Files
orca/src/main/ssh/system-ssh-command.ts
T
4dbc9f3817 feat(ssh): add ControlMaster multiplexing for system SSH transport (#6922)
* feat(ssh): add ControlMaster multiplexing for system SSH transport

System SSH transport spawns a new OpenSSH process per exec command
(platform detect, relay install check, node resolution, relay launch,
socket probe). Each process pays the full SSH handshake cost — ~9s on
Uber devpods — making a typical relay connect take 54s+ and reliably
exceeding the 15s startup reconnect budget.

Add SSH ControlMaster multiplexing via a per-target socket in
$TMPDIR/orca-ssh-ctl/<hash>.sock. The first command establishes the
master; subsequent commands reuse it at ~100ms per exec instead of ~9s.
ControlPersist=300 keeps the master alive after commands exit so rapid
reconnects (e.g. on tab focus) also benefit. Windows is excluded since
OpenSSH's ControlMaster support there is limited.

* fix(ssh): address ControlMaster key collision and directory permission risks

- Use target.id in the socket key so distinct SSH targets can never
  collide even when configHost/port/user happen to match
- Switch from SHA1 to SHA256 and extend hash slice from 12 to 16 chars
- Stat the control-socket directory after mkdirSync to reject pre-existing
  dirs that are symlinks, foreign-owned, or have group/other write bits
  (mkdirSync mode is ignored on pre-existing dirs)
- Update two tests that used exact spawn-arg arrays; replace with
  ordering assertions (forward flags before --) that stay correct
  regardless of which extra ControlMaster options are injected

* fix(ssh): bind ControlPath identity to route and reject symlinked ctl dir

Fold proxyCommand/jumpHost/identity fields into the ControlPath hash so a
target whose route is edited no longer reuses a still-alive master built on
the old route. Switch the control-socket dir check from statSync to lstatSync
so a planted symlink fails the directory validation outright.

* test(ssh): drop tautological argv re-assertion in spawn checks

The toHaveBeenCalledWith re-passed the args array extracted from the same
mock call, making that argument position always pass. argv content is
already verified by the index-ordering assertions above; use expect.any(Array)
so the spawn check only claims what it actually verifies (binary path, stdio).

* fix(ssh): harden system ssh connection reuse

Co-authored-by: Orca <help@stably.ai>

* test(ssh): isolate control socket runtime dir

Co-authored-by: Orca <help@stably.ai>

---------

Co-authored-by: Test <test@example.com>
Co-authored-by: Jinwoo-H <jinwoo0825@gmail.com>
Co-authored-by: Orca <help@stably.ai>
2026-07-01 21:29:48 -07:00

160 lines
4.4 KiB
TypeScript

import { spawn, type ChildProcess } from 'node:child_process'
import { Duplex } from 'node:stream'
import type { ClientChannel } from 'ssh2'
import type { SshTarget } from '../../shared/ssh-types'
import { wrapRemoteCommandForPosixShell, type SshExecOptions } from './ssh-connection-utils'
import { buildSshArgs, type SystemSshBuildArgsOptions } from './system-ssh-args'
import { findSystemSsh } from './system-ssh-binary'
export type SystemSshProcess = {
stdin: NodeJS.WritableStream
stdout: NodeJS.ReadableStream
stderr: NodeJS.ReadableStream
kill: () => void
onExit: (cb: (code: number | null) => void) => void
pid: number | undefined
}
export type SystemSshCommandChannel = ClientChannel & {
_process?: ChildProcess
}
type SystemSshCommandOptions = SshExecOptions & SystemSshBuildArgsOptions
/**
* Spawn a system ssh process connecting to the given target.
* Used when ssh2 cannot handle the auth method (FIDO2, ControlMaster).
*
* The returned process's stdin/stdout are used as the transport for
* the relay's JSON-RPC protocol, exactly like an ssh2 channel.
*/
export function spawnSystemSsh(
target: SshTarget,
options?: SystemSshBuildArgsOptions
): SystemSshProcess {
const sshPath = findSystemSsh()
if (!sshPath) {
throw new Error(
'No system ssh binary found. Install OpenSSH to use FIDO2 keys or ControlMaster.'
)
}
const args = buildSshArgs(target, options)
const proc = spawn(sshPath, args, {
stdio: ['pipe', 'pipe', 'pipe'],
windowsHide: true
})
return wrapChildProcess(proc)
}
export function spawnSystemSshCommand(
target: SshTarget,
command: string,
options?: SystemSshCommandOptions
): SystemSshCommandChannel {
const sshPath = findSystemSsh()
if (!sshPath) {
throw new Error(
'No system ssh binary found. Install OpenSSH to use ProxyUseFdpass, FIDO2 keys, or ControlMaster.'
)
}
const remoteCommand =
options?.wrapCommand === false ? command : wrapRemoteCommandForPosixShell(command)
const proc = spawn(sshPath, [...buildSshArgs(target, options), remoteCommand], {
stdio: ['pipe', 'pipe', 'pipe'],
windowsHide: true
})
return wrapCommandProcess(proc)
}
function wrapChildProcess(proc: ChildProcess): SystemSshProcess {
return {
stdin: proc.stdin!,
stdout: proc.stdout!,
stderr: proc.stderr!,
pid: proc.pid,
kill: () => {
try {
proc.kill('SIGTERM')
} catch {
// Process may already be dead
}
},
onExit: (cb) => {
proc.on('exit', (code) => cb(code))
}
}
}
function wrapCommandProcess(proc: ChildProcess): SystemSshCommandChannel {
const duplex = new Duplex({
read() {},
write(chunk, encoding, cb) {
proc.stdin!.write(chunk, encoding, cb)
}
})
const channel = duplex as unknown as SystemSshCommandChannel
const mutableChannel = channel as unknown as {
stdin: NodeJS.WritableStream
stderr: NodeJS.ReadableStream
_process?: ChildProcess
close: () => void
}
mutableChannel.stdin = proc.stdin!
mutableChannel.stderr = proc.stderr!
mutableChannel._process = proc
mutableChannel.close = () => {
try {
proc.kill('SIGTERM')
} catch {
// Process may already be dead
}
}
const cleanupProcessListeners = (): void => {
proc.stdout!.off('data', onStdoutData)
proc.stdout!.off('end', onStdoutEnd)
proc.off('exit', onExit)
proc.off('close', onClose)
proc.off('error', onProcessError)
proc.stdin!.off('error', onStreamError)
proc.stdout!.off('error', onStreamError)
}
const fail = (err: Error): void => {
cleanupProcessListeners()
duplex.destroy(err)
}
const onStdoutData = (data: Buffer): void => {
duplex.push(data)
}
const onStdoutEnd = (): void => {
duplex.push(null)
}
const onExit = (code: number | null, signal?: NodeJS.Signals | null): void => {
channel.emit('exit', code, signal)
}
const onClose = (code: number | null, signal?: NodeJS.Signals | null): void => {
cleanupProcessListeners()
channel.emit('close', code, signal)
}
const onProcessError = (err: Error): void => {
fail(err)
}
const onStreamError = (err: Error): void => {
fail(err)
}
proc.stdout!.on('data', onStdoutData)
proc.stdout!.on('end', onStdoutEnd)
proc.on('exit', onExit)
proc.on('close', onClose)
proc.on('error', onProcessError)
proc.stdin!.on('error', onStreamError)
proc.stdout!.on('error', onStreamError)
return channel
}