mathias
4a2067063d
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>
97 lines
3.3 KiB
Go
97 lines
3.3 KiB
Go
package uploads_test
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"git.d-ma.be/mathias/tapir/internal/domain"
|
|
"git.d-ma.be/mathias/tapir/internal/uploads"
|
|
)
|
|
|
|
// A full queue is the user's to retry, not a server fault: a typed rejection, the row
|
|
// failed honestly, the audio removed (adversarial review F6).
|
|
|
|
func TestAccept_AFullQueueIsABusyRejectionNotAServerErrorAndLeavesNothingBehind(t *testing.T) {
|
|
r := newRig(t)
|
|
r.sub.err = uploads.ErrQueueFull
|
|
|
|
_, err := r.in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
|
|
|
|
var rej *uploads.RejectError
|
|
require.True(t, errors.As(err, &rej), "a full queue must be a rejection the web layer can answer with 429: %v", err)
|
|
assert.Equal(t, uploads.ReasonBusy, rej.Reason)
|
|
assert.Contains(t, rej.Message, "waiting")
|
|
assert.Equal(t, domain.UploadErrBusy, r.st.failed["up-1"], "the row must not sit queued: that is the stuck spinner")
|
|
assert.Empty(t, r.tmpFiles(t), "the audio is deleted")
|
|
}
|
|
|
|
// roomSubmitter is a Submitter that can say, before anything is spooled, that there is no room.
|
|
type roomSubmitter struct {
|
|
fakeSubmitter
|
|
room bool
|
|
}
|
|
|
|
func (r *roomSubmitter) HasRoom(string) bool { return r.room }
|
|
|
|
func TestAccept_ANoRoomQueueIsRefusedBeforeAnythingIsSpooledProbedOrStored(t *testing.T) {
|
|
// Checking only at Submit meant 200 MB was spooled and ffprobe run for every refused
|
|
// attempt, and a failed row was left behind each time (second adversarial review).
|
|
r := newRig(t)
|
|
full := &roomSubmitter{room: false}
|
|
in := uploads.NewIntake(r.st, r.pr, full, uploads.Limits{MaxBytes: 1024, MaxDuration: 90 * time.Minute}, r.tmp)
|
|
|
|
_, err := in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
|
|
|
|
var rej *uploads.RejectError
|
|
require.True(t, errors.As(err, &rej))
|
|
assert.Equal(t, uploads.ReasonBusy, rej.Reason)
|
|
assert.Empty(t, r.st.created, "no row for an upload that was never accepted")
|
|
assert.Empty(t, r.pr.paths, "ffprobe was never run on it")
|
|
assert.Empty(t, r.tmpFiles(t), "nothing was spooled")
|
|
assert.Empty(t, full.jobs)
|
|
}
|
|
|
|
func TestAccept_ASubmitterThatCannotSayStillWorksAsBefore(t *testing.T) {
|
|
r := newRig(t)
|
|
|
|
_, err := r.in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
|
|
|
|
require.NoError(t, err, "a Submitter without HasRoom is accepted: the check at Submit remains")
|
|
}
|
|
|
|
// brokenBody is a client body that fails mid-read, like a connection that dropped.
|
|
type brokenBody struct{ n int }
|
|
|
|
func (b *brokenBody) Read(p []byte) (int, error) {
|
|
if b.n > 0 {
|
|
b.n = 0
|
|
return copy(p, "partial audio"), nil
|
|
}
|
|
return 0, io.ErrUnexpectedEOF
|
|
}
|
|
|
|
func TestAccept_AnErrorReadingTheClientsBodyIsMarkedAsTheClientsAndAWrappedSubmitErrorIsNot(t *testing.T) {
|
|
r := newRig(t)
|
|
|
|
_, err := r.in.Accept(context.Background(), "user-1", "t", &brokenBody{n: 1})
|
|
|
|
require.Error(t, err)
|
|
assert.ErrorIs(t, err, uploads.ErrClientRead, "a dropped client body is the sender's to retry")
|
|
assert.Empty(t, r.tmpFiles(t))
|
|
|
|
// A fault that is ours must NOT carry the marker, even if it wraps the same sentinel.
|
|
r2 := newRig(t)
|
|
r2.sub.err = fmt.Errorf("db: %w", io.ErrUnexpectedEOF)
|
|
_, err = r2.in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
|
|
require.Error(t, err)
|
|
assert.NotErrorIs(t, err, uploads.ErrClientRead)
|
|
}
|