feat(sense): add reconciliation safety controls [T-012]

Sense/internal/metrics/metrics_test.go

@@ -0,0 +1,84 @@
+package metrics
+
+import (
+	"net/http/httptest"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+)
+
+func TestHandlerUsesOnlyFixedLowCardinalityLabels(t *testing.T) {
+	t.Parallel()
+	registry := New("ins_test-1", "v-test")
+	registry.ObserveReconcileRun(nil, 1500*time.Millisecond)
+	registry.ObserveReconcileItem("success")
+	registry.ObserveReconcileItem("lease_lost")
+	registry.SetConvergence(16, 2)
+	registry.ObserveOrphanScan(20, 1, 3, nil)
+	registry.ObserveOrphanCleanupBlocked("ratio_exceeded")
+	registry.ObserveOrphanCleanup(1, 1)
+
+	request := httptest.NewRequest("GET", "/metrics", nil)
+	response := httptest.NewRecorder()
+	registry.Handler().ServeHTTP(response, request)
+	body := response.Body.String()
+	for _, expected := range []string{
+		`sense_build_info{instance_id="ins_test-1",version="v-test"} 1`,
+		`sense_reconcile_items_total{result="lease_lost"} 1`,
+		`sense_reconcile_devices{state="unconverged"} 2`,
+		`sense_orphan_paths{classification="owned_stale"} 1`,
+		`sense_orphan_cleanup_blocked_total{reason="ratio_exceeded"} 1`,
+	} {
+		if !strings.Contains(body, expected) {
+			t.Fatalf("metrics output lacks %q:\n%s", expected, body)
+		}
+	}
+	for _, forbidden := range []string{
+		"tenant_id", "site_id", "device_id", "path_name", "rtsp://", "credential",
+	} {
+		if strings.Contains(body, forbidden) {
+			t.Fatalf("high-cardinality or secret-bearing label appeared: %q", forbidden)
+		}
+	}
+	if response.Header().Get("Cache-Control") != "no-store" {
+		t.Fatal("metrics responses must not be cached")
+	}
+}
+
+func TestRegistryIsSafeForConcurrentObservers(t *testing.T) {
+	t.Parallel()
+	registry := New("ins_concurrent", "dev")
+	var wait sync.WaitGroup
+	for index := 0; index < 32; index++ {
+		wait.Add(1)
+		go func() {
+			defer wait.Done()
+			for count := 0; count < 100; count++ {
+				registry.ObserveReconcileItem("success")
+				registry.SetConvergence(128, count%17)
+			}
+		}()
+	}
+	wait.Wait()
+	response := httptest.NewRecorder()
+	registry.Handler().ServeHTTP(response, httptest.NewRequest("GET", "/metrics", nil))
+	if !strings.Contains(response.Body.String(), `sense_reconcile_items_total{result="success"} 3200`) {
+		t.Fatalf("concurrent counter lost updates: %s", response.Body.String())
+	}
+}
+
+func TestGenerateInstanceIDShape(t *testing.T) {
+	t.Parallel()
+	first, err := GenerateInstanceID()
+	if err != nil {
+		t.Fatal(err)
+	}
+	second, err := GenerateInstanceID()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(first) != 28 || !strings.HasPrefix(first, "ins_") || first == second {
+		t.Fatalf("unexpected instance identifiers: %q %q", first, second)
+	}
+}