feat(server): serve /metrics endpoint when embedded metrics enabled

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/claude-agent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

internal/server/server.go

@@ -26,7 +26,7 @@ type Server struct {
 	apiKeys    atomic.Pointer[map[string]struct{}]
 }
 
-func New(cfg *config.Config, pool *auth.Pool, profile *proxy.SniffedProfile, tracker *ratelimit.Tracker) *Server {
+func New(cfg *config.Config, pool *auth.Pool, profile *proxy.SniffedProfile, tracker *ratelimit.Tracker, metricsHandler http.Handler) *Server {
 	s := &Server{configPath: "config.yaml"}
 
 	san := proxy.NewSanitizer(cfg.Sanitize)
@@ -39,7 +39,7 @@ func New(cfg *config.Config, pool *auth.Pool, profile *proxy.SniffedProfile, tra
 	engine := gin.New()
 	engine.Use(gin.Recovery())
 	engine.Use(corsMiddleware())
-	if cfg.Telemetry.ExportEnabled() {
+	if cfg.Telemetry.Export.Enabled() {
 		engine.Use(otelgin.Middleware(cfg.Telemetry.ServiceName))
 	}
 	engine.Use(s.authMiddleware())
@@ -51,6 +51,10 @@ func New(cfg *config.Config, pool *auth.Pool, profile *proxy.SniffedProfile, tra
 	engine.POST("/v1/messages", handler)
 	engine.POST("/messages", handler)
 
+	if metricsHandler != nil {
+		engine.GET("/metrics", gin.WrapH(metricsHandler))
+	}
+
 	engine.POST("/reload", s.handleReload())
 	engine.POST("/debug/refresh", handleDebugRefresh(pool))
 	engine.GET("/healthz", func(c *gin.Context) {
@@ -137,7 +141,7 @@ func corsMiddleware() gin.HandlerFunc {
 func (s *Server) authMiddleware() gin.HandlerFunc {
 	return func(c *gin.Context) {
 		path := c.Request.URL.Path
-		if path == "/healthz" || path == "/reload" {
+		if path == "/healthz" || path == "/reload" || path == "/metrics" {
 			c.Next()
 			return
 		}