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

@@ -0,0 +1,196 @@
package audit_test
import (
"context"
"log/slog"
"net/http"
"net/http/httptest"
"os"
"testing"
"github.com/prometheus/client_golang/prometheus"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/fx"
"sneak.berlin/go/upaas/internal/config"
"sneak.berlin/go/upaas/internal/database"
"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/audit"
)
func setupTestAuditService(t *testing.T) (*audit.Service, *database.Database) {
t.Helper()
globals.SetAppname("upaas-test")
globals.SetVersion("test")
tmpDir := t.TempDir()
cfg := &config.Config{
DataDir: tmpDir,
}
log := slog.New(slog.NewTextHandler(os.Stderr, nil))
logWrapper := logger.NewForTest(log)
db, err := database.New(fx.Lifecycle(nil), database.Params{
Logger: logWrapper,
Config: cfg,
})
require.NoError(t, err)
reg := prometheus.NewRegistry()
metricsInstance := metrics.NewForTest(reg)
svc, err := audit.New(fx.Lifecycle(nil), audit.ServiceParams{
Logger: logWrapper,
Database: db,
Metrics: metricsInstance,
})
require.NoError(t, err)
return svc, db
}
func TestAuditServiceLog(t *testing.T) {
t.Parallel()
svc, db := setupTestAuditService(t)
ctx := context.Background()
svc.Log(ctx, audit.LogEntry{
UserID: 1,
Username: "admin",
Action: models.AuditActionLogin,
ResourceType: models.AuditResourceSession,
Detail: "user logged in",
RemoteIP: "127.0.0.1",
})
entries, err := models.FindAuditEntries(ctx, db, 10)
require.NoError(t, err)
require.Len(t, entries, 1)
assert.Equal(t, "admin", entries[0].Username)
assert.Equal(t, models.AuditActionLogin, entries[0].Action)
assert.Equal(t, "127.0.0.1", entries[0].RemoteIP.String)
}
func TestAuditServiceLogFromRequest(t *testing.T) {
t.Parallel()
svc, db := setupTestAuditService(t)
ctx := context.Background()
request := httptest.NewRequest(http.MethodPost, "/apps", nil)
request.RemoteAddr = "10.0.0.1:12345"
svc.LogFromRequest(ctx, request, audit.LogEntry{
Username: "admin",
Action: models.AuditActionAppCreate,
ResourceType: models.AuditResourceApp,
ResourceID: "app-1",
Detail: "created app",
})
entries, err := models.FindAuditEntries(ctx, db, 10)
require.NoError(t, err)
require.Len(t, entries, 1)
assert.Equal(t, "10.0.0.1", entries[0].RemoteIP.String)
assert.Equal(t, "app-1", entries[0].ResourceID.String)
}
func TestAuditServiceLogFromRequestWithXRealIP(t *testing.T) {
t.Parallel()
svc, db := setupTestAuditService(t)
ctx := context.Background()
request := httptest.NewRequest(http.MethodPost, "/apps", nil)
request.Header.Set("X-Real-IP", "203.0.113.50")
svc.LogFromRequest(ctx, request, audit.LogEntry{
Username: "admin",
Action: models.AuditActionAppCreate,
ResourceType: models.AuditResourceApp,
})
entries, err := models.FindAuditEntries(ctx, db, 10)
require.NoError(t, err)
require.Len(t, entries, 1)
assert.Equal(t, "203.0.113.50", entries[0].RemoteIP.String)
}
func TestAuditServiceRecent(t *testing.T) {
t.Parallel()
svc, _ := setupTestAuditService(t)
ctx := context.Background()
for range 5 {
svc.Log(ctx, audit.LogEntry{
Username: "admin",
Action: models.AuditActionLogin,
ResourceType: models.AuditResourceSession,
})
}
entries, err := svc.Recent(ctx, 3)
require.NoError(t, err)
assert.Len(t, entries, 3)
}
func TestAuditServiceForResource(t *testing.T) {
t.Parallel()
svc, _ := setupTestAuditService(t)
ctx := context.Background()
// Log entries for different resources.
svc.Log(ctx, audit.LogEntry{
Username: "admin",
Action: models.AuditActionAppCreate,
ResourceType: models.AuditResourceApp,
ResourceID: "app-1",
})
svc.Log(ctx, audit.LogEntry{
Username: "admin",
Action: models.AuditActionAppDeploy,
ResourceType: models.AuditResourceApp,
ResourceID: "app-1",
})
svc.Log(ctx, audit.LogEntry{
Username: "admin",
Action: models.AuditActionAppCreate,
ResourceType: models.AuditResourceApp,
ResourceID: "app-2",
})
entries, err := svc.ForResource(ctx, models.AuditResourceApp, "app-1", 10)
require.NoError(t, err)
assert.Len(t, entries, 2)
}
func TestAuditServiceLogWithNoOptionalFields(t *testing.T) {
t.Parallel()
svc, db := setupTestAuditService(t)
ctx := context.Background()
svc.Log(ctx, audit.LogEntry{
Username: "system",
Action: models.AuditActionWebhookReceive,
ResourceType: models.AuditResourceWebhook,
})
entries, err := models.FindAuditEntries(ctx, db, 10)
require.NoError(t, err)
require.Len(t, entries, 1)
assert.False(t, entries[0].UserID.Valid)
assert.False(t, entries[0].ResourceID.Valid)
assert.False(t, entries[0].Detail.Valid)
assert.False(t, entries[0].RemoteIP.Valid)
}