Merge pull request #421 from Randalix/fix/remote-file-access

fix(files): read remote-case previews, downloads and attachments over ssh
This commit is contained in:
Codeman maintainer
2026-09-14 23:42:06 +02:00
15 changed files with 2003 additions and 131 deletions
+105 -12
View File
@@ -10,10 +10,12 @@ import { randomUUID } from 'node:crypto';
import { realpathSync } from 'node:fs';
import fs from 'node:fs/promises';
import { basename, extname, isAbsolute } from 'node:path';
import { isBlockedAttachmentPath, loadAttachmentGuardConfig } from './config/attachment-guard.js';
import { isBlockedAttachmentPath, isUnderTree, loadAttachmentGuardConfig } from './config/attachment-guard.js';
import { EDITABLE_EXTENSIONS } from './config/file-editing.js';
import { validateSessionFilePath } from './web/route-helpers.js';
import { remoteProbePaths, RemoteFileAccessError } from './remote-files.js';
import type { AttachmentDetectedEvent, AttachmentDetectedType } from './types.js';
import type { SessionRemote } from './types/session.js';
/**
* Playable media extensions, single-sourced here because the WORKSPACE preview
@@ -215,6 +217,92 @@ export interface RegisterExternalAttachmentOptions {
* `codeman attach` CLI (which POSTs directly when a session id is known).
*/
forceWorkspaceConfinement?: boolean;
/**
* Remote (SSH) case: the path exists on the REMOTE host, so it is resolved and
* stat'ed there (`remoteProbePaths`) instead of with local `realpathSync`/`fs.stat`,
* which cannot see it at all (#415). A file outside the case directory is
* unreachable exactly like a file inside it.
*
* `sessionWorkingDir` must then be the REMOTE path too, and the workspace
* confinement check (when active) compares against the remotely canonicalized root,
* so a symlinked `remotePath` does not refuse every registration.
*/
remote?: SessionRemote;
}
/**
* A path an attachment request resolved to, on whichever host it lives — the local
* filesystem or the remote host of a remote-SSH case. The rest of
* {@link registerExternalAttachment} (guards, extension allowlist, registry) is then
* host-agnostic: it only ever sees canonical absolute paths and numbers.
*/
interface ResolvedAttachmentFile {
resolvedPath: string;
size: number;
mtimeMs: number;
isFile: boolean;
extension: string;
/** Remote only: the workspace root, with symlinks resolved on the remote host. */
workspaceRoot?: string;
}
/** `extension` the way the attachment registry defines it (no dot, lowercased). */
function attachmentExtensionOf(path: string): string {
return extname(path).toLowerCase().replace(/^\./, '');
}
/** Local resolution: the historical realpath + stat. */
async function resolveLocalAttachment(requestedPath: string): Promise<ResolvedAttachmentFile> {
let resolvedPath: string;
try {
resolvedPath = realpathSync(requestedPath);
} catch {
throw new AttachmentRegistrationError('Attachment file not found', 404);
}
const stat = await fs.stat(resolvedPath);
return {
resolvedPath,
size: stat.size,
mtimeMs: stat.mtimeMs ?? 0,
isFile: typeof stat.isFile === 'function' ? stat.isFile() : true,
extension: attachmentExtensionOf(resolvedPath),
};
}
/**
* Remote resolution for a remote-SSH case: ONE ssh round trip returns the
* symlink-resolved path, the size/mtime and the kind, for the file AND (when a
* workspace is known) its root, which the confinement check compares against.
*/
async function resolveRemoteAttachment(
requestedPath: string,
remote: SessionRemote,
sessionWorkingDir?: string
): Promise<ResolvedAttachmentFile> {
const paths = sessionWorkingDir ? [requestedPath, sessionWorkingDir] : [requestedPath];
let probes;
try {
probes = await remoteProbePaths(remote, paths);
} catch (err) {
throw new AttachmentRegistrationError(
err instanceof RemoteFileAccessError ? err.message : 'remote host unreachable',
502
);
}
const [probe, rootProbe] = probes;
if (!probe) {
throw new AttachmentRegistrationError('Attachment file not found', 404);
}
return {
resolvedPath: probe.realPath,
size: probe.size,
mtimeMs: probe.mtimeMs,
isFile: probe.kind === 'file',
extension: attachmentExtensionOf(probe.realPath),
workspaceRoot: rootProbe?.realPath,
};
}
export async function registerExternalAttachment(
@@ -226,12 +314,9 @@ export async function registerExternalAttachment(
throw new AttachmentRegistrationError('Attachment path must be an absolute local path');
}
let resolvedPath: string;
try {
resolvedPath = realpathSync(requestedPath);
} catch {
throw new AttachmentRegistrationError('Attachment file not found', 404);
}
const resolved = await (options.remote
? resolveRemoteAttachment(requestedPath, options.remote, options.sessionWorkingDir)
: resolveLocalAttachment(requestedPath));
// COD-53: enforce the active attachment-guard policy on the symlink-resolved
// path before doing anything else.
@@ -243,7 +328,10 @@ export async function registerExternalAttachment(
// the caller forces it for this registration (the magic-link scanner — see
// forceWorkspaceConfinement). Strictly more restrictive than the blocklist.
const workingDir = options.sessionWorkingDir;
if (!workingDir || !validateSessionFilePath(workingDir, resolvedPath)) {
const confined = options.remote
? !!workingDir && isUnderTree(resolved.resolvedPath, resolved.workspaceRoot ?? workingDir)
: !!workingDir && !!validateSessionFilePath(workingDir, resolved.resolvedPath);
if (!confined) {
throw new AttachmentRegistrationError('Access to this file is blocked', 403);
}
}
@@ -253,20 +341,25 @@ export async function registerExternalAttachment(
// operator-configured extra trees. Symlinks are already resolved above.
// Cross-workspace attachment of non-blocked files stays allowed, so
// codeman-publish and the ~/.codeman review loop keep working.
if (isBlockedAttachmentPath(resolvedPath, guard.blockedTrees)) {
//
// The list is a pattern list over ABSOLUTE paths, so it is host-agnostic and holds
// for a remote path exactly as it does for a local one.
if (isBlockedAttachmentPath(resolved.resolvedPath, guard.blockedTrees)) {
throw new AttachmentRegistrationError('Access to this file is blocked', 403);
}
const extension = extname(resolvedPath).toLowerCase().replace(/^\./, '');
const resolvedPath = resolved.resolvedPath;
const extension = resolved.extension;
if (!isSupportedAttachmentExtension(extension)) {
throw new AttachmentRegistrationError('Unsupported attachment type');
}
const stat = await fs.stat(resolvedPath);
if (typeof stat.isFile === 'function' && !stat.isFile()) {
if (!resolved.isFile) {
throw new AttachmentRegistrationError('Attachment path is not a file');
}
const stat = { size: resolved.size, mtimeMs: resolved.mtimeMs };
const existing = attachmentRegistry.findByFilePath(sessionId, resolvedPath);
if (existing) {
existing.size = stat.size;
+21 -7
View File
@@ -13,11 +13,14 @@ import { realpathSync } from 'node:fs';
import { homedir } from 'node:os';
import { join, normalize, sep } from 'node:path';
import { registerExternalAttachment, type AttachmentRegistrationResult } from './attachment-registry.js';
import type { SessionRemote } from './types/session.js';
export interface GeneratedArtifactRegistrationOptions {
sessionId: string;
filePath: string;
sessionWorkingDir: string;
/** Remote (SSH) case: the path lives on the remote host (see attachment-registry). */
remote?: SessionRemote;
}
export async function registerGeneratedArtifactAttachment(
@@ -26,19 +29,30 @@ export async function registerGeneratedArtifactAttachment(
// Decide trust on the symlink-resolved path. If it can't be resolved, fall
// back to the strict force-confined policy (registration will 404 a missing
// file anyway).
let forceWorkspaceConfinement = true;
try {
const resolvedPath = realpathSync(options.filePath);
forceWorkspaceConfinement = !isAllowedGeneratedArtifactPath(resolvedPath, options.sessionWorkingDir);
} catch {
// Keep force confinement.
}
//
// A remote case keeps that strict policy unconditionally: the well-known Codex
// artifact directories are anchored at THIS host's home, which says nothing about
// a remote home, so only a file inside the remote workspace is trusted here.
const resolvedPath = options.remote ? undefined : tryRealpath(options.filePath);
const forceWorkspaceConfinement = !resolvedPath
? true
: !isAllowedGeneratedArtifactPath(resolvedPath, options.sessionWorkingDir);
return registerExternalAttachment(options.sessionId, options.filePath, {
sessionWorkingDir: options.sessionWorkingDir,
forceWorkspaceConfinement,
remote: options.remote,
});
}
/** `realpathSync` without the throw — undefined when the path does not resolve. */
function tryRealpath(path: string): string | undefined {
try {
return realpathSync(path);
} catch {
return undefined;
}
}
/** Well-known Codex generated-artifact directories, anchored at the user's home. */
function codexGeneratedDirs(): string[] {
const home = homedir();
+296
View File
@@ -0,0 +1,296 @@
/**
* @fileoverview Remote (SSH) file access for remote-SSH cases.
*
* A remote case's `workingDir` is an absolute path on ANOTHER host
* (`Session.workingDir = RemoteCase.remotePath`, see docs/remote-sessions.md). Every
* file route used to read it with local `fs`, which cannot work: the local
* `realpathSync` in `validateSessionFilePath` fails first, so the request died as a
* 404 "File not found" before a byte was read (#415). This module is the ONE place
* that reads remote bytes, mirroring how `remote-hosts.ts` is the one place that
* builds an ssh command line.
*
* Connection options come from `buildSshConnectionArgs()` — never a hand-built ssh
* line (the COD-107 discipline in docs/remote-sessions.md) — so a proxied,
* custom-port or jump-hosted case reaches its files with exactly the credentials the
* launch used, and `BatchMode=yes` means a host that needs a passphrase fails fast
* instead of hanging on a prompt nothing can answer.
*
* ⚠️ The path is the injection surface: it arrives from the browser (`?path=`). It is
* always interpolated as a single `shellescape`d token, and the whole remote command
* is itself shellescaped into the ssh line, so the local shell and the remote shell
* each see one opaque argument. Never build a command here by concatenating a raw
* path into the string.
*
* Read-only by design: previews, text reads and streaming. Writing to a remote file
* is deliberately NOT implemented (docs/file-viewer-edit-plan.md §6), nor are the
* office-conversion/thumbnail paths that would need the bytes on the server's disk.
*/
import { exec, spawn } from 'node:child_process';
import { promisify } from 'node:util';
import type { Readable } from 'node:stream';
import type { SessionRemote } from './types/session.js';
import { buildSshConnectionArgs, remoteSshTarget, shellescape } from './remote-hosts.js';
const execAsync = promisify(exec);
/**
* Bound on the probe (realpath + stat) round trip. The connect itself is already
* bounded by `buildSshConnectionArgs`'s default `-o ConnectTimeout=10`; this covers
* a host that accepts the TCP connection and then never answers.
*/
const REMOTE_PROBE_TIMEOUT_MS = 20_000;
/** Bound on a buffered remote read (`cat`), on top of the caller's own size cap. */
const REMOTE_READ_TIMEOUT_MS = 30_000;
/** Slack over the caller's byte cap so a file exactly at the limit still fits. */
const READ_BUFFER_SLACK_BYTES = 64 * 1024;
/** Marker a probe prints when the path does not exist on the remote host. */
const NOT_FOUND_MARKER = 'n';
/** What a remote path turned out to be. `other` = symlink/socket/fifo/device. */
export type RemotePathKind = 'file' | 'directory' | 'other';
export interface RemoteProbe {
/** The path with symlinks resolved on the REMOTE host. */
realPath: string;
kind: RemotePathKind;
/** Size in bytes (0 for anything that is not a regular file). */
size: number;
/** mtime in ms since epoch (0 when the remote `stat` reported none). */
mtimeMs: number;
}
/**
* A remote file access failed for a reason that is NOT "the file is missing" —
* unreachable host, timeout, ssh error, unexpected probe output. Callers map this to
* a 5xx with the remote reason in the message; a missing file is reported separately
* as `null`/404 so the two cannot be confused.
*/
export class RemoteFileAccessError extends Error {
constructor(message: string) {
super(message);
this.name = 'RemoteFileAccessError';
}
}
/**
* Wrap a remote shell command in the shared, shellescaped ssh line.
*
* The single entry point for "run this on the remote host": connection args (port,
* identity, jump host, SOCKS ProxyCommand, extra `-o`) all come from
* `buildSshConnectionArgs`, and the command is ONE shellescaped token, so a path with
* spaces, quotes or `$(…)` cannot escape into the ssh command line.
*/
export function buildRemoteFileCommand(remote: SessionRemote, shellCommand: string): string {
return [...buildSshConnectionArgs(remote), remoteSshTarget(remote), shellescape(shellCommand)].join(' ');
}
/**
* `realpath + stat + existence` for one or more paths, in a SINGLE ssh round trip.
*
* One call instead of three matters: without a shared connection (no ControlMaster)
* every extra `ssh` is a fresh handshake, and the file routes need the path AND the
* workspace root canonicalized to compare them.
*
* Each path emits exactly one line — `n` when it does not exist, otherwise
* `kind|size|mtime|realPath` with `realPath` LAST so a path containing `|` still
* parses (the earlier fields are fixed and the remainder is the path).
*
* Symlink resolution is portable on purpose: `readlink -f` where available (Linux,
* macOS >= 12.3), else the POSIX `cd`/`pwd -P` fallback, which resolves the DIRECTORY
* chain. Resolution is required here rather than optional: `isSensitivePath()`
* demands an already-realpath'd input, so a remote read must not be able to reach a
* blocked target through a symlink any more than a local one can.
*/
export function buildRemoteProbeCommand(paths: readonly string[]): string {
const probes = paths.map((path) => `probe ${shellescape(path)}`).join('\n');
return [
'probe() {',
' p=$1',
' r=$(readlink -f "$p" 2>/dev/null) || r=$(cd "$(dirname "$p")" 2>/dev/null && printf %s/%s "$(pwd -P)" "$(basename "$p")")',
' [ -n "$r" ] || r=$p',
` if [ ! -e "$p" ]; then printf '%s\\n' ${NOT_FOUND_MARKER}; return; fi`,
' if [ -d "$r" ]; then t=d; elif [ -f "$r" ]; then t=f; else t=o; fi',
' s=0',
' if [ "$t" = f ]; then s=$(wc -c < "$r" 2>/dev/null | tr -d " "); [ -n "$s" ] || s=0; fi',
' m=$(stat -c %Y "$r" 2>/dev/null || stat -f %m "$r" 2>/dev/null || printf 0)',
` printf '%s|%s|%s|%s\\n' "$t" "$s" "$m" "$r"`,
'}',
probes,
].join('\n');
}
/** Parse one probe line. `null` for the not-found marker or anything malformed. */
export function parseRemoteProbeLine(line: string): RemoteProbe | null {
const trimmed = line.replace(/\r$/, '');
if (!trimmed || trimmed === NOT_FOUND_MARKER) return null;
const parts = trimmed.split('|');
if (parts.length < 4) return null;
const [kindRaw, sizeRaw, mtimeRaw] = parts;
const kind: RemotePathKind | null =
kindRaw === 'f' ? 'file' : kindRaw === 'd' ? 'directory' : kindRaw === 'o' ? 'other' : null;
if (!kind) return null;
const realPath = parts.slice(3).join('|');
if (!realPath) return null;
const size = Number.parseInt(sizeRaw, 10);
const mtimeSeconds = Number.parseInt(mtimeRaw, 10);
return {
realPath,
kind,
size: Number.isFinite(size) && size > 0 ? size : 0,
mtimeMs: Number.isFinite(mtimeSeconds) && mtimeSeconds > 0 ? mtimeSeconds * 1000 : 0,
};
}
/**
* Parse the output of {@link buildRemoteProbeCommand} into one entry per requested
* path, in order. Throws when the output cannot be one line per path — that means the
* transport or the remote shell did something unexpected, and silently treating it as
* "not found" would turn an infrastructure failure into a wrong 404.
*
* The LAST `paths.length` lines are used so a login banner or an eager rc-file `echo`
* on the remote host cannot shift the alignment.
*/
export function parseRemoteProbeLines(stdout: string, paths: readonly string[]): Array<RemoteProbe | null> {
const lines = stdout.split('\n').filter((line) => line !== '');
if (lines.length < paths.length) {
throw new RemoteFileAccessError('remote host returned no usable file information');
}
return lines.slice(-paths.length).map((line) => parseRemoteProbeLine(line));
}
/** Probe one or more remote paths. Entry is `null` for a path that does not exist. */
export async function remoteProbePaths(
remote: SessionRemote,
paths: readonly string[]
): Promise<Array<RemoteProbe | null>> {
const command = buildRemoteFileCommand(remote, buildRemoteProbeCommand(paths));
let stdout: string;
try {
const result = await execAsync(command, { timeout: REMOTE_PROBE_TIMEOUT_MS, maxBuffer: 64 * 1024 });
stdout = result.stdout;
} catch (err) {
throw new RemoteFileAccessError(
`remote host ${remote.label || remote.host} unreachable: ${describeExecError(err)}`
);
}
return parseRemoteProbeLines(stdout, paths);
}
/** Read a whole remote file into memory, capped by `maxBytes`. */
export async function remoteReadFile(remote: SessionRemote, remotePath: string, maxBytes: number): Promise<Buffer> {
const command = buildRemoteFileCommand(remote, `cat ${shellescape(remotePath)}`);
try {
const result = await execAsync(command, {
timeout: REMOTE_READ_TIMEOUT_MS,
maxBuffer: maxBytes + READ_BUFFER_SLACK_BYTES,
encoding: 'buffer',
});
return Buffer.isBuffer(result.stdout) ? result.stdout : Buffer.from(result.stdout);
} catch (err) {
throw new RemoteFileAccessError(`failed to read remote file: ${describeExecError(err)}`);
}
}
/**
* Command that writes a remote file's bytes to stdout.
*
* ⚠️ Range reads use `tail -c +N | head -c L` (both POSIX, constant memory) because
* the alternative — `dd bs=1` — issues one read syscall per byte and would make video
* seeking unusable. The trade-off is that a `tail` failure (the file vanished
* mid-request) reports `head`'s exit status, i.e. a short body on an already-sent
* 206; the client retries. The uncompressed path (`cat`) reports its own failure
* correctly, so the streaming error path is still covered by the normal case.
*/
export function buildRemoteReadCommand(remotePath: string, range?: { start: number; end: number }): string {
const quoted = shellescape(remotePath);
if (!range) return `cat ${quoted}`;
const length = range.end - range.start + 1;
return `tail -c +${range.start + 1} ${quoted} | head -c ${length}`;
}
export interface RemoteFileStream {
/** The remote file's bytes, streamed from the ssh child's stdout. */
stream: Readable;
/**
* Abort the transfer and reap the ssh child. The caller MUST call this when the
* HTTP request ends — especially on a client disconnect — or the `ssh` process
* keeps running (and holding a connection open) after nobody is reading it.
*/
close(): void;
}
/**
* Stream a remote file (optionally a byte range) as a Node Readable.
*
* Nothing is buffered in server memory: the bytes go from `ssh`'s stdout straight to
* the HTTP response, which is what makes a multi-GB remote video cost one pipe.
*/
export function remoteCreateReadStream(
remote: SessionRemote,
remotePath: string,
range?: { start: number; end: number }
): RemoteFileStream {
const command = buildRemoteFileCommand(remote, buildRemoteReadCommand(remotePath, range));
const child = spawn(command, { shell: true, stdio: ['ignore', 'pipe', 'pipe'] });
let stderr = '';
child.stderr?.on('data', (chunk: Buffer) => {
if (stderr.length < 2000) stderr += chunk.toString();
});
const stream = child.stdout;
let ended = false;
stream.on('end', () => {
ended = true;
});
stream.on('error', () => {
ended = true;
});
child.on('error', (err: Error) => {
stream.destroy(err);
});
child.on('close', (code: number | null) => {
// Only a truncated transfer is an error. A non-zero exit AFTER the body finished
// (e.g. a signal delivered as the last byte was flushed) must not destroy an
// already-complete response, or the browser reports a broken body for a file it
// received in full.
if (ended || code === 0 || code === null) return;
const detail = stderr.trim().split('\n')[0];
stream.destroy(new RemoteFileAccessError(`remote read failed (ssh exit ${code})${detail ? `: ${detail}` : ''}`));
});
return {
stream,
close(): void {
if (!stream.destroyed) stream.destroy();
child.kill('SIGTERM');
},
};
}
/** First useful line of an exec/stderr error, for a user-facing message. */
function describeExecError(err: unknown): string {
if (typeof err === 'object' && err !== null) {
const record = err as { stderr?: unknown; message?: unknown; code?: unknown; killed?: unknown };
const stderr =
typeof record.stderr === 'string' ? record.stderr : Buffer.isBuffer(record.stderr) ? String(record.stderr) : '';
const line = stderr
.split('\n')
.map((entry) => entry.trim())
.find((entry) => entry.length > 0);
if (line) return line;
if (record.killed) return 'timed out';
if (typeof record.message === 'string' && record.message.length > 0) return record.message;
if (typeof record.code === 'string' || typeof record.code === 'number') return `ssh exit ${record.code}`;
}
return 'unknown error';
}
+7 -1
View File
@@ -147,8 +147,14 @@ export function remoteSshTarget(host: Pick<RemoteHost, 'username' | 'host'>): st
* POSIX single-quote shell-escaping (end-quote, escaped-quote, restart-quote).
* Mirrors the helper in tmux-manager.ts so a value with spaces/metachars stays a
* single shell token. Used here for identity paths and `-o KEY=VALUE` options.
*
* EXPORTED for `remote-files.ts` (#415, remote file access): that module wraps a
* remote shell command in the ssh line built by `buildSshConnectionArgs()`, so it
* needs the same escaping discipline for the remote command itself and for every
* path interpolated into it. A third private copy of this function is exactly how
* two escaping implementations drift apart.
*/
function shellescape(str: string): string {
export function shellescape(str: string): string {
return "'" + str.replace(/'/g, "'\\''") + "'";
}
+34 -2
View File
@@ -88,11 +88,43 @@ export function validateSessionFilePath(
} catch {
return null;
}
const relativePath = relative(resolvedWorkingDir, resolvedPath);
return confineToRoot(resolvedWorkingDir, resolvedPath);
}
/**
* The lexical half of {@link validateSessionFilePath}: same containment rule, but
* WITHOUT touching the filesystem.
*
* Needed for remote-SSH cases (`src/remote-files.ts`), where `workingDir` is an
* absolute path on the REMOTE host and any local `realpathSync` fails by
* construction — which is how every file-raw/file-content request in a remote case
* used to end up as a 404 before a single byte was read. The caller follows this
* pre-check with a remote realpath + the same containment rule, so escapes are
* refused exactly as they are locally; what changes is only WHICH filesystem
* resolves the symlinks.
*
* A lexical check alone would follow nothing, so it must never be the last word for
* a path that can contain a symlink — it is the cheap reject in front of the real
* (local or remote) resolution, not a replacement for it.
*/
export function validateSessionFilePathLexical(
sessionWorkingDir: string,
filePath: string
): { resolvedPath: string; relativePath: string } | null {
return confineToRoot(resolve(sessionWorkingDir), resolve(sessionWorkingDir, filePath));
}
/**
* Shared containment rule: `candidate` must sit inside `root` (both already
* canonical for their filesystem). `relative()` is the whole test — a `..` or an
* absolute result means the candidate escaped.
*/
function confineToRoot(root: string, candidate: string): { resolvedPath: string; relativePath: string } | null {
const relativePath = relative(root, candidate);
if (relativePath.startsWith('..') || isAbsolute(relativePath)) {
return null;
}
return { resolvedPath, relativePath };
return { resolvedPath: candidate, relativePath };
}
// Maximum hook data size (prevents oversized SSE broadcasts)
File diff suppressed because it is too large Load Diff
+2
View File
@@ -1719,10 +1719,12 @@ export class WebServer extends EventEmitter {
sessionId,
filePath,
sessionWorkingDir: session.workingDir,
remote: session.remote,
})
: await registerExternalAttachment(sessionId, filePath, {
sessionWorkingDir: session.workingDir,
forceWorkspaceConfinement: true,
remote: session.remote,
});
const record = attachmentRegistry.get(sessionId, event.attachmentId);
if (record) {