feat(observability): instrument AI + HTTP paths, serve /metrics on a side port (ADR-030, #15)
Wire the metrics package into the live paths and serve it: - summarizer: per-endpoint latency by model/outcome(success|error|parse_error)/fallback + slog. - youtube.FetchTranscript: latency by outcome (captions|none|rate_limited) + slog. - chat: answer latency by model + slog. - llm usage hook → token counts (prompt|completion) per model, wired in buildSummarizer/buildChat. - oidc callback: login counter. - cmdServe: wrap Router in metrics.HTTPMiddleware (request count + latency by bounded route pattern) and serve /metrics on TAPIR_METRICS_ADDR (default :9090), a SEPARATE port — never on the public app mux. BDD: observability.feature scenarios un-pended + mapped. TDD: summarizer wiring tested black-box via the /metrics scrape; metrics-not-on-public-mux asserted. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
+20
-1
@@ -28,6 +28,7 @@ import (
|
||||
"gitea.d-ma.be/mathias/tapir/internal/adapters/youtube"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/auth"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/config"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/metrics"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/runner"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/web"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/web/oidc"
|
||||
@@ -310,16 +311,34 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
|
||||
|
||||
srv := &http.Server{
|
||||
Addr: cfg.HTTPAddr,
|
||||
Handler: app.Router(),
|
||||
Handler: metrics.HTTPMiddleware(app.Router()),
|
||||
ReadHeaderTimeout: 10 * time.Second,
|
||||
}
|
||||
|
||||
// Prometheus /metrics on a SEPARATE port (ADR-030) — never on the public app
|
||||
// mux, so a scrape is in-cluster only. Empty TAPIR_METRICS_ADDR disables it.
|
||||
var metricsSrv *http.Server
|
||||
if cfg.MetricsAddr != "" {
|
||||
mmux := http.NewServeMux()
|
||||
mmux.Handle("GET /metrics", metrics.Handler())
|
||||
metricsSrv = &http.Server{Addr: cfg.MetricsAddr, Handler: mmux, ReadHeaderTimeout: 10 * time.Second}
|
||||
go func() {
|
||||
log.Info("serving metrics", "addr", cfg.MetricsAddr)
|
||||
if err := metricsSrv.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
|
||||
log.Error("metrics server", "err", err)
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
// Graceful shutdown on signal: stop accepting, drain in-flight requests.
|
||||
go func() {
|
||||
<-ctx.Done()
|
||||
shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
||||
defer cancel()
|
||||
_ = srv.Shutdown(shutdownCtx)
|
||||
if metricsSrv != nil {
|
||||
_ = metricsSrv.Shutdown(shutdownCtx)
|
||||
}
|
||||
}()
|
||||
|
||||
log.Info("serving web ui", "addr", cfg.HTTPAddr, "user", cfg.UserID)
|
||||
|
||||
@@ -13,6 +13,7 @@ import (
|
||||
"gitea.d-ma.be/mathias/tapir/internal/adapters/youtube"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/config"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/metrics"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/ports"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/usecase"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/web"
|
||||
@@ -69,7 +70,7 @@ func buildSummarizer(cfg config.Config) *summarizer.Summarizer {
|
||||
func summarizerEndpoint(cfg config.Config) func(model string) summarizer.Endpoint {
|
||||
return func(model string) summarizer.Endpoint {
|
||||
return summarizer.Endpoint{
|
||||
Client: llm.New(cfg.GatewayURL, cfg.GatewayKey, model, cfg.SummarizerTimeout, llm.WithMaxTokens(cfg.SummaryMaxTokens)),
|
||||
Client: llm.New(cfg.GatewayURL, cfg.GatewayKey, model, cfg.SummarizerTimeout, llm.WithMaxTokens(cfg.SummaryMaxTokens), llm.WithUsageHook(metrics.RecordTokens)),
|
||||
Provider: providerOf(model),
|
||||
Model: model,
|
||||
}
|
||||
@@ -150,7 +151,7 @@ func buildChat(cfg config.Config) *chat.Service {
|
||||
return nil
|
||||
}
|
||||
newClient := func(model string) chat.Completer {
|
||||
return llm.New(cfg.GatewayURL, cfg.GatewayKey, model, cfg.SummarizerTimeout, llm.WithMaxTokens(cfg.SummaryMaxTokens))
|
||||
return llm.New(cfg.GatewayURL, cfg.GatewayKey, model, cfg.SummarizerTimeout, llm.WithMaxTokens(cfg.SummaryMaxTokens), llm.WithUsageHook(metrics.RecordTokens))
|
||||
}
|
||||
return chat.New(newClient, models, cfg.MaxTranscriptChars)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user