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:
@@ -13,11 +13,13 @@ import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/metrics"
|
||||
)
|
||||
|
||||
// Completer is the minimal LLM chat surface the Summarizer needs.
|
||||
@@ -95,16 +97,23 @@ func (s *Summarizer) Summarize(ctx context.Context, v domain.Video, t domain.Tra
|
||||
|
||||
var errs []error
|
||||
for i, ep := range s.endpoints {
|
||||
fallback := i > 0
|
||||
start := time.Now()
|
||||
out, err := ep.Client.Complete(ctx, systemPrompt, user)
|
||||
dur := time.Since(start)
|
||||
if err != nil {
|
||||
metrics.ObserveSummarize(ep.Model, "error", fallback, dur)
|
||||
errs = append(errs, fmt.Errorf("%s/%s call: %w", ep.Provider, ep.Model, err))
|
||||
continue
|
||||
}
|
||||
sum, perr := s.build(v, ep, i > 0, out)
|
||||
sum, perr := s.build(v, ep, fallback, out)
|
||||
if perr != nil {
|
||||
metrics.ObserveSummarize(ep.Model, "parse_error", fallback, dur)
|
||||
errs = append(errs, fmt.Errorf("%s/%s output: %w", ep.Provider, ep.Model, perr))
|
||||
continue
|
||||
}
|
||||
metrics.ObserveSummarize(ep.Model, "success", fallback, dur)
|
||||
slog.Default().Info("summarized", "model", ep.Model, "fallback", fallback, "elapsed_ms", dur.Milliseconds())
|
||||
return sum, nil
|
||||
}
|
||||
return domain.Summary{}, fmt.Errorf("summarize: all %d endpoint(s) failed: %w", len(s.endpoints), errors.Join(errs...))
|
||||
|
||||
Reference in New Issue
Block a user