feat(uploads): an auto-language job is planned without the engines it never runs (#61)

PlanFor(lang) on the Ensemble and a LanguagePlanner the worker prefers: the page lists
the other engine (and the fallback if configured), not the base engine, the comparison and
the decisions as coming. Found by the PR #62 review.

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

internal/adapters/transcribe/ensemble.go

@@ -32,14 +32,24 @@ 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{
-		{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"},
+// 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 +160,22 @@ 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")
+}

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()))
+		})
+	}
+}