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>

ROADMAP2.md

@@ -304,9 +304,14 @@ and wired refs, one click or one CLI call.
   are rewritten on every remote reconcile and removed on teardown or
   local placement. Agents report managed-container states at every
   heartbeat — exits, OOMs, and crash loops land in inventory between
-  reconciles (tombstones never resurrect). Remote nodes run
+  reconciles (tombstones never resurrect). Remote sleep/wake shipped:
-  registry-pulled images only — git builds and remote sleep are
+  heartbeats carry per-container net counters, idle remote services
-  documented ceilings. Tag affinity shipped: `node_agents.tags`
+  lose replicas via agent remove + tombstones, and the route file
+  repoints at `/internal/wake-page/:id` on the backend — first hit
+  retriggers the wake reconcile, which recreates replicas and restores
+  real upstreams. Remote nodes run
+  registry-pulled images only — git builds are the remaining
+  documented ceiling. Tag affinity shipped: `node_agents.tags`
   (operator-set via `PUT /agents/:id` / `nodes update --tags`) +
   `services.placement_tags` — `auto` and `spread` only consider
   online schedulable agents carrying every required tag, tags are

app/backend/cmd/agent/main.go

@@ -210,25 +210,86 @@ func sendHeartbeat(ctx context.Context, client *http.Client, cfg agentConfig, ag
 }
 
 // managedContainerStates lists every containr-managed container's docker
-// state so the server can reflect exits and crash loops between reconciles.
+// state plus cumulative network counters — state keeps runtime honest,
-// One docker call per heartbeat; nil on error (states simply go stale).
+// net bytes let the sleeper detect idle remote services.
-func managedContainerStates() []map[string]string {
+func managedContainerStates() []map[string]interface{} {
 	out, err := runDocker("ps", "-a",
 		"--filter", "label=containr.managed=true",
 		"--format", "{{.Names}}\t{{.State}}")
 	if err != nil {
 		return nil
 	}
-	var states []map[string]string
+	netIO := containerNetIO()
+	var states []map[string]interface{}
 	for _, line := range strings.Split(out, "\n") {
 		parts := strings.SplitN(line, "\t", 2)
-		if len(parts) == 2 && parts[0] != "" {
+		if len(parts) != 2 || parts[0] == "" {
-			states = append(states, map[string]string{"name": parts[0], "state": parts[1]})
+			continue
 		}
+		entry := map[string]interface{}{"name": parts[0], "state": parts[1]}
+		if io, ok := netIO[parts[0]]; ok {
+			entry["rx_bytes"], entry["tx_bytes"] = io[0], io[1]
+		}
+		states = append(states, entry)
 	}
 	return states
 }
 
+// containerNetIO snapshots cumulative rx/tx per running container. Stats
+// only covers running containers — stopped replicas report state without
+// counters, which is all the sleeper needs.
+func containerNetIO() map[string][2]int64 {
+	out, err := runDocker("stats", "--no-stream",
+		"--format", "{{.Name}}\t{{.NetIO}}")
+	if err != nil {
+		return nil
+	}
+	result := map[string][2]int64{}
+	for _, line := range strings.Split(out, "\n") {
+		parts := strings.SplitN(line, "\t", 2)
+		if len(parts) != 2 {
+			continue
+		}
+		io := strings.Split(parts[1], "/")
+		if len(io) != 2 {
+			continue
+		}
+		result[parts[0]] = [2]int64{parseHumanBytes(io[0]), parseHumanBytes(io[1])}
+	}
+	return result
+}
+
+// parseHumanBytes converts docker's human units ("1.2kB", "3.4MB") to bytes.
+func parseHumanBytes(s string) int64 {
+	s = strings.TrimSpace(s)
+	var num float64
+	var unit string
+	if _, err := fmt.Sscanf(s, "%f%s", &num, &unit); err != nil {
+		return 0
+	}
+	switch strings.ToUpper(unit) {
+	case "B":
+		return int64(num)
+	case "KB":
+		return int64(num * 1e3)
+	case "MB":
+		return int64(num * 1e6)
+	case "GB":
+		return int64(num * 1e9)
+	case "TB":
+		return int64(num * 1e12)
+	case "KIB":
+		return int64(num * 1024)
+	case "MIB":
+		return int64(num * 1024 * 1024)
+	case "GIB":
+		return int64(num * 1024 * 1024 * 1024)
+	case "TIB":
+		return int64(num * 1024 * 1024 * 1024 * 1024)
+	}
+	return int64(num)
+}
+
 func processCommands(ctx context.Context, client *http.Client, cfg agentConfig, agentID string) error {
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, fmt.Sprintf("%s/api/agents/%s/commands", cfg.APIURL, agentID), nil)
 	if err != nil {

app/backend/internal/api/agents.go

@@ -207,6 +207,8 @@ type AgentHeartbeat struct {
 type AgentContainerState struct {
 	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 http.StatusServiceUnavailable, gin.H{"error": "deployment engine unavailable"}
-		return
 	}
 	id, err := uuid.Parse(c.Param("id"))
 	if err != nil {
-		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid service id"})
+		return http.StatusBadRequest, gin.H{"error": "invalid service id"}
-		return
 	}
 	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 http.StatusNotFound, gin.H{"error": "service not found"}
-		return
 	}
 	if service.Status == "running" || service.Status == "deployed" {
-		c.JSON(http.StatusOK, gin.H{"status": service.Status})
+		return http.StatusOK, gin.H{"status": service.Status}
-		return
 	}
 	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,
 	}
+	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
+// Agent heartbeat reports real docker state + net counters; reconcile
-// this node owns. Tombstones win — never resurrect a removed replica.
+// 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
+	// Agent heartbeat reports real docker state + net counters; reconcile
-	// this node owns. Tombstones win — never resurrect a removed replica.
+	// 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

app/backend/sqlc/queries/agents.sql

@@ -180,7 +180,7 @@ LIMIT 1;
 UPDATE node_agents SET tags = $2::jsonb, updated_at = NOW() WHERE id = $1;
 
 -- 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;
 
 -- name: SetAgentSchedulable :exec
@@ -204,10 +204,12 @@ ON CONFLICT (id) DO UPDATE SET
 DELETE FROM container_instances WHERE node_agent_id = $1 AND service_id = $2;
 
 -- name: UpdateContainerStateByName :exec
--- Agent heartbeat reports real docker state; reconcile inventory for rows
+-- Agent heartbeat reports real docker state + net counters; reconcile
--- this node owns. Tombstones win — never resurrect a removed replica.
+-- inventory for rows this node owns. Tombstones win — never resurrect a
+-- removed replica. $4 is the cumulative rx+tx byte counter.
 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';

app/frontend/src/generated/docs-snapshot.ts

@@ -40,7 +40,7 @@ export const bundledDocs: BundledDoc[] = [
     "path": "guides/CLI.md",
     "section": "guides",
     "title": "Containr CLI",
-    "markdown": "# Containr CLI\n\nThe CLI controls every part of a Containr instance — the same API surface\nthe web UI uses. Build it with `scripts/build-cli.sh` or\n`go build ./cmd/cli` from `app/backend`.\n\n## Authentication\n\nCreate a personal access token in the web UI under\n**Settings → Personal Access Tokens** (or `containr tokens create`), then:\n\n```bash\ncontainr auth login cnp_...                      # verify + store\ncontainr auth login cnp_... --url https://containr.example.com\ncontainr auth login cnp_... --name production    # named profile\ncontainr auth status                             # show active profile + identity\ncontainr auth logout\n```\n\nResolution order for every command: `--token`/`--api-url` flags >\n`CONTAINR_TOKEN`/`CONTAINR_API_URL` env > active profile >\n`http://localhost:8080/api/v1`. The active profile is `--profile` >\n`CONTAINR_PROFILE` > `current_profile` in `~/.containr.yaml`.\n\n## Output and scripting\n\n- `--json` prints the raw API response — safe to pipe and parse.\n- `--yes` / `-y` skips confirmation on destructive commands (delete,\n  revoke, restore, failover). Non-interactive shells refuse destructive\n  commands without it.\n- Exit codes are stable: `0` ok, `1` error, `2` auth/permission,\n  `3` not found, `4` validation, `5` unreachable.\n\n## Commands\n\n```\nauth login|logout|status         token auth and profiles\ntokens list|create|revoke        personal access tokens\nprojects list|get|create|delete\nservices list|get|create|update|delete|start|stop|restart|redeploy\nservices clone|move              duplicate config or re-parent a service\nservices domains list|add|remove|default|check   multi-domain + DNS preflight\nregistries list|add|update|remove  private-image pull credentials\nvolumes list|delete              docker volume inventory + cleanup (admin)\ndeploy <service-id>              trigger a deployment (--no-cache, --commit-hash, --branch)\ndeployments list|get|logs|rollback|cancel\nlogs <service-id> [--follow]     runtime logs (SSE follow)\nexec <service-id> -- <cmd>       one-off container command\nvariables list|set|unset         env vars (secrets masked; --redeploy applies them)\nvariables shared list|set|unset  project shared vars — referenced as ${{shared.KEY}}\ndatabases list|get|create|update|delete|action|backup|restore|download-backup|import-backup\n                               import-backup <id> <file.tar.gz|-> uploads an archive as a restore\n                               point; ships offsite too when a backup target is assigned\ndatabases list|get|create|update|delete|action|backup|restore|download-backup\n                               create --public exposes the port on all interfaces;\n                               update <id> --public/--public=false toggles it (container recreates, data persists)\ndatabases register <name>      register an external database (--type --host --port --database --username --password --ssl; probed before storing)\ndatabases test-connection      probe a connection — by id, or ad-hoc flags\nbackup-targets list|add|update|remove|test\n                               S3-compatible archive destinations; add/update probe the bucket\n                               first, empty --access-key/--secret-key on update keep stored keys;\n                               update <db-id> --backup-target assigns a target (\"\" clears it)\ncron list|get|create|delete|trigger|executions\ntemplates list|get|create|delete|deploy|plan|import-compose|deploy-graph\n                               deploy --name --var K=V; plan dry-resolves expressions;\n                               import-compose <compose.yml|-> converts a compose file into\n                               a v2 graph config; deploy-graph <project-id> <config.json|->\n                               deploys an ad-hoc service graph\nimport compose <project-id> <compose.yml|->\n                               deploys a docker-compose file straight into a project —\n                               no template row. DB images become managed databases\n                               attached under their service name; --var K=V overrides\n                               template variables\nnodes list|get|delete|tokens     node agents + onboarding tokens (admin)\nnodes add <user@host>            SSH bootstrap — one session installs the agent, then never needed again (--print for manual runs)\nnodes update|prune|commands      rename/auto-prune, bounded docker prune, command history\nmigrate railway                  pull a Railway project (services, vars, domains) via GraphQL and recreate it — --dry-run prints the plan\nmigrate dflow                    import a dflow project (services, vars, volumes, domains) via its Payload REST API — needs --url + --api-key, --dry-run prints the plan\nscaling status|policies|services|scale\nha status|alerts|health|policies|enable|disable|failover\nsecurity scan|vulnerabilities|metrics\ngateway services|keys|anLine truncated
+    "markdown": "# Containr CLI\n\nThe CLI controls every part of a Containr instance — the same API surface\nthe web UI uses. Build it with `scripts/build-cli.sh` or\n`go build ./cmd/cli` from `app/backend`.\n\n## Authentication\n\nCreate a personal access token in the web UI under\n**Settings → Personal Access Tokens** (or `containr tokens create`), then:\n\n```bash\ncontainr auth login cnp_...                      # verify + store\ncontainr auth login cnp_... --url https://containr.example.com\ncontainr auth login cnp_... --name production    # named profile\ncontainr auth status                             # show active profile + identity\ncontainr auth logout\n```\n\nResolution order for every command: `--token`/`--api-url` flags >\n`CONTAINR_TOKEN`/`CONTAINR_API_URL` env > active profile >\n`http://localhost:8080/api/v1`. The active profile is `--profile` >\n`CONTAINR_PROFILE` > `current_profile` in `~/.containr.yaml`.\n\n## Output and scripting\n\n- `--json` prints the raw API response — safe to pipe and parse.\n- `--yes` / `-y` skips confirmation on destructive commands (delete,\n  revoke, restore, failover). Non-interactive shells refuse destructive\n  commands without it.\n- Exit codes are stable: `0` ok, `1` error, `2` auth/permission,\n  `3` not found, `4` validation, `5` unreachable.\n\n## Commands\n\n```\nauth login|logout|status         token auth and profiles\ntokens list|create|revoke        personal access tokens\nprojects list|get|create|delete\nservices list|get|create|update|delete|start|stop|restart|redeploy\nservices clone|move              duplicate config or re-parent a service\nservices domains list|add|remove|default|check   multi-domain + DNS preflight\nregistries list|add|update|remove  private-image pull credentials\nvolumes list|delete              docker volume inventory + cleanup (admin)\ndeploy <service-id>              trigger a deployment (--no-cache, --commit-hash, --branch)\ndeployments list|get|logs|rollback|cancel\nlogs <service-id> [--follow]     runtime logs (SSE follow)\nexec <service-id> -- <cmd>       one-off container command\nvariables list|set|unset         env vars (secrets masked; --redeploy applies them)\nvariables shared list|set|unset  project shared vars — referenced as ${{shared.KEY}}\ndatabases list|get|create|update|delete|action|backup|restore|download-backup|import-backup\n                               import-backup <id> <file.tar.gz|-> uploads an archive as a restore\n                               point; ships offsite too when a backup target is assigned\ndatabases list|get|create|update|delete|action|backup|restore|download-backup\n                               create --public exposes the port on all interfaces;\n                               update <id> --public/--public=false toggles it (container recreates, data persists)\ndatabases register <name>      register an external database (--type --host --port --database --username --password --ssl; probed before storing)\ndatabases test-connection      probe a connection — by id, or ad-hoc flags\nbackup-targets list|add|update|remove|test\n                               S3-compatible archive destinations; add/update probe the bucket\n                               first, empty --access-key/--secret-key on update keep stored keys;\n                               update <db-id> --backup-target assigns a target (\"\" clears it)\ncron list|get|create|delete|trigger|executions\ntemplates list|get|create|delete|deploy|plan|import-compose|deploy-graph\n                               deploy --name --var K=V; plan dry-resolves expressions;\n                               import-compose <compose.yml|-> converts a compose file into\n                               a v2 graph config; deploy-graph <project-id> <config.json|->\n                               deploys an ad-hoc service graph\nimport compose <project-id> <compose.yml|->\n                               deploys a docker-compose file straight into a project —\n                               no template row. DB images become managed databases\n                               attached under their service name; --var K=V overrides\n                               template variables\nnodes list|get|delete|tokens     node agents + onboarding tokens (admin)\nnodes add <user@host>            SSH bootstrap — one session installs the agent, then never needed again (--print for manual runs)\nnodes update|prune|commands      rename/auto-prune, bounded docker prune, command history\nmigrate railway                  pull a Railway project (services, vars, domains) via GraphQL and recreate it — --dry-run prints the plan\nmigrate dflow                    import a dflow project (services, vars, volumes, domains) via its Payload REST API — needs --url + --api-key, --dry-run prints the plan\nscaling status|policies|services|scale\nha status|alerts|health|policies|enable|disable|failover\nsecurity scan|vulnerabilities|metrics\ngateway services|keys|anLine truncated
   },
   {
     "path": "guides/CLOUDFLARE_SETUP.md",

docs/guides/CLI.md

@@ -161,12 +161,15 @@ containr nodes update <id> --tags gpu,eu-west
 containr services update <id> --placement-tags gpu     # only gpu nodes are eligible
 ```
 
-Remote nodes run registry-pulled images only — git builds and sleep
+Remote nodes run registry-pulled images only — git builds stay local.
-detection stay local. Domains work remotely: the agent publishes the
+Domains work remotely: the agent publishes the service port and the
-service port and the backend writes a Traefik file-provider route to the
+backend writes a Traefik file-provider route to the node's mesh IP
-node's mesh IP (TRAEFIK_DYNAMIC_DIR — wired by the infra compose).
+(TRAEFIK_DYNAMIC_DIR — wired by the infra compose). Sleep mode works
-Start, stop, restart, redeploy, and delete all fan out to the pinned
+too: heartbeats carry per-container net counters, idle remote services
-node's agent. `services get` shows the resolved `node_name`.
+lose their replicas via the agent, and the route repoints at the
+backend's wake page — the next hit reconciles the service back. Start,
+stop, restart, redeploy, and delete all fan out to the pinned node's
+agent. `services get` shows the resolved `node_name`.
 
 Take a node out of rotation or empty it entirely (admin):
 

infra/docker-compose.yml

@@ -103,6 +103,7 @@ services:
       - CONTAINR_AGENT_AUTH_TOKEN=${CONTAINR_AGENT_AUTH_TOKEN:-}
       - CONTAINR_AGENT_AUTH_TOKENS=${CONTAINR_AGENT_AUTH_TOKENS:-}
       - TRAEFIK_DYNAMIC_DIR=/traefik-dynamic
+      - TRAEFIK_BACKEND_URL=http://containr-backend:8080
       - COOKIE_SECURE=${COOKIE_SECURE:-true}
       - TRUSTED_PROXY_CIDR=${TRUSTED_PROXY_CIDR:-172.20.0.0/16}
       - CORS_ORIGINS=${CORS_ORIGINS:-http://localhost,http://localhost:3000}