mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-16 16:30:15 +01:00
🤖 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
This commit is contained in:
parent
1e6b1b9554
commit
37964975c1
68 changed files with 1796 additions and 623 deletions
|
|
@ -1,5 +1,10 @@
|
|||
const { Constants } = require('librechat-data-provider');
|
||||
const { createAbortController, handleAbortError } = require('~/server/middleware');
|
||||
const {
|
||||
handleAbortError,
|
||||
createAbortController,
|
||||
cleanupAbortController,
|
||||
} = require('~/server/middleware');
|
||||
const { disposeClient, clientRegistry, requestDataMap } = require('~/server/cleanup');
|
||||
const { sendMessage } = require('~/server/utils');
|
||||
const { saveMessage } = require('~/models');
|
||||
const { logger } = require('~/config');
|
||||
|
|
@ -14,16 +19,22 @@ const AgentController = async (req, res, next, initializeClient, addTitle) => {
|
|||
} = req.body;
|
||||
|
||||
let sender;
|
||||
let abortKey;
|
||||
let userMessage;
|
||||
let promptTokens;
|
||||
let userMessageId;
|
||||
let responseMessageId;
|
||||
let userMessagePromise;
|
||||
let getAbortData;
|
||||
let client = null;
|
||||
// Initialize as an array
|
||||
let cleanupHandlers = [];
|
||||
|
||||
const newConvo = !conversationId;
|
||||
const user = req.user.id;
|
||||
const userId = req.user.id;
|
||||
|
||||
const getReqData = (data = {}) => {
|
||||
// Create handler to avoid capturing the entire parent scope
|
||||
let getReqData = (data = {}) => {
|
||||
for (let key in data) {
|
||||
if (key === 'userMessage') {
|
||||
userMessage = data[key];
|
||||
|
|
@ -36,30 +47,96 @@ const AgentController = async (req, res, next, initializeClient, addTitle) => {
|
|||
promptTokens = data[key];
|
||||
} else if (key === 'sender') {
|
||||
sender = data[key];
|
||||
} else if (key === 'abortKey') {
|
||||
abortKey = data[key];
|
||||
} else if (!conversationId && key === 'conversationId') {
|
||||
conversationId = data[key];
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// Create a function to handle final cleanup
|
||||
const performCleanup = () => {
|
||||
logger.debug('[AgentController] Performing cleanup');
|
||||
// Make sure cleanupHandlers is an array before iterating
|
||||
if (Array.isArray(cleanupHandlers)) {
|
||||
// Execute all cleanup handlers
|
||||
for (const handler of cleanupHandlers) {
|
||||
try {
|
||||
if (typeof handler === 'function') {
|
||||
handler();
|
||||
}
|
||||
} catch (e) {
|
||||
// Ignore cleanup errors
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Clean up abort controller
|
||||
if (abortKey) {
|
||||
logger.debug('[AgentController] Cleaning up abort controller');
|
||||
cleanupAbortController(abortKey);
|
||||
}
|
||||
|
||||
// Dispose client properly
|
||||
if (client) {
|
||||
disposeClient(client);
|
||||
}
|
||||
|
||||
// Clear all references
|
||||
client = null;
|
||||
getReqData = null;
|
||||
userMessage = null;
|
||||
getAbortData = null;
|
||||
endpointOption.agent = null;
|
||||
endpointOption = null;
|
||||
cleanupHandlers = null;
|
||||
userMessagePromise = null;
|
||||
|
||||
// Clear request data map
|
||||
if (requestDataMap.has(req)) {
|
||||
requestDataMap.delete(req);
|
||||
}
|
||||
logger.debug('[AgentController] Cleanup completed');
|
||||
};
|
||||
|
||||
try {
|
||||
/** @type {{ client: TAgentClient }} */
|
||||
const { client } = await initializeClient({ req, res, endpointOption });
|
||||
const result = await initializeClient({ req, res, endpointOption });
|
||||
client = result.client;
|
||||
|
||||
const getAbortData = () => ({
|
||||
sender,
|
||||
userMessage,
|
||||
promptTokens,
|
||||
conversationId,
|
||||
userMessagePromise,
|
||||
messageId: responseMessageId,
|
||||
content: client.getContentParts(),
|
||||
parentMessageId: overrideParentMessageId ?? userMessageId,
|
||||
});
|
||||
// Register client with finalization registry if available
|
||||
if (clientRegistry) {
|
||||
clientRegistry.register(client, { userId }, client);
|
||||
}
|
||||
|
||||
// Store request data in WeakMap keyed by req object
|
||||
requestDataMap.set(req, { client });
|
||||
|
||||
// Use WeakRef to allow GC but still access content if it exists
|
||||
const contentRef = new WeakRef(client.contentParts || []);
|
||||
|
||||
// Minimize closure scope - only capture small primitives and WeakRef
|
||||
getAbortData = () => {
|
||||
// Dereference WeakRef each time
|
||||
const content = contentRef.deref();
|
||||
|
||||
return {
|
||||
sender,
|
||||
content: content || [],
|
||||
userMessage,
|
||||
promptTokens,
|
||||
conversationId,
|
||||
userMessagePromise,
|
||||
messageId: responseMessageId,
|
||||
parentMessageId: overrideParentMessageId ?? userMessageId,
|
||||
};
|
||||
};
|
||||
|
||||
const { abortController, onStart } = createAbortController(req, res, getAbortData, getReqData);
|
||||
|
||||
res.on('close', () => {
|
||||
// Simple handler to avoid capturing scope
|
||||
const closeHandler = () => {
|
||||
logger.debug('[AgentController] Request closed');
|
||||
if (!abortController) {
|
||||
return;
|
||||
|
|
@ -71,10 +148,19 @@ const AgentController = async (req, res, next, initializeClient, addTitle) => {
|
|||
|
||||
abortController.abort();
|
||||
logger.debug('[AgentController] Request aborted on close');
|
||||
};
|
||||
|
||||
res.on('close', closeHandler);
|
||||
cleanupHandlers.push(() => {
|
||||
try {
|
||||
res.removeListener('close', closeHandler);
|
||||
} catch (e) {
|
||||
// Ignore
|
||||
}
|
||||
});
|
||||
|
||||
const messageOptions = {
|
||||
user,
|
||||
user: userId,
|
||||
onStart,
|
||||
getReqData,
|
||||
conversationId,
|
||||
|
|
@ -83,69 +169,103 @@ const AgentController = async (req, res, next, initializeClient, addTitle) => {
|
|||
overrideParentMessageId,
|
||||
progressOptions: {
|
||||
res,
|
||||
// parentMessageId: overrideParentMessageId || userMessageId,
|
||||
},
|
||||
};
|
||||
|
||||
let response = await client.sendMessage(text, messageOptions);
|
||||
response.endpoint = endpointOption.endpoint;
|
||||
|
||||
const { conversation = {} } = await client.responsePromise;
|
||||
// Extract what we need and immediately break reference
|
||||
const messageId = response.messageId;
|
||||
const endpoint = endpointOption.endpoint;
|
||||
response.endpoint = endpoint;
|
||||
|
||||
// Store database promise locally
|
||||
const databasePromise = response.databasePromise;
|
||||
delete response.databasePromise;
|
||||
|
||||
// Resolve database-related data
|
||||
const { conversation: convoData = {} } = await databasePromise;
|
||||
const conversation = { ...convoData };
|
||||
conversation.title =
|
||||
conversation && !conversation.title ? null : conversation?.title || 'New Chat';
|
||||
|
||||
if (req.body.files && client.options.attachments) {
|
||||
// Process files if needed
|
||||
if (req.body.files && client.options?.attachments) {
|
||||
userMessage.files = [];
|
||||
const messageFiles = new Set(req.body.files.map((file) => file.file_id));
|
||||
for (let attachment of client.options.attachments) {
|
||||
if (messageFiles.has(attachment.file_id)) {
|
||||
userMessage.files.push(attachment);
|
||||
userMessage.files.push({ ...attachment });
|
||||
}
|
||||
}
|
||||
delete userMessage.image_urls;
|
||||
}
|
||||
|
||||
// Only send if not aborted
|
||||
if (!abortController.signal.aborted) {
|
||||
// Create a new response object with minimal copies
|
||||
const finalResponse = { ...response };
|
||||
|
||||
sendMessage(res, {
|
||||
final: true,
|
||||
conversation,
|
||||
title: conversation.title,
|
||||
requestMessage: userMessage,
|
||||
responseMessage: response,
|
||||
responseMessage: finalResponse,
|
||||
});
|
||||
res.end();
|
||||
|
||||
if (!client.savedMessageIds.has(response.messageId)) {
|
||||
// Save the message if needed
|
||||
if (client.savedMessageIds && !client.savedMessageIds.has(messageId)) {
|
||||
await saveMessage(
|
||||
req,
|
||||
{ ...response, user },
|
||||
{ ...finalResponse, user: userId },
|
||||
{ context: 'api/server/controllers/agents/request.js - response end' },
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Save user message if needed
|
||||
if (!client.skipSaveUserMessage) {
|
||||
await saveMessage(req, userMessage, {
|
||||
context: 'api/server/controllers/agents/request.js - don\'t skip saving user message',
|
||||
});
|
||||
}
|
||||
|
||||
// Add title if needed - extract minimal data
|
||||
if (addTitle && parentMessageId === Constants.NO_PARENT && newConvo) {
|
||||
addTitle(req, {
|
||||
text,
|
||||
response,
|
||||
response: { ...response },
|
||||
client,
|
||||
});
|
||||
})
|
||||
.then(() => {
|
||||
logger.debug('[AgentController] Title generation started');
|
||||
})
|
||||
.catch((err) => {
|
||||
logger.error('[AgentController] Error in title generation', err);
|
||||
})
|
||||
.finally(() => {
|
||||
logger.debug('[AgentController] Title generation completed');
|
||||
performCleanup();
|
||||
});
|
||||
} else {
|
||||
performCleanup();
|
||||
}
|
||||
} catch (error) {
|
||||
// Handle error without capturing much scope
|
||||
handleAbortError(res, req, error, {
|
||||
conversationId,
|
||||
sender,
|
||||
messageId: responseMessageId,
|
||||
parentMessageId: overrideParentMessageId ?? userMessageId ?? parentMessageId,
|
||||
}).catch((err) => {
|
||||
logger.error('[api/server/controllers/agents/request] Error in `handleAbortError`', err);
|
||||
});
|
||||
})
|
||||
.catch((err) => {
|
||||
logger.error('[api/server/controllers/agents/request] Error in `handleAbortError`', err);
|
||||
})
|
||||
.finally(() => {
|
||||
performCleanup();
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue