tapir/cmd/tapir/uploads_test.go

package main

import (
	"context"
	"errors"
	"os"
	"path/filepath"
	"testing"
	"time"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"

	"git.d-ma.be/mathias/tapir/internal/adapters/transcribe"
	"git.d-ma.be/mathias/tapir/internal/config"
	"git.d-ma.be/mathias/tapir/internal/domain"
	"git.d-ma.be/mathias/tapir/internal/web"
)

// fakeUploadsStore satisfies the store surface buildUploads needs, and counts the
// start-up sweep.
type fakeUploadsStore struct {
	sweeps      int
	sweepErr    error
	failedKinds []domain.UploadErrorKind
}

func (f *fakeUploadsStore) CreateUpload(context.Context, string, string, bool) (string, error) {
	return "id", nil
}

func (f *fakeUploadsStore) FailUpload(_ context.Context, _, _ string, k domain.UploadErrorKind) error {
	f.failedKinds = append(f.failedKinds, k)
	return nil
}

func (f *fakeUploadsStore) StartTranscribing(context.Context, string, string) error { return nil }

func (f *fakeUploadsStore) CompleteUpload(context.Context, string, string, domain.Transcription) error {
	return nil
}

func (f *fakeUploadsStore) SaveProgress(context.Context, string, string, []domain.ProgressStep, time.Time) error {
	return nil
}

func (f *fakeUploadsStore) Heartbeat(context.Context, string, string) error { return nil }

func (f *fakeUploadsStore) FailInterruptedUploads(context.Context) (int, error) {
	f.sweeps++
	return 2, f.sweepErr
}

func uploadCfg(t *testing.T, enabled bool) config.Config {
	t.Helper()
	var cfg config.Config
	cfg.GatewayURL = "http://gateway.invalid/v1"
	cfg.UploadsEnabled = enabled
	cfg.UploadMaxBytes = 200 << 20
	cfg.UploadTmpDir = filepath.Join(t.TempDir(), "spool")
	cfg.TranscribeModel = "iguana/kb-whisper"
	cfg.TranscribeFallbackModel = "berget/kb-whisper"
	return cfg
}

func TestBuildUploads_DisabledMountsNothingAndSweepsNothing(t *testing.T) {
	st := &fakeUploadsStore{}

	in, w, err := buildUploads(context.Background(), uploadCfg(t, false), st, quietLog())

	require.NoError(t, err)
	assert.Nil(t, in, "a typed-nil Intake must never reach web.App.Uploads: it would mount the routes over nothing")
	assert.Nil(t, w)
	assert.Zero(t, st.sweeps)
}

func TestBuildUploads_EnabledFailsInterruptedRowsBeforeAnythingElseStarts(t *testing.T) {
	st := &fakeUploadsStore{}

	in, w, err := buildUploads(context.Background(), uploadCfg(t, true), st, quietLog())

	require.NoError(t, err)
	require.NotNil(t, in)
	require.NotNil(t, w)
	assert.Equal(t, 1, st.sweeps,
		"audio is not retained, so rows left queued/transcribing by a restart can never resume: fail them at start-up, not never")
}

func TestBuildUploads_SweepFailureStopsStartup(t *testing.T) {
	st := &fakeUploadsStore{sweepErr: errors.New("db down")}

	_, _, err := buildUploads(context.Background(), uploadCfg(t, true), st, quietLog())

	require.Error(t, err)
	assert.Contains(t, err.Error(), "db down")
}

func TestBuildUploads_CreatesTheSpoolDirectoryPrivately(t *testing.T) {
	cfg := uploadCfg(t, true)

	_, _, err := buildUploads(context.Background(), cfg, &fakeUploadsStore{}, quietLog())

	require.NoError(t, err)
	info, err := os.Stat(cfg.UploadTmpDir)
	require.NoError(t, err)
	assert.True(t, info.IsDir())
	assert.Equal(t, os.FileMode(0o700), info.Mode().Perm(), "spooled audio is private third-party content")
}

func TestBuildUploads_EnabledWithoutAGatewayIsAnError(t *testing.T) {
	cfg := uploadCfg(t, true)
	cfg.GatewayURL = ""

	_, _, err := buildUploads(context.Background(), cfg, &fakeUploadsStore{}, quietLog())

	assert.Error(t, err, "uploads on with nowhere to transcribe must fail loudly at start-up, not at the first upload")
}

func TestBuildUploads_RemovesAudioLeftBehindByACrash(t *testing.T) {
	cfg := uploadCfg(t, true)
	require.NoError(t, os.MkdirAll(cfg.UploadTmpDir, 0o700))
	leftovers := []string{"upload-123", "wav-456"}
	for _, n := range leftovers {
		require.NoError(t, os.WriteFile(filepath.Join(cfg.UploadTmpDir, n), []byte("audio"), 0o600))
	}
	unrelated := filepath.Join(cfg.UploadTmpDir, "someone-elses-file")
	require.NoError(t, os.WriteFile(unrelated, []byte("keep"), 0o600))

	_, _, err := buildUploads(context.Background(), cfg, &fakeUploadsStore{}, quietLog())

	require.NoError(t, err)
	for _, n := range leftovers {
		_, err := os.Stat(filepath.Join(cfg.UploadTmpDir, n))
		assert.True(t, os.IsNotExist(err), "%s: audio is never retained, so a spooled file from a crashed run must not survive start-up", n)
	}
	_, err = os.Stat(unrelated)
	assert.NoError(t, err, "only our own spool files are removed")
}

func TestWireUploads_SetsEverythingTheWebAppNeedsForUploadsAndChat(t *testing.T) {
	cfg := uploadCfg(t, true)
	cfg.UploadMaxDuration = 90 * 60 * 1e9
	cfg.MaxUploadedTranscriptChars = 90000
	cfg.UploadChatModel = "iguana/gemma4-26b"
	in, _, err := buildUploads(context.Background(), cfg, &fakeUploadsStore{}, quietLog())
	require.NoError(t, err)
	app := &web.App{}

	wireUploads(app, cfg, in)

	assert.NotNil(t, app.Uploads)
	assert.Equal(t, cfg.UploadMaxBytes, app.UploadLimits.MaxBytes, "the form states the limits Intake enforces")
	assert.Equal(t, cfg.UploadMaxDuration, app.UploadLimits.MaxDuration)
	assert.Equal(t, 90000, app.UploadChatMaxChars,
		"without this the chat would use the 18,000-char caption default and cut an hour to its first third")
	assert.Equal(t, "iguana/gemma4-26b", app.UploadChatModel)
}

func TestWireUploads_NilIntakeLeavesTheAppUntouched(t *testing.T) {
	app := &web.App{}

	wireUploads(app, uploadCfg(t, false), nil)

	assert.Nil(t, app.Uploads, "a nil *Intake must not become a non-nil interface that mounts the routes")
	assert.Zero(t, app.UploadChatMaxChars)
}

func TestBuildTranscriber_DefaultIsTheSingleEngineChainAsBefore(t *testing.T) {
	cfg := uploadCfg(t, true)

	tr := buildTranscriber(cfg)

	assert.IsType(t, &transcribe.Chain{}, tr, "with no base engine configured nothing changes")
}

func TestBuildTranscriber_ABaseEngineTurnsOnTheEnsemble(t *testing.T) {
	cfg := uploadCfg(t, true)
	cfg.ReconcileBaseModel = "iguana/pianissimo"
	cfg.ReconcileModel = "iguana/gemma4-26b"

	tr := buildTranscriber(cfg)

	assert.IsType(t, &transcribe.Ensemble{}, tr)
}

func TestBuildUploads_WiresTheEnsembleWhenConfigured(t *testing.T) {
	cfg := uploadCfg(t, true)
	cfg.ReconcileBaseModel = "iguana/pianissimo"
	cfg.ReconcileModel = "iguana/gemma4-26b"

	in, w, err := buildUploads(context.Background(), cfg, &fakeUploadsStore{}, quietLog())

	require.NoError(t, err)
	assert.NotNil(t, in)
	assert.NotNil(t, w)
}