feat(uploads): choose the language of a recording; record it, show it, carry it to the engines (#61)

Form field (Swedish preselected, Other = auto) read before the file part and refused
before anything is spooled if outside the closed set; stored on the row (migration 021,
CHECK constraint, default sv for history); carried on the Job and the worker's context;
shown on the status page. Feature scenarios and the coverage map are updated, and
ADR-033/034 amended.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

internal/adapters/store/migrations/021_uploaded_transcripts_language.down.sql

@@ -0,0 +1,2 @@
+ALTER TABLE uploaded_transcripts
+    DROP COLUMN language;

internal/adapters/store/migrations/021_uploaded_transcripts_language.up.sql

@@ -0,0 +1,13 @@
+-- Migration 021: the language an upload is transcribed as (tapir#61).
+--
+-- 'sv'   Swedish: the engines are sent language=sv. Every row before this migration was
+--        transcribed that way (the request hard-coded it), so the default is true history.
+-- 'auto' Other: the engine detects the language and the Swedish-only engine is not used.
+--
+-- A closed set held by the table as well as by the form and the request code, so a second
+-- writer or a bug cannot store a value the engines are never meant to receive. The column
+-- sits on the already-FORCE'd, RLS-scoped uploaded_transcripts, so the exact-set isolation
+-- test is unaffected.
+ALTER TABLE uploaded_transcripts
+    ADD COLUMN language TEXT NOT NULL DEFAULT 'sv'
+        CONSTRAINT uploaded_transcripts_language_check CHECK (language IN ('sv', 'auto'));

internal/adapters/store/uploaded_transcripts.go

@@ -31,12 +31,12 @@ var ErrUploadInProgress = errors.New("store: uploaded transcript is still being
 // CreateUpload records a new upload in the queued state and returns its id.
 // hadVideo records that the file carried a video track (only its audio is used);
 // it is kept for the life of the row so the page can say so.
-func (s *Store) CreateUpload(ctx context.Context, userID, title string, hadVideo bool) (string, error) {
+func (s *Store) CreateUpload(ctx context.Context, userID, title string, lang domain.Language, hadVideo bool) (string, error) {
 	var id string
 	if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
 		return tx.QueryRow(ctx,
-			`INSERT INTO uploaded_transcripts (user_id, title, had_video) VALUES ($1, $2, $3) RETURNING id`,
-			userID, title, hadVideo).Scan(&id)
+			`INSERT INTO uploaded_transcripts (user_id, title, language, had_video) VALUES ($1, $2, $3, $4) RETURNING id`,
+			userID, title, string(lang), hadVideo).Scan(&id)
 	}); err != nil {
 		return "", fmt.Errorf("store: create upload: %w", err)
 	}
@@ -221,7 +221,7 @@ func (s *Store) FailInterruptedUploads(ctx context.Context) (int, error) {
 	return total, nil
 }
 
-const uploadSelect = `SELECT id, user_id, title, status, content, segments, endpoint,
+const uploadSelect = `SELECT id, user_id, title, language, status, content, segments, endpoint,
        audio_seconds, error_kind, had_video, reconciliation, progress, progress_at, alive_at,
        created_at, finished_at FROM uploaded_transcripts`
 
@@ -234,11 +234,13 @@ func scanUpload(row pgx.Row, u *domain.UploadedTranscript, withText bool) error
 		seconds                            *float64
 		finished, progressAt, aliveAt      *time.Time
 	)
-	if err := row.Scan(&u.ID, &u.UserID, &u.Title, &status, &content, &segments, &endpoint,
+	var language string
+	if err := row.Scan(&u.ID, &u.UserID, &u.Title, &language, &status, &content, &segments, &endpoint,
 		&seconds, &errKind, &u.HadVideo, &reconciliation, &progress, &progressAt, &aliveAt,
 		&u.CreatedAt, &finished); err != nil {
 		return err
 	}
+	u.Language = domain.Language(language)
 	u.Status = domain.UploadStatus(deref(status))
 	u.Endpoint = deref(endpoint)
 	u.ErrorKind = domain.UploadErrorKind(deref(errKind))

internal/adapters/store/uploaded_transcripts_delete_test.go

@@ -42,7 +42,7 @@ func TestDeleteUpload_RefusesAnUploadThatIsStillQueuedOrTranscribingAndKeepsTheR
 	s := newStore(t)
 	ctx := context.Background()
 	queued := startedUpload(t, s)
-	running, err := s.CreateUpload(ctx, userA, "running", false)
+	running, err := s.CreateUpload(ctx, userA, "running", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, running))
 

internal/adapters/store/uploaded_transcripts_failguard_test.go

@@ -34,7 +34,7 @@ func TestFailUpload_StillFailsAQueuedOrTranscribingUpload(t *testing.T) {
 	s := newStore(t)
 	ctx := context.Background()
 	queued := startedUpload(t, s)
-	running, err := s.CreateUpload(ctx, userA, "r", false)
+	running, err := s.CreateUpload(ctx, userA, "r", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, running))
 

internal/adapters/store/uploaded_transcripts_progress_test.go

@@ -20,7 +20,7 @@ import (
 func startedUpload(t *testing.T, s *store.Store) string {
 	t.Helper()
 	seedUsers(t, userA, userB)
-	id, err := s.CreateUpload(context.Background(), userA, "m", false)
+	id, err := s.CreateUpload(context.Background(), userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 	return id
 }

internal/adapters/store/uploaded_transcripts_test.go

@@ -33,7 +33,7 @@ func TestCreateUpload_StartsQueuedAndIsOwnedByTheCreator(t *testing.T) {
 	seedUsers(t, userA)
 	ctx := context.Background()
 
-	id, err := s.CreateUpload(ctx, userA, "Teams export", false)
+	id, err := s.CreateUpload(ctx, userA, "Teams export", domain.LangSwedish, false)
 	require.NoError(t, err)
 
 	got, err := s.GetUpload(ctx, userA, id)
@@ -50,7 +50,7 @@ func TestUploadLifecycle_CompletedKeepsTextSegmentsEndpointAndDuration(t *testin
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "m", false)
+	id, err := s.CreateUpload(ctx, userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 
 	require.NoError(t, s.StartTranscribing(ctx, userA, id))
@@ -84,7 +84,7 @@ func TestUploadLifecycle_FailedRecordsTypedKindAndNoContent(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "m", false)
+	id, err := s.CreateUpload(ctx, userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, id))
 
@@ -102,7 +102,7 @@ func TestGetUpload_AnotherUsersIDIsNotFound(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA, userB)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "A's meeting", false)
+	id, err := s.CreateUpload(ctx, userA, "A's meeting", domain.LangSwedish, false)
 	require.NoError(t, err)
 
 	_, err = s.GetUpload(ctx, userB, id)
@@ -115,7 +115,7 @@ func TestUploadWrites_ByAnotherUserChangeNothing(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA, userB)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "A's meeting", false)
+	id, err := s.CreateUpload(ctx, userA, "A's meeting", domain.LangSwedish, false)
 	require.NoError(t, err)
 
 	assert.ErrorIs(t, s.StartTranscribing(ctx, userB, id), store.ErrUploadNotFound)
@@ -132,11 +132,11 @@ func TestListUploads_ReturnsOnlyTheCallersNewestFirstWithoutTranscriptText(t *te
 	s := newStore(t)
 	seedUsers(t, userA, userB)
 	ctx := context.Background()
-	first, err := s.CreateUpload(ctx, userA, "first", false)
+	first, err := s.CreateUpload(ctx, userA, "first", domain.LangSwedish, false)
 	require.NoError(t, err)
-	second, err := s.CreateUpload(ctx, userA, "second", false)
+	second, err := s.CreateUpload(ctx, userA, "second", domain.LangSwedish, false)
 	require.NoError(t, err)
-	_, err = s.CreateUpload(ctx, userB, "B's", false)
+	_, err = s.CreateUpload(ctx, userB, "B's", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, first))
 	require.NoError(t, s.CompleteUpload(ctx, userA, first, domain.Transcription{Text: "long text body", Endpoint: "e"}))
@@ -160,12 +160,12 @@ func TestFailInterruptedUploads_FailsOnlyUnfinishedRowsForEveryUser(t *testing.T
 		_, err := super.Exec(ctx, `INSERT INTO user_identities (dex_subject, user_id) VALUES ($1, $2)`, subject, uid)
 		require.NoError(t, err)
 	}
-	queued, err := s.CreateUpload(ctx, userA, "queued", false)
+	queued, err := s.CreateUpload(ctx, userA, "queued", domain.LangSwedish, false)
 	require.NoError(t, err)
-	running, err := s.CreateUpload(ctx, userB, "running", false)
+	running, err := s.CreateUpload(ctx, userB, "running", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userB, running))
-	done, err := s.CreateUpload(ctx, userA, "done", false)
+	done, err := s.CreateUpload(ctx, userA, "done", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, done))
 	require.NoError(t, s.CompleteUpload(ctx, userA, done, domain.Transcription{Text: "kept", Endpoint: "e"}))
@@ -191,9 +191,9 @@ func TestCreateUpload_RecordsWhetherTheFileHadAVideoTrack(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	withVideo, err := s.CreateUpload(ctx, userA, "camera off", true)
+	withVideo, err := s.CreateUpload(ctx, userA, "camera off", domain.LangSwedish, true)
 	require.NoError(t, err)
-	audioOnly, err := s.CreateUpload(ctx, userA, "voice only", false)
+	audioOnly, err := s.CreateUpload(ctx, userA, "voice only", domain.LangSwedish, false)
 	require.NoError(t, err)
 
 	gotVideo, err := s.GetUpload(ctx, userA, withVideo)
@@ -216,9 +216,9 @@ func TestUploadHadVideo_SurvivesCompletionAndFailure(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	done, err := s.CreateUpload(ctx, userA, "d", true)
+	done, err := s.CreateUpload(ctx, userA, "d", domain.LangSwedish, true)
 	require.NoError(t, err)
-	failed, err := s.CreateUpload(ctx, userA, "f", true)
+	failed, err := s.CreateUpload(ctx, userA, "f", domain.LangSwedish, true)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, done))
 	require.NoError(t, s.CompleteUpload(ctx, userA, done, domain.Transcription{Text: "x", Endpoint: "e"}))
@@ -235,7 +235,7 @@ func TestUploadLifecycle_ReconciliationRoundTripsWithItsContestedSpots(t *testin
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "m", false)
+	id, err := s.CreateUpload(ctx, userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, id))
 	want := &domain.Reconciliation{
@@ -258,7 +258,7 @@ func TestUploadLifecycle_ASingleEngineTranscriptHasNoReconciliation(t *testing.T
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "m", false)
+	id, err := s.CreateUpload(ctx, userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, id))
 	require.NoError(t, s.CompleteUpload(ctx, userA, id, domain.Transcription{Text: "x", Endpoint: "e"}))
@@ -273,7 +273,7 @@ func TestUploadLifecycle_ASkippedReconciliationKeepsItsReason(t *testing.T) {
 	s := newStore(t)
 	seedUsers(t, userA)
 	ctx := context.Background()
-	id, err := s.CreateUpload(ctx, userA, "m", false)
+	id, err := s.CreateUpload(ctx, userA, "m", domain.LangSwedish, false)
 	require.NoError(t, err)
 	require.NoError(t, s.StartTranscribing(ctx, userA, id))
 	rec := &domain.Reconciliation{Status: domain.ReconcileSkipped, Reason: "the model failed 3 times in a row: gateway down", Errors: 3}
@@ -284,3 +284,55 @@ func TestUploadLifecycle_ASkippedReconciliationKeepsItsReason(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, rec, got.Reconciliation)
 }
+
+func TestCreateUpload_RecordsTheLanguageTheUserChoseAndTheListCarriesIt(t *testing.T) {
+	s := newStore(t)
+	seedUsers(t, userA)
+	ctx := context.Background()
+	swedish, err := s.CreateUpload(ctx, userA, "sv", domain.LangSwedish, false)
+	require.NoError(t, err)
+	auto, err := s.CreateUpload(ctx, userA, "auto", domain.LangAuto, false)
+	require.NoError(t, err)
+
+	gotSv, err := s.GetUpload(ctx, userA, swedish)
+	require.NoError(t, err)
+	gotAuto, err := s.GetUpload(ctx, userA, auto)
+	require.NoError(t, err)
+	listed, err := s.ListUploads(ctx, userA)
+	require.NoError(t, err)
+
+	assert.Equal(t, domain.LangSwedish, gotSv.Language)
+	assert.Equal(t, domain.LangAuto, gotAuto.Language)
+	byID := map[string]domain.Language{}
+	for _, u := range listed {
+		byID[u.ID] = u.Language
+	}
+	assert.Equal(t, map[string]domain.Language{swedish: domain.LangSwedish, auto: domain.LangAuto}, byID)
+}
+
+// The closed set is also held by the table, so a bug or a second writer cannot store a
+// value the engines are never meant to receive (tapir#61).
+func TestUploadedTranscripts_TheTableRefusesALanguageOutsideTheClosedSet(t *testing.T) {
+	newStore(t)
+	seedUsers(t, userA)
+
+	_, err := rawPool(t).Exec(context.Background(),
+		`INSERT INTO uploaded_transcripts (user_id, title, language) VALUES ($1, 'x', 'en')`, userA)
+
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "language", "the CHECK constraint names the column")
+}
+
+// A row from before the column existed was transcribed as Swedish; the default says so.
+func TestUploadedTranscripts_ARowInsertedWithoutALanguageIsSwedish(t *testing.T) {
+	s := newStore(t)
+	seedUsers(t, userA)
+	var id string
+	require.NoError(t, rawPool(t).QueryRow(context.Background(),
+		`INSERT INTO uploaded_transcripts (user_id, title) VALUES ($1, 'old') RETURNING id`, userA).Scan(&id))
+
+	got, err := s.GetUpload(context.Background(), userA, id)
+
+	require.NoError(t, err)
+	assert.Equal(t, domain.LangSwedish, got.Language)
+}