Add TTFT & ITL Metrics for LLM Inference (#28)

Time-to-First-Token (TTFT) and Inter-Token Latency (ITL) metrics for LLM inference observability Metrics: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total Closes #31 #32 #33 --------- Co-authored-by: poimen <[email protected]> Reviewed-on: #28
2026-09-15 08:53:58 +00:00
parent 30e0a83a50
commit d439536ca9
22 changed files with 2224 additions and 199 deletions
@@ -0,0 +1,28 @@
+package observability
+
+import (
+	"net/http"
+)
+
+// MetricsHandler serves Prometheus metrics
+type MetricsHandler struct {
+	exporter *PrometheusExporter
+}
+
+// NewMetricsHandler creates a new metrics handler
+func NewMetricsHandler(m *Metrics) *MetricsHandler {
+	return &MetricsHandler{
+		exporter: NewPrometheusExporter(m),
+	}
+}
+
+// ServeHTTP implements http.Handler for Prometheus /metrics endpoint
+func (h *MetricsHandler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Content-Type", "text/plain; version=0.0.4; charset=utf-8")
+	w.Header().Set("Cache-Control", "no-cache, no-store, must-revalidate")
+	w.Header().Set("Pragma", "no-cache")
+	w.Header().Set("Expires", "0")
+
+	w.WriteHeader(http.StatusOK)
+	w.Write([]byte(h.exporter.Export()))
+}