officerdev/platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

stop caching transcriptions and OCR

Browse Source 
Both endpoints kept a copy under cache/ and returned it on the next call, and
also short-circuited when the sibling .md already existed. So a re-run never
re-ran: a bad transcription stayed bad, and there was no way to ask for a fresh
one. Every caller passes saveNextTo, so the cache-path return was dead code
anyway.

Both now always do the work and overwrite the sibling. CACHE_PREFIXES drops the
two prefixes, since /save-result has nothing left to promote for them; the tts
and audio caches are untouched.

Also fixes the task runner output being unreadable in light mode. The panel is a
fixed dark terminal, but stdout lines were classed text-foreground, which follows
the app theme and renders black on the dark background. They now inherit the
pre's own colour.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
brunorezio
2026-07-26 03:23:30 +01:00
co-authored by Claude Opus 5
parent 1263a4f851
commit d6b4b900ff
2 changed files with 9 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/servers/api/file-browser/router.ts
+5 -55
View File
@@ -602,7 +602,7 @@ router.get('/probe-folder', async (ctx) => {
});
// Save a cached result (ocr/tts/transcriptions/audio) next to the original file
const CACHE_PREFIXES = ['cache/ocr/', 'cache/tts/', 'cache/transcriptions/', 'cache/audio/'];
const CACHE_PREFIXES = ['cache/tts/', 'cache/audio/'];
router.post('/save-result', async (ctx) => {
const user = ctx.get('user');
@@ -775,31 +775,8 @@ router.post('/ocr', async (ctx) => {
const s = await stat(absPath);
if (s.isDirectory()) throw errors.BAD_REQUEST('Cannot OCR a directory');
const userDataDir = getUserDataDir(user.email);
// No caching: OCR is always run fresh and overwrites any previous result.
const { dir, name } = parsePath(filePath.replace(/^\/+/, ''));
const cacheRel = dir ? `cache/ocr/${dir}/${name}.md` : `cache/ocr/${name}.md`;
const cacheAbs = resolve(userDataDir, cacheRel);
// When saving next to file, check if the sibling .md already exists
if (saveNextTo) {
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
if (existsSync(siblingAbs)) {
return ctx.json({ ocrPath: `/${siblingRel}`, ocrRoot: root ?? 'home', cached: true });
}
}
if (existsSync(cacheAbs)) {
if (saveNextTo) {
const text = await readFile(cacheAbs, 'utf-8');
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
await Bun.write(siblingAbs, text);
return ctx.json({ ocrPath: `/${siblingRel}`, ocrRoot: root ?? 'home', cached: true });
}
const text = await readFile(cacheAbs, 'utf-8');
return ctx.json({ text, ocrPath: cacheRel, ocrRoot: 'user-data', cached: true });
}
const ocrConfig = await readOcrConfig();
if (!ocrConfig) throw errors.BAD_REQUEST('OCR not configured — set it up in Settings → OCR');
@@ -851,9 +828,6 @@ router.post('/ocr', async (ctx) => {
const json = (await res.json()) as { choices: { message: { content: string } }[] };
const text = json.choices[0]?.message?.content ?? '';
await mkdir(dirname(cacheAbs), { recursive: true });
await Bun.write(cacheAbs, text);
if (saveNextTo) {
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
@@ -861,7 +835,7 @@ router.post('/ocr', async (ctx) => {
return ctx.json({ ocrPath: `/${siblingRel}`, ocrRoot: root ?? 'home', cached: false });
}
return ctx.json({ text, ocrPath: cacheRel, ocrRoot: 'user-data', cached: false });
return ctx.json({ text, cached: false });
});
// Extract audio from video via ffmpeg with caching
@@ -999,29 +973,8 @@ router.post('/transcribe', async (ctx) => {
const s = await stat(absPath);
if (s.isDirectory()) throw errors.BAD_REQUEST('Cannot transcribe a directory');
const userDataDir = getUserDataDir(user.email);
// No caching: a transcription is always produced fresh and overwrites any previous one.
const { dir, name } = parsePath(filePath.replace(/^\/+/, ''));
const cacheRel = dir ? `cache/transcriptions/${dir}/${name}.md` : `cache/transcriptions/${name}.md`;
const cacheAbs = resolve(userDataDir, cacheRel);
if (saveNextTo) {
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
if (existsSync(siblingAbs)) {
return ctx.json({ transcriptionPath: `/${siblingRel}`, transcriptionRoot: root ?? 'home', cached: true });
}
}
if (existsSync(cacheAbs)) {
if (saveNextTo) {
const text = await readFile(cacheAbs, 'utf-8');
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
await Bun.write(siblingAbs, text);
return ctx.json({ transcriptionPath: `/${siblingRel}`, transcriptionRoot: root ?? 'home', cached: true });
}
return ctx.json({ transcriptionPath: cacheRel, transcriptionRoot: 'user-data', cached: true });
}
const sttConfig = await readSttConfig();
const whisperUrl = sttConfig?.url;
@@ -1038,9 +991,6 @@ router.post('/transcribe', async (ctx) => {
throw errors.BAD_REQUEST(err instanceof Error ? err.message : 'Transcription failed');
}
await mkdir(dirname(cacheAbs), { recursive: true });
await Bun.write(cacheAbs, text);
if (saveNextTo) {
const siblingRel = dir ? `${dir}/${name}.md` : `${name}.md`;
const siblingAbs = resolveUserPath(rootDir, siblingRel);
@@ -1048,7 +998,7 @@ router.post('/transcribe', async (ctx) => {
return ctx.json({ transcriptionPath: `/${siblingRel}`, transcriptionRoot: root ?? 'home', cached: false });
}
return ctx.json({ transcriptionPath: cacheRel, transcriptionRoot: 'user-data', cached: false });
return ctx.json({ text, cached: false });
});
// Search files by name