llmgw/internal/guard/metrics.go

package guard

import (
	"context"
	"errors"
	"time"

	"github.com/prometheus/client_golang/prometheus"
)

// gateMetrics are what only the gate sees: the judge, and redactions.
type gateMetrics struct {
	judgeLatency *prometheus.HistogramVec
	judgeErrors  *prometheus.CounterVec
	failOpen     prometheus.Counter
	redactions   *prometheus.CounterVec
}

func newGateMetrics() *gateMetrics {
	return &gateMetrics{
		judgeLatency: prometheus.NewHistogramVec(prometheus.HistogramOpts{
			Name:    "llmgw_guard_judge_latency_seconds",
			Help:    "Time a judge model took to answer the guardrails, cached answers excluded.",
			Buckets: []float64{.01, .025, .05, .1, .25, .5, 1, 2.5, 5},
		}, []string{"judge_model"}),
		judgeErrors: prometheus.NewCounterVec(prometheus.CounterOpts{
			Name: "llmgw_guard_judge_errors_total",
			Help: "Judge calls that gave no verdict, by reason: timeout, unavailable, format, no_judge.",
		}, []string{"reason"}),
		failOpen: prometheus.NewCounter(prometheus.CounterOpts{
			Name: "llmgw_guard_fail_open_total",
			Help: "Requests and answers served unjudged because a judge did not answer and the policy fails open.",
		}),
		redactions: prometheus.NewCounterVec(prometheus.CounterOpts{
			Name: "llmgw_guard_redactions_total",
			Help: "Values the guardrails rewrote as placeholders, by kind.",
		}, []string{"kind"}),
	}
}

// Describe and Collect make the gate a Prometheus collector.
func (g *Gate) Describe(ch chan<- *prometheus.Desc) {
	for _, c := range g.collectors() {
		c.Describe(ch)
	}
}

func (g *Gate) Collect(ch chan<- prometheus.Metric) {
	for _, c := range g.collectors() {
		c.Collect(ch)
	}
}

func (g *Gate) collectors() []prometheus.Collector {
	m := g.m
	return []prometheus.Collector{m.judgeLatency, m.judgeErrors, m.failOpen, m.redactions}
}

func (m *gateMetrics) judged(model string, took time.Duration, err error) {
	if err == nil {
		m.judgeLatency.WithLabelValues(model).Observe(took.Seconds())
		return
	}
	reason := "unavailable"
	switch {
	case errors.Is(err, context.DeadlineExceeded):
		reason = "timeout"
	case errors.Is(err, errNoJudge):
		reason = "no_judge"
	case errors.Is(err, errJudgeFormat):
		reason = "format"
	}
	m.judgeErrors.WithLabelValues(reason).Inc()
}