Stage 16: deploy infra & test contour
CI / unit (pull_request) Successful in 9s
CI / integration (pull_request) Successful in 11s
CI / ui (pull_request) Successful in 19s
CI / deploy (pull_request) Failing after 1s

- backend + gateway multi-stage distroless Dockerfiles; the gateway embeds and
  serves the SPA at / and /telegram/ via go:embed (committed dist placeholder,
  real build baked in by the image's node stage)
- deploy/docker-compose.yml: backend + gateway + Postgres + Telegram connector
  (VPN sidecar) + OTel Collector + Prometheus (15d) + Tempo (72h) + Grafana,
  fronted by a caddy owning a single /_gm Basic-Auth (admin console + Grafana
  subpath); inter-service on a private network, only caddy on the edge network
- new metrics: backend accounts_created_total{kind} (robots excluded) and an
  in-memory gateway active_users{window=24h,7d} gauge
- CI: single .gitea/workflows/ci.yaml (unit/integration/ui + a gated test-contour
  deploy) on the new feature/* -> development -> master branch model; the old
  go-unit/integration/ui-test workflows are folded in; the connector-scoped
  compose is retired (superseded by deploy/)
- docs: ARCHITECTURE §11/§12/§13, root + gateway READMEs, CLAUDE.md branching,
  PLAN.md (stage 16 done + refinements + Stage 17 forward-notes)
This commit is contained in:
Ilia Denisov
2026-06-05 11:42:26 +02:00
parent 8c8f8c4d42
commit 8700fbfae1
35 changed files with 1413 additions and 318 deletions
+37 -3
View File
@@ -12,14 +12,26 @@ import (
// meterName scopes the gateway edge's OpenTelemetry instruments.
const meterName = "scrabble/gateway/edge"
// activeUserWindows are the rolling windows the active_users gauge reports.
var activeUserWindows = []struct {
label string
dur time.Duration
}{
{label: "24h", dur: 24 * time.Hour},
{label: "7d", dur: 7 * 24 * time.Hour},
}
// serverMetrics holds the edge's operational instruments. It defaults to no-ops;
// NewServer installs the real meter when one is supplied in Deps.
type serverMetrics struct {
edge metric.Float64Histogram
edge metric.Float64Histogram
active *activeUsers
}
// newServerMetrics builds the instruments on meter (nil selects a no-op meter),
// falling back to a no-op histogram on the (rare) construction error.
// falling back to a no-op histogram on the (rare) construction error. The
// active_users gauge is registered as an observable callback over the in-memory
// tracker.
func newServerMetrics(meter metric.Meter) *serverMetrics {
if meter == nil {
meter = noop.NewMeterProvider().Meter(meterName)
@@ -30,7 +42,24 @@ func newServerMetrics(meter metric.Meter) *serverMetrics {
if err != nil {
h, _ = noop.NewMeterProvider().Meter(meterName).Float64Histogram("edge_request_duration")
}
return &serverMetrics{edge: h}
m := &serverMetrics{edge: h, active: newActiveUsers()}
gauge, err := meter.Int64ObservableGauge("active_users",
metric.WithDescription("Distinct accounts that performed an authenticated action within the window (in-memory, single gateway instance)."))
if err == nil {
windows := make([]time.Duration, len(activeUserWindows))
for i, w := range activeUserWindows {
windows[i] = w.dur
}
_, _ = meter.RegisterCallback(func(_ context.Context, o metric.Observer) error {
counts := m.active.counts(windows)
for i, w := range activeUserWindows {
o.ObserveInt64(gauge, int64(counts[i]), metric.WithAttributes(attribute.String("window", w.label)))
}
return nil
}, gauge)
}
return m
}
// recordEdge records the duration of one Execute call labelled by message type and
@@ -41,3 +70,8 @@ func (m *serverMetrics) recordEdge(ctx context.Context, msgType, result string,
attribute.String("result", result),
))
}
// recordActive marks account uid active now, feeding the active_users gauge.
func (m *serverMetrics) recordActive(uid string) {
m.active.seen(uid)
}