llmgw/internal/router/admin_test.go

package router

import (
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"

	"github.com/prometheus/client_golang/prometheus"

	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
)

type constantCollector struct{ desc *prometheus.Desc }

func (c constantCollector) Describe(ch chan<- *prometheus.Desc) { ch <- c.desc }
func (c constantCollector) Collect(ch chan<- prometheus.Metric) {
	ch <- prometheus.MustNewConstMetric(c.desc, prometheus.GaugeValue, 1)
}

func TestARegisteredCollectorReachesTheMetricsEndpoint(t *testing.T) {
	// Registering after AdminHandler silently published nothing, because that
	// is where the registry is built. The fleet metrics were deployed and
	// absent, and only looking at the live endpoint showed it — a wiring
	// mistake that no type checks and nothing fails on.
	e := newFakeEngine(t, "m")
	rt := newTestRouter(t, baseConfig(config.Endpoint{ID: "a", URL: e.srv.URL, Models: []string{"m"}}))

	if err := rt.RegisterMetrics(constantCollector{
		desc: prometheus.NewDesc("llmgw_test_collector", "proof it was registered", nil, nil),
	}); err != nil {
		t.Fatal(err)
	}

	mux, err := rt.AdminHandler()
	if err != nil {
		t.Fatal(err)
	}
	req := httptest.NewRequest(http.MethodGet, "/metrics", nil)
	rec := httptest.NewRecorder()
	mux.ServeHTTP(rec, req)

	if !strings.Contains(rec.Body.String(), "llmgw_test_collector") {
		t.Error("a registered collector did not reach /metrics")
	}
}

func TestTheMetricsListenerServesMetricsAndNotPprof(t *testing.T) {
	// The whole reason it exists. pprof can dump the process heap, and API keys
	// are in that heap in plaintext — so the listener that can be reached from
	// another machine must not carry it. Sharing one meant a fleet could be
	// monitored or keep its heap private, and not both.
	e := newFakeEngine(t, "m")
	rt := newTestRouter(t, baseConfig(config.Endpoint{ID: "a", URL: e.srv.URL, Models: []string{"m"}}))
	if _, err := rt.AdminHandler(); err != nil {
		t.Fatal(err)
	}

	h := rt.MetricsHandler()
	if h == nil {
		t.Fatal("no metrics handler after AdminHandler")
	}

	rec := httptest.NewRecorder()
	h.ServeHTTP(rec, httptest.NewRequest(http.MethodGet, "/metrics", nil))
	if rec.Code != http.StatusOK {
		t.Errorf("/metrics returned %d", rec.Code)
	}
	if !strings.Contains(rec.Body.String(), "llmgw_") {
		t.Error("/metrics served nothing recognisable")
	}

	for _, path := range []string{
		"/debug/pprof/", "/debug/pprof/heap", "/debug/pprof/cmdline",
		"/debug/pprof/profile", "/debug/pprof/trace", "/api/v1/nodes", "/admin",
	} {
		rec := httptest.NewRecorder()
		h.ServeHTTP(rec, httptest.NewRequest(http.MethodGet, path, nil))
		if rec.Code != http.StatusNotFound {
			t.Errorf("%s returned %d on the metrics listener; it must not be reachable there",
				path, rec.Code)
		}
	}
}

func TestMetricsStayOnTheAdminListenerToo(t *testing.T) {
	// Anything already scraping the admin listener keeps working; adding a door
	// is not the same as moving one.
	e := newFakeEngine(t, "m")
	rt := newTestRouter(t, baseConfig(config.Endpoint{ID: "a", URL: e.srv.URL, Models: []string{"m"}}))
	mux, err := rt.AdminHandler()
	if err != nil {
		t.Fatal(err)
	}
	rec := httptest.NewRecorder()
	mux.ServeHTTP(rec, httptest.NewRequest(http.MethodGet, "/metrics", nil))
	if rec.Code != http.StatusOK {
		t.Errorf("/metrics on the admin listener returned %d", rec.Code)
	}
}

func TestTheMetricsHandlerIsNilBeforeTheRegistryExists(t *testing.T) {
	// Ordering has bitten this exact area once already: a collector registered
	// after AdminHandler published nothing at all, silently. Saying nil beats
	// serving an empty page that looks like a working scrape target.
	e := newFakeEngine(t, "m")
	rt := newTestRouter(t, baseConfig(config.Endpoint{ID: "a", URL: e.srv.URL, Models: []string{"m"}}))
	if rt.MetricsHandler() != nil {
		t.Error("a metrics handler existed before the registry was built")
	}
}