feat(uploads): write prompt uploads to a hidden, self-ignoring .codeman-uploads/ folder

A pasted image landed in <workspace>/.claude-images/, a name that belongs to another tool, in a folder nothing ignored, so it showed up in git status of every case that ever received a paste. Uploads now go to a flat <workspace>/.codeman-uploads/ that carries a .gitignore of `*` (written once, never over a file already there): in the workspace because that is the only path identical for a local agent and a container, flat because a nested .codeman/ is the data dir itself when the workspace is the home directory.

The directory names live in paste-image-gc.ts alone. The old folder receives nothing but stays readable for one release: the hourly sweep and the delete cleanup go through uploadDirs(), the image watcher's ignore filter reads the names. uploadDirs() lists only real directories, none that is, contains or sits inside the data dir, and nothing for a remote session, since both consumers delete. The route refuses a remote (SSH) session before touching disk: the file would land on this host under the remote path, where the agent cannot read it.

test/paste-image-dir-shared.test.ts binds port 0 and leaves the port guard's legacy list.

Decided in #553.
This commit is contained in:
JD committed 2026-10-09 14:10:54 -04:00
1 parent 3a0cee6b90
commit f12b5ac88b
17 files changed
+459 -100

No files matched your search

+83 -31
View File
@@ -1,25 +1,76 @@
/**
* @fileoverview Periodic GC for paste-image files.
* @fileoverview Periodic GC for prompt-upload files, and the one place that
* names the directories they live in.
*
* Without cleanup, /api/sessions/:id/paste-image accumulates files indefinitely
* under {workingDir}/.claude-images/. The route only triggers cleanup on
* under {workingDir}/.codeman-uploads/. The route only triggers cleanup on
* killMux=true session deletion, so long-lived sessions can fill disk under
* heavy pasting. This sweeper bounds disk use by deleting `paste-*` files
* older than MAX_AGE_MS from each live session's image dir on an interval.
* older than MAX_AGE_MS from each live session's upload dirs on an interval.
*
* Conservative defaults — only files matching the `paste-` prefix are
* considered, and we lstat (not stat) so a planted symlink cannot escape the
* image dir.
* upload dir.
*/
import fs from 'node:fs/promises';
import { realpathSync } from 'node:fs';
import { join, resolve } from 'node:path';
import { lstatSync, realpathSync } from 'node:fs';
import { join, resolve, sep } from 'node:path';
import { getDataDir } from '../config/instance.js';
import type { SessionPort } from './ports/index.js';
const MAX_AGE_MS = 7 * 24 * 60 * 60 * 1000; // 7 days
const SWEEP_INTERVAL_MS = 60 * 60 * 1000; // 1 hour
const INITIAL_DELAY_MS = 30 * 1000; // 30s after startup
/**
* Where a prompt upload is written, relative to the session's working
* directory. IN the workspace, because that is the only path that resolves
* identically for a local agent and a container (only the workspace is
* bind-mounted, at the same absolute path); hidden, so it stays out of
* `git status` and the agent's view of the repository; FLAT, because a nested
* `<workspace>/.codeman/` is Codeman's own data dir when the workspace is the
* home directory; and self-ignoring, through a `.gitignore` of `*` the route
* writes once.
*/
export const UPLOADS_DIR = '.codeman-uploads';
/** Where uploads landed before the move: written to by nothing, readable for one release. */
export const LEGACY_UPLOADS_DIR = '.claude-images';
/** Every upload dir name, current first. Retiring the legacy one here retires it for every reader. */
export const UPLOAD_DIR_NAMES = [UPLOADS_DIR, LEGACY_UPLOADS_DIR];
/**
* Every directory a session's uploads sit in, current first. Both consumers
* act on what this returns, the hourly sweep and the recursive delete in
* cleanupSession(), so it lists only REAL directories (a link planted by a
* workspace script, `.codeman-uploads -> /other-case/.codeman-uploads`, is
* not one; readdir follows a link to a directory), none that is, contains or
* sits inside this instance's data dir (a home workspace reaches it under a
* contrived instance name, `CODEMAN_INSTANCE=uploads`, and `CODEMAN_DATA_DIR`
* can point inside one), and nothing for a remote (SSH) session, whose
* workingDir is the remote path and would name a same-named LOCAL directory
* here. The check is made when listing: a same-user process that swaps a
* listed directory for a link afterwards is accepted, since it already writes
* anywhere this process can.
*/
export function uploadDirs(session: { workingDir: string; remote?: unknown }): string[] {
if (session.remote) return [];
const dataDir = canonicalDir(getDataDir());
return UPLOAD_DIR_NAMES.map((name) => join(session.workingDir, name)).filter((dir) => {
if (!isRealDir(dir)) return false;
const real = canonicalDir(dir);
return real !== dataDir && !real.startsWith(dataDir + sep) && !dataDir.startsWith(real + sep);
});
}
/** lstat, so a symlink is not a directory, whatever it points at. */
function isRealDir(p: string): boolean {
try {
return lstatSync(p).isDirectory();
} catch {
return false;
}
}
export async function sweepPasteImagesOnce(
ctx: Pick<SessionPort, 'sessions'>,
now: number = Date.now()
@@ -28,26 +79,27 @@ export async function sweepPasteImagesOnce(
let scanned = 0;
let deleted = 0;
for (const session of ctx.sessions.values()) {
const dir = join(session.workingDir, '.claude-images');
let entries: string[];
try {
entries = await fs.readdir(dir);
} catch {
continue; // dir absent — nothing to do
}
for (const name of entries) {
if (!name.startsWith('paste-')) continue;
const p = join(dir, name);
scanned += 1;
for (const dir of uploadDirs(session)) {
let entries: string[];
try {
const st = await fs.lstat(p);
if (!st.isFile()) continue;
if (st.mtimeMs < cutoff) {
await fs.unlink(p);
deleted += 1;
}
entries = await fs.readdir(dir);
} catch {
// best-effort: skip permission/race errors silently
continue; // gone since listed — nothing to do
}
for (const name of entries) {
if (!name.startsWith('paste-')) continue;
const p = join(dir, name);
scanned += 1;
try {
const st = await fs.lstat(p);
if (!st.isFile()) continue;
if (st.mtimeMs < cutoff) {
await fs.unlink(p);
deleted += 1;
}
} catch {
// best-effort: skip permission/race errors silently
}
}
}
}
@@ -55,7 +107,7 @@ export async function sweepPasteImagesOnce(
}
/**
* The path two sessions must share to share a paste-image dir: the canonical
* The path two sessions must share to share an upload dir: the canonical
* path when it can be resolved, so a sibling that reaches the same directory
* through a symlink matches, and the normalised path otherwise (a directory
* that no longer exists has nothing left to protect).
@@ -68,7 +120,7 @@ function canonicalDir(dir: string): string {
}
}
/** One session the paste-image guard weighs: its id, directory and, for a persisted record, its status. */
/** One session the upload-dir guard weighs: its id, directory and, for a persisted record, its status. */
export interface PasteImageDirUser {
id: string;
workingDir: string;
@@ -76,11 +128,11 @@ export interface PasteImageDirUser {
}
/**
* Does another live session still use this working directory's paste-image
* dir? Deleting a session removes `{workingDir}/.claude-images` recursively,
* and several sessions routinely share one case directory, so without this
* check closing one session deletes the pasted images a sibling in the same
* case still refers to.
* Does another live session still use this working directory's upload dirs?
* Deleting a session removes them (`uploadDirs()`) recursively, and several
* sessions routinely share one case directory, so without this check closing
* one session deletes the pasted images a sibling in the same case still
* refers to.
*
* Two kinds of sibling count as live:
*
+1 -1
View File
@@ -2004,7 +2004,7 @@ Object.assign(CodemanApp.prototype, {
const cmdPattern = /\b(tail|cat|head|less|grep|watch|vim|nano)\s+(?:[^\s\/]+\s+){0,4}(\/[^\s"'<>|;&\n\x00-\x1f]+)/g;
// Pattern 2: Paths with common extensions. Image/PDF/media extensions are
// included so pasted-attachment paths (`.claude-images/paste-*.png`) and
// included so pasted-attachment paths (`.codeman-uploads/paste-*.png`) and
// screenshots an agent just wrote are clickable; those open the file
// preview rather than the log viewer (see addLink).
//
+1 -1
View File
@@ -275,7 +275,7 @@ export function registerRebootRestoreRoutes(app: FastifyInstance, ctx: RebootRes
// count this session's historical tokens into the lifetime totals, demote
// a pinned record to `stopped` (which this pass reads as an intentional
// kill, making the session permanently unrestorable) and delete the
// workspace's `.claude-images`. This undoes only the construction.
// workspace's `.codeman-uploads`. This undoes only the construction.
await ctx
.discardPartiallyBuiltSession(entry.sessionId)
.catch((discardErr: unknown) =>
+62 -31
View File
@@ -188,6 +188,7 @@ import {
} from '../response-viewer-transcript.js';
import { readDeepSeekLastResponse } from '../../deepseek-transcript.js';
import { appendClaudeCustomTitle } from '../../claude-session-title.js';
import { UPLOADS_DIR } from '../paste-image-gc.js';
// Path to linked-cases registry (same file used by case-routes resolveCasePath)
const LINKED_CASES_FILE = dataPath('linked-cases.json');
@@ -361,6 +362,50 @@ export function imageMagicMatchesExt(data: Buffer, ext: string): boolean {
}
}
/**
* Create or re-verify `{workingDir}/.codeman-uploads` for a prompt upload, or
* null when something other than a regular directory sits there. An agent or
* postinstall script could plant `.codeman-uploads -> ~/.ssh/` and redirect
* future writes outside workingDir: lstat (not stat) sees the symlink itself,
* and mkdir without `recursive` does not follow one for the leaf either;
* O_EXCL|O_NOFOLLOW on the file open makes the write itself symlink-safe.
* The folder ignores itself: a `.gitignore` of `*`, written once with O_EXCL,
* so the user's repository never sees uploads, their own ignore file is never
* touched, and a file already there is theirs and stays as it is.
*/
async function ensureUploadDir(workingDir: string): Promise<string | null> {
// workingDir is guaranteed to exist (live session).
const uploadDir = join(workingDir, UPLOADS_DIR);
try {
const dirStat = await fs.lstat(uploadDir);
if (dirStat.isSymbolicLink() || !dirStat.isDirectory()) return null;
} catch (err: unknown) {
if ((err as NodeJS.ErrnoException).code !== 'ENOENT') throw err;
try {
await fs.mkdir(uploadDir);
} catch (mkErr: unknown) {
// Concurrent uploads (a batch of photos) race to create the dir — the
// losers get EEXIST. Treat an already-present REAL directory as success,
// but re-verify it isn't a symlink a racing actor planted.
if ((mkErr as NodeJS.ErrnoException).code !== 'EEXIST') throw mkErr;
const raceStat = await fs.lstat(uploadDir);
if (raceStat.isSymbolicLink() || !raceStat.isDirectory()) return null;
}
}
const ignoreFile = join(uploadDir, '.gitignore');
try {
// 'wx' = O_CREAT|O_EXCL, which also fails on a symlink at the path.
await fs.writeFile(ignoreFile, '*\n', { flag: 'wx' });
} catch (err: unknown) {
if ((err as NodeJS.ErrnoException).code === 'EEXIST') return uploadDir;
// The create can succeed before the write fails (ENOSPC): an empty ignore
// file would read as the user's on the next upload, so take it back.
await fs.rm(ignoreFile, { force: true });
throw err;
}
return uploadDir;
}
// 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.
@@ -5198,6 +5243,18 @@ export function registerSessionRoutes(
const session = findSessionOrFail(ctx, id, req);
// The file lands on THIS host under the session's working directory, which
// for a remote (SSH) session is the remote path: the agent there could never
// read it, and the write would land in a same-named local directory or fail.
// Docker is fine, its workspace is bind-mounted at the same absolute path.
if (session.remote) {
reply.code(400);
return createErrorResponse(
ApiErrorCode.INVALID_INPUT,
'Prompt uploads are not supported for remote (SSH) sessions'
);
}
if (!req.isMultipart()) {
reply.code(400);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'Expected multipart/form-data');
@@ -5294,37 +5351,11 @@ export function registerSessionRoutes(
return createErrorResponse(ApiErrorCode.INVALID_INPUT, `Image bytes do not match declared type ${ext}`);
}
// Save to {workingDir}/.claude-images/
// Refuse symlinks at imageDir — an agent or postinstall script could plant
// `.claude-images -> ~/.ssh/` and redirect future writes outside workingDir.
// We lstat (not stat) so we see the symlink itself. Use mkdir without
// `recursive` so the leaf creation does not follow a symlink either, and
// O_EXCL|O_NOFOLLOW on the file open so the write itself is symlink-safe.
const imageDir = join(session.workingDir, '.claude-images');
try {
const dirStat = await fs.lstat(imageDir);
if (dirStat.isSymbolicLink() || !dirStat.isDirectory()) {
reply.code(403);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, '.claude-images is not a regular directory');
}
} catch (err: unknown) {
if ((err as NodeJS.ErrnoException).code !== 'ENOENT') throw err;
// Non-recursive mkdir: does not follow symlinks for the leaf.
// session.workingDir is guaranteed to exist (live session).
try {
await fs.mkdir(imageDir);
} catch (mkErr: unknown) {
// Concurrent uploads (a batch of photos) race to create .claude-images —
// the losers get EEXIST. Treat an already-present REAL directory as
// success, but re-verify it isn't a symlink a racing actor planted
// (preserve the symlink-safety guarantee above).
if ((mkErr as NodeJS.ErrnoException).code !== 'EEXIST') throw mkErr;
const raceStat = await fs.lstat(imageDir);
if (raceStat.isSymbolicLink() || !raceStat.isDirectory()) {
reply.code(403);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, '.claude-images is not a regular directory');
}
}
// {workingDir}/.codeman-uploads/, see ensureUploadDir.
const imageDir = await ensureUploadDir(session.workingDir);
if (!imageDir) {
reply.code(403);
return createErrorResponse(ApiErrorCode.INVALID_INPUT, `${UPLOADS_DIR} is not a regular directory`);
}
// Date.now() collides on same-ms uploads from two tabs (last-write wins
// silently). Append 8 hex chars so concurrent pastes get distinct names.
+11 -8
View File
@@ -33,7 +33,7 @@ import fastifyCookie from '@fastify/cookie';
import fastifyStatic from '@fastify/static';
import fastifyWebsocket from '@fastify/websocket';
import fastifyMultipart from '@fastify/multipart';
import { pasteImageDirInUseByOtherSession, startPasteImageGc } from './paste-image-gc.js';
import { pasteImageDirInUseByOtherSession, startPasteImageGc, uploadDirs } from './paste-image-gc.js';
import { CLEAN_EXIT_CLOSE_REASON, shouldCloseCleanlyExitedSession } from '../pane-exit-sweep.js';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
@@ -1546,11 +1546,14 @@ export class WebServer extends EventEmitter {
killing: this.killingSessions,
})
) {
const pasteImageDir = join(session.workingDir, '.claude-images');
try {
rmSync(pasteImageDir, { recursive: true, force: true });
} catch {
// Best-effort cleanup
// Both upload dirs, the pre-move one too; uploadDirs() lists only real
// directories clear of the data dir, and none for a remote session.
for (const uploadDir of uploadDirs(session)) {
try {
rmSync(uploadDir, { recursive: true, force: true });
} catch {
// Best-effort cleanup
}
}
}
// Drop the agent skill's preamble cache for this session (seeded at create).
@@ -2911,7 +2914,7 @@ export class WebServer extends EventEmitter {
}
// Bound disk use under heavy paste-image traffic: delete `paste-*` files
// older than 7 days from each live session's .claude-images/ hourly.
// older than 7 days from each live session's upload dirs hourly.
if (!this.testMode) {
this._pasteImageGcStop = startPasteImageGc({ sessions: this.sessions });
// Surface event-loop stalls (e.g. a slow synchronous tmux/ps call) so the
@@ -3363,7 +3366,7 @@ export class WebServer extends EventEmitter {
* path adds the session's token totals to the lifetime figures, demotes a
* pinned record to `stopped` (the durable marker of an intentional kill, which
* would make the session permanently ineligible for a reboot restore), drops
* the persisted Ralph state, and recursively removes `.claude-images` from the
* the persisted Ralph state, and recursively removes the upload dirs from the
* WORKING DIRECTORY, which belongs to the workspace rather than to this session
* and may hold another live session's pasted images.
*