The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
TypeScript 3d-modelingagent-frameworkagent-harnessai-agentscadclaude-codecodexcoding-agentsdeveloper-toolsesp32game-developmentmcp-servermulti-agentopen-hardwareopencodeopenharnesspcbroboticsterminaltmux
/**
* The WebSocket roadmap's Done criteria for Phase 0 and Phase 1 (Ken, 2026-10-28), judged on one
* account's sockets for a few minutes (harness/socketScenario.ts): two daemons, a deleted machine X and
* an offline machine Y pinned on one of them, a Desktop's windows and a browser tab, all on a local
* backend and measured by a recording proxy in front of it.
*
* The roadmap's population numbers (under 40 web-ws connects a minute, a median lifetime over a minute)
* are prod's, over every account. One account cannot reach them or miss them: on the main of 2026-10-28
* this scenario made 12.5 connects a minute, already under 40, while the window to the offline machine
* alone kept the median at a few milliseconds. So each churn cause the scenario holds is checked on its
* own, and the two numbers are printed with the report for the prod measurement after release.
*
* Every check here also passes when nothing happened, so a run that did not do what the scenario says (A's relay
* never reached B, the tab never opened a session, X was never refused, Y was selected under twice) fails every
* check with what it missed (socketScenarioRan.e2e.ts).
*
* Red on the main of 2026-10-28; each check turns green as the phase that owns it lands, and a phase ships
* only once its checks pass. Opt in with HARNESS_E2E_SERVICES_DIR, as the other real-backend suites do;
* scripts/socket-churn.sh runs it and keeps the report.
*
* SOCKET_SCENARIO_MINUTES sets the run (default 3). SOCKET_REPORT_FILE keeps the report as JSON.
*/
import { writeFileSync } from 'node:fs'
import { beforeAll, describe, expect, it } from 'vitest'
import { offlineRetryProblems, runSocketScenario, shortfalls, type ScenarioResult } from './harness/socketScenario.js'
const minutes = Number(process.env.SOCKET_SCENARIO_MINUTES ?? 3)
/** The scenario's daemons, A and B (harness/socketScenario.ts). */
const DAEMONS = 2
let result: ScenarioResult
/** When each web-ws select of `machineId` was sent, in order. */
const selectTimes = (machineId: string): number[] => result.sockets
.filter((s) => s.endpoint === '/api/web-ws')
.flatMap((s) => s.selects.filter((select) => select.machineId === machineId).map((select) => select.at))
.sort((a, b) => a - b)
describe.skipIf(!process.env.HARNESS_E2E_SERVICES_DIR)('WebSocket phases 0 and 1: one account\'s sockets', () => {
beforeAll(async () => {
const lines: string[] = []
result = await runSocketScenario({ durationMs: minutes * 60_000, log: (line) => lines.push(line) })
console.log(`socket scenario: ${lines.join(' | ')}\n${JSON.stringify(result.report, null, 2)}`)
if (process.env.SOCKET_REPORT_FILE) writeFileSync(process.env.SOCKET_REPORT_FILE, JSON.stringify(result, null, 2))
const missing = shortfalls(result)
if (missing.length) throw new Error(`The scenario did not run as it says, so no check here means anything: ${missing.join('; ')}`)
}, minutes * 60_000 + 240_000)
const webWs = () => result.report.endpoints['/api/web-ws']
it('Phase 0: at least 95% of web-ws connects name their client kind and version', () => {
expect(webWs().attributed).toBeGreaterThanOrEqual(0.95)
})
it('Phase 0: so does each kind of client, so many relays cannot hide one kind that never does', () => {
const below = Object.entries(webWs().attributedByClient).filter(([, share]) => share < 0.95)
expect(below).toEqual([])
})
// Once per daemon, not once per account (Lead, 2026-10-29, #2101): A pinned the deleted machine, and B learns it from A's
// roster before A finds it gone, so each finds it gone once (remoteRelay.ts marks it gone) and neither dials it again. The
// meter cannot tell the two daemons apart; a daemon that kept dialling would fail this within a minute (main: 16 in 3).
it('Phase 1: a deleted machine is selected at most once by each daemon, by the socket that finds it gone, and never again', () => {
expect(selectTimes(result.machines.deleted).length).toBeLessThanOrEqual(DAEMONS)
})
// Per daemon (Lead, 2026-10-29, #2104): each of A and B is told the 30 s, and each waits it out; one daemon's select
// a few seconds after the other's is two clients, not a retry. Each must have retried at least once, through its own
// named entry, so the check measures something (harness/socketScenario.ts `offlineRetryProblems`).
it('Phase 1: each daemon selects an offline machine again only after the backend\'s retryAfterMs (30 s)', () => {
expect(offlineRetryProblems(result)).toEqual([])
})
it('Phase 1: no socket that selected a machine is dropped within a minute', () => {
expect(webWs().acceptedThenDiedUnder1m).toBe(0)
})
})