paliad/cmd/server/main_smoke_test.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. paliad.applied_migrations covers every on-disk *.up.sql — no
//     migration was silently skipped, no version is missing. The set
//     contract is stronger than the old single-counter check: applied
//     set must EQUAL on-disk set, not just reach the max version.
//  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, plus the mig-103 parallel-merge
// skip-hole that t-paliad-218 closed (m/paliad#44).
//
// 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 and
// docs/design-migration-runner-applied-set-2026-05-20.md §6.

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 applied set equals the on-disk set. The new runner
	// tracks applied state per-migration; a silently-skipped version
	// would surface as a row missing from paliad.applied_migrations even
	// though max(version) matches. Comparing sets — not just max —
	// catches the failure mode the t-paliad-218 post-mortem documented.
	onDisk := embeddedMigrationVersions(t)
	applied := appliedMigrationVersions(t, url)

	if missing := setDiff(onDisk, applied); len(missing) > 0 {
		t.Errorf("paliad.applied_migrations missing %d on-disk versions: %v "+
			"(a migration was skipped — investigate before deploying)",
			len(missing), missing)
	}
	if extra := setDiff(applied, onDisk); len(extra) > 0 {
		t.Errorf("paliad.applied_migrations has %d versions with no on-disk file: %v "+
			"(orphan rows — either restore the file or DELETE the row)",
			len(extra), extra)
	}

	// (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)
	}

	// (4) Readiness probe. With a nil Services bundle the endpoint MUST
	// report 503 — that's the contract documented in handlers/handlers.go.
	// A separate svc-with-Pool case is exercised in TestHealthReady (live).
	rec = httptest.NewRecorder()
	req = httptest.NewRequest(http.MethodGet, "/health/ready", nil)
	mux.ServeHTTP(rec, req)
	if rec.Code != http.StatusServiceUnavailable {
		t.Errorf("GET /health/ready (nil svc): status=%d; want 503", rec.Code)
	}
}

// TestHealthReady_Live asserts the readiness probe answers 200 when the
// pool is reachable, 503 when it isn't. Requires TEST_DATABASE_URL.
//
// Why a separate test: TestBootSmoke runs Register with svc=nil to keep
// its setup minimal; the pool-reachable path needs the pool wired in
// through svc.Pool. Two tests, two assertions, no entanglement.
func TestHealthReady_Live(t *testing.T) {
	url := os.Getenv("TEST_DATABASE_URL")
	if url == "" {
		t.Skip("TEST_DATABASE_URL not set — skipping live readiness probe")
	}

	if err := db.ApplyMigrations(url); err != nil {
		t.Fatalf("db.ApplyMigrations: %v", err)
	}
	pool, err := db.OpenPool(url)
	if err != nil {
		t.Fatalf("open pool: %v", err)
	}

	mux := http.NewServeMux()
	authClient := auth.NewClient("https://test.invalid", "anon-key", []byte("test-secret"))
	handlers.Register(mux, authClient, "", &handlers.Services{Pool: pool})

	rec := httptest.NewRecorder()
	req := httptest.NewRequest(http.MethodGet, "/health/ready", nil)
	mux.ServeHTTP(rec, req)
	if rec.Code != http.StatusOK {
		t.Errorf("GET /health/ready (live pool): status=%d, body=%q; want 200", rec.Code, rec.Body.String())
	}
	if body := strings.TrimSpace(rec.Body.String()); body != "ready" {
		t.Errorf("GET /health/ready (live pool): body=%q; want \"ready\"", body)
	}
}

// embeddedMigrationVersions returns every N where N_*.up.sql exists in
// internal/db/migrations/ on disk. The boot smoke compares this set
// against paliad.applied_migrations to detect skipped or orphan
// migrations.
//
// Read from disk (not the embed.FS inside the db package — it's unexported)
// since the test runs from the repo. The two views must agree for the
// build to be self-consistent; if they diverge, the smoke test is the
// wrong place to learn about it (the build is). We trust them to match.
func embeddedMigrationVersions(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
}

// appliedMigrationVersions reads paliad.applied_migrations and returns
// the sorted list of versions. Fails the test if the table doesn't exist —
// db.ApplyMigrations is supposed to have created it by this point.
func appliedMigrationVersions(t *testing.T, url string) []int {
	t.Helper()
	conn, err := sql.Open("postgres", url)
	if err != nil {
		t.Fatalf("open: %v", err)
	}
	defer conn.Close()
	rows, err := conn.Query(`SELECT version FROM paliad.applied_migrations ORDER BY version`)
	if err != nil {
		t.Fatalf("read applied_migrations: %v", err)
	}
	defer rows.Close()
	var out []int
	for rows.Next() {
		var v int
		if err := rows.Scan(&v); err != nil {
			t.Fatalf("scan: %v", err)
		}
		out = append(out, v)
	}
	if err := rows.Err(); err != nil {
		t.Fatalf("rows: %v", err)
	}
	return out
}

// setDiff returns the elements of a that are not in b. Inputs are sorted
// ascending; output preserves that ordering.
func setDiff(a, b []int) []int {
	bset := make(map[int]bool, len(b))
	for _, v := range b {
		bset[v] = true
	}
	var out []int
	for _, v := range a {
		if !bset[v] {
			out = append(out, v)
		}
	}
	return out
}

// 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
	}
}