Feat v0.6.0 cluster registry + HA

PG-backed cluster registry for horizontal scaling — zero new
infrastructure (no etcd/Consul/Redis). MVP convergence point.

- node_registry UNLOGGED table (migration 013)
- Self-registration, heartbeat tick (10s), stale sweep (30s),
  self-eviction (os.Exit on 0 rows → K8s restarts)
- GET /api/v1/admin/cluster returns nodes with runtime stats
- Health endpoints include node_id + cluster size/peers
- cluster-dashboard admin surface with auto-refresh
- 3-replica E2E test (docker-compose-e2e.yml + ci/e2e-cluster-test.sh)
- chat + cluster-dashboard added to curated default bundle
- 5 new tests (3 unit + 2 handler), all passing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

server/main.go

@@ -16,6 +16,7 @@ import (
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 
 	"switchboard-core/auth"
+	"switchboard-core/cluster"
 	"switchboard-core/config"
 	"switchboard-core/crypto"
 	"switchboard-core/database"
@@ -209,6 +210,27 @@ func main() {
 	// ── WebSocket Hub ─────────────────────────
 	hub := events.NewHub(bus, middleware.GetAllowedOrigins(cfg))
 
+	// ── Cluster Registry (v0.6.0) ────────────
+	// PG-backed node self-registration + heartbeat. No-op on SQLite.
+	var clusterReg *cluster.Registry
+	if database.IsPostgres() && stores.Cluster != nil {
+		nodeID := cfg.ClusterNodeID
+		if nodeID == "" {
+			hostname, _ := os.Hostname()
+			nodeID = fmt.Sprintf("%s-%d", hostname, os.Getpid())
+		}
+		clusterReg = cluster.NewRegistry(nodeID, cfg.ClusterEndpoint, stores.Cluster, hub, cluster.RegistryConfig{
+			HeartbeatInterval: cfg.ClusterHeartbeatInterval,
+			StaleThreshold:    cfg.ClusterStaleThreshold,
+		})
+		if err := clusterReg.Start(); err != nil {
+			log.Printf("⚠ Cluster registry failed to start: %v", err)
+			clusterReg = nil
+		} else {
+			defer clusterReg.Stop()
+		}
+	}
+
 	// ── WebSocket Ticket Store (v0.32.0: PG-backed for cross-pod) ─────
 	ticketAdapter := &events.TicketValidatorAdapter{Store: stores.Tickets}
 
@@ -244,13 +266,15 @@ func main() {
 
 	// Health check (k8s probes hit this directly)
 	base.GET("/health", func(c *gin.Context) {
-		c.JSON(200, gin.H{
+		info := gin.H{
 			"status":         "ok",
 			"version":        Version,
 			"database":       database.IsConnected(),
 			"database_name":  database.Name(),
 			"schema_version": database.SchemaVersion(),
-		})
+		}
+		appendClusterHealth(info, clusterReg, stores)
+		c.JSON(200, info)
 	})
 
 	// v0.32.0: Kubernetes probe endpoints
@@ -345,6 +369,7 @@ func main() {
 			if database.IsConnected() {
 				info["registration_enabled"] = handlers.IsRegistrationEnabled(stores)
 			}
+			appendClusterHealth(info, clusterReg, stores)
 			c.JSON(200, info)
 		})
 
@@ -762,6 +787,12 @@ func main() {
 			admin.PUT("/schedules/:id/disable", schedH.AdminDisableSchedule)
 			admin.DELETE("/schedules/:id", schedH.AdminDeleteSchedule)
 
+			// ── Cluster (v0.6.0) ─────────────────
+			if stores.Cluster != nil {
+				clusterH := handlers.NewClusterHandler(stores)
+				admin.GET("/cluster", clusterH.ListNodes)
+			}
+
 			// Surface aliases (backward compat — same handlers)
 			admin.GET("/surfaces", pkgAdm.ListPackages)
 			admin.GET("/surfaces/:id", pkgAdm.GetPackage)
@@ -841,6 +872,32 @@ func main() {
 	}
 }
 
+// appendClusterHealth adds cluster info to a health response if the registry is active.
+func appendClusterHealth(info gin.H, reg *cluster.Registry, stores store.Stores) {
+	if reg == nil || stores.Cluster == nil {
+		return
+	}
+	nodes, err := stores.Cluster.ListNodes(context.Background())
+	if err != nil {
+		return
+	}
+	var peers []string
+	var heartbeatAge time.Duration
+	for _, n := range nodes {
+		if n.NodeID != reg.NodeID() {
+			peers = append(peers, n.NodeID)
+		} else {
+			heartbeatAge = time.Since(n.Heartbeat)
+		}
+	}
+	info["node_id"] = reg.NodeID()
+	info["cluster"] = gin.H{
+		"size":             len(nodes),
+		"peers":            peers,
+		"heartbeat_age_ms": heartbeatAge.Milliseconds(),
+	}
+}
+
 // ── Vault CLI Commands ──────────────────────
 
 func runVaultCommand(subcmd string) {