Add orphan GC sweeper and Prometheus metrics with explicit registration

Co-Authored-By: Claude <noreply@anthropic.com>

internal/metrics/metrics.go

@@ -0,0 +1,119 @@
+// Package metrics defines the operator's Prometheus metrics. Nothing here
+// registers itself — no init(), per house rules — the composition root
+// calls Register explicitly, which also lets every test use a fresh
+// registry.
+package metrics
+
+import (
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+)
+
+// Metrics holds the vector metrics the operator's components feed. The
+// consuming packages (health, discovery, provider) each define their own
+// small recorder interface; *Metrics satisfies all of them structurally,
+// so none of them import this package's prometheus surface.
+type Metrics struct {
+	healthcheckDuration *prometheus.HistogramVec
+	healthcheckFailures *prometheus.CounterVec
+	leaseRequests       *prometheus.CounterVec
+	providerRequests    *prometheus.CounterVec
+}
+
+// New builds the metric set, unregistered.
+func New() *Metrics {
+	return &Metrics{
+		healthcheckDuration: prometheus.NewHistogramVec(prometheus.HistogramOpts{
+			Name:    "proxy_operator_healthcheck_duration_seconds",
+			Help:    "Duration of through-the-proxy health probes.",
+			Buckets: prometheus.DefBuckets,
+		}, []string{"proxy"}),
+		healthcheckFailures: prometheus.NewCounterVec(prometheus.CounterOpts{
+			Name: "proxy_operator_healthcheck_failures_total",
+			Help: "Failed health probes.",
+		}, []string{"proxy"}),
+		leaseRequests: prometheus.NewCounterVec(prometheus.CounterOpts{
+			Name: "proxy_operator_lease_requests_total",
+			Help: "Lease acquisition requests by outcome.",
+		}, []string{"outcome"}),
+		providerRequests: prometheus.NewCounterVec(prometheus.CounterOpts{
+			Name: "proxy_operator_provider_requests_total",
+			Help: "Provider API calls by operation and classified result.",
+		}, []string{"provider", "op", "result"}),
+	}
+}
+
+// Register registers the vectors plus the two scrape-time collectors.
+// proxyPhases and activeLeases are read at every scrape: gauges derived
+// from reconcile-time increments inevitably drift and leak series on
+// delete; reading the source of truth cannot.
+func (m *Metrics) Register(reg prometheus.Registerer, proxyPhases func() map[string]int, activeLeases func() int) error {
+	collectors := []prometheus.Collector{
+		m.healthcheckDuration,
+		m.healthcheckFailures,
+		m.leaseRequests,
+		m.providerRequests,
+		&constCollector{
+			desc: prometheus.NewDesc("proxy_operator_proxies",
+				"Proxy objects by phase.", []string{"phase"}, nil),
+			read: proxyPhases,
+		},
+		&constCollector{
+			desc: prometheus.NewDesc("proxy_operator_leases_active",
+				"Currently active leases.", nil, nil),
+			read: func() map[string]int { return map[string]int{"": activeLeases()} },
+		},
+	}
+	for _, c := range collectors {
+		if err := reg.Register(c); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// ObserveProbe records one health probe. Called on every probe — metrics
+// are the home for high-frequency signal that must never touch status.
+func (m *Metrics) ObserveProbe(proxy string, latency time.Duration, success bool) {
+	m.healthcheckDuration.WithLabelValues(proxy).Observe(latency.Seconds())
+	if !success {
+		m.healthcheckFailures.WithLabelValues(proxy).Inc()
+	}
+}
+
+// ForgetProxy drops the per-proxy series when the health engine prunes its
+// state — without this, series for deleted proxies leak forever.
+func (m *Metrics) ForgetProxy(proxy string) {
+	m.healthcheckDuration.DeleteLabelValues(proxy)
+	m.healthcheckFailures.DeleteLabelValues(proxy)
+}
+
+// LeaseRequest records a lease acquisition outcome ("granted"|"no_match").
+func (m *Metrics) LeaseRequest(outcome string) {
+	m.leaseRequests.WithLabelValues(outcome).Inc()
+}
+
+// ProviderRequest records one provider API call with its classified result.
+func (m *Metrics) ProviderRequest(provider, op, result string) {
+	m.providerRequests.WithLabelValues(provider, op, result).Inc()
+}
+
+// constCollector reads a label→value map at scrape time and emits one
+// gauge sample per entry. An empty-string label key means "no labels".
+type constCollector struct {
+	desc *prometheus.Desc
+	read func() map[string]int
+}
+
+func (c *constCollector) Describe(ch chan<- *prometheus.Desc) { ch <- c.desc }
+
+func (c *constCollector) Collect(ch chan<- prometheus.Metric) {
+	for label, value := range c.read() {
+		if label == "" {
+			ch <- prometheus.MustNewConstMetric(c.desc, prometheus.GaugeValue, float64(value))
+			continue
+		}
+		ch <- prometheus.MustNewConstMetric(c.desc, prometheus.GaugeValue, float64(value), label)
+	}
+}