Files
tonemark/src/routes/api/model/events/+server.ts
Giancarmine Salucci b90d57984c 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>
2026-05-09 00:08:21 +02:00

44 lines
1.1 KiB
TypeScript

const WHISPER_URL = process.env.WHISPER_URL ?? 'http://localhost:8080';
/** Relay the whisper /model/events SSE stream to the browser. */
export async function GET({ request }) {
const { default: fetch } = await import('node-fetch');
const ac = new AbortController();
request.signal.addEventListener('abort', () => ac.abort());
const stream = new ReadableStream({
async start(controller) {
try {
const upstream = await fetch(`${WHISPER_URL}/model/events`, {
signal: ac.signal as AbortSignal
});
if (!upstream.body) {
controller.close();
return;
}
for await (const chunk of upstream.body) {
if (ac.signal.aborted) break;
controller.enqueue(chunk instanceof Buffer ? chunk : Buffer.from(String(chunk)));
}
} catch {
// upstream closed, client disconnected, or whisper unreachable — all fine
} finally {
controller.close();
}
},
cancel() {
ac.abort();
}
});
return new Response(stream, {
headers: {
'Content-Type': 'text/event-stream',
'Cache-Control': 'no-cache',
Connection: 'keep-alive',
'X-Accel-Buffering': 'no'
}
});
}