Add web auth, infinite-scroll, agent admission and review fixes across agent/server/web

agent/internal/metrics/metrics.go

@@ -13,24 +13,29 @@ import (
 type Metrics struct {
 	Registry *prometheus.Registry
 
-	CheckRuns        *prometheus.CounterVec
-	CheckSkipped     *prometheus.CounterVec
-	CheckDuration    *prometheus.HistogramVec
-	CheckStatus      *prometheus.GaugeVec
-	CheckExitCode    *prometheus.GaugeVec
-	CheckLastRun     *prometheus.GaugeVec
-	CheckLastSuccess *prometheus.GaugeVec
-	CheckInterval    *prometheus.GaugeVec
-	ChecksConfigured prometheus.Gauge
-	SpoolDepth       prometheus.Gauge
-	SpoolBytes       prometheus.Gauge
-	SendAttempts     *prometheus.CounterVec
-	SendFailures     *prometheus.CounterVec
-	EventsAccepted   prometheus.Counter
-	EventsDedup      prometheus.Counter
-	EventsDropped    *prometheus.CounterVec
-	LastHeartbeat    prometheus.Gauge
-	BuildInfo        *prometheus.GaugeVec
+	CheckRuns                  *prometheus.CounterVec
+	CheckSkipped               *prometheus.CounterVec
+	CheckDuration              *prometheus.HistogramVec
+	CheckStatus                *prometheus.GaugeVec
+	CheckExitCode              *prometheus.GaugeVec
+	CheckLastRun               *prometheus.GaugeVec
+	CheckLastSuccess           *prometheus.GaugeVec
+	CheckInterval              *prometheus.GaugeVec
+	ChecksConfigured           prometheus.Gauge
+	ConfigLoadSuccess          prometheus.Gauge
+	ConfigReloadTotal          *prometheus.CounterVec
+	ConfigLastReloadSuccess    prometheus.Gauge
+	ResourceLimitApplyFailures *prometheus.CounterVec
+	EventsChannelFull          prometheus.Counter
+	SpoolDepth                 prometheus.Gauge
+	SpoolBytes                 prometheus.Gauge
+	SendAttempts               *prometheus.CounterVec
+	SendFailures               *prometheus.CounterVec
+	EventsAccepted             prometheus.Counter
+	EventsDedup                prometheus.Counter
+	EventsDropped              *prometheus.CounterVec
+	LastHeartbeat              prometheus.Gauge
+	BuildInfo                  *prometheus.GaugeVec
 }
 
 // StatusCode maps a CheckResultEvent status string to a numeric gauge value.
@@ -115,6 +120,26 @@ func New() *Metrics {
 		Name: "monlet_agent_checks_configured",
 		Help: "Number of checks configured.",
 	})
+	m.ConfigLoadSuccess = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_config_load_success",
+		Help: "Whether the last agent config load or reload succeeded.",
+	})
+	m.ConfigReloadTotal = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_config_reload_total",
+		Help: "Number of config reload attempts by result.",
+	}, []string{"result"})
+	m.ConfigLastReloadSuccess = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_config_last_reload_success_timestamp_seconds",
+		Help: "Unix timestamp of the last successful config reload.",
+	})
+	m.ResourceLimitApplyFailures = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_resource_limit_apply_failures_total",
+		Help: "Number of failed resource limit applications by check and resource.",
+	}, []string{"check_id", "resource"})
+	m.EventsChannelFull = prometheus.NewCounter(prometheus.CounterOpts{
+		Name: "monlet_agent_events_channel_full_total",
+		Help: "Number of times scheduler event delivery would block because the agent event channel was full.",
+	})
 	m.LastHeartbeat = prometheus.NewGauge(prometheus.GaugeOpts{
 		Name: "monlet_agent_last_heartbeat_timestamp_seconds",
 		Help: "Unix timestamp of the last successful heartbeat ack.",
@@ -126,6 +151,9 @@ func New() *Metrics {
 	reg.MustRegister(m.CheckRuns, m.CheckSkipped, m.CheckDuration,
 		m.CheckStatus, m.CheckExitCode, m.CheckLastRun, m.CheckLastSuccess,
 		m.CheckInterval, m.ChecksConfigured,
+		m.ConfigLoadSuccess, m.ConfigReloadTotal, m.ConfigLastReloadSuccess,
+		m.ResourceLimitApplyFailures,
+		m.EventsChannelFull,
 		m.SpoolDepth, m.SpoolBytes,
 		m.SendAttempts, m.SendFailures,
 		m.EventsAccepted, m.EventsDedup, m.EventsDropped,
@@ -133,6 +161,19 @@ func New() *Metrics {
 	return m
 }
 
+// DeleteCheck removes metric series for a check that no longer exists.
+func (m *Metrics) DeleteCheck(checkID string) {
+	m.CheckRuns.DeletePartialMatch(prometheus.Labels{"check_id": checkID})
+	m.CheckSkipped.DeleteLabelValues(checkID)
+	m.CheckDuration.DeleteLabelValues(checkID)
+	m.CheckStatus.DeleteLabelValues(checkID)
+	m.CheckExitCode.DeleteLabelValues(checkID)
+	m.CheckLastRun.DeleteLabelValues(checkID)
+	m.CheckLastSuccess.DeleteLabelValues(checkID)
+	m.CheckInterval.DeleteLabelValues(checkID)
+	m.ResourceLimitApplyFailures.DeletePartialMatch(prometheus.Labels{"check_id": checkID})
+}
+
 // Serve blocks until ctx is done; the listener is closed on shutdown.
 func (m *Metrics) Serve(ctx context.Context, addr string) error {
 	mux := http.NewServeMux()

agent/internal/metrics/metrics_test.go

@@ -14,6 +14,7 @@ func TestMetricsExposeRegistered(t *testing.T) {
 	m := New()
 	m.CheckRuns.WithLabelValues("c1", "ok").Inc()
 	m.SpoolDepth.Set(7)
+	m.EventsChannelFull.Inc()
 	srv := httptest.NewServer(promhttp.HandlerFor(m.Registry, promhttp.HandlerOpts{}))
 	defer srv.Close()
 	resp, err := http.Get(srv.URL)
@@ -26,6 +27,7 @@ func TestMetricsExposeRegistered(t *testing.T) {
 	for _, want := range []string{
 		`monlet_agent_check_runs_total{check_id="c1",status="ok"} 1`,
 		`monlet_agent_spool_events 7`,
+		`monlet_agent_events_channel_full_total 1`,
 	} {
 		if !strings.Contains(s, want) {
 			t.Errorf("missing %q in output", want)