Add a webhooker resetpw subcommand and a bootstrap banner (closes #208) (#239)

The admin bootstrap password was printed once, as one line among roughly
45 fx lines, and under docker run -d went to container logs subject to
rotation. There was no reset path at all -- no subcommand, no forgot-password
flow, no env override -- so recovery meant hand-deleting the users row from
webhooker.db, which was documented nowhere.

Adds webhooker resetpw [-generate] <username>. The password is read from
stdin or generated with the existing crypto/rand helper, never taken from
argv where /proc would publish it. It reuses the existing Argon2id hashing
rather than reimplementing the parameters, and writes a single UPDATE only
after the hash is complete, so no failure can leave an account with no
usable password. An unknown username is a hard error and never creates an
account.

It refuses to run against a DATA_DIR held by a live instance, via the
exclusive lock from #201. DATA_DIR and webhooker.db are checked to exist
before the lock is acquired, so a mistyped path creates nothing -- neither
a directory tree nor a stray lock file.

The bootstrap password now appears exactly once, in a distinct banner
written straight to a caller-named writer rather than as an fx log line.

internal/resetpw/resetpw_test.go

@@ -0,0 +1,443 @@
+package resetpw_test
+
+import (
+	"bytes"
+	"context"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"go.uber.org/fx/fxtest"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/datadir"
+	"sneak.berlin/go/webhooker/internal/delivery"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/handlers"
+	"sneak.berlin/go/webhooker/internal/healthcheck"
+	"sneak.berlin/go/webhooker/internal/logger"
+	"sneak.berlin/go/webhooker/internal/middleware"
+	"sneak.berlin/go/webhooker/internal/resetpw"
+	"sneak.berlin/go/webhooker/internal/session"
+)
+
+const (
+	// operatorUser is the account these tests recover.
+	operatorUser = "admin"
+
+	// newPassword is what the operator sets it to.
+	newPassword = "correct horse battery staple"
+
+	// placeholderHash stands in for the stored credential nobody
+	// knows any more — the lost bootstrap password. Nothing here
+	// verifies against it; what matters is whether it is still there
+	// after a refusal, or replaced after a reset.
+	placeholderHash = "$argon2id$lost"
+
+	// exitOK and exitFailure are the statuses Run returns.
+	exitOK      = 0
+	exitFailure = 1
+)
+
+// testLogger is quiet unless something goes wrong.
+func testLogger() *slog.Logger {
+	return slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{
+		Level: slog.LevelWarn,
+	}))
+}
+
+// newDeployment builds a data directory holding a migrated database
+// with one account whose password is unknown, and points DATA_DIR at
+// it. It deliberately does not boot the server graph: seeding through
+// it would spend an Argon2id hash on a password no test can use.
+func newDeployment(t *testing.T) string {
+	t.Helper()
+
+	dir := t.TempDir()
+	t.Setenv("DATA_DIR", dir)
+
+	db, err := database.Open(dir, testLogger())
+	require.NoError(t, err)
+
+	require.NoError(t, db.DB().Create(&database.User{
+		Username: operatorUser,
+		Password: placeholderHash,
+	}).Error)
+
+	require.NoError(t, db.Close())
+
+	return dir
+}
+
+// storedHash reads the account's stored credential back.
+func storedHash(t *testing.T, dir string) string {
+	t.Helper()
+
+	db, err := database.Open(dir, testLogger())
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, db.Close()) }()
+
+	var user database.User
+
+	require.NoError(t, db.DB().
+		Where("username = ?", operatorUser).
+		First(&user).Error)
+
+	return user.Password
+}
+
+// bannerPassword returns the plaintext a credentials banner printed.
+func bannerPassword(t *testing.T, out string) string {
+	t.Helper()
+
+	for line := range strings.SplitSeq(out, "\n") {
+		_, value, found := strings.Cut(line, "password: ")
+		if found {
+			return strings.TrimSpace(value)
+		}
+	}
+
+	t.Fatalf("no password line in:\n%s", out)
+
+	return ""
+}
+
+// run drives the subcommand with the given standard input and returns
+// its status alongside what it wrote.
+func run(
+	t *testing.T, stdin string, args ...string,
+) (int, string, string) {
+	t.Helper()
+
+	var stdout, stderr bytes.Buffer
+
+	code := resetpw.Run(
+		args, strings.NewReader(stdin), &stdout, &stderr,
+	)
+
+	return code, stdout.String(), stderr.String()
+}
+
+type noopNotifier struct{}
+
+func (n *noopNotifier) Notify([]delivery.Task) {}
+
+type noopEvictor struct{}
+
+func (n *noopEvictor) EvictWebhook(string) {}
+
+// newServerApp starts the real login path against dir: the handlers,
+// the middleware that bounds password verification, the session store
+// and the database, exactly as internal/handlers builds them.
+//
+// One application per test function, not per case: every start that
+// finds no account seeds one at 64 MB of Argon2id, and this package's
+// budget is not the place to spend that repeatedly.
+func newServerApp(
+	t *testing.T, dir string,
+) (*handlers.Handlers, *fxtest.App) {
+	t.Helper()
+
+	var h *handlers.Handlers
+
+	app := fxtest.New(
+		t,
+		fx.Provide(
+			globals.New,
+			logger.New,
+			func() *config.Config {
+				return &config.Config{DataDir: dir}
+			},
+			database.New,
+			database.NewWebhookDBManager,
+			healthcheck.New,
+			session.New,
+			func() delivery.Notifier { return &noopNotifier{} },
+			func() delivery.WebhookEvictor { return &noopEvictor{} },
+			middleware.New,
+			handlers.New,
+		),
+		fx.Populate(&h),
+	)
+
+	app.RequireStart()
+
+	return h, app
+}
+
+// submitLogin drives one login form POST through the real handler.
+func submitLogin(
+	h *handlers.Handlers, username, password string,
+) *httptest.ResponseRecorder {
+	form := url.Values{}
+	form.Set("username", username)
+	form.Set("password", password)
+
+	req := httptest.NewRequestWithContext(
+		context.Background(),
+		http.MethodPost,
+		"/pages/login",
+		strings.NewReader(form.Encode()),
+	)
+	req.Header.Set(
+		"Content-Type", "application/x-www-form-urlencoded",
+	)
+	req.RemoteAddr = "10.0.0.1:44444"
+
+	w := httptest.NewRecorder()
+	h.HandleLoginSubmit().ServeHTTP(w, req)
+
+	return w
+}
+
+// TestResetThenLogin is the definition of done of
+// https://git.eeqj.de/sneak/webhooker/issues/208: an operator who lost
+// the one-time bootstrap password sets a new one from the command line
+// and logs in with it.
+//
+// The login is the real one — the form POST through
+// handlers.HandleLoginSubmit, which looks the account up and verifies
+// the stored Argon2id hash — so a reset that wrote a hash the login
+// path cannot verify fails here rather than passing a re-implementation
+// of the check.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestResetThenLogin(t *testing.T) {
+	dir := newDeployment(t)
+
+	code, stdout, stderr := run(t, newPassword+"\n", operatorUser)
+	require.Equal(t, exitOK, code, "stderr: %s", stderr)
+
+	assert.NotContains(
+		t, stdout, newPassword,
+		"a password the operator supplied must not be echoed back",
+	)
+	assert.Contains(t, stdout, operatorUser)
+
+	h, app := newServerApp(t, dir)
+
+	defer app.RequireStop()
+
+	got := submitLogin(h, operatorUser, newPassword)
+	require.Equal(
+		t, http.StatusSeeOther, got.Code,
+		"the new password must log in",
+	)
+
+	got = submitLogin(h, operatorUser, "not-"+newPassword)
+	require.NotEqual(
+		t, http.StatusSeeOther, got.Code,
+		"the reset must not make every password work",
+	)
+}
+
+// TestGeneratedPasswordIsPrintedAndWorks covers -generate, the mode an
+// operator recovering a deployment actually reaches for. The generated
+// password is shown once, in the banner, and must be the one stored.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestGeneratedPasswordIsPrintedAndWorks(t *testing.T) {
+	dir := newDeployment(t)
+
+	code, stdout, stderr := run(t, "", "-generate", operatorUser)
+	require.Equal(t, exitOK, code, "stderr: %s", stderr)
+
+	require.Contains(
+		t, stdout, strings.Repeat("=", 20),
+		"a generated password must be printed as a banner",
+	)
+
+	password := bannerPassword(t, stdout)
+
+	ok, err := database.VerifyPassword(password, storedHash(t, dir))
+	require.NoError(t, err)
+	assert.True(
+		t, ok, "the printed password must open the account",
+	)
+}
+
+// failingWriter is a standard output that cannot be written to.
+type failingWriter struct{}
+
+func (failingWriter) Write([]byte) (int, error) {
+	return 0, assert.AnError
+}
+
+// TestGeneratedPasswordSurvivesAFailedStdout covers the one outcome
+// worse than an error: the password is already stored, so a banner
+// that cannot be written to standard output must go to standard error
+// rather than leaving the deployment behind a password nobody has seen.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestGeneratedPasswordSurvivesAFailedStdout(t *testing.T) {
+	dir := newDeployment(t)
+
+	var stderr bytes.Buffer
+
+	code := resetpw.Run(
+		[]string{"-generate", operatorUser},
+		strings.NewReader(""), failingWriter{}, &stderr,
+	)
+
+	require.Equal(t, exitOK, code)
+
+	password := bannerPassword(t, stderr.String())
+
+	ok, err := database.VerifyPassword(password, storedHash(t, dir))
+	require.NoError(t, err)
+	assert.True(t, ok)
+}
+
+// TestRefusesLiveInstance pins the refusal the issue requires. The
+// running deployment keeps serving the sessions that authenticated
+// with the old password, so a reset underneath it would report a
+// change the service does not honour.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestRefusesLiveInstance(t *testing.T) {
+	dir := newDeployment(t)
+
+	lock, err := datadir.Acquire(dir)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, lock.Release()) }()
+
+	code, _, stderr := run(t, newPassword+"\n", operatorUser)
+
+	require.Equal(t, exitFailure, code)
+	assert.Contains(t, stderr, dir, "the refusal must name DATA_DIR")
+	assert.Contains(t, stderr, "running webhooker")
+	assert.Equal(
+		t, placeholderHash, storedHash(t, dir),
+		"a refused reset must not touch the stored credential",
+	)
+}
+
+// TestMissingDataDirCreatesNothing pins the side effect that must not
+// happen. datadir.Acquire calls os.MkdirAll, so reaching it with a
+// mistyped DATA_DIR would build the directory, take a lock in it and
+// migrate an empty database there — reporting success against a
+// deployment that does not exist.
+func TestMissingDataDirCreatesNothing(t *testing.T) {
+	dir := filepath.Join(t.TempDir(), "typo", "webhooker")
+	t.Setenv("DATA_DIR", dir)
+
+	code, _, stderr := run(t, newPassword+"\n", operatorUser)
+
+	require.Equal(t, exitFailure, code)
+	assert.Contains(t, stderr, dir)
+
+	_, err := os.Stat(dir)
+	assert.ErrorIs(
+		t, err, os.ErrNotExist,
+		"a mistyped DATA_DIR must not be created",
+	)
+}
+
+// TestMissingDatabaseCreatesNothing covers the directory that exists
+// but holds no deployment: an empty volume, or the wrong one. Nothing
+// may be written there either, lock file included.
+func TestMissingDatabaseCreatesNothing(t *testing.T) {
+	dir := t.TempDir()
+	t.Setenv("DATA_DIR", dir)
+
+	code, _, stderr := run(t, newPassword+"\n", operatorUser)
+
+	require.Equal(t, exitFailure, code)
+	assert.Contains(t, stderr, database.MainDBFileName)
+
+	entries, err := os.ReadDir(dir)
+	require.NoError(t, err)
+	assert.Empty(
+		t, entries,
+		"nothing may be created in a directory holding no database",
+	)
+}
+
+// TestUnknownUserFails states the decision: resetpw changes an
+// existing account's password and never creates an account. A typo in
+// the username must say so rather than quietly adding a second user.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestUnknownUserFails(t *testing.T) {
+	dir := newDeployment(t)
+
+	code, _, stderr := run(t, newPassword+"\n", "amdin")
+
+	require.Equal(t, exitFailure, code)
+	assert.Contains(t, stderr, "amdin")
+	assert.Equal(t, placeholderHash, storedHash(t, dir))
+
+	var count int64
+
+	db, err := database.Open(dir, testLogger())
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, db.Close()) }()
+
+	require.NoError(t, db.DB().Model(&database.User{}).
+		Count(&count).Error)
+	assert.EqualValues(
+		t, 1, count, "no account may have been created",
+	)
+}
+
+// TestRejectsUnusablePasswords covers what standard input can carry by
+// accident: nothing at all, and a stray keystroke. Either would
+// otherwise become the account's only credential.
+//
+//nolint:paralleltest // newDeployment sets DATA_DIR with t.Setenv.
+func TestRejectsUnusablePasswords(t *testing.T) {
+	dir := newDeployment(t)
+
+	for name, stdin := range map[string]string{
+		"empty":   "",
+		"newline": "\n",
+		"short":   "hunter2\n",
+	} {
+		t.Run(name, func(t *testing.T) {
+			code, _, stderr := run(t, stdin, operatorUser)
+
+			require.Equal(t, exitFailure, code)
+			assert.NotEmpty(t, stderr)
+			assert.Equal(
+				t, placeholderHash, storedHash(t, dir),
+				"a rejected password must not be stored",
+			)
+		})
+	}
+}
+
+// TestUsageErrors pins the statuses a caller can script against: 2 for
+// being called wrong, which is not the same as a refusal.
+func TestUsageErrors(t *testing.T) {
+	t.Parallel()
+
+	for name, args := range map[string][]string{
+		"no username":   {},
+		"two usernames": {"admin", "root"},
+		"unknown flag":  {"-force", "admin"},
+	} {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			var stdout, stderr bytes.Buffer
+
+			code := resetpw.Run(
+				args, strings.NewReader(""), &stdout, &stderr,
+			)
+
+			assert.Equal(t, 2, code)
+			assert.NotEmpty(t, stderr)
+		})
+	}
+}