feat: connection candidates refresh + relay identity hardening

Candidates refresh (server + mobile + desktop clients):
- GET /api/client-auth/connection/candidates returns the server's current
  LAN URLs, relay candidate, and serverId for already-paired devices
- /health and /api/version expose serverId so clients can verify a learned
  address belongs to the expected server before sending their bearer token
- mobile: refresh saved candidates over the live transport after every
  connect/wake, hot-switch relay->LAN when a fresh address is reachable;
  serverId gate on direct probes; token no longer sent to /health
- desktop: refresh stored host apiUrl after a relay connect and hot-switch
  back to direct; electron probe verifies serverId before authenticated fetch

Fixes found while debugging a dead pairing:
- settings: strict reader that throws on corrupt/unreadable file instead of
  returning {}; relay signing/encryption key generation is now gated on it,
  so a swallowed read failure can no longer mint a new server identity and
  orphan every paired device (loud log when a keypair IS generated)
- SessionAuthGate: bounded auto-retry for transient session-check failures
  (initial request racing the relay tunnel's first WS attempt, startup 5xx)
This commit is contained in:
Bohdan Triapitsyn
2026-07-12 18:09:54 +03:00
parent 22d5ad3814
commit afb368e11b
16 changed files with 610 additions and 27 deletions
+38
View File
@@ -365,6 +365,7 @@ const settingsRuntime = createSettingsRuntime({
const readSettingsFromDiskMigrated = (...args) => settingsRuntime.readSettingsFromDiskMigrated(...args);
const readSettingsFromDisk = (...args) => settingsRuntime.readSettingsFromDisk(...args);
const readSettingsFromDiskStrict = (...args) => settingsRuntime.readSettingsFromDiskStrict(...args);
const writeSettingsToDisk = (...args) => settingsRuntime.writeSettingsToDisk(...args);
const persistSettings = (...args) => settingsRuntime.persistSettings(...args);
@@ -409,6 +410,7 @@ const apnsRuntime = createApnsRuntime({
APNS_TOKENS_FILE_PATH,
readSettingsFromDiskMigrated,
writeSettingsToDisk,
readSettingsStrict: readSettingsFromDiskStrict,
});
const addOrUpdateApnsToken = (...args) => apnsRuntime.addOrUpdateApnsToken(...args);
@@ -1214,6 +1216,37 @@ async function main(options = {}) {
const lan = lanHost ? `http://${lanHost.includes(':') ? `[${lanHost}]` : lanHost}:${activePort}` : null;
return { local, lan, relayAvailable: true };
};
// ALL direct LAN URLs this server is currently reachable on, for the
// candidates-refresh endpoint: the address the requesting client already
// reached us on first (guaranteed routable from its network — over the relay
// tunnel this is loopback and yields nothing), then every non-internal IPv4
// interface. A client that paired while the machine had a different DHCP
// lease uses this to replace its stale LAN candidate.
const resolveDirectLanUrls = (req) => {
const activePort = tunnelRuntimeContext.getActivePort() || port;
const urls = [];
const push = (host) => {
if (typeof host !== 'string' || !host) return;
const url = `http://${host.includes(':') ? `[${host}]` : host}:${activePort}`;
if (!urls.includes(url)) urls.push(url);
};
if (isNetworkExposedBindHost(effectiveBindHost)) {
push(requestReachedLanAddress(req));
try {
for (const list of Object.values(os.networkInterfaces())) {
for (const entry of (list || [])) {
if (entry.family === 'IPv4' && !entry.internal) push(entry.address);
}
}
} catch {
// interface scan failure → whatever we already collected
}
} else {
const h = String(effectiveBindHost || '').toLowerCase();
if (h && h !== '127.0.0.1' && h !== 'localhost' && h !== '::1') push(effectiveBindHost);
}
return urls;
};
const uiPassword = typeof options.uiPassword === 'string'
? options.uiPassword
: (typeof process.env.OPENCHAMBER_UI_PASSWORD === 'string' ? process.env.OPENCHAMBER_UI_PASSWORD : null);
@@ -1374,6 +1407,10 @@ async function main(options = {}) {
// redeemed device can flip relay demand on or off).
reconcileRelay: () => (relayServiceInstance ? relayServiceInstance.reconcile() : Promise.resolve()),
getPairingTransports: resolvePairingTransports,
getDirectCandidateUrls: resolveDirectLanUrls,
// Stable server identity for client-side verification of learned addresses.
// Lazily resolved: the relay service is constructed after these routes.
getServerId: () => (relayServiceInstance ? relayServiceInstance.getServerId() : Promise.resolve(null)),
// The display name a paired device shows for THIS server. Devices name the
// connection by the issuing machine's hostname, not the per-device pairing
// label typed by the operator.
@@ -1436,6 +1473,7 @@ async function main(options = {}) {
os,
readSettingsFromDiskMigrated,
writeSettingsToDisk,
readSettingsStrict: readSettingsFromDiskStrict,
remoteClientAuthRuntime,
getLocalPort: () => tunnelRuntimeContext.getActivePort(),
// Relay demand = any paired device or pending pairing session that uses the
@@ -42,6 +42,8 @@ export const createApnsRuntime = (deps) => {
APNS_TOKENS_FILE_PATH,
readSettingsFromDiskMigrated,
writeSettingsToDisk,
// Strict settings reader gating identity regeneration (see signing-key.js).
readSettingsStrict,
} = deps;
let persistLock = Promise.resolve();
@@ -60,7 +62,7 @@ export const createApnsRuntime = (deps) => {
// relay identity — same keypair, same storage, same serverId derivation).
const getOrCreateRelayKeypair = async () => {
if (cachedRelayKey) return cachedRelayKey;
cachedRelayKey = await getOrCreateRelaySigningKeypair({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk });
cachedRelayKey = await getOrCreateRelaySigningKeypair({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk, readSettingsStrict });
return cachedRelayKey;
};
+5
View File
@@ -26,6 +26,8 @@ export const createBootstrapRuntime = (dependencies) => {
getRelayPairingCandidate,
reconcileRelay,
getPairingTransports,
getDirectCandidateUrls,
getServerId,
getServerLabel,
readSettingsFromDiskMigrated,
normalizeTunnelSessionTtlMs,
@@ -76,6 +78,7 @@ export const createBootstrapRuntime = (dependencies) => {
serverStartedAt,
gracefulShutdown,
getHealthSnapshot,
getServerId,
tunnelAuthController,
uiAuthController,
});
@@ -91,6 +94,8 @@ export const createBootstrapRuntime = (dependencies) => {
getRelayPairingCandidate,
reconcileRelay,
getPairingTransports,
getDirectCandidateUrls,
getServerId,
getServerLabel,
readSettingsFromDiskMigrated,
normalizeTunnelSessionTtlMs,
@@ -67,10 +67,29 @@ export const registerServerStatusRoutes = (app, dependencies) => {
serverStartedAt,
gracefulShutdown,
getHealthSnapshot,
// Stable server identity (hash of the public signing key — not a secret).
// Exposed on /health and /api/version so a client can verify that a
// learned/probed address belongs to the expected server BEFORE sending its
// bearer token there. Optional: older wiring omits it.
getServerId = async () => null,
tunnelAuthController = null,
uiAuthController = null,
} = dependencies;
// The identity is immutable for the process lifetime; resolve once, and never
// let an identity failure break health reporting.
let cachedServerId = null;
const resolveServerId = async () => {
if (cachedServerId) return cachedServerId;
try {
const value = await getServerId();
cachedServerId = typeof value === 'string' && value.trim() ? value.trim() : null;
} catch {
cachedServerId = null;
}
return cachedServerId;
};
const allocateLoopbackPort = async () => {
const net = await import('node:net');
return await new Promise((resolve, reject) => {
@@ -213,24 +232,28 @@ export const registerServerStatusRoutes = (app, dependencies) => {
}
};
app.get('/health', (_req, res) => {
app.get('/health', async (_req, res) => {
const serverId = await resolveServerId();
res.json({
status: 'ok',
timestamp: new Date().toISOString(),
openchamberVersion,
runtime: runtimeName,
compatibility,
...(serverId ? { serverId } : {}),
...getHealthSnapshot(),
});
});
app.get('/api/version', (_req, res) => {
app.get('/api/version', async (_req, res) => {
const serverId = await resolveServerId();
res.json({
status: 'ok',
openchamberVersion,
runtime: runtimeName,
startedAt: serverStartedAt,
compatibility,
...(serverId ? { serverId } : {}),
});
});
@@ -371,6 +394,12 @@ export const registerAuthAndAccessRoutes = (app, dependencies) => {
// server can actually be reached on (LAN derived from the server bind, not
// the UI origin), for the create-device dialog.
getPairingTransports = () => ({ local: null, lan: null, relayAvailable: true }),
// Returns ALL direct LAN URLs the server is currently reachable on (client-
// reached address first, then interface scan) for the candidates-refresh
// endpoint. Empty when the server is loopback-only.
getDirectCandidateUrls = () => [],
// Stable server identity for client-side verification of learned addresses.
getServerId = async () => null,
// Display name a paired device shows for THIS server (issuing machine's
// hostname), distinct from the per-device pairing label typed by the operator.
getServerLabel = () => 'OpenChamber',
@@ -796,6 +825,48 @@ export const registerAuthAndAccessRoutes = (app, dependencies) => {
});
});
// Current reachable transports for an ALREADY-PAIRED device. Pairing-payload
// candidates are a snapshot: when DHCP hands this machine a new address, the
// device's saved LAN candidate goes stale and it is stuck on the relay forever.
// A client that connected over any live transport calls this to learn the
// server's present LAN URLs (plus the relay candidate when enabled) and update
// its saved candidate set. `serverId` lets the client bind the response — and
// later /health probes of the learned addresses — to this server's identity
// before trusting them with its bearer token.
// Auth: UI session or client bearer; never the short-lived URL token.
app.get('/api/client-auth/connection/candidates', async (req, res, next) => {
await runWithClientManagementAuth(req, res, next, async () => {
const candidates = [];
const directUrls = (() => {
try {
const urls = getDirectCandidateUrls(req);
return Array.isArray(urls) ? urls : [];
} catch {
return [];
}
})();
for (const url of directUrls) {
const normalized = normalizeCandidateUrl(url);
if (normalized) candidates.push({ type: 'lan', url: normalized, priority: 10 });
}
try {
const relayCandidate = await getRelayPairingCandidate({ ensureEnabled: false });
if (relayCandidate) candidates.push(relayCandidate);
} catch {
// Relay status failure must not break the direct-candidate refresh.
}
let serverId = null;
try {
const value = await getServerId();
serverId = typeof value === 'string' && value.trim() ? value.trim() : null;
} catch {
serverId = null;
}
res.setHeader('Cache-Control', 'no-store');
res.json({ label: getServerLabel(), ...(serverId ? { serverId } : {}), candidates });
});
});
// Direct transports the server can be reached on (for the create-device dialog).
app.get('/api/client-auth/pairing/transports', async (req, res, next) => {
await runWithClientCreateAuth(req, res, next, async () => {
@@ -571,6 +571,56 @@ describe('client auth routes', () => {
expect(listedAfterPurge.body.clients).toHaveLength(0);
});
it('reports current connection candidates with server identity for paired devices', async () => {
const app = express();
const relayCandidate = {
type: 'relay',
relayUrl: 'wss://relay.example/ws',
serverId: 'server-abc',
hostEncPubJwk: { kty: 'EC', crv: 'P-256', x: 'x', y: 'y' },
priority: 30,
};
const dependencies = {
...createDependencies({ resolveAuthContext: async () => ({ type: 'client', clientId: 'client-1' }) }),
getDirectCandidateUrls: () => ['http://192.168.1.20:3000', 'http://10.0.0.5:3000', 'not-a-url'],
getRelayPairingCandidate: async () => relayCandidate,
getServerId: async () => 'server-abc',
getServerLabel: () => 'my-host',
};
registerAuthAndAccessRoutes(app, dependencies);
const response = await request(app).get('/api/client-auth/connection/candidates');
expect(response.status).toBe(200);
expect(response.headers['cache-control']).toBe('no-store');
expect(response.body.serverId).toBe('server-abc');
expect(response.body.label).toBe('my-host');
expect(response.body.candidates).toEqual([
{ type: 'lan', url: 'http://192.168.1.20:3000', priority: 10 },
{ type: 'lan', url: 'http://10.0.0.5:3000', priority: 10 },
relayCandidate,
]);
});
it('omits serverId and relay candidate when unavailable and survives failures', async () => {
const app = express();
const dependencies = {
...createDependencies(),
getDirectCandidateUrls: () => {
throw new Error('scan failed');
},
getRelayPairingCandidate: async () => {
throw new Error('relay status failed');
},
getServerId: async () => null,
};
registerAuthAndAccessRoutes(app, dependencies);
const response = await request(app).get('/api/client-auth/connection/candidates');
expect(response.status).toBe(200);
expect(response.body).not.toHaveProperty('serverId');
expect(response.body.candidates).toEqual([]);
});
it('scopes non-desktop client credentials to list and revoke only themselves', async () => {
const app = express();
let authContext = { type: 'session' };
@@ -438,6 +438,30 @@ export const createSettingsRuntime = (deps) => {
}
};
// Strict variant for callers that REGENERATE persisted identity when a key is
// absent (relay signing/encryption keys). The lenient reader above maps every
// failure — corrupt JSON, EACCES, transient I/O — to `{}`, which such callers
// cannot distinguish from "first run": they would mint a NEW identity, orphan
// every paired device and push binding, and overwrite the settings file with
// the empty spread. Here only a genuinely missing file means "no settings";
// any other failure (including a non-object payload) throws.
const readSettingsFromDiskStrict = async () => {
let raw;
try {
raw = await fsPromises.readFile(SETTINGS_FILE_PATH, 'utf8');
} catch (error) {
if (error && typeof error === 'object' && error.code === 'ENOENT') {
return {};
}
throw error;
}
const parsed = JSON.parse(raw);
if (!parsed || typeof parsed !== 'object') {
throw new Error('Settings file is malformed (non-object payload)');
}
return parsed;
};
const sleep = (ms) => new Promise((resolve) => setTimeout(resolve, ms));
const isTransientWindowsReplaceError = (error) => {
@@ -870,6 +894,7 @@ export const createSettingsRuntime = (deps) => {
return {
readSettingsFromDisk,
readSettingsFromDiskStrict,
readSettingsFromDiskMigrated,
writeSettingsToDisk,
persistSettings,
@@ -59,6 +59,25 @@ The host dispatcher restricts tunneled traffic to explicit path allowlists (one
4. **Handshake.** Over that connection pair, client and host run the E2EE handshake and derive a shared encrypted channel the relay cannot read.
5. **Traffic.** All normal app traffic is multiplexed and encrypted through that channel. On the host, decrypted requests are dispatched to the local server over loopback; responses stream back encrypted. Reconnects re-establish a fresh channel and the app's existing retry machinery recovers.
## Candidate refresh (staying off the relay when direct works)
Pairing-payload transport candidates are a snapshot: when DHCP hands the host
machine a new LAN address, a device's saved direct candidate goes stale and the
device silently degrades to relay-only. To recover, an already-paired client can
call `GET /api/client-auth/connection/candidates` (UI session or client bearer;
registered with the auth/access routes) over any live transport — including
through the tunnel — to learn the server's **current** LAN URLs plus the relay
candidate, and update its saved candidate set (mobile: `mobileConnections.ts`;
desktop: `desktopRelayRestore.ts`).
Identity gating: the response carries the stable `serverId` (base64url SHA-256 of
the public signing JWK — the same identity the relay routes by, exposed by the
relay service's `getServerId()` and echoed unauthenticated on `/health` and
`/api/version`). Clients ignore a refresh whose `serverId` does not match their
pinned relay identity, and verify `/health`'s `serverId` on a learned address
**before** sending their bearer token to it — a re-assigned LAN address may now
belong to a different machine.
## Two implementations, kept in sync
The E2EE and framing logic exists twice: TypeScript in `packages/ui/src/lib/relay/` (shared by the client and the normative reference) and a JavaScript mirror in this module (the host, which is plain JS ESM). They **must stay byte-compatible** — a client encrypted by one must decrypt on the other. A cross-compatibility test (`cross-compat.test.js`) imports the TS modules directly and exercises a full TS-client ↔ JS-host exchange. Any change to the wire format, frame codec, handshake, or batching must update both sides and keep that test green.
+24 -4
View File
@@ -16,10 +16,15 @@ import { exportPublicKeyJwk, generateEcdhKeyPair, importEcdhPrivateKey } from '.
const isJwkPair = (value) => Boolean(value && typeof value === 'object' && value.privateJwk && value.publicJwk);
/**
* @param {{ crypto: typeof import('node:crypto'), readSettingsFromDiskMigrated: () => Promise<object>, writeSettingsToDisk: (settings: object) => Promise<void> }} deps
* @param {{
* crypto: typeof import('node:crypto'),
* readSettingsFromDiskMigrated: () => Promise<object>,
* writeSettingsToDisk: (settings: object) => Promise<void>,
* readSettingsStrict?: () => Promise<object>,
* }} deps
*/
export const createRelayIdentityRuntime = (deps) => {
const { crypto, readSettingsFromDiskMigrated, writeSettingsToDisk } = deps;
const { crypto, readSettingsFromDiskMigrated, writeSettingsToDisk, readSettingsStrict } = deps;
let cachedIdentity = null;
@@ -29,10 +34,25 @@ export const createRelayIdentityRuntime = (deps) => {
if (isJwkPair(existing)) {
return existing;
}
// Same regeneration gate as the signing key: never mint a replacement
// identity key off a swallowed read failure — a new encryption key breaks
// the E2EE trust anchor pinned by every paired device. Verify "missing" via
// the strict reader (throws on corrupt/unreadable) before generating.
let verifiedSettings = settings;
if (readSettingsStrict) {
verifiedSettings = await readSettingsStrict();
const verified = verifiedSettings?.relayEncryptionKey;
if (isJwkPair(verified)) {
return verified;
}
}
// Loud on purpose: a new encryption key invalidates the E2EE trust anchor of
// every paired device. Expected exactly once, on first relay use.
console.warn('[relay-identity] Generating NEW relay encryption keypair (E2EE trust anchor changes; previously paired devices must re-pair)');
const keyPair = await generateEcdhKeyPair();
const privateJwk = await globalThis.crypto.subtle.exportKey('jwk', keyPair.privateKey);
const publicJwk = await exportPublicKeyJwk(keyPair.publicKey);
await writeSettingsToDisk({ ...settings, relayEncryptionKey: { privateJwk, publicJwk } });
await writeSettingsToDisk({ ...settings, ...(verifiedSettings || {}), relayEncryptionKey: { privateJwk, publicJwk } });
return { privateJwk, publicJwk };
};
@@ -46,7 +66,7 @@ export const createRelayIdentityRuntime = (deps) => {
*/
const getRelayIdentity = async () => {
if (cachedIdentity) return cachedIdentity;
const signing = await getOrCreateRelaySigningKeypair({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk });
const signing = await getOrCreateRelaySigningKeypair({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk, readSettingsStrict });
const serverId = deriveServerId({ crypto }, signing.publicJwk);
const encryption = await getOrCreateEncryptionKeypair();
const hostEncPrivateKey = await importEcdhPrivateKey(encryption.privateJwk);
+14 -1
View File
@@ -58,13 +58,16 @@ export const createRelayService = ({
crypto,
readSettingsFromDiskMigrated,
writeSettingsToDisk,
// Strict settings reader (throws on corrupt/unreadable) gating identity
// regeneration — see identity.js/signing-key.js.
readSettingsStrict,
getLocalPort,
// Returns true when any paired device or pending pairing session uses the
// relay transport. The relay lifecycle is driven purely by this demand.
hasRelayDemand = async () => false,
logger = console,
}) => {
const identityRuntime = createRelayIdentityRuntime({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk });
const identityRuntime = createRelayIdentityRuntime({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk, readSettingsStrict });
let hostClient = null;
let status = { state: 'disabled', lastError: null, connectedClients: 0 };
@@ -145,6 +148,15 @@ export const createRelayService = ({
}
};
// Stable server identity (base64url SHA-256 of the canonical public signing
// JWK). Derived from a public key, so it is not a secret; clients use it to
// verify that a learned/probed address belongs to this server before trusting
// it. Independent of whether the relay host is currently enabled.
const getServerId = async () => {
const identity = await identityRuntime.getRelayIdentity();
return identity.serverId;
};
const getStatus = async () => {
const config = await readConfig();
const identity = await identityRuntime.getRelayIdentity();
@@ -241,6 +253,7 @@ export const createRelayService = ({
reconcile,
stop,
getStatus,
getServerId,
getPairingCandidate,
ensureEnabledForPairing,
};
+30 -7
View File
@@ -6,22 +6,45 @@
// serverId must stay stable because push token binding depends on it.
/**
* @param {{ crypto: typeof import('node:crypto'), readSettingsFromDiskMigrated: () => Promise<object>, writeSettingsToDisk: (settings: object) => Promise<void> }} deps
* @param {{
* crypto: typeof import('node:crypto'),
* readSettingsFromDiskMigrated: () => Promise<object>,
* writeSettingsToDisk: (settings: object) => Promise<void>,
* readSettingsStrict?: () => Promise<object>,
* }} deps
* @returns {Promise<{ privateKey: import('node:crypto').KeyObject, publicJwk: JsonWebKey }>}
*/
export const getOrCreateRelaySigningKeypair = async ({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk }) => {
export const getOrCreateRelaySigningKeypair = async ({ crypto, readSettingsFromDiskMigrated, writeSettingsToDisk, readSettingsStrict }) => {
const toKeypair = (stored) => ({
privateKey: crypto.createPrivateKey({ key: stored.privateJwk, format: 'jwk' }),
publicJwk: stored.publicJwk,
});
const settings = await readSettingsFromDiskMigrated();
const existing = settings?.relaySigningKey;
if (existing && existing.privateJwk && existing.publicJwk) {
return {
privateKey: crypto.createPrivateKey({ key: existing.privateJwk, format: 'jwk' }),
publicJwk: existing.publicJwk,
};
return toKeypair(existing);
}
// Regeneration gate: the lenient settings reader maps read failures to `{}`,
// indistinguishable from "first run". Minting a new keypair changes serverId,
// which orphans every paired device and push binding AND the write below would
// clobber the settings file with the empty spread. Re-verify with the strict
// reader (throws on corrupt/unreadable) before generating; if it finds the
// key the lenient read lost, use it and generate nothing.
let verifiedSettings = settings;
if (readSettingsStrict) {
verifiedSettings = await readSettingsStrict();
const verified = verifiedSettings?.relaySigningKey;
if (verified && verified.privateJwk && verified.publicJwk) {
return toKeypair(verified);
}
}
// Loud on purpose: a new signing key means a new serverId — every previously
// paired device and push binding is orphaned. Expected exactly once, on first run.
console.warn('[relay-identity] Generating NEW relay signing keypair (serverId changes; previously paired devices must re-pair)');
const { privateKey, publicKey } = crypto.generateKeyPairSync('ec', { namedCurve: 'P-256' });
const privateJwk = privateKey.export({ format: 'jwk' });
const publicJwk = publicKey.export({ format: 'jwk' });
await writeSettingsToDisk({ ...settings, relaySigningKey: { privateJwk, publicJwk } });
await writeSettingsToDisk({ ...settings, ...(verifiedSettings || {}), relaySigningKey: { privateJwk, publicJwk } });
return { privateKey, publicJwk };
};