fix(terminal): bun-safe exec attach, box self-heal, surfaced errors

The workspace terminal died everywhere: bun's node:http client never
emits the client 'upgrade' event (it surfaces the 101 as a plain
response), so docker-modem's exec.start({hijack:true}) waited forever —
a connected WebSocket with no bytes flowing (prod), or an instant close
when the socket was unreachable (dev). The pre-Phase-1 bridge avoided
dockerode attach for exactly this reason; the real-TTY-resize rewrite
reintroduced it.

- runtime/exec-stream.ts: speak the exec-start HTTP upgrade over a raw
  net socket (docker and podman both answer 101 UPGRADED). Works under
  bun and node; honors the modem's socketPath/host:port. The stream is
  returned paused so the first screen paint can't race the caller's
  data handler. Exec create/resize stay on dockerode (plain POSTs).
- user-container.ts: acquireUserBox re-ensures the container on every
  acquire instead of trusting a cached "initialized" flag, so a box
  removed behind the worker's back (manual rm, another instance's
  reaper) is recreated instead of bricking terminals and agent turns
  until restart.
- terminal.ts: bridge failures are logged and close the WebSocket with
  a clamped human-readable reason instead of a silent catch;
  xterm-session.tsx displays that reason instead of a mute
  "Session ended". Also roomier terminal line spacing (1.2 -> 1.35).
This commit is contained in:
Gabriel Brown
2026-07-12 22:14:37 -04:00
parent c0dd8759af
commit a640b5cb94
6 changed files with 321 additions and 36 deletions
@@ -0,0 +1,131 @@
import net from 'node:net';
import type { Duplex } from 'node:stream';
import { getDockerClient } from './docker';
// Hand-rolled replacement for docker-modem's hijacked `exec.start`. Bun's
// node:http client never emits the `'upgrade'` event (it surfaces the 101 as a
// plain response), so dockerode's `exec.start({ hijack: true })` waits forever
// under bun — the terminal connects but no bytes ever flow. Docker and podman
// both answer the exec-start upgrade with `101 UPGRADED` followed by the raw
// TTY byte stream on the same connection, so we speak that one exchange
// directly over a net socket and hand the socket to the caller.
export type UpgradeParse =
| { complete: false }
| { complete: true; statusCode: number; remainder: Buffer };
const HEADER_TERMINATOR = Buffer.from('\r\n\r\n');
// Parse an accumulating exec-start response buffer. Incomplete until the CRLF
// CRLF header terminator arrives; after it, `remainder` is the start of the raw
// stream (or the error body) and must be preserved byte-exact.
export const parseUpgradeResponse = (data: Buffer): UpgradeParse => {
const headerEnd = data.indexOf(HEADER_TERMINATOR);
if (headerEnd === -1) return { complete: false };
const statusLine =
data.subarray(0, headerEnd).toString('latin1').split('\r\n', 1)[0] ?? '';
const match = /^HTTP\/1\.[01] (\d{3})/.exec(statusLine);
return {
complete: true,
statusCode: match?.[1] ? Number.parseInt(match[1], 10) : 0,
remainder: data.subarray(headerEnd + HEADER_TERMINATOR.length),
};
};
type ModemTarget = {
socketPath?: string;
host?: string;
port?: number | string;
protocol?: string;
};
/**
* Start a created exec and return the raw bidirectional TTY stream. Writes are
* stdin; reads are the terminal output (Tty:true, so no stdcopy framing). The
* socket is returned PAUSED: output that arrives while the caller is still
* wiring handlers stays buffered instead of being dropped (the first tmux
* screen paint often lands within the same tick as the upgrade). Callers must
* `stream.resume()` once their `data` handler is attached.
*/
export const openExecStream = (
execId: string,
{ timeoutMs = 15_000 }: { timeoutMs?: number } = {},
): Promise<Duplex> =>
new Promise((resolve, reject) => {
const modem = getDockerClient().modem as ModemTarget;
if (modem.protocol && modem.protocol !== 'http' && !modem.socketPath) {
reject(
new Error(
`Exec streaming supports unix sockets and plain tcp docker hosts; got protocol "${modem.protocol}".`,
),
);
return;
}
const socket = modem.socketPath
? net.connect({ path: modem.socketPath })
: net.connect({
host: modem.host ?? 'localhost',
port: Number(modem.port ?? 2375),
});
let buffered = Buffer.alloc(0);
let settled = false;
const fail = (error: Error) => {
if (settled) return;
settled = true;
clearTimeout(timer);
socket.destroy();
reject(error);
};
const timer = setTimeout(
() => fail(new Error(`Exec start timed out after ${timeoutMs}ms.`)),
timeoutMs,
);
socket.on('error', (error: Error) =>
fail(new Error(`Exec stream connection failed: ${error.message}`)),
);
socket.on('close', () =>
fail(
new Error(
`Exec stream closed before the upgrade completed${buffered.length ? `: ${buffered.toString('utf8').slice(0, 300)}` : '.'}`,
),
),
);
socket.on('connect', () => {
const body = JSON.stringify({ Detach: false, Tty: true });
socket.write(
`POST /exec/${encodeURIComponent(execId)}/start HTTP/1.1\r\n` +
'Host: docker\r\n' +
'Content-Type: application/json\r\n' +
`Content-Length: ${Buffer.byteLength(body)}\r\n` +
'Connection: Upgrade\r\n' +
'Upgrade: tcp\r\n' +
'\r\n' +
body,
);
});
const onData = (chunk: Buffer) => {
buffered = Buffer.concat([buffered, chunk]);
const parsed = parseUpgradeResponse(buffered);
if (!parsed.complete) return;
if (parsed.statusCode !== 101 && parsed.statusCode !== 200) {
fail(
new Error(
`Exec start failed: HTTP ${parsed.statusCode || 'unparseable'} ${parsed.remainder.toString('utf8').slice(0, 300)}`.trim(),
),
);
return;
}
settled = true;
clearTimeout(timer);
socket.off('data', onData);
socket.pause();
if (parsed.remainder.length > 0) socket.unshift(parsed.remainder);
resolve(socket);
};
socket.on('data', onData);
});