feat: whisper-side cancellation + SSE-triggered retry
All checks were successful
Build & Push Docker Image / build-and-push (push) Successful in 48s

- Add cancelJob() to whisper.ts: sends DELETE /jobs/:id to the whisper
  server (best-effort, errors silently ignored)
- DELETE /api/jobs/[id] now calls cancelJob() when cancelling an active
  job that has a whisperJobId, stopping GPU use immediately
- Webhook handler guards against locally-cancelled jobs: returns ok early
  so whisper's late completion cannot overwrite cancelled status or send
  a phantom 'Transcript ready' notification
- Replace blind sleep(Retry-After + 1s) in submitJob() with
  waitForModelReady(): subscribes to /model/events SSE and proceeds as
  soon as state:ready arrives; falls back to the Retry-After timeout if
  SSE is unreachable or closes without model_ready
- Refactor retry tests to use URL-aware makeJobFetch() helper; add 7 new
  tests (3 SSE-triggered retry, 3 cancelJob, 1 webhook cancelled-guard)
  — 144/144 passing

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Giancarmine Salucci
2026-05-09 00:40:40 +02:00
parent 01845bec25
commit 04142b17a8
5 changed files with 267 additions and 73 deletions

View File

@@ -4,8 +4,6 @@ function whisperUrl() {
return process.env.WHISPER_URL ?? 'http://localhost:8080';
}
const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));
/** Get the current model state from whisper-rtx2080. */
export async function getModelStatus(): Promise<ModelStatus> {
const { default: fetch } = await import('node-fetch');
@@ -16,11 +14,69 @@ export async function getModelStatus(): Promise<ModelStatus> {
return res.json() as Promise<ModelStatus>;
}
/**
* Wait for the whisper model to become ready.
*
* Subscribes to /model/events SSE and resolves as soon as a payload with
* state:"ready" arrives. Falls back to a plain timeout (`timeoutMs`) if the
* SSE connection fails or closes without that event, so the retry loop can
* try again without hanging indefinitely.
*/
async function waitForModelReady(timeoutMs: number): Promise<void> {
const { default: fetch } = await import('node-fetch');
const ac = new AbortController();
return new Promise((resolve) => {
let done = false;
const finish = () => {
if (!done) {
done = true;
ac.abort();
resolve();
}
};
const timer = setTimeout(finish, timeoutMs);
fetch(`${whisperUrl()}/model/events`, { signal: ac.signal as AbortSignal })
.then(async (res) => {
if (!res.body) {
clearTimeout(timer);
return finish();
}
let buf = '';
for await (const chunk of res.body) {
if (ac.signal.aborted) break;
buf += chunk.toString();
const lines = buf.split('\n');
buf = lines.pop() ?? '';
for (const line of lines) {
if (!line.startsWith('data:')) continue;
try {
const payload = JSON.parse(line.slice(5).trim());
if (payload.state === 'ready') {
clearTimeout(timer);
finish();
return;
}
} catch { /* ignore parse errors */ }
}
}
// Stream ended without model_ready → proceed to retry immediately
clearTimeout(timer);
finish();
})
.catch(() => {
// SSE unreachable — fallback timer will fire eventually
});
});
}
/**
* Submit an audio file to whisper-rtx2080. Returns the whisper job id.
*
* Handles 503 (model not ready) transparently: retries using the
* `Retry-After` header until the model loads or maxAttempts is exhausted.
* Handles 503 (model not ready) transparently: retries after subscribing to
* /model/events SSE — proceeds as soon as state:"ready" arrives, or after the
* Retry-After timeout elapses (whichever comes first).
* Calls `onModelWaiting` on each 503 so the caller can surface the wait to the user.
*/
export async function submitJob(
@@ -60,7 +116,7 @@ export async function submitJob(
const state = body.state ?? 'unloaded';
const waitSecs = body.retry_after_secs ?? parseInt(res.headers.get('Retry-After') ?? '15');
onModelWaiting?.(state, waitSecs);
await sleep((waitSecs + 1) * 1000);
await waitForModelReady((waitSecs + 1) * 1000);
continue;
}
@@ -71,6 +127,20 @@ export async function submitJob(
throw new Error(`Whisper model did not become ready after ${maxAttempts} attempts`);
}
/**
* Cancel a queued or running job on the whisper server (best-effort).
* Errors are silently ignored — local job status is already set to cancelled.
*/
export async function cancelJob(whisperJobId: string): Promise<void> {
try {
const { default: fetch } = await import('node-fetch');
await fetch(`${whisperUrl()}/jobs/${whisperJobId}`, {
method: 'DELETE',
signal: AbortSignal.timeout(5000)
});
} catch { /* best-effort */ }
}
/** Open an SSE stream from whisper and call onProgress/onDone callbacks. */
export async function streamJob(
whisperJobId: string,