commit 49814eee56824921830960c7b0ca813b08e301d5
parent 051f308bcaea03c739f95c77d5118715c9c47b2d
Author: I Mean I'm Just Saying <imeanimjustsaying@kiwifarms.st>
Date: Fri, 19 Jun 2026 19:04:00 -0400
Fix retry-bucket prefilter skipping partials with an audio-check snapshot
destinationExists() decided a transcribe channel's video was "already
complete" via a hand-rolled `startsWith("audio.") && !endsWith(".part")`
check, which wrongly matched audio-integrity snapshots
(audio.<ext>.part.good/.part.testing), sidecars (audio.info.json,
audio.live_chat.json), and temp files. A genuine audio.<ext>.part sitting
next to a .part.good snapshot was prefiltered out ("Nothing to fetch")
even though the partial-downloads bucket — which uses isRealAudioFile —
correctly excludes those same files.
Reuse isRealAudioFile in destinationExists so the prefilter and the bucket
agree. Add a regression e2e test that seeds a .part.good snapshot beside
the .part and asserts the partial is kept (verified it fails without the
fix).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Diffstat:
3 files changed, 45 insertions(+), 4 deletions(-)
diff --git a/common/ytdlp/runYtdlp.ts b/common/ytdlp/runYtdlp.ts
@@ -13,6 +13,7 @@ import { getSettings } from "../lib/settings";
import { checkDiskSpace } from "../lib/diskSpace";
import { formatBytes } from "../lib/format";
import { detectPlatform } from "../lib/platform";
+import { isRealAudioFile } from "../lib/videoStatus";
import type { Paths } from "../lib/paths";
import {
EXCLUDED_FROM_DOWNLOAD,
@@ -878,11 +879,13 @@ export async function destinationExists(
}
// Transcribe channels treat raw audio as a download in progress so we don't
// re-fetch it before whisper runs. YouTube channels expect a .vtt; an audio
- // file alone shouldn't suppress the next sync.
+ // file alone shouldn't suppress the next sync. Use isRealAudioFile (the same
+ // predicate the partial-downloads bucket uses) so audio-check snapshots
+ // (audio.<ext>.part.good/.part.testing), sidecars (audio.info.json,
+ // audio.live_chat.json), and temp files don't get mistaken for finished audio
+ // — otherwise a genuine partial carrying a .part.good snapshot is skipped.
if (handling === "transcribe") {
- return entries.some(
- (e) => e.startsWith("audio.") && !e.endsWith(".part"),
- );
+ return entries.some(isRealAudioFile);
}
return false;
}
diff --git a/editor/CHANGELOG.md b/editor/CHANGELOG.md
@@ -1,6 +1,7 @@
# Changelog
## [Unreleased]
+- **"Retry partial downloads" no longer skips partials that carry an audio-check snapshot.** A transcribe channel's retry-bucket prefilter decided a video was "already complete" by looking for any `audio.*` file not ending in `.part` — which wrongly matched the audio-integrity snapshots (`audio.<ext>.part.good` / `.part.testing`) and sidecars (`audio.info.json`, `audio.live_chat.json`, `audio.*.tmp-*`) left in a partial video's dir. So a genuine `audio.<ext>.part` that happened to sit next to a `.part.good` snapshot got prefiltered out (`Prefilter: 0 missing destination files, N already complete` → `Nothing to fetch`), even though that same snapshot is excluded when the video is placed in the **Partial downloads** bucket. The prefilter (`destinationExists`) now reuses the same `isRealAudioFile` predicate the bucket uses, so the two agree and genuine partials resume. See `common/ytdlp/runYtdlp.ts` and `common/lib/videoStatus.ts`.
- **One-click "Drain all" to spin work down before a server restart.** The `/jobs/active` header gained a **Drain all** button that, in a single confirmed action, **drains every running job** (lets in-flight sub-operations finish, starts no new ones) and **cancels every queued job** — so you can wind the queue down gracefully before restarting the server instead of draining/cancelling each job row by hand. It reuses the existing per-job drain path (`requestDrain` drains running jobs and cancels queued ones), so semantics match the per-row **Drain**/**Cancel** buttons exactly; non-drainable running kinds are marked draining and finish on their own. A confirm prompt guards the bulk action. See `editor/app/jobs/components/DrainAllButton.tsx` and `drainAllAction` in `editor/app/jobs/actions.ts`.
- **Queued jobs now have a Cancel button right on the row.** On `/jobs/active`, a queued (not-yet-started) job previously offered no inline way to cancel it — you had to expand its log to find a control. Each active row now shows a **Cancel** button directly (queued *and* running), so you can drop a queued job without opening anything. The running-only **Drain** button is unchanged. See `editor/app/jobs/components/RunningJobsList.tsx`.
- **The Bookmarks panel is now a compact one-click run menu, with management moved to its own page.** The bookmarks block atop `/jobs` and `/jobs/active` used to render a heavy multi-row card per bookmark — inline rename, tags, created/last-run metadata, a confirm-gated delete, and a full streaming **Run again** button that popped a tall inline log box on every run — which buried the live job list below it. It's now a tight **wrap of quick-access buttons**, one per bookmark, labeled with the bookmark's name (the full kind/bucket/channel shows on hover). Clicking a button **launches the job fire-and-forget** — no inline shell, no expanding log — and the relaunched job simply appears in the live list below (it runs to completion server-side whether or not the page watches its stream); the button briefly reads *Launching… → Launched ✓*, an empty re-derived bucket still reads as a neutral *"Nothing to retry right now"* line, and a bookmark whose channel was deleted is disabled with a *channel missing* hint. The heavier controls — rename, delete, created/last-run metadata, and the full streaming **Run again** with its inline log — move to a new **`/jobs/bookmarks`** management page, reachable via the **Manage** link in the menu header. See `editor/app/jobs/components/BookmarksMenu.tsx`, `editor/app/jobs/components/BookmarkRunButton.tsx`, and `editor/app/jobs/bookmarks/page.tsx`.
diff --git a/editor/e2e/partial-downloads-bucket.spec.ts b/editor/e2e/partial-downloads-bucket.spec.ts
@@ -64,3 +64,40 @@ test("resume action re-downloads the partial video", async ({ page }) => {
await pathExists(`${CHANNEL_ROOT}/data/vidA/audio.m4a`),
).toBe(true);
});
+
+test("resume retries a partial that carries an audio-check snapshot", async ({
+ page,
+}) => {
+ // Regression: a genuine audio.<ext>.part alongside an audio-check snapshot
+ // (audio.<ext>.part.good) used to be prefiltered out as "already complete"
+ // because destinationExists() matched any audio.* not ending in .part. The
+ // prefilter must agree with the bucket and keep the partial.
+ test.setTimeout(60_000);
+ await resetData("one-transcribe-channel-with-audio");
+ await rename(
+ resolvePath(`${CHANNEL_ROOT}/data/vidA/audio.m4a`),
+ resolvePath(`${CHANNEL_ROOT}/data/vidA/audio.m4a.part`),
+ );
+ // The leftover audio-check snapshot that previously fooled the prefilter.
+ await writeFile(
+ resolvePath(`${CHANNEL_ROOT}/data/vidA/audio.m4a.part.good`),
+ "snapshot\n",
+ );
+ await writeFile(
+ resolvePath(`${CHANNEL_ROOT}/playlist`),
+ "https://www.youtube.com/watch?v=vidA\n",
+ );
+
+ await page.goto(`/channels/${CHANNEL}`);
+
+ await page
+ .getByLabel("retry resume partial downloads bucket")
+ .getByRole("button", { name: /^Retry \(1\)$/ })
+ .click();
+
+ const log = page.getByLabel("Retry resume partial downloads output");
+ await expect(log).toContainText("Prefilter: 1 missing destination files", {
+ timeout: 30_000,
+ });
+ await expect(log).not.toContainText("Nothing to fetch.");
+});
