feat: add observability improvements (metrics, audit log, structured logging)
All checks were successful
Check / check (pull_request) Successful in 1m45s

- Add Prometheus metrics package (internal/metrics) with deployment,
  container health, webhook, HTTP request, and audit counters/histograms
- Add audit_log SQLite table via migration 007
- Add AuditEntry model with CRUD operations and query methods
- Add audit service (internal/service/audit) for recording user actions
- Instrument deploy service with deployment duration, count, and
  in-flight metrics; container health gauge updates on deploy completion
- Instrument webhook service with event counters by app/type/matched
- Instrument HTTP middleware with request count, duration, and response
  size metrics; also log response bytes in structured request logs
- Add audit logging to all key handler operations: login/logout, app
  CRUD, deploy, cancel, rollback, restart/stop/start, webhook receipt,
  and initial setup
- Add GET /api/audit endpoint for querying recent audit entries
- Make /metrics endpoint always available (optionally auth-protected)
- Add comprehensive tests for metrics, audit model, and audit service
- Update existing test infrastructure with metrics and audit dependencies
- Update README with Observability section documenting all metrics,
  audit log, and structured logging
This commit is contained in:
clawbot
2026-03-17 02:23:44 -07:00
parent fd110e69db
commit f558e2cdd8
21 changed files with 1399 additions and 42 deletions

View File

@@ -8,6 +8,7 @@ import (
"testing"
"time"
"github.com/prometheus/client_golang/prometheus"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/fx"
@@ -17,6 +18,7 @@ import (
"sneak.berlin/go/upaas/internal/docker"
"sneak.berlin/go/upaas/internal/globals"
"sneak.berlin/go/upaas/internal/logger"
"sneak.berlin/go/upaas/internal/metrics"
"sneak.berlin/go/upaas/internal/models"
"sneak.berlin/go/upaas/internal/service/deploy"
"sneak.berlin/go/upaas/internal/service/notify"
@@ -63,13 +65,17 @@ func setupTestService(t *testing.T) (*webhook.Service, *database.Database, func(
notifySvc, err := notify.New(fx.Lifecycle(nil), notify.ServiceParams{Logger: deps.logger})
require.NoError(t, err)
metricsInstance := metrics.NewForTest(prometheus.NewRegistry())
deploySvc, err := deploy.New(fx.Lifecycle(nil), deploy.ServiceParams{
Logger: deps.logger, Config: deps.config, Database: deps.db, Docker: dockerClient, Notify: notifySvc,
Metrics: metricsInstance,
})
require.NoError(t, err)
svc, err := webhook.New(fx.Lifecycle(nil), webhook.ServiceParams{
Logger: deps.logger, Database: deps.db, Deploy: deploySvc,
Metrics: metricsInstance,
})
require.NoError(t, err)