BitSquare/Codeman
2
0
Fork 0
mirror of https://github.com/Ark0N/Codeman.git synced 2026-10-08 16:39:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(review): worker-thread HEIC conversion with bomb guard, concurrency cap, and magic-byte routing (PR #151)

Browse Source 
- Event-loop blockage: HEIC decode/encode (CPU-synchronous libheif WASM +
  jpeg-js) now runs in a per-conversion worker_threads Worker
  (src/web/heic-jpeg-worker.ts, spawned by heic-jpeg-converter.ts) with
  resourceLimits and a 30s hard timeout that terminates the worker —
  verified end-to-end under tsx and against compiled dist/ output with a
  real iPhone HEIC (event-loop max stall 52ms during conversion).
- No server-side concurrency cap: conversions now acquire a slot from the
  existing global runWithConversionLimit() pool (document-conversion-limiter),
  bounding peak decode memory/CPU across simultaneous uploads.
- Decompression bomb: header-declared dimensions are read via heic-decode's
  allocation-free `.all` path and rejected above 64MP BEFORE decode() can
  allocate width*height*4 bytes (a <300-byte crafted file can declare
  30000x30000 = 3.6GB). Regression-tested with a crafted ISOBMFF fixture
  against the real heic-decode WASM (test/heic-jpeg-core.test.ts).
- Mislabeled HEIC (documented Android/MIUI case): conversion now routes on
  ftyp magic-byte sniff of the raw buffer regardless of declared
  ext/Content-Type, so a HEIF uploaded as image/jpeg converts instead of
  415ing; the magic-mismatch 415 only fires for genuinely unrecognized bytes.
- Brand allowlist narrowed to what heic-decode's isHeic() accepts
  (heim/heis/hevm/hevs dropped — they could only ever fail conversion).
- Converted-output size: the JPEG result is checked against
  MAX_PASTE_IMAGE_BYTES (jpeg-js can inflate a within-limit HEIC past the cap).
- Deps: heic-convert replaced with its underlying heic-decode + jpeg-js
  (the wrapper could not expose the pre-decode dimension check); lockfile
  synced, drops pngjs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer
2026-07-12 18:06:59 +02:00
parent bb1d16e230
commit 309959be27
9 changed files with 428 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/web/routes/session-routes.ts
+21 -32
View File
@@ -54,6 +54,7 @@ import {
} from '../../hooks-config.js';
import { generateClaudeMd } from '../../templates/claude-md.js';
import { imageWatcher } from '../../image-watcher.js';
import { convertHeicToJpeg } from '../heic-jpeg-converter.js';
import { getLifecycleLog } from '../../session-lifecycle-log.js';
import type { SessionPort, EventPort, ConfigPort, InfraPort, AuthPort } from '../ports/index.js';
import { MAX_CONCURRENT_SESSIONS } from '../../config/map-limits.js';
@@ -191,30 +192,18 @@ export function imageMagicMatchesExt(data: Buffer, ext: string): boolean {
return data[0] === 0x42 && data[1] === 0x4d;
case '.heic':
case '.heif': {
// ISO Base Media File Format: size + "ftyp" + major brand.
// ISO Base Media File Format: size + "ftyp" + major brand. The brand
// list matches heic-decode's own isHeic() — accepting more brands here
// would only route bytes into a conversion that always throws.
if (u32be(4) !== 0x66747970) return false;
const brand = data.subarray(8, 12).toString('ascii');
return ['heic', 'heix', 'hevc', 'hevx', 'heim', 'heis', 'hevm', 'hevs', 'mif1', 'msf1'].includes(brand);
return ['heic', 'heix', 'hevc', 'hevx', 'mif1', 'msf1'].includes(brand);
}
default:
return false;
}
}
async function convertHeicToJpeg(imageBytes: Buffer): Promise<Buffer> {
const { default: convert } = await import('heic-convert');
const converted = await convert({ buffer: imageBytes, format: 'JPEG', quality: 0.92 });
const jpegBytes = Buffer.isBuffer(converted)
? converted
: converted instanceof ArrayBuffer
? Buffer.from(converted)
: Buffer.from(converted.buffer, converted.byteOffset, converted.byteLength);
if (!imageMagicMatchesExt(jpegBytes, '.jpg')) {
throw new Error('HEIC conversion did not produce JPEG bytes');
}
return jpegBytes;
}
// Per-(IP, sessionId) token bucket for paste-image. 30 requests/minute.
// Bucket map entries are pruned when they drift > 1h stale to bound memory
// against a flood of unique IP keys.
@@ -1889,22 +1878,12 @@ export function registerSessionRoutes(
);
}
// Sniff actual bytes — filename and Content-Type are both attacker-supplied.
// Polyglot HTML/PNG would otherwise pass and serve back with image/png MIME.
if (!imageMagicMatchesExt(imageBytes, ext)) {
// Diagnostic: on some Android galleries (e.g. MIUI) a WebP/HEIF is
// mislabeled as image/jpeg, so the declared ext passes the allowlist but
// the magic bytes do not. Log the real header so format mismatches can be
// pinned down without a reproduce-and-guess loop. The client now
// re-encodes images to JPEG/PNG before upload, so this should be rare.
console.warn(
`[paste-image] magic mismatch: filename=${JSON.stringify(part.filename)} mime=${JSON.stringify(part.mimetype)} declaredExt=${ext} magic=${imageBytes.subarray(0, 12).toString('hex')}`
);
reply.code(415);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, `Image bytes do not match declared type ${ext}`);
}
if (ext === '.heic' || ext === '.heif') {
// Route HEIC on the raw bytes, NOT the declared ext/mime: on some Android
// galleries (e.g. MIUI) a HEIF comes back mislabeled as image/jpeg, and
// browsers that cannot decode HEIF upload the original file as-is — so a
// HEIC payload can arrive under any declared type. Filename and
// Content-Type are attacker-supplied anyway; only the bytes are trusted.
if (imageMagicMatchesExt(imageBytes, '.heic')) {
try {
imageBytes = await convertHeicToJpeg(imageBytes);
ext = '.jpg';
@@ -1915,6 +1894,16 @@ export function registerSessionRoutes(
reply.code(415);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'Could not convert HEIC image to JPEG');
}
} else if (!imageMagicMatchesExt(imageBytes, ext)) {
// Sniff actual bytes — a polyglot HTML/PNG would otherwise pass and
// serve back with image/png MIME. Log the real header so format
// mismatches can be pinned down without a reproduce-and-guess loop. The
// client re-encodes images to JPEG/PNG before upload, so this is rare.
console.warn(
`[paste-image] magic mismatch: filename=${JSON.stringify(part.filename)} mime=${JSON.stringify(part.mimetype)} declaredExt=${ext} magic=${imageBytes.subarray(0, 12).toString('hex')}`
);
reply.code(415);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, `Image bytes do not match declared type ${ext}`);
}
// Save to {workingDir}/.claude-images/