("get latest for non-existent: %v", err)
+	}
+	if latestNone != nil {
+		t.Fatalf("expected nil for non-existent node")
+	}
+}
+
+func TestGetMetricsWithTimeRange(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	now := time.Now().UnixMilli()
+
+	for i := 0; i < 5; i++ {
+		info := SystemInfo{
+			CPUUsage:    float64(40 + i*5),
+			MemoryUsage: 50.0,
+			DiskUsage:   30.0,
+		}
+		svc.RecordNodeMetric(1, info)
+		time.Sleep(10 * time.Millisecond)
+	}
+
+	svc.flushNodeMetrics()
+
+	metrics, err := svc.GetMetrics(1, 0, now+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) != 5 {
+		t.Fatalf("expected 5 metrics, got %d", len(metrics))
+	}
+}
+
+func TestPruneMetrics(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+	svc.retentionDays = 1
+
+	info := SystemInfo{CPUUsage: 50.0, MemoryUsage: 60.0, DiskUsage: 30.0}
+
+	svc.RecordNodeMetric(1, info)
+	svc.flushNodeMetrics()
+
+	svc.pruneMetrics()
+
+	metrics, err := r.GetNodeMetrics(1, 0, time.Now().UnixMilli()+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) != 1 {
+		t.Fatalf("expected 1 metric (not pruned), got %d", len(metrics))
+	}
+}
+
+func TestMultipleNodes(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	info := SystemInfo{
+		CPUUsage:    50.0,
+		MemoryUsage: 60.0,
+		DiskUsage:   30.0,
+	}
+
+	svc.RecordNodeMetric(1, info)
+	svc.RecordNodeMetric(2, info)
+	svc.RecordNodeMetric(3, info)
+
+	svc.flushNodeMetrics()
+
+	for nodeID := int64(1); nodeID <= 3; nodeID++ {
+		metrics, err := r.GetNodeMetrics(nodeID, 0, time.Now().UnixMilli()+1000)
+		if err != nil {
+			t.Fatalf("get metrics for node %d: %v", nodeID, err)
+		}
+		if len(metrics) != 1 {
+			t.Fatalf("expected 1 metric for node %d, got %d", nodeID, len(metrics))
+		}
+	}
+}
+
+func TestZeroValues(t *testing.T) {
+	r, err := repo.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	svc := NewIngestionService(r)
+
+	info := SystemInfo{}
+
+	svc.RecordNodeMetric(1, info)
+	svc.flushNodeMetrics()
+
+	metrics, err := r.GetNodeMetrics(1, 0, time.Now().UnixMilli()+1000)
+	if err != nil {
+		t.Fatalf("get metrics: %v", err)
+	}
+	if len(metrics) != 1 {
+		t.Fatalf("expected 1 metric, got %d", len(metrics))
+	}
+
+	m := metrics[0]
+	if m.CPUUsage != 0 || m.MemUsage != 0 || m.DiskUsage != 0 {
+		t.Fatalf("expected zero values, got CPU=%f Mem=%f Disk=%f", m.CPUUsage, m.MemUsage, m.DiskUsage)
+	}
+}

go-backend/internal/monitoring/limits.go

@@ -0,0 +1,114 @@
+package monitoring
+
+import (
+	"strconv"
+	"strings"
+)
+
+type ServiceMonitorLimits struct {
+	CheckerScanIntervalSec int `json:"checkerScanIntervalSec"`
+	WorkerLimit            int `json:"workerLimit"`
+
+	MinIntervalSec     int `json:"minIntervalSec"`
+	DefaultIntervalSec int `json:"defaultIntervalSec"`
+
+	MinTimeoutSec     int `json:"minTimeoutSec"`
+	DefaultTimeoutSec int `json:"defaultTimeoutSec"`
+	MaxTimeoutSec     int `json:"maxTimeoutSec"`
+}
+
+const (
+	ConfigServiceMonitorCheckerScanIntervalSec = "service_monitor_checker_scan_interval_sec"
+	ConfigServiceMonitorWorkerLimit            = "service_monitor_worker_limit"
+	ConfigServiceMonitorMinIntervalSec         = "service_monitor_min_interval_sec"
+	ConfigServiceMonitorDefaultIntervalSec     = "service_monitor_default_interval_sec"
+	ConfigServiceMonitorMinTimeoutSec          = "service_monitor_min_timeout_sec"
+	ConfigServiceMonitorDefaultTimeoutSec      = "service_monitor_default_timeout_sec"
+	ConfigServiceMonitorMaxTimeoutSec          = "service_monitor_max_timeout_sec"
+)
+
+func DefaultServiceMonitorLimits() ServiceMonitorLimits {
+	return ServiceMonitorLimits{
+		CheckerScanIntervalSec: 30,
+		WorkerLimit:            5,
+		MinIntervalSec:         30,
+		DefaultIntervalSec:     60,
+		MinTimeoutSec:          1,
+		DefaultTimeoutSec:      5,
+		MaxTimeoutSec:          60,
+	}
+}
+
+// ServiceMonitorLimitsFromConfigMap parses limits from vite_config values.
+// Missing/invalid values fall back to defaults.
+func ServiceMonitorLimitsFromConfigMap(cfg map[string]string) ServiceMonitorLimits {
+	limits := DefaultServiceMonitorLimits()
+	if cfg == nil {
+		return limits
+	}
+
+	limits.CheckerScanIntervalSec = parseConfigInt(cfg, ConfigServiceMonitorCheckerScanIntervalSec, limits.CheckerScanIntervalSec)
+	limits.WorkerLimit = parseConfigInt(cfg, ConfigServiceMonitorWorkerLimit, limits.WorkerLimit)
+	limits.MinIntervalSec = parseConfigInt(cfg, ConfigServiceMonitorMinIntervalSec, limits.MinIntervalSec)
+	limits.DefaultIntervalSec = parseConfigInt(cfg, ConfigServiceMonitorDefaultIntervalSec, limits.DefaultIntervalSec)
+	limits.MinTimeoutSec = parseConfigInt(cfg, ConfigServiceMonitorMinTimeoutSec, limits.MinTimeoutSec)
+	limits.DefaultTimeoutSec = parseConfigInt(cfg, ConfigServiceMonitorDefaultTimeoutSec, limits.DefaultTimeoutSec)
+	limits.MaxTimeoutSec = parseConfigInt(cfg, ConfigServiceMonitorMaxTimeoutSec, limits.MaxTimeoutSec)
+
+	return normalizeServiceMonitorLimits(limits)
+}
+
+func normalizeServiceMonitorLimits(limits ServiceMonitorLimits) ServiceMonitorLimits {
+	if limits.CheckerScanIntervalSec <= 0 {
+		limits.CheckerScanIntervalSec = 30
+	}
+	if limits.WorkerLimit <= 0 {
+		limits.WorkerLimit = 5
+	}
+	if limits.WorkerLimit > 50 {
+		limits.WorkerLimit = 50
+	}
+
+	if limits.MinIntervalSec <= 0 {
+		limits.MinIntervalSec = limits.CheckerScanIntervalSec
+	}
+	if limits.MinIntervalSec < limits.CheckerScanIntervalSec {
+		limits.MinIntervalSec = limits.CheckerScanIntervalSec
+	}
+	if limits.DefaultIntervalSec <= 0 {
+		limits.DefaultIntervalSec = 60
+	}
+	if limits.DefaultIntervalSec < limits.MinIntervalSec {
+		limits.DefaultIntervalSec = limits.MinIntervalSec
+	}
+
+	if limits.MinTimeoutSec <= 0 {
+		limits.MinTimeoutSec = 1
+	}
+	if limits.DefaultTimeoutSec <= 0 {
+		limits.DefaultTimeoutSec = 5
+	}
+	if limits.DefaultTimeoutSec < limits.MinTimeoutSec {
+		limits.DefaultTimeoutSec = limits.MinTimeoutSec
+	}
+	if limits.MaxTimeoutSec <= 0 {
+		limits.MaxTimeoutSec = 60
+	}
+	if limits.MaxTimeoutSec < limits.DefaultTimeoutSec {
+		limits.MaxTimeoutSec = limits.DefaultTimeoutSec
+	}
+
+	return limits
+}
+
+func parseConfigInt(cfg map[string]string, key string, fallback int) int {
+	v := strings.TrimSpace(cfg[key])
+	if v == "" {
+		return fallback
+	}
+	n, err := strconv.Atoi(v)
+	if err != nil {
+		return fallback
+	}
+	return n
+}

go-backend/internal/store/model/model.go

@@ -235,6 +235,16 @@ type GroupPermissionGrant struct {
 
 func (GroupPermissionGrant) TableName() string { return "group_permission_grant" }
 
+// MonitorPermission grants a non-admin user access to monitoring endpoints.
+// One row per user_id.
+type MonitorPermission struct {
+	ID          int64 `gorm:"primaryKey;autoIncrement" json:"id"`
+	UserID      int64 `gorm:"column:user_id;not null;uniqueIndex:idx_monitor_permission_user" json:"userId"`
+	CreatedTime int64 `gorm:"column:created_time;not null" json:"createdTime"`
+}
+
+func (MonitorPermission) TableName() string { return "monitor_permission" }
+
 type ViteConfig struct {
 	ID    int64  `gorm:"primaryKey;autoIncrement" json:"id"`
 	Name  string `gorm:"type:varchar(200);not null;uniqueIndex" json:"name"`
@@ -641,3 +651,66 @@ type UserForwardDetail struct {
 	Status     int
 	CreatedAt  int64
 }
+
+type NodeMetric struct {
+	ID          int64   `gorm:"primaryKey;autoIncrement" json:"id"`
+	NodeID      int64   `gorm:"column:node_id;not null;index:idx_node_metric_node_time,priority:1" json:"nodeId"`
+	Timestamp   int64   `gorm:"not null;index:idx_node_metric_node_time,priority:2;index:idx_node_metric_time" json:"timestamp"`
+	CPUUsage    float64 `gorm:"column:cpu_usage" json:"cpuUsage"`
+	MemUsage    float64 `gorm:"column:mem_usage" json:"memoryUsage"`
+	DiskUsage   float64 `gorm:"column:disk_usage" json:"diskUsage"`
+	NetInBytes  int64   `gorm:"column:net_in_bytes" json:"netInBytes"`
+	NetOutBytes int64   `gorm:"column:net_out_bytes" json:"netOutBytes"`
+	NetInSpeed  int64   `gorm:"column:net_in_speed" json:"netInSpeed"`
+	NetOutSpeed int64   `gorm:"column:net_out_speed" json:"netOutSpeed"`
+	Load1       float64 `gorm:"column:load1" json:"load1"`
+	Load5       float64 `gorm:"column:load5" json:"load5"`
+	Load15      float64 `gorm:"column:load15" json:"load15"`
+	TCPConns    int64   `gorm:"column:tcp_conns" json:"tcpConns"`
+	UDPConns    int64   `gorm:"column:udp_conns" json:"udpConns"`
+	Uptime      int64   `gorm:"column:uptime" json:"uptime"`
+}
+
+func (NodeMetric) TableName() string { return "node_metric" }
+
+type TunnelMetric struct {
+	ID           int64   `gorm:"primaryKey;autoIncrement" json:"id"`
+	TunnelID     int64   `gorm:"column:tunnel_id;not null;index:idx_tunnel_metric_tunnel_time,priority:1" json:"tunnelId"`
+	NodeID       int64   `gorm:"column:node_id;not null;index:idx_tunnel_metric_tunnel_time,priority:2" json:"nodeId"`
+	Timestamp    int64   `gorm:"not null;index:idx_tunnel_metric_tunnel_time,priority:3;index:idx_tunnel_metric_time" json:"timestamp"`
+	BytesIn      int64   `gorm:"column:bytes_in" json:"bytesIn"`
+	BytesOut     int64   `gorm:"column:bytes_out" json:"bytesOut"`
+	Connections  int64   `gorm:"column:connections" json:"connections"`
+	Errors       int64   `gorm:"column:errors" json:"errors"`
+	AvgLatencyMs float64 `gorm:"column:avg_latency_ms" json:"avgLatencyMs"`
+}
+
+func (TunnelMetric) TableName() string { return "tunnel_metric" }
+
+type ServiceMonitor struct {
+	ID          int64  `gorm:"primaryKey;autoIncrement" json:"id"`
+	Name        string `gorm:"type:varchar(100);not null" json:"name"`
+	Type        string `gorm:"type:varchar(20);not null" json:"type"`
+	Target      string `gorm:"type:text;not null" json:"target"`
+	IntervalSec int    `gorm:"column:interval_sec;not null;default:60" json:"intervalSec"`
+	TimeoutSec  int    `gorm:"column:timeout_sec;not null;default:5" json:"timeoutSec"`
+	NodeID      int64  `gorm:"column:node_id;index" json:"nodeId"`
+	Enabled     int    `gorm:"not null;default:1" json:"enabled"`
+	CreatedTime int64  `gorm:"column:created_time;not null" json:"createdTime"`
+	UpdatedTime int64  `gorm:"column:updated_time;not null" json:"updatedTime"`
+}
+
+func (ServiceMonitor) TableName() string { return "service_monitor" }
+
+type ServiceMonitorResult struct {
+	ID           int64   `gorm:"primaryKey;autoIncrement" json:"id"`
+	MonitorID    int64   `gorm:"column:monitor_id;not null;index:idx_monitor_result_monitor_time,priority:1" json:"monitorId"`
+	NodeID       int64   `gorm:"column:node_id;not null;index" json:"nodeId"`
+	Timestamp    int64   `gorm:"not null;index:idx_monitor_result_monitor_time,priority:2" json:"timestamp"`
+	Success      int     `gorm:"not null" json:"success"`
+	LatencyMs    float64 `gorm:"column:latency_ms" json:"latencyMs"`
+	StatusCode   int     `gorm:"column:status_code" json:"statusCode"`
+	ErrorMessage string  `gorm:"column:error_message;type:text" json:"errorMessage"`
+}
+
+func (ServiceMonitorResult) TableName() string { return "service_monitor_result" }

go-backend/internal/store/repo/repository.go

@@ -47,6 +47,10 @@ type UserGroupBackup = model.UserGroupBackup
 type PermissionBackup = model.PermissionBackup
 type PermissionGrantBackup = model.PermissionGrantBackup
 type ImportResult = model.ImportResult
+type NodeMetric = model.NodeMetric
+type TunnelMetric = model.TunnelMetric
+type ServiceMonitor = model.ServiceMonitor
+type ServiceMonitorResult = model.ServiceMonitorResult
 
 // ─── Repository ──────────────────────────────────────────────────────
 
@@ -176,12 +180,17 @@ func autoMigrateAll(db *gorm.DB) error {
 		&model.UserGroupUser{},
 		&model.GroupPermission{},
 		&model.GroupPermissionGrant{},
+		&model.MonitorPermission{},
 		&model.ViteConfig{},
 		&model.PeerShare{},
 		&model.PeerShareRuntime{},
 		&model.FederationTunnelBinding{},
 		&model.Announcement{},
 		&model.SchemaVersion{},
+		&model.NodeMetric{},
+		&model.TunnelMetric{},
+		&model.ServiceMonitor{},
+		&model.ServiceMonitorResult{},
 	}
 
 	if db.Dialector.Name() != "sqlite" {
@@ -394,6 +403,24 @@ func (r *Repository) ListConfigs() (map[string]string, error) {
 	return result, nil
 }
 
+func (r *Repository) GetConfigsByNames(names []string) (map[string]string, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	if len(names) == 0 {
+		return map[string]string{}, nil
+	}
+	var configs []model.ViteConfig
+	if err := r.db.Select("name", "value").Where("name IN ?", names).Find(&configs).Error; err != nil {
+		return nil, err
+	}
+	result := make(map[string]string, len(configs))
+	for _, c := range configs {
+		result[c.Name] = c.Value
+	}
+	return result, nil
+}
+
 func (r *Repository) UpsertConfig(name, value string, now int64) error {
 	if r == nil || r.db == nil {
 		return errors.New("repository not initialized")
@@ -2689,12 +2716,13 @@ func (r *Repository) GetUserTunnelByID(id int64) (*model.UserTunnel, error) {
 
 // ─── Migration ───────────────────────────────────────────────────────
 
-const currentSchemaVersion = 5
+const currentSchemaVersion = 6
 
 var ensurePostgresIDDefaultsFn = ensurePostgresIDDefaults
 var migrateViteConfigValueColumnTypeFn = migrateViteConfigValueColumnType
 var migrateSpeedLimitTunnelBindingFn = migrateSpeedLimitTunnelBinding
 var migratePostgresTrafficInt64ColumnsFn = migratePostgresTrafficInt64Columns
+var migrateTunnelMetricBucketUniqueIndexFn = migrateTunnelMetricBucketUniqueIndex
 
 func getSchemaVersion(db *gorm.DB) int {
 	var v model.SchemaVersion
@@ -2764,6 +2792,12 @@ func migrateSchema(db *gorm.DB) error {
 		}
 	}
 
+	if ver < 6 {
+		if err := migrateTunnelMetricBucketUniqueIndexFn(db); err != nil {
+			return err
+		}
+	}
+
 	setSchemaVersion(db, currentSchemaVersion)
 	return nil
 }
@@ -2867,6 +2901,130 @@ func migratePostgresTrafficInt64Columns(db *gorm.DB) error {
 	return nil
 }
 
+func migrateTunnelMetricBucketUniqueIndex(db *gorm.DB) error {
+	if db == nil {
+		return errors.New("nil db")
+	}
+
+	if !db.Migrator().HasTable(&model.TunnelMetric{}) {
+		return nil
+	}
+
+	return db.Transaction(func(tx *gorm.DB) error {
+		// Only do the heavier dedupe work when needed.
+		var dupGroups int64
+		q := `
+			SELECT COUNT(1) AS cnt
+			FROM (
+				SELECT 1
+				FROM tunnel_metric
+				GROUP BY tunnel_id, node_id, timestamp
+				HAVING COUNT(*) > 1
+			) t
+		`
+		if err := tx.Raw(q).Scan(&dupGroups).Error; err != nil {
+			return fmt.Errorf("inspect tunnel_metric duplicates: %w", err)
+		}
+
+		if dupGroups > 0 {
+			switch tx.Dialector.Name() {
+			case "postgres":
+				sql := `
+					WITH agg AS (
+						SELECT MIN(id) AS keep_id,
+						       tunnel_id,
+						       node_id,
+						       timestamp,
+						       SUM(bytes_in) AS bytes_in,
+						       SUM(bytes_out) AS bytes_out,
+						       SUM(connections) AS connections,
+						       SUM(errors) AS errors,
+						       AVG(avg_latency_ms) AS avg_latency_ms
+						FROM tunnel_metric
+						GROUP BY tunnel_id, node_id, timestamp
+						HAVING COUNT(*) > 1
+					), updated AS (
+						UPDATE tunnel_metric tm
+						SET bytes_in = agg.bytes_in,
+						    bytes_out = agg.bytes_out,
+						    connections = agg.connections,
+						    errors = agg.errors,
+						    avg_latency_ms = agg.avg_latency_ms
+						FROM agg
+						WHERE tm.id = agg.keep_id
+						RETURNING tm.id
+					)
+					DELETE FROM tunnel_metric tm
+					USING agg
+					WHERE tm.tunnel_id = agg.tunnel_id
+					  AND tm.node_id = agg.node_id
+					  AND tm.timestamp = agg.timestamp
+					  AND tm.id <> agg.keep_id
+				`
+				if err := tx.Exec(sql).Error; err != nil {
+					return fmt.Errorf("dedupe tunnel_metric buckets: %w", err)
+				}
+			default:
+				// SQLite (and other) path.
+				if err := tx.Exec(`DROP TABLE IF EXISTS tunnel_metric_dedupe`).Error; err != nil {
+					return fmt.Errorf("prepare tunnel_metric dedupe table: %w", err)
+				}
+				if err := tx.Exec(`
+					CREATE TEMP TABLE tunnel_metric_dedupe AS
+					SELECT MIN(id) AS keep_id,
+					       tunnel_id,
+					       node_id,
+					       timestamp,
+					       SUM(bytes_in) AS bytes_in,
+					       SUM(bytes_out) AS bytes_out,
+					       SUM(connections) AS connections,
+					       SUM(errors) AS errors,
+					       AVG(avg_latency_ms) AS avg_latency_ms
+					FROM tunnel_metric
+					GROUP BY tunnel_id, node_id, timestamp
+					HAVING COUNT(*) > 1
+				`).Error; err != nil {
+					return fmt.Errorf("build tunnel_metric dedupe table: %w", err)
+				}
+				if err := tx.Exec(`
+					UPDATE tunnel_metric
+					SET bytes_in = (SELECT bytes_in FROM tunnel_metric_dedupe d WHERE d.keep_id = tunnel_metric.id),
+					    bytes_out = (SELECT bytes_out FROM tunnel_metric_dedupe d WHERE d.keep_id = tunnel_metric.id),
+					    connections = (SELECT connections FROM tunnel_metric_dedupe d WHERE d.keep_id = tunnel_metric.id),
+					    errors = (SELECT errors FROM tunnel_metric_dedupe d WHERE d.keep_id = tunnel_metric.id),
+					    avg_latency_ms = (SELECT avg_latency_ms FROM tunnel_metric_dedupe d WHERE d.keep_id = tunnel_metric.id)
+					WHERE id IN (SELECT keep_id FROM tunnel_metric_dedupe)
+				`).Error; err != nil {
+					return fmt.Errorf("update tunnel_metric deduped rows: %w", err)
+				}
+				if err := tx.Exec(`
+					DELETE FROM tunnel_metric
+					WHERE id IN (
+						SELECT tm.id
+						FROM tunnel_metric tm
+						JOIN tunnel_metric_dedupe d
+						  ON tm.tunnel_id = d.tunnel_id
+						 AND tm.node_id = d.node_id
+						 AND tm.timestamp = d.timestamp
+						WHERE tm.id <> d.keep_id
+					)
+				`).Error; err != nil {
+					return fmt.Errorf("delete tunnel_metric duplicates: %w", err)
+				}
+				_ = tx.Exec(`DROP TABLE IF EXISTS tunnel_metric_dedupe`).Error
+			}
+		}
+
+		// Uniqueness is required for safe upsert on (tunnel_id, node_id, timestamp).
+		if err := tx.Exec(
+			`CREATE UNIQUE INDEX IF NOT EXISTS uidx_tunnel_metric_bucket ON tunnel_metric(tunnel_id, node_id, timestamp)`,
+		).Error; err != nil {
+			return fmt.Errorf("create tunnel_metric unique index: %w", err)
+		}
+		return nil
+	})
+}
+
 func alterPostgresColumnToBigIntIfNeeded(db *gorm.DB, tableName, columnName string) error {
 	if db == nil {
 		return errors.New("nil db")
@@ -3140,3 +3298,331 @@ var osMkdirAll = func(path string) error {
 
 // Suppress unused import warning for log
 var _ = log.Printf
+
+func (r *Repository) InsertNodeMetric(m *model.NodeMetric) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Create(m).Error
+}
+
+func (r *Repository) InsertNodeMetricBatch(metrics []*model.NodeMetric) error {
+	if r == nil || r.db == nil || len(metrics) == 0 {
+		return nil
+	}
+	return r.db.CreateInBatches(metrics, 100).Error
+}
+
+func (r *Repository) GetNodeMetrics(nodeID int64, startMs, endMs int64) ([]model.NodeMetric, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var metrics []model.NodeMetric
+	err := r.db.Where("node_id = ? AND timestamp >= ? AND timestamp <= ?", nodeID, startMs, endMs).
+		Order("timestamp DESC").
+		Limit(5000).
+		Find(&metrics).Error
+	if len(metrics) > 1 {
+		for i, j := 0, len(metrics)-1; i < j; i, j = i+1, j-1 {
+			metrics[i], metrics[j] = metrics[j], metrics[i]
+		}
+	}
+	return metrics, err
+}
+
+func (r *Repository) GetLatestNodeMetric(nodeID int64) (*model.NodeMetric, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var m model.NodeMetric
+	err := r.db.Where("node_id = ?", nodeID).Order("timestamp DESC").First(&m).Error
+	if err != nil {
+		if errors.Is(err, gorm.ErrRecordNotFound) {
+			return nil, nil
+		}
+		return nil, err
+	}
+	return &m, nil
+}
+
+func (r *Repository) PruneNodeMetrics(olderThanMs int64) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Where("timestamp < ?", olderThanMs).Delete(&model.NodeMetric{}).Error
+}
+
+func (r *Repository) InsertTunnelMetric(m *model.TunnelMetric) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Create(m).Error
+}
+
+func (r *Repository) InsertTunnelMetricBatch(metrics []*model.TunnelMetric) error {
+	if r == nil || r.db == nil || len(metrics) == 0 {
+		return nil
+	}
+	return r.db.CreateInBatches(metrics, 100).Error
+}
+
+// UpsertTunnelMetricBuckets adds the provided metric deltas into per-minute buckets.
+// Requires a unique index on (tunnel_id, node_id, timestamp) for safe upserts.
+func (r *Repository) UpsertTunnelMetricBuckets(metrics []*model.TunnelMetric) error {
+	if r == nil || r.db == nil || len(metrics) == 0 {
+		return nil
+	}
+
+	// Postgres rejects a single INSERT ... ON CONFLICT when the input contains
+	// duplicate conflict keys. Pre-aggregate within this batch to keep inserts safe.
+	type bucketKey struct {
+		tunnelID  int64
+		nodeID    int64
+		timestamp int64
+	}
+
+	agg := make(map[bucketKey]*model.TunnelMetric, len(metrics))
+	for _, m := range metrics {
+		if m == nil {
+			continue
+		}
+		if m.TunnelID <= 0 || m.NodeID <= 0 || m.Timestamp <= 0 {
+			continue
+		}
+		if m.BytesIn == 0 && m.BytesOut == 0 && m.Connections == 0 && m.Errors == 0 {
+			continue
+		}
+
+		k := bucketKey{tunnelID: m.TunnelID, nodeID: m.NodeID, timestamp: m.Timestamp}
+		if existing, ok := agg[k]; ok {
+			existing.BytesIn += m.BytesIn
+			existing.BytesOut += m.BytesOut
+			existing.Connections += m.Connections
+			existing.Errors += m.Errors
+			if existing.AvgLatencyMs == 0 && m.AvgLatencyMs != 0 {
+				existing.AvgLatencyMs = m.AvgLatencyMs
+			}
+			continue
+		}
+		cp := *m
+		agg[k] = &cp
+	}
+	if len(agg) == 0 {
+		return nil
+	}
+
+	rows := make([]*model.TunnelMetric, 0, len(agg))
+	for _, v := range agg {
+		rows = append(rows, v)
+	}
+
+	return r.db.Clauses(clause.OnConflict{
+		Columns: []clause.Column{{Name: "tunnel_id"}, {Name: "node_id"}, {Name: "timestamp"}},
+		DoUpdates: clause.Assignments(map[string]interface{}{
+			"bytes_in":    gorm.Expr("bytes_in + excluded.bytes_in"),
+			"bytes_out":   gorm.Expr("bytes_out + excluded.bytes_out"),
+			"connections": gorm.Expr("connections + excluded.connections"),
+			"errors":      gorm.Expr("errors + excluded.errors"),
+			// avg_latency_ms is not additive; keep the existing bucket value.
+		}),
+	}).CreateInBatches(rows, 100).Error
+}
+
+func (r *Repository) GetTunnelMetrics(tunnelID int64, startMs, endMs int64) ([]model.TunnelMetric, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var metrics []model.TunnelMetric
+	err := r.db.Where("tunnel_id = ? AND timestamp >= ? AND timestamp <= ?", tunnelID, startMs, endMs).
+		Order("timestamp DESC").
+		Limit(5000).
+		Find(&metrics).Error
+	if len(metrics) > 1 {
+		for i, j := 0, len(metrics)-1; i < j; i, j = i+1, j-1 {
+			metrics[i], metrics[j] = metrics[j], metrics[i]
+		}
+	}
+	return metrics, err
+}
+
+// GetTunnelMetricsAggregated returns tunnel-level aggregated series (one point per timestamp).
+// Storage remains per (tunnel_id, node_id, timestamp) for future drill-down.
+func (r *Repository) GetTunnelMetricsAggregated(tunnelID int64, startMs, endMs int64) ([]model.TunnelMetric, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+
+	var metrics []model.TunnelMetric
+	err := r.db.Model(&model.TunnelMetric{}).
+		Select(
+			"tunnel_id, 0 AS node_id, timestamp, "+
+				"SUM(bytes_in) AS bytes_in, "+
+				"SUM(bytes_out) AS bytes_out, "+
+				"SUM(connections) AS connections, "+
+				"SUM(errors) AS errors, "+
+				"AVG(avg_latency_ms) AS avg_latency_ms",
+		).
+		Where("tunnel_id = ? AND timestamp >= ? AND timestamp <= ?", tunnelID, startMs, endMs).
+		Group("tunnel_id, timestamp").
+		Order("timestamp ASC").
+		Limit(5000).
+		Scan(&metrics).Error
+	if metrics == nil {
+		metrics = make([]model.TunnelMetric, 0)
+	}
+	return metrics, err
+}
+
+func (r *Repository) PruneTunnelMetrics(olderThanMs int64) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Where("timestamp < ?", olderThanMs).Delete(&model.TunnelMetric{}).Error
+}
+
+func (r *Repository) ListServiceMonitors() ([]model.ServiceMonitor, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var monitors []model.ServiceMonitor
+	err := r.db.Order("id ASC").Find(&monitors).Error
+	return monitors, err
+}
+
+func (r *Repository) ListEnabledServiceMonitors() ([]model.ServiceMonitor, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var monitors []model.ServiceMonitor
+	err := r.db.Where("enabled = 1 AND type IN (?)", []string{"tcp", "icmp"}).Order("id ASC").Find(&monitors).Error
+	return monitors, err
+}
+
+func (r *Repository) GetServiceMonitor(id int64) (*model.ServiceMonitor, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	var m model.ServiceMonitor
+	err := r.db.First(&m, id).Error
+	if err != nil {
+		if errors.Is(err, gorm.ErrRecordNotFound) {
+			return nil, nil
+		}
+		return nil, err
+	}
+	return &m, nil
+}
+
+func (r *Repository) CreateServiceMonitor(m *model.ServiceMonitor) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Create(m).Error
+}
+
+func (r *Repository) UpdateServiceMonitor(m *model.ServiceMonitor) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Save(m).Error
+}
+
+func (r *Repository) DeleteServiceMonitor(id int64) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	if id <= 0 {
+		return nil
+	}
+
+	// Keep API/UI semantics simple: deleting a monitor also deletes its history.
+	return r.db.Transaction(func(tx *gorm.DB) error {
+		if err := tx.Where("monitor_id = ?", id).Delete(&model.ServiceMonitorResult{}).Error; err != nil {
+			return err
+		}
+		return tx.Delete(&model.ServiceMonitor{}, id).Error
+	})
+}
+
+func (r *Repository) InsertServiceMonitorResult(result *model.ServiceMonitorResult) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Create(result).Error
+}
+
+func (r *Repository) GetServiceMonitorResults(monitorID int64, limit int) ([]model.ServiceMonitorResult, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+	if limit <= 0 {
+		limit = 100
+	}
+	var results []model.ServiceMonitorResult
+	err := r.db.Where("monitor_id = ?", monitorID).
+		Order("timestamp DESC").
+		Limit(limit).
+		Find(&results).Error
+	return results, err
+}
+
+// GetLatestServiceMonitorResults returns the newest result per monitor_id.
+// This is intended for list rendering (avoid N+1 queries).
+func (r *Repository) GetLatestServiceMonitorResults() ([]model.ServiceMonitorResult, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+
+	var results []model.ServiceMonitorResult
+
+	// Prefer a window-function query (works on modern SQLite + Postgres).
+	q1 := `
+		SELECT id, monitor_id, node_id, timestamp, success, latency_ms, status_code, error_message
+		FROM (
+			SELECT *, ROW_NUMBER() OVER (PARTITION BY monitor_id ORDER BY timestamp DESC, id DESC) AS rn
+			FROM service_monitor_result
+		) t
+		WHERE rn = 1
+		ORDER BY monitor_id ASC
+	`
+	if err := r.db.Raw(q1).Scan(&results).Error; err == nil {
+		return results, nil
+	}
+
+	// Fallback: just return newest rows (best-effort). This avoids hard failure on older SQLite builds.
+	// Note: This may not include all monitors if the table is extremely large and skewed.
+	results = nil
+	q2 := `
+		SELECT id, monitor_id, node_id, timestamp, success, latency_ms, status_code, error_message
+		FROM service_monitor_result
+		ORDER BY timestamp DESC, id DESC
+		LIMIT 5000
+	`
+	err := r.db.Raw(q2).Scan(&results).Error
+	if err != nil {
+		return nil, err
+	}
+
+	seen := make(map[int64]struct{}, len(results))
+	out := make([]model.ServiceMonitorResult, 0, len(results))
+	for _, row := range results {
+		if row.MonitorID <= 0 {
+			continue
+		}
+		if _, ok := seen[row.MonitorID]; ok {
+			continue
+		}
+		seen[row.MonitorID] = struct{}{}
+		out = append(out, row)
+	}
+	// Keep response stable for the frontend.
+	sort.Slice(out, func(i, j int) bool { return out[i].MonitorID < out[j].MonitorID })
+	return out, nil
+}
+
+func (r *Repository) PruneServiceMonitorResults(olderThanMs int64) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Where("timestamp < ?", olderThanMs).Delete(&model.ServiceMonitorResult{}).Error
+}

go-backend/internal/store/repo/repository_control.go

@@ -64,6 +64,7 @@ func (r *Repository) ListForwardsByTunnelTx(tx *gorm.DB, tunnelID int64) ([]mode
 	return rows, nil
 }
 
+
 func (r *Repository) ListActiveTunnelIDsByNode(nodeID int64) ([]int64, error) {
 	if r == nil || r.db == nil {
 		return nil, errors.New("repository not initialized")
@@ -125,6 +126,7 @@ func (r *Repository) ListForwardPortsTx(tx *gorm.DB, forwardID int64) ([]model.F
 	return rows, nil
 }
 
+
 func (r *Repository) HasOtherForwardOnNodePort(nodeID int64, port int, currentForwardID int64) (bool, error) {
 	if r == nil || r.db == nil {
 		return false, errors.New("repository not initialized")
@@ -151,6 +153,7 @@ func (r *Repository) HasOtherForwardOnNodePortTx(tx *gorm.DB, nodeID int64, port
 	return count > 0, nil
 }
 
+
 func (r *Repository) GetTunnelOutProtocol(tunnelID int64) (string, error) {
 	if r == nil || r.db == nil {
 		return "", errors.New("repository not initialized")

go-backend/internal/store/repo/repository_flow.go

@@ -161,6 +161,64 @@ func (r *Repository) ForwardExists(forwardID int64) (bool, error) {
 	return count > 0, nil
 }
 
+// MapForwardIDsToTunnelIDs returns a mapping from forward.id to forward.tunnel_id.
+// Missing forward IDs are omitted from the returned map.
+func (r *Repository) MapForwardIDsToTunnelIDs(forwardIDs []int64) (map[int64]int64, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	if len(forwardIDs) == 0 {
+		return map[int64]int64{}, nil
+	}
+
+	// Deduplicate and filter invalid IDs.
+	ids := make([]int64, 0, len(forwardIDs))
+	seen := make(map[int64]struct{}, len(forwardIDs))
+	for _, id := range forwardIDs {
+		if id <= 0 {
+			continue
+		}
+		if _, ok := seen[id]; ok {
+			continue
+		}
+		seen[id] = struct{}{}
+		ids = append(ids, id)
+	}
+	if len(ids) == 0 {
+		return map[int64]int64{}, nil
+	}
+
+	type row struct {
+		ID       int64 `gorm:"column:id"`
+		TunnelID int64 `gorm:"column:tunnel_id"`
+	}
+
+	out := make(map[int64]int64, len(ids))
+	const chunkSize = 500
+	for start := 0; start < len(ids); start += chunkSize {
+		end := start + chunkSize
+		if end > len(ids) {
+			end = len(ids)
+		}
+
+		var rows []row
+		if err := r.db.Model(&model.Forward{}).
+			Select("id", "tunnel_id").
+			Where("id IN ?", ids[start:end]).
+			Find(&rows).Error; err != nil {
+			return nil, err
+		}
+		for _, r := range rows {
+			if r.ID <= 0 || r.TunnelID <= 0 {
+				continue
+			}
+			out[r.ID] = r.TunnelID
+		}
+	}
+
+	return out, nil
+}
+
 func (r *Repository) SpeedLimitExists(id int64) (bool, error) {
 	if r == nil || r.db == nil {
 		return false, errors.New("repository not initialized")

go-backend/internal/store/repo/repository_monitor_nodes.go

@@ -0,0 +1,18 @@
+package repo
+
+import (
+	"errors"
+
+	"go-backend/internal/store/model"
+)
+
+func (r *Repository) ListMonitorNodes() ([]model.Node, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	var nodes []model.Node
+	err := r.db.Select("id", "inx", "name", "status", "updated_time").
+		Order("inx ASC, id ASC").
+		Find(&nodes).Error
+	return nodes, err
+}

go-backend/internal/store/repo/repository_monitor_permission.go

@@ -0,0 +1,54 @@
+package repo
+
+import (
+	"errors"
+
+	"go-backend/internal/store/model"
+
+	"gorm.io/gorm/clause"
+)
+
+func (r *Repository) InsertMonitorPermission(userID int64, now int64) error {
+	if r == nil || r.db == nil {
+		return errors.New("repository not initialized")
+	}
+	if userID <= 0 {
+		return nil
+	}
+	row := model.MonitorPermission{UserID: userID, CreatedTime: now}
+	return r.db.Clauses(clause.OnConflict{DoNothing: true}).Create(&row).Error
+}
+
+func (r *Repository) DeleteMonitorPermission(userID int64) error {
+	if r == nil || r.db == nil {
+		return errors.New("repository not initialized")
+	}
+	if userID <= 0 {
+		return nil
+	}
+	return r.db.Where("user_id = ?", userID).Delete(&model.MonitorPermission{}).Error
+}
+
+func (r *Repository) HasMonitorPermission(userID int64) (bool, error) {
+	if r == nil || r.db == nil {
+		return false, errors.New("repository not initialized")
+	}
+	if userID <= 0 {
+		return false, nil
+	}
+	var count int64
+	err := r.db.Model(&model.MonitorPermission{}).Where("user_id = ?", userID).Count(&count).Error
+	if err != nil {
+		return false, err
+	}
+	return count > 0, nil
+}
+
+func (r *Repository) ListMonitorPermissions() ([]model.MonitorPermission, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	var items []model.MonitorPermission
+	err := r.db.Order("id ASC").Find(&items).Error
+	return items, err
+}

go-backend/internal/store/repo/repository_monitor_tunnels.go

@@ -0,0 +1,18 @@
+package repo
+
+import (
+	"errors"
+
+	"go-backend/internal/store/model"
+)
+
+func (r *Repository) ListMonitorTunnels() ([]model.Tunnel, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	var tunnels []model.Tunnel
+	err := r.db.Select("id", "inx", "name", "status", "updated_time").
+		Order("inx ASC, id ASC").
+		Find(&tunnels).Error
+	return tunnels, err
+}

go-backend/internal/store/repo/repository_monitoring_test.go

@@ -0,0 +1,134 @@
+package repo
+
+import (
+	"sync"
+	"testing"
+	"time"
+
+	"go-backend/internal/store/model"
+)
+
+func TestGetTunnelMetricsAggregatedSumsAcrossNodes(t *testing.T) {
+	r, err := Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	ts := time.Now().UnixMilli()
+
+	if err := r.InsertTunnelMetric(&model.TunnelMetric{
+		TunnelID:  1,
+		NodeID:    1,
+		Timestamp: ts,
+		BytesIn:   100,
+		BytesOut:  200,
+	}); err != nil {
+		t.Fatalf("insert tunnel metric n1: %v", err)
+	}
+	if err := r.InsertTunnelMetric(&model.TunnelMetric{
+		TunnelID:  1,
+		NodeID:    2,
+		Timestamp: ts,
+		BytesIn:   300,
+		BytesOut:  400,
+	}); err != nil {
+		t.Fatalf("insert tunnel metric n2: %v", err)
+	}
+
+	metrics, err := r.GetTunnelMetricsAggregated(1, ts-1000, ts+1000)
+	if err != nil {
+		t.Fatalf("get aggregated tunnel metrics: %v", err)
+	}
+	if len(metrics) != 1 {
+		t.Fatalf("expected 1 aggregated point, got %d", len(metrics))
+	}
+	if metrics[0].Timestamp != ts {
+		t.Fatalf("expected timestamp %d, got %d", ts, metrics[0].Timestamp)
+	}
+	if metrics[0].BytesIn != 400 {
+		t.Fatalf("expected bytesIn 400, got %d", metrics[0].BytesIn)
+	}
+	if metrics[0].BytesOut != 600 {
+		t.Fatalf("expected bytesOut 600, got %d", metrics[0].BytesOut)
+	}
+}
+
+func TestUpsertTunnelMetricBucketsAggregatesDuplicateKeysInBatch(t *testing.T) {
+	r, err := Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	ts := time.Now().UnixMilli()
+
+	items := []*model.TunnelMetric{
+		{TunnelID: 1, NodeID: 1, Timestamp: ts, BytesIn: 10, BytesOut: 20},
+		{TunnelID: 1, NodeID: 1, Timestamp: ts, BytesIn: 30, BytesOut: 40},
+	}
+	if err := r.UpsertTunnelMetricBuckets(items); err != nil {
+		t.Fatalf("upsert buckets: %v", err)
+	}
+
+	rows, err := r.GetTunnelMetrics(1, ts-1000, ts+1000)
+	if err != nil {
+		t.Fatalf("get tunnel metrics: %v", err)
+	}
+	if len(rows) != 1 {
+		t.Fatalf("expected 1 stored row, got %d", len(rows))
+	}
+	if rows[0].BytesIn != 40 {
+		t.Fatalf("expected bytesIn 40, got %d", rows[0].BytesIn)
+	}
+	if rows[0].BytesOut != 60 {
+		t.Fatalf("expected bytesOut 60, got %d", rows[0].BytesOut)
+	}
+}
+
+func TestUpsertTunnelMetricBucketsIsSafeUnderConcurrency(t *testing.T) {
+	r, err := Open(":memory:")
+	if err != nil {
+		t.Fatalf("open repo: %v", err)
+	}
+	defer r.Close()
+
+	ts := time.Now().UnixMilli()
+
+	const workers = 20
+	const perWorkerIn = int64(5)
+	const perWorkerOut = int64(7)
+
+	var wg sync.WaitGroup
+	wg.Add(workers)
+	for i := 0; i < workers; i++ {
+		go func() {
+			defer wg.Done()
+			_ = r.UpsertTunnelMetricBuckets([]*model.TunnelMetric{{
+				TunnelID:  1,
+				NodeID:    1,
+				Timestamp: ts,
+				BytesIn:   perWorkerIn,
+				BytesOut:  perWorkerOut,
+			}})
+		}()
+	}
+	wg.Wait()
+
+	rows, err := r.GetTunnelMetrics(1, ts-1000, ts+1000)
+	if err != nil {
+		t.Fatalf("get tunnel metrics: %v", err)
+	}
+	if len(rows) != 1 {
+		t.Fatalf("expected 1 stored row, got %d", len(rows))
+	}
+
+	wantIn := int64(workers) * perWorkerIn
+	wantOut := int64(workers) * perWorkerOut
+	if rows[0].BytesIn != wantIn {
+		t.Fatalf("expected bytesIn %d, got %d", wantIn, rows[0].BytesIn)
+	}
+	if rows[0].BytesOut != wantOut {
+		t.Fatalf("expected bytesOut %d, got %d", wantOut, rows[0].BytesOut)
+	}
+}

go-backend/internal/ws/server.go

@@ -72,6 +72,7 @@ type Server struct {
 	jwtSecret    string
 	upgrader     websocket.Upgrader
 	onNodeOnline func(nodeID int64)
+	onNodeMetric func(nodeID int64, info SystemInfo)
 
 	mu      sync.RWMutex
 	admins  map[*connWrap]struct{}
@@ -80,6 +81,22 @@ type Server struct {
 	pending map[string]pendingRequest
 }
 
+type SystemInfo struct {
+	Uptime           uint64  `json:"uptime"`
+	BytesReceived    uint64  `json:"bytes_received"`
+	BytesTransmitted uint64  `json:"bytes_transmitted"`
+	CPUUsage         float64 `json:"cpu_usage"`
+	MemoryUsage      float64 `json:"memory_usage"`
+	DiskUsage        float64 `json:"disk_usage"`
+	Load1            float64 `json:"load1"`
+	Load5            float64 `json:"load5"`
+	Load15           float64 `json:"load15"`
+	TCPConns         int64   `json:"tcp_conns"`
+	UDPConns         int64   `json:"udp_conns"`
+	NetInSpeed       int64   `json:"net_in_speed"`
+	NetOutSpeed      int64   `json:"net_out_speed"`
+}
+
 func (s *Server) SetNodeOnlineHook(fn func(nodeID int64)) {
 	if s == nil {
 		return
@@ -89,6 +106,15 @@ func (s *Server) SetNodeOnlineHook(fn func(nodeID int64)) {
 	s.mu.Unlock()
 }
 
+func (s *Server) SetNodeMetricHook(fn func(nodeID int64, info SystemInfo)) {
+	if s == nil {
+		return
+	}
+	s.mu.Lock()
+	s.onNodeMetric = fn
+	s.mu.Unlock()
+}
+
 func NewServer(repo *repo.Repository, jwtSecret string) *Server {
 	return &Server{
 		repo:      repo,
@@ -231,12 +257,73 @@ func (s *Server) handleNode(w http.ResponseWriter, r *http.Request, nodeID int64
 		var parsed struct {
 			Type string `json:"type"`
 		}
-		if json.Unmarshal([]byte(msg), &parsed) == nil && parsed.Type == "UpgradeProgress" {
-			s.broadcastTyped(nodeID, "upgrade_progress", msg)
-		} else {
-			s.broadcastInfo(nodeID, msg)
+		if json.Unmarshal([]byte(msg), &parsed) == nil && parsed.Type != "" {
+			switch parsed.Type {
+			case "UpgradeProgress":
+				s.broadcastTyped(nodeID, "upgrade_progress", msg)
+				continue
+			default:
+				// Unknown typed messages still get broadcast so future
+				// agent message types are not silently lost.
+				s.broadcastInfo(nodeID, msg)
+				continue
+			}
+		}
+
+		if looksLikeSystemInfoMessage(msg) {
+			var sysInfo SystemInfo
+			if err := json.Unmarshal([]byte(msg), &sysInfo); err == nil {
+				s.mu.RLock()
+				onMetric := s.onNodeMetric
+				s.mu.RUnlock()
+				if onMetric != nil {
+					go onMetric(nodeID, sysInfo)
+				}
+				s.broadcastTyped(nodeID, "metric", msg)
+				continue
+			}
+		}
+
+		s.broadcastInfo(nodeID, msg)
+	}
+}
+
+func looksLikeSystemInfoMessage(msg string) bool {
+	// Keep this as a cheap heuristic so that arbitrary JSON objects don't get
+	// misclassified as metrics (SystemInfo unmarshal would otherwise succeed with
+	// all-zero values).
+	if strings.TrimSpace(msg) == "" {
+		return false
+	}
+	if !strings.Contains(msg, "{") {
+		return false
+	}
+
+	keys := []string{
+		"\"uptime\"",
+		"\"cpu_usage\"",
+		"\"memory_usage\"",
+		"\"disk_usage\"",
+		"\"bytes_received\"",
+		"\"bytes_transmitted\"",
+		"\"net_in_speed\"",
+		"\"net_out_speed\"",
+		"\"tcp_conns\"",
+		"\"udp_conns\"",
+		"\"load1\"",
+		"\"load5\"",
+		"\"load15\"",
+	}
+	matched := 0
+	for _, k := range keys {
+		if strings.Contains(msg, k) {
+			matched++
+			if matched >= 3 {
+				return true
+			}
 		}
 	}
+	return false
 }
 
 func (s *Server) SendCommand(nodeID int64, cmdType string, data interface{}, timeout time.Duration) (CommandResult, error) {

go-backend/tests/contract/issue313_entry_port_conflict_contract_test.go

@@ -112,6 +112,12 @@ func TestIssue313_EntryPortCrossTunnelConflictContract(t *testing.T) {
 		t.Fatalf("insert forward_port a: %v", err)
 	}
 
+	// Simulate legacy dirty data: tunnel A already occupies port 2000 on entryB2.
+	// When tunnel B adds entryB2, the inherited forward port should conflict cross-tunnel.
+	if err := repo.DB().Exec(`INSERT INTO forward_port(forward_id, node_id, port) VALUES(?, ?, ?)`, forwardAID, entryB2, 2000).Error; err != nil {
+		t.Fatalf("insert forward_port a on entryB2: %v", err)
+	}
+
 	if err := repo.DB().Exec(`
 		INSERT INTO user_tunnel(id, user_id, tunnel_id, speed_id, num, flow, in_flow, out_flow, flow_reset_time, exp_time, status)
 		VALUES(3132, 1, ?, NULL, 999, 99999, 0, 0, 1, 2727251700000, 1)
@@ -170,7 +176,8 @@ func TestIssue313_EntryPortCrossTunnelConflictContract(t *testing.T) {
 		t.Fatalf("expected update failure due to cross-tunnel port conflict, got success with code 0")
 	}
 
-	if !bytes.Contains([]byte(out.Msg), []byte("端口")) && !bytes.Contains([]byte(out.Msg), []byte("占用")) {
+	msgBytes := []byte(out.Msg)
+	if !bytes.Contains(msgBytes, []byte("端口")) && !bytes.Contains(msgBytes, []byte("占用")) {
 		t.Fatalf("expected port conflict error message, got %q", out.Msg)
 	}
 

go-backend/tests/contract/tunnel_metrics_ingestion_contract_test.go

@@ -0,0 +1,97 @@
+package contract_test
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"go-backend/internal/store/model"
+)
+
+func TestFlowUploadInsertsTunnelMetrics(t *testing.T) {
+	secret := "monitoring-jwt-secret"
+	router, repo := setupContractRouter(t, secret)
+
+	now := time.Now().UnixMilli()
+
+	node := &model.Node{
+		Name:          "node-1",
+		Secret:        "node-secret",
+		ServerIP:      "127.0.0.1",
+		Port:          "10000-10010",
+		TCPListenAddr: "[::]",
+		UDPListenAddr: "[::]",
+		CreatedTime:   now,
+		Status:        1,
+	}
+	if err := repo.DB().Create(node).Error; err != nil {
+		t.Fatalf("seed node: %v", err)
+	}
+
+	tunnel := &model.Tunnel{
+		Name:         "tunnel-1",
+		TrafficRatio: 1.0,
+		Type:         1,
+		Protocol:     "tls",
+		Flow:         1,
+		CreatedTime:  now,
+		UpdatedTime:  now,
+		Status:       1,
+	}
+	if err := repo.DB().Create(tunnel).Error; err != nil {
+		t.Fatalf("seed tunnel: %v", err)
+	}
+
+	forward := &model.Forward{
+		UserID:      123,
+		UserName:    "user-123",
+		Name:        "forward-1",
+		TunnelID:    tunnel.ID,
+		RemoteAddr:  "1.1.1.1:80",
+		CreatedTime: now,
+		UpdatedTime: now,
+		Status:      1,
+	}
+	if err := repo.DB().Create(forward).Error; err != nil {
+		t.Fatalf("seed forward: %v", err)
+	}
+
+	serviceName := jsonNumber(forward.ID) + "_123_0"
+	body, _ := json.Marshal([]map[string]interface{}{{
+		"n": serviceName,
+		"u": 200,
+		"d": 100,
+	}})
+
+	req := httptest.NewRequest(http.MethodPost, "/flow/upload?secret="+node.Secret, bytes.NewReader(body))
+	res := httptest.NewRecorder()
+	router.ServeHTTP(res, req)
+
+	if res.Code != http.StatusOK {
+		t.Fatalf("expected status 200, got %d", res.Code)
+	}
+
+	metrics, err := repo.GetTunnelMetrics(tunnel.ID, 0, now+60_000)
+	if err != nil {
+		t.Fatalf("get tunnel metrics: %v", err)
+	}
+	if len(metrics) != 1 {
+		t.Fatalf("expected 1 tunnel metric row, got %d", len(metrics))
+	}
+
+	if metrics[0].TunnelID != tunnel.ID {
+		t.Fatalf("expected tunnelId %d, got %d", tunnel.ID, metrics[0].TunnelID)
+	}
+	if metrics[0].NodeID != node.ID {
+		t.Fatalf("expected nodeId %d, got %d", node.ID, metrics[0].NodeID)
+	}
+	if metrics[0].BytesIn != 100 {
+		t.Fatalf("expected bytesIn 100, got %d", metrics[0].BytesIn)
+	}
+	if metrics[0].BytesOut != 200 {
+		t.Fatalf("expected bytesOut 200, got %d", metrics[0].BytesOut)
+	}
+}

go-gost/x/service/service.go

@@ -7,7 +7,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"log"
 	"net"
 	"os"
 	"os/exec"
@@ -63,11 +62,9 @@ func SetProtocolBlock(httpOn int, tlsOn int, socksOn int) {
 type Option func(opts *options)
 
 func init() {
-	_, err := LoadConfig("config.json")
-	fmt.Println("config.json loaded")
-	if err != nil {
-		log.Fatal(err)
-	}
+	// NOTE: This package can be imported by tests/tools that don't have a local
+	// config.json. Missing config should not crash the process.
+	_, _ = LoadConfig("config.json")
 	needWrap = isTls+isSocks+isHttp > 0
 }
 

go-gost/x/socket/websocket_reporter.go

@@ -17,7 +17,7 @@ import (
 	"runtime"
 	"strconv"
 	"strings"
-	"sync" // 新增：用于管理连接状态的互斥锁
+	"sync"
 	"time"
 
 	"github.com/go-gost/x/config"
@@ -25,34 +25,67 @@ import (
 	"github.com/go-gost/x/service"
 	"github.com/gorilla/websocket"
 	"github.com/shirou/gopsutil/v3/cpu"
+	"github.com/shirou/gopsutil/v3/disk"
 	"github.com/shirou/gopsutil/v3/host"
+	"github.com/shirou/gopsutil/v3/load"
 	"github.com/shirou/gopsutil/v3/mem"
 	psnet "github.com/shirou/gopsutil/v3/net"
+	"golang.org/x/net/icmp"
+	"golang.org/x/net/ipv4"
+	"golang.org/x/net/ipv6"
 )
 
 // SystemInfo 系统信息结构体
 type SystemInfo struct {
-	Uptime           uint64  `json:"uptime"`            // 开机时间	（秒）
-	BytesReceived    uint64  `json:"bytes_received"`    // 接收字节数
-	BytesTransmitted uint64  `json:"bytes_transmitted"` // 发送字节数
-	CPUUsage         float64 `json:"cpu_usage"`         // CPU使用率（百分比）
-	MemoryUsage      float64 `json:"memory_usage"`      // 内存使用率（百分比）
+	Uptime           uint64  `json:"uptime"`
+	BytesReceived    uint64  `json:"bytes_received"`
+	BytesTransmitted uint64  `json:"bytes_transmitted"`
+	CPUUsage         float64 `json:"cpu_usage"`
+	MemoryUsage      float64 `json:"memory_usage"`
+	DiskUsage        float64 `json:"disk_usage"`
+	Load1            float64 `json:"load1"`
+	Load5            float64 `json:"load5"`
+	Load15           float64 `json:"load15"`
+	TCPConns         int64   `json:"tcp_conns"`
+	UDPConns         int64   `json:"udp_conns"`
+	NetInSpeed       int64   `json:"net_in_speed"`
+	NetOutSpeed      int64   `json:"net_out_speed"`
 }
 
 // NetworkStats 网络统计信息
 type NetworkStats struct {
-	BytesReceived    uint64 `json:"bytes_received"`    // 接收字节数
-	BytesTransmitted uint64 `json:"bytes_transmitted"` // 发送字节数
+	BytesReceived    uint64 `json:"bytes_received"`
+	BytesTransmitted uint64 `json:"bytes_transmitted"`
+	BytesRecvDelta   uint64 `json:"bytes_recv_delta"`
+	BytesSentDelta   uint64 `json:"bytes_sent_delta"`
 }
 
 // CPUInfo CPU信息
 type CPUInfo struct {
-	Usage float64 `json:"usage"` // CPU使用率（百分比）
+	Usage float64 `json:"usage"`
 }
 
 // MemoryInfo 内存信息
 type MemoryInfo struct {
-	Usage float64 `json:"usage"` // 内存使用率（百分比）
+	Usage float64 `json:"usage"`
+}
+
+// DiskInfo 磁盘信息
+type DiskInfo struct {
+	Usage float64 `json:"usage"`
+}
+
+// LoadInfo 负载信息
+type LoadInfo struct {
+	Load1  float64 `json:"load1"`
+	Load5  float64 `json:"load5"`
+	Load15 float64 `json:"load15"`
+}
+
+// ConnectionInfo 连接信息
+type ConnectionInfo struct {
+	TCPConns int64 `json:"tcp_conns"`
+	UDPConns int64 `json:"udp_conns"`
 }
 
 // CommandMessage 命令消息结构体
@@ -91,6 +124,25 @@ type TcpPingResponse struct {
 	RequestId    string  `json:"requestId,omitempty"`
 }
 
+// ServiceMonitorCheckRequest service monitor check request.
+type ServiceMonitorCheckRequest struct {
+	MonitorID  int64  `json:"monitorId"`
+	Type       string `json:"type"` // tcp|icmp
+	Target     string `json:"target"`
+	TimeoutSec int    `json:"timeoutSec"`
+}
+
+// ServiceMonitorCheckResult node-executed check output.
+// CommandResponse.Success indicates command execution status.
+// Actual check success is represented by this struct.
+type ServiceMonitorCheckResult struct {
+	MonitorID    int64   `json:"monitorId"`
+	Success      bool    `json:"success"`
+	LatencyMs    float64 `json:"latencyMs"`
+	StatusCode   int     `json:"statusCode,omitempty"`
+	ErrorMessage string  `json:"errorMessage,omitempty"`
+}
+
 const (
 	reporterReadWait  = 60 * time.Second
 	reporterWriteWait = 5 * time.Second
@@ -134,7 +186,7 @@ func NewWebSocketReporter(serverURL string, secret string) *WebSocketReporter {
 	return &WebSocketReporter{
 		url:            serverURL,
 		reconnectTime:  5 * time.Second,  // 重连间隔
-		pingInterval:   2 * time.Second,  // 发送间隔改为2秒
+		pingInterval:   5 * time.Second,  // 指标上报间隔
 		configInterval: 10 * time.Minute, // 配置上报间隔
 		ctx:            ctx,
 		cancel:         cancel,
@@ -449,11 +501,35 @@ func (w *WebSocketReporter) handleConnection() {
 	}
 }
 
+var lastNetBytesReceived uint64
+var lastNetBytesTransmitted uint64
+var lastNetTime int64
+
+var connInfoCached ConnectionInfo
+var connInfoCachedAt int64
+var connInfoCachedMu sync.Mutex
+
 // collectSystemInfo 收集系统信息
 func (w *WebSocketReporter) collectSystemInfo() SystemInfo {
 	networkStats := getNetworkStats()
 	cpuInfo := getCPUInfo()
 	memoryInfo := getMemoryInfo()
+	diskInfo := getDiskInfo()
+	loadInfo := getLoadInfo()
+	connInfo := getConnectionInfo()
+
+	now := time.Now().UnixMilli()
+	var netInSpeed, netOutSpeed int64
+	if lastNetTime > 0 {
+		deltaMs := now - lastNetTime
+		if deltaMs > 0 {
+			netInSpeed = int64(float64(networkStats.BytesRecvDelta) * 1000 / float64(deltaMs))
+			netOutSpeed = int64(float64(networkStats.BytesSentDelta) * 1000 / float64(deltaMs))
+		}
+	}
+	lastNetBytesReceived = networkStats.BytesReceived
+	lastNetBytesTransmitted = networkStats.BytesTransmitted
+	lastNetTime = now
 
 	return SystemInfo{
 		Uptime:           getUptime(),
@@ -461,6 +537,14 @@ func (w *WebSocketReporter) collectSystemInfo() SystemInfo {
 		BytesTransmitted: networkStats.BytesTransmitted,
 		CPUUsage:         cpuInfo.Usage,
 		MemoryUsage:      memoryInfo.Usage,
+		DiskUsage:        diskInfo.Usage,
+		Load1:            loadInfo.Load1,
+		Load5:            loadInfo.Load5,
+		Load15:           loadInfo.Load15,
+		TCPConns:         connInfo.TCPConns,
+		UDPConns:         connInfo.UDPConns,
+		NetInSpeed:       netInSpeed,
+		NetOutSpeed:      netOutSpeed,
 	}
 }
 
@@ -622,7 +706,7 @@ func (w *WebSocketReporter) handleReceivedMessage(messageType int, message []byt
 
 			if cmdMsg.Type != "call" {
 				// 其他状态变更命令保持同步，确保顺序执行
-				if cmdMsg.Type == "TcpPing" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
+				if cmdMsg.Type == "TcpPing" || cmdMsg.Type == "ServiceMonitorCheck" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
 					go w.routeCommand(cmdMsg)
 				} else {
 					w.routeCommand(cmdMsg)
@@ -638,7 +722,7 @@ func (w *WebSocketReporter) handleReceivedMessage(messageType int, message []byt
 			}
 			if cmdMsg.Type != "call" {
 				// 其他状态变更命令保持同步，确保顺序执行
-				if cmdMsg.Type == "TcpPing" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
+				if cmdMsg.Type == "TcpPing" || cmdMsg.Type == "ServiceMonitorCheck" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
 					go w.routeCommand(cmdMsg)
 				} else {
 					w.routeCommand(cmdMsg)
@@ -726,6 +810,13 @@ func (w *WebSocketReporter) routeCommand(cmd CommandMessage) {
 		response.Data = tcpPingResult
 		// needSaveConfig = false (默认值)
 
+	// Service monitor check (read-only)
+	case "ServiceMonitorCheck":
+		var checkResult ServiceMonitorCheckResult
+		checkResult, err = w.handleServiceMonitorCheck(cmd.Data)
+		response.Type = "ServiceMonitorCheckResponse"
+		response.Data = checkResult
+
 	// Protocol blocking switches
 	case "SetProtocol":
 		err = w.handleSetProtocol(cmd.Data)
@@ -1381,17 +1472,21 @@ func getNetworkStats() NetworkStats {
 		return stats
 	}
 
-	// 汇总所有非回环接口的流量
 	for _, io := range ioCounters {
-		// 跳过回环接口
 		if io.Name == "lo" || strings.HasPrefix(io.Name, "lo") {
 			continue
 		}
-
 		stats.BytesReceived += io.BytesRecv
 		stats.BytesTransmitted += io.BytesSent
 	}
 
+	if lastNetBytesReceived > 0 && stats.BytesReceived >= lastNetBytesReceived {
+		stats.BytesRecvDelta = stats.BytesReceived - lastNetBytesReceived
+	}
+	if lastNetBytesTransmitted > 0 && stats.BytesTransmitted >= lastNetBytesTransmitted {
+		stats.BytesSentDelta = stats.BytesTransmitted - lastNetBytesTransmitted
+	}
+
 	return stats
 }
 
@@ -1399,8 +1494,8 @@ func getNetworkStats() NetworkStats {
 func getCPUInfo() CPUInfo {
 	var cpuInfo CPUInfo
 
-	// 获取CPU使用率
-	percentages, err := cpu.Percent(time.Second, false)
+	// 获取CPU使用率 (non-blocking)
+	percentages, err := cpu.Percent(0, false)
 	if err == nil && len(percentages) > 0 {
 		cpuInfo.Usage = percentages[0]
 	}
@@ -1422,6 +1517,69 @@ func getMemoryInfo() MemoryInfo {
 	return memInfo
 }
 
+// getDiskInfo 获取磁盘信息
+func getDiskInfo() DiskInfo {
+	var diskInfo DiskInfo
+
+	usage, err := disk.Usage("/")
+	if err != nil {
+		return diskInfo
+	}
+
+	diskInfo.Usage = usage.UsedPercent
+
+	return diskInfo
+}
+
+// getLoadInfo 获取负载信息
+func getLoadInfo() LoadInfo {
+	var loadInfo LoadInfo
+
+	avg, err := load.Avg()
+	if err != nil {
+		return loadInfo
+	}
+
+	loadInfo.Load1 = avg.Load1
+	loadInfo.Load5 = avg.Load5
+	loadInfo.Load15 = avg.Load15
+
+	return loadInfo
+}
+
+// getConnectionInfo 获取连接信息
+func getConnectionInfo() ConnectionInfo {
+	now := time.Now().UnixMilli()
+	const refreshEveryMs = int64((15 * time.Second) / time.Millisecond)
+
+	connInfoCachedMu.Lock()
+	if connInfoCachedAt > 0 && now-connInfoCachedAt < refreshEveryMs {
+		v := connInfoCached
+		connInfoCachedMu.Unlock()
+		return v
+	}
+	connInfoCachedMu.Unlock()
+
+	var connInfo ConnectionInfo
+
+	connStats, err := psnet.Connections("tcp")
+	if err == nil {
+		connInfo.TCPConns = int64(len(connStats))
+	}
+
+	udpStats, err := psnet.Connections("udp")
+	if err == nil {
+		connInfo.UDPConns = int64(len(udpStats))
+	}
+
+	connInfoCachedMu.Lock()
+	connInfoCached = connInfo
+	connInfoCachedAt = now
+	connInfoCachedMu.Unlock()
+
+	return connInfo
+}
+
 // StartWebSocketReporterWithConfig 使用配置字段启动WebSocket报告器
 func StartWebSocketReporterWithConfig(addr string, secret string, http int, tls int, socks int, version string) *WebSocketReporter {
 
@@ -1503,6 +1661,210 @@ func (w *WebSocketReporter) handleTcpPing(data interface{}) (TcpPingResponse, er
 	return response, nil
 }
 
+// handleServiceMonitorCheck executes a service monitor check on this node.
+// It always returns a result (command execution is considered successful even if the check fails).
+func (w *WebSocketReporter) handleServiceMonitorCheck(data interface{}) (ServiceMonitorCheckResult, error) {
+	jsonData, err := json.Marshal(data)
+	if err != nil {
+		return ServiceMonitorCheckResult{}, fmt.Errorf("序列化检查数据失败: %v", err)
+	}
+
+	var req ServiceMonitorCheckRequest
+	if err := json.Unmarshal(jsonData, &req); err != nil {
+		return ServiceMonitorCheckResult{}, fmt.Errorf("解析检查请求失败: %v", err)
+	}
+
+	checkType := strings.ToLower(strings.TrimSpace(req.Type))
+	target := strings.TrimSpace(req.Target)
+	res := ServiceMonitorCheckResult{MonitorID: req.MonitorID}
+
+	if checkType != "tcp" && checkType != "icmp" {
+		res.Success = false
+		res.ErrorMessage = "不支持的检查类型"
+		return res, nil
+	}
+	if target == "" {
+		res.Success = false
+		res.ErrorMessage = "检查目标为空"
+		return res, nil
+	}
+
+	timeoutSec := req.TimeoutSec
+	if timeoutSec <= 0 {
+		timeoutSec = 5
+	}
+	timeout := time.Duration(timeoutSec) * time.Second
+
+	start := time.Now()
+
+	switch checkType {
+	case "tcp":
+		// Validate and normalize host:port.
+		_, _, splitErr := net.SplitHostPort(target)
+		if splitErr != nil {
+			res.Success = false
+			res.ErrorMessage = "无效的TCP目标"
+			res.LatencyMs = float64(time.Since(start).Milliseconds())
+			return res, nil
+		}
+		conn, dialErr := net.DialTimeout("tcp", target, timeout)
+		res.LatencyMs = float64(time.Since(start).Milliseconds())
+		if dialErr != nil {
+			res.Success = false
+			res.ErrorMessage = dialErr.Error()
+			return res, nil
+		}
+		_ = conn.Close()
+		res.Success = true
+		return res, nil
+
+	case "icmp":
+		rtt, pingErr := icmpPing(target, timeout)
+		res.LatencyMs = float64(rtt.Milliseconds())
+		if pingErr != nil {
+			res.Success = false
+			res.ErrorMessage = pingErr.Error()
+			return res, nil
+		}
+		res.Success = true
+		return res, nil
+	}
+
+	res.Success = false
+	res.ErrorMessage = "未知错误"
+	res.LatencyMs = float64(time.Since(start).Milliseconds())
+	return res, nil
+}
+
+func icmpPing(target string, timeout time.Duration) (time.Duration, error) {
+	start := time.Now()
+
+	target = strings.TrimSpace(target)
+	if target == "" {
+		return time.Since(start), fmt.Errorf("无效的ICMP目标")
+	}
+	// Avoid accepting URL-like targets.
+	if strings.Contains(target, "://") {
+		return time.Since(start), fmt.Errorf("无效的ICMP目标")
+	}
+	if strings.HasPrefix(target, "[") && strings.HasSuffix(target, "]") {
+		target = strings.TrimSuffix(strings.TrimPrefix(target, "["), "]")
+	}
+
+	ipAddr, err := net.ResolveIPAddr("ip", target)
+	if err != nil || ipAddr == nil || ipAddr.IP == nil {
+		if err == nil {
+			err = fmt.Errorf("unknown address")
+		}
+		return time.Since(start), fmt.Errorf("解析目标失败: %v", err)
+	}
+
+	isV4 := ipAddr.IP.To4() != nil
+	listenAddr := "0.0.0.0"
+	proto := 1
+	var echoType icmp.Type = ipv4.ICMPTypeEcho
+	var echoReplyType icmp.Type = ipv4.ICMPTypeEchoReply
+	networks := []string{"udp4", "ip4:icmp"}
+	if !isV4 {
+		listenAddr = "::"
+		proto = 58
+		echoType = ipv6.ICMPTypeEchoRequest
+		echoReplyType = ipv6.ICMPTypeEchoReply
+		networks = []string{"udp6", "ip6:ipv6-icmp"}
+	}
+
+	var conn *icmp.PacketConn
+	selectedNetwork := ""
+	var lastErr error
+	for _, nw := range networks {
+		c, err := icmp.ListenPacket(nw, listenAddr)
+		if err == nil {
+			conn = c
+			selectedNetwork = nw
+			break
+		}
+		lastErr = err
+	}
+	if conn == nil {
+		if lastErr != nil {
+			return time.Since(start), fmt.Errorf("创建ICMP连接失败: %v", lastErr)
+		}
+		return time.Since(start), fmt.Errorf("创建ICMP连接失败")
+	}
+	defer conn.Close()
+
+	id := os.Getpid() & 0xffff
+	seq := 1
+
+	wm := icmp.Message{
+		Type: echoType,
+		Code: 0,
+		Body: &icmp.Echo{
+			ID:   id,
+			Seq:  seq,
+			Data: []byte("FLVX-PING"),
+		},
+	}
+	wb, err := wm.Marshal(nil)
+	if err != nil {
+		return time.Since(start), err
+	}
+
+	_ = conn.SetDeadline(time.Now().Add(timeout))
+
+	var dst net.Addr
+	if strings.HasPrefix(selectedNetwork, "udp") {
+		dst = &net.UDPAddr{IP: ipAddr.IP, Zone: ipAddr.Zone}
+	} else {
+		dst = &net.IPAddr{IP: ipAddr.IP, Zone: ipAddr.Zone}
+	}
+
+	if _, err := conn.WriteTo(wb, dst); err != nil {
+		return time.Since(start), err
+	}
+
+	addrIP := func(a net.Addr) net.IP {
+		switch v := a.(type) {
+		case *net.IPAddr:
+			return v.IP
+		case *net.UDPAddr:
+			return v.IP
+		default:
+			return nil
+		}
+	}
+
+	rb := make([]byte, 1500)
+	for {
+		n, peer, err := conn.ReadFrom(rb)
+		if err != nil {
+			return time.Since(start), err
+		}
+		if p := addrIP(peer); p != nil && !p.Equal(ipAddr.IP) {
+			continue
+		}
+		rm, err := icmp.ParseMessage(proto, rb[:n])
+		if err != nil {
+			continue
+		}
+		if rm.Type != echoReplyType {
+			continue
+		}
+		echo, ok := rm.Body.(*icmp.Echo)
+		if !ok {
+			continue
+		}
+		if echo.Seq != seq {
+			continue
+		}
+		// For non-privileged endpoints, the kernel may choose the ID.
+		if !strings.HasPrefix(selectedNetwork, "udp") && echo.ID != id {
+			continue
+		}
+		return time.Since(start), nil
+	}
+}
+
 // tcpPingHost 执行TCP连接测试，返回平均连接时间和失败率
 func tcpPingHost(ip string, port int, count int, timeoutMs int) (float64, float64, error) {
 	var totalTime float64

plans/037-monitoring-metrics-health.md

@@ -0,0 +1,104 @@
+# 037 - Monitoring: Node Metrics + Service Health Checks
+
+## Context
+This worktree introduces a monitoring feature set:
+- Node runtime metrics streamed via WebSocket (agent -> panel -> admin clients)
+- Metrics ingestion + retention in panel DB
+- Service monitoring (TCP/ICMP checks only) + result storage
+- Frontend monitor view (charts + monitor CRUD + run + results)
+- Dedicated monitor page (`/monitor`) that works for authorized non-admin users
+
+The initial implementation landed without a plan doc and had several correctness issues (API JSON shape mismatch, wrong time units, contract test hangs under SQLite single-connection mode, etc.). This plan documents what exists, what was fixed, and what is still incomplete/needs decisions.
+
+## Goals
+- Metrics endpoints return stable JSON fields matching frontend types.
+- Contract tests cover metrics + monitor CRUD and are deterministic.
+- WebSocket metric messages update node cards correctly.
+- Monitoring view queries the correct time range and renders timestamps correctly.
+- go-gost/x unit tests do not depend on a local config.json.
+
+## Non-goals (for this plan)
+- A full monitor scheduling system (jitter/backoff/concurrency budgets/per-monitor next-run) beyond the current simple loop.
+- Building a full alerting pipeline (notifications, thresholds, paging).
+
+## Current Status (as of this worktree)
+- Backend models updated with JSON tags for monitoring structs.
+- Handler endpoints for metrics + service monitors added.
+- Metrics ingestion service implemented with buffering + retention pruning.
+- Health checker implemented (panel-side when `nodeId == 0`; node-executed via WS when `nodeId > 0`) and background jobs wired.
+- Frontend monitor view added; build passes.
+- Contract tests for monitoring added.
+- Monitoring endpoints are accessible by admin users and non-admin users explicitly authorized by admin (via `monitor_permission`).
+- Frontend exposes monitoring via a dedicated `/monitor` page; admin can grant/revoke monitoring permission from the User permissions modal.
+- Frontend includes tunnel metrics charts (backed by `/api/v1/monitor/tunnels` list + `/api/v1/monitor/tunnels/:id/metrics`).
+
+## Known Semantics Gaps (need decisions)
+- `service_monitor.intervalSec` is best-effort (checker ticks every 30s; intervals shorter than that won't run faster).
+- `service_monitor_result.success` is stored as int (0/1). Frontend currently treats it as number; decide if API should expose boolean.
+
+## Admin Authorization API
+Monitoring permission management (admin-only):
+- `GET /api/v1/monitor/permission/list`
+- `POST /api/v1/monitor/permission/assign` body: `{ "userId": 123 }`
+- `POST /api/v1/monitor/permission/remove` body: `{ "userId": 123 }`
+
+## Checklist
+
+### Phase 1: Correctness + Contracts
+- [x] Align monitoring JSON response fields with frontend/contract expectations (add json tags or DTO mapping).
+- [x] Fix frontend monitor time range query (use ms start/end; avoid `start=60`).
+- [x] Fix frontend timestamp rendering (treat timestamp as UnixMilli).
+- [x] Fix node realtime metric speed field compatibility (support snake_case speed fields).
+- [x] Fix SQLite contract hang by ensuring tunnel-entry precheck uses tx-safe DB reads (no nested connection acquisition).
+- [x] Ensure monitoring contract tests pass.
+
+### Phase 2: Semantics Alignment (Decide + Implement)
+- [x] Decide "service monitors run where":
+  - Option B: node-executed when `nodeId > 0` (chosen)
+- [ ] Define interval semantics:
+  - Per-monitor next-run scheduling vs global scan loop
+  - Backoff on failures
+  - Maximum monitors + runtime cost guardrails
+- [ ] Standardize API type for `success`:
+  - Keep int for backward compatibility, or
+  - Return boolean in API responses (DTO) while storing int in DB
+
+### Phase 2.1: Partial Implementation (No Semantics Decision Yet)
+- [x] Honor `intervalSec` best-effort in panel-side checker (min cadence still bound by global loop).
+
+### Phase 2.2: Node-Executed Checks
+- [x] Add a WebSocket command for node-executed monitor checks (`ServiceMonitorCheck`).
+- [x] Panel health checker dispatches checks to the specified node when `nodeId > 0`.
+- [x] Allow unrestricted targets by policy; restrict monitoring endpoints to admin + explicitly authorized users.
+- [x] Remove HTTP checks; service monitoring supports only `tcp` and `icmp`.
+
+### Phase 3: Hardening + Performance
+- [x] Add query limits/guards for metrics endpoints (max range, max rows) to avoid accidental full-history pulls.
+- [ ] Consider indexing review and retention configurability (env or config table).
+- [ ] Review concurrency: ingestion buffer flush goroutine spawning and DB write pressure.
+- [x] Add minimal UI affordances: time range selector, empty/error states, and service monitor run/results UI.
+- [x] Ensure monitoring UI works for authorized non-admin users (dedicated `/monitor` page; no reliance on admin-only `/node/*`).
+
+### Phase 4: Hygiene
+- [x] Add `.entire/metadata/` to `.gitignore` (should never be committed).
+- [ ] Add a short developer note in docs/README if needed (API endpoints + semantics).
+
+## Test Plan
+Backend:
+```bash
+cd go-backend && go test ./... -count=1
+cd go-backend && go test ./tests/contract -count=1 -timeout 120s
+```
+
+Agent fork:
+```bash
+cd go-gost/x && go test ./... -count=1
+```
+
+Frontend:
+```bash
+cd vite-frontend && npm run build
+```
+
+## Notes
+- Node-executed checks can be used for internal probing by design; access is restricted to administrators.

plans/038-monitoring-bugfixes-and-optimizations.md

@@ -0,0 +1,59 @@
+# 038 - Monitoring Bug Fixes + Optimizations
+
+## Context
+Monitoring in FLVX currently spans:
+- Agent -> panel WebSocket realtime system metrics (CPU/mem/disk/net/load/conns)
+- Panel-side ingestion + retention pruning (`node_metric`)
+- Service monitors (TCP/ICMP) with scheduled checks + stored results
+- Frontend monitor page (`/monitor`) with charts + monitor CRUD/run/results
+
+While the feature set works end-to-end, there are a few correctness footguns and a couple of obvious performance hot spots (agent-side sampling cost and frontend N+1 polling patterns).
+
+## Goals
+- Service monitor updates do not accidentally clear `nodeId` / `enabled` when fields are omitted.
+- Checker cadence is explicit (intervals below the scan cadence are clamped / best-effort).
+- Reduce frontend requests for service monitor status (avoid per-monitor polling).
+- Reduce agent sampling overhead and DB write volume without breaking UI expectations.
+- Avoid misclassifying arbitrary JSON as a metric message on the WS channel.
+
+## Non-goals
+- A full scheduler (per-monitor next-run queue, jitter/backoff, concurrency budgets).
+- Alerting/notifications.
+- Implementing full tunnel-metrics ingestion (connections/errors/latency) beyond current endpoints.
+
+## Checklist
+
+### Phase 1: Backend Correctness + Hardening
+- [x] Make `/api/v1/monitor/services/update` treat `nodeId` and `enabled` as optional fields (no accidental zeroing).
+- [x] Clamp `intervalSec` to a minimum that matches the checker scan cadence (and apply the same clamp in the checker).
+- [x] Add `GET /api/v1/monitor/services/latest-results` returning the latest result per monitor (for frontend list rendering).
+- [x] WS metric parsing: only treat messages as metrics when they look like a system-metric payload.
+
+### Phase 2: Frontend UX + Request Reduction
+- [x] Fix “立即检查” toast severity (failure should be an error toast).
+- [x] Use `latest-results` endpoint to render service monitor status without N+1 polling.
+- [x] Add a small hint when chart data is truncated by backend row limits.
+
+### Phase 3: Agent Sampling Optimizations
+- [x] Reduce default WS metric send interval (2s -> 5s).
+- [x] Make CPU sampling non-blocking and cache heavy metrics (e.g. connection counts) to reduce per-sample cost.
+
+## Test Plan
+Backend:
+```bash
+cd go-backend && go test ./... -count=1
+```
+
+Agent fork:
+```bash
+cd go-gost/x && go test ./... -count=1
+```
+
+Frontend (best-effort in this environment):
+```bash
+cd vite-frontend && npm run build
+```
+
+## Rollout Notes
+- Agent sampling interval change reduces metric resolution and DB growth; charts remain usable and realtime UI remains responsive.
+- Existing monitors with very small `intervalSec` are best-effort; effective cadence remains bounded by the checker scan loop.

plans/039-monitoring-tunnel-metrics-ingestion.md

@@ -0,0 +1,41 @@
+# 039 - Monitoring: Tunnel Metrics Ingestion
+
+## Context
+The `/monitor` UI includes tunnel metric charts backed by:
+- `GET /api/v1/monitor/tunnels` (list)
+- `GET /api/v1/monitor/tunnels/:id/metrics` (timeseries)
+
+The backend has the `tunnel_metric` table + query endpoints, but there is no production code path that writes tunnel metrics. As a result, tunnel charts are typically empty.
+
+## Goal
+Persist tunnel traffic timeseries based on agent flow uploads (`POST /flow/upload`).
+
+## Scope
+- Write `tunnel_metric` rows from flow uploads.
+- Keep write volume bounded (aggregate per minute).
+- Provide contract coverage that a flow upload creates tunnel metrics.
+
+## Non-goals
+- Populate connections/errors/latency for tunnel metrics (remain 0 for now).
+- A full aggregation pipeline across multiple nodes per tunnel at query time.
+
+UI note:
+- The tunnel chart only exposes the Traffic view for now; other tabs are hidden.
+
+## Design
+- Agent reports per-service traffic deltas via `/flow/upload` with items `{n,u,d}`.
+- Backend derives `forward_id` from service name (`<forwardID>_<userID>_<userTunnelID>[...suffix]`).
+- Map `forward_id -> tunnel_id` in batch.
+- Aggregate per `(node_id, tunnel_id, minute_bucket)` and upsert into `tunnel_metric` using an UPDATE-then-INSERT fallback.
+
+## Checklist
+- [x] Add repository helper: map forward IDs to tunnel IDs.
+- [x] Add repository helper: upsert per-minute tunnel metric buckets.
+- [x] Extend `/flow/upload` handler to record tunnel metrics from incoming items.
+- [x] Add contract test verifying flow upload produces tunnel metrics.
+- [x] Run backend tests.
+
+## Test Plan
+```bash
+cd go-backend && go test ./... -count=1
+```

plans/040-service-monitor-configurable-limits-and-ui-hints.md

@@ -0,0 +1,40 @@
+# 040 - Service Monitor Limits Config + UI Hints
+
+## Goal
+Make service monitor interval/timeout constraints configurable (instead of hard-coded clamps) and make the UI clearly communicate the effective limits.
+
+## Current Pain
+- Backend clamps `intervalSec` and `timeoutSec` with hard-coded constants.
+- Checker scan cadence is also hard-coded, so users can set values that will never be honored.
+- Frontend form does not explain allowed ranges or why values may change.
+
+## Approach
+- Add frontend-configurable limits stored in `vite_config` (with safe defaults matching current behavior).
+- Backend always normalizes using the configured limits.
+- Expose the current limits via a monitoring endpoint so the UI can render accurate hints.
+- Frontend shows min/max and validates before submit.
+- Admin can edit the limits on `/config`.
+
+## Config Keys (vite_config)
+- `service_monitor_checker_scan_interval_sec` (default: 30)
+- `service_monitor_min_interval_sec` (default: 30; auto-raised to at least scan interval)
+- `service_monitor_default_interval_sec` (default: 60)
+- `service_monitor_min_timeout_sec` (default: 1)
+- `service_monitor_default_timeout_sec` (default: 5)
+- `service_monitor_max_timeout_sec` (default: 60)
+
+## Checklist
+Backend:
+- [x] Introduce shared `ServiceMonitorLimits` config loader.
+- [x] Use limits for create/update normalization.
+- [x] Use limits in checker (scan interval + timeout clamp).
+- [x] Add `GET /api/v1/monitor/services/limits` to return current limits.
+
+Frontend:
+- [x] Fetch limits once and render input descriptions.
+- [x] Validate interval/timeout client-side and show inline errors.
+- [x] Add `/config` items to edit the `vite_config` keys.
+
+Verification:
+- [x] `cd go-backend && go test ./... -count=1`
+- [x] `cd vite-frontend && npm run lint && npm run build`

plans/041-monitoring-reliability-realtime-and-ux-hardening.md

@@ -0,0 +1,224 @@
+# 041 - Monitoring Reliability, Realtime, and UX Hardening
+
+## Context
+Current monitoring support in FLVX already covers three major areas:
+- Node runtime metrics from agent WebSocket telemetry, buffered into `node_metric`, exposed by `/api/v1/monitor/nodes*`, and rendered on `/monitor`.
+- Tunnel metrics derived from `/flow/upload`, stored in `tunnel_metric`, exposed by `/api/v1/monitor/tunnels*`, and rendered on `/monitor`.
+- Service monitoring for `tcp` and `icmp`, including CRUD, scheduled checks, manual run, history, and non-admin authorization via `monitor_permission`.
+
+The feature set is usable, but the audit found several correctness, reliability, and UX gaps:
+- The monitor page is not truly realtime and can lag DB ingestion by tens of seconds.
+- Tunnel metrics are only partially implemented and are not aggregated correctly for multi-node tunnels.
+- Some monitoring writes fail silently, which can hide data-loss and retention issues.
+- Service monitor scheduling is functional but too naive for larger monitor sets and restart scenarios.
+- The monitoring UI exposes incomplete semantics, weak freshness cues, and inconsistent permission/error affordances.
+- Several monitoring endpoints and edge cases still lack direct automated coverage.
+
+This plan collects all currently known monitoring follow-up work into one implementation document.
+
+## Goals
+- Make node monitoring data freshness explicit and reduce stale or misleading chart behavior.
+- Make tunnel metrics correct for multi-node tunnels and align schema/query/UI semantics.
+- Harden service monitor scheduling, persistence, and cleanup behavior.
+- Improve observability so monitoring ingestion and result writes never fail silently.
+- Upgrade the monitoring UI so operators can understand status, freshness, scope, and failures at a glance.
+- Expand automated coverage for all monitoring APIs and the highest-risk aggregation/scheduler cases.
+
+## Non-goals
+- Add a full alerting or notification pipeline.
+- Add brand-new monitor protocols beyond the current `tcp` and `icmp` scope.
+- Build a large analytics dashboard outside the existing monitoring page structure.
+- Introduce frontend test infrastructure for broad component/unit testing unless required by an implementation step.
+
+## Audit Findings To Address
+- Node metrics on `/monitor` are DB-polled rather than realtime-streamed.
+- Node metrics are buffered for 30s, so charts can lag behind observed node state.
+- Tunnel metrics are stored per `(tunnel_id, node_id, timestamp)` but queried and rendered as if they were already tunnel-level aggregates.
+- Tunnel metric minute-bucket upsert uses update-then-insert without uniqueness guarantees.
+- Tunnel metrics only populate `bytesIn` and `bytesOut`; `connections`, `errors`, and `avgLatencyMs` are placeholder values.
+- Node/tunnel/service-monitor writes can fail silently due to ignored errors.
+- Service monitor scheduler is serial and uses in-memory `lastRun`, causing restart skew and slow-monitor head-of-line blocking.
+- Deleting a service monitor does not clean up related historical results.
+- `expectedCode` exists on the model but is not implemented in behavior or UX.
+- The monitoring page/menu is exposed before permission is known, leading to avoidable denied-entry UX.
+- Service monitor UI does not clearly show latest result freshness, last check time, or whether a displayed row is stale.
+- Chart labels and units are not operator-friendly for long time windows and network-heavy views.
+- Monitoring API coverage is incomplete for list, permission, limits, latest-results, multi-node tunnel aggregation, and concurrency paths.
+
+## Design
+
+### 1. Node Monitoring Freshness and Realtime Model
+- Keep the existing WebSocket node telemetry stream as the source of live state.
+- Preserve DB-backed metrics queries for historical charts, but explicitly separate them from live cards/status.
+- On `/monitor`, add a lightweight realtime subscription path reusing the existing admin WebSocket feed already used by the node page.
+- Use realtime events for:
+  - node online/offline state,
+  - a small “latest value” strip or summary above charts,
+  - freshness timestamp display.
+- Keep charts historical and DB-backed by default, but add a visible freshness hint such as:
+  - `历史图表，最近落库延迟约 0-30s`, or
+  - `最近入库时间: ...`.
+- Do not remove buffered ingestion immediately; first make lag transparent in UI and observable in logs/metrics.
+- Optional second-step optimization: reduce flush interval or add a bounded flush-on-latest-view mode if DB pressure remains acceptable.
+
+### 2. Tunnel Metrics Data Model and Query Semantics
+- Decide and document one API contract:
+  - `GET /api/v1/monitor/tunnels/:id/metrics` must return tunnel-level aggregated series for the selected time range, not raw per-node rows.
+- Keep storage per `(tunnel_id, node_id, timestamp)` because it is useful for future drill-down.
+- Change query behavior so the tunnel metrics endpoint aggregates rows by timestamp across all nodes for the tunnel:
+  - `SUM(bytes_in)`,
+  - `SUM(bytes_out)`,
+  - `SUM(connections)`,
+  - `SUM(errors)`,
+  - `AVG` or weighted-average strategy for latency, if latency is later implemented.
+- Return a single point per timestamp to the frontend.
+- If future node drill-down is needed, add a separate endpoint rather than mixing per-node rows into the current chart API.
+
+### 3. Tunnel Metric Upsert Safety
+- Replace the current update-then-insert fallback with a uniqueness-backed upsert strategy.
+- Add a unique index on `(tunnel_id, node_id, timestamp)`.
+- Implement DB-safe upsert behavior compatible with SQLite and PostgreSQL via GORM clauses or equivalent dialect-safe SQL.
+- Preserve additive semantics for traffic counters inside the bucket.
+- Add concurrency coverage proving that parallel uploads for the same bucket do not create duplicate rows.
+
+### 4. Tunnel Metric Scope Clarification
+- Short term: make the UI and API explicitly traffic-only where the backend only has traffic truth.
+- Remove or hide unsupported tunnel metric modes from the current UX until real data exists.
+- Do not expose zero-filled placeholders as if they were valid telemetry.
+- Keep schema fields if future support is planned, but label them as unimplemented in code comments and avoid rendering them as live features.
+
+### 5. Service Monitor Scheduler Hardening
+- Replace the current fully serial best-effort loop with bounded concurrency:
+  - retain a global scan loop or next-run calculation,
+  - collect monitors due for execution,
+  - execute them with a configurable worker limit,
+  - avoid one slow node/target delaying all others.
+- Move scheduling semantics from pure in-memory `lastRun` toward persisted or history-derived next-run safety:
+  - on restart, do not fire an uncontrolled burst for all monitors if they just ran;
+  - use latest persisted result timestamp or a persisted scheduler state to calculate due-ness.
+- Keep interval clamping behavior aligned with configured limits.
+- Continue supporting local panel execution for `tcp` and node execution for `tcp`/`icmp`.
+
+### 6. Service Monitor Data Lifecycle
+- Define monitor deletion semantics explicitly:
+  - either cascade-delete historical `service_monitor_result` rows when a monitor is deleted, or
+  - retain them intentionally and exclude orphan rows from latest/list endpoints.
+- Preferred approach: delete associated results with the monitor so the UI/API model stays simple.
+- Either implement `expectedCode` fully or remove it from the model/API surface for now.
+- Because service monitoring currently supports only `tcp` and `icmp`, and no HTTP checks are implemented, `expectedCode` should likely be removed from the data model/API until a real HTTP monitor exists.
+
+### 7. Observability and Failure Handling
+- Stop swallowing monitoring persistence errors.
+- For all node/tunnel/service-monitor writes:
+  - log structured errors with entity identifiers and operation names,
+  - increment internal counters if an existing metrics/logging primitive exists,
+  - keep request/loop behavior resilient, but make failure visible.
+- Apply this to:
+  - node metric batch flush,
+  - tunnel metric bucket writes,
+  - scheduled service monitor result writes,
+  - manual service monitor result writes,
+  - pruning failures.
+- Avoid user-facing hard failures for background ingestion, but surface operational diagnostics in logs.
+
+### 8. Monitoring UI Semantics and Navigation
+- Keep `/monitor` accessible only to authenticated users, but improve pre-entry affordances:
+  - hide or disable the navigation item for users without monitor permission when role/permission data is known,
+  - or show a locked state with explanation instead of allowing a full denied page transition.
+- Preserve the backend permission check as the source of truth.
+- On the page itself, upgrade semantics:
+  - distinguish `enabled/disabled` from `healthy/unhealthy` in the service monitor table,
+  - show `last checked at`,
+  - show `latest result` separately from monitor switch state,
+  - show whether the latest displayed result is stale.
+- Add an at-a-glance monitoring summary near the top:
+  - online/offline node counts,
+  - monitors healthy/unhealthy/disabled counts,
+  - latest data freshness text.
+
+### 9. Monitoring UI Readability Improvements
+- Improve chart axis labeling for long ranges:
+  - use date + time formatting for 24h windows,
+  - keep shorter labels for short ranges.
+- Format bytes and rates into human-readable units (`KB/s`, `MB/s`, `GB`) instead of raw integers.
+- Expose clear empty states and fetch-error states instead of silent failures.
+- Make tunnel charts explicitly say `流量趋势` if only traffic is supported.
+- Show `statusCode` in the results modal only if the corresponding monitor type ever uses it; otherwise omit it.
+
+### 10. API and Test Coverage Expansion
+- Add contract coverage for:
+  - `GET /api/v1/monitor/nodes`,
+  - `GET /api/v1/monitor/tunnels`,
+  - `GET /api/v1/monitor/services/latest-results`,
+  - `GET /api/v1/monitor/services/limits`,
+  - monitor permission list/assign/remove endpoints.
+- Add backend tests for:
+  - multi-node tunnel aggregation returning one point per timestamp,
+  - tunnel upsert concurrency safety,
+  - service monitor restart/due scheduling semantics,
+  - service monitor delete cleanup behavior,
+  - background write failure logging where practical.
+- Keep existing build/test targets green for backend, agent, and frontend.
+
+## Checklist
+
+### Phase 1: Correctness Fixes
+- [x] Aggregate `GET /api/v1/monitor/tunnels/:id/metrics` by timestamp across all node rows for the selected tunnel.
+- [x] Add a unique index for tunnel metric minute buckets and replace the race-prone update-then-insert flow with safe upsert logic.
+- [x] Stop exposing unsupported tunnel metric dimensions (`connections`, `errors`, `latency`) as active UI features while the backend still stores placeholders.
+- [x] Define and implement service monitor deletion cleanup so history does not leave orphaned result rows.
+- [x] Remove or fully implement `expectedCode`; do not keep dead monitoring fields in the live API/model contract.
+
+### Phase 2: Reliability and Scheduling
+- [x] Replace serial service monitor execution with bounded-concurrency execution for due monitors.
+- [x] Persist or derive service monitor next-run behavior so process restarts do not trigger uncontrolled immediate reruns.
+- [x] Ensure monitor scheduler semantics remain aligned with configured min interval and checker scan cadence.
+- [x] Add structured logging for all monitoring persistence failures and prune failures.
+- [x] Audit all ignored monitoring write errors and convert them into visible operational diagnostics.
+
+### Phase 3: Realtime and Freshness UX
+- [x] Reuse the existing admin WebSocket stream on `/monitor` for live node status and latest-value freshness indicators.
+- [x] Add visible chart freshness metadata so users know historical charts are DB-backed and may lag ingestion.
+- [x] Decide whether to reduce node metric flush interval after instrumentation confirms acceptable DB impact (decision: keep 30s default for now; revisit after observing DB write rate and UI staleness in production).
+- [x] Add a monitoring summary strip showing online nodes, unhealthy monitors, and latest data time.
+
+### Phase 4: Monitoring Page UX Cleanup
+- [x] Separate service monitor switch state (`启用/禁用`) from probe health (`成功/失败`).
+- [x] Add `last checked at` to the service monitor list and results modal context.
+- [x] Mark stale results clearly when the latest result is older than the configured interval budget.
+- [x] Format traffic and speed values in human-readable units instead of raw bytes.
+- [x] Improve chart time labels for 24h windows to include date context.
+- [x] Replace silent frontend fetch failures with explicit inline error or toast handling.
+- [x] Rename or relabel tunnel chart UI to make its current scope unambiguous.
+
+### Phase 5: Permission and Navigation UX
+- [x] Avoid showing a fully interactive monitor nav entry to users who lack monitoring permission once permission state is known.
+- [x] Preserve backend authorization as the final gate and keep denied responses intact.
+- [x] Improve denied-state copy so users understand whether they need admin grant vs role change.
+
+### Phase 6: Automated Coverage
+- [x] Add contract tests for monitor node list, tunnel list, latest service monitor results, limits, and permission endpoints.
+- [x] Add contract or repository tests for multi-node tunnel aggregation correctness.
+- [x] Add concurrency tests for tunnel metric upsert safety.
+- [x] Add scheduler tests covering restart behavior, due monitor selection, and slow-monitor isolation.
+- [x] Keep existing monitoring contract tests passing after all changes.
+
+## Implementation Notes
+- Prefer backward-compatible API changes where possible, but favor correctness over preserving misleading tunnel metric semantics.
+- Do not introduce a fake realtime chart if the data source remains DB-backed; label it honestly.
+- If permission visibility requires an extra frontend capability call, keep it lightweight and cacheable.
+- If schema/index changes are introduced, they must remain compatible with both SQLite and PostgreSQL.
+
+## Final Verification Targets
+- [x] `GET /api/v1/monitor/tunnels/:id/metrics` returns one aggregated point per timestamp even when multiple nodes report the same tunnel bucket.
+- [x] Parallel `/flow/upload` calls for the same tunnel/node/minute do not create duplicate bucket rows.
+- [x] `/monitor` clearly distinguishes live state from historical persisted charts and surfaces data freshness to the operator.
+- [x] Service monitor list shows enabled state, latest health result, latest check time, and stale-state semantics correctly.
+- [x] Deleting a service monitor no longer leaves dangling historical data in list-facing APIs.
+- [x] Monitoring ingestion/result write failures are visible in logs and no longer fail silently.
+- [x] Non-admin users without monitoring permission do not get a confusing monitor-entry experience, while granted users continue to access monitoring successfully.
+- [x] Backend monitoring contract tests pass.
+- [x] New repository/scheduler tests pass.
+- [x] `cd go-backend && go test ./... -count=1` passes.
+- [x] `cd go-gost/x && go test ./socket/... -count=1` passes.
+- [x] `cd vite-frontend && npm run build` passes.

plans/045-release-2-1-8.md

@@ -0,0 +1,10 @@
+# PLAN: Release 2.1.8
+
+## Overview
+Synchronize with the main branch and release a new tag `2.1.8`.
+
+## Tasks
+- [x] Pull latest changes from `main`
+- [x] Update `AGENTS.md` with new tag and current commit hash (PR #337 created and set to auto-merge)
+- [x] Create git tag `2.1.8`
+- [x] Push git tag `2.1.8` to origin

vite-frontend/src/App.tsx

@@ -4,6 +4,7 @@ import { useEffect } from "react";
 import IndexPage from "@/pages/index";
 import ChangePasswordPage from "@/pages/change-password";
 import DashboardPage from "@/pages/dashboard";
+import MonitorPage from "@/pages/monitor";
 import ForwardPage from "@/pages/forward";
 import TunnelPage from "@/pages/tunnel";
 import NodePage from "@/pages/node";
@@ -122,6 +123,14 @@ function App() {
         }
         path="/dashboard"
       />
+      <Route
+        element={
+          <ProtectedRoute>
+            <MonitorPage />
+          </ProtectedRoute>
+        }
+        path="/monitor"
+      />
       <Route
         element={
           <ProtectedRoute>

vite-frontend/src/api/index.ts

@@ -30,6 +30,16 @@ import type {
   SpeedLimitMutationPayload,
   UpdatePasswordPayload,
   BackupImportPayload,
+  NodeMetricApiItem,
+  TunnelMetricApiItem,
+  ServiceMonitorApiItem,
+  ServiceMonitorResultApiItem,
+  ServiceMonitorLimitsApiData,
+  ServiceMonitorMutationPayload,
+  MonitorNodeApiItem,
+  MonitorTunnelApiItem,
+  MonitorPermissionApiItem,
+  MonitorAccessApiData,
 } from "./types";
 
 import axios from "axios";
@@ -402,3 +412,85 @@ export const getAnnouncement = () =>
   Network.get<AnnouncementData>("/announcement/get");
 export const updateAnnouncement = (data: AnnouncementData) =>
   Network.post("/announcement/update", data);
+
+export const getNodeMetrics = (
+  nodeId: number,
+  start?: number,
+  end?: number,
+) => {
+  const params: Record<string, string> = {};
+
+  if (start) params.start = String(start);
+  if (end) params.end = String(end);
+
+  return Network.get<NodeMetricApiItem[]>(
+    `/monitor/nodes/${nodeId}/metrics`,
+    params,
+  );
+};
+
+export const getNodeMetricsLatest = (nodeId: number) =>
+  Network.get<NodeMetricApiItem>(`/monitor/nodes/${nodeId}/metrics/latest`);
+
+export const getTunnelMetrics = (
+  tunnelId: number,
+  start?: number,
+  end?: number,
+) => {
+  const params: Record<string, string> = {};
+
+  if (start) params.start = String(start);
+  if (end) params.end = String(end);
+
+  return Network.get<TunnelMetricApiItem[]>(
+    `/monitor/tunnels/${tunnelId}/metrics`,
+    params,
+  );
+};
+
+export const getMonitorTunnels = () =>
+  Network.get<MonitorTunnelApiItem[]>("/monitor/tunnels");
+
+export const getServiceMonitorList = () =>
+  Network.get<ServiceMonitorApiItem[]>("/monitor/services");
+
+export const getServiceMonitorLimits = () =>
+  Network.get<ServiceMonitorLimitsApiData>("/monitor/services/limits");
+
+export const createServiceMonitor = (data: ServiceMonitorMutationPayload) =>
+  Network.post<ServiceMonitorApiItem>("/monitor/services/create", data);
+
+export const updateServiceMonitor = (data: ServiceMonitorMutationPayload) =>
+  Network.post<ServiceMonitorApiItem>("/monitor/services/update", data);
+
+export const deleteServiceMonitor = (id: number) =>
+  Network.post("/monitor/services/delete", { id });
+
+export const getServiceMonitorResults = (monitorId: number, limit = 100) =>
+  Network.get<ServiceMonitorResultApiItem[]>(
+    `/monitor/services/${monitorId}/results`,
+    { limit: String(limit) },
+  );
+
+export const getServiceMonitorLatestResults = () =>
+  Network.get<ServiceMonitorResultApiItem[]>(
+    "/monitor/services/latest-results",
+  );
+
+export const runServiceMonitor = (id: number) =>
+  Network.post<ServiceMonitorResultApiItem>("/monitor/services/run", { id });
+
+export const getMonitorNodes = () =>
+  Network.get<MonitorNodeApiItem[]>("/monitor/nodes");
+
+export const getMonitorAccess = () =>
+  Network.get<MonitorAccessApiData>("/monitor/access");
+
+export const getMonitorPermissionList = () =>
+  Network.get<MonitorPermissionApiItem[]>("/monitor/permission/list");
+
+export const assignMonitorPermission = (userId: number) =>
+  Network.post("/monitor/permission/assign", { userId });
+
+export const removeMonitorPermission = (userId: number) =>
+  Network.post("/monitor/permission/remove", { userId });

vite-frontend/src/api/types.ts

@@ -385,3 +385,105 @@ export interface BackupImportPayload {
   types: string[];
   [key: string]: unknown;
 }
+
+export interface NodeMetricApiItem {
+  id: number;
+  nodeId: number;
+  timestamp: number;
+  cpuUsage: number;
+  memoryUsage: number;
+  diskUsage: number;
+  netInBytes: number;
+  netOutBytes: number;
+  netInSpeed: number;
+  netOutSpeed: number;
+  load1: number;
+  load5: number;
+  load15: number;
+  tcpConns: number;
+  udpConns: number;
+  uptime: number;
+}
+
+export interface TunnelMetricApiItem {
+  id: number;
+  tunnelId: number;
+  nodeId: number;
+  timestamp: number;
+  bytesIn: number;
+  bytesOut: number;
+  connections: number;
+  errors: number;
+  avgLatencyMs: number;
+}
+
+export interface ServiceMonitorApiItem {
+  id: number;
+  name: string;
+  // Keep as string for forward-compatibility.
+  type: string;
+  target: string;
+  intervalSec: number;
+  timeoutSec: number;
+  nodeId: number;
+  enabled: number;
+  createdTime: number;
+  updatedTime: number;
+}
+
+export interface ServiceMonitorResultApiItem {
+  id: number;
+  monitorId: number;
+  timestamp: number;
+  success: number;
+  latencyMs: number;
+  statusCode: number;
+  errorMessage: string;
+}
+
+export interface ServiceMonitorMutationPayload {
+  id?: number;
+  name: string;
+  type: "tcp" | "icmp";
+  target: string;
+  intervalSec?: number;
+  timeoutSec?: number;
+  nodeId?: number;
+  enabled?: number;
+}
+
+export interface ServiceMonitorLimitsApiData {
+  checkerScanIntervalSec: number;
+  minIntervalSec: number;
+  defaultIntervalSec: number;
+  minTimeoutSec: number;
+  defaultTimeoutSec: number;
+  maxTimeoutSec: number;
+}
+
+export interface MonitorNodeApiItem {
+  id: number;
+  inx: number;
+  name: string;
+  status: number;
+  updatedTime: number;
+}
+
+export interface MonitorTunnelApiItem {
+  id: number;
+  inx: number;
+  name: string;
+  status: number;
+  updatedTime: number;
+}
+
+export interface MonitorPermissionApiItem {
+  id: number;
+  userId: number;
+  createdTime: number;
+}
+
+export interface MonitorAccessApiData {
+  allowed: boolean;
+  reason?: string;
+}

vite-frontend/src/layouts/admin.tsx

@@ -21,7 +21,7 @@ import {
 import { Input } from "@/shadcn-bridge/heroui/input";
 import { BrandLogo } from "@/components/brand-logo";
 import { VersionFooter } from "@/components/version-footer";
-import { updatePassword } from "@/api";
+import { getMonitorAccess, updatePassword } from "@/api";
 import { safeLogout } from "@/utils/logout";
 import { siteConfig } from "@/config/site";
 import { useMobileBreakpoint } from "@/hooks/useMobileBreakpoint";
@@ -56,6 +56,10 @@ export default function AdminLayout({
   );
   const [username, setUsername] = useState("");
   const [isAdmin, setIsAdmin] = useState(false);
+  const [monitorAllowed, setMonitorAllowed] = useState<boolean | null>(null);
+  const [monitorAccessReason, setMonitorAccessReason] = useState<string | null>(
+    null,
+  );
   const [passwordLoading, setPasswordLoading] = useState(false);
   const [passwordForm, setPasswordForm] = useState<PasswordForm>({
     newUsername: "",
@@ -117,6 +121,19 @@ export default function AdminLayout({
       ),
       adminOnly: true,
     },
+    {
+      path: "/monitor",
+      label: "监控",
+      icon: (
+        <svg className="w-5 h-5" fill="currentColor" viewBox="0 0 20 20">
+          <path
+            clipRule="evenodd"
+            d="M3 3a1 1 0 000 2v11a1 1 0 001 1h13a1 1 0 100-2H5V5a1 1 0 00-1-1H3zm13.707 4.293a1 1 0 00-1.414 0L12 10.586 10.707 9.293a1 1 0 00-1.414 0L7 11.586l-1.293-1.293a1 1 0 10-1.414 1.414l2 2a1 1 0 001.414 0L10 11.414l1.293 1.293a1 1 0 001.414 0l3-3a1 1 0 000-1.414z"
+            fillRule="evenodd"
+          />
+        </svg>
+      ),
+    },
     {
       path: "/limit",
       label: "限速",
@@ -184,6 +201,41 @@ export default function AdminLayout({
 
     setUsername(name);
     setIsAdmin(adminFlag);
+
+    // Monitor permission is not strictly role-based; non-admin users may be
+    // granted access explicitly. Fetch a lightweight capability flag so we can
+    // avoid a confusing 403 navigation.
+    if (adminFlag) {
+      setMonitorAllowed(true);
+      setMonitorAccessReason(null);
+      return;
+    }
+
+    let cancelled = false;
+    (async () => {
+      try {
+        const res = await getMonitorAccess();
+        if (cancelled) return;
+        if (res.code === 0 && res.data) {
+          setMonitorAllowed(Boolean(res.data.allowed));
+          setMonitorAccessReason(
+            res.data.allowed ? null : (res.data.reason || null),
+          );
+          return;
+        }
+        // Fail open to preserve legacy navigation behavior.
+        setMonitorAllowed(true);
+        setMonitorAccessReason(null);
+      } catch {
+        if (cancelled) return;
+        setMonitorAllowed(true);
+        setMonitorAccessReason(null);
+      }
+    })();
+
+    return () => {
+      cancelled = true;
+    };
   }, []);
 
   useEffect(() => {
@@ -218,6 +270,23 @@ export default function AdminLayout({
 
   // 菜单点击处理
   const handleMenuClick = (path: string) => {
+    if (path === "/monitor" && monitorAllowed !== true) {
+      if (monitorAllowed == null) {
+        toast("正在检查监控权限，请稍后重试");
+
+        return;
+      }
+
+      const hint =
+        monitorAccessReason === "need_admin_grant"
+          ? "暂无监控权限，请联系管理员在用户页面授予监控权限"
+          : "暂无监控权限，请联系管理员授权";
+
+      toast.error(hint);
+
+      return;
+    }
+
     navigate(path);
     if (isMobile) {
       hideMobileMenu();
@@ -346,6 +415,8 @@ export default function AdminLayout({
           <ul className="space-y-1">
             {filteredMenuItems.map((item) => {
               const isActive = location.pathname === item.path;
+              const isMonitor = item.path === "/monitor";
+              const isMonitorBlocked = isMonitor && monitorAllowed !== true;
 
               return (
                 <li key={item.path}>
@@ -353,13 +424,23 @@ export default function AdminLayout({
                     className={`
                        w-full flex items-center p-2 rounded-lg text-left
                        relative min-h-[44px] overflow-hidden transition-colors
+                       ${isMonitorBlocked ? "opacity-60" : ""}
                        ${
                          isActive
                            ? "text-primary-600 dark:text-primary-300"
-                           : "text-gray-700 dark:text-gray-200"
+                            : isMonitorBlocked
+                              ? "text-gray-500 dark:text-gray-400"
+                              : "text-gray-700 dark:text-gray-200"
                        }
                      `}
-                    title={isCollapsed ? item.label : undefined}
+                    aria-disabled={isMonitorBlocked}
+                    title={
+                      isCollapsed
+                        ? isMonitorBlocked
+                          ? `${item.label} (无权限)`
+                          : item.label
+                        : undefined
+                    }
                     transition={{ duration: 0.15 }}
                     onClick={() => handleMenuClick(item.path)}
                   >

vite-frontend/src/layouts/h5.tsx

@@ -1,8 +1,10 @@
 import React, { useState, useEffect } from "react";
 import { useNavigate, useLocation } from "react-router-dom";
+import toast from "react-hot-toast";
 
 import { BrandLogo } from "@/components/brand-logo";
 import { siteConfig } from "@/config/site";
+import { getMonitorAccess } from "@/api";
 import { getAdminFlag } from "@/utils/session";
 import { useScrollTopOnPathChange } from "@/hooks/useScrollTopOnPathChange";
 
@@ -17,6 +19,10 @@ export default function H5Layout({ children }: { children: React.ReactNode }) {
   const navigate = useNavigate();
   const location = useLocation();
   const [isAdmin, setIsAdmin] = useState(false);
+  const [monitorAllowed, setMonitorAllowed] = useState<boolean | null>(null);
+  const [monitorAccessReason, setMonitorAccessReason] = useState<string | null>(
+    null,
+  );
 
   useScrollTopOnPathChange();
 
@@ -72,6 +78,19 @@ export default function H5Layout({ children }: { children: React.ReactNode }) {
       ),
       adminOnly: true,
     },
+    {
+      path: "/monitor",
+      label: "监控",
+      icon: (
+        <svg className="w-6 h-6" fill="currentColor" viewBox="0 0 20 20">
+          <path
+            clipRule="evenodd"
+            d="M3 3a1 1 0 000 2v11a1 1 0 001 1h13a1 1 0 100-2H5V5a1 1 0 00-1-1H3zm13.707 4.293a1 1 0 00-1.414 0L12 10.586 10.707 9.293a1 1 0 00-1.414 0L7 11.586l-1.293-1.293a1 1 0 10-1.414 1.414l2 2a1 1 0 001.414 0L10 11.414l1.293 1.293a1 1 0 001.414 0l3-3a1 1 0 000-1.414z"
+            fillRule="evenodd"
+          />
+        </svg>
+      ),
+    },
     {
       path: "/profile",
       label: "我的",
@@ -84,11 +103,60 @@ export default function H5Layout({ children }: { children: React.ReactNode }) {
   ];
 
   useEffect(() => {
-    setIsAdmin(getAdminFlag());
+    const adminFlag = getAdminFlag();
+
+    setIsAdmin(adminFlag);
+    if (adminFlag) {
+      setMonitorAllowed(true);
+      setMonitorAccessReason(null);
+
+      return;
+    }
+
+    let cancelled = false;
+    (async () => {
+      try {
+        const res = await getMonitorAccess();
+        if (cancelled) return;
+        if (res.code === 0 && res.data) {
+          setMonitorAllowed(Boolean(res.data.allowed));
+          setMonitorAccessReason(
+            res.data.allowed ? null : (res.data.reason || null),
+          );
+          return;
+        }
+        setMonitorAllowed(true);
+        setMonitorAccessReason(null);
+      } catch {
+        if (cancelled) return;
+        setMonitorAllowed(true);
+        setMonitorAccessReason(null);
+      }
+    })();
+
+    return () => {
+      cancelled = true;
+    };
   }, []);
 
   // Tab点击处理
   const handleTabClick = (path: string) => {
+    if (path === "/monitor" && monitorAllowed !== true) {
+      if (monitorAllowed == null) {
+        toast("正在检查监控权限，请稍后重试");
+
+        return;
+      }
+
+      const hint =
+        monitorAccessReason === "need_admin_grant"
+          ? "暂无监控权限，请联系管理员授权"
+          : "暂无监控权限";
+
+      toast.error(hint);
+
+      return;
+    }
     navigate(path);
   };
 
@@ -121,6 +189,8 @@ export default function H5Layout({ children }: { children: React.ReactNode }) {
       <nav className="bg-white dark:bg-black border-t border-gray-200 dark:border-gray-600 h-[calc(4rem+var(--safe-area-bottom))] flex-shrink-0 flex items-center justify-around px-2 fixed bottom-0 left-0 right-0 z-30">
         {filteredTabItems.map((item) => {
           const isActive = location.pathname === item.path;
+          const isMonitor = item.path === "/monitor";
+          const isMonitorBlocked = isMonitor && monitorAllowed !== true;
 
           return (
             <button
@@ -128,10 +198,13 @@ export default function H5Layout({ children }: { children: React.ReactNode }) {
               className={`
                 flex flex-col items-center justify-center flex-1 h-full pb-[var(--safe-area-bottom)]
                 transition-colors duration-200 min-h-[44px]
+                ${isMonitorBlocked ? "opacity-60" : ""}
                 ${
                   isActive
                     ? "text-primary-600 dark:text-primary-400"
-                    : "text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-200"
+                    : isMonitorBlocked
+                      ? "text-gray-500 dark:text-gray-400"
+                      : "text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-200"
                 }
               `}
               onClick={() => handleTabClick(item.path)}

vite-frontend/src/pages/monitor.tsx

@@ -0,0 +1,111 @@
+import type { MonitorNodeApiItem } from "@/api/types";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import toast from "react-hot-toast";
+import { RefreshCw } from "lucide-react";
+
+import { AnimatedPage } from "@/components/animated-page";
+import { Button } from "@/shadcn-bridge/heroui/button";
+import { Card, CardBody, CardHeader } from "@/shadcn-bridge/heroui/card";
+import { getMonitorNodes } from "@/api";
+import { MonitorView } from "@/pages/node/monitor-view";
+
+type MonitorNode = {
+  id: number;
+  name: string;
+  connectionStatus: "online" | "offline";
+};
+
+export default function MonitorPage() {
+  const [nodes, setNodes] = useState<MonitorNodeApiItem[]>([]);
+  const [nodesLoading, setNodesLoading] = useState(false);
+  const [nodesError, setNodesError] = useState<string | null>(null);
+
+  const loadNodes = useCallback(async () => {
+    setNodesLoading(true);
+    try {
+      const response = await getMonitorNodes();
+
+      if (response.code === 0 && Array.isArray(response.data)) {
+        setNodesError(null);
+        setNodes(response.data);
+
+        return;
+      }
+
+      if (response.code === 403) {
+        setNodes([]);
+        setNodesError(response.msg || "暂无监控权限，请联系管理员授权");
+
+        return;
+      }
+
+      toast.error(response.msg || "加载节点失败");
+    } catch {
+      toast.error("加载节点失败");
+    } finally {
+      setNodesLoading(false);
+    }
+  }, []);
+
+  useEffect(() => {
+    void loadNodes();
+  }, [loadNodes]);
+
+  useEffect(() => {
+    const timer = window.setInterval(() => {
+      void loadNodes();
+    }, 30_000);
+
+    return () => window.clearInterval(timer);
+  }, [loadNodes]);
+
+  const nodeMap = useMemo(() => {
+    const list: MonitorNode[] = nodes
+      .filter((n) => Number(n.id) > 0)
+      .map((n) => ({
+        id: Number(n.id),
+        name: String(n.name ?? ""),
+        connectionStatus: n.status === 1 ? "online" : "offline",
+      }));
+
+    return new Map<number, MonitorNode>(list.map((n) => [n.id, n]));
+  }, [nodes]);
+
+  return (
+    <AnimatedPage className="px-3 lg:px-6 py-8">
+      <div className="mb-6 space-y-3">
+        <div className="flex items-center justify-between gap-3">
+          <div className="min-w-0">
+            <h2 className="text-xl font-semibold truncate">监控</h2>
+            <div className="text-xs text-default-500 truncate">
+              实时节点状态 + 历史指标图表 + 隧道流量 + 服务监控（TCP/ICMP）
+            </div>
+          </div>
+          <Button
+            isLoading={nodesLoading}
+            size="sm"
+            variant="flat"
+            onPress={loadNodes}
+          >
+            <RefreshCw className="w-4 h-4 mr-1" />
+            刷新节点
+          </Button>
+        </div>
+
+        {nodesError ? (
+          <Card>
+            <CardHeader>
+              <h3 className="text-sm font-semibold">节点列表</h3>
+            </CardHeader>
+            <CardBody>
+              <div className="text-sm text-default-600">{nodesError}</div>
+            </CardBody>
+          </Card>
+        ) : null}
+      </div>
+
+      <MonitorView nodeMap={nodeMap} />
+    </AnimatedPage>
+  );
+}

vite-frontend/src/pages/node.tsx

@@ -67,7 +67,10 @@ import {
   getNodeRenewalCycleLabel,
   type NodeRenewalCycle,
 } from "@/pages/node/renewal";
-import { buildNodeSystemInfo } from "@/pages/node/system-info";
+import {
+  buildNodeSystemInfo,
+  type NodeSystemInfo,
+} from "@/pages/node/system-info";
 import { useNodeOfflineTimers } from "@/pages/node/use-node-offline-timers";
 import { useNodeRealtime } from "@/pages/node/use-node-realtime";
 import { useLocalStorageState } from "@/hooks/use-local-storage-state";
@@ -100,15 +103,7 @@ interface Node {
   remoteUrl?: string;
   syncError?: string;
   connectionStatus: "online" | "offline";
-  systemInfo?: {
-    cpuUsage: number;
-    memoryUsage: number;
-    uploadTraffic: number;
-    downloadTraffic: number;
-    uploadSpeed: number;
-    downloadSpeed: number;
-    uptime: number;
-  } | null;
+  systemInfo?: NodeSystemInfo | null;
   copyLoading?: boolean;
   upgradeLoading?: boolean;
   rollbackLoading?: boolean;
@@ -297,6 +292,13 @@ export default function NodePage() {
     "node-active-tab",
     "local",
   );
+
+  // Backward-compat: older versions stored extra tab values.
+  useEffect(() => {
+    if (activeTab !== "local" && activeTab !== "remote") {
+      setActiveTab("local");
+    }
+  }, [activeTab, setActiveTab]);
   const [remoteUsageMap, setRemoteUsageMap] = useState<
     Record<number, RemoteUsageNode>
   >({});
@@ -581,6 +583,43 @@ export default function NodePage() {
       } catch {
         // ignore parse errors
       }
+    } else if (type === "metric") {
+      clearOfflineTimer(nodeId);
+      setNodeList((prev) =>
+        prev.map((node) => {
+          if (node.id !== nodeId) return node;
+
+          const metric =
+            typeof messageData === "string"
+              ? JSON.parse(messageData)
+              : messageData;
+
+          if (!metric || typeof metric !== "object") return node;
+
+          return {
+            ...node,
+            connectionStatus: "online",
+            systemInfo: {
+              cpuUsage: metric.cpuUsage ?? metric.cpu_usage ?? 0,
+              memoryUsage: metric.memoryUsage ?? metric.memory_usage ?? 0,
+              uploadTraffic:
+                metric.netOutBytes ?? metric.bytes_transmitted ?? 0,
+              downloadTraffic: metric.netInBytes ?? metric.bytes_received ?? 0,
+              uploadSpeed: metric.netOutSpeed ?? metric.net_out_speed ?? 0,
+              downloadSpeed: metric.netInSpeed ?? metric.net_in_speed ?? 0,
+              uptime: metric.uptime ?? 0,
+              diskUsage: metric.diskUsage ?? metric.disk_usage,
+              load1: metric.load1,
+              load5: metric.load5,
+              load15: metric.load15,
+              tcpConns: metric.tcpConns ?? metric.tcp_conns,
+              udpConns: metric.udpConns ?? metric.udp_conns,
+              netInSpeed: metric.netInSpeed ?? metric.net_in_speed,
+              netOutSpeed: metric.netOutSpeed ?? metric.net_out_speed,
+            },
+          };
+        }),
+      );
     }
   };
 
@@ -2244,6 +2283,111 @@ export default function NodePage() {
                                     </div>
                                   </div>
                                 </div>
+
+                                {/* 扩展指标：磁盘/负载/连接 */}
+                                {node.connectionStatus === "online" &&
+                                  node.systemInfo && (
+                                    <div className="space-y-2">
+                                      {node.systemInfo.diskUsage !==
+                                        undefined && (
+                                        <div>
+                                          <div className="flex justify-between text-xs mb-1">
+                                            <span>磁盘</span>
+                                            <span className="font-mono">
+                                              {node.systemInfo.diskUsage.toFixed(
+                                                1,
+                                              )}
+                                              %
+                                            </span>
+                                          </div>
+                                          <Progress
+                                            aria-label="磁盘使用率"
+                                            color={getProgressColor(
+                                              node.systemInfo.diskUsage,
+                                              false,
+                                            )}
+                                            size="sm"
+                                            value={node.systemInfo.diskUsage}
+                                          />
+                                        </div>
+                                      )}
+                                      {(node.systemInfo.load1 !== undefined ||
+                                        node.systemInfo.load5 !== undefined ||
+                                        node.systemInfo.load15 !==
+                                          undefined) && (
+                                        <div className="grid grid-cols-3 gap-1 text-xs">
+                                          {node.systemInfo.load1 !==
+                                            undefined && (
+                                            <div className="text-center p-1.5 bg-default-50 dark:bg-default-100 rounded">
+                                              <div className="text-default-500 text-[10px]">
+                                                负载 1m
+                                              </div>
+                                              <div className="font-mono">
+                                                {node.systemInfo.load1.toFixed(
+                                                  2,
+                                                )}
+                                              </div>
+                                            </div>
+                                          )}
+                                          {node.systemInfo.load5 !==
+                                            undefined && (
+                                            <div className="text-center p-1.5 bg-default-50 dark:bg-default-100 rounded">
+                                              <div className="text-default-500 text-[10px]">
+                                                负载 5m
+                                              </div>
+                                              <div className="font-mono">
+                                                {node.systemInfo.load5.toFixed(
+                                                  2,
+                                                )}
+                                              </div>
+                                            </div>
+                                          )}
+                                          {node.systemInfo.load15 !==
+                                            undefined && (
+                                            <div className="text-center p-1.5 bg-default-50 dark:bg-default-100 rounded">
+                                              <div className="text-default-500 text-[10px]">
+                                                负载 15m
+                                              </div>
+                                              <div className="font-mono">
+                                                {node.systemInfo.load15.toFixed(
+                                                  2,
+                                                )}
+                                              </div>
+                                            </div>
+                                          )}
+                                        </div>
+                                      )}
+                                      {(node.systemInfo.tcpConns !==
+                                        undefined ||
+                                        node.systemInfo.udpConns !==
+                                          undefined) && (
+                                        <div className="grid grid-cols-2 gap-2 text-xs">
+                                          {node.systemInfo.tcpConns !==
+                                            undefined && (
+                                            <div className="text-center p-1.5 bg-default-50 dark:bg-default-100 rounded">
+                                              <div className="text-default-500 text-[10px]">
+                                                TCP 连接
+                                              </div>
+                                              <div className="font-mono">
+                                                {node.systemInfo.tcpConns}
+                                              </div>
+                                            </div>
+                                          )}
+                                          {node.systemInfo.udpConns !==
+                                            undefined && (
+                                            <div className="text-center p-1.5 bg-default-50 dark:bg-default-100 rounded">
+                                              <div className="text-default-500 text-[10px]">
+                                                UDP 连接
+                                              </div>
+                                              <div className="font-mono">
+                                                {node.systemInfo.udpConns}
+                                              </div>
+                                            </div>
+                                          )}
+                                        </div>
+                                      )}
+                                    </div>
+                                  )}
                               </div>
                             </>
                           )}
@@ -2329,7 +2473,6 @@ export default function NodePage() {
           </SortableContext>
         </DndContext>
       )}
-
       {/* 新增/编辑节点对话框 */}
       <Modal
         backdrop="blur"

vite-frontend/src/pages/node/system-info.ts

@@ -6,6 +6,14 @@ export interface NodeSystemInfo {
   uploadSpeed: number;
   downloadSpeed: number;
   uptime: number;
+  diskUsage?: number;
+  load1?: number;
+  load5?: number;
+  load15?: number;
+  tcpConns?: number;
+  udpConns?: number;
+  netInSpeed?: number;
+  netOutSpeed?: number;
 }
 
 type RawSystemInfo = Record<string, string | number | undefined>;
@@ -82,5 +90,13 @@ export const buildNodeSystemInfo = (
     uploadSpeed,
     downloadSpeed,
     uptime,
+    diskUsage: toFloat(raw.disk_usage),
+    load1: toFloat(raw.load1),
+    load5: toFloat(raw.load5),
+    load15: toFloat(raw.load15),
+    tcpConns: toInteger(raw.tcp_conns),
+    udpConns: toInteger(raw.udp_conns),
+    netInSpeed: toInteger(raw.net_in_speed),
+    netOutSpeed: toInteger(raw.net_out_speed),
   };
 };

vite-frontend/src/pages/user.tsx

@@ -30,6 +30,7 @@ import { Chip } from "@/shadcn-bridge/heroui/chip";
 import { Select, SelectItem } from "@/shadcn-bridge/heroui/select";
 import { RadioGroup, Radio } from "@/shadcn-bridge/heroui/radio";
 import { Checkbox } from "@/shadcn-bridge/heroui/checkbox";
+import { Switch } from "@/shadcn-bridge/heroui/switch";
 import { DatePicker } from "@/shadcn-bridge/heroui/date-picker";
 import { Spinner } from "@/shadcn-bridge/heroui/spinner";
 import { Progress } from "@/shadcn-bridge/heroui/progress";
@@ -58,6 +59,9 @@ import {
   resetUserQuota,
   getUserGroupList,
   getUserGroups,
+  getMonitorPermissionList,
+  assignMonitorPermission,
+  removeMonitorPermission,
 } from "@/api";
 import {
   EditIcon,
@@ -229,6 +233,13 @@ export default function UserPage() {
     onClose: onTunnelModalClose,
   } = useDisclosure();
   const [currentUser, setCurrentUser] = useState<User | null>(null);
+  const [monitorPermissionUserIds, setMonitorPermissionUserIds] = useState<
+    Set<number>
+  >(new Set());
+  const [monitorPermissionLoading, setMonitorPermissionLoading] =
+    useState(false);
+  const [monitorPermissionMutatingUserId, setMonitorPermissionMutatingUserId] =
+    useState<number | null>(null);
   const [userTunnels, setUserTunnels] = useState<UserTunnel[]>([]);
   const [tunnelListLoading, setTunnelListLoading] = useState(false);
 
@@ -396,6 +407,32 @@ export default function UserPage() {
     } catch {}
   }, []);
 
+  const loadMonitorPermissions = useCallback(async () => {
+    setMonitorPermissionLoading(true);
+    try {
+      const response = await getMonitorPermissionList();
+
+      if (response.code === 0) {
+        const ids = new Set<number>();
+
+        if (Array.isArray(response.data)) {
+          response.data.forEach((item: any) => {
+            const id = Number(item?.userId ?? 0);
+
+            if (id > 0) ids.add(id);
+          });
+        }
+        setMonitorPermissionUserIds(ids);
+      } else if (response.code !== 403) {
+        toast.error(response.msg || "获取监控权限失败");
+      }
+    } catch {
+      // ignore
+    } finally {
+      setMonitorPermissionLoading(false);
+    }
+  }, []);
+
   const loadUserTunnels = useCallback(async (userId: number) => {
     setTunnelListLoading(true);
     try {
@@ -422,7 +459,8 @@ export default function UserPage() {
     void loadTunnels();
     void loadSpeedLimits();
     void loadUserGroups();
-  }, [loadSpeedLimits, loadTunnels, loadUserGroups]);
+    void loadMonitorPermissions();
+  }, [loadMonitorPermissions, loadSpeedLimits, loadTunnels, loadUserGroups]);
 
   useEffect(() => {
     void loadUsers();
@@ -598,6 +636,63 @@ export default function UserPage() {
     }
   };
 
+  const setUserMonitorPermission = useCallback(
+    async (userId: number, enabled: boolean) => {
+      if (userId <= 0) return;
+      if (monitorPermissionMutatingUserId === userId) return;
+
+      const prevEnabled = monitorPermissionUserIds.has(userId);
+
+      if (prevEnabled === enabled) return;
+
+      setMonitorPermissionMutatingUserId(userId);
+
+      // Optimistic update for better UX.
+      setMonitorPermissionUserIds((prev) => {
+        const next = new Set(prev);
+
+        if (enabled) {
+          next.add(userId);
+        } else {
+          next.delete(userId);
+        }
+
+        return next;
+      });
+
+      try {
+        const response = enabled
+          ? await assignMonitorPermission(userId)
+          : await removeMonitorPermission(userId);
+
+        if (response.code === 0) {
+          toast.success(enabled ? "已授权监控" : "已撤销监控");
+
+          return;
+        }
+
+        toast.error(response.msg || "操作失败");
+        throw new Error("mutation failed");
+      } catch {
+        // Revert optimistic update on failure.
+        setMonitorPermissionUserIds((prev) => {
+          const next = new Set(prev);
+
+          if (prevEnabled) {
+            next.add(userId);
+          } else {
+            next.delete(userId);
+          }
+
+          return next;
+        });
+      } finally {
+        setMonitorPermissionMutatingUserId(null);
+      }
+    },
+    [monitorPermissionMutatingUserId, monitorPermissionUserIds],
+  );
+
   // 隧道权限管理操作
   const handleManageTunnels = (user: User) => {
     setCurrentUser(user);
@@ -1050,6 +1145,26 @@ export default function UserPage() {
 
                       {/* 其他信息 */}
                       <div className="space-y-1.5 pt-2 border-t border-divider">
+                        {(user.dailyQuotaGB ?? 0) > 0 ||
+                        (user.monthlyQuotaGB ?? 0) > 0 ||
+                        (user.disabledByQuota ?? 0) > 0 ? (
+                          <>
+                            <div className="flex justify-between text-sm">
+                              <span className="text-default-600">每日配额</span>
+                              <span className="font-medium text-xs">
+                                {formatFlow(Number(user.dailyUsedBytes ?? 0))} /{" "}
+                                {formatQuotaLimit(user.dailyQuotaGB)}
+                              </span>
+                            </div>
+                            <div className="flex justify-between text-sm">
+                              <span className="text-default-600">每月配额</span>
+                              <span className="font-medium text-xs">
+                                {formatFlow(Number(user.monthlyUsedBytes ?? 0))}{" "}
+                                / {formatQuotaLimit(user.monthlyQuotaGB)}
+                              </span>
+                            </div>
+                          </>
+                        ) : null}
                         <div className="flex justify-between text-sm">
                           <span className="text-default-600">规则数量</span>
                           <span className="font-medium text-xs">
@@ -1414,9 +1529,43 @@ export default function UserPage() {
         onClose={onTunnelModalClose}
       >
         <ModalContent>
-          <ModalHeader>用户 {currentUser?.user} 的隧道权限管理</ModalHeader>
+          <ModalHeader>用户 {currentUser?.user} 的权限管理</ModalHeader>
           <ModalBody>
             <div className="space-y-6">
+              {/* 监控权限部分 */}
+              <div>
+                <h3 className="text-lg font-semibold mb-4">监控权限</h3>
+                <div className="flex items-center justify-between gap-4 bg-default-100 dark:bg-default-50 p-4 rounded-lg border border-default-200 dark:border-default-100/30">
+                  <div className="min-w-0">
+                    <div className="text-sm font-medium text-foreground">
+                      允许访问监控功能
+                    </div>
+                    <div className="text-xs text-default-500 mt-1">
+                      授予后，该用户可以访问监控页面并管理服务监控（TCP/ICMP）。
+                    </div>
+                  </div>
+                  <div className="flex items-center gap-2 shrink-0">
+                    {monitorPermissionLoading ? <Spinner size="sm" /> : null}
+                    <Switch
+                      isDisabled={
+                        !currentUser ||
+                        monitorPermissionLoading ||
+                        monitorPermissionMutatingUserId === currentUser.id
+                      }
+                      isSelected={
+                        currentUser
+                          ? monitorPermissionUserIds.has(currentUser.id)
+                          : false
+                      }
+                      onValueChange={(v) =>
+                        currentUser &&
+                        void setUserMonitorPermission(currentUser.id, v)
+                      }
+                    />
+                  </div>
+                </div>
+              </div>
+
               {/* 分配新权限部分 */}
               <div>
                 <h3 className="text-lg font-semibold mb-4">分配新权限</h3>