Stage 12: observability & performance (OTel/OTLP, domain metrics, guest GC)
Tests · Go / test (push) Successful in 11s
Tests · Integration / integration (push) Successful in 12s
Tests · Go / test (pull_request) Successful in 10s
Tests · Integration / integration (pull_request) Successful in 11s

- pkg/telemetry: shared OTel provider bootstrap (none/stdout/otlp + W3C
  propagators + Go runtime metrics); backend/internal/telemetry becomes a thin
  facade keeping its gin middleware.
- Telemetry parity: gateway and the Telegram connector gain telemetry runtimes
  and config (GATEWAY_/TELEGRAM_ SERVICE_NAME + OTEL_*); otelgrpc instruments the
  backend push server, the gateway's backend+connector clients and the connector
  server. Default exporter stays none (collector/dashboards are Stage 14).
- Operational metrics (variant attribute on game-scoped ones): game_replay_duration,
  game_move_validate_duration, games_started_total, games_abandoned_total,
  game_cache_active, chat_messages_total{kind}, gateway edge_request_duration.
  Wired via the SetMetrics setter pattern (default no-op meter).
- TODO-3: account.GuestReaper deletes guests with no game seat past
  BACKEND_GUEST_RETENTION (default 30d, swept every BACKEND_GUEST_REAP_INTERVAL).
- Tests: pkg/telemetry exporter selection; game/social/edge metric recording via
  a manual reader; config (otlp accepted, guest knobs); inttest guest reaper.
- Docs: PLAN.md re-scopes Stage 12 and adds Stage 13 (alphabet-on-wire) + Stage 14
  (CI/deploy) with the agreed dictionary-versioning resolution; ARCHITECTURE 11/13,
  TESTING, the three READMEs and FUNCTIONAL(+ru) updated.
This commit is contained in:
Ilia Denisov
2026-06-04 14:22:15 +02:00
parent 01485d8fc6
commit dcd8de8b00
44 changed files with 1434 additions and 224 deletions
+9 -2
View File
@@ -33,6 +33,7 @@ type Service struct {
clock func() time.Time
rng func() int64
pub notify.Publisher
metrics *gameMetrics
log *zap.Logger
}
@@ -51,6 +52,7 @@ func NewService(store *Store, accounts *account.Store, registry *engine.Registry
clock: clock,
rng: randomSeed,
pub: notify.Nop{},
metrics: defaultGameMetrics(),
log: log,
}
}
@@ -135,7 +137,8 @@ func (svc *Service) Create(ctx context.Context, params CreateParams) (Game, erro
if err := svc.store.CreateGame(ctx, ins, params.Seats); err != nil {
return Game{}, err
}
svc.cache.put(id, g)
svc.cache.put(id, g, params.Variant.String())
svc.metrics.recordStarted(ctx, params.Variant)
return svc.store.GetGame(ctx, id)
}
@@ -350,6 +353,7 @@ func (svc *Service) timeoutGame(ctx context.Context, gameID uuid.UUID, now time.
if _, err := svc.commit(ctx, gameID, g, rec, "timeout", rackBefore, nil, cur.Seats); err != nil {
return false, err
}
svc.metrics.recordAbandoned(ctx, cur.Variant)
return true, nil
}
@@ -373,7 +377,9 @@ func (svc *Service) EvaluatePlay(ctx context.Context, gameID, accountID uuid.UUI
if err != nil {
return EvalResult{}, err
}
validateStart := time.Now()
rec, err := g.EvaluatePlay(dir, tiles)
svc.metrics.recordValidate(ctx, pre.Variant, validateStart)
if err != nil {
if errors.Is(err, engine.ErrIllegalPlay) {
return EvalResult{Valid: false}, nil
@@ -704,7 +710,7 @@ func (svc *Service) liveGame(ctx context.Context, pre Game) (*engine.Game, error
return nil, err
}
if !g.Over() {
svc.cache.put(pre.ID, g)
svc.cache.put(pre.ID, g, pre.Variant.String())
}
return g, nil
}
@@ -713,6 +719,7 @@ func (svc *Service) liveGame(ctx context.Context, pre Game) (*engine.Game, error
// re-applying every journalled move in order. The deterministic bag makes the
// reconstruction exact.
func (svc *Service) replay(ctx context.Context, pre Game) (*engine.Game, error) {
defer svc.metrics.recordReplay(ctx, pre.Variant, time.Now())
seed, err := svc.store.GameSeed(ctx, pre.ID)
if err != nil {
return nil, err