Add cron schedules and sync docs

agent/internal/app/app.go

@@ -47,9 +47,7 @@ func (a *App) Run(ctx context.Context) error {
 	a.Metrics.ConfigLoadSuccess.Set(1)
 	a.Metrics.ChecksConfigured.Set(float64(len(cfg.Checks)))
 	a.Metrics.BuildInfo.WithLabelValues(a.Version, boolLabel(cfg.PushesToServer()), boolLabel(cfg.ExposesMetrics())).Set(1)
-	for _, c := range cfg.Checks {
-		a.Metrics.CheckInterval.WithLabelValues(c.ID).Set(c.Interval.Duration.Seconds())
-	}
+	a.recordCheckScheduleMetrics(cfg.Checks)
 
 	var wg sync.WaitGroup
 
@@ -256,9 +254,7 @@ func (a *App) Reload(newCfg *config.Config, newAgentID string) error {
 	a.Metrics.ConfigReloadTotal.WithLabelValues("success").Inc()
 	a.Metrics.ConfigLastReloadSuccess.Set(float64(time.Now().Unix()))
 	a.Metrics.ChecksConfigured.Set(float64(len(newCfg.Checks)))
-	for _, c := range newCfg.Checks {
-		a.Metrics.CheckInterval.WithLabelValues(c.ID).Set(c.Interval.Duration.Seconds())
-	}
+	a.recordCheckScheduleMetrics(newCfg.Checks)
 
 	a.schedulerMu.RLock()
 	mgr := a.scheduler
@@ -275,6 +271,16 @@ func (a *App) RecordReloadFailure() {
 	a.Metrics.ConfigReloadTotal.WithLabelValues("failure").Inc()
 }
 
+func (a *App) recordCheckScheduleMetrics(checks []config.CheckConfig) {
+	for _, c := range checks {
+		if c.UsesInterval() {
+			a.Metrics.CheckInterval.WithLabelValues(c.ID).Set(c.Interval.Duration.Seconds())
+		} else {
+			a.Metrics.CheckInterval.DeleteLabelValues(c.ID)
+		}
+	}
+}
+
 func (a *App) config() *config.Config {
 	a.cfgMu.RLock()
 	defer a.cfgMu.RUnlock()

agent/internal/app/app_test.go

@@ -17,6 +17,7 @@ import (
 	"github.com/monlet/agent/internal/config"
 	"github.com/monlet/agent/internal/metrics"
 	"github.com/monlet/agent/internal/spool"
+	dto "github.com/prometheus/client_model/go"
 )
 
 func TestPrometheusOnlyDoesNotPush(t *testing.T) {
@@ -257,6 +258,92 @@ func TestReloadAcceptsLabelsAndChecks(t *testing.T) {
 	}
 }
 
+func TestReloadUpdatesIntervalMetricForCron(t *testing.T) {
+	oldCfg := &config.Config{
+		AgentID:  "a1",
+		Hostname: "h",
+		StateDir: "/tmp/old",
+		Server: config.ServerConfig{
+			Enabled:           boolPtr(true),
+			URL:               "http://server",
+			HeartbeatInterval: config.Duration{Duration: 10 * time.Second},
+			BatchInterval:     config.Duration{Duration: 10 * time.Second},
+		},
+		Metrics: config.MetricsConfig{Enabled: false},
+		Checks: []config.CheckConfig{{
+			ID:       "c1",
+			Command:  "true",
+			Interval: config.Duration{Duration: time.Second},
+			Timeout:  config.Duration{Duration: time.Second},
+		}},
+	}
+	a := &App{
+		Cfg:     oldCfg,
+		AgentID: "a1",
+		Metrics: metrics.New(),
+	}
+	a.recordCheckScheduleMetrics(oldCfg.Checks)
+	if got, ok := checkIntervalMetric(t, a, "c1"); !ok || got != 1 {
+		t.Fatalf("interval metric missing before reload: value=%v ok=%v", got, ok)
+	}
+
+	cronCfg := *oldCfg
+	cronCfg.Checks = []config.CheckConfig{{
+		ID:      "c1",
+		Command: "true",
+		Cron:    "0 * * * *",
+		Timeout: config.Duration{Duration: time.Second},
+	}}
+	if err := a.Reload(&cronCfg, "a1"); err != nil {
+		t.Fatal(err)
+	}
+	if got, ok := checkIntervalMetric(t, a, "c1"); ok {
+		t.Fatalf("interval metric must be deleted for cron check, got %v", got)
+	}
+
+	intervalCfg := cronCfg
+	intervalCfg.Checks = []config.CheckConfig{{
+		ID:       "c1",
+		Command:  "true",
+		Interval: config.Duration{Duration: 2 * time.Second},
+		Timeout:  config.Duration{Duration: time.Second},
+	}}
+	if err := a.Reload(&intervalCfg, "a1"); err != nil {
+		t.Fatal(err)
+	}
+	if got, ok := checkIntervalMetric(t, a, "c1"); !ok || got != 2 {
+		t.Fatalf("interval metric missing after interval reload: value=%v ok=%v", got, ok)
+	}
+}
+
+func checkIntervalMetric(t *testing.T, a *App, checkID string) (float64, bool) {
+	t.Helper()
+	families, err := a.Metrics.Registry.Gather()
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, family := range families {
+		if family.GetName() != "monlet_agent_check_interval_seconds" {
+			continue
+		}
+		for _, metric := range family.GetMetric() {
+			if labelValue(metric.GetLabel(), "check_id") == checkID && metric.GetGauge() != nil {
+				return metric.GetGauge().GetValue(), true
+			}
+		}
+	}
+	return 0, false
+}
+
+func labelValue(labels []*dto.LabelPair, name string) string {
+	for _, label := range labels {
+		if label.GetName() == name {
+			return label.GetValue()
+		}
+	}
+	return ""
+}
+
 func boolPtr(v bool) *bool {
 	return &v
 }