`POST /renew` is authenticated by mTLS with the very leaf it renews, so once that leaf lapsed the host could never renew it and the tunnel stayed down until an operator re-paired by hand. Production hit exactly this: the Mac slept through its 8h renewal window, the 24h leaf expired, and the agent then logged `client certificate has expired; renew before dialling` 6380 times over 8 days without recovering. Three layers independently refused an expired leaf, so all three had to move: - agent `buildTlsOptions` gains an opt-in `expiredGraceMs`. Absent/0 keeps the historical fail-closed behaviour, and the TUNNEL dial never passes it — only the renew transport does. Past the window it throws the new `CertExpiredBeyondGraceError`. - agent rotator routes an already-expired leaf to a separate recovery endpoint and treats "beyond grace" as TERMINAL: report once via `onExhausted`, stop retrying, and name the fix (re-pair) instead of spamming warnings forever. - control-plane `assertPresentedCertTrusted` grants a bounded grace on `notAfter` only. Chain validation, SPIFFE identity, `notBefore`, and the registry `active`/account checks are all unchanged, so revocation still bites. - new `deploy/nginx/recover-mtls.conf` (:8472). The strict enroll vhost cannot host this: under `ssl_verify_client optional` nginx answers a bare 400 as soon as a presented cert fails verification, so an expired leaf never reaches the location — and the directive is server-level, not per-location. Grace defaults to 30 days on both ends and is configurable (`RECOVER_URL`, `expiredRenewGraceMs`). The honest trade is recorded in the code: a stale stolen leaf stays reusable for the window, which widens an existing exposure (an unexpired stolen leaf already renews indefinitely) rather than opening a new one. Verified: agent 296/296, control-plane 286/286, tsc clean on both.
191 lines
6.8 KiB
TypeScript
191 lines
6.8 KiB
TypeScript
import { describe, expect, it, vi } from 'vitest'
|
|
import { mkdtempSync, rmSync } from 'node:fs'
|
|
import { tmpdir } from 'node:os'
|
|
import { join } from 'node:path'
|
|
import type { AgentConfig } from '../src/config/agentConfig.js'
|
|
import { generateIdentity } from '../src/keys/identity.js'
|
|
import { openKeystore } from '../src/keys/keystore.js'
|
|
import {
|
|
CertExpiredBeyondGraceError,
|
|
CertExpiredError,
|
|
DEFAULT_EXPIRED_RENEW_GRACE_MS,
|
|
NotEnrolledError,
|
|
buildTlsOptions,
|
|
dialRelay,
|
|
type RawTlsWs,
|
|
type TlsWsConstructor,
|
|
} from '../src/transport/dial.js'
|
|
|
|
const CFG: AgentConfig = {
|
|
relayUrl: 'wss://relay.example.com/agent',
|
|
enrollUrl: 'https://example.com/enroll',
|
|
stateDir: '/tmp/x',
|
|
localTargetUrl: 'ws://127.0.0.1:3000',
|
|
subdomain: 'host-42',
|
|
hostId: 'h-1',
|
|
}
|
|
|
|
function enrolledKs() {
|
|
const dir = mkdtempSync(join(tmpdir(), 'wta-dial-'))
|
|
const ks = openKeystore(dir)
|
|
ks.saveIdentity(generateIdentity())
|
|
ks.saveCert('CERTPEM', 'CAPEM')
|
|
return { dir, ks }
|
|
}
|
|
|
|
const future: () => { validTo: Date } = () => ({ validTo: new Date(Date.now() + 86_400_000) })
|
|
const past: () => { validTo: Date } = () => ({ validTo: new Date(Date.now() - 1000) })
|
|
|
|
describe('buildTlsOptions (T12, INV14/INV4)', () => {
|
|
it('wires cert + key + CA and forces rejectUnauthorized true', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
const tls = buildTlsOptions(ks, { certParser: future })
|
|
expect(tls.cert).toBe('CERTPEM')
|
|
expect(tls.ca).toBe('CAPEM')
|
|
expect(tls.key).toContain('PRIVATE KEY') // in-process key PEM
|
|
expect(tls.rejectUnauthorized).toBe(true)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('carries NO bearer/agent token (mTLS is the auth)', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
const tls = buildTlsOptions(ks, { certParser: future })
|
|
expect(JSON.stringify(tls)).not.toMatch(/token|authorization|bearer/i)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('missing cert → NotEnrolledError (fail-fast)', () => {
|
|
const dir = mkdtempSync(join(tmpdir(), 'wta-dial-'))
|
|
expect(() => buildTlsOptions(openKeystore(dir))).toThrow(NotEnrolledError)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('expired cert → CertExpiredError', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
expect(() => buildTlsOptions(ks, { certParser: past })).toThrow(CertExpiredError)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
})
|
|
|
|
/**
|
|
* Expired-leaf RENEWAL grace. The tunnel dial stays fail-closed forever; only the /renew recovery
|
|
* path may opt in, and only inside a bounded window — otherwise an expired leaf deadlocks the agent
|
|
* (mTLS renew needs a cert, and the only cert has expired) and the host is bricked until a re-pair.
|
|
*/
|
|
describe('buildTlsOptions expired-renewal grace (deadlock recovery)', () => {
|
|
const expiredBy = (ms: number) => () => ({ validTo: new Date(Date.now() - ms) })
|
|
const DAY = 86_400_000
|
|
|
|
it('stays fail-closed by DEFAULT — no grace opt-in ⇒ CertExpiredError', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
expect(() => buildTlsOptions(ks, { certParser: expiredBy(DAY) })).toThrow(CertExpiredError)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('expired INSIDE the grace window → returns options so /renew can authenticate', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
const tls = buildTlsOptions(ks, {
|
|
certParser: expiredBy(8 * DAY),
|
|
expiredGraceMs: DEFAULT_EXPIRED_RENEW_GRACE_MS,
|
|
})
|
|
expect(tls.cert).toBe('CERTPEM')
|
|
expect(tls.rejectUnauthorized).toBe(true)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('expired BEYOND the grace window → CertExpiredBeyondGraceError (re-pair required)', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
expect(() =>
|
|
buildTlsOptions(ks, {
|
|
certParser: expiredBy(31 * DAY),
|
|
expiredGraceMs: DEFAULT_EXPIRED_RENEW_GRACE_MS,
|
|
}),
|
|
).toThrow(CertExpiredBeyondGraceError)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('grace of 0 is not a bypass — an expired leaf still throws', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
expect(() => buildTlsOptions(ks, { certParser: expiredBy(1000), expiredGraceMs: 0 })).toThrow(
|
|
CertExpiredError,
|
|
)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('a still-valid cert is unaffected by the grace option', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
const tls = buildTlsOptions(ks, {
|
|
certParser: future,
|
|
expiredGraceMs: DEFAULT_EXPIRED_RENEW_GRACE_MS,
|
|
})
|
|
expect(tls.cert).toBe('CERTPEM')
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('the TUNNEL dial never gets grace — an expired leaf still refuses to dial', () => {
|
|
const { dir, ks } = enrolledKs()
|
|
let constructed = 0
|
|
class NeverCtor implements RawTlsWs {
|
|
constructor() {
|
|
constructed += 1
|
|
}
|
|
send(): void {}
|
|
close(): void {}
|
|
on(): void {}
|
|
once(): void {}
|
|
}
|
|
// `dialRelay` has no grace seam at all: it fails fast (synchronously) before any socket exists.
|
|
expect(() =>
|
|
dialRelay(CFG, ks, { Ctor: NeverCtor as unknown as TlsWsConstructor, certParser: past }),
|
|
).toThrow(CertExpiredError)
|
|
expect(constructed).toBe(0)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
})
|
|
|
|
describe('dialRelay (T12)', () => {
|
|
it('constructs the wss client with the TLS options and resolves on open', async () => {
|
|
const { dir, ks } = enrolledKs()
|
|
let capturedUrl = ''
|
|
let capturedOpts: unknown
|
|
class FakeTlsWs implements RawTlsWs {
|
|
constructor(url: string, opts: unknown) {
|
|
capturedUrl = url
|
|
capturedOpts = opts
|
|
queueMicrotask(() => this.openCb?.())
|
|
}
|
|
private openCb?: () => void
|
|
send(): void {}
|
|
close(): void {}
|
|
on(): void {}
|
|
once(ev: string, cb: () => void): void {
|
|
if (ev === 'open') this.openCb = cb
|
|
}
|
|
}
|
|
const ws = await dialRelay(CFG, ks, { Ctor: FakeTlsWs as unknown as TlsWsConstructor, certParser: future })
|
|
expect(capturedUrl).toBe('wss://relay.example.com/agent')
|
|
expect((capturedOpts as { rejectUnauthorized: boolean }).rejectUnauthorized).toBe(true)
|
|
expect(ws).toBeDefined()
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
|
|
it('rejects when the server errors before open (bad chain / MITM)', async () => {
|
|
const { dir, ks } = enrolledKs()
|
|
class FakeTlsWs implements RawTlsWs {
|
|
private errCb?: (e: unknown) => void
|
|
constructor() {
|
|
queueMicrotask(() => this.errCb?.(new Error('unable to verify leaf signature')))
|
|
}
|
|
send(): void {}
|
|
close(): void {}
|
|
on(): void {}
|
|
once(ev: string, cb: (e: unknown) => void): void {
|
|
if (ev === 'error') this.errCb = cb
|
|
}
|
|
}
|
|
const p = dialRelay(CFG, ks, { Ctor: FakeTlsWs as unknown as TlsWsConstructor, certParser: future })
|
|
await expect(p).rejects.toThrow(/verify/)
|
|
rmSync(dir, { recursive: true, force: true })
|
|
})
|
|
})
|