feat(nodes): remote ingress via Traefik file provider

Remote replicas publish an ephemeral host port; the agent reports the
assigned binding back in the create_container result and the backend
renders a per-service file-provider config into TRAEFIK_DYNAMIC_DIR
pointing Traefik at the node's mesh IP + port. Routes are rewritten on
every remote reconcile and removed on teardown or local placement.

Also: RetireService retires remote leftovers when a service returns to
local placement; remove_container is idempotent agent-side; tombstoned
replicas skip remove dispatch; the domains-stay-local ceiling is gone.

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

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

.env.example

@@ -49,6 +49,10 @@ CONTAINR_AGENT_AUTH_TOKEN=replace_with_strong_agent_secret
 # CONTAINR_AGENT_AUTH_TOKENS=current_secret,next_secret
 # Bundled agent binaries dir served at /api/agents/download/:platform.
 # CONTAINR_AGENT_BIN_DIR=/agents
+# Directory Traefik's file provider watches. The backend writes one
+# config per remote service here so domains route to node agents. The
+# infra compose wires a shared volume — set only for custom layouts.
+# TRAEFIK_DYNAMIC_DIR=/traefik-dynamic
 # Optional remote template catalog (another Containr instance). Its
 # templates merge into GET /templates as source:"registry" and
 # materialize locally on deploy. The bundled catalog works without it.

ROADMAP2.md

@@ -296,9 +296,15 @@ and wired refs, one click or one CLI call.
   utilisation, then cpu, then container count, with uninstrumented
   agents sorting last. Lifecycle and `GET /runtime` are
   inventory-driven, so remote replicas show up and tear down wherever
-  they run. Remote nodes run registry-pulled
+  they run. Remote ingress shipped: the agent reports assigned host
-  images only — git builds, Traefik domains, and remote sleep are
+  ports in the `create_container` result, the backend renders a
-  documented ceilings. Tag affinity shipped: `node_agents.tags`
+  Traefik file-provider config per remote service into
+  `TRAEFIK_DYNAMIC_DIR` (shared volume, `watch=true`) pointing the
+  loadbalancer at each replica's mesh IP + published port; route files
+  are rewritten on every remote reconcile and removed on teardown or
+  local placement. Remote nodes run registry-pulled
+  images only — git builds and remote sleep are documented ceilings.
+  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

@@ -272,7 +272,12 @@ func executeCommand(item command) (string, error) {
 	case "restart_container":
 		return runDocker("restart", commandTarget(item.Payload))
 	case "remove_container":
-		return runDocker("rm", "-f", commandTarget(item.Payload))
+		out, err := runDocker("rm", "-f", commandTarget(item.Payload))
+		// A missing container is the desired end state — report success.
+		if err != nil && strings.Contains(out, "No such container") {
+			return out, nil
+		}
+		return out, err
 	case "prune":
 		return dockerPrune(item.Payload)
 	case "system_df":
@@ -460,7 +465,25 @@ func createContainer(payload map[string]interface{}) (string, error) {
 		logs, _ := runDocker("logs", "--tail", "5", name)
 		return "", fmt.Errorf("container %s is %q after start: %s", name, state, logs)
 	}
-	return name, nil
+	// Report the real host port bindings — ephemeral publishes pick a port
+	// the server can't guess, and remote ingress needs the actual mapping.
+	hostPorts := map[string]string{}
+	portsJSON, _ := runDocker("inspect", "-f", "{{json .NetworkSettings.Ports}}", name)
+	var bindings map[string][]struct {
+		HostIP   string `json:"HostIp"`
+		HostPort string `json:"HostPort"`
+	}
+	if json.Unmarshal([]byte(portsJSON), &bindings) == nil {
+		for cport, addrs := range bindings {
+			for _, a := range addrs {
+				if a.HostPort != "" && a.HostPort != "0" {
+					hostPorts[cport] = a.HostPort
+				}
+			}
+		}
+	}
+	out, _ := json.Marshal(map[string]interface{}{"name": name, "host_ports": hostPorts})
+	return string(out), nil
 }
 
 // registryHostOf mirrors the server's registryHost: first path segment with

app/backend/internal/api/ingress.go

@@ -0,0 +1,171 @@
+package api
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	"containr/internal/database"
+	"containr/internal/database/sqlcdb"
+	"containr/internal/deployment"
+)
+
+// Remote ingress: replicas on node agents aren't on the hub's
+// containr-network, so Traefik's Docker provider can't see them. Instead
+// the backend renders one file-provider config per service into
+// TRAEFIK_DYNAMIC_DIR (a directory Traefik watches), pointing the
+// loadbalancer at the node's reachable IP + the ephemeral host port the
+// agent reported back after `create_container`.
+//
+// Empty dir → feature off (bare-metal dev). Files are best-effort: a
+// failed write never fails a reconcile.
+
+func ingressDir() string { return os.Getenv("TRAEFIK_DYNAMIC_DIR") }
+
+func ingressFile(serviceID string) string {
+	return filepath.Join(ingressDir(), "containr-"+serviceID+".yml")
+}
+
+// jsonInt coerces JSON-ish numbers (int/int32/int64/float64) to int —
+// spec fields arrive as int32, agent payloads unmarshal as float64.
+func jsonInt(v interface{}) int {
+	switch n := v.(type) {
+	case int:
+		return n
+	case int32:
+		return int(n)
+	case int64:
+		return int(n)
+	case float64:
+		return int(n)
+	}
+	return 0
+}
+
+// reportedHostPorts parses the agent's create_container result —
+// {"name": ..., "host_ports": {"80/tcp": "32768"}}. Older agents return a
+// bare name string; JSON parse failure means no port info.
+func reportedHostPorts(result string) map[string]string {
+	var out struct {
+		HostPorts map[string]string `json:"host_ports"`
+	}
+	if json.Unmarshal([]byte(result), &out) != nil {
+		return nil
+	}
+	return out.HostPorts
+}
+
+// nodeIngressIP picks the address the hub can reach the node on. Mesh
+// overlays first — the agent operator joined a mesh precisely so the hub
+// can reach it — then the reported primary IP as a LAN fallback.
+func nodeIngressIP(agent sqlcdb.NodeAgent) string {
+	var meta struct {
+		Mesh map[string]string `json:"mesh"`
+	}
+	_ = json.Unmarshal(agent.Metadata.RawMessage, &meta)
+	for _, prefix := range []string{"tailscale", "netbird", "wg", "zt"} {
+		var keys []string
+		for name := range meta.Mesh {
+			keys = append(keys, name)
+		}
+		sort.Strings(keys)
+		for _, name := range keys {
+			if strings.HasPrefix(name, prefix) && meta.Mesh[name] != "" {
+				return meta.Mesh[name]
+			}
+		}
+	}
+	return agent.IpAddress
+}
+
+// syncRemoteIngress rewrites the service's file-provider config from the
+// live remote replica set. Called after every remote reconcile so replica
+// adds/removals and node retargets converge the upstream list.
+func syncRemoteIngress(ctx context.Context, db *database.DB, spec deployment.RuntimeSpec) {
+	if ingressDir() == "" {
+		return
+	}
+	domains := spec.Domains
+	if len(domains) == 0 && spec.Domain != "" {
+		domains = []string{spec.Domain}
+	}
+	if len(domains) == 0 || spec.Port <= 0 {
+		removeServiceIngress(spec.ServiceID)
+		return
+	}
+
+	q := sqlcdb.New(db.DB)
+	rows, err := q.ListServiceContainers(ctx, spec.ServiceID)
+	if err != nil {
+		return
+	}
+	type upstream struct{ ip, port string }
+	var servers []upstream
+	for _, row := range rows {
+		var st struct {
+			State string `json:"state"`
+		}
+		_ = json.Unmarshal(row.Status.RawMessage, &st)
+		if st.State != "running" {
+			continue
+		}
+		var port string
+		var plist []map[string]interface{}
+		if err := json.Unmarshal(row.Ports.RawMessage, &plist); err == nil {
+			for _, p := range plist {
+				if hp, ok := p["host_port"].(float64); ok && hp > 0 {
+					port = fmt.Sprintf("%d", int(hp))
+				}
+			}
+		}
+		if port == "" {
+			continue
+		}
+		agent, err := q.GetAgent(ctx, row.NodeAgentID)
+		if err != nil {
+			continue
+		}
+		if ip := nodeIngressIP(agent); ip != "" {
+			servers = append(servers, upstream{ip, port})
+		}
+	}
+	if len(servers) == 0 {
+		removeServiceIngress(spec.ServiceID)
+		return
+	}
+
+	router := "svc-" + spec.ServiceID[:8]
+	rules := make([]string, 0, len(domains))
+	for _, d := range domains {
+		rules = append(rules, "Host(`"+d+"`)")
+	}
+	var b strings.Builder
+	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("  services:\n    " + router + ":\n      loadBalancer:\n        servers:\n")
+	for _, s := range servers {
+		b.WriteString("          - url: \"http://" + s.ip + ":" + s.port + "\"\n")
+	}
+	// Atomic-ish: write temp then rename so Traefik's watcher never reads a
+	// truncated file.
+	tmp := ingressFile(spec.ServiceID) + ".tmp"
+	if err := os.WriteFile(tmp, []byte(b.String()), 0o644); err != nil {
+		return
+	}
+	_ = os.Rename(tmp, ingressFile(spec.ServiceID))
+}
+
+// removeServiceIngress deletes the service's remote route. Called on
+// remote teardown and when a service returns to local placement.
+func removeServiceIngress(serviceID string) {
+	if ingressDir() == "" {
+		return
+	}
+	_ = os.Remove(ingressFile(serviceID))
+}

app/backend/internal/api/noderunner.go

@@ -19,8 +19,8 @@ import (
 
 // agentNodeRunner implements deployment.NodeRunner by dispatching container
 // lifecycle commands to a node agent's command queue and waiting for the
-// reported result. Remote nodes have no Traefik — domains stay local-only
+// reported result. Domains route through the file provider —
-// until per-node ingress lands.
+// syncRemoteIngress renders per-service configs from live inventory.
 type agentNodeRunner struct {
 	q  *sqlcdb.Queries
 	db *database.DB
@@ -131,10 +131,6 @@ func (r *agentNodeRunner) RemoteRuntimeState(ctx context.Context, serviceID stri
 // targetFor and retires stale replicas on any agent — including leftovers
 // from a previous pin or a different spread assignment.
 func (r *agentNodeRunner) reconcileOnAgents(ctx context.Context, spec deployment.RuntimeSpec, targetFor func(replica int) string) (*deployment.RuntimeState, error) {
-	if len(spec.Domains) > 0 || spec.Domain != "" {
-		return nil, fmt.Errorf("domains are routed by the local Traefik — remove the service's domains or run it on the local node")
-	}
-
 	replicas := spec.Replicas
 	if replicas < 1 {
 		replicas = 1
@@ -151,7 +147,7 @@ func (r *agentNodeRunner) reconcileOnAgents(ctx context.Context, spec deployment
 		if keep {
 			continue
 		}
-		if cmdErr := r.enqueueAndWait(ctx, row.NodeAgentID, "", "remove_container",
+		if _, cmdErr := r.enqueueAndWait(ctx, row.NodeAgentID, "", "remove_container",
 			map[string]interface{}{"container_name": row.Name}); cmdErr != nil {
 			return nil, fmt.Errorf("remove stale replica %s on node %s: %w", row.Name, row.NodeAgentID, cmdErr)
 		}
@@ -185,18 +181,41 @@ func (r *agentNodeRunner) reconcileOnAgents(ctx context.Context, spec deployment
 			HealthCheck:   rawJSON(map[string]interface{}{"path": spec.HealthPath}),
 		})
 
-		if err := r.enqueueAndWait(ctx, agentID, containerID, "create_container",
+		result, err := r.enqueueAndWait(ctx, agentID, containerID, "create_container",
-			map[string]interface{}{"container": container}); err != nil {
+			map[string]interface{}{"container": container})
+		if err != nil {
 			return nil, fmt.Errorf("replica %d on node %s: %w", i, agentID, err)
 		}
+		if assigned := reportedHostPorts(result); len(assigned) > 0 {
+			for _, p := range ports {
+				pm, ok := p.(map[string]interface{})
+				if !ok {
+					continue
+				}
+				cport := jsonInt(pm["container_port"])
+				proto, _ := pm["protocol"].(string)
+				if hp, ok := assigned[fmt.Sprintf("%d/%s", cport, proto)]; ok {
+					if n, err := strconv.Atoi(hp); err == nil {
+						pm["host_port"] = n
+					}
+				}
+			}
+			_ = r.q.UpdateContainerPorts(ctx, sqlcdb.UpdateContainerPortsParams{
+				ID:     containerID,
+				Status: rawJSON(map[string]interface{}{"state": "running", "health": "none"}),
+				Ports:  rawJSON(ports),
+			})
+		} else {
 			_ = r.q.UpdateContainerStatus(ctx, sqlcdb.UpdateContainerStatusParams{
 				ID:     containerID,
 				Status: rawJSON(map[string]interface{}{"state": "running", "health": "none"}),
 			})
+		}
 		state.Containers = append(state.Containers, deployment.RuntimeContainer{
 			ID: containerID, Name: name, State: "running", Replica: i,
 		})
 	}
+	syncRemoteIngress(ctx, r.db, spec)
 	return state, nil
 }
 
@@ -296,7 +315,17 @@ func (r *agentNodeRunner) ControlService(ctx context.Context, serviceID, agentID
 		if row.ServiceID != serviceID {
 			continue
 		}
-		if err := r.enqueueAndWait(ctx, agentID, row.ID, cmdType,
+		// Tombstoned replicas are already gone remotely — skip the dispatch
+		// or a fresh docker rm on a missing name reports a false failure.
+		if action == "remove" {
+			var st struct {
+				State string `json:"state"`
+			}
+			if err := json.Unmarshal(row.Status.RawMessage, &st); err == nil && st.State == "removed" {
+				continue
+			}
+		}
+		if _, err := r.enqueueAndWait(ctx, agentID, row.ID, cmdType,
 			map[string]interface{}{"container_name": row.Name}); err != nil {
 			return fmt.Errorf("%s %s on node: %w", action, row.Name, err)
 		}
@@ -314,16 +343,38 @@ func (r *agentNodeRunner) RemoveService(ctx context.Context, serviceID, agentID
 	if err := r.ControlService(ctx, serviceID, agentID, "remove"); err != nil {
 		return err
 	}
-	return r.q.DeleteServiceContainersOnAgent(ctx, sqlcdb.DeleteServiceContainersOnAgentParams{
+	if err := r.q.DeleteServiceContainersOnAgent(ctx, sqlcdb.DeleteServiceContainersOnAgentParams{
 		NodeAgentID: agentID,
 		ServiceID:   serviceID,
-	})
+	}); err != nil {
+		return err
+	}
+	removeServiceIngress(serviceID)
+	return nil
+}
+
+// RetireService removes the service's remote replicas wherever they run —
+// called when the service converges to local placement so a cleared pin or
+// removed tag requirement doesn't leave containers behind.
+func (r *agentNodeRunner) RetireService(ctx context.Context, serviceID string) error {
+	agentIDs, err := r.q.ListServiceAgents(ctx, serviceID)
+	if err != nil {
+		return err
+	}
+	for _, agentID := range agentIDs {
+		if err := r.RemoveService(ctx, serviceID, agentID); err != nil {
+			return fmt.Errorf("retire on node %s: %w", agentID, err)
+		}
+	}
+	removeServiceIngress(serviceID)
+	return nil
 }
 
 // enqueueAndWait pushes a command to the agent's queue and polls for the
-// reported result. Agents poll on their own interval (≥5s), so this blocks —
+// reported result, returning the agent's result string on success. Agents
-// it runs inside the deploy queue worker, never on a request path.
+// poll on their own interval (≥5s), so this blocks — it runs inside the
-func (r *agentNodeRunner) enqueueAndWait(ctx context.Context, agentID, containerID, cmdType string, payload map[string]interface{}) error {
+// deploy queue worker, never on a request path.
+func (r *agentNodeRunner) enqueueAndWait(ctx context.Context, agentID, containerID, cmdType string, payload map[string]interface{}) (string, error) {
 	var cid sql.NullString
 	if containerID != "" {
 		cid = sql.NullString{String: containerID, Valid: true}
@@ -336,7 +387,7 @@ func (r *agentNodeRunner) enqueueAndWait(ctx context.Context, agentID, container
 		Payload:     rawJSON(payload),
 	})
 	if err != nil {
-		return err
+		return "", err
 	}
 
 	deadline := time.Now().Add(8 * time.Minute) // image pulls on a cold node
@@ -348,20 +399,20 @@ func (r *agentNodeRunner) enqueueAndWait(ctx context.Context, agentID, container
 		if err == nil {
 			switch row.Status.String {
 			case "completed":
-				return nil
+				return row.Result.String, nil
 			case "failed":
 				if row.Error.Valid && row.Error.String != "" {
-					return fmt.Errorf("agent: %s", row.Error.String)
+					return "", fmt.Errorf("agent: %s", row.Error.String)
 				}
-				return fmt.Errorf("agent reported failure")
+				return "", fmt.Errorf("agent reported failure")
 			}
 		}
 		if time.Now().After(deadline) {
-			return fmt.Errorf("command %s timed out waiting for the agent", cmdType)
+			return "", fmt.Errorf("command %s timed out waiting for the agent", cmdType)
 		}
 		select {
 		case <-ctx.Done():
-			return ctx.Err()
+			return "", ctx.Err()
 		case <-time.After(2 * time.Second):
 		}
 	}

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

@@ -765,8 +765,36 @@ func (q *Queries) ListSchedulableAgentsMatching(ctx context.Context, dollar_1 js
 	return items, nil
 }
 
+const listServiceAgents = `-- name: ListServiceAgents :many
+SELECT DISTINCT node_agent_id FROM container_instances WHERE service_id = $1
+`
+
+// Distinct agents holding inventory rows for a service.
+func (q *Queries) ListServiceAgents(ctx context.Context, serviceID string) ([]string, error) {
+	rows, err := q.db.QueryContext(ctx, listServiceAgents, serviceID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	items := []string{}
+	for rows.Next() {
+		var node_agent_id string
+		if err := rows.Scan(&node_agent_id); err != nil {
+			return nil, err
+		}
+		items = append(items, node_agent_id)
+	}
+	if err := rows.Close(); err != nil {
+		return nil, err
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
 const listServiceContainers = `-- name: ListServiceContainers :many
-SELECT id, name, node_agent_id, status FROM container_instances
+SELECT id, name, node_agent_id, status, ports FROM container_instances
 WHERE service_id = $1
 `
 
@@ -775,6 +803,7 @@ type ListServiceContainersRow struct {
 	Name        string                `json:"name"`
 	NodeAgentID string                `json:"node_agent_id"`
 	Status      pqtype.NullRawMessage `json:"status"`
+	Ports       pqtype.NullRawMessage `json:"ports"`
 }
 
 func (q *Queries) ListServiceContainers(ctx context.Context, serviceID string) ([]ListServiceContainersRow, error) {
@@ -791,6 +820,7 @@ func (q *Queries) ListServiceContainers(ctx context.Context, serviceID string) (
 			&i.Name,
 			&i.NodeAgentID,
 			&i.Status,
+			&i.Ports,
 		); err != nil {
 			return nil, err
 		}
@@ -1005,6 +1035,24 @@ func (q *Queries) UpdateAgentHeartbeat(ctx context.Context, arg UpdateAgentHeart
 	return err
 }
 
+const updateContainerPorts = `-- name: UpdateContainerPorts :exec
+UPDATE container_instances SET status = $2, ports = $3, updated_at = NOW()
+WHERE id = $1
+`
+
+type UpdateContainerPortsParams struct {
+	ID     string                `json:"id"`
+	Status pqtype.NullRawMessage `json:"status"`
+	Ports  pqtype.NullRawMessage `json:"ports"`
+}
+
+// Agent reports the real host bindings after create — persist them with
+// the status flip so ingress can route to the assigned port.
+func (q *Queries) UpdateContainerPorts(ctx context.Context, arg UpdateContainerPortsParams) error {
+	_, err := q.db.ExecContext(ctx, updateContainerPorts, arg.ID, arg.Status, arg.Ports)
+	return err
+}
+
 const updateContainerStatus = `-- name: UpdateContainerStatus :exec
 UPDATE container_instances SET status = $2, updated_at = NOW()
 WHERE id = $1

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

@@ -98,6 +98,8 @@ type Querier interface {
 	ListSchedulableAgents(ctx context.Context) ([]ListSchedulableAgentsRow, error)
 	// Only agents carrying every required placement tag (jsonb array containment).
 	ListSchedulableAgentsMatching(ctx context.Context, dollar_1 json.RawMessage) ([]ListSchedulableAgentsMatchingRow, error)
+	// Distinct agents holding inventory rows for a service.
+	ListServiceAgents(ctx context.Context, serviceID string) ([]string, error)
 	ListServiceContainers(ctx context.Context, serviceID string) ([]ListServiceContainersRow, error)
 	ListServiceTemplatesByCategoryForUser(ctx context.Context, arg ListServiceTemplatesByCategoryForUserParams) ([]ServiceTemplate, error)
 	ListServiceTemplatesForUser(ctx context.Context, ownerID uuid.NullUUID) ([]ServiceTemplate, error)
@@ -134,6 +136,9 @@ type Querier interface {
 	UpdateAgentHeartbeat(ctx context.Context, arg UpdateAgentHeartbeatParams) error
 	UpdateBackupTargetByIDAndUser(ctx context.Context, arg UpdateBackupTargetByIDAndUserParams) error
 	UpdateBanner(ctx context.Context, arg UpdateBannerParams) (Banner, error)
+	// 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
 	UpdateContainerStatus(ctx context.Context, arg UpdateContainerStatusParams) error
 	UpdateDatabaseServiceNameAndPlanByIDAndUser(ctx context.Context, arg UpdateDatabaseServiceNameAndPlanByIDAndUserParams) error
 	UpdateDatabaseServiceNameByIDAndUser(ctx context.Context, arg UpdateDatabaseServiceNameByIDAndUserParams) error

app/backend/internal/deployment/engine.go

@@ -32,6 +32,9 @@ type NodeRunner interface {
 	// RemoteRuntimeState reads the service's remote replicas from inventory
 	// across all agents. nil/empty means nothing runs remotely.
 	RemoteRuntimeState(ctx context.Context, serviceID string) (*RuntimeState, error)
+	// RetireService removes every remote replica of the service across all
+	// agents — used when a service returns to local placement.
+	RetireService(ctx context.Context, serviceID string) error
 }
 
 type DeploymentEngine struct {

app/backend/internal/deployment/runtime.go

@@ -182,6 +182,12 @@ func (de *DeploymentEngine) ReconcileService(ctx context.Context, spec RuntimeSp
 		}
 		return de.nodeRunner.ReconcileAuto(ctx, spec)
 	}
+	// Local placement: retire any remote leftovers from a previous pin,
+	// spread, or tag affinity before reconciling local replicas.
+	if de.nodeRunner != nil {
+		_ = de.nodeRunner.RetireService(ctx, spec.ServiceID)
+	}
+
 	if spec.Replicas < 1 {
 		spec.Replicas = 1
 	}

app/backend/sqlc/queries/agents.sql

@@ -110,6 +110,12 @@ RETURNING *;
 UPDATE container_instances SET status = $2, updated_at = NOW()
 WHERE id = $1;
 
+-- name: UpdateContainerPorts :exec
+-- Agent reports the real host bindings after create — persist them with
+-- the status flip so ingress can route to the assigned port.
+UPDATE container_instances SET status = $2, ports = $3, updated_at = NOW()
+WHERE id = $1;
+
 -- name: GetLastAgentCommandByType :one
 SELECT * FROM agent_commands
 WHERE node_agent_id = $1 AND type = $2
@@ -174,7 +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 FROM container_instances
+SELECT id, name, node_agent_id, status, ports FROM container_instances
 WHERE service_id = $1;
 
 -- name: SetAgentSchedulable :exec
@@ -197,5 +203,9 @@ ON CONFLICT (id) DO UPDATE SET
 -- name: DeleteServiceContainersOnAgent :exec
 DELETE FROM container_instances WHERE node_agent_id = $1 AND service_id = $2;
 
+-- name: ListServiceAgents :many
+-- Distinct agents holding inventory rows for a service.
+SELECT DISTINCT node_agent_id FROM container_instances WHERE service_id = $1;
+
 -- name: ScrubCommandPayload :exec
 UPDATE agent_commands SET payload = $2, updated_at = NOW() WHERE id = $1;

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

@@ -161,10 +161,12 @@ 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, domains
+Remote nodes run registry-pulled images only — git builds and sleep
-(Traefik lives on the host), and sleep detection stay local. Start,
+detection stay local. Domains work remotely: the agent publishes the
-stop, restart, redeploy, and delete all fan out to the pinned node's
+service port and the backend writes a Traefik file-provider route to the
-agent. `services get` shows the resolved `node_name`.
+node's mesh IP (TRAEFIK_DYNAMIC_DIR — wired by the infra compose).
+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

@@ -7,7 +7,8 @@ services:
       - "--api.insecure=${TRAEFIK_API_INSECURE:-true}"
       - "--providers.docker=true"
       - "--providers.docker.exposedbydefault=false"
-      - "--providers.file.filename=/etc/traefik/traefik-dynamic.yml"
+      - "--providers.file.directory=/traefik-dynamic"
+      - "--providers.file.watch=true"
       - "--entrypoints.web.address=:80"
       - "--entrypoints.websecure.address=:443"
       - "--entrypoints.traefik.address=:8080"
@@ -26,7 +27,8 @@ services:
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock:ro
       - ../data/letsencrypt:/letsencrypt
-      - ./traefik-dynamic.yml:/etc/traefik/traefik-dynamic.yml:ro
+      - traefik_dynamic:/traefik-dynamic
+      - ./traefik-dynamic.yml:/traefik-dynamic/00-base.yml:ro
     networks:
       - containr-network
     restart: unless-stopped
@@ -100,6 +102,7 @@ services:
       - JWT_SECRET=${JWT_SECRET:-dev_jwt_secret_key_change_in_production}
       - CONTAINR_AGENT_AUTH_TOKEN=${CONTAINR_AGENT_AUTH_TOKEN:-}
       - CONTAINR_AGENT_AUTH_TOKENS=${CONTAINR_AGENT_AUTH_TOKENS:-}
+      - TRAEFIK_DYNAMIC_DIR=/traefik-dynamic
       - COOKIE_SECURE=${COOKIE_SECURE:-true}
       - TRUSTED_PROXY_CIDR=${TRUSTED_PROXY_CIDR:-172.20.0.0/16}
       - CORS_ORIGINS=${CORS_ORIGINS:-http://localhost,http://localhost:3000}
@@ -136,6 +139,7 @@ services:
       - GITEA_BASE_URL=${GITEA_BASE_URL:-https://gitea.example.com}
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock
+      - traefik_dynamic:/traefik-dynamic
     group_add:
       - "${DOCKER_GID:-0}"
     networks:
@@ -213,6 +217,8 @@ volumes:
     driver: local
   dragonfly_data:
     driver: local
+  traefik_dynamic:
+    driver: local
 
 networks:
   containr-network: