Harden production workflows and agent admission

agent/internal/metrics/metrics.go

@@ -28,6 +28,7 @@ type Metrics struct {
 	SendFailures     *prometheus.CounterVec
 	EventsAccepted   prometheus.Counter
 	EventsDedup      prometheus.Counter
+	EventsDropped    *prometheus.CounterVec
 	LastHeartbeat    prometheus.Gauge
 	BuildInfo        *prometheus.GaugeVec
 }
@@ -86,6 +87,10 @@ func New() *Metrics {
 		Name: "monlet_agent_events_deduplicated_total",
 		Help: "Events the server reported as duplicates.",
 	})
+	m.EventsDropped = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_events_dropped_total",
+		Help: "Events dropped by the agent before server acceptance, by reason (low-cardinality enum).",
+	}, []string{"reason"})
 	m.CheckStatus = prometheus.NewGaugeVec(prometheus.GaugeOpts{
 		Name: "monlet_agent_check_status",
 		Help: "Last observed status per check: 0=ok,1=warning,2=critical,3=unknown.",
@@ -123,7 +128,7 @@ func New() *Metrics {
 		m.CheckInterval, m.ChecksConfigured,
 		m.SpoolDepth, m.SpoolBytes,
 		m.SendAttempts, m.SendFailures,
-		m.EventsAccepted, m.EventsDedup,
+		m.EventsAccepted, m.EventsDedup, m.EventsDropped,
 		m.LastHeartbeat, m.BuildInfo)
 	return m
 }