Files
paliad/cmd/server/main_smoke_test.go
mAi 586ba29b86 feat(test): migration dry-run gate + boot smoke (Slice 1)
Slice 1 of docs/design-paliad-test-strategy-2026-05-19.md — the test
infrastructure that would have caught mig 098 (digit-regex) and mig 099
(missing audit_reason) before the deploy hit prod.

Three new files + one route addition:

- Makefile: `make verify-migrations` (alias `verify-mig`) runs the
  per-migration dry-run + boot smoke against TEST_DATABASE_URL. Fails
  fast with a clear error if TEST_DATABASE_URL is unset so CI can't
  silently pass a missing env var. `make test` and `make test-go`
  cover the rest of the short / full Go suites.

- internal/db/migrate_test.go (TestMigrations_DryRun): walks every
  pending *.up.sql in numeric order, applies each inside its own
  BEGIN..ROLLBACK transaction, fails on the first SQL error with the
  file name + Postgres error. "Pending" = greater than the scratch
  DB's current tracker version, so fresh-DB CI runs verify everything
  while developer scratch DBs only re-verify the new pending migration.
  Always non-destructive — the rollback runs even on success.

- cmd/server/main_smoke_test.go (TestBootSmoke): boots the apply path
  end-to-end, asserts (a) db.ApplyMigrations returns nil, (b) the
  tracker advanced to the highest *.up.sql version on disk with
  dirty=false, (c) GET /healthz on the registered mux returns 200.
  The dry-run catches per-migration syntax errors; this catches the
  apply+bind path the container actually runs.

- internal/handlers/handlers.go: adds a GET /healthz public route — a
  no-auth, no-DB liveness probe. Used by the boot smoke; also safe
  for any future orchestrator or uptime check.

Both live-DB tests gate on TEST_DATABASE_URL and skip cleanly without
it, matching the rest of paliad's live-DB test pattern.

Verification: go build ./... clean, go vet ./... clean,
go test -short ./internal/... ./cmd/... clean (all packages pass,
live-DB tests skip), bun run build clean (2436 i18n keys unchanged).

Per CLAUDE.md inventor → coder gate, NOT self-merged.
2026-05-19 12:41:15 +02:00

171 lines
5.6 KiB
Go

// Boot smoke test — assert paliad reaches a serving state.
//
// Three checks against TEST_DATABASE_URL:
//
// 1. db.ApplyMigrations does not panic and returns nil.
// 2. The migration tracker (public.paliad_schema_migrations) advances to
// the highest *.up.sql version on disk — no migrations were silently
// skipped, no "dirty=true" stragglers left behind.
// 3. The handler mux (with /healthz mounted) responds 200 to GET /healthz.
//
// This is the lightweight cousin of the migration dry-run gate
// (internal/db/migrate_test.go): the dry-run catches per-migration syntax
// errors before merge; this smoke confirms the apply+bind path the
// container actually runs at boot. Together they cover the mig-098 /
// mig-099 class of crash-loops end-to-end.
//
// Skipped without TEST_DATABASE_URL — matches the rest of the live-DB tests.
//
// Design: docs/design-paliad-test-strategy-2026-05-19.md §5 Slice 1.
package main
import (
"database/sql"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"sort"
"strconv"
"strings"
"testing"
_ "github.com/lib/pq"
"mgit.msbls.de/m/paliad/internal/auth"
"mgit.msbls.de/m/paliad/internal/db"
"mgit.msbls.de/m/paliad/internal/handlers"
)
func TestBootSmoke(t *testing.T) {
url := os.Getenv("TEST_DATABASE_URL")
if url == "" {
t.Skip("TEST_DATABASE_URL not set — skipping boot smoke")
}
// (1) Apply migrations end-to-end. The same code path the prod
// container runs at boot before `http.ListenAndServe`. A regression
// like mig-098's digit-regex would surface here as a non-nil error.
if err := db.ApplyMigrations(url); err != nil {
t.Fatalf("db.ApplyMigrations: %v", err)
}
// (2) Assert the tracker advanced to the highest *.up.sql version we
// embed. If a migration was silently skipped or the tracker is dirty,
// the prod container would crash-loop — this turns that into a test
// failure with a precise reason.
expected := highestEmbeddedMigrationVersion(t)
got, dirty := readTrackerVersion(t, url)
if dirty {
t.Errorf("tracker reports dirty=true at version %d — investigate before deploying", got)
}
if got != expected {
t.Errorf("tracker at version %d; expected %d (highest *.up.sql on disk). "+
"A migration was skipped or applied out of order.",
got, expected)
}
// (3) Mount the public handlers (the same Register call main() makes,
// minus the DB-backed Services bundle which the /healthz route doesn't
// need) and assert /healthz returns 200. This is the bind-and-serve
// half of the smoke: catches a regression that would make /healthz
// 404 or break the mux registration order.
//
// We deliberately do not boot the full main() — that would require
// SUPABASE_URL, SUPABASE_ANON_KEY, SUPABASE_JWT_SECRET, an open
// listening socket and a real auth client. The /healthz handler is
// auth-independent by design, and Register registers it on the outer
// mux before any DB-backed route, so this minimal setup exercises the
// exact code path main() takes.
mux := http.NewServeMux()
authClient := auth.NewClient("https://test.invalid", "anon-key", []byte("test-secret"))
handlers.Register(mux, authClient, "", nil)
rec := httptest.NewRecorder()
req := httptest.NewRequest(http.MethodGet, "/healthz", nil)
mux.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Errorf("GET /healthz: status=%d, body=%q; want 200 OK", rec.Code, rec.Body.String())
}
if body := strings.TrimSpace(rec.Body.String()); body != "ok" {
t.Errorf("GET /healthz: body=%q; want \"ok\"", body)
}
}
// highestEmbeddedMigrationVersion finds max(N) over every NNN_*.up.sql
// file in internal/db/migrations/ on disk. Used as the expected tracker
// version after a clean apply. We read from disk (not the embed.FS in
// the db package — it's unexported) since the test runs from the repo.
func highestEmbeddedMigrationVersion(t *testing.T) int {
t.Helper()
root, err := repoRoot()
if err != nil {
t.Fatalf("locate repo root: %v", err)
}
dir := filepath.Join(root, "internal", "db", "migrations")
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatalf("read migrations dir %s: %v", dir, err)
}
var versions []int
for _, e := range entries {
name := e.Name()
if !strings.HasSuffix(name, ".up.sql") {
continue
}
base := strings.TrimSuffix(name, ".up.sql")
underscore := strings.IndexByte(base, '_')
if underscore <= 0 {
continue
}
v, err := strconv.Atoi(base[:underscore])
if err != nil {
continue
}
versions = append(versions, v)
}
if len(versions) == 0 {
t.Fatalf("no *.up.sql files found in %s", dir)
}
sort.Ints(versions)
return versions[len(versions)-1]
}
// readTrackerVersion fetches the lone row from the tracker. golang-migrate
// keeps exactly one row; if we ever see zero or more, that's the dirty-state
// the test is designed to flag.
func readTrackerVersion(t *testing.T, url string) (version int, dirty bool) {
t.Helper()
conn, err := sql.Open("postgres", url)
if err != nil {
t.Fatalf("open: %v", err)
}
defer conn.Close()
row := conn.QueryRow(`SELECT version, dirty FROM public.paliad_schema_migrations LIMIT 1`)
if err := row.Scan(&version, &dirty); err != nil {
t.Fatalf("read tracker: %v", err)
}
return version, dirty
}
// repoRoot walks upward from the test binary's working directory until it
// finds a go.mod. `go test` runs in the package dir, so we typically have
// to climb a couple of levels.
func repoRoot() (string, error) {
dir, err := os.Getwd()
if err != nil {
return "", err
}
for {
if _, err := os.Stat(filepath.Join(dir, "go.mod")); err == nil {
return dir, nil
}
parent := filepath.Dir(dir)
if parent == dir {
return "", os.ErrNotExist
}
dir = parent
}
}