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/handlers/cluster.go

@@ -0,0 +1,32 @@
+package handlers
+
+import (
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+
+	"switchboard-core/store"
+)
+
+// ClusterHandler serves the admin cluster API.
+type ClusterHandler struct {
+	stores store.Stores
+}
+
+func NewClusterHandler(stores store.Stores) *ClusterHandler {
+	return &ClusterHandler{stores: stores}
+}
+
+// ListNodes returns all registered cluster nodes.
+// GET /api/v1/admin/cluster
+func (h *ClusterHandler) ListNodes(c *gin.Context) {
+	nodes, err := h.stores.Cluster.ListNodes(c.Request.Context())
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to list cluster nodes"})
+		return
+	}
+	if nodes == nil {
+		nodes = []store.ClusterNode{}
+	}
+	c.JSON(http.StatusOK, gin.H{"data": nodes})
+}

server/handlers/cluster_test.go

@@ -0,0 +1,114 @@
+package handlers
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/gin-gonic/gin"
+
+	"switchboard-core/store"
+)
+
+// mockClusterStore implements store.ClusterStore for handler tests.
+type mockClusterStore struct {
+	nodes []store.ClusterNode
+}
+
+func (m *mockClusterStore) Register(_ context.Context, _, _ string) error               { return nil }
+func (m *mockClusterStore) Heartbeat(_ context.Context, _ string, _ json.RawMessage) (int64, error) {
+	return 1, nil
+}
+func (m *mockClusterStore) SweepStale(_ context.Context, _ time.Duration) (int64, error) { return 0, nil }
+func (m *mockClusterStore) ListNodes(_ context.Context) ([]store.ClusterNode, error) {
+	return m.nodes, nil
+}
+func (m *mockClusterStore) Deregister(_ context.Context, _ string) error { return nil }
+
+func TestClusterListNodes(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	mock := &mockClusterStore{
+		nodes: []store.ClusterNode{
+			{
+				NodeID:       "node-1",
+				Endpoint:     "http://node-1:8080",
+				Seq:          1,
+				RegisteredAt: time.Now(),
+				Heartbeat:    time.Now(),
+				Stats:        json.RawMessage(`{"ws_clients":3}`),
+			},
+			{
+				NodeID:       "node-2",
+				Endpoint:     "http://node-2:8080",
+				Seq:          2,
+				RegisteredAt: time.Now(),
+				Heartbeat:    time.Now(),
+				Stats:        json.RawMessage(`{"ws_clients":7}`),
+			},
+		},
+	}
+
+	stores := store.Stores{Cluster: mock}
+	h := NewClusterHandler(stores)
+
+	r := gin.New()
+	r.GET("/api/v1/admin/cluster", h.ListNodes)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/v1/admin/cluster", nil)
+	w := httptest.NewRecorder()
+	r.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("status = %d, want %d", w.Code, http.StatusOK)
+	}
+
+	var resp struct {
+		Data []store.ClusterNode `json:"data"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("unmarshal response: %v", err)
+	}
+	if len(resp.Data) != 2 {
+		t.Fatalf("data length = %d, want 2", len(resp.Data))
+	}
+	if resp.Data[0].NodeID != "node-1" {
+		t.Errorf("data[0].node_id = %q, want %q", resp.Data[0].NodeID, "node-1")
+	}
+	if resp.Data[1].NodeID != "node-2" {
+		t.Errorf("data[1].node_id = %q, want %q", resp.Data[1].NodeID, "node-2")
+	}
+}
+
+func TestClusterListNodesEmpty(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	mock := &mockClusterStore{nodes: nil}
+	stores := store.Stores{Cluster: mock}
+	h := NewClusterHandler(stores)
+
+	r := gin.New()
+	r.GET("/api/v1/admin/cluster", h.ListNodes)
+
+	req := httptest.NewRequest(http.MethodGet, "/api/v1/admin/cluster", nil)
+	w := httptest.NewRecorder()
+	r.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("status = %d, want %d", w.Code, http.StatusOK)
+	}
+
+	var resp struct {
+		Data []json.RawMessage `json:"data"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("unmarshal: %v", err)
+	}
+	// Should be empty array, not null
+	if resp.Data == nil {
+		t.Error("data should be [], not null")
+	}
+}

server/handlers/packages_bundled.go

@@ -23,13 +23,19 @@ import (
 )
 
 // defaultBundledPackages is the curated set of packages installed by default.
+// This is the dev/test bundle — includes demos and workflow examples.
 // Other packages still ship in the Docker image but require BUNDLED_PACKAGES
 // to be set explicitly (or "*" for all).
+//
+// Recommended production override (lean):
+//   BUNDLED_PACKAGES=notes,chat,chat-core,cluster-dashboard
 var defaultBundledPackages = map[string]bool{
 	"notes":                 true,
+	"chat":                  true,
 	"chat-core":             true,
 	"workflow-chat":         true,
 	"dashboard":             true,
+	"cluster-dashboard":     true,
 	"workflow-demo":         true,
 	"bug-report-triage":     true,
 	"content-approval":      true,