Files
sencho/backend/src/__tests__/mesh-service-proxy-tunnel-reconcile.test.ts
T
Anso f6e42535c8 fix(mesh): route peer→central traffic over the existing forward WS (#1094)
* fix(mesh): route peer→central traffic over the existing forward WS

The reverse mesh callback path (`/api/mesh/proxy-tunnel-from-peer`) needed
SENCHO_PRIMARY_URL on central plus a publicly reachable origin from the
peer's perspective. In a typical homelab where central sits behind NAT,
peer→central dispatch silently failed at the dialer's short-circuit and
the headline "call any service on any node by hostname" worked one way
only.

The forward WS at `/api/mesh/proxy-tunnel` is already bidirectional end
to end. Make the bridge a persistent control-plane primitive: dial every
mesh-enabled proxy peer at startup, reconcile every 60 s, never idle-close.
Peer→central traffic multiplexes over the same WS via `tcp_open_reverse`.

Removed:
- `meshProxyTunnelFromPeer.ts` WS handler and dispatch
- `MeshCentralRegistry`, `PeerToCentralMeshSessionDialer`
- `mesh_handshake` first-frame state machine in `meshProxyTunnel.ts`
- `maybeSendBootstrap`, `buildHandshakeFrame` in the dialer
- `mesh_proxy_callback_bootstrap` capability and `maybeWarnUnsetPrimaryUrl`
- `mesh_centrals` table (drop migration; greenfield, no users)
- `PilotTunnelManager.replaceOrRegisterProxyBridge` (dead after handler removal)
- twelve associated unit/integration tests plus the peer-recovery branch
  in `MeshService.openCrossNode`

Added:
- `MeshService.proactiveBridgeFanout` selects every mesh-enabled proxy
  peer (no longer gated on `mesh_stacks` rows)
- `startBridgeReconcileLoop` runs the fanout every 60 s (override via
  `SENCHO_MESH_RECONCILE_INTERVAL_MS`)
- `MeshProxyTunnelDialer` default idle TTL is now `0` and exposes
  `isDialing(nodeId)` for the status surface
- `MeshNodeStatus.reverseCallbackStatus` discriminator
  (`connected | connecting | unavailable | not_applicable`) surfaced via
  `/api/mesh/status` and rendered as a pill in the Routing tab
- `openCrossNode` error message distinguishes "no proxy target" from
  "waiting for central to dial the reverse bridge"
- New tests: `mesh-service-proxy-tunnel-reconcile`,
  `mesh-status-reverse-callback`, `mesh-proxy-tunnel-dialer-no-idle-close`

SENCHO_PRIMARY_URL is no longer required for any mesh function.

* fix(mesh): rewrite proxy-tunnel reconcile test contents

The previous commit renamed the file but the rewritten test bodies stayed
unstaged on top of the rename. This commit lands the actual rewrite: the
fanout assertion now requires every mesh-enabled proxy peer to be dialed,
not just those with `mesh_stacks` rows, and adds a reconcile-tick
repeated-call test.
2026-05-17 22:00:31 -04:00

149 lines
5.0 KiB
TypeScript

/**
* `MeshService.proactiveBridgeFanout` and the bridge-reconcile loop.
*
* Central proactively dials every mesh-enabled proxy-mode peer at startup
* and on every reconcile tick so peer→central reverse traffic always has a
* live forward WS to multiplex through. The fanout selects ALL such peers
* regardless of whether they have any `mesh_stacks` rows yet, because the
* bridge is a control-plane primitive, not stack-scoped.
*/
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
import { setupTestDb, cleanupTestDb } from './helpers/setupTestDb';
import { MeshService } from '../services/MeshService';
import { MeshProxyTunnelDialer } from '../services/MeshProxyTunnelDialer';
import { DatabaseService } from '../services/DatabaseService';
let tmpDir: string;
beforeAll(async () => {
tmpDir = await setupTestDb();
});
afterAll(() => {
cleanupTestDb(tmpDir);
});
function uniqueSuffix(): string {
return `${Date.now()}-${Math.random().toString(36).slice(2, 10)}`;
}
function seedProxyNode(meshEnabled: boolean): number {
const db = DatabaseService.getInstance();
const id = db.addNode({
name: `peer-fanout-${uniqueSuffix()}`,
type: 'remote',
mode: 'proxy',
api_url: `https://peer-${uniqueSuffix()}.example.com`,
api_token: `tok-${uniqueSuffix()}`,
compose_dir: '/tmp',
is_default: false,
});
if (meshEnabled) {
db.setNodeMeshEnabled(id, true);
}
return id;
}
function insertMeshStack(nodeId: number, stackName: string): void {
const db = DatabaseService.getInstance();
db.getDb().prepare(
'INSERT INTO mesh_stacks (node_id, stack_name, created_at, created_by) VALUES (?, ?, ?, ?)',
).run(nodeId, stackName, Date.now(), 'test');
}
function clearNodesAndMeshStacks(): void {
const db = DatabaseService.getInstance().getDb();
db.prepare('DELETE FROM mesh_stacks').run();
db.prepare('DELETE FROM nodes WHERE is_default = 0').run();
}
function callFanout(): Promise<void> {
return (MeshService.getInstance() as unknown as {
proactiveBridgeFanout: () => Promise<void>;
}).proactiveBridgeFanout();
}
describe('MeshService.proactiveBridgeFanout', () => {
beforeEach(() => {
clearNodesAndMeshStacks();
MeshProxyTunnelDialer.resetForTest();
});
afterEach(() => {
vi.restoreAllMocks();
});
it('iterates every mesh-enabled proxy-mode node regardless of mesh_stacks rows', async () => {
const calls: number[] = [];
vi.spyOn(MeshProxyTunnelDialer.getInstance(), 'ensureBridge')
.mockImplementation(async (id: number) => {
calls.push(id);
return null;
});
const withStack = seedProxyNode(true);
insertMeshStack(withStack, `stack-${uniqueSuffix()}`);
// Mesh-enabled proxy node WITHOUT any mesh_stacks row. The old
// SQL excluded these; this assertion locks in the new behavior.
const withoutStack = seedProxyNode(true);
// Mesh-disabled proxy node WITH a mesh_stacks row. Must still be skipped.
const meshOff = seedProxyNode(false);
insertMeshStack(meshOff, `stack-meshoff-${uniqueSuffix()}`);
await callFanout();
expect(calls.sort((a, b) => a - b)).toEqual([withStack, withoutStack].sort((a, b) => a - b));
});
it('throttles to concurrency 4', async () => {
let inflight = 0;
let maxInflight = 0;
vi.spyOn(MeshProxyTunnelDialer.getInstance(), 'ensureBridge')
.mockImplementation(async () => {
inflight++;
if (inflight > maxInflight) maxInflight = inflight;
await new Promise((r) => setTimeout(r, 10));
inflight--;
return null;
});
for (let i = 0; i < 12; i++) seedProxyNode(true);
await callFanout();
expect(maxInflight).toBeLessThanOrEqual(4);
expect(maxInflight).toBeGreaterThan(0);
});
it('failures do not abort the fanout', async () => {
const ids: number[] = [];
for (let i = 0; i < 3; i++) ids.push(seedProxyNode(true));
const failingId = ids[1];
const calls: number[] = [];
vi.spyOn(MeshProxyTunnelDialer.getInstance(), 'ensureBridge')
.mockImplementation(async (id: number) => {
calls.push(id);
if (id === failingId) throw new Error('boom');
return null;
});
await callFanout();
expect(calls.slice().sort((a, b) => a - b)).toEqual(ids.slice().sort((a, b) => a - b));
});
it('repeated fanout calls invoke ensureBridge each tick (reconcile semantics)', async () => {
const ensureSpy = vi.spyOn(MeshProxyTunnelDialer.getInstance(), 'ensureBridge')
.mockResolvedValue(null);
const id = seedProxyNode(true);
await callFanout();
await callFanout();
expect(ensureSpy.mock.calls.filter(([n]) => n === id).length).toBe(2);
});
});