package uploads import ( "context" "errors" "fmt" "log/slog" "os" "sync" "time" "git.d-ma.be/mathias/tapir/internal/domain" "git.d-ma.be/mathias/tapir/internal/progress" ) // ErrStopped is returned by Submit once the worker has stopped. var ErrStopped = errors.New("uploads: worker stopped") // Converter turns the uploaded file into the 16 kHz mono PCM WAV whisper wants. type Converter interface { ToWAV(ctx context.Context, src, dst string) error } // Transcriber turns a WAV into a timed transcription. The gateway chain // (iguana primary, berget fallback) implements it. type Transcriber interface { Transcribe(ctx context.Context, wavPath string) (domain.Transcription, error) } // 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 // declares it reports itself, through progress.From(ctx) (ADR-035). type Planner interface { Plan() []progress.Planned } // WorkerStore is the slice of the private transcript store the worker drives. type WorkerStore interface { StartTranscribing(ctx context.Context, userID, id string) error CompleteUpload(ctx context.Context, userID, id string, t domain.Transcription) error FailUpload(ctx context.Context, userID, id string, kind domain.UploadErrorKind) error SaveProgress(ctx context.Context, userID, id string, steps []domain.ProgressStep, at time.Time) error Heartbeat(ctx context.Context, userID, id string) error } // WorkerOption tunes a Worker. type WorkerOption func(*Worker) // WithHeartbeat sets how often a running job stamps its row alive and how often it logs // which phase is still running. The defaults are 10 s and 5 min (ADR-035). func WithHeartbeat(beat, still time.Duration) WorkerOption { return func(w *Worker) { w.beatEvery, w.stillEvery = beat, still } } // WithLogger replaces slog.Default() as the worker's logger. func WithLogger(l *slog.Logger) WorkerOption { return func(w *Worker) { w.log = l } } const ( defaultBeatEvery = 10 * time.Second defaultStillEvery = 5 * time.Minute ) // jobSink binds the store to one job so a progress.Tracker can persist through it. type jobSink struct { st WorkerStore userID, id string } func (s jobSink) SaveProgress(ctx context.Context, steps []domain.ProgressStep, at time.Time) error { return s.st.SaveProgress(ctx, s.userID, s.id, steps, at) } func (s jobSink) Beat(ctx context.Context) error { return s.st.Heartbeat(ctx, s.userID, s.id) } // Worker transcribes accepted uploads in-process, ONE AT A TIME (ADR-033). It is // not a second deployable: it shares the web process's lifetime, which is why it // inherits ADR-018's single-replica assumption — the queue is process-local. The // concurrency of one is deliberate: two simultaneous 90-minute jobs on iguana were // never measured, and a Metal OOM there latches the whisper backend (infra#273). type Worker struct { store WorkerStore conv Converter tr Transcriber tmpDir string timeout time.Duration log *slog.Logger beatEvery, stillEvery time.Duration mu sync.Mutex queue []Job stopped bool wake chan struct{} } // NewWorker wires a Worker. timeout bounds each job (conversion + transcription); // a job that outlives it is failed rather than left spinning. func NewWorker(s WorkerStore, c Converter, t Transcriber, tmpDir string, timeout time.Duration, opts ...WorkerOption) *Worker { w := &Worker{ store: s, conv: c, tr: t, tmpDir: tmpDir, timeout: timeout, wake: make(chan struct{}, 1), beatEvery: defaultBeatEvery, stillEvery: defaultStillEvery, } for _, o := range opts { o(w) } return w } // Submit queues a job. It never blocks. It satisfies Submitter. func (w *Worker) Submit(j Job) error { w.mu.Lock() defer w.mu.Unlock() if w.stopped { return ErrStopped } w.queue = append(w.queue, j) select { case w.wake <- struct{}{}: default: } return nil } // Run processes queued jobs until ctx ends, then deletes the audio of anything // still queued and refuses new jobs. The rows of those jobs stay queued or // transcribing and are failed as interrupted by the start-up sweep // (store.FailInterruptedUploads): the audio is not retained, so they cannot resume. func (w *Worker) Run(ctx context.Context) { defer w.stop() for { job, ok := w.next(ctx) if !ok { return } w.Process(ctx, job) } } // next blocks for the next job. Cancellation wins over a non-empty queue: a job // still queued at shutdown must not be STARTED (it would begin a long conversion // with an already-cancelled context); stop() deletes its audio instead. func (w *Worker) next(ctx context.Context) (Job, bool) { for { if ctx.Err() != nil { return Job{}, false } w.mu.Lock() if len(w.queue) > 0 { j := w.queue[0] w.queue = w.queue[1:] w.mu.Unlock() return j, true } w.mu.Unlock() select { case <-w.wake: case <-ctx.Done(): return Job{}, false } } } func (w *Worker) stop() { w.mu.Lock() defer w.mu.Unlock() w.stopped = true for _, j := range w.queue { _ = os.Remove(j.Path) } w.queue = nil } // Process runs one job: row -> transcribing, convert, transcribe, store. The // uploaded file and the converted WAV are deleted on every path — the audio is // never retained (ADR-033). A failure is recorded with a TYPED kind; a shutdown // mid-job is not a failure and leaves the row for the start-up sweep. // // Every phase is reported through one progress.Tracker, which saves it to the row for // the page and logs it, and a heartbeat stamps the row on its own while the job runs // (ADR-035). Nothing logged or saved here carries transcript text or the file's name. func (w *Worker) Process(ctx context.Context, job Job) { defer func() { _ = os.Remove(job.Path) }() base := w.log if base == nil { base = slog.Default() } log := base.With("upload", job.UploadID) start := time.Now() if err := w.store.StartTranscribing(ctx, job.UserID, job.UploadID); err != nil { log.Error("upload: start transcribing", "err", err) w.fail(ctx, job, log) return } plan := []progress.Planned{{Key: "received", Label: "Received"}, {Key: "audio", Label: "Preparing the audio"}} planner, planned := w.tr.(Planner) if planned { plan = append(plan, planner.Plan()...) } else { plan = append(plan, progress.Planned{Key: "transcribe", Label: "Transcribing"}) } plan = append(plan, progress.Planned{Key: "save", Label: "Saving the transcript"}) tr := progress.NewTracker(ctx, jobSink{st: w.store, userID: job.UserID, id: job.UploadID}, log, plan) tr.Start() tr.Begin("received", 0) tr.Done("received") hbCtx, stopBeat := context.WithCancel(ctx) hbDone := make(chan struct{}) go func() { defer close(hbDone) tr.Heartbeat(hbCtx, w.beatEvery, w.stillEvery) }() defer func() { stopBeat(); <-hbDone }() // no heartbeat outlives its job // abort records where the job stopped. A shutdown (the parent context ended) is not // a failure: the row is left for the start-up sweep, so the step stays as it was. abort := func() { if ctx.Err() == nil { tr.Fail() } w.fail(ctx, job, log) } wav, err := w.tempWAV() if err != nil { log.Error("upload: temp wav", "err", err) abort() return } defer func() { _ = os.Remove(wav) }() jobCtx, cancel := context.WithTimeout(ctx, w.timeout) defer cancel() tr.Begin("audio", 0) if err := w.conv.ToWAV(jobCtx, job.Path, wav); err != nil { log.Error("upload: convert", "err", err) abort() return } tr.Done("audio") if !planned { tr.Begin("transcribe", 0) } t, err := w.tr.Transcribe(progress.With(jobCtx, tr), wav) if err != nil { log.Error("upload: transcribe", "err", err, "elapsed", time.Since(start).Round(time.Second)) abort() return } if !planned { tr.Done("transcribe") } tr.Begin("save", 0) if err := w.store.CompleteUpload(ctx, job.UserID, job.UploadID, t); err != nil { log.Error("upload: store transcript", "err", err) abort() return } tr.Done("save") tr.Finish() log.Info("upload transcribed", "endpoint", t.Endpoint, "audio_s", t.AudioSeconds, "segments", len(t.Segments), "elapsed", time.Since(start).Round(time.Second)) } // fail records a transcription failure — unless the PARENT context ended, which // is a shutdown, not a failure: the row is left for the start-up sweep. func (w *Worker) fail(ctx context.Context, job Job, log *slog.Logger) { if ctx.Err() != nil { return } if err := w.store.FailUpload(ctx, job.UserID, job.UploadID, domain.UploadErrTranscriptionFailed); err != nil { log.Error("upload: record failure", "err", err) } } func (w *Worker) tempWAV() (string, error) { f, err := os.CreateTemp(w.tmpDir, "wav-*") if err != nil { return "", fmt.Errorf("uploads: temp wav: %w", err) } name := f.Name() if err := f.Close(); err != nil { _ = os.Remove(name) return "", fmt.Errorf("uploads: temp wav: %w", err) } return name, nil }