LibreChat/api/server/middleware/limiters/sttLimiters.js
Danny Avila 37964975c1
🤖 refactor: Improve Agents Memory Usage, Bump Keyv, Grok 3 (#6850)
* chore: remove unused redis file

* chore: bump keyv dependencies, and update related imports

* refactor: Implement IoRedis client for rate limiting across middleware, as node-redis via keyv not compatible

* fix: Set max listeners to expected amount

* WIP: memory improvements

* refactor: Simplify getAbortData assignment in createAbortController

* refactor: Update getAbortData to use WeakRef for content management

* WIP: memory improvements in agent chat requests

* refactor: Enhance memory management with finalization registry and cleanup functions

* refactor: Simplify domainParser calls by removing unnecessary request parameter

* refactor: Update parameter types for action tools and agent loading functions to use minimal configs

* refactor: Simplify domainParser tests by removing unnecessary request parameter

* refactor: Simplify domainParser call by removing unnecessary request parameter

* refactor: Enhance client disposal by nullifying additional properties to improve memory management

* refactor: Improve title generation by adding abort controller and timeout handling, consolidate request cleanup

* refactor: Update checkIdleConnections to skip current user when checking for idle connections if passed

* refactor: Update createMCPTool to derive userId from config and handle abort signals

* refactor: Introduce createTokenCounter function and update tokenCounter usage; enhance disposeClient to reset Graph values

* refactor: Update getMCPManager to accept userId parameter for improved idle connection handling

* refactor: Extract logToolError function for improved error handling in AgentClient

* refactor: Update disposeClient to clear handlerRegistry and graphRunnable references in client.run

* refactor: Extract createHandleNewToken function to streamline token handling in initializeClient

* chore: bump @librechat/agents

* refactor: Improve timeout handling in addTitle function for better error management

* refactor: Introduce createFetch instead of using class method

* refactor: Enhance client disposal and request data handling in AskController and EditController

* refactor: Update import statements for AnthropicClient and OpenAIClient to use specific paths

* refactor: Use WeakRef for response handling in SplitStreamHandler to prevent memory leaks

* refactor: Simplify client disposal and rename getReqData to processReqData in AskController and EditController

* refactor: Improve logging structure and parameter handling in OpenAIClient

* refactor: Remove unused GraphEvents and improve stream event handling in AnthropicClient and OpenAIClient

* refactor: Simplify client initialization in AskController and EditController

* refactor: Remove unused mock functions and implement in-memory store for KeyvMongo

* chore: Update dependencies in package-lock.json to latest versions

* refactor: Await token usage recording in OpenAIClient to ensure proper async handling

* refactor: Remove handleAbort route from multiple endpoints and enhance client disposal logic

* refactor: Enhance abort controller logic by managing abortKey more effectively

* refactor: Add newConversation handling in useEventHandlers for improved conversation management

* fix: dropparams

* refactor: Use optional chaining for safer access to request properties in BaseClient

* refactor: Move client disposal and request data processing logic to cleanup module for better organization

* refactor: Remove aborted request check from addTitle function for cleaner logic

* feat: Add Grok 3 model pricing and update tests for new models

* chore: Remove trace warnings and inspect flags from backend start script used for debugging

* refactor: Replace user identifier handling with userId for consistency across controllers, use UserId in clientRegistry

* refactor: Enhance client disposal logic to prevent memory leaks by clearing additional references

* chore: Update @librechat/agents to version 2.4.14 in package.json and package-lock.json
2025-04-12 18:46:36 -04:00

90 lines
2.7 KiB
JavaScript

const rateLimit = require('express-rate-limit');
const { RedisStore } = require('rate-limit-redis');
const { ViolationTypes } = require('librechat-data-provider');
const ioredisClient = require('~/cache/ioredisClient');
const logViolation = require('~/cache/logViolation');
const { isEnabled } = require('~/server/utils');
const { logger } = require('~/config');
const getEnvironmentVariables = () => {
const STT_IP_MAX = parseInt(process.env.STT_IP_MAX) || 100;
const STT_IP_WINDOW = parseInt(process.env.STT_IP_WINDOW) || 1;
const STT_USER_MAX = parseInt(process.env.STT_USER_MAX) || 50;
const STT_USER_WINDOW = parseInt(process.env.STT_USER_WINDOW) || 1;
const sttIpWindowMs = STT_IP_WINDOW * 60 * 1000;
const sttIpMax = STT_IP_MAX;
const sttIpWindowInMinutes = sttIpWindowMs / 60000;
const sttUserWindowMs = STT_USER_WINDOW * 60 * 1000;
const sttUserMax = STT_USER_MAX;
const sttUserWindowInMinutes = sttUserWindowMs / 60000;
return {
sttIpWindowMs,
sttIpMax,
sttIpWindowInMinutes,
sttUserWindowMs,
sttUserMax,
sttUserWindowInMinutes,
};
};
const createSTTHandler = (ip = true) => {
const { sttIpMax, sttIpWindowInMinutes, sttUserMax, sttUserWindowInMinutes } =
getEnvironmentVariables();
return async (req, res) => {
const type = ViolationTypes.STT_LIMIT;
const errorMessage = {
type,
max: ip ? sttIpMax : sttUserMax,
limiter: ip ? 'ip' : 'user',
windowInMinutes: ip ? sttIpWindowInMinutes : sttUserWindowInMinutes,
};
await logViolation(req, res, type, errorMessage);
res.status(429).json({ message: 'Too many STT requests. Try again later' });
};
};
const createSTTLimiters = () => {
const { sttIpWindowMs, sttIpMax, sttUserWindowMs, sttUserMax } = getEnvironmentVariables();
const ipLimiterOptions = {
windowMs: sttIpWindowMs,
max: sttIpMax,
handler: createSTTHandler(),
};
const userLimiterOptions = {
windowMs: sttUserWindowMs,
max: sttUserMax,
handler: createSTTHandler(false),
keyGenerator: function (req) {
return req.user?.id; // Use the user ID or NULL if not available
},
};
if (isEnabled(process.env.USE_REDIS) && ioredisClient) {
logger.debug('Using Redis for STT rate limiters.');
const sendCommand = (...args) => ioredisClient.call(...args);
const ipStore = new RedisStore({
sendCommand,
prefix: 'stt_ip_limiter:',
});
const userStore = new RedisStore({
sendCommand,
prefix: 'stt_user_limiter:',
});
ipLimiterOptions.store = ipStore;
userLimiterOptions.store = userStore;
}
const sttIpLimiter = rateLimit(ipLimiterOptions);
const sttUserLimiter = rateLimit(userLimiterOptions);
return { sttIpLimiter, sttUserLimiter };
};
module.exports = createSTTLimiters;