test(transcribe): the wrapper does not restart a cancelled job; PlanFor of an empty or unknown language is pinned (#61)

Low findings of the PR #62 re-review: the WithTimeout test's comment claimed cancellation
travels on the context but only the language was asserted (the WithoutCancel mutant survived),
and PlanFor('') and PlanFor(unknown) were untested.

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

docs/use-cases/audio_upload.feature

@@ -289,4 +289,5 @@ Feature: Upload an audio recording, get a private Swedish transcript, discuss it
 
   Scenario: A recording in another language never reaches the Swedish-only engine
     When I choose Other for a recording
-    Then the language is left for the engine to detect and no Swedish-only engine or reconcile is used
+    Then the language is left for the engine to detect and the Swedish-only base engine and the reconcile are not used
+    And the engine that does run is the configured one, which is not tuned for other languages

internal/adapters/transcribe/ensemble.go

@@ -32,15 +32,25 @@ func NewEnsemble(base, alt, fallback Backend, adj reconcile.Adjudicator, opts re
 	return &Ensemble{base: base, alt: alt, fallback: fallback, adj: adj, opts: opts}
 }
 
-// Plan implements uploads.Planner: the phases this ensemble reports, so the page can
-// show them before they run. The fallback is a phase only when one is configured.
-func (e *Ensemble) Plan() []progress.Planned {
-	plan := []progress.Planned{
+// Plan implements uploads.Planner: the phases of a Swedish job, the two-engine one. The
+// fallback is a phase only when one is configured.
+func (e *Ensemble) Plan() []progress.Planned { return e.PlanFor(domain.LangSwedish) }
+
+// PlanFor implements uploads.LanguagePlanner. A recording that is not Swedish never runs the
+// base engine, the comparison or the decisions (transcribeOther), so the page lists only
+// what can run: the other engine, then the fallback if one is configured.
+func (e *Ensemble) PlanFor(lang domain.Language) []progress.Planned {
+	var plan []progress.Planned
+	if lang == domain.LangSwedish || lang == "" {
+		plan = []progress.Planned{
 			{Key: "engine_a", Label: "Transcribing with " + e.base.Name()},
 			{Key: "engine_b", Label: "Transcribing with " + e.alt.Name()},
 			{Key: "compare", Label: "Comparing the two transcripts"},
 			{Key: "decide", Label: "Deciding the differences"},
 		}
+	} else {
+		plan = []progress.Planned{{Key: "engine_b", Label: "Transcribing with " + e.alt.Name()}}
+	}
 	if e.fallback != nil {
 		plan = append(plan, progress.Planned{Key: "fallback", Label: "Cloud fallback (" + e.fallback.Name() + ")"})
 	}

internal/adapters/transcribe/ensemble_progress_test.go

@@ -160,3 +160,25 @@ func TestEnsembleProgress_TheReconcileCountsAreNotedForTheOperator(t *testing.T)
 	assert.Equal(t, 0, n["unsure"])
 	assert.Equal(t, 0, n["errors"])
 }
+
+// An auto-language upload never runs the base engine, the comparison or the decisions, so the
+// page must not list them as coming (tapir#61, PR #62 review).
+func TestEnsemblePlanFor_AnAutoLanguageListsOnlyThePhasesThatCanRun(t *testing.T) {
+	with := newEnsemble("a", "a", nil, nil, true, &verdictAdj{}).e
+	without := newEnsemble("a", "a", nil, nil, false, &verdictAdj{}).e
+	keys := func(p []progress.Planned) []string {
+		var k []string
+		for _, s := range p {
+			k = append(k, s.Key)
+		}
+		return k
+	}
+
+	assert.Equal(t, []string{"engine_b", "fallback"}, keys(with.PlanFor(domain.LangAuto)))
+	assert.Equal(t, []string{"engine_b"}, keys(without.PlanFor(domain.LangAuto)), "no fallback configured: none promised")
+	assert.Equal(t, with.Plan(), with.PlanFor(domain.LangSwedish), "Swedish is the plan it always was")
+	assert.Contains(t, with.PlanFor(domain.LangAuto)[0].Label, "iguana/kb-whisper")
+	assert.Equal(t, with.Plan(), with.PlanFor(""), "a job queued before the choice existed is Swedish")
+	assert.Equal(t, with.PlanFor(domain.LangAuto), with.PlanFor(domain.Language("xx")),
+		"an unknown language is planned as it is run: not the Swedish phases")
+}

internal/adapters/transcribe/timeout_test.go

@@ -102,3 +102,45 @@ func TestEnsemble_AHungEngineIsASoftFailureAndTheOtherEnginesTextIsUsed(t *testi
 	assert.Contains(t, got.Reconciliation.Reason, "timeout")
 	assert.False(t, errors.Is(err, context.DeadlineExceeded))
 }
+
+// WithTimeout sits in front of both local engines in production (cmd/tapir/uploads.go). It
+// must hand the engine the job's context, not a fresh one: the language and the
+// cancellation both travel on it (tapir#61).
+
+func TestWithTimeout_TheEngineStillReceivesTheLanguageOfTheJob(t *testing.T) {
+	for name, tt := range map[string]struct {
+		ctx       context.Context
+		wantField bool
+	}{
+		"auto leaves the field out": {domain.WithLanguage(context.Background(), domain.LangAuto), false},
+		"swedish sends sv":          {domain.WithLanguage(context.Background(), domain.LangSwedish), true},
+	} {
+		t.Run(name, func(t *testing.T) {
+			var got seen
+			srv := serve(t, 200, verboseJSON, &got)
+			b := transcribe.WithTimeout(transcribe.NewGateway(srv.URL+"/v1", "k", "iguana/kb-whisper", srv.Client()), time.Minute)
+
+			_, err := b.Transcribe(tt.ctx, wavFile(t, "RIFF-synthetic-pcm"))
+
+			require.NoError(t, err)
+			lang, present := got.fields["language"]
+			assert.Equal(t, tt.wantField, present)
+			if tt.wantField {
+				assert.Equal(t, "sv", lang)
+			}
+		})
+	}
+}
+
+func TestWithTimeout_ACancelledJobIsNotRestartedByTheWrapper(t *testing.T) {
+	var got seen
+	srv := serve(t, 200, verboseJSON, &got)
+	b := transcribe.WithTimeout(transcribe.NewGateway(srv.URL+"/v1", "k", "iguana/kb-whisper", srv.Client()), time.Minute)
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	_, err := b.Transcribe(ctx, wavFile(t, "RIFF-synthetic-pcm"))
+
+	require.Error(t, err)
+	assert.Empty(t, got.method, "a cancelled job must not send its audio anywhere through the wrapper")
+}

internal/uploads/worker.go

@@ -33,6 +33,13 @@ type Transcriber interface {
 	Transcribe(ctx context.Context, wavPath string) (domain.Transcription, error)
 }
 
+// LanguagePlanner is a Planner whose phases depend on the language of the job: a recording
+// that is not Swedish skips the second engine and the reconcile, and the page should not list
+// them as coming (tapir#61). The worker prefers it over Planner.
+type LanguagePlanner interface {
+	PlanFor(lang domain.Language) []progress.Planned
+}
+
 // Planner is an optional extra on a Transcriber: it declares its own phases (for
 // example one per engine) so the page can show them. A Transcriber that does not
 // implement it gets a single "transcribing" phase from the worker. Whatever a Planner
@@ -251,8 +258,14 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 	}
 
 	plan := []progress.Planned{{Key: "received", Label: "Received"}, {Key: "audio", Label: "Preparing the audio"}}
+	lang := job.Language
+	if lang == "" {
+		lang = domain.LangSwedish // queued before the choice existed
+	}
 	planner, planned := w.tr.(Planner)
-	if planned {
+	if lp, ok := w.tr.(LanguagePlanner); ok {
+		plan = append(plan, lp.PlanFor(lang)...)
+	} else if planned {
 		plan = append(plan, planner.Plan()...)
 	} else {
 		plan = append(plan, progress.Planned{Key: "transcribe", Label: "Transcribing"})
@@ -313,7 +326,7 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 	if !planned {
 		tr.Begin("transcribe", 0)
 	}
-	t, err := w.tr.Transcribe(domain.WithLanguage(progress.With(jobCtx, tr), job.Language), wav)
+	t, err := w.tr.Transcribe(domain.WithLanguage(progress.With(jobCtx, tr), lang), wav)
 	if err != nil {
 		log.Error("upload: transcribe", "kind", errkind.Of(err), "elapsed", time.Since(start).Round(time.Second))
 		abort(domain.UploadErrTranscriptionFailed)

internal/uploads/worker_progress_test.go

@@ -213,3 +213,47 @@ func TestWorkerProgress_AStoreFailureLogsItsSQLStateNeverTheValueItQuotes(t *tes
 	assert.Contains(t, out, "upload: store transcript")
 	assert.Contains(t, out, "kind=sql_22P02")
 }
+
+// langPlannedTr plans per language, like the Ensemble: an auto job has no base engine.
+type langPlannedTr struct{ *fakeTranscriber }
+
+func (langPlannedTr) Plan() []progress.Planned { return plannedTr{}.Plan() }
+func (langPlannedTr) PlanFor(l domain.Language) []progress.Planned {
+	if l == domain.LangAuto {
+		return []progress.Planned{{Key: "engine_b", Label: "Transcribing with B"}}
+	}
+	return plannedTr{}.Plan()
+}
+
+func (p langPlannedTr) Transcribe(ctx context.Context, wav string) (domain.Transcription, error) {
+	r := progress.From(ctx)
+	if domain.LanguageFrom(ctx) != domain.LangAuto {
+		r.Begin("engine_a", 0)
+		r.Done("engine_a")
+	}
+	r.Begin("engine_b", 0)
+	r.Done("engine_b")
+	return p.fakeTranscriber.Transcribe(ctx, wav)
+}
+
+func TestWorkerProgress_AJobGetsThePlanOfItsLanguage(t *testing.T) {
+	for name, tt := range map[string]struct {
+		lang domain.Language
+		want []string
+	}{
+		"auto":    {domain.LangAuto, []string{"received:done", "audio:done", "engine_b:done", "save:done"}},
+		"swedish": {domain.LangSwedish, []string{"received:done", "audio:done", "engine_a:done", "engine_b:done", "save:done"}},
+		"no language (queued before the choice existed)": {"", []string{"received:done", "audio:done", "engine_a:done", "engine_b:done", "save:done"}},
+	} {
+		t.Run(name, func(t *testing.T) {
+			r := newWRig(t, time.Minute)
+			w := newProgressWorker(t, r, langPlannedTr{r.tr})
+			job := r.spool(t, "a")
+			job.Language = tt.lang
+
+			w.Process(context.Background(), job)
+
+			assert.Equal(t, tt.want, keysAndStates(r.st.lastSteps()))
+		})
+	}
+}

internal/web/uploads.templ

@@ -57,6 +57,7 @@ templ UploadPage(u domain.UploadedTranscript, chatEnabled bool, now time.Time) {
 	@Layout("Tapir — " + u.Title) {
 		<article class="account">
 			<h1>{ u.Title }</h1>
+			<p class="muted">Language: { languageLabel(u.Language) }</p>
 			@uploadStatus(u, chatEnabled, now)
 			<p><a href="/uploads">All recordings</a></p>
 		</article>
@@ -74,7 +75,6 @@ templ uploadStatus(u domain.UploadedTranscript, chatEnabled bool, now time.Time)
 					Transcribed { uploads.FormatDuration(time.Duration(u.AudioSeconds * float64(time.Second))) }
 					of audio by <span class="chip">{ u.Endpoint }</span>.
 				</p>
-				<p>Language: { languageLabel(u.Language) }</p>
 				if provider, cloud := cloudProvider(u.Endpoint); cloud {
 					<p class="cloud-note">
 						This recording's audio left the homelab: it was transcribed by a cloud service ({ provider })

internal/web/uploads_language_handler_test.go

@@ -109,7 +109,7 @@ func TestUploadPost_ALanguageOutsideTheClosedSetIsRefusedBeforeAnythingIsSpooled
 			rows, err := newStore(t).ListUploads(context.Background(), userID)
 			require.NoError(t, err)
 			assert.Empty(t, rows, "and must leave no row")
-			assert.Contains(t, body(t, rec), "language")
+			assert.Contains(t, body(t, rec), "Choose a language from the list.")
 		})
 	}
 }
@@ -127,7 +127,8 @@ func TestUploadPage_TheFormOffersSwedishPreselectedAndOtherBeforeTheFilePart(t *
 	assert.Contains(t, b, `<option value="auto"`)
 }
 
-func TestUploadStatus_NamesTheLanguageTheRecordingWasTranscribedAs(t *testing.T) {
+func TestUploadPage_NamesTheLanguageInEveryState(t *testing.T) {
+	for _, status := range []string{"queued", "transcribing", "done", "failed"} {
 		for _, tt := range []struct {
 			language domain.Language
 			want     string
@@ -135,15 +136,16 @@ func TestUploadStatus_NamesTheLanguageTheRecordingWasTranscribedAs(t *testing.T)
 			{domain.LangSwedish, "Swedish"},
 			{domain.LangAuto, "Other (detected by the engine)"},
 		} {
-		t.Run(string(tt.language), func(t *testing.T) {
+			t.Run(status+"/"+string(tt.language), func(t *testing.T) {
 				app, _ := newUploadApp(t, audioOK, 200<<20)
-			id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
+				id := seedUpload(t, userID, "m", status, "Synthetic transcript text.")
 				_, err := rawPool(t).Exec(context.Background(), `UPDATE uploaded_transcripts SET language = $2 WHERE id = $1`, id, string(tt.language))
 				require.NoError(t, err)
 
-			b := body(t, do(t, app, get("/uploads/"+id+"/status")))
+				b := body(t, do(t, app, get("/uploads/"+id)))
 
 				assert.Contains(t, b, "Language: "+tt.want)
 			})
 		}
 	}
+}

internal/web/uploads_templ.go

@@ -222,7 +222,20 @@ func UploadPage(u domain.UploadedTranscript, chatEnabled bool, now time.Time) te
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "</h1>")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 15, "</h1><p class=\"muted\">Language: ")
+			if templ_7745c5c3_Err != nil {
+				return templ_7745c5c3_Err
+			}
+			var templ_7745c5c3_Var12 string
+			templ_7745c5c3_Var12, templ_7745c5c3_Err = templ.JoinStringErrs(languageLabel(u.Language))
+			if templ_7745c5c3_Err != nil {
+				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 60, Col: 57}
+			}
+			_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var12))
+			if templ_7745c5c3_Err != nil {
+				return templ_7745c5c3_Err
+			}
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "</p>")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
@@ -230,7 +243,7 @@ func UploadPage(u domain.UploadedTranscript, chatEnabled bool, now time.Time) te
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 16, "<p><a href=\"/uploads\">All recordings</a></p></article>")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 17, "<p><a href=\"/uploads\">All recordings</a></p></article>")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
@@ -262,14 +275,14 @@ func uploadStatus(u domain.UploadedTranscript, chatEnabled bool, now time.Time)
 			}()
 		}
 		ctx = templ.InitializeContext(ctx)
-		templ_7745c5c3_Var12 := templ.GetChildren(ctx)
-		if templ_7745c5c3_Var12 == nil {
-			templ_7745c5c3_Var12 = templ.NopComponent
+		templ_7745c5c3_Var13 := templ.GetChildren(ctx)
+		if templ_7745c5c3_Var13 == nil {
+			templ_7745c5c3_Var13 = templ.NopComponent
 		}
 		ctx = templ.ClearChildren(ctx)
 		switch u.Status {
 		case domain.UploadDone:
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 17, "<div class=\"upload-status upload-done\" role=\"status\">")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 18, "<div class=\"upload-status upload-done\" role=\"status\">")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
@@ -277,46 +290,33 @@ func uploadStatus(u domain.UploadedTranscript, chatEnabled bool, now time.Time)
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 18, "<p>Transcribed ")
-			if templ_7745c5c3_Err != nil {
-				return templ_7745c5c3_Err
-			}
-			var templ_7745c5c3_Var13 string
-			templ_7745c5c3_Var13, templ_7745c5c3_Err = templ.JoinStringErrs(uploads.FormatDuration(time.Duration(u.AudioSeconds * float64(time.Second))))
-			if templ_7745c5c3_Err != nil {
-				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 74, Col: 95}
-			}
-			_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var13))
-			if templ_7745c5c3_Err != nil {
-				return templ_7745c5c3_Err
-			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 19, " of audio by <span class=\"chip\">")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 19, "<p>Transcribed ")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
 			var templ_7745c5c3_Var14 string
-			templ_7745c5c3_Var14, templ_7745c5c3_Err = templ.JoinStringErrs(u.Endpoint)
+			templ_7745c5c3_Var14, templ_7745c5c3_Err = templ.JoinStringErrs(uploads.FormatDuration(time.Duration(u.AudioSeconds * float64(time.Second))))
 			if templ_7745c5c3_Err != nil {
-				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 75, Col: 48}
+				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 75, Col: 95}
 			}
 			_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var14))
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 20, "</span>.</p><p>Language: ")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 20, " of audio by <span class=\"chip\">")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
 			var templ_7745c5c3_Var15 string
-			templ_7745c5c3_Var15, templ_7745c5c3_Err = templ.JoinStringErrs(languageLabel(u.Language))
+			templ_7745c5c3_Var15, templ_7745c5c3_Err = templ.JoinStringErrs(u.Endpoint)
 			if templ_7745c5c3_Err != nil {
-				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 77, Col: 44}
+				return templ.Error{Err: templ_7745c5c3_Err, FileName: `internal/web/uploads.templ`, Line: 76, Col: 48}
 			}
 			_, templ_7745c5c3_Err = templ_7745c5c3_Buffer.WriteString(templ.EscapeString(templ_7745c5c3_Var15))
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}
-			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 21, "</p>")
+			templ_7745c5c3_Err = templruntime.WriteString(templ_7745c5c3_Buffer, 21, "</span>.</p>")
 			if templ_7745c5c3_Err != nil {
 				return templ_7745c5c3_Err
 			}