Files
sencho/backend/src/__tests__/pilot-close-tunnel.test.ts
T
Anso e65c5e8551 fix(pilot): post-merge audit followups (WS via getProxyTarget, closeTunnel lifecycle, mesh source buffer, docs) (#1128)
* fix(pilot): route remote WS upgrades through NodeRegistry.getProxyTarget

Pilot-mode nodes carry empty api_url and api_token by design and expose
their API on a per-tunnel loopback bridge. The upgrade handler gated the
remote-forwarder branch on `node.api_url && node.api_token`, so WS
requests targeting pilot nodes silently fell through to the local
handlers (live logs, exec, generic) instead of tunneling to the agent.

Resolve the target via NodeRegistry.getProxyTarget so pilot and proxy
modes share one dispatch path, mirroring the HTTP proxy.
handleRemoteForwarder now takes the resolved target and, when the target
is the pilot loopback (empty token), skips the console-token exchange
and the Authorization injection so the tunnel-side auth is the only
source of truth on that path. Unresolvable targets reject the upgrade
with HTTP 503 instead of being served gateway-local data.

* fix(pilot): emit tunnel-down and mark node offline on closeTunnel

PilotTunnelManager.closeTunnel closed the underlying WebSocket but
skipped the cleanup the natural-disconnect path runs, so explicit
closures (enrollment regenerate, node deletion) left the node row at
status='online' until the next reconnect. The dashboard kept showing
the stale state for the entire interval.

closeTunnel now writes nodes.status='offline' and emits tunnel-down for
pilot bridges, and emits proxy-bridge-down for central-initiated proxy
bridges. The maps are cleared before bridge.close() so the natural
'closed' handler's bridge-identity guard short-circuits and we do not
double-emit.

* fix(mesh): buffer cross-node source data until tcp_open_ack arrives

openCrossNode piped src socket data straight to tcpStream.write before
the forward TcpStream emitted 'open'. The first packet on a fresh
cross-node stream raced ahead of the agent's tcp_open_ack on the wire,
which broke protocols that send immediately after connect (HTTP, TLS,
Redis, Postgres) on Pilot and proxy mesh paths.

Buffer src chunks in a local array capped at STREAM_PENDING_DATA_MAX_BYTES
until tcpStream emits 'open', then flush them in order before any
post-open writes. Tear down both sockets if the buffer overflows so a
misbehaving source cannot exhaust gateway memory while waiting for the
ack.

* docs(pilot): clarify host-console non-parity and narrow the parity claim

Pilot mode disables the host-console capability at the capability
registry (the agent container has no useful host shell to surface), but
the public docs listed host console among the WebSockets that ride
through the tunnel and described pilot as behaving identically to proxy
mode. State the shared-capability claim more carefully and call out the
intentional non-parity in a dedicated subsection.
2026-05-21 01:00:47 -04:00

118 lines
4.4 KiB
TypeScript

/**
* Regression for PilotTunnelManager.closeTunnel lifecycle parity.
*
* The natural-disconnect path (bridge's `'closed'` event) writes
* `nodes.status='offline'` and emits `tunnel-down` for pilot bridges, or
* emits `proxy-bridge-down` for proxy bridges. Explicit `closeTunnel` calls
* (enrollment regenerate, node deletion) must run the same cleanup so the
* UI does not keep showing a Pilot node as Online after the operator has
* intentionally torn its session down.
*/
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { EventEmitter } from 'events';
import { WebSocket } from 'ws';
import { setupTestDb, cleanupTestDb } from './helpers/setupTestDb';
import { PilotTunnelManager } from '../services/PilotTunnelManager';
let tmpDir: string;
let DatabaseService: typeof import('../services/DatabaseService').DatabaseService;
beforeAll(async () => {
tmpDir = await setupTestDb();
({ DatabaseService } = await import('../services/DatabaseService'));
});
afterAll(() => cleanupTestDb(tmpDir));
function makeMockTunnelWs(): EventEmitter & {
sent: unknown[];
readyState: number;
bufferedAmount: number;
send: (data: unknown) => void;
ping: () => void;
close: () => void;
} {
const ws = new EventEmitter() as EventEmitter & {
sent: unknown[];
readyState: number;
bufferedAmount: number;
send: (data: unknown) => void;
ping: () => void;
close: () => void;
};
ws.sent = [];
ws.readyState = WebSocket.OPEN;
ws.bufferedAmount = 0;
ws.send = (data: unknown) => { ws.sent.push(data); };
ws.ping = () => { /* no-op */ };
ws.close = () => { ws.readyState = WebSocket.CLOSED; ws.emit('close'); };
return ws;
}
describe('PilotTunnelManager.closeTunnel lifecycle parity', () => {
it('marks the node offline and emits tunnel-down when closing a pilot bridge', async () => {
const mgr = PilotTunnelManager.getInstance();
const nodeId = DatabaseService.getInstance().addNode({
name: `pilot-close-${Date.now()}`,
type: 'remote',
mode: 'pilot_agent',
compose_dir: '/tmp/x',
is_default: false,
api_url: '',
api_token: '',
});
const ws = makeMockTunnelWs();
await mgr.registerTunnel(nodeId, ws as unknown as WebSocket, 'test-1.0.0');
// Confirm the registration write actually landed before we measure
// the close-side delta; otherwise the assertion would pass for the
// wrong reason on a fresh node that defaulted to status=null.
expect(DatabaseService.getInstance().getNode(nodeId)?.status).toBe('online');
let tunnelDownNodeId: number | null = null;
const onTunnelDown = (id: number): void => { tunnelDownNodeId = id; };
mgr.once('tunnel-down', onTunnelDown);
mgr.closeTunnel(nodeId);
expect(DatabaseService.getInstance().getNode(nodeId)?.status).toBe('offline');
expect(tunnelDownNodeId).toBe(nodeId);
expect(mgr.hasActiveTunnel(nodeId)).toBe(false);
});
it('does not double-emit tunnel-down when the bridge close fires after closeTunnel', async () => {
const mgr = PilotTunnelManager.getInstance();
const nodeId = DatabaseService.getInstance().addNode({
name: `pilot-no-double-${Date.now()}`,
type: 'remote',
mode: 'pilot_agent',
compose_dir: '/tmp/x',
is_default: false,
api_url: '',
api_token: '',
});
const ws = makeMockTunnelWs();
await mgr.registerTunnel(nodeId, ws as unknown as WebSocket, 'test-1.0.0');
let emitCount = 0;
const onTunnelDown = (id: number): void => {
if (id === nodeId) emitCount += 1;
};
mgr.on('tunnel-down', onTunnelDown);
// closeTunnel deletes the map entry, then calls bridge.close() which
// synchronously emits 'closed' on the mock ws. The bridge's
// `bridges.get(nodeId) === bridge` check inside its 'closed' handler
// must short-circuit because we already deleted the entry, so this
// produces exactly one tunnel-down emission.
mgr.closeTunnel(nodeId);
// Yield a tick for any deferred listeners.
await new Promise((r) => setTimeout(r, 10));
mgr.off('tunnel-down', onTunnelDown);
expect(emitCount).toBe(1);
});
});