tapir/internal/web/uploads_cloud_note_test.go

package web_test

// A transcript produced by the cloud fallback means this recording's audio left the
// homelab, which the reader is told in plain words (#52). "Local" is config.IsLocalModel:
// one definition, not a second string match in the view.

import (
	"context"
	"testing"

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

func setEndpoint(t *testing.T, id, endpoint string) {
	t.Helper()
	_, err := rawPool(t).Exec(context.Background(), `UPDATE uploaded_transcripts SET endpoint = $2 WHERE id = $1`, id, endpoint)
	require.NoError(t, err)
}

func TestUploadStatus_ACloudServedTranscriptSaysTheAudioLeftTheHomelab(t *testing.T) {
	app, _ := newUploadApp(t, audioOK, 200<<20)
	id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
	setEndpoint(t, id, "berget/kb-whisper")

	b := body(t, do(t, app, get("/uploads/"+id+"/status")))

	assert.Contains(t, b, "left the homelab")
	assert.Contains(t, b, "cloud service (berget)")
}

func TestUploadStatus_ALocallyServedTranscriptCarriesNoCloudNote(t *testing.T) {
	for _, endpoint := range []string{"iguana/kb-whisper", "koala/whisper", ""} {
		t.Run(endpoint, func(t *testing.T) {
			app, _ := newUploadApp(t, audioOK, 200<<20)
			id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
			setEndpoint(t, id, endpoint)

			b := body(t, do(t, app, get("/uploads/"+id+"/status")))

			assert.NotContains(t, b, "left the homelab")
		})
	}
}

func TestUploadStatus_AnEndpointThatOnlyLooksLocalIsStillNamedAsCloud(t *testing.T) {
	// The prefix alone must not decide it: IsLocalModel refuses path tricks.
	app, _ := newUploadApp(t, audioOK, 200<<20)
	id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
	setEndpoint(t, id, "iguana/../berget/kb-whisper")

	b := body(t, do(t, app, get("/uploads/"+id+"/status")))

	assert.Contains(t, b, "left the homelab")
}

// The two-engine path (ADR-034) writes one composite endpoint string. Every name in it is
// a local model, so the audio never left the homelab and the note must not say it did.
func TestUploadStatus_AReconciledAllLocalEndpointCarriesNoCloudNote(t *testing.T) {
	for _, endpoint := range []string{
		"iguana/kb-whisper + koala/whisper, reconciled by iguana/gemma4-26b",
		"iguana/kb-whisper + koala/whisper, reconciled by iguana/gemma4-26b\n",
	} {
		t.Run(endpoint, func(t *testing.T) {
			app, _ := newUploadApp(t, audioOK, 200<<20)
			id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
			setEndpoint(t, id, endpoint)

			b := body(t, do(t, app, get("/uploads/"+id+"/status")))

			assert.NotContains(t, b, "left the homelab")
		})
	}
}

func TestUploadStatus_AReconciledEndpointNamingACloudEngineStillNamesTheCloudProvider(t *testing.T) {
	app, _ := newUploadApp(t, audioOK, 200<<20)
	id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
	setEndpoint(t, id, "iguana/kb-whisper + berget/kb-whisper, reconciled by iguana/gemma4-26b")

	b := body(t, do(t, app, get("/uploads/"+id+"/status")))

	assert.Contains(t, b, "cloud service (berget)")
}

// An alias without a provider prefix is not a local model, wherever it sits in the
// composite: it must never be dropped from the judgement (PR #58 re-review).
func TestUploadStatus_AReconciledEndpointWithAnUnprefixedAliasIsNotCalledLocal(t *testing.T) {
	for _, endpoint := range []string{
		"iguana/kb-whisper + whisper-1, reconciled by iguana/gemma4-26b",
		"iguana/kb-whisper + whisper 1, reconciled by iguana/gemma4-26b",
		"iguana/kb-whisper + berget / x, reconciled by iguana/gemma4-26b",
	} {
		t.Run(endpoint, func(t *testing.T) {
			app, _ := newUploadApp(t, audioOK, 200<<20)
			id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
			setEndpoint(t, id, endpoint)

			b := body(t, do(t, app, get("/uploads/"+id+"/status")))

			assert.Contains(t, b, "left the homelab")
			assert.NotContains(t, b, "cloud service ()", "the note names a provider")
		})
	}
}

// "by", "reconciled" and "+" are connectors only inside the composite format. As a whole
// endpoint, or as an alias within the composite, they are model names and are judged.
func TestUploadStatus_AConnectorWordUsedAsAModelNameIsStillJudged(t *testing.T) {
	for _, endpoint := range []string{
		"by",
		"reconciled",
		"+",
		"iguana/kb-whisper + by, reconciled by iguana/gemma4-26b",
		"iguana/kb-whisper + reconciled, reconciled by iguana/gemma4-26b",
		"iguana/kb-whisper + +, reconciled by iguana/gemma4-26b",
		"/x", // no provider at all: the note must still name something
	} {
		t.Run(endpoint, func(t *testing.T) {
			app, _ := newUploadApp(t, audioOK, 200<<20)
			id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
			setEndpoint(t, id, endpoint)

			b := body(t, do(t, app, get("/uploads/"+id+"/status")))

			assert.Contains(t, b, "left the homelab")
			assert.NotContains(t, b, "cloud service ()")
		})
	}
}

func TestUploadStatus_AReconcilerThatIsNotLocalNamesTheCloudProvider(t *testing.T) {
	app, _ := newUploadApp(t, audioOK, 200<<20)
	id := seedUpload(t, userID, "m", "done", "Synthetic transcript text.")
	setEndpoint(t, id, "iguana/kb-whisper + koala/whisper, reconciled by berget/mistral-large")

	b := body(t, do(t, app, get("/uploads/"+id+"/status")))

	assert.Contains(t, b, "cloud service (berget)")
}