LibreChat/api/server/experimental.js
Dustin Healy 0e14d91ed9
⏱️ fix: Compile admin file-config MIME patterns on a linear-time engine (ReDoS) (#14555)
* ⏱️ fix: Compile admin file-config MIME patterns on a linear-time engine

convertStringsToRegex compiled admin-configured supportedMimeTypes with the native RegExp engine, and checkType runs those patterns against an uploaded file's Content-Type on the server event loop, so a catastrophic-backtracking pattern in fileConfig could ReDoS the whole process on upload.

The MIME-pattern compiler is now swappable. It defaults to native RegExp, which browser builds keep so no engine is added to the client bundle, and the server injects a linear-time engine (RE2JS) at startup. Only test is ever called on these matchers, so the shared type widens to a structural RegexLike with no behavior change for valid patterns. The browser stays on native because a client-side stall would only affect that one tab.

* ⏱️ fix: Wire the linear MIME compiler in the experimental entry point

api/server/experimental.js mounts the same upload routes and calls mergeFileConfig but never set the linear-time compiler, so admin MIME patterns still compiled with native RegExp there. Mirror the setup, and widen the client-side supportedMimeTypes type to the shared RegexLike so the browser typechecks against the same structural matcher.

* 🧹 refactor: Configure the file-config linear engine from a shared helper

Move the RE2 wiring out of both JS server entry points into a single
configureFileConfigRegexEngine helper exported from @librechat/api, so /api stays a thin
caller and the setup no longer has to be kept in sync across index.js and experimental.js.

Also warn loudly when compiling an endpoint's supportedMimeTypes drops every pattern (an
empty allowlist would reject all uploads), and correct the isMimeTypeSupported docstring to
say RegexLike rather than RegExp.

* fix: fail closed when every MIME pattern fails to compile

convertStringsToRegex returned [] when all configured patterns failed to
compile, and filter.ts reads an empty allowlist as no restriction, so a
restrictive config whose patterns all fail allowed every attachment.
Return a single reject-all matcher instead so every consumer fails closed.
2026-08-06 09:05:42 -04:00

587 lines
20 KiB
JavaScript

require('dotenv').config();
const fs = require('fs');
const path = require('path');
require('module-alias')({ base: path.resolve(__dirname, '..') });
const cluster = require('cluster');
const Redis = require('ioredis');
const cors = require('cors');
const axios = require('axios');
const express = require('express');
const passport = require('passport');
const compression = require('compression');
const cookieParser = require('cookie-parser');
const { logger, runAsSystem } = require('@librechat/data-schemas');
const mongoSanitize = require('express-mongo-sanitize');
const {
isEnabled,
apiNotFound,
ErrorController,
QUERY_DEVTOOLS_HEADER,
performStartupChecks,
handleJsonParseError,
initializeFileStorage,
loadToolApprovalHooks,
maybeInjectQueryDevtoolsBootstrap,
preAuthTenantMiddleware,
requestContextMiddleware,
configureServerTimeouts,
configureMessageFilterRegexValidator,
configureFileConfigRegexEngine,
} = require('@librechat/api');
const { connectDb, indexSync } = require('~/db');
const initializeOAuthReconnectManager = require('./services/initializeOAuthReconnectManager');
const { capabilityContextMiddleware } = require('./middleware/roles/capabilities');
const createValidateImageRequest = require('./middleware/validateImageRequest');
const { startExpiredFileSweep } = require('./services/Files/process');
const { initializeGitHubSkillSync } = require('./services/Skills/sync');
const { jwtLogin, ldapLogin, passportLogin } = require('~/strategies');
const { updateInterfacePermissions: updateInterfacePerms } = require('@librechat/api');
const {
getRoleByName,
updateAccessPermissions,
seedDatabase,
sweepOrphanedPreviews,
} = require('~/models');
const { checkMigrations } = require('./services/start/migration');
const initializeMCPs = require('./services/initializeMCPs');
const configureSocialLogins = require('./socialLogins');
const createSpaFallback = require('./utils/fallback');
const { getAppConfig } = require('./services/Config');
const staticCache = require('./utils/staticCache');
const optionalJwtAuth = require('./middleware/optionalJwtAuth');
const noIndex = require('./middleware/noIndex');
const routes = require('./routes');
/** Route admin file-config MIME patterns through a linear-time engine (ReDoS-safe) on upload. */
configureFileConfigRegexEngine();
/** Reject messageFilter PII patterns the RE2 runtime engine cannot compile, at config load. */
configureMessageFilterRegexValidator();
const { PORT, HOST, ALLOW_SOCIAL_LOGIN, DISABLE_COMPRESSION, TRUST_PROXY } = process.env ?? {};
/** Allow PORT=0 to be used for automatic free port assignment */
const port = isNaN(Number(PORT)) ? 3080 : Number(PORT);
const host = HOST || 'localhost';
const trusted_proxy = Number(TRUST_PROXY) || 1;
/** Number of worker processes to spawn (simulating multiple pods) */
const workers = Number(process.env.CLUSTER_WORKERS) || 4;
/** Helper to wrap log messages for better visibility */
const wrapLogMessage = (msg) => {
return `\n${'='.repeat(50)}\n${msg}\n${'='.repeat(50)}`;
};
/**
* Flushes the Redis cache on startup
* This ensures a clean state for testing multi-pod MCP connection issues
*/
const flushRedisCache = async () => {
/** Skip cache flush if Redis is not enabled */
if (!isEnabled(process.env.USE_REDIS)) {
logger.info('Redis is not enabled, skipping cache flush');
return;
}
const redisConfig = {
host: process.env.REDIS_HOST || 'localhost',
port: process.env.REDIS_PORT || 6379,
};
if (process.env.REDIS_PASSWORD) {
redisConfig.password = process.env.REDIS_PASSWORD;
}
/** Handle Redis Cluster configuration */
if (isEnabled(process.env.USE_REDIS_CLUSTER) || process.env.REDIS_URI?.includes(',')) {
logger.info('Detected Redis Cluster configuration');
const uris = process.env.REDIS_URI?.split(',').map((uri) => {
const url = new URL(uri.trim());
return {
host: url.hostname,
port: parseInt(url.port || '6379', 10),
};
});
const redis = new Redis.Cluster(uris, {
redisOptions: {
password: process.env.REDIS_PASSWORD,
},
});
try {
logger.info('Attempting to connect to Redis Cluster...');
await redis.ping();
logger.info('Connected to Redis Cluster. Executing flushall...');
const result = await Promise.race([
redis.flushall(),
new Promise((_, reject) => setTimeout(() => reject(new Error('Flush timeout')), 10000)),
]);
logger.info('Redis Cluster cache flushed successfully', { result });
} catch (err) {
logger.error('Error while flushing Redis Cluster cache:', err);
throw err;
} finally {
redis.disconnect();
}
return;
}
/** Handle single Redis instance */
const redis = new Redis(redisConfig);
try {
logger.info('Attempting to connect to Redis...');
await redis.ping();
logger.info('Connected to Redis. Executing flushall...');
const result = await Promise.race([
redis.flushall(),
new Promise((_, reject) => setTimeout(() => reject(new Error('Flush timeout')), 5000)),
]);
logger.info('Redis cache flushed successfully', { result });
} catch (err) {
logger.error('Error while flushing Redis cache:', err);
throw err;
} finally {
redis.disconnect();
}
};
/**
* Master process
* Manages worker processes and handles graceful shutdowns
*/
if (cluster.isMaster) {
logger.info(wrapLogMessage(`Master ${process.pid} is starting...`));
logger.info(`Spawning ${workers} workers to simulate multi-pod environment`);
let activeWorkers = 0;
const listeningWorkers = new Set();
let retentionSweepWorkerId = null;
const startTime = Date.now();
const assignRetentionSweepWorker = () => {
if (retentionSweepWorkerId && cluster.workers[retentionSweepWorkerId]) {
return;
}
const connectedWorkers = Object.values(cluster.workers).filter(
(worker) => worker && worker.isConnected(),
);
const availableWorkers = connectedWorkers.filter((worker) => listeningWorkers.has(worker.id));
const workerPool = availableWorkers.length > 0 ? availableWorkers : connectedWorkers;
const retentionSweepWorker = workerPool[workerPool.length - 1];
if (!retentionSweepWorker) {
return;
}
retentionSweepWorkerId = retentionSweepWorker.id;
logger.info(
wrapLogMessage(`Worker ${retentionSweepWorker.process.pid} assigned to file-retention sweep`),
);
retentionSweepWorker.send({ type: 'file-retention-sweep-worker' });
};
/** Flush Redis cache before starting workers */
flushRedisCache()
.then(() => {
logger.info('Cache flushed, forking workers...');
for (let i = 0; i < workers; i++) {
cluster.fork();
}
})
.catch((err) => {
logger.error('Unable to flush Redis cache, not forking workers:', err);
process.exit(1);
});
/** Track worker lifecycle */
cluster.on('online', (worker) => {
activeWorkers++;
const uptime = ((Date.now() - startTime) / 1000).toFixed(2);
logger.info(
`Worker ${worker.process.pid} is online (${activeWorkers}/${workers}) after ${uptime}s`,
);
/** Assign one worker for process-wide background jobs */
if (activeWorkers === workers) {
logger.info(wrapLogMessage(`All ${workers} workers are online`));
}
});
cluster.on('listening', (worker) => {
listeningWorkers.add(worker.id);
if (
listeningWorkers.size === workers ||
(!retentionSweepWorkerId && activeWorkers >= workers)
) {
assignRetentionSweepWorker();
}
});
cluster.on('exit', (worker, code, signal) => {
activeWorkers--;
listeningWorkers.delete(worker.id);
if (worker.id === retentionSweepWorkerId) {
retentionSweepWorkerId = null;
assignRetentionSweepWorker();
}
logger.error(
`Worker ${worker.process.pid} died (${activeWorkers}/${workers}). Code: ${code}, Signal: ${signal}`,
);
logger.info('Starting a new worker to replace it...');
cluster.fork();
});
/** Graceful shutdown on SIGTERM/SIGINT */
const shutdown = () => {
logger.info('Master received shutdown signal, terminating workers...');
for (const id in cluster.workers) {
cluster.workers[id].kill();
}
setTimeout(() => {
logger.info('Forcing shutdown after timeout');
process.exit(0);
}, 10000);
};
process.on('SIGTERM', shutdown);
process.on('SIGINT', shutdown);
} else {
/**
* Worker process
* Each worker runs a full Express server instance
*/
const app = express();
/**
* The master may assign the sweep worker before or after this worker has
* loaded app config. These flags join the IPC assignment with config
* availability and ensure the background sweep starts only once.
*/
let shouldStartExpiredFileSweep = false;
let expiredFileSweepOptions = null;
let expiredFileSweepStarted = false;
const startExpiredFileSweepOnce = () => {
if (!shouldStartExpiredFileSweep || expiredFileSweepStarted || !expiredFileSweepOptions) {
return;
}
expiredFileSweepStarted = true;
startExpiredFileSweep(expiredFileSweepOptions);
};
/** Handle inter-process messages from master */
process.on('message', (msg) => {
if (msg.type === 'file-retention-sweep-worker') {
shouldStartExpiredFileSweep = true;
logger.info(wrapLogMessage(`Worker ${process.pid} is assigned file-retention sweep`));
startExpiredFileSweepOnce();
}
});
const startServer = async () => {
logger.info(`Worker ${process.pid} initializing...`);
if (typeof Bun !== 'undefined') {
axios.defaults.headers.common['Accept-Encoding'] = 'gzip';
}
/** Connect to MongoDB */
await connectDb();
logger.info(`Worker ${process.pid}: Connected to MongoDB`);
/** Background index sync (non-blocking) */
indexSync().catch((err) => {
logger.error(`[Worker ${process.pid}][indexSync] Background sync failed:`, err);
});
app.disable('x-powered-by');
app.set('trust proxy', trusted_proxy);
/** Seed database (idempotent) */
await seedDatabase();
/* Mirrors `server/index.js`; `runAsSystem` for tenant-isolated File. */
runAsSystem(sweepOrphanedPreviews).catch((err) => {
logger.error('[sweepOrphanedPreviews] Background sweep failed:', err);
});
/** Initialize app configuration */
const appConfig = await getAppConfig();
initializeFileStorage(appConfig);
initializeGitHubSkillSync(appConfig);
// Register configured tool-approval policy hooks (mirrors the standard startup path).
// Honors the `enabled` kill switch; hooks are base-config-only, registered process-wide.
// Read from the BASE config specifically — `appConfig` above (getAppConfig() with no
// principal) still merges DB `__base__` overrides, which must not drive which hook
// modules load in every worker (matches api/server/index.js's baseOnly usage).
const baseAppConfig = await getAppConfig({ baseOnly: true });
const toolApproval = baseAppConfig?.endpoints?.agents?.toolApproval;
await loadToolApprovalHooks(toolApproval?.enabled ? toolApproval.hooks : undefined, {
basePath: path.resolve(__dirname, '../..'),
});
expiredFileSweepOptions = { appConfig, loadAppConfig: getAppConfig };
startExpiredFileSweepOnce();
await performStartupChecks(appConfig);
await updateInterfacePerms({ appConfig, getRoleByName, updateAccessPermissions });
/** Load index.html for SPA serving */
const indexPath = path.join(appConfig.paths.dist, 'index.html');
let indexHTML = fs.readFileSync(indexPath, 'utf8');
/** Support serving in subdirectory if DOMAIN_CLIENT is set */
if (process.env.DOMAIN_CLIENT) {
const clientUrl = new URL(process.env.DOMAIN_CLIENT);
const baseHref = clientUrl.pathname.endsWith('/')
? clientUrl.pathname
: `${clientUrl.pathname}/`;
if (baseHref !== '/') {
logger.info(`Setting base href to ${baseHref}`);
indexHTML = indexHTML.replace(/base href="\/"/, `base href="${baseHref}"`);
}
}
const sendIndexHtml = (req, res) => {
res.set({
'Cache-Control': process.env.INDEX_CACHE_CONTROL || 'no-cache, no-store, must-revalidate',
Pragma: process.env.INDEX_PRAGMA || 'no-cache',
Expires: process.env.INDEX_EXPIRES || '0',
});
res.vary(QUERY_DEVTOOLS_HEADER);
const lang = req.cookies.lang || req.headers['accept-language']?.split(',')[0] || 'en-US';
const saneLang = lang.replace(/"/g, '&quot;');
let updatedIndexHtml = indexHTML.replace(/lang="en-US"/g, `lang="${saneLang}"`);
updatedIndexHtml = maybeInjectQueryDevtoolsBootstrap(updatedIndexHtml, req);
res.type('html');
res.send(updatedIndexHtml);
};
/** Health check endpoint */
app.get('/health', (_req, res) => res.status(200).send('OK'));
/** Middleware */
app.use(requestContextMiddleware);
app.use(noIndex);
app.use(express.json({ limit: '3mb' }));
app.use(express.urlencoded({ extended: true, limit: '3mb' }));
app.use(handleJsonParseError);
/**
* Express 5 Compatibility: Make req.query writable for mongoSanitize
* In Express 5, req.query is read-only by default, but express-mongo-sanitize needs to modify it
*/
app.use((req, _res, next) => {
Object.defineProperty(req, 'query', {
...Object.getOwnPropertyDescriptor(req, 'query'),
value: req.query,
writable: true,
});
next();
});
app.use(mongoSanitize());
app.use(cors());
app.use(cookieParser());
if (!isEnabled(DISABLE_COMPRESSION)) {
app.use(compression());
} else {
logger.warn('Response compression has been disabled via DISABLE_COMPRESSION.');
}
app.get('/index.html', sendIndexHtml);
app.use(staticCache(appConfig.paths.dist));
app.use(staticCache(appConfig.paths.fonts));
app.use(staticCache(appConfig.paths.assets));
if (!ALLOW_SOCIAL_LOGIN) {
logger.warn('Social logins are disabled. Set ALLOW_SOCIAL_LOGIN=true to enable them.');
}
/** OAUTH */
app.use(passport.initialize());
passport.use(jwtLogin());
passport.use(passportLogin());
/** LDAP Auth */
if (process.env.LDAP_URL && process.env.LDAP_USER_SEARCH_BASE) {
passport.use(ldapLogin);
}
if (isEnabled(ALLOW_SOCIAL_LOGIN)) {
await configureSocialLogins(app);
}
app.use(capabilityContextMiddleware);
/** Routes */
app.use('/oauth', routes.oauth);
app.use('/api/auth', routes.auth);
app.use('/api/admin', routes.adminAuth);
app.use('/api/admin/skills', routes.adminSkills);
app.use('/api/actions', routes.actions);
app.use('/api/keys', routes.keys);
app.use('/api/api-keys', routes.apiKeys);
app.use('/api/user', routes.user);
app.use('/api/search', routes.search);
app.use('/api/messages', routes.messages);
app.use('/api/convos', routes.convos);
app.use('/api/presets', routes.presets);
app.use('/api/projects', routes.projects);
app.use('/api/prompts', routes.prompts);
app.use('/api/skills', routes.skills);
app.use('/api/categories', routes.categories);
app.use('/api/endpoints', routes.endpoints);
app.use('/api/balance', routes.balance);
app.use('/api/models', routes.models);
app.use('/api/config', preAuthTenantMiddleware, optionalJwtAuth, routes.config);
app.use('/api/assistants', routes.assistants);
app.use('/api/files', await routes.files.initialize());
app.use('/images/', createValidateImageRequest(appConfig.secureImageLinks), routes.staticRoute);
app.use('/api/share', routes.share);
app.use('/api/roles', routes.roles);
app.use('/api/agents', routes.agents);
app.use('/api/banner', routes.banner);
app.use('/api/memories', routes.memories);
app.use('/api/permissions', routes.accessPermissions);
app.use('/api/tags', routes.tags);
app.use('/api/mcp', routes.mcp);
/** 404 for unmatched API routes */
app.use('/api', apiNotFound);
/** SPA fallback - serve index.html for all unmatched routes */
app.use(createSpaFallback(sendIndexHtml));
/** Error handler (must be last - Express identifies error middleware by its 4-arg signature) */
app.use(ErrorController);
/** Start listening on shared port (cluster will distribute connections) */
const server = app.listen(port, host, async (err) => {
if (err) {
logger.error(`Worker ${process.pid} failed to start server:`, err);
process.exit(1);
}
logger.info(
`Worker ${process.pid} started: Server listening at http://${
host == '0.0.0.0' ? 'localhost' : host
}:${port}`,
);
/**
* The listen callback is async, so any rejection from these awaits
* would otherwise be detached from `startServer().catch(...)`. Without
* explicit handling, the global `unhandledRejection` handler would
* swallow init failures and leave the worker listening but only
* partially initialized.
*/
try {
/** Initialize MCP servers and OAuth reconnection for this worker */
await initializeMCPs();
await initializeOAuthReconnectManager();
await checkMigrations();
} catch (initErr) {
logger.error(`Worker ${process.pid} post-listen initialization failed:`, initErr);
process.exit(1);
}
});
configureServerTimeouts(server);
logger.info(`Worker ${process.pid} HTTP server timeout configuration`, {
keepAliveTimeout: server.keepAliveTimeout,
keepAliveTimeoutBuffer: server.keepAliveTimeoutBuffer,
headersTimeout: server.headersTimeout,
requestTimeout: server.requestTimeout,
});
};
startServer().catch((err) => {
logger.error(`Failed to start worker ${process.pid}:`, err);
process.exit(1);
});
/** Export app for testing purposes (only available in worker processes) */
module.exports = app;
}
/**
* Uncaught exception handler
* Filters out known non-critical errors
*/
let messageCount = 0;
process.on('uncaughtException', (err) => {
if (!err.message.includes('fetch failed')) {
logger.error('There was an uncaught error:', err);
}
if (err.message && err.message?.toLowerCase()?.includes('abort')) {
logger.warn('There was an uncatchable abort error.');
return;
}
if (err.message.includes('GoogleGenerativeAI')) {
logger.warn(
'\n\n`GoogleGenerativeAI` errors cannot be caught due to an upstream issue, see: https://github.com/google-gemini/generative-ai-js/issues/303',
);
return;
}
if (err.message.includes('fetch failed')) {
if (messageCount === 0) {
logger.warn('Meilisearch error, search will be disabled');
messageCount++;
}
return;
}
if (err.message.includes('OpenAIError') || err.message.includes('ChatCompletionMessage')) {
logger.error(
'\n\nAn Uncaught `OpenAIError` error may be due to your reverse-proxy setup or stream configuration, or a bug in the `openai` node package.',
);
return;
}
if (err.stack && err.stack.includes('@librechat/agents')) {
logger.error(
'\n\nAn error occurred in the agents system. The error has been logged and the app will continue running.',
{
message: err.message,
stack: err.stack,
},
);
return;
}
process.exit(1);
});
/**
* Unhandled promise rejection handler.
*
* Node 15+ terminates the process by default when a promise rejection is
* unhandled. MCP OAuth reconnect storms and streamable-HTTP transport resets
* can produce transient fire-and-forget rejections (ECONNRESET, token refresh
* races) that are recoverable — the server should log and keep serving other
* requests rather than silently crash under load.
*
* Non-Error reasons are forwarded as-is so structured payloads (e.g.
* `{ code: "ECONNRESET", errno: -104 }`) survive instead of being collapsed to
* "[object Object]" by `String()`.
*/
process.on('unhandledRejection', (reason) => {
if (reason instanceof Error) {
logger.error('Unhandled promise rejection. The app will continue running.', {
name: reason.name,
message: reason.message,
stack: reason.stack,
cause: reason.cause,
});
return;
}
logger.error('Unhandled promise rejection. The app will continue running.', { reason });
});