feat: model-on-demand lifecycle — retry on 503, live status pill, warming indicator

- whisper.ts: add getModelStatus(); fix submitJob() to retry on 503 using
  Retry-After header instead of throwing; optional onModelWaiting callback
  lets the pipeline surface model state to the UI during the wait
- pipeline.ts: pass onModelWaiting callback → emits model_warming SSE event
  so the job detail page can show 'Warming up model…' while waiting
- types.ts: add ModelStateTag union and ModelStatus interface
- api/model/status: GET route proxies whisper /model/status (falls back to
  {state:'unloaded'} if whisper unreachable)
- api/model/events: GET route relays whisper SSE stream to the browser;
  AbortController tied to request.signal cleans up on disconnect
- layout.svelte: status pill is now live — initial fetch + EventSource on
  /api/model/events; dot colour + label reflect real model state with a
  pulsing animation while loading or waiting_for_gpu
- jobs/[id]/+page.svelte: handle model_warming event type → show a yellow
  'Warming up model…' sub-label with spinner inside the progress card
- whisper.test.ts: update submitJob mocks to status:202 to match real API

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Giancarmine Salucci
2026-05-09 00:08:21 +02:00
parent ffd5d48c0d
commit b90d57984c
8 changed files with 201 additions and 19 deletions

View File

@@ -31,6 +31,7 @@ describe('submitJob', () => {
it('POSTs to /jobs and returns job_id', async () => {
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'whisper-job-abc' })
});
const id = await submitJob('/tmp/audio.wav', 'http://host/api/webhook/job-1');
@@ -41,6 +42,7 @@ describe('submitJob', () => {
vi.stubEnv('WHISPER_URL', 'http://localhost:8091');
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'x' })
});
await submitJob('/tmp/audio.wav', 'http://host/api/webhook/job-1');
@@ -54,6 +56,7 @@ describe('submitJob', () => {
it('includes task=transcribe in the form', async () => {
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'x' })
});
await submitJob('/tmp/audio.wav', 'http://host/webhook');
@@ -63,6 +66,7 @@ describe('submitJob', () => {
it('includes webhook_url in the form', async () => {
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'x' })
});
await submitJob('/tmp/audio.wav', 'http://192.168.1.10:3000/api/webhook/job-99');
@@ -75,6 +79,7 @@ describe('submitJob', () => {
it('includes language when provided', async () => {
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'x' })
});
await submitJob('/tmp/audio.wav', 'http://host/webhook', 'en');
@@ -84,6 +89,7 @@ describe('submitJob', () => {
it('omits language field when not provided', async () => {
mocks.fetch.mockResolvedValue({
ok: true,
status: 202,
json: () => Promise.resolve({ job_id: 'x' })
});
await submitJob('/tmp/audio.wav', 'http://host/webhook');