Upload a recording (audio, or video with the camera off), get a private Swedish transcript, and chat about it. - ADR-033: RLS-scoped private transcript store; ffprobe/ffmpeg intake; gateway transcription (iguana kb-whisper, berget fallback); in-process single-replica worker; chat over the transcript (local models only). - ADR-034: optional two-engine mode (pianissimo + kb-whisper) reconciled by a LOCAL model; off unless TAPIR_RECONCILE_BASE_MODEL is set. - ADR-035: real progress (phases, running/quiet/lost), phase logging, every judged spot stored, merged segments. - Hardening from four adversarial reviews: errors logged and stored as kinds never text; per-engine deadlines; converted-length check; bounded queue; client hang-ups are not errors; strict local-alias check. - Dockerfile: static ffmpeg/ffprobe 7.0.2 pinned by sha256 (#34). Built and inspected by hand; CI does not build the image on a PR, so its first CI build is this merge. Uploads stay OFF until TAPIR_UPLOADS_ENABLED is set in the deployment. Closes #33, #34, #42, #43, #44. Co-authored-by: Mathias <mthbqv@gmail.com>
This commit was merged in pull request #39.
This commit is contained in:
@@ -0,0 +1,286 @@
|
||||
package store_test
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"git.d-ma.be/mathias/tapir/internal/adapters/store"
|
||||
"git.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
// These exercise the Store API over uploaded_transcripts. The test Store connects
|
||||
// as the superuser, which BYPASSES row-level security — so the cross-user cases
|
||||
// here prove the query's own user_id predicate (defence in depth), while the
|
||||
// database-enforced guarantee is proven separately, as the non-superuser app
|
||||
// role, in uploaded_transcripts_isolation_test.go. Text is synthetic; this repo is
|
||||
// public and no real transcript may appear in it (#33).
|
||||
|
||||
func seedUsers(t *testing.T, ids ...string) {
|
||||
t.Helper()
|
||||
super := rawPool(t)
|
||||
resetDB(t, super)
|
||||
for _, id := range ids {
|
||||
_, err := super.Exec(context.Background(), `INSERT INTO users (id) VALUES ($1)`, id)
|
||||
require.NoError(t, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestCreateUpload_StartsQueuedAndIsOwnedByTheCreator(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
|
||||
id, err := s.CreateUpload(ctx, userA, "Teams export", false)
|
||||
require.NoError(t, err)
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, id, got.ID)
|
||||
assert.Equal(t, userA, got.UserID)
|
||||
assert.Equal(t, "Teams export", got.Title)
|
||||
assert.Equal(t, domain.UploadQueued, got.Status)
|
||||
assert.Empty(t, got.Content)
|
||||
assert.True(t, got.FinishedAt.IsZero(), "an unfinished upload has no finish time")
|
||||
}
|
||||
|
||||
func TestUploadLifecycle_CompletedKeepsTextSegmentsEndpointAndDuration(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
id, err := s.CreateUpload(ctx, userA, "m", false)
|
||||
require.NoError(t, err)
|
||||
|
||||
require.NoError(t, s.StartTranscribing(ctx, userA, id))
|
||||
mid, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadTranscribing, mid.Status)
|
||||
|
||||
want := domain.Transcription{
|
||||
Text: "God morgon allihopa. Vi går igenom läget.",
|
||||
Segments: []domain.Segment{
|
||||
{Start: 0.0, End: 1.5, Text: "God morgon allihopa."},
|
||||
{Start: 1.5, End: 4.25, Text: "Vi går igenom läget."},
|
||||
},
|
||||
Endpoint: "iguana/kb-whisper",
|
||||
AudioSeconds: 4.25,
|
||||
}
|
||||
require.NoError(t, s.CompleteUpload(ctx, userA, id, want))
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadDone, got.Status)
|
||||
assert.Equal(t, want.Text, got.Content)
|
||||
assert.Equal(t, want.Segments, got.Segments, "segment times must survive the JSONB round trip")
|
||||
assert.Equal(t, "iguana/kb-whisper", got.Endpoint, "the serving endpoint is a quality fact and is recorded per row")
|
||||
assert.InDelta(t, 4.25, got.AudioSeconds, 1e-9)
|
||||
assert.False(t, got.FinishedAt.IsZero())
|
||||
assert.Empty(t, got.ErrorKind)
|
||||
}
|
||||
|
||||
func TestUploadLifecycle_FailedRecordsTypedKindAndNoContent(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
id, err := s.CreateUpload(ctx, userA, "m", false)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, s.StartTranscribing(ctx, userA, id))
|
||||
|
||||
require.NoError(t, s.FailUpload(ctx, userA, id, domain.UploadErrTranscriptionFailed))
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadFailed, got.Status)
|
||||
assert.Equal(t, domain.UploadErrTranscriptionFailed, got.ErrorKind)
|
||||
assert.Empty(t, got.Content)
|
||||
assert.False(t, got.FinishedAt.IsZero())
|
||||
}
|
||||
|
||||
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)
|
||||
require.NoError(t, err)
|
||||
|
||||
_, err = s.GetUpload(ctx, userB, id)
|
||||
|
||||
assert.ErrorIs(t, err, store.ErrUploadNotFound,
|
||||
"a non-owner must get not-found, not forbidden: existence is not disclosed")
|
||||
}
|
||||
|
||||
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)
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.ErrorIs(t, s.StartTranscribing(ctx, userB, id), store.ErrUploadNotFound)
|
||||
assert.ErrorIs(t, s.CompleteUpload(ctx, userB, id, domain.Transcription{Text: "planted"}), store.ErrUploadNotFound)
|
||||
assert.ErrorIs(t, s.FailUpload(ctx, userB, id, domain.UploadErrTranscriptionFailed), store.ErrUploadNotFound)
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadQueued, got.Status, "B's writes must leave A's upload exactly as it was")
|
||||
assert.Empty(t, got.Content)
|
||||
}
|
||||
|
||||
func TestListUploads_ReturnsOnlyTheCallersNewestFirstWithoutTranscriptText(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA, userB)
|
||||
ctx := context.Background()
|
||||
first, err := s.CreateUpload(ctx, userA, "first", false)
|
||||
require.NoError(t, err)
|
||||
second, err := s.CreateUpload(ctx, userA, "second", false)
|
||||
require.NoError(t, err)
|
||||
_, err = s.CreateUpload(ctx, userB, "B's", 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"}))
|
||||
|
||||
got, err := s.ListUploads(ctx, userA)
|
||||
|
||||
require.NoError(t, err)
|
||||
require.Len(t, got, 2, "A must see only A's uploads")
|
||||
assert.Equal(t, second, got[0].ID, "newest first")
|
||||
assert.Equal(t, first, got[1].ID)
|
||||
assert.Empty(t, got[1].Content, "a list row must not drag the whole transcript along")
|
||||
assert.Equal(t, domain.UploadDone, got[1].Status)
|
||||
}
|
||||
|
||||
func TestFailInterruptedUploads_FailsOnlyUnfinishedRowsForEveryUser(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA, userB)
|
||||
super := rawPool(t)
|
||||
ctx := context.Background()
|
||||
for subject, uid := range map[string]string{"sub-a": userA, "sub-b": userB} {
|
||||
_, 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)
|
||||
require.NoError(t, err)
|
||||
running, err := s.CreateUpload(ctx, userB, "running", false)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, s.StartTranscribing(ctx, userB, running))
|
||||
done, err := s.CreateUpload(ctx, userA, "done", 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"}))
|
||||
|
||||
n, err := s.FailInterruptedUploads(ctx)
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, 2, n, "the queued and the transcribing row, across both users")
|
||||
for _, c := range []struct{ user, id string }{{userA, queued}, {userB, running}} {
|
||||
got, err := s.GetUpload(ctx, c.user, c.id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadFailed, got.Status)
|
||||
assert.Equal(t, domain.UploadErrInterrupted, got.ErrorKind,
|
||||
"audio is not retained, so a restart cannot resume: the honest state is failed/interrupted")
|
||||
}
|
||||
kept, err := s.GetUpload(ctx, userA, done)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, domain.UploadDone, kept.Status, "a finished transcript must survive the sweep")
|
||||
assert.Equal(t, "kept", kept.Content)
|
||||
}
|
||||
|
||||
func TestCreateUpload_RecordsWhetherTheFileHadAVideoTrack(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
withVideo, err := s.CreateUpload(ctx, userA, "camera off", true)
|
||||
require.NoError(t, err)
|
||||
audioOnly, err := s.CreateUpload(ctx, userA, "voice only", false)
|
||||
require.NoError(t, err)
|
||||
|
||||
gotVideo, err := s.GetUpload(ctx, userA, withVideo)
|
||||
require.NoError(t, err)
|
||||
gotAudio, err := s.GetUpload(ctx, userA, audioOnly)
|
||||
require.NoError(t, err)
|
||||
listed, err := s.ListUploads(ctx, userA)
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.True(t, gotVideo.HadVideo, "the page must be able to say the video was ignored")
|
||||
assert.False(t, gotAudio.HadVideo)
|
||||
byID := map[string]bool{}
|
||||
for _, u := range listed {
|
||||
byID[u.ID] = u.HadVideo
|
||||
}
|
||||
assert.Equal(t, map[string]bool{withVideo: true, audioOnly: false}, byID, "the list carries it too")
|
||||
}
|
||||
|
||||
func TestUploadHadVideo_SurvivesCompletionAndFailure(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
done, err := s.CreateUpload(ctx, userA, "d", true)
|
||||
require.NoError(t, err)
|
||||
failed, err := s.CreateUpload(ctx, userA, "f", 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"}))
|
||||
require.NoError(t, s.FailUpload(ctx, userA, failed, domain.UploadErrTranscriptionFailed))
|
||||
|
||||
for _, id := range []string{done, failed} {
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.True(t, got.HadVideo, "completing or failing must not clear it: the notice outlives the job")
|
||||
}
|
||||
}
|
||||
|
||||
func TestUploadLifecycle_ReconciliationRoundTripsWithItsContestedSpots(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
id, err := s.CreateUpload(ctx, userA, "m", false)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, s.StartTranscribing(ctx, userA, id))
|
||||
want := &domain.Reconciliation{
|
||||
Status: domain.ReconcileDone, Base: "iguana/pianissimo", Alt: "iguana/kb-whisper", Reconciler: "iguana/gemma4-26b",
|
||||
Disputes: 380, AutoResolved: 90, Adjudicated: 285, Changed: 120, Unsure: 5, Errors: 0,
|
||||
Contested: []domain.ContestedSpot{
|
||||
{Seconds: 2210.5, Base: "Axel", Alt: "Alex", Used: "alt"},
|
||||
{Seconds: 3400, Base: "A+2", Alt: "en A", Used: "base", Unsure: true},
|
||||
},
|
||||
}
|
||||
|
||||
require.NoError(t, s.CompleteUpload(ctx, userA, id, domain.Transcription{Text: "x", Endpoint: "e", Reconciliation: want}))
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, want, got.Reconciliation)
|
||||
}
|
||||
|
||||
func TestUploadLifecycle_ASingleEngineTranscriptHasNoReconciliation(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
id, err := s.CreateUpload(ctx, userA, "m", 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"}))
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.Nil(t, got.Reconciliation, "no reconciliation is not an empty one: the page must not claim a second opinion")
|
||||
}
|
||||
|
||||
func TestUploadLifecycle_ASkippedReconciliationKeepsItsReason(t *testing.T) {
|
||||
s := newStore(t)
|
||||
seedUsers(t, userA)
|
||||
ctx := context.Background()
|
||||
id, err := s.CreateUpload(ctx, userA, "m", 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}
|
||||
|
||||
require.NoError(t, s.CompleteUpload(ctx, userA, id, domain.Transcription{Text: "x", Endpoint: "e", Reconciliation: rec}))
|
||||
|
||||
got, err := s.GetUpload(ctx, userA, id)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, rec, got.Reconciliation)
|
||||
}
|
||||
Reference in New Issue
Block a user