feat: implement Uptime Kuma style historic quality bars for tunnel monitor (#355)

Implement tunnel quality metrics collection and display

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

@@ -42,6 +42,8 @@ type Handler struct {
 
 	upgradeMu              sync.Mutex
 	pendingUpgradeRedeploy map[int64]struct{}
+
+	qualityProber *tunnelQualityProber
 }
 
 type loginRequest struct {
@@ -93,6 +95,7 @@ func New(repo *repo.Repository, jwtSecret string) *Handler {
 		pendingUpgradeRedeploy: make(map[int64]struct{}),
 	}
 	h.healthCheck = health.NewChecker(repo, h.wsServer)
+	h.qualityProber = newTunnelQualityProber(h)
 	h.wsServer.SetNodeOnlineHook(h.onNodeOnline)
 	h.wsServer.SetNodeMetricHook(func(nodeID int64, info ws.SystemInfo) {
 		metricInfo := metrics.SystemInfo{
@@ -229,6 +232,7 @@ func (h *Handler) Register(mux *http.ServeMux) {
 	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/quality", h.monitorTunnelQualityHandler)
 	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)
@@ -1234,6 +1238,21 @@ func nullableNullInt64(v sql.NullInt64) interface{} {
 	return nil
 }
 
+// flowCryptoCache caches AES crypto instances by secret to avoid per-request SHA256+GCM init.
+var flowCryptoCache sync.Map
+
+func getOrCreateFlowCrypto(secret string) *security.AESCrypto {
+	if v, ok := flowCryptoCache.Load(secret); ok {
+		return v.(*security.AESCrypto)
+	}
+	c, err := security.NewAESCrypto(secret)
+	if err != nil {
+		return nil
+	}
+	flowCryptoCache.Store(secret, c)
+	return c
+}
+
 func readAndDecryptFlowBody(body io.ReadCloser, secret string) (string, error) {
 	defer body.Close()
 	raw, err := io.ReadAll(body)
@@ -1254,8 +1273,8 @@ func readAndDecryptFlowBody(body io.ReadCloser, secret string) (string, error) {
 		return text, nil
 	}
 
-	crypto, err := security.NewAESCrypto(secret)
-	if err != nil {
+	crypto := getOrCreateFlowCrypto(secret)
+	if crypto == nil {
 		return text, nil
 	}
 	plain, err := crypto.Decrypt(wrap.Data)

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

@@ -18,7 +18,7 @@ func (h *Handler) StartBackgroundJobs() {
 	ctx, cancel := context.WithCancel(context.Background())
 	h.jobsCancel = cancel
 	h.jobsStarted = true
-	h.jobsWG.Add(5)
+	h.jobsWG.Add(6)
 	h.jobsMu.Unlock()
 
 	go h.runHourlyStatsLoop(ctx)
@@ -26,6 +26,7 @@ func (h *Handler) StartBackgroundJobs() {
 	go h.runNodeRenewalCycleLoop(ctx)
 	go h.runMetricsIngestion(ctx)
 	go h.runHealthChecks(ctx)
+	go h.runTunnelQualityProber(ctx)
 }
 
 func (h *Handler) StopBackgroundJobs() {
@@ -63,6 +64,13 @@ func (h *Handler) runHealthChecks(ctx context.Context) {
 	}
 }
 
+func (h *Handler) runTunnelQualityProber(ctx context.Context) {
+	defer h.jobsWG.Done()
+	if h.qualityProber != nil {
+		h.qualityProber.Start(ctx)
+	}
+}
+
 func (h *Handler) runHourlyStatsLoop(ctx context.Context) {
 	defer h.jobsWG.Done()
 

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

@@ -207,6 +207,98 @@ func (h *Handler) handleNodeMetricsLatest(w http.ResponseWriter, _ *http.Request
 	response.WriteJSON(w, response.OK(metric))
 }
 
+func (h *Handler) monitorTunnelQualityHandler(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
+	}
+
+	// Try in-memory cache first
+	if h.qualityProber != nil {
+		items := h.qualityProber.GetAll()
+		if len(items) > 0 {
+			response.WriteJSON(w, response.OK(items))
+			return
+		}
+	}
+
+	// Fallback to database (latest per tunnel)
+	qualities, err := h.repo.GetLatestTunnelQualities()
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	snapshots := make([]tunnelQualitySnapshot, 0, len(qualities))
+	for _, q := range qualities {
+		snapshots = append(snapshots, tunnelQualitySnapshot{
+			TunnelID:           q.TunnelID,
+			EntryToExitLatency: q.EntryToExitLatency,
+			ExitToBingLatency:  q.ExitToBingLatency,
+			EntryToExitLoss:    q.EntryToExitLoss,
+			ExitToBingLoss:     q.ExitToBingLoss,
+			Success:            q.Success == 1,
+			ErrorMessage:       q.ErrorMessage,
+			Timestamp:          q.Timestamp,
+		})
+	}
+	response.WriteJSON(w, response.OK(snapshots))
+}
+
+// monitorTunnelQualityHistory returns quality probe history for charting.
+// GET /api/v1/monitor/tunnels/{id}/quality?start=...&end=...
+// Mirrors monitorTunnelMetrics / monitorServiceResultsHandler pattern.
+func (h *Handler) monitorTunnelQualityHistory(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/", "/quality")
+	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 || 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
+	}
+
+	results, err := h.repo.GetTunnelQualityHistory(tunnelID, startMs, endMs)
+	if err != nil {
+		response.WriteJSON(w, response.Err(-2, err.Error()))
+		return
+	}
+
+	response.WriteJSON(w, response.OK(results))
+}
+
 func (h *Handler) monitorTunnelMetrics(w http.ResponseWriter, r *http.Request) {
 	if r.Method != http.MethodGet {
 		response.WriteJSON(w, response.ErrDefault("请求失败"))
@@ -216,7 +308,23 @@ func (h *Handler) monitorTunnelMetrics(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	tunnelIDStr := extractPathParam(r.URL.Path, "/api/v1/monitor/tunnels/", "/metrics")
+	path := r.URL.Path
+	prefix := "/api/v1/monitor/tunnels/"
+	if !strings.HasPrefix(path, prefix) {
+		response.WriteJSON(w, response.ErrDefault("无效的路径"))
+		return
+	}
+
+	rest := strings.TrimPrefix(path, prefix)
+
+	// Route: /api/v1/monitor/tunnels/{id}/quality
+	if strings.HasSuffix(rest, "/quality") {
+		h.monitorTunnelQualityHistory(w, r)
+		return
+	}
+
+	// Route: /api/v1/monitor/tunnels/{id}/metrics (original)
+	tunnelIDStr := extractPathParam(path, prefix, "/metrics")
 	tunnelID, err := strconv.ParseInt(tunnelIDStr, 10, 64)
 	if err != nil || tunnelID <= 0 {
 		response.WriteJSON(w, response.ErrDefault("无效的隧道ID"))

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

@@ -0,0 +1,332 @@
+package handler
+
+import (
+	"context"
+	"log"
+	"sync"
+	"time"
+
+	"go-backend/internal/store/model"
+)
+
+const (
+	tunnelQualityProbeInterval = 10 * time.Second
+	tunnelQualityProbeTimeout  = 8 * time.Second
+	tunnelQualityPingTimeoutMs = 5000
+	tunnelQualityRetention     = 24 * time.Hour // keep 24h of history
+	tunnelQualityPruneInterval = 10 * time.Minute
+)
+
+// tunnelQualitySnapshot is the in-memory latest probe result for a tunnel.
+type tunnelQualitySnapshot struct {
+	TunnelID           int64   `json:"tunnelId"`
+	EntryToExitLatency float64 `json:"entryToExitLatency"`
+	ExitToBingLatency  float64 `json:"exitToBingLatency"`
+	EntryToExitLoss    float64 `json:"entryToExitLoss"`
+	ExitToBingLoss     float64 `json:"exitToBingLoss"`
+	Success            bool    `json:"success"`
+	ErrorMessage       string  `json:"errorMessage,omitempty"`
+	Timestamp          int64   `json:"timestamp"`
+}
+
+// tunnelQualityProber runs periodic TCP ping probes against all enabled tunnels.
+// Design mirrors health.Checker: background goroutine with worker pool + scheduled cleanup.
+type tunnelQualityProber struct {
+	handler   *Handler
+	cache     sync.Map // tunnelID (int64) → *tunnelQualitySnapshot
+	ctx       context.Context
+	cancel    context.CancelFunc
+	interval  time.Duration
+	lastPrune int64
+}
+
+// newTunnelQualityProber creates a new prober (not yet running).
+func newTunnelQualityProber(h *Handler) *tunnelQualityProber {
+	ctx, cancel := context.WithCancel(context.Background())
+	return &tunnelQualityProber{
+		handler:  h,
+		ctx:      ctx,
+		cancel:   cancel,
+		interval: tunnelQualityProbeInterval,
+	}
+}
+
+// Start launches the background probe loop (call from jobs.go).
+func (p *tunnelQualityProber) Start(ctx context.Context) {
+	// Use the provided context so we stop with other background jobs.
+	p.ctx, p.cancel = context.WithCancel(ctx)
+	p.loop()
+}
+
+// Stop halts the background probe loop.
+func (p *tunnelQualityProber) Stop() {
+	p.cancel()
+}
+
+// GetAll returns all cached quality snapshots (latest per tunnel).
+func (p *tunnelQualityProber) GetAll() []tunnelQualitySnapshot {
+	var items []tunnelQualitySnapshot
+	p.cache.Range(func(_, value interface{}) bool {
+		if snap, ok := value.(*tunnelQualitySnapshot); ok {
+			items = append(items, *snap)
+		}
+		return true
+	})
+	return items
+}
+
+func (p *tunnelQualityProber) loop() {
+	// Initial delay to let the system boot up
+	select {
+	case <-time.After(5 * time.Second):
+	case <-p.ctx.Done():
+		return
+	}
+
+	// Run once immediately
+	p.probeAll()
+
+	ticker := time.NewTicker(p.interval)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-p.ctx.Done():
+			return
+		case <-ticker.C:
+			p.probeAll()
+			p.maybePrune()
+		}
+	}
+}
+
+// maybePrune deletes old quality rows periodically (mirrors PruneServiceMonitorResults).
+func (p *tunnelQualityProber) maybePrune() {
+	now := time.Now().UnixMilli()
+	if p.lastPrune > 0 && now-p.lastPrune < int64(tunnelQualityPruneInterval/time.Millisecond) {
+		return
+	}
+	p.lastPrune = now
+
+	h := p.handler
+	if h == nil || h.repo == nil {
+		return
+	}
+
+	cutoff := now - int64(tunnelQualityRetention/time.Millisecond)
+	if err := h.repo.PruneTunnelQualityResults(cutoff); err != nil {
+		log.Printf("tunnel_quality_prober: prune err=%v", err)
+	}
+}
+
+func (p *tunnelQualityProber) probeAll() {
+	h := p.handler
+	if h == nil || h.repo == nil {
+		return
+	}
+
+	tunnelIDs, err := h.repo.ListEnabledTunnelIDs()
+	if err != nil {
+		log.Printf("tunnel_quality_prober: list enabled tunnels err=%v", err)
+		return
+	}
+	if len(tunnelIDs) == 0 {
+		return
+	}
+
+	// Probe tunnels concurrently with a worker limit
+	// (mirrors health.Checker worker pool pattern)
+	const maxWorkers = 4
+	sem := make(chan struct{}, maxWorkers)
+	var wg sync.WaitGroup
+
+	for _, tunnelID := range tunnelIDs {
+		select {
+		case <-p.ctx.Done():
+			return
+		default:
+		}
+
+		wg.Add(1)
+		sem <- struct{}{}
+		go func(tid int64) {
+			defer wg.Done()
+			defer func() { <-sem }()
+			p.probeTunnel(tid)
+		}(tunnelID)
+	}
+	wg.Wait()
+}
+
+func (p *tunnelQualityProber) probeTunnel(tunnelID int64) {
+	h := p.handler
+	if h == nil || h.repo == nil {
+		return
+	}
+
+	now := time.Now().UnixMilli()
+	snap := &tunnelQualitySnapshot{
+		TunnelID:  tunnelID,
+		Timestamp: now,
+	}
+
+	// Get tunnel chain info
+	tunnel, err := h.getTunnelRecord(tunnelID)
+	if err != nil {
+		snap.ErrorMessage = "隧道不存在"
+		p.storeResult(snap)
+		return
+	}
+
+	chainRows, err := h.listChainNodesForTunnel(tunnelID)
+	if err != nil || len(chainRows) == 0 {
+		snap.ErrorMessage = "隧道配置不完整"
+		p.storeResult(snap)
+		return
+	}
+
+	ipPreference := h.repo.GetTunnelIPPreference(tunnelID)
+	inNodes, _, outNodes := splitChainNodeGroups(chainRows)
+
+	options := diagnosisExecOptions{
+		commandTimeout: tunnelQualityProbeTimeout,
+		pingTimeoutMS:  tunnelQualityPingTimeoutMs,
+		timeoutMessage: "探测超时",
+	}
+
+	switch tunnel.Type {
+	case 1:
+		// Port forwarding: entry → Bing only
+		if len(inNodes) > 0 {
+			lat, loss, err := p.tcpPingNode(inNodes[0].NodeID, "www.bing.com", 443, options)
+			if err == nil {
+				snap.ExitToBingLatency = lat
+				snap.ExitToBingLoss = loss
+				snap.Success = true
+			} else {
+				snap.ErrorMessage = err.Error()
+			}
+		}
+	case 2:
+		// Tunnel forwarding: entry → exit + exit → Bing
+		probeOK := true
+
+		if len(inNodes) > 0 && len(outNodes) > 0 {
+			// Entry → Exit
+			targetNode, nodeErr := h.getNodeRecord(outNodes[0].NodeID)
+			if nodeErr == nil && targetNode != nil {
+				fromNode, _ := h.getNodeRecord(inNodes[0].NodeID)
+				targetIP, targetPort, resolveErr := resolveChainProbeTarget(fromNode, targetNode, outNodes[0].Port, ipPreference, outNodes[0].ConnectIP)
+				if resolveErr == nil {
+					lat, loss, err := p.tcpPingNode(inNodes[0].NodeID, targetIP, targetPort, options)
+					if err == nil {
+						snap.EntryToExitLatency = lat
+						snap.EntryToExitLoss = loss
+					} else {
+						snap.EntryToExitLatency = -1
+						snap.EntryToExitLoss = 100
+						probeOK = false
+					}
+				} else {
+					snap.ErrorMessage = resolveErr.Error()
+					probeOK = false
+				}
+			} else {
+				snap.ErrorMessage = "出口节点不可用"
+				probeOK = false
+			}
+		}
+
+		// Exit → Bing
+		if len(outNodes) > 0 {
+			lat, loss, err := p.tcpPingNode(outNodes[0].NodeID, "www.bing.com", 443, options)
+			if err == nil {
+				snap.ExitToBingLatency = lat
+				snap.ExitToBingLoss = loss
+			} else {
+				if snap.ErrorMessage == "" {
+					snap.ErrorMessage = err.Error()
+				}
+				probeOK = false
+			}
+		}
+
+		snap.Success = probeOK
+	default:
+		// Unknown type: entry → Bing
+		if len(inNodes) > 0 {
+			lat, loss, err := p.tcpPingNode(inNodes[0].NodeID, "www.bing.com", 443, options)
+			if err == nil {
+				snap.ExitToBingLatency = lat
+				snap.ExitToBingLoss = loss
+				snap.Success = true
+			} else {
+				snap.ErrorMessage = err.Error()
+			}
+		}
+	}
+
+	p.storeResult(snap)
+}
+
+func (p *tunnelQualityProber) tcpPingNode(nodeID int64, ip string, port int, options diagnosisExecOptions) (latency float64, loss float64, err error) {
+	h := p.handler
+	if h == nil {
+		return 0, 100, nil
+	}
+
+	node, nodeErr := h.getNodeRecord(nodeID)
+	if nodeErr != nil {
+		return 0, 100, nodeErr
+	}
+
+	var pingData map[string]interface{}
+	var pingErr error
+	if node != nil && node.IsRemote == 1 {
+		pingData, pingErr = h.tcpPingViaRemoteNode(node, ip, port, options)
+	} else {
+		pingData, pingErr = h.tcpPingViaNode(nodeID, ip, port, options)
+	}
+	if pingErr != nil {
+		return 0, 100, pingErr
+	}
+
+	avgTime := asFloat(pingData["averageTime"], 0)
+	packetLoss := asFloat(pingData["packetLoss"], 100)
+
+	return avgTime, packetLoss, nil
+}
+
+func (p *tunnelQualityProber) storeResult(snap *tunnelQualitySnapshot) {
+	if snap == nil {
+		return
+	}
+
+	// Update in-memory cache (latest per tunnel)
+	p.cache.Store(snap.TunnelID, snap)
+
+	// Persist to database (history)
+	h := p.handler
+	if h == nil || h.repo == nil {
+		return
+	}
+
+	successInt := 0
+	if snap.Success {
+		successInt = 1
+	}
+
+	q := &model.TunnelQuality{
+		TunnelID:           snap.TunnelID,
+		EntryToExitLatency: snap.EntryToExitLatency,
+		ExitToBingLatency:  snap.ExitToBingLatency,
+		EntryToExitLoss:    snap.EntryToExitLoss,
+		ExitToBingLoss:     snap.ExitToBingLoss,
+		Success:            successInt,
+		ErrorMessage:       snap.ErrorMessage,
+		Timestamp:          snap.Timestamp,
+	}
+	if err := h.repo.InsertTunnelQuality(q); err != nil {
+		log.Printf("tunnel_quality_prober: insert db err=%v tunnel_id=%d", err, snap.TunnelID)
+	}
+}

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

@@ -714,3 +714,20 @@ type ServiceMonitorResult struct {
 }
 
 func (ServiceMonitorResult) TableName() string { return "service_monitor_result" }
+
+// TunnelQuality stores periodic probe results for a tunnel.
+// Unlike the old upsert model, rows accumulate for history/charting.
+// Old rows are pruned periodically (default: keep 24h).
+type TunnelQuality struct {
+	ID                 int64   `gorm:"primaryKey;autoIncrement" json:"id"`
+	TunnelID           int64   `gorm:"column:tunnel_id;not null;index:idx_tunnel_quality_tunnel_time,priority:1" json:"tunnelId"`
+	EntryToExitLatency float64 `gorm:"column:entry_to_exit_latency" json:"entryToExitLatency"`
+	ExitToBingLatency  float64 `gorm:"column:exit_to_bing_latency" json:"exitToBingLatency"`
+	EntryToExitLoss    float64 `gorm:"column:entry_to_exit_loss" json:"entryToExitLoss"`
+	ExitToBingLoss     float64 `gorm:"column:exit_to_bing_loss" json:"exitToBingLoss"`
+	Success            int     `gorm:"not null;default:1" json:"success"`
+	ErrorMessage       string  `gorm:"column:error_message;type:text" json:"errorMessage,omitempty"`
+	Timestamp          int64   `gorm:"not null;index:idx_tunnel_quality_tunnel_time,priority:2;index:idx_tunnel_quality_time" json:"timestamp"`
+}
+
+func (TunnelQuality) TableName() string { return "tunnel_quality" }

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

@@ -51,6 +51,7 @@ type NodeMetric = model.NodeMetric
 type TunnelMetric = model.TunnelMetric
 type ServiceMonitor = model.ServiceMonitor
 type ServiceMonitorResult = model.ServiceMonitorResult
+type TunnelQuality = model.TunnelQuality
 
 // ─── Repository ──────────────────────────────────────────────────────
 
@@ -191,6 +192,7 @@ func autoMigrateAll(db *gorm.DB) error {
 		&model.TunnelMetric{},
 		&model.ServiceMonitor{},
 		&model.ServiceMonitorResult{},
+		&model.TunnelQuality{},
 	}
 
 	if db.Dialector.Name() != "sqlite" {

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

@@ -0,0 +1,98 @@
+package repo
+
+import (
+	"errors"
+
+	"go-backend/internal/store/model"
+)
+
+// InsertTunnelQuality appends a tunnel quality probe result.
+// (Follows the same pattern as InsertServiceMonitorResult.)
+func (r *Repository) InsertTunnelQuality(q *model.TunnelQuality) error {
+	if r == nil || r.db == nil {
+		return errors.New("repository not initialized")
+	}
+	if q == nil || q.TunnelID <= 0 {
+		return nil
+	}
+	return r.db.Create(q).Error
+}
+
+// GetTunnelQualityHistory returns quality probe results for a tunnel
+// within a time range, ordered by timestamp ascending.
+// (Mirrors GetServiceMonitorResults pattern.)
+func (r *Repository) GetTunnelQualityHistory(tunnelID int64, startMs, endMs int64) ([]model.TunnelQuality, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	var results []model.TunnelQuality
+	err := r.db.Where("tunnel_id = ? AND timestamp >= ? AND timestamp <= ?", tunnelID, startMs, endMs).
+		Order("timestamp ASC").
+		Find(&results).Error
+	return results, err
+}
+
+// GetLatestTunnelQualities returns the newest quality result per tunnel_id.
+// (Mirrors GetLatestServiceMonitorResults pattern.)
+func (r *Repository) GetLatestTunnelQualities() ([]model.TunnelQuality, error) {
+	if r == nil || r.db == nil {
+		return nil, nil
+	}
+
+	var results []model.TunnelQuality
+
+	// Use window function (works on modern SQLite 3.25+ and PostgreSQL).
+	q := `
+		SELECT id, tunnel_id, entry_to_exit_latency, exit_to_bing_latency,
+		       entry_to_exit_loss, exit_to_bing_loss, success, error_message, timestamp
+		FROM (
+			SELECT *, ROW_NUMBER() OVER (PARTITION BY tunnel_id ORDER BY timestamp DESC, id DESC) AS rn
+			FROM tunnel_quality
+		) t
+		WHERE rn = 1
+		ORDER BY tunnel_id ASC
+	`
+	if err := r.db.Raw(q).Scan(&results).Error; err == nil {
+		return results, nil
+	}
+
+	// Fallback for older SQLite
+	results = nil
+	err := r.db.Order("timestamp DESC, id DESC").Limit(5000).Find(&results).Error
+	if err != nil {
+		return nil, err
+	}
+
+	seen := make(map[int64]struct{}, len(results))
+	out := make([]model.TunnelQuality, 0, len(results))
+	for _, row := range results {
+		if row.TunnelID <= 0 {
+			continue
+		}
+		if _, ok := seen[row.TunnelID]; ok {
+			continue
+		}
+		seen[row.TunnelID] = struct{}{}
+		out = append(out, row)
+	}
+	return out, nil
+}
+
+// PruneTunnelQualityResults deletes quality results older than the given timestamp.
+// (Mirrors PruneServiceMonitorResults pattern.)
+func (r *Repository) PruneTunnelQualityResults(olderThanMs int64) error {
+	if r == nil || r.db == nil {
+		return nil
+	}
+	return r.db.Where("timestamp < ?", olderThanMs).Delete(&model.TunnelQuality{}).Error
+}
+
+// ListEnabledTunnelIDs returns IDs of all tunnels with status=1.
+func (r *Repository) ListEnabledTunnelIDs() ([]int64, error) {
+	if r == nil || r.db == nil {
+		return nil, errors.New("repository not initialized")
+	}
+	var ids []int64
+	err := r.db.Model(&model.Tunnel{}).Where("status = ?", 1).Pluck("id", &ids).Error
+	return ids, err
+}

go-backend/internal/ws/server.go

@@ -39,6 +39,7 @@ type nodeSession struct {
 	nodeID int64
 	secret string
 	conn   *connWrap
+	crypto *security.AESCrypto // 缓存的 AES 加密器，避免每条消息重建
 }
 
 type commandResponse struct {
@@ -211,7 +212,12 @@ func (s *Server) handleNode(w http.ResponseWriter, r *http.Request, nodeID int64
 		_ = old.conn.conn.Close()
 		delete(s.byConn, old.conn.conn)
 	}
-	ns := &nodeSession{nodeID: nodeID, secret: secret, conn: cw}
+	// 初始化 AES 加密器并缓存（仅创建一次）
+	var nodeCrypto *security.AESCrypto
+	if strings.TrimSpace(secret) != "" {
+		nodeCrypto, _ = security.NewAESCrypto(secret)
+	}
+	ns := &nodeSession{nodeID: nodeID, secret: secret, conn: cw, crypto: nodeCrypto}
 	s.nodes[nodeID] = ns
 	s.byConn[conn] = ns
 	s.mu.Unlock()
@@ -251,7 +257,7 @@ func (s *Server) handleNode(w http.ResponseWriter, r *http.Request, nodeID int64
 			return
 		}
 
-		msg := decryptIfNeeded(payload, secret)
+		msg := decryptIfNeeded(payload, ns.crypto, secret)
 		s.tryResolvePending(nodeID, msg)
 
 		var parsed struct {
@@ -259,6 +265,26 @@ func (s *Server) handleNode(w http.ResponseWriter, r *http.Request, nodeID int64
 		}
 		if json.Unmarshal([]byte(msg), &parsed) == nil && parsed.Type != "" {
 			switch parsed.Type {
+			case "metric":
+				// Agent 新版指标消息：{type:"metric", data:{...}}
+				var envelope struct {
+					Data json.RawMessage `json:"data"`
+				}
+				if err := json.Unmarshal([]byte(msg), &envelope); err == nil && len(envelope.Data) > 0 {
+					// 解析 SystemInfo 并调用 hook
+					var sysInfo SystemInfo
+					if json.Unmarshal(envelope.Data, &sysInfo) == nil {
+						s.mu.RLock()
+						onMetric := s.onNodeMetric
+						s.mu.RUnlock()
+						if onMetric != nil {
+							go onMetric(nodeID, sysInfo)
+						}
+					}
+					// 广播内层 data 给前端（保持平坦结构兼容性）
+					s.broadcastTyped(nodeID, "metric", string(envelope.Data))
+				}
+				continue
 			case "UpgradeProgress":
 				s.broadcastTyped(nodeID, "upgrade_progress", msg)
 				continue
@@ -270,6 +296,7 @@ func (s *Server) handleNode(w http.ResponseWriter, r *http.Request, nodeID int64
 			}
 		}
 
+		// 兼容旧版 Agent：无 type 字段的系统信息消息
 		if looksLikeSystemInfoMessage(msg) {
 			var sysInfo SystemInfo
 			if err := json.Unmarshal([]byte(msg), &sysInfo); err == nil {
@@ -372,13 +399,8 @@ func (s *Server) SendCommand(nodeID int64, cmdType string, data interface{}, tim
 	}
 
 	messageData := rawCmd
-	if strings.TrimSpace(ns.secret) != "" {
-		crypto, err := security.NewAESCrypto(ns.secret)
-		if err != nil {
-			cleanup()
-			return CommandResult{}, err
-		}
-		encrypted, err := crypto.Encrypt(rawCmd)
+	if ns.crypto != nil {
+		encrypted, err := ns.crypto.Encrypt(rawCmd)
 		if err != nil {
 			cleanup()
 			return CommandResult{}, err
@@ -428,6 +450,11 @@ func (s *Server) tryResolvePending(nodeID int64, message string) {
 		return
 	}
 
+	// 快速短路：指标消息永远不含 requestId，跳过完整 JSON 解析
+	if !strings.Contains(message, "\"requestId\"") {
+		return
+	}
+
 	var resp commandResponse
 	if err := json.Unmarshal([]byte(message), &resp); err != nil {
 		return
@@ -545,18 +572,22 @@ func (s *Server) broadcastToAdmins(message string) {
 	}
 }
 
-func decryptIfNeeded(payload []byte, secret string) string {
+func decryptIfNeeded(payload []byte, crypto *security.AESCrypto, secret string) string {
 	text := string(payload)
 	var wrap encryptedMessage
 	if err := json.Unmarshal(payload, &wrap); err != nil || !wrap.Encrypted || strings.TrimSpace(wrap.Data) == "" {
 		return text
 	}
 
-	crypto, err := security.NewAESCrypto(secret)
-	if err != nil {
+	// 优先使用缓存的 crypto 实例
+	c := crypto
+	if c == nil && strings.TrimSpace(secret) != "" {
+		c, _ = security.NewAESCrypto(secret)
+	}
+	if c == nil {
 		return text
 	}
-	plain, err := crypto.Decrypt(wrap.Data)
+	plain, err := c.Decrypt(wrap.Data)
 	if err != nil {
 		return text
 	}

go-gost/x/socket/websocket_reporter.go

@@ -9,6 +9,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"math/rand"
 	"net"
 	"net/http"
 	"net/url"
@@ -146,6 +147,9 @@ type ServiceMonitorCheckResult struct {
 const (
 	reporterReadWait  = 60 * time.Second
 	reporterWriteWait = 5 * time.Second
+	wsPingInterval    = 20 * time.Second // 独立 WebSocket ping 间隔
+	initialBackoff    = 2 * time.Second  // 重连初始退避
+	maxBackoff        = 2 * time.Minute  // 重连最大退避
 )
 
 type WebSocketReporter struct {
@@ -155,15 +159,15 @@ type WebSocketReporter struct {
 	version           string // 保存版本号
 	preferredWSScheme string
 	conn              *websocket.Conn
-	reconnectTime     time.Duration
+	curBackoff        time.Duration // 当前重连退避间隔
 	pingInterval      time.Duration
 	configInterval    time.Duration
 	ctx               context.Context
 	cancel            context.CancelFunc
 	connected         bool
-	connecting        bool              // 新增：正在连接状态
-	connMutex         sync.Mutex        // 新增：连接状态锁
-	aesCrypto         *crypto.AESCrypto // 新增：AES加密器
+	connecting        bool              // 正在连接状态
+	connMutex         sync.Mutex        // 连接状态锁
+	aesCrypto         *crypto.AESCrypto // AES加密器
 }
 
 var wsDial = func(dialer *websocket.Dialer, rawURL string) (*websocket.Conn, *http.Response, error) {
@@ -185,7 +189,7 @@ func NewWebSocketReporter(serverURL string, secret string) *WebSocketReporter {
 
 	return &WebSocketReporter{
 		url:            serverURL,
-		reconnectTime:  5 * time.Second,  // 重连间隔
+		curBackoff:     initialBackoff,   // 当前退避间隔
 		pingInterval:   5 * time.Second,  // 指标上报间隔
 		configInterval: 10 * time.Minute, // 配置上报间隔
 		ctx:            ctx,
@@ -204,10 +208,17 @@ func (w *WebSocketReporter) Start() {
 // Stop 停止WebSocket报告器
 func (w *WebSocketReporter) Stop() {
 	w.cancel()
+	w.connMutex.Lock()
 	if w.conn != nil {
 		w.conn.Close()
 	}
+	w.connMutex.Unlock()
+}
 
+// backoffWithJitter 返回带随机抖动的退避时间（±25%）
+func backoffWithJitter(base time.Duration) time.Duration {
+	jitter := time.Duration(float64(base) * (0.75 + rand.Float64()*0.5))
+	return jitter
 }
 
 // run 主运行循环
@@ -224,23 +235,32 @@ func (w *WebSocketReporter) run() {
 
 			if needConnect {
 				if err := w.connect(); err != nil {
-					fmt.Printf("❌ WebSocket连接失败: %v，%v后重试\n", err, w.reconnectTime)
+					wait := backoffWithJitter(w.curBackoff)
+					fmt.Printf("❌ WebSocket连接失败: %v，%v后重试\n", err, wait)
+					// 指数退避：翻倍当前退避间隔，上限 maxBackoff
+					w.curBackoff *= 2
+					if w.curBackoff > maxBackoff {
+						w.curBackoff = maxBackoff
+					}
 					select {
-					case <-time.After(w.reconnectTime):
+					case <-time.After(wait):
 						continue
 					case <-w.ctx.Done():
 						return
 					}
 				}
+				// 连接成功：重置退避
+				w.curBackoff = initialBackoff
 			}
 
 			// 连接成功，开始发送消息
 			if w.connected {
 				w.handleConnection()
 			} else {
+				wait := backoffWithJitter(w.curBackoff)
 				// 如果连接失败，等待重试
 				select {
-				case <-time.After(w.reconnectTime):
+				case <-time.After(wait):
 					continue
 				case <-w.ctx.Done():
 					return
@@ -473,15 +493,34 @@ func (w *WebSocketReporter) handleConnection() {
 	// 启动消息接收goroutine
 	go w.receiveMessages()
 
-	// 主发送循环
-	ticker := time.NewTicker(w.pingInterval)
-	defer ticker.Stop()
+	// 指标上报 ticker
+	metricTicker := time.NewTicker(w.pingInterval)
+	defer metricTicker.Stop()
+
+	// 独立 WebSocket keepalive ping ticker
+	pingTicker := time.NewTicker(wsPingInterval)
+	defer pingTicker.Stop()
 
 	for {
 		select {
 		case <-w.ctx.Done():
 			return
-		case <-ticker.C:
+
+		case <-pingTicker.C:
+			// 发送 WebSocket ping 保活，独立于指标上报
+			w.connMutex.Lock()
+			conn := w.conn
+			isConnected := w.connected
+			w.connMutex.Unlock()
+			if !isConnected || conn == nil {
+				return
+			}
+			if err := conn.WriteControl(websocket.PingMessage, nil, time.Now().Add(reporterWriteWait)); err != nil {
+				fmt.Printf("❌ 发送WebSocket ping失败: %v，准备重连\n", err)
+				return
+			}
+
+		case <-metricTicker.C:
 			// 检查连接状态
 			w.connMutex.Lock()
 			isConnected := w.connected
@@ -548,6 +587,37 @@ func (w *WebSocketReporter) collectSystemInfo() SystemInfo {
 	}
 }
 
+// encryptPayload 加密 JSON 数据，返回加密后的消息字节（若加密失败则回退到原始数据）
+func (w *WebSocketReporter) encryptPayload(jsonData []byte) []byte {
+	if w.aesCrypto == nil {
+		return jsonData
+	}
+
+	encryptedData, err := w.aesCrypto.Encrypt(jsonData)
+	if err != nil {
+		fmt.Printf("⚠️ 加密失败，发送原始数据: %v\n", err)
+		return jsonData
+	}
+
+	encryptedMessage := map[string]interface{}{
+		"encrypted": true,
+		"data":      encryptedData,
+		"timestamp": time.Now().Unix(),
+	}
+	messageData, err := json.Marshal(encryptedMessage)
+	if err != nil {
+		fmt.Printf("⚠️ 序列化加密消息失败，发送原始数据: %v\n", err)
+		return jsonData
+	}
+	return messageData
+}
+
+// metricEnvelope wraps SystemInfo with a type field for fast identification on the panel side.
+type metricEnvelope struct {
+	Type string     `json:"type"`
+	Data SystemInfo `json:"data"`
+}
+
 // sendSystemInfo 发送系统信息
 func (w *WebSocketReporter) sendSystemInfo(sysInfo SystemInfo) error {
 	w.connMutex.Lock()
@@ -557,42 +627,19 @@ func (w *WebSocketReporter) sendSystemInfo(sysInfo SystemInfo) error {
 		return fmt.Errorf("连接未建立")
 	}
 
-	// 转换为JSON
-	jsonData, err := json.Marshal(sysInfo)
+	// 使用 type:"metric" 信封包装，Panel 可通过 type 字段直接识别指标消息
+	envelope := metricEnvelope{Type: "metric", Data: sysInfo}
+	jsonData, err := json.Marshal(envelope)
 	if err != nil {
 		return fmt.Errorf("序列化系统信息失败: %v", err)
 	}
 
-	var messageData []byte
+	messageData := w.encryptPayload(jsonData)
 
-	// 如果有加密器，则加密数据
-	if w.aesCrypto != nil {
-		encryptedData, err := w.aesCrypto.Encrypt(jsonData)
-		if err != nil {
-			fmt.Printf("⚠️ 加密失败，发送原始数据: %v\n", err)
-			messageData = jsonData
-		} else {
-			// 创建加密消息包装器
-			encryptedMessage := map[string]interface{}{
-				"encrypted": true,
-				"data":      encryptedData,
-				"timestamp": time.Now().Unix(),
-			}
-			messageData, err = json.Marshal(encryptedMessage)
-			if err != nil {
-				fmt.Printf("⚠️ 序列化加密消息失败，发送原始数据: %v\n", err)
-				messageData = jsonData
-			}
-		}
-	} else {
-		messageData = jsonData
-	}
-
-	// 设置写入超时
 	w.conn.SetWriteDeadline(time.Now().Add(5 * time.Second))
 
 	if err := w.conn.WriteMessage(websocket.TextMessage, messageData); err != nil {
-		w.connected = false // 标记连接已断开
+		w.connected = false
 		return fmt.Errorf("写入消息失败: %v", err)
 	}
 
@@ -601,23 +648,19 @@ func (w *WebSocketReporter) sendSystemInfo(sysInfo SystemInfo) error {
 
 // receiveMessages 接收服务端发送的消息
 func (w *WebSocketReporter) receiveMessages() {
+	// 获取连接引用一次即可，连接生命周期由 handleConnection 管理
+	w.connMutex.Lock()
+	conn := w.conn
+	w.connMutex.Unlock()
+	if conn == nil {
+		return
+	}
+
 	for {
 		select {
 		case <-w.ctx.Done():
 			return
 		default:
-			w.connMutex.Lock()
-			conn := w.conn
-			connected := w.connected
-			w.connMutex.Unlock()
-
-			if conn == nil || !connected {
-				return
-			}
-
-			// 设置读取超时
-			conn.SetReadDeadline(time.Now().Add(reporterReadWait))
-
 			messageType, message, err := conn.ReadMessage()
 			if err != nil {
 				if websocket.IsUnexpectedCloseError(err, websocket.CloseGoingAway, websocket.CloseAbnormalClosure) {
@@ -705,12 +748,8 @@ 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 == "ServiceMonitorCheck" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
-					go w.routeCommand(cmdMsg)
-				} else {
-					w.routeCommand(cmdMsg)
-				}
+				// 所有命令统一异步执行，避免阻塞消息接收循环
+				go w.routeCommand(cmdMsg)
 			}
 		} else {
 			// 处理普通消息
@@ -721,12 +760,8 @@ func (w *WebSocketReporter) handleReceivedMessage(messageType int, message []byt
 				return
 			}
 			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 == "ServiceMonitorCheck" || cmdMsg.Type == "UpgradeAgent" || cmdMsg.Type == "RollbackAgent" {
-					go w.routeCommand(cmdMsg)
-				} else {
-					w.routeCommand(cmdMsg)
-				}
+				// 所有命令统一异步执行，避免阻塞消息接收循环
+				go w.routeCommand(cmdMsg)
 			}
 		}
 
@@ -1400,30 +1435,7 @@ func (w *WebSocketReporter) sendResponse(response CommandResponse) {
 		return
 	}
 
-	var messageData []byte
-
-	// 如果有加密器，则加密数据
-	if w.aesCrypto != nil {
-		encryptedData, err := w.aesCrypto.Encrypt(jsonData)
-		if err != nil {
-			fmt.Printf("⚠️ 加密响应失败，发送原始数据: %v\n", err)
-			messageData = jsonData
-		} else {
-			// 创建加密消息包装器
-			encryptedMessage := map[string]interface{}{
-				"encrypted": true,
-				"data":      encryptedData,
-				"timestamp": time.Now().Unix(),
-			}
-			messageData, err = json.Marshal(encryptedMessage)
-			if err != nil {
-				fmt.Printf("⚠️ 序列化加密响应失败，发送原始数据: %v\n", err)
-				messageData = jsonData
-			}
-		}
-	} else {
-		messageData = jsonData
-	}
+	messageData := w.encryptPayload(jsonData)
 
 	// 检查消息大小，如果超过10MB则记录警告
 	if len(messageData) > 10*1024*1024 {

plans/054-agent-panel-comm-optimization.md

@@ -0,0 +1,147 @@
+# Agent-Panel 通信优化：提升稳定性与效率
+
+## 背景
+
+Agent（`go-gost/x/socket/websocket_reporter.go`）与 Panel（`go-backend/internal/ws/server.go`）之间通过 WebSocket 进行实时通信，包括指标上报（每 5s）、命令下发/响应、和流量上报（HTTP）。经过代码审查，以下是发现的问题和优化建议。
+
+---
+
+## 发现的问题
+
+### 1. Keepalive 时序不匹配 —— 导致误断连
+
+| 参数 | Agent 侧 | Panel 侧 |
+|------|----------|----------|
+| Read deadline | `reporterReadWait` = 60s | `wsPongWait` = 45s |
+| Ping 发送间隔 | 无主动 ping（靠指标数据 5s 续命） | `wsPingPeriod` = 15s |
+| Write timeout | `reporterWriteWait` = 5s | `wsWriteWait` = 5s |
+
+**问题**：Panel 每 15s 发 ping，Agent read deadline 60s，但 Panel pong deadline 只有 45s。如果 Agent 的指标消息被延迟（网络抖动），Panel 可能因 pong 超时而关闭连接。两侧的超时参数缺乏协调设计。
+
+### 2. 固定重连间隔 —— 无退避策略
+
+Agent 断线后以固定 5s 间隔重试（`reconnectTime = 5 * time.Second`），在 Panel 长时间不可用（升级、网络故障）的情况下，会产生大量无用连接尝试。
+
+### 3. Panel 侧每次解密都重建 AES 加密器
+
+`ws/server.go` 的 `decryptIfNeeded()` 和 `SendCommand()` 每次调用都 `security.NewAESCrypto(secret)` 重新创建 cipher（SHA256 + AES-GCM 初始化），对于高频指标消息（5s/次 × N 节点），有不必要的 CPU 开销。
+
+### 4. 指标消息使用 JSON Text 格式传输
+
+每 5s 发送一次包含 13 个字段的 SystemInfo JSON，加密后还需 base64 编码，一条消息约 300-500 bytes（加密后约 700 bytes）。对于大量节点场景，存在优化空间。
+
+### 5. `receiveMessages` 紧循环中有频繁锁竞争
+
+`receiveMessages()` 在每次 `ReadMessage()` 前都要 `Lock/Unlock connMutex` 检查连接状态，但 `ReadMessage` 本身是阻塞的，实际不需要在循环外检查。
+
+### 6. 状态变更命令阻塞读消息循环
+
+`routeCommand` 中的 Service/Chain/Limiter CRUD 命令是同步执行的，包括 `saveConfig()` 文件写入。执行期间会阻塞 `receiveMessages` 的读取循环。
+
+---
+
+## 推荐的优化方案（按优先级排列）
+
+### P0 — 高收益、低风险
+
+#### 优化 1：协调 Keepalive 参数
+
+**文件**：`websocket_reporter.go`
+
+- Agent 增加独立的 WebSocket ping 发送（每 20s），不依赖指标数据来维持连接
+- 统一 read deadline 设置，确保两侧 read timeout > 2×ping interval
+
+#### 优化 2：指数退避重连
+
+**文件**：`websocket_reporter.go`
+
+- 初始间隔 2s，按指数退避增长至最大 2 分钟
+- 连接成功后立即重置退避
+- 增加随机抖动（jitter）避免大量 Agent 同时重连
+
+#### 优化 3：Panel 侧缓存 AES 加密器
+
+**文件**：`ws/server.go`
+
+- 将 `AESCrypto` 实例缓存在 `nodeSession` 中，避免每条消息重建
+- `SendCommand` 复用缓存实例
+
+### P1 — 中等收益
+
+#### 优化 4：减少 `receiveMessages` 锁竞争
+
+**文件**：`websocket_reporter.go`
+
+- 将连接状态检查移到循环外，只在出错/关闭时通过 channel 通知退出
+- 用 `context.WithCancel` 代替锁检查 `connected` flag 来控制生命周期
+
+#### 优化 5：异步化状态变更命令处理
+
+**文件**：`websocket_reporter.go`
+
+- 所有命令统一异步执行（通过 goroutine + response channel），避免阻塞 readLoop
+- 当前只有 TcpPing/ServiceMonitorCheck/UpgradeAgent/RollbackAgent 是异步的
+
+---
+
+## 具体代码变更
+
+### Agent 侧 (`go-gost/x/socket`)
+
+---
+
+#### [MODIFY] [websocket_reporter.go](file:///Users/sagit/Documents/github/flvx/go-gost/x/socket/websocket_reporter.go)
+
+1. **指数退避重连**：将 `reconnectTime` 从固定 `5s` 改为动态退避字段，增加 `curBackoff/maxBackoff` 字段
+2. **独立 Ping 发送**：在 `handleConnection()` 中增加 WebSocket ping ticker（20s），独立于指标上报
+3. **减少锁竞争**：`receiveMessages` 中只在循环入口检查一次连接，此后靠 `ReadMessage` 的 error 退出
+4. **统一命令异步化**：所有 `routeCommand` 调用统一使用 goroutine
+
+---
+
+### Panel 侧 (`go-backend/internal/ws`)
+
+---
+
+#### [MODIFY] [server.go](file:///Users/sagit/Documents/github/flvx/go-backend/internal/ws/server.go)
+
+1. **缓存 AES 加密器**：在 `nodeSession` 中增加 `crypto *security.AESCrypto` 字段，节点连接时初始化
+2. **`decryptIfNeeded` 接收 crypto 参数**而非 secret 字符串
+3. **`SendCommand` 使用缓存 crypto** 实例
+
+---
+
+## Verification Plan
+
+### Automated Tests
+
+```bash
+# 运行现有 agent 侧单元测试（验证不回归）
+(cd go-gost/x && go test ./socket/... -v -count=1)
+
+# 运行现有流量上报测试
+(cd go-gost/x && go test ./service/... -v -count=1)
+
+# 运行 panel 侧全部测试
+(cd go-backend && go test ./... -count=1)
+```
+
+### Manual Verification
+
+> [!IMPORTANT]
+> 本次改动涉及实时通信核心路径，建议在 staging 环境部署后观察至少 30 分钟：
+> 1. 检查节点在面板中状态是否正常显示为在线
+> 2. 手动停止面板后观察 Agent 日志，确认重连间隔呈指数增长
+> 3. 恢复面板后确认 Agent 能自动恢复连接并恢复指标上报
+> 4. 通过面板下发命令（如添加/删除 service），确认命令执行成功
+
+---
+
+## 任务清单
+
+- [x] 优化 1：Agent 增加独立 WebSocket ping 发送
+- [x] 优化 2：Agent 指数退避重连
+- [x] 优化 3：Panel 缓存 AES 加密器
+- [x] 优化 4：Agent 减少 receiveMessages 锁竞争
+- [x] 优化 5：Agent 命令处理统一异步化
+- [x] 运行现有测试验证不回归

plans/055-tunnel-quality-periodic-probing.md

@@ -0,0 +1,31 @@
+# 055 - 隧道质量定时探测 + 实时展示 + 历史图表
+
+## 背景
+当前隧道质量检测是手动触发的：用户点击"诊断"按钮 → 后端调用节点 TcpPing → 返回结果。
+需求：改为**后端定时（每10秒）自动探测**所有启用隧道的质量（入口→出口延迟、出口→Bing延迟），
+结果保留历史（24h），前端隧道 Tab 实时展示 + 图表历史趋势。
+
+## 设计原则：与服务监控复用
+
+| 复用点 | 服务监控 | 隧道质量 |
+|--------|---------|---------|
+| 调度方式 | `health.Checker.Start(ctx)` via `jobs.go` | `tunnelQualityProber.Start(ctx)` via `jobs.go` |
+| 存储模式 | `service_monitor_result` (history, insert) | `tunnel_quality` (history, insert) |
+| 清理方式 | `PruneServiceMonitorResults(olderThanMs)` | `PruneTunnelQualityResults(olderThanMs)` |
+| 最新查询 | `GetLatestServiceMonitorResults()` (window func) | `GetLatestTunnelQualities()` (window func) |
+| 历史查询 | `GetServiceMonitorResults(id, limit)` | `GetTunnelQualityHistory(id, start, end)` |
+| API 模式 | `GET /monitor/services/{id}/results` | `GET /monitor/tunnels/{id}/quality` |
+| 前端图表 | Recharts LineChart (延迟趋势) | Recharts LineChart (同样模式) |
+
+## 任务清单
+
+- [x] 1. `TunnelQuality` model 改为历史存储（composite index, 非 unique）
+- [x] 2. Repo 改为 insert（非 upsert），复用服务监控的查询模式
+- [x] 3. 添加 `PruneTunnelQualityResults` + `GetLatestTunnelQualities` + `GetTunnelQualityHistory`
+- [x] 4. Prober 生命周期集成到 `jobs.go`（与 healthCheck 同级）
+- [x] 5. Prober 添加 24h 清理周期
+- [x] 6. 添加 API `GET /monitor/tunnels/{id}/quality` 返回历史
+- [x] 7. 前端添加 `getMonitorTunnelQualityHistory()` API
+- [x] 8. 前端详情页添加质量趋势图表（复用服务监控图表组件模式）
+- [x] 9. Go 编译 + 测试通过
+- [x] 10. TypeScript 编译通过

plans/056-tunnel-uptime-kuma-bars.md

@@ -0,0 +1,16 @@
+# Tunnel Quality Uptime Kuma Display
+**Plan ID**: 056-tunnel-uptime-kuma-bars.md
+
+## Objective
+The goal is to modify the "Monitor - Tunnel" UI page to remove the isolated "Quality" column/chip, and replace the specific latency readouts for entry->exit and exit->Bing with an Uptime Kuma style row of visual history bars.
+
+## Steps
+- [x] Remove the individual "Quality" column from the tunnel monitor table view.
+- [x] Remove the individual "Quality" chip from the tunnel monitor grid view.
+- [x] Implement `<UptimeHistoryBar />` to display a historical sequence of up to 30 metrics, coloring by latency (success, warning, danger) and packet loss (danger).
+- [x] Modify the front-end to poll/load initial tunnel quality history, effectively padding the history bars instead of them starting empty.
+- [x] Update `getMonitorTunnelQuality` auto-polling locally to append strictly to the local history state, truncating appropriately.
+- [x] Retain current latency display next to or below the Uptime bars to allow numerical visibility.
+
+## Status
+Completed. The interface will now load history for all displayed tunnels upon open, and continue tracking with bars appending in real time every 10-second polling interval.

vite-frontend/src/api/index.ts

@@ -40,6 +40,7 @@ import type {
   MonitorTunnelApiItem,
   MonitorPermissionApiItem,
   MonitorAccessApiData,
+  TunnelQualityApiItem,
 } from "./types";
 
 import axios from "axios";
@@ -451,6 +452,25 @@ export const getTunnelMetrics = (
 export const getMonitorTunnels = () =>
   Network.get<MonitorTunnelApiItem[]>("/monitor/tunnels");
 
+export const getMonitorTunnelQuality = () =>
+  Network.get<TunnelQualityApiItem[]>("/monitor/tunnels/quality");
+
+export const getMonitorTunnelQualityHistory = (
+  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<TunnelQualityApiItem[]>(
+    `/monitor/tunnels/${tunnelId}/quality`,
+    params,
+  );
+};
+
 export const getServiceMonitorList = () =>
   Network.get<ServiceMonitorApiItem[]>("/monitor/services");
 

vite-frontend/src/api/types.ts

@@ -487,3 +487,14 @@ export interface MonitorAccessApiData {
   allowed: boolean;
   reason?: string;
 }
+
+export interface TunnelQualityApiItem {
+  tunnelId: number;
+  entryToExitLatency: number;
+  exitToBingLatency: number;
+  entryToExitLoss: number;
+  exitToBingLoss: number;
+  success: boolean;
+  errorMessage?: string;
+  timestamp: number;
+}

vite-frontend/src/pages/limit.tsx

@@ -18,6 +18,15 @@ import {
   ModalFooter,
 } from "@/shadcn-bridge/heroui/modal";
 import { Chip } from "@/shadcn-bridge/heroui/chip";
+import { LayoutGrid, List } from "lucide-react";
+import {
+  Table,
+  TableHeader,
+  TableColumn,
+  TableBody,
+  TableRow,
+  TableCell,
+} from "@/shadcn-bridge/heroui/table";
 import {
   createSpeedLimit,
   getSpeedLimitList,
@@ -51,6 +60,10 @@ export default function LimitPage() {
     "",
   );
   const [isSearchVisible, setIsSearchVisible] = useState(false);
+  const [viewMode, setViewMode] = useLocalStorageState<"list" | "grid">(
+    "limit-view-mode",
+    "grid",
+  );
 
   const filteredRules = useMemo(() => {
     if (!searchKeyword.trim()) return rules;
@@ -231,13 +244,85 @@ export default function LimitPage() {
           />
         </div>
 
-        <Button color="primary" size="sm" variant="flat" onPress={handleAdd}>
-          新增
-        </Button>
+        <div className="flex items-center gap-2">
+          <Button
+            isIconOnly
+            size="sm"
+            variant="flat"
+            onPress={() => setViewMode(viewMode === "list" ? "grid" : "list")}
+          >
+            {viewMode === "list" ? <LayoutGrid className="w-4 h-4" /> : <List className="w-4 h-4" />}
+          </Button>
+          <Button color="primary" size="sm" variant="flat" onPress={handleAdd}>
+            新增
+          </Button>
+        </div>
       </div>
 
       {/* 统一卡片网格 */}
       {filteredRules.length > 0 ? (
+        viewMode === "list" ? (
+          <Card>
+          <Table
+            aria-label="限速规则列表"
+            className="overflow-x-auto min-w-full"
+            classNames={{
+              th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+              td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+              tr: "hover:bg-default-50/50 transition-colors",
+            }}
+          >
+            <TableHeader>
+              <TableColumn>规则名称</TableColumn>
+              <TableColumn>速度限制</TableColumn>
+              <TableColumn>操作</TableColumn>
+            </TableHeader>
+            <TableBody items={filteredRules}>
+              {(rule) => (
+                <TableRow key={rule.id}>
+                  <TableCell>
+                    <div className="flex items-center gap-2">
+                       <div
+                         className={`shrink-0 w-2 h-2 rounded-full ${
+                           rule.status === 1 ? "bg-success" : "bg-danger"
+                         }`}
+                       />
+                       <span className="font-medium text-foreground text-sm">
+                         {rule.name}
+                       </span>
+                    </div>
+                  </TableCell>
+                  <TableCell>
+                    <span className="text-sm font-mono text-default-600">
+                      {rule.speed} Mbps
+                    </span>
+                  </TableCell>
+                  <TableCell>
+                    <div className="flex flex-wrap items-center gap-1.5 min-w-max">
+                      <Button
+                        className="h-6 px-2 min-w-0 text-xs bg-indigo-50 text-indigo-600 hover:bg-indigo-100 dark:bg-indigo-950/30 dark:text-indigo-400"
+                        size="sm"
+                        variant="flat"
+                        onPress={() => handleEdit(rule)}
+                      >
+                        编辑
+                      </Button>
+                      <Button
+                        className="h-6 px-2 min-w-0 text-xs bg-rose-50 text-rose-600 hover:bg-rose-100 dark:bg-rose-950/30 dark:text-rose-400"
+                        size="sm"
+                        variant="flat"
+                        onPress={() => handleDelete(rule)}
+                      >
+                        删除
+                      </Button>
+                    </div>
+                  </TableCell>
+                </TableRow>
+              )}
+            </TableBody>
+          </Table>
+          </Card>
+        ) : (
         <StaggerList className="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 gap-4">
           {filteredRules.map((rule) => (
             <StaggerItem key={rule.id}>
@@ -324,6 +409,7 @@ export default function LimitPage() {
             </StaggerItem>
           ))}
         </StaggerList>
+        )
       ) : (
         /* 空状态 */
         <Card className="shadow-sm border border-gray-200 dark:border-gray-700 bg-default-50/50">

vite-frontend/src/pages/node.tsx

@@ -1768,7 +1768,15 @@ export default function NodePage() {
         />
       ) : viewMode === "list" ? (
         <Card>
-          <Table aria-label="节点列表" className="overflow-x-auto min-w-full">
+          <Table
+            aria-label="节点列表"
+            className="overflow-x-auto min-w-full"
+            classNames={{
+              th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+              td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+              tr: "hover:bg-default-50/50 transition-colors",
+            }}
+          >
             <TableHeader>
               <TableColumn className="w-12 px-4 whitespace-nowrap overflow-hidden">
                 <Checkbox

vite-frontend/src/pages/node/monitor-view.tsx

@@ -1065,7 +1065,15 @@ export function MonitorView({ nodeMap, viewMode = "grid" }: MonitorViewProps) {
             </div>
           ) : (
             <Card className="w-full">
-              <Table aria-label="节点列表">
+              <Table
+                aria-label="节点列表"
+                className="overflow-x-auto min-w-full"
+                classNames={{
+                  th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+                  td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+                  tr: "hover:bg-default-50/50 transition-colors",
+                }}
+              >
                 <TableHeader>
                   <TableColumn>状态</TableColumn>
                   <TableColumn>名称</TableColumn>
@@ -1084,7 +1092,7 @@ export function MonitorView({ nodeMap, viewMode = "grid" }: MonitorViewProps) {
                     const isOnline = node.connectionStatus === "online";
 
                     return (
-                      <TableRow key={node.id} className="border-b border-divider/50 last:border-b-0">
+                      <TableRow key={node.id}>
                         <TableCell>
                           <div className={`w-2 h-2 rounded-full ml-1 ${isOnline ? "bg-success" : "bg-danger"}`} />
                         </TableCell>
@@ -1536,7 +1544,15 @@ export function MonitorView({ nodeMap, viewMode = "grid" }: MonitorViewProps) {
                 <RefreshCw className="w-6 h-6 animate-spin" />
               </div>
             ) : modalResults.length > 0 ? (
-              <Table aria-label="监控记录" className="w-full">
+              <Table
+                aria-label="监控记录"
+                className="w-full overflow-x-auto"
+                classNames={{
+                  th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+                  td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+                  tr: "hover:bg-default-50/50 transition-colors",
+                }}
+              >
                 <TableHeader>
                   <TableColumn>时间</TableColumn>
                   <TableColumn>结果</TableColumn>

vite-frontend/src/pages/tunnel.tsx

@@ -45,6 +45,15 @@ import { Alert } from "@/shadcn-bridge/heroui/alert";
 import { Checkbox } from "@/shadcn-bridge/heroui/checkbox";
 import { Progress } from "@/shadcn-bridge/heroui/progress";
 import { Radio, RadioGroup } from "@/shadcn-bridge/heroui/radio";
+import { LayoutGrid, List } from "lucide-react";
+import {
+  Table,
+  TableHeader,
+  TableColumn,
+  TableBody,
+  TableRow,
+  TableCell,
+} from "@/shadcn-bridge/heroui/table";
 import {
   createTunnel,
   batchDeleteTunnelsWithForwards,
@@ -181,6 +190,10 @@ export default function TunnelPage() {
     "",
   );
   const [isSearchVisible, setIsSearchVisible] = useState(false);
+  const [viewMode, setViewMode] = useLocalStorageState<"list" | "grid">(
+    "tunnel-view-mode",
+    "grid",
+  );
 
   // 模态框状态
   const [modalOpen, setModalOpen] = useState(false);
@@ -1523,6 +1536,14 @@ export default function TunnelPage() {
                 >
                   批量
                 </Button>
+                <Button
+                  isIconOnly
+                  size="sm"
+                  variant="flat"
+                  onPress={() => setViewMode(viewMode === "list" ? "grid" : "list")}
+                >
+                  {viewMode === "list" ? <LayoutGrid className="w-4 h-4" /> : <List className="w-4 h-4" />}
+                </Button>
                 <Button
                   color="primary"
                   size="sm"
@@ -1556,6 +1577,131 @@ export default function TunnelPage() {
 
       {/* 隧道卡片网格 */}
       {tunnels.length > 0 ? (
+        viewMode === "list" ? (
+          <Card>
+          <Table
+            aria-label="隧道列表"
+            className="overflow-x-auto min-w-full"
+            classNames={{
+              th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+              td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+              tr: "hover:bg-default-50/50 transition-colors",
+            }}
+          >
+            <TableHeader>
+              {selectMode ? <TableColumn className="w-12 px-4 whitespace-nowrap overflow-hidden">
+                <Checkbox
+                  isSelected={selectedIds.size === sortedTunnels.length && sortedTunnels.length > 0}
+                  onValueChange={(checked) => checked ? selectAll() : deselectAll()}
+                />
+              </TableColumn> : <TableColumn className="w-0 p-0 overflow-hidden text-[0px]"></TableColumn>}
+              <TableColumn>隧道名称</TableColumn>
+              <TableColumn>类型</TableColumn>
+              <TableColumn>拓扑</TableColumn>
+              <TableColumn>流量统计</TableColumn>
+              <TableColumn>操作</TableColumn>
+            </TableHeader>
+            <TableBody items={sortedTunnels}>
+              {(tunnel) => {
+                const typeDisplay = getTunnelTypeDisplay(tunnel.type);
+                const tunnelTypeChipClassName =
+                  tunnel.type === 1
+                    ? "text-[10px] h-5 bg-primary-100 text-primary-800 border-primary-300 dark:bg-primary-900/45 dark:text-primary-200 dark:border-primary-700"
+                    : "text-[10px] h-5 bg-success-100 text-success-800 border-success-300 dark:bg-success-900/35 dark:text-success-200 dark:border-success-700";
+                    
+                return (
+                  <TableRow key={tunnel.id}>
+                    {selectMode ? <TableCell className="px-4">
+                      <Checkbox
+                        isSelected={selectedIds.has(tunnel.id)}
+                        onValueChange={() => toggleSelect(tunnel.id)}
+                      />
+                    </TableCell> : <TableCell className="w-0 p-0 overflow-hidden text-[0px]"></TableCell>}
+                    <TableCell>
+                      <div className="flex items-center gap-2">
+                        <div
+                          className={`shrink-0 w-2 h-2 rounded-full ${
+                            tunnel.status === 1 ? "bg-success" : "bg-danger"
+                          }`}
+                        />
+                        <span className="font-medium text-foreground text-sm">
+                          {tunnel.name}
+                        </span>
+                      </div>
+                    </TableCell>
+                    <TableCell>
+                      <Chip
+                        className={tunnelTypeChipClassName}
+                        color={typeDisplay.color as any}
+                        size="sm"
+                        variant="flat"
+                      >
+                        {typeDisplay.text}
+                      </Chip>
+                    </TableCell>
+                    <TableCell>
+                       <div className="flex items-center gap-1.5 text-xs">
+                          <span className="font-semibold text-primary-700 dark:text-primary-400">
+                            {tunnel.inNodeId?.length || 0}入口
+                          </span>
+                          <span className="text-default-400">→</span>
+                          <span className="font-semibold text-secondary-700 dark:text-secondary-400">
+                            {tunnel.type === 2 ? tunnel.chainNodes?.length || 0 : 0}跳
+                          </span>
+                          <span className="text-default-400">→</span>
+                          <span className="font-semibold text-success-700 dark:text-success-400">
+                            {tunnel.type === 2 ? tunnel.outNodeId?.length || 0 : tunnel.inNodeId?.length || 0}出口
+                          </span>
+                       </div>
+                    </TableCell>
+                    <TableCell>
+                       <div className="flex items-center gap-2 text-xs">
+                         <span className="text-default-500">{getTunnelFlowDisplay(tunnel.flow)}</span>
+                         <span className="text-default-300">|</span>
+                         <span className="text-default-500">{tunnel.trafficRatio}x</span>
+                         {tunnel.type === 2 && tunnel.ipPreference && (
+                           <>
+                             <span className="text-default-300">|</span>
+                             <span className="text-default-500">{tunnel.ipPreference === "v4" ? "IPv4" : "IPv6"}</span>
+                           </>
+                         )}
+                       </div>
+                    </TableCell>
+                    <TableCell>
+                      <div className="flex flex-wrap items-center gap-1.5 min-w-max">
+                        <Button
+                          className="h-6 px-2 min-w-0 text-xs bg-indigo-50 text-indigo-600 hover:bg-indigo-100 dark:bg-indigo-950/30 dark:text-indigo-400"
+                          size="sm"
+                          variant="flat"
+                          onPress={() => handleEdit(tunnel)}
+                        >
+                          编辑
+                        </Button>
+                        <Button
+                          className="h-6 px-2 min-w-0 text-xs bg-amber-50 text-amber-600 hover:bg-amber-100 dark:bg-amber-950/30 dark:text-amber-400"
+                          size="sm"
+                          variant="flat"
+                          onPress={() => handleDiagnose(tunnel)}
+                        >
+                          诊断
+                        </Button>
+                        <Button
+                          className="h-6 px-2 min-w-0 text-xs bg-rose-50 text-rose-600 hover:bg-rose-100 dark:bg-rose-950/30 dark:text-rose-400"
+                          size="sm"
+                          variant="flat"
+                          onPress={() => handleDelete(tunnel)}
+                        >
+                          删除
+                        </Button>
+                      </div>
+                    </TableCell>
+                  </TableRow>
+                );
+              }}
+            </TableBody>
+          </Table>
+          </Card>
+        ) : (
         <DndContext sensors={sensors} onDragEnd={handleDragEnd}>
           <SortableContext
             items={sortableTunnelIds}
@@ -1836,6 +1982,7 @@ export default function TunnelPage() {
             </div>
           </SortableContext>
         </DndContext>
+        )
       ) : (
         /* 空状态 */
         <Card className="shadow-sm border border-gray-200 dark:border-gray-700 bg-default-50/50">

vite-frontend/src/pages/user.tsx

@@ -1080,7 +1080,15 @@ export default function UserPage() {
         </Card>
       ) : viewMode === "list" ? (
         <Card>
-          <Table aria-label="用户列表" className="overflow-x-auto min-w-full">
+          <Table
+            aria-label="用户列表"
+            className="overflow-x-auto min-w-full"
+            classNames={{
+              th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+              td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+              tr: "hover:bg-default-50/50 transition-colors",
+            }}
+          >
             <TableHeader>
               <TableColumn>用户名</TableColumn>
               <TableColumn>流量统计</TableColumn>
@@ -1888,8 +1896,9 @@ export default function UserPage() {
                 <Table
                   aria-label="用户隧道权限列表"
                   classNames={{
-                    wrapper: "shadow-none",
-                    th: "bg-gray-50 dark:bg-gray-800 text-gray-700 dark:text-gray-300 font-medium",
+                    th: "bg-default-100/50 text-default-600 font-semibold text-sm border-b border-divider py-3 uppercase tracking-wider",
+                    td: "py-3 border-b border-divider/50 group-data-[last=true]:border-b-0",
+                    tr: "hover:bg-default-50/50 transition-colors",
                   }}
                 >
                   <TableHeader>