feat(nodes): remote sleep/wake — idle detection + wake-page ingress

Agents report per-container net IO at heartbeat; the sleeper measures
idleness from those counters for remote services, removes replicas via
the agent queue, and repoints the domain route at the backend's new
/internal/wake-page endpoint (replacePath + priority-100 route in the
file provider). First hit serves a reloading page and retriggers the
wake reconcile, which recreates replicas and restores real upstreams.

Manual POST /services/:id/sleep also routes remote; local sleep/wake
flow is unchanged.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

app/backend/internal/api/agents.go

@@ -205,8 +205,10 @@ type AgentHeartbeat struct {
 }
 
 type AgentContainerState struct {
-	Name  string `json:"name"`
-	State string `json:"state"`
+	Name    string `json:"name"`
+	State   string `json:"state"`
+	RxBytes int64  `json:"rx_bytes,omitempty"`
+	TxBytes int64  `json:"tx_bytes,omitempty"`
 }
 
 type SystemLoad struct {
@@ -681,10 +683,12 @@ func (h *NodeAgentHandler) SendHeartbeat(c *gin.Context) {
 			continue
 		}
 		stateJSON, _ := json.Marshal(rc.State)
+		bytesJSON, _ := json.Marshal(rc.RxBytes + rc.TxBytes)
 		_ = h.q.UpdateContainerStateByName(ctx, sqlcdb.UpdateContainerStateByNameParams{
 			Name:        rc.Name,
 			NodeAgentID: heartbeat.NodeAgentID,
 			Column3:     stateJSON,
+			Column4:     bytesJSON,
 		})
 	}
 

app/backend/internal/api/ingress.go

@@ -169,3 +169,44 @@ func removeServiceIngress(serviceID string) {
 	}
 	_ = os.Remove(ingressFile(serviceID))
 }
+
+// wakeUpstreamURL is where a sleeping remote service's route points —
+// the backend's wake-page endpoint. Defaults to the compose service name;
+// TRAEFIK_BACKEND_URL overrides for custom layouts.
+func wakeUpstreamURL(apiPort int) string {
+	if v := strings.TrimSpace(os.Getenv("TRAEFIK_BACKEND_URL")); v != "" {
+		return strings.TrimRight(v, "/")
+	}
+	return fmt.Sprintf("http://containr-backend:%d", apiPort)
+}
+
+// writeWakeIngress routes the service's domains at the wake-page endpoint —
+// first hit triggers the wake reconcile and serves a reloading page.
+func writeWakeIngress(serviceID string, domains []string, apiPort int) {
+	if ingressDir() == "" {
+		return
+	}
+	sort.Strings(domains)
+	router := "svc-" + serviceID[:8] + "-wake"
+	rules := make([]string, 0, len(domains))
+	for _, d := range domains {
+		rules = append(rules, "Host(`"+d+"`)")
+	}
+	var b strings.Builder
+	mw := router + "-rw"
+	b.WriteString("http:\n  routers:\n    " + router + ":\n")
+	b.WriteString("      rule: \"" + strings.Join(rules, " || ") + "\"\n")
+	b.WriteString("      entrypoints: [web]\n")
+	b.WriteString("      service: " + router + "\n")
+	b.WriteString("      priority: 100\n")
+	b.WriteString("      middlewares: [" + mw + "]\n")
+	b.WriteString("  middlewares:\n    " + mw + ":\n")
+	b.WriteString("      replacePath:\n        path: \"/api/v1/internal/wake-page/" + serviceID + "\"\n")
+	b.WriteString("  services:\n    " + router + ":\n      loadBalancer:\n        servers:\n")
+	b.WriteString("          - url: \"" + wakeUpstreamURL(apiPort) + "\"\n")
+	tmp := ingressFile(serviceID) + ".tmp"
+	if err := os.WriteFile(tmp, []byte(b.String()), 0o644); err != nil {
+		return
+	}
+	_ = os.Rename(tmp, ingressFile(serviceID))
+}

app/backend/internal/api/routes.go

@@ -285,6 +285,7 @@ func SetupRoutes(router *gin.Engine, db *database.DB, redis *database.Redis, cfg
 			// Wake callback for sleep-mode placeholders. Unauthenticated but
 			// non-destructive: it only reconciles the service back to running.
 			public.Any("/internal/wake/:id", handleServiceWake)
+			public.Any("/internal/wake-page/:id", handleServiceWakePage)
 		}
 
 		// Read routes — public browsing. OptionalAuth resolves a session when

app/backend/internal/api/sleeper.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	"containr/internal/database"
+	"containr/internal/database/sqlcdb"
 	"containr/internal/deployment"
 	"containr/internal/docker"
 
@@ -100,7 +101,20 @@ func sweepSleeping(ctx context.Context, db *database.DB, dc *docker.Client, engi
 	}
 	rows.Close()
 
+	q := sqlcdb.New(db.DB)
 	for _, svc := range candidates {
+		// Remote replicas live in inventory, not the local docker host —
+		// idleness comes from heartbeat-reported net counters instead.
+		if remote := remoteLiveContainers(ctx, q, svc.ID.String()); len(remote) > 0 {
+			var total uint64
+			for _, row := range remote {
+				total += rowNetBytes(row)
+			}
+			if markIdle(svc.ID, total, time.Duration(svc.IdleMinutes)*time.Minute) {
+				putToSleepRemote(ctx, db, q, svc, apiPort)
+			}
+			continue
+		}
 		containers, err := engine.ListServiceContainers(ctx, svc.ID.String())
 		if err != nil || len(containers) == 0 {
 			continue
@@ -125,6 +139,65 @@ func sweepSleeping(ctx context.Context, db *database.DB, dc *docker.Client, engi
 	}
 }
 
+// remoteLiveContainers returns inventory rows whose replicas are alive on
+// node agents — the signal that idleness must be measured remotely.
+func remoteLiveContainers(ctx context.Context, q *sqlcdb.Queries, serviceID string) []sqlcdb.ListServiceContainersRow {
+	rows, err := q.ListServiceContainers(ctx, serviceID)
+	if err != nil {
+		return nil
+	}
+	live := rows[:0]
+	for _, row := range rows {
+		var st struct {
+			State string `json:"state"`
+		}
+		if err := json.Unmarshal(row.Status.RawMessage, &st); err == nil &&
+			st.State != "" && st.State != "removed" && st.State != "sleeping" {
+			live = append(live, row)
+		}
+	}
+	return live
+}
+
+// rowNetBytes reads the cumulative rx+tx the agent reported at its last
+// heartbeat — 0 for rows written before the counter existed.
+func rowNetBytes(row sqlcdb.ListServiceContainersRow) uint64 {
+	var res struct {
+		NetBytes uint64 `json:"net_bytes"`
+	}
+	_ = json.Unmarshal(row.Resources.RawMessage, &res)
+	return res.NetBytes
+}
+
+// putToSleepRemote removes the service's remote replicas via their agents,
+// marks the service sleeping, and repoints the domain route at the wake
+// endpoint so inbound traffic brings it back.
+func putToSleepRemote(ctx context.Context, db *database.DB, q *sqlcdb.Queries, svc sleepCandidate, apiPort int) {
+	runner := newAgentNodeRunner(db)
+	for _, agentID := range remoteAgentsForService(ctx, db, svc.ID) {
+		if err := runner.ControlService(ctx, svc.ID.String(), agentID, "remove"); err != nil {
+			log.Printf("sleep: remote remove on %s failed: %v", agentID, err)
+			continue
+		}
+		_ = q.DeleteServiceContainersOnAgent(ctx, sqlcdb.DeleteServiceContainersOnAgentParams{
+			NodeAgentID: agentID,
+			ServiceID:   svc.ID.String(),
+		})
+	}
+	tracker.mu.Lock()
+	delete(tracker.activity, svc.ID)
+	tracker.mu.Unlock()
+	_, _ = db.Exec(`UPDATE services SET status = 'sleeping', updated_at = $1 WHERE id = $2`, time.Now(), svc.ID)
+	log.Printf("sleep: %s (%s) remote replicas removed after idle timeout", svc.Name, svc.ID)
+
+	var domain string
+	_ = db.QueryRow(`SELECT COALESCE(domain,'') FROM services WHERE id = $1`, svc.ID).Scan(&domain)
+	domains := serviceDomainNames(db, svc.ID, domain)
+	if len(domains) > 0 {
+		writeWakeIngress(svc.ID.String(), domains, apiPort)
+	}
+}
+
 // markIdle returns true when the network counter stopped growing past the
 // timeout. First sighting only sets the baseline — no idle without history.
 func markIdle(id uuid.UUID, bytes uint64, timeout time.Duration) bool {
@@ -346,18 +419,40 @@ func pruneWakeContainers(ctx context.Context, db *database.DB, dc *docker.Client
 // idempotent and non-destructive, so no token is required; the endpoint
 // never mutates configuration.
 func handleServiceWake(c *gin.Context) {
+	code, body := triggerServiceWake(c)
+	if code != 0 {
+		c.JSON(code, body)
+	}
+}
+
+// handleServiceWakePage is the remote ingress wake target — Traefik routes
+// a sleeping remote service's domain here via the file provider. Every hit
+// (re)triggers the wake reconcile and returns a reloading page.
+func handleServiceWakePage(c *gin.Context) {
+	triggerServiceWake(c)
+	c.Header("Content-Type", "text/html; charset=utf-8")
+	c.String(http.StatusOK, wakePageHTML)
+}
+
+const wakePageHTML = `<!doctype html><html><head><meta http-equiv="refresh" content="4"><title>Waking up</title>` +
+	`<style>body{font-family:system-ui,sans-serif;background:#0b0d12;color:#dde2ea;display:flex;align-items:center;justify-content:center;min-height:100vh;margin:0}` +
+	`.card{text-align:center;max-width:34rem;padding:2rem}h1{font-size:1.25rem;font-weight:600}p{color:#98a2b3}</style></head>` +
+	`<body><div class="card"><h1>Service is waking up</h1><p>This Containr service was sleeping and is resuming now. The page reloads automatically.</p></div></body></html>`
+
+// triggerServiceWake loads the service and reconciles it back to running
+// in the background. Returns (0, nil) when a response was already written
+// by an embedded handler path, else the JSON status to send.
+func triggerServiceWake(c *gin.Context) (int, gin.H) {
 	dbVal, _ := c.Get("db")
 	db := dbVal.(*database.DB)
 	engineVal, _ := c.Get("deployment_engine")
 	engine, _ := engineVal.(*deployment.DeploymentEngine)
 	if engine == nil {
-		c.JSON(http.StatusServiceUnavailable, gin.H{"error": "deployment engine unavailable"})
-		return
+		return http.StatusServiceUnavailable, gin.H{"error": "deployment engine unavailable"}
 	}
 	id, err := uuid.Parse(c.Param("id"))
 	if err != nil {
-		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid service id"})
-		return
+		return http.StatusBadRequest, gin.H{"error": "invalid service id"}
 	}
 	var service Service
 	err = db.QueryRow(
@@ -385,12 +480,10 @@ func handleServiceWake(c *gin.Context) {
 		&service.CreatedAt, &service.UpdatedAt,
 	)
 	if err != nil {
-		c.JSON(http.StatusNotFound, gin.H{"error": "service not found"})
-		return
+		return http.StatusNotFound, gin.H{"error": "service not found"}
 	}
 	if service.Status == "running" || service.Status == "deployed" {
-		c.JSON(http.StatusOK, gin.H{"status": service.Status})
-		return
+		return http.StatusOK, gin.H{"status": service.Status}
 	}
 	go func() {
 		ctx, cancel := context.WithTimeout(context.Background(), 3*time.Minute)
@@ -411,7 +504,7 @@ func handleServiceWake(c *gin.Context) {
 		}
 		_, _ = db.Exec(`UPDATE services SET status = $1, updated_at = $2 WHERE id = $3`, status, time.Now(), service.ID)
 	}()
-	c.JSON(http.StatusAccepted, gin.H{"status": "waking"})
+	return http.StatusAccepted, gin.H{"status": "waking"}
 }
 
 // handleServiceSleep puts a service to sleep immediately (owner+ only).
@@ -438,7 +531,12 @@ func handleServiceSleep(c *gin.Context) {
 		Name:      service.Name,
 		Status:    service.Status,
 	}
-	go putToSleep(context.Background(), db, dc, engine, svc, apiPortFromContext(c))
+	q := sqlcdb.New(db.DB)
+	if len(remoteLiveContainers(c.Request.Context(), q, service.ID.String())) > 0 {
+		go putToSleepRemote(context.Background(), db, q, svc, apiPortFromContext(c))
+	} else {
+		go putToSleep(context.Background(), db, dc, engine, svc, apiPortFromContext(c))
+	}
 	c.JSON(http.StatusAccepted, gin.H{"status": "sleeping"})
 }
 

app/backend/internal/database/sqlcdb/agents.sql.go

@@ -794,7 +794,7 @@ func (q *Queries) ListServiceAgents(ctx context.Context, serviceID string) ([]st
 }
 
 const listServiceContainers = `-- name: ListServiceContainers :many
-SELECT id, name, node_agent_id, status, ports FROM container_instances
+SELECT id, name, node_agent_id, status, ports, resources FROM container_instances
 WHERE service_id = $1
 `
 
@@ -804,6 +804,7 @@ type ListServiceContainersRow struct {
 	NodeAgentID string                `json:"node_agent_id"`
 	Status      pqtype.NullRawMessage `json:"status"`
 	Ports       pqtype.NullRawMessage `json:"ports"`
+	Resources   pqtype.NullRawMessage `json:"resources"`
 }
 
 func (q *Queries) ListServiceContainers(ctx context.Context, serviceID string) ([]ListServiceContainersRow, error) {
@@ -821,6 +822,7 @@ func (q *Queries) ListServiceContainers(ctx context.Context, serviceID string) (
 			&i.NodeAgentID,
 			&i.Status,
 			&i.Ports,
+			&i.Resources,
 		); err != nil {
 			return nil, err
 		}
@@ -1056,6 +1058,7 @@ func (q *Queries) UpdateContainerPorts(ctx context.Context, arg UpdateContainerP
 const updateContainerStateByName = `-- name: UpdateContainerStateByName :exec
 UPDATE container_instances SET
     status = jsonb_set(status, '{state}', $3::jsonb),
+    resources = jsonb_set(COALESCE(resources, '{}'::jsonb), '{net_bytes}', $4::jsonb),
     updated_at = NOW()
 WHERE name = $1 AND node_agent_id = $2
   AND status->>'state' IS DISTINCT FROM 'removed'
@@ -1065,12 +1068,19 @@ type UpdateContainerStateByNameParams struct {
 	Name        string          `json:"name"`
 	NodeAgentID string          `json:"node_agent_id"`
 	Column3     json.RawMessage `json:"column_3"`
+	Column4     json.RawMessage `json:"column_4"`
 }
 
-// Agent heartbeat reports real docker state; reconcile inventory for rows
-// this node owns. Tombstones win — never resurrect a removed replica.
+// Agent heartbeat reports real docker state + net counters; reconcile
+// inventory for rows this node owns. Tombstones win — never resurrect a
+// removed replica. $4 is the cumulative rx+tx byte counter.
 func (q *Queries) UpdateContainerStateByName(ctx context.Context, arg UpdateContainerStateByNameParams) error {
-	_, err := q.db.ExecContext(ctx, updateContainerStateByName, arg.Name, arg.NodeAgentID, arg.Column3)
+	_, err := q.db.ExecContext(ctx, updateContainerStateByName,
+		arg.Name,
+		arg.NodeAgentID,
+		arg.Column3,
+		arg.Column4,
+	)
 	return err
 }
 

app/backend/internal/database/sqlcdb/querier.go

@@ -139,8 +139,9 @@ type Querier interface {
 	// Agent reports the real host bindings after create — persist them with
 	// the status flip so ingress can route to the assigned port.
 	UpdateContainerPorts(ctx context.Context, arg UpdateContainerPortsParams) error
-	// Agent heartbeat reports real docker state; reconcile inventory for rows
-	// this node owns. Tombstones win — never resurrect a removed replica.
+	// Agent heartbeat reports real docker state + net counters; reconcile
+	// inventory for rows this node owns. Tombstones win — never resurrect a
+	// removed replica. $4 is the cumulative rx+tx byte counter.
 	UpdateContainerStateByName(ctx context.Context, arg UpdateContainerStateByNameParams) error
 	UpdateContainerStatus(ctx context.Context, arg UpdateContainerStatusParams) error
 	UpdateDatabaseServiceNameAndPlanByIDAndUser(ctx context.Context, arg UpdateDatabaseServiceNameAndPlanByIDAndUserParams) error