Complete alert event log governance proof

Bind monitor-side event-log bootstrap to its canonical boundary and exercise the new event infrastructure through the registry-recognized alerts, API, monitoring, and agent-lifecycle proof files.

Change-source: pulse-maintainer

docs/release-control/v6/internal/subsystems/monitoring.md

@@ -32,6 +32,11 @@ monitor restart.
 Monitor construction also applies the persisted grouping enabled flag, window,
 and node/guest keys as one notification-manager policy, so restart behavior is
 identical to a live alert-configuration save.
+Monitor construction enables the alerts-owned persistent event log once for
+each tenant alert manager. This is bootstrap wiring only: monitoring does not
+own event types, retention, query semantics, or lifecycle/notification truth,
+and an event-store startup or append failure must not interrupt polling, state
+assembly, alert evaluation, or notification delivery.
 Monitoring also owns the distinction between Proxmox VM power state and QEMU
 guest-agent reachability: fresh or never-healthy VMs with an enabled but
 unavailable guest agent stay `not-running`, while only VMs with recent healthy

internal/alerts/alerts_test.go

@@ -12,6 +12,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/rcourtman/pulse-go-rewrite/internal/alerts/eventlog"
 	alertspecs "github.com/rcourtman/pulse-go-rewrite/internal/alerts/specs"
 	"github.com/rcourtman/pulse-go-rewrite/internal/models"
 	"github.com/rcourtman/pulse-go-rewrite/internal/proxmoxidentity"
@@ -31,6 +32,23 @@ func ptrTime(t time.Time) *time.Time {
 	return &tt
 }
 
+func TestAlertEventLogDoesNotInventFiringFromActiveStorage(t *testing.T) {
+	manager := newEventLogManager(t)
+	addEventLogAlert(manager, &Alert{
+		ID:           "restored-alert",
+		Type:         "cpu",
+		Level:        AlertLevelWarning,
+		ResourceID:   "node-1",
+		ResourceName: "node-1",
+		StartTime:    time.Now().Add(-10 * time.Minute),
+	})
+
+	events := queryAlertEvents(t, manager, eventlog.Filter{AlertID: "restored-alert"})
+	if len(events) != 0 {
+		t.Fatalf("active-storage insertion recorded events = %+v, want none", events)
+	}
+}
+
 func TestGuestAlertIncludesTagsForNotificationRouting(t *testing.T) {
 	m := newTestManager(t)
 	m.ClearActiveAlerts()

internal/api/alerts_endpoints_test.go

@@ -8,6 +8,7 @@ import (
 	"testing"
 
 	"github.com/rcourtman/pulse-go-rewrite/internal/alerts"
+	"github.com/rcourtman/pulse-go-rewrite/internal/alerts/eventlog"
 )
 
 func TestAlertsEndpoints(t *testing.T) {
@@ -285,6 +286,26 @@ func TestAlertsEndpoints(t *testing.T) {
 		}
 	})
 
+	t.Run("GetAlertEvents", func(t *testing.T) {
+		res, err := http.Get(srv.server.URL + "/api/alerts/events")
+		if err != nil {
+			t.Fatalf("request failed: %v", err)
+		}
+		defer res.Body.Close()
+
+		if res.StatusCode != http.StatusOK {
+			t.Fatalf("status code = %d, want %d", res.StatusCode, http.StatusOK)
+		}
+
+		var events []eventlog.Event
+		if err := json.NewDecoder(res.Body).Decode(&events); err != nil {
+			t.Fatalf("decode alert events: %v", err)
+		}
+		if events == nil {
+			t.Fatal("alert events decoded as nil, want an empty JSON array")
+		}
+	})
+
 	// 5. Get alert history
 	t.Run("GetAlertHistory", func(t *testing.T) {
 		res, err := http.Get(srv.server.URL + "/api/alerts/history")

internal/monitoring/monitor_host_agent_removal_lifecycle_test.go

@@ -8,6 +8,7 @@ import (
 	"time"
 
 	"github.com/rcourtman/pulse-go-rewrite/internal/alerts"
+	"github.com/rcourtman/pulse-go-rewrite/internal/alerts/eventlog"
 	"github.com/rcourtman/pulse-go-rewrite/internal/config"
 	"github.com/rcourtman/pulse-go-rewrite/internal/models"
 	"github.com/rcourtman/pulse-go-rewrite/internal/unifiedresources"
@@ -16,6 +17,10 @@ import (
 
 func newHostRemovalLifecycleMonitor(t *testing.T, dataPath string) *Monitor {
 	t.Helper()
+	events, err := eventlog.OpenInMemory()
+	if err != nil {
+		t.Fatalf("open alert event log: %v", err)
+	}
 	monitor := &Monitor{
 		state:               models.NewState(),
 		alertManager:        alerts.NewManagerWithDataDir(dataPath),
@@ -25,6 +30,10 @@ func newHostRemovalLifecycleMonitor(t *testing.T, dataPath string) *Monitor {
 		config:              &config.Config{DataPath: dataPath},
 		hostContinuityStore: config.NewHostContinuityStore(dataPath, nil),
 	}
+	// Production monitor construction enables the alerts-owned event log.
+	// Exercise agent removal and re-enrollment with the same adjacent runtime
+	// enabled so it cannot accidentally become lifecycle authority.
+	monitor.alertManager.SetEventLog(events)
 	t.Cleanup(func() { monitor.alertManager.Stop() })
 	return monitor
 }