fix(tunnel): close the three leftovers from the renewal-deadlock fix

1. `.gitignore` swallowed a source file. `agent/src/dist/buildBinary.ts` is the
   packaging config, not build output, but the blanket `dist/` rule meant it was
   never committed — a fresh clone could neither typecheck `agent/src/index.ts`
   nor import it from the committed `agent/test/buildBinary.test.ts`. Re-included
   the DIRECTORY first (git does not descend into an excluded one, so un-ignoring
   just the file would not have worked) and committed the file. Verified build
   output under `agent/dist/`, `dist/`, `public/build/` is still ignored.

2. Tunnel logs named no host. `pair` learned hostId/subdomain from the enroll
   response and threw them away, so the long-running `run` process logged
   `{"subdomain":null,"hostId":null}` — including all 6380 warnings during the
   8-day outage, at exactly the moment you want to know which host. New
   `config/hostRecord.ts` persists them at enrol; `resolveHostIdentity` resolves
   config > record > the subdomain embedded in the leaf's SPIFFE SAN, so hosts
   enrolled before the record existed get an identifier back without re-pairing.

3. The phone track had no recovery path. Added `POST /device/:id/recover`,
   mirroring the host route: cert in the body, device-CA path validation, SPIFFE
   parse, `notBefore` never graced, and the full registry check (active + same
   account + `:id` matches the cert + same key) — only `notAfter` is relaxed.

Verified: agent 300/300, control-plane 296/296, tsc clean on both.
NOTE: the iOS/Android clients are not wired to call /device/:id/recover yet —
the server capability exists, the client-side trigger does not.

agent/src/certs/nativeRenew.ts

@@ -18,6 +18,7 @@
  */
 import { request as httpsRequest } from 'node:https'
 import type { AgentConfig } from '../config/agentConfig.js'
+import { resolveHostIdentity } from '../config/hostRecord.js'
 import type { Keystore } from '../keys/keystore.js'
 import type { Logger } from '../log/logger.js'
 import type { TimerLike } from '../transport/seams.js'
@@ -265,5 +266,8 @@ export function startNativeAutoRenew(
       ? { retryBackoff: createBackoff({ baseMs: opts.retryBaseMs, jitter: false }) }
       : {}),
   })
-  return wireAutoRenew(rotator, hooks, logger, { subdomain: cfg.subdomain, hostId: cfg.hostId })
+  // Prefer the resolved identity (config > enrolment record > leaf SPIFFE SAN) so renewal warnings
+  // actually name the host — `cfg` alone is null on every install that predates the record.
+  const ids = resolveHostIdentity(cfg, () => ks.loadCert()?.certPem ?? null)
+  return wireAutoRenew(rotator, hooks, logger, ids)
 }

agent/src/cli/deps.ts

@@ -13,6 +13,7 @@ import { dirname, join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import type { CliDeps, NativeEnrollResult } from '../cli.js'
 import type { AgentConfig } from '../config/agentConfig.js'
+import { resolveHostIdentity, saveHostRecord } from '../config/hostRecord.js'
 import { loadAgentConfig } from '../config/agentConfig.js'
 import { openKeystore } from '../keys/keystore.js'
 import { generateIdentity, generateP256Identity } from '../keys/identity.js'
@@ -100,6 +101,9 @@ async function enrollNative(
   ks: Keystore,
 ): Promise<NativeEnrollResult> {
   const enroll = await redeemPairingCode(cfg.enrollUrl, code, id, ks, { allowMissingContentSecret: true })
+  // Write the identifiers down: the long-running `run` process has no other way to learn them, and
+  // without them every log line from the tunnel reads `{"subdomain":null,"hostId":null}`.
+  saveHostRecord(cfg.stateDir, { hostId: enroll.hostId, subdomain: enroll.subdomain })
   return { hostId: enroll.hostId, subdomain: enroll.subdomain }
 }
 
@@ -184,7 +188,8 @@ function superviseNative(cfg: AgentConfig, ks: Keystore): Promise<number> {
       }),
     (report) => {
       // INV9: only non-secret identifiers (subdomain/host id/expiry date) + boolean flags are logged.
-      const ids = { subdomain: cfg.subdomain, hostId: cfg.hostId, certNotAfter: certNotAfter(ks) }
+      const host = resolveHostIdentity(cfg, () => ks.loadCert()?.certPem ?? null)
+      const ids = { ...host, certNotAfter: certNotAfter(ks) }
       for (const line of renderHealthStatus(ids, report)) logger.log('info', line)
     },
   )

agent/src/config/hostRecord.ts

@@ -0,0 +1,97 @@
+/**
+ * Enrolment identifiers (`hostId` / `subdomain`) persisted next to the keystore.
+ *
+ * WHY: `pair --install` learns both from the control-plane's enroll response, but nothing ever wrote
+ * them down — so the long-running `run` process had `cfg.subdomain === null` and `cfg.hostId === null`
+ * and every log line came out as `{"subdomain":null,"hostId":null}`. When the tunnel broke in
+ * production, 6380 warnings named no host at all, which is exactly the moment you want them to.
+ *
+ * They are NOT secrets (the subdomain is a public DNS label), so this is a plain JSON file — kept in
+ * `stateDir` only because that is the one directory the agent already owns on every platform.
+ *
+ * Legacy installs enrolled before this existed have no record. Their leaf still carries the
+ * subdomain in its SPIFFE URI SAN, so `resolveHostIdentity` recovers it from there rather than
+ * forcing a re-pair just to get an identifier back into the logs.
+ */
+import { X509Certificate } from 'node:crypto'
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs'
+import { join } from 'node:path'
+import type { AgentConfig } from './agentConfig.js'
+
+const RECORD_FILE = 'host.json'
+const DIR_MODE = 0o700
+
+/** Non-secret identifiers assigned by the control-plane at enrolment. */
+export interface HostRecord {
+  readonly hostId: string | null
+  readonly subdomain: string | null
+}
+
+/** A non-empty string, or null — anything else on disk is treated as absent (never trusted). */
+function stringOrNull(value: unknown): string | null {
+  return typeof value === 'string' && value.length > 0 ? value : null
+}
+
+/** Persist the enrolment identifiers into `stateDir`. Overwrites any previous record. */
+export function saveHostRecord(stateDir: string, record: HostRecord): void {
+  if (!existsSync(stateDir)) mkdirSync(stateDir, { recursive: true, mode: DIR_MODE })
+  writeFileSync(join(stateDir, RECORD_FILE), `${JSON.stringify(record, null, 2)}\n`)
+}
+
+/**
+ * Read the persisted identifiers, or null if this host has none. A missing, unreadable, or
+ * malformed file is reported as "no record" — this feeds a logging path and must never throw into
+ * the run loop.
+ */
+export function loadHostRecord(stateDir: string): HostRecord | null {
+  const path = join(stateDir, RECORD_FILE)
+  if (!existsSync(path)) return null
+  try {
+    const parsed: unknown = JSON.parse(readFileSync(path, 'utf8'))
+    if (typeof parsed !== 'object' || parsed === null) return null
+    const rec = parsed as Record<string, unknown>
+    return { hostId: stringOrNull(rec['hostId']), subdomain: stringOrNull(rec['subdomain']) }
+  } catch {
+    return null
+  }
+}
+
+/** SPIFFE IDs issued for hosts end in `/host/<subdomain>` (see relay-auth `spiffeIdFor`). */
+const SPIFFE_HOST_RE = /URI:(spiffe:\/\/[^\s,]*\/host\/([^\s,/]+))/
+
+/**
+ * Recover the subdomain from a leaf's SPIFFE URI SAN, or null if it carries none. Parse failures
+ * are null, never throws — a legacy install with a damaged cert must still start.
+ */
+export function subdomainFromCertPem(certPem: string): string | null {
+  try {
+    const san = new X509Certificate(certPem).subjectAltName ?? ''
+    const match = SPIFFE_HOST_RE.exec(san)
+    return match?.[2] ?? null
+  } catch {
+    return null
+  }
+}
+
+/**
+ * Resolve the identifiers to log for this host, most authoritative first:
+ *   1. explicit config (argv/env `SUBDOMAIN` / `HOST_ID`) — an operator override always wins;
+ *   2. the enrolment record written by `pair`;
+ *   3. the subdomain embedded in the stored leaf (legacy installs; yields no hostId).
+ *
+ * `readCertPem` is injected so this stays a pure decision over a supplied cert.
+ */
+export function resolveHostIdentity(
+  cfg: AgentConfig,
+  readCertPem: () => string | null,
+): HostRecord {
+  const record = loadHostRecord(cfg.stateDir)
+  const subdomain =
+    cfg.subdomain ??
+    record?.subdomain ??
+    ((): string | null => {
+      const pem = readCertPem()
+      return pem === null ? null : subdomainFromCertPem(pem)
+    })()
+  return { hostId: cfg.hostId ?? record?.hostId ?? null, subdomain }
+}

agent/src/dist/buildBinary.ts

@@ -0,0 +1,45 @@
+/**
+ * Static-binary build spec — PLAN_RELAY_AGENT T16 (EXPLORE §6 distribution rank 2). Produces a
+ * `bun --compile` spec for a one-`curl | sh` install. `npx web-terminal-agent` stays the MVP path
+ * (rank 1). The bundle EXCLUDES dev/test deps and any terminal parser (INV11 re-check at the
+ * package boundary — the agent is a byte-shuttle, never an ANSI interpreter).
+ */
+export type BinaryTarget = 'darwin-arm64' | 'darwin-x64' | 'linux-x64' | 'linux-arm64'
+
+export const BINARY_TARGETS: readonly BinaryTarget[] = [
+  'darwin-arm64',
+  'darwin-x64',
+  'linux-x64',
+  'linux-arm64',
+]
+
+export interface BuildSpec {
+  readonly tool: 'bun'
+  readonly entry: string
+  readonly target: BinaryTarget
+  readonly bunTarget: string // bun's --target triple
+  readonly outfile: string
+  readonly minify: true
+  /** Package-name substrings that must NOT appear in the bundle graph (INV11 tripwire). */
+  readonly forbiddenDeps: readonly string[]
+}
+
+const BUN_TRIPLE: Readonly<Record<BinaryTarget, string>> = {
+  'darwin-arm64': 'bun-darwin-arm64',
+  'darwin-x64': 'bun-darwin-x64',
+  'linux-x64': 'bun-linux-x64',
+  'linux-arm64': 'bun-linux-arm64',
+}
+
+/** Build the `bun --compile` spec for a target triple. Entry is the CLI. */
+export function buildBinaryConfig(target: BinaryTarget): BuildSpec {
+  return {
+    tool: 'bun',
+    entry: 'src/cli.ts',
+    target,
+    bunTarget: BUN_TRIPLE[target],
+    outfile: `dist/web-terminal-agent-${target}`,
+    minify: true,
+    forbiddenDeps: ['xterm', 'ansi', 'vt100'],
+  }
+}

agent/test/hostRecord.test.ts

@@ -0,0 +1,126 @@
+import { describe, expect, it } from 'vitest'
+import { mkdtempSync, rmSync, writeFileSync } from 'node:fs'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import type { AgentConfig } from '../src/config/agentConfig.js'
+import {
+  loadHostRecord,
+  resolveHostIdentity,
+  saveHostRecord,
+  subdomainFromCertPem,
+} from '../src/config/hostRecord.js'
+
+const CFG: AgentConfig = {
+  relayUrl: 'wss://relay/agent',
+  enrollUrl: 'https://enroll.terminal.example.com/enroll',
+  stateDir: '/tmp/x',
+  localTargetUrl: 'ws://127.0.0.1:3000',
+  subdomain: null,
+  hostId: null,
+}
+
+function tmpState(): string {
+  return mkdtempSync(join(tmpdir(), 'wta-hr-'))
+}
+
+/** A real frp-client leaf as issued by the control-plane (SPIFFE URI SAN carries the subdomain). */
+const LEAF_PEM = `-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----`
+
+describe('host record persistence', () => {
+  it('round-trips the enrolment identifiers through stateDir', () => {
+    const dir = tmpState()
+    saveHostRecord(dir, { hostId: 'h-1', subdomain: 'h7fd8' })
+    expect(loadHostRecord(dir)).toEqual({ hostId: 'h-1', subdomain: 'h7fd8' })
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  it('returns null when nothing was ever enrolled here', () => {
+    const dir = tmpState()
+    expect(loadHostRecord(dir)).toBeNull()
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  it('treats a corrupt record as absent rather than throwing (never crashes the run loop)', () => {
+    const dir = tmpState()
+    writeFileSync(join(dir, 'host.json'), '{not json')
+    expect(loadHostRecord(dir)).toBeNull()
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  it('ignores a record whose fields are the wrong shape', () => {
+    const dir = tmpState()
+    writeFileSync(join(dir, 'host.json'), JSON.stringify({ hostId: 42, subdomain: [] }))
+    expect(loadHostRecord(dir)).toEqual({ hostId: null, subdomain: null })
+    rmSync(dir, { recursive: true, force: true })
+  })
+})
+
+describe('subdomainFromCertPem', () => {
+  it('reads the subdomain out of the leaf SPIFFE URI SAN', () => {
+    expect(subdomainFromCertPem(LEAF_PEM)).toBe('h7fd8')
+  })
+
+  it('returns null for a certificate with no SPIFFE SAN', () => {
+    expect(subdomainFromCertPem('-----BEGIN CERTIFICATE-----\nnope\n-----END CERTIFICATE-----')).toBeNull()
+  })
+
+  it('returns null for garbage instead of throwing', () => {
+    expect(subdomainFromCertPem('not a cert')).toBeNull()
+  })
+})
+
+describe('resolveHostIdentity precedence', () => {
+  it('keeps explicit config (env/argv) over everything else', () => {
+    const dir = tmpState()
+    saveHostRecord(dir, { hostId: 'from-file', subdomain: 'from-file' })
+    const out = resolveHostIdentity(
+      { ...CFG, stateDir: dir, subdomain: 'from-env', hostId: 'from-env' },
+      () => LEAF_PEM,
+    )
+    expect(out).toEqual({ hostId: 'from-env', subdomain: 'from-env' })
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  it('falls back to the persisted enrolment record', () => {
+    const dir = tmpState()
+    saveHostRecord(dir, { hostId: 'h-1', subdomain: 'h7fd8' })
+    expect(resolveHostIdentity({ ...CFG, stateDir: dir }, () => null)).toEqual({
+      hostId: 'h-1',
+      subdomain: 'h7fd8',
+    })
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  /**
+   * Hosts enrolled before the record existed have no `host.json`. Their leaf still carries the
+   * subdomain, so they get an identifier in the logs without needing a re-pair.
+   */
+  it('falls back to the leaf SPIFFE SAN when there is no record (legacy installs)', () => {
+    const dir = tmpState()
+    expect(resolveHostIdentity({ ...CFG, stateDir: dir }, () => LEAF_PEM)).toEqual({
+      hostId: null,
+      subdomain: 'h7fd8',
+    })
+    rmSync(dir, { recursive: true, force: true })
+  })
+
+  it('yields nulls when nothing is known (unenrolled host)', () => {
+    const dir = tmpState()
+    expect(resolveHostIdentity({ ...CFG, stateDir: dir }, () => null)).toEqual({
+      hostId: null,
+      subdomain: null,
+    })
+    rmSync(dir, { recursive: true, force: true })
+  })
+})