feat(files): raise the download cap to 2GB and stream /api/download

The 50MB cap on file-raw, the attachment /raw route and /api/download was
memory protection for a `readFile()` that no longer exists: file-raw and
/raw were rewritten to stream through `sendFileBody()` and answer Range
requests, so size costs a read stream rather than RSS (measured: a 600MB
download moved peak RSS by ~37MB). All the cap still did was refuse
legitimate downloads of build artifacts, videos and archives.

It is now MAX_FILE_DOWNLOAD_BYTES in config/buffer-limits.ts, default 2GB,
env CODEMAN_MAX_DOWNLOAD_BYTES, 0 = unlimited. `parseByteLimitEnv()` is
separate from the `parseInt(...) || default` idiom used elsewhere in that
file precisely because that idiom reads 0 as falsy and would silently
restore the default for the one value that means "no limit".

/api/download was the last route that really did buffer the whole file. It
now shares sendFileBody() with the other two, so it streams, advertises
Accept-Ranges, and is resumable. Its Content-Disposition also goes through
buildContentDisposition() rather than raw interpolation.

Refusals move from 400 to 413 across all three, which is the correct status
for the case; with the cap at 2GB it is a path almost nothing reaches now.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer
2026-09-10 02:57:07 +02:00
parent 5130ca6633
commit d4fe3afc9d
7 changed files with 118 additions and 54 deletions
+47
View File
@@ -112,3 +112,50 @@ export const FILE_PEEK_BYTES = 8 * 1024 - 1; // 8KB (inclusive end offset)
* Override: CODEMAN_MAX_PASTE_IMAGE_BYTES (bytes)
*/
export const MAX_PASTE_IMAGE_BYTES = parseInt(process.env.CODEMAN_MAX_PASTE_IMAGE_BYTES || '') || 50 * 1024 * 1024; // 50MB
// ============================================================================
// File Download Limits
// ============================================================================
/**
* Parse a byte-limit env var, where `0` explicitly means "no limit".
*
* The `parseInt(...) || default` idiom used elsewhere in this file cannot
* express that: it treats 0 as falsy and silently restores the default.
*/
function parseByteLimitEnv(raw: string | undefined, fallback: number): number {
if (raw === undefined || raw.trim() === '') return fallback;
const parsed = Number.parseInt(raw, 10);
if (!Number.isFinite(parsed) || parsed < 0) return fallback;
return parsed;
}
/**
* Maximum size (bytes) of a file served by the raw/download file routes:
* `GET /api/sessions/:id/file-raw` (the Files panel's download link and the
* file-preview overlay), the attachment `/raw` route, and `GET /api/download`.
*
* ⚠️ This is a sanity bound, NOT memory protection. All three bodies are
* STREAMED and `Range`-aware (`sendFileBody` in file-routes.ts), so a large
* file costs one read stream rather than its size in RSS. The historical 50MB
* cap predates that streaming rewrite and its "prevent memory exhaustion"
* comment described a `readFile()` that no longer exists — all it did was
* refuse legitimate downloads of build artifacts, videos and archives.
*
* Set `CODEMAN_MAX_DOWNLOAD_BYTES=0` to remove the cap entirely.
* Override: CODEMAN_MAX_DOWNLOAD_BYTES (bytes)
*/
export const MAX_FILE_DOWNLOAD_BYTES = parseByteLimitEnv(
process.env.CODEMAN_MAX_DOWNLOAD_BYTES,
2 * 1024 * 1024 * 1024 // 2GB
);
/** True when `size` exceeds the download cap (a cap of 0 means unlimited). */
export function exceedsDownloadLimit(size: number): boolean {
return MAX_FILE_DOWNLOAD_BYTES > 0 && size > MAX_FILE_DOWNLOAD_BYTES;
}
/** Human-readable "File too large (…)" message for a refused download. */
export function downloadTooLargeMessage(size: number): string {
return `File too large (${Math.round(size / 1024 / 1024)}MB > ${Math.round(MAX_FILE_DOWNLOAD_BYTES / 1024 / 1024)}MB limit). Raise or remove it with CODEMAN_MAX_DOWNLOAD_BYTES (0 = unlimited).`;
}
+16 -41
View File
@@ -50,6 +50,7 @@ import {
} from '../route-helpers.js';
import type { FastifyRequest } from 'fastify';
import type { SessionAttachmentHistoryItem, SessionState } from '../../types/session.js';
import { downloadTooLargeMessage, exceedsDownloadLimit } from '../../config/buffer-limits.js';
import { parseByteRange } from '../http-range.js';
import { isSensitivePath } from '../sensitive-path.js';
import { SseEvent } from '../sse-events.js';
@@ -183,16 +184,8 @@ async function serveRawFile(
rangeHeader?: string | string[]
): Promise<void> {
const stat = await fs.stat(resolvedPath);
const MAX_RAW_ATTACHMENT_SIZE = 50 * 1024 * 1024; // 50MB, matching file-raw / download
if (stat.size > MAX_RAW_ATTACHMENT_SIZE) {
reply
.code(413)
.send(
createErrorResponse(
ApiErrorCode.INVALID_INPUT,
`File too large (${Math.round(stat.size / 1024 / 1024)}MB > ${MAX_RAW_ATTACHMENT_SIZE / 1024 / 1024}MB limit)`
)
);
if (exceedsDownloadLimit(stat.size)) {
reply.code(413).send(createErrorResponse(ApiErrorCode.INVALID_INPUT, downloadTooLargeMessage(stat.size)));
return;
}
// Markup is download-only: served with a renderable type on our own origin it
@@ -1562,18 +1555,11 @@ export function registerFileRoutes(app: FastifyInstance, ctx: SessionPort & Even
const { resolvedPath } = validated;
try {
// Validate file size before reading (DoS protection - prevent memory exhaustion)
const MAX_RAW_FILE_SIZE = 50 * 1024 * 1024; // 50MB for raw files
// Sanity bound only: the body below is streamed and Range-aware, so size
// does not translate into resident memory. Configurable, 0 = unlimited.
const stat = await fs.stat(resolvedPath);
if (stat.size > MAX_RAW_FILE_SIZE) {
reply
.code(400)
.send(
createErrorResponse(
ApiErrorCode.INVALID_INPUT,
`File too large (${Math.round(stat.size / 1024 / 1024)}MB > ${MAX_RAW_FILE_SIZE / 1024 / 1024}MB limit)`
)
);
if (exceedsDownloadLimit(stat.size)) {
reply.code(413).send(createErrorResponse(ApiErrorCode.INVALID_INPUT, downloadTooLargeMessage(stat.size)));
return;
}
@@ -1954,17 +1940,8 @@ export function registerFileRoutes(app: FastifyInstance, ctx: SessionPort & Even
return;
}
// 50MB size limit
const MAX_DOWNLOAD_SIZE = 50 * 1024 * 1024;
if (stat.size > MAX_DOWNLOAD_SIZE) {
reply
.code(400)
.send(
createErrorResponse(
ApiErrorCode.INVALID_INPUT,
`File too large (${Math.round(stat.size / 1024 / 1024)}MB > 50MB limit)`
)
);
if (exceedsDownloadLimit(stat.size)) {
reply.code(413).send(createErrorResponse(ApiErrorCode.INVALID_INPUT, downloadTooLargeMessage(stat.size)));
return;
}
@@ -1988,15 +1965,13 @@ export function registerFileRoutes(app: FastifyInstance, ctx: SessionPort & Even
};
const filename = pathBasename(resolvedPath);
const content = await fs.readFile(resolvedPath);
// Bypass Fastify compression — write directly to raw response
reply.raw.writeHead(200, {
...inheritedHeaders(reply),
'Content-Type': mimeTypes[ext] || 'application/octet-stream',
'Content-Disposition': `attachment; filename="${filename}"`,
'Content-Length': content.length,
});
reply.raw.end(content);
// Streamed rather than read into memory, and Range-aware, so a multi-GB
// artifact costs one read stream and can be resumed. sendFileBody()
// hijacks the reply, which also keeps Fastify's compression out of it.
reply.header('Content-Type', mimeTypes[ext] || 'application/octet-stream');
reply.header('Content-Disposition', buildContentDisposition('attachment', filename));
reply.header('X-Content-Type-Options', 'nosniff');
sendFileBody(reply, resolvedPath, stat.size, req.headers.range);
return;
} catch (err) {
reply