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/cluster/registry_test.go

@@ -0,0 +1,112 @@
+package cluster
+
+import (
+	"context"
+	"encoding/json"
+	"testing"
+	"time"
+
+	"switchboard-core/store"
+)
+
+// mockClusterStore implements store.ClusterStore for unit tests.
+type mockClusterStore struct {
+	nodes          []store.ClusterNode
+	heartbeatRows  int64
+	heartbeatErr   error
+	sweepCalled    bool
+	registerCalled bool
+	lastStats      json.RawMessage
+}
+
+func (m *mockClusterStore) Register(_ context.Context, nodeID, endpoint string) error {
+	m.registerCalled = true
+	return nil
+}
+
+func (m *mockClusterStore) Heartbeat(_ context.Context, nodeID string, stats json.RawMessage) (int64, error) {
+	m.lastStats = stats
+	return m.heartbeatRows, m.heartbeatErr
+}
+
+func (m *mockClusterStore) SweepStale(_ context.Context, _ time.Duration) (int64, error) {
+	m.sweepCalled = true
+	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
+}
+
+// mockHub implements ConnCounter.
+type mockHub struct{ count int }
+
+func (h *mockHub) ConnCount() int { return h.count }
+
+func TestCollectStats(t *testing.T) {
+	hub := &mockHub{count: 5}
+	reg := NewRegistry("test-node", "http://localhost:8080", nil, hub, RegistryConfig{
+		HeartbeatInterval: 10 * time.Second,
+		StaleThreshold:    30 * time.Second,
+	})
+
+	data := reg.collectStats()
+
+	var stats map[string]any
+	if err := json.Unmarshal(data, &stats); err != nil {
+		t.Fatalf("collectStats returned invalid JSON: %v", err)
+	}
+
+	// Verify expected keys
+	expectedKeys := []string{"goroutines", "heap_alloc", "heap_sys", "gc_cycles", "gc_pause_ns", "uptime_sec", "ws_clients"}
+	for _, key := range expectedKeys {
+		if _, ok := stats[key]; !ok {
+			t.Errorf("missing expected stats key: %s", key)
+		}
+	}
+
+	// ws_clients should reflect hub count
+	if ws, ok := stats["ws_clients"].(float64); !ok || int(ws) != 5 {
+		t.Errorf("ws_clients = %v, want 5", stats["ws_clients"])
+	}
+}
+
+func TestRegistryStartStop(t *testing.T) {
+	ms := &mockClusterStore{heartbeatRows: 1}
+	hub := &mockHub{count: 0}
+
+	reg := NewRegistry("test-node", "", ms, hub, RegistryConfig{
+		HeartbeatInterval: 50 * time.Millisecond,
+		StaleThreshold:    150 * time.Millisecond,
+	})
+
+	if err := reg.Start(); err != nil {
+		t.Fatalf("Start() error: %v", err)
+	}
+	if !ms.registerCalled {
+		t.Error("Register was not called on Start")
+	}
+
+	// Let at least one tick fire
+	time.Sleep(100 * time.Millisecond)
+
+	reg.Stop()
+
+	if !ms.sweepCalled {
+		t.Error("SweepStale was never called during tick")
+	}
+	if ms.lastStats == nil {
+		t.Error("Heartbeat was never called with stats")
+	}
+}
+
+func TestNodeID(t *testing.T) {
+	reg := NewRegistry("my-node-123", "", nil, &mockHub{}, RegistryConfig{})
+	if got := reg.NodeID(); got != "my-node-123" {
+		t.Errorf("NodeID() = %q, want %q", got, "my-node-123")
+	}
+}