LibreChat/api/server/routes/ask/gptPlugins.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

241 lines
6.4 KiB
JavaScript

const express = require('express');
const { getResponseSender, Constants } = require('librechat-data-provider');
const { initializeClient } = require('~/server/services/Endpoints/gptPlugins');
const { sendMessage, createOnProgress } = require('~/server/utils');
const { addTitle } = require('~/server/services/Endpoints/openAI');
const { saveMessage, updateMessage } = require('~/models');
const {
handleAbort,
createAbortController,
handleAbortError,
setHeaders,
validateModel,
validateEndpoint,
buildEndpointOption,
moderateText,
} = require('~/server/middleware');
const { validateTools } = require('~/app');
const { logger } = require('~/config');
const router = express.Router();
router.use(moderateText);
router.post(
'/',
validateEndpoint,
validateModel,
buildEndpointOption,
setHeaders,
async (req, res) => {
let {
text,
endpointOption,
conversationId,
parentMessageId = null,
overrideParentMessageId = null,
} = req.body;
logger.debug('[/ask/gptPlugins]', { text, conversationId, ...endpointOption });
let userMessage;
let userMessagePromise;
let promptTokens;
let userMessageId;
let responseMessageId;
const sender = getResponseSender({
...endpointOption,
model: endpointOption.modelOptions.model,
});
const newConvo = !conversationId;
const user = req.user.id;
const plugins = [];
const getReqData = (data = {}) => {
for (let key in data) {
if (key === 'userMessage') {
userMessage = data[key];
userMessageId = data[key].messageId;
} else if (key === 'userMessagePromise') {
userMessagePromise = data[key];
} else if (key === 'responseMessageId') {
responseMessageId = data[key];
} else if (key === 'promptTokens') {
promptTokens = data[key];
} else if (!conversationId && key === 'conversationId') {
conversationId = data[key];
}
}
};
let streaming = null;
let timer = null;
const {
onProgress: progressCallback,
sendIntermediateMessage,
getPartialText,
} = createOnProgress({
onProgress: () => {
if (timer) {
clearTimeout(timer);
}
streaming = new Promise((resolve) => {
timer = setTimeout(() => {
resolve();
}, 250);
});
},
});
const pluginMap = new Map();
const onAgentAction = async (action, runId) => {
pluginMap.set(runId, action.tool);
sendIntermediateMessage(res, {
plugins,
parentMessageId: userMessage.messageId,
messageId: responseMessageId,
});
};
const onToolStart = async (tool, input, runId, parentRunId) => {
const pluginName = pluginMap.get(parentRunId);
const latestPlugin = {
runId,
loading: true,
inputs: [input],
latest: pluginName,
outputs: null,
};
if (streaming) {
await streaming;
}
const extraTokens = ':::plugin:::\n';
plugins.push(latestPlugin);
sendIntermediateMessage(
res,
{ plugins, parentMessageId: userMessage.messageId, messageId: responseMessageId },
extraTokens,
);
};
const onToolEnd = async (output, runId) => {
if (streaming) {
await streaming;
}
const pluginIndex = plugins.findIndex((plugin) => plugin.runId === runId);
if (pluginIndex !== -1) {
plugins[pluginIndex].loading = false;
plugins[pluginIndex].outputs = output;
}
};
const getAbortData = () => ({
sender,
conversationId,
userMessagePromise,
messageId: responseMessageId,
parentMessageId: overrideParentMessageId ?? userMessageId,
text: getPartialText(),
plugins: plugins.map((p) => ({ ...p, loading: false })),
userMessage,
promptTokens,
});
const { abortController, onStart } = createAbortController(req, res, getAbortData, getReqData);
try {
endpointOption.tools = await validateTools(user, endpointOption.tools);
const { client } = await initializeClient({ req, res, endpointOption });
const onChainEnd = () => {
if (!client.skipSaveUserMessage) {
saveMessage(
req,
{ ...userMessage, user },
{ context: 'api/server/routes/ask/gptPlugins.js - onChainEnd' },
);
}
sendIntermediateMessage(res, {
plugins,
parentMessageId: userMessage.messageId,
messageId: responseMessageId,
});
};
let response = await client.sendMessage(text, {
user,
conversationId,
parentMessageId,
overrideParentMessageId,
getReqData,
onAgentAction,
onChainEnd,
onToolStart,
onToolEnd,
onStart,
getPartialText,
...endpointOption,
progressCallback,
progressOptions: {
res,
// parentMessageId: overrideParentMessageId || userMessageId,
plugins,
},
abortController,
});
if (overrideParentMessageId) {
response.parentMessageId = overrideParentMessageId;
}
logger.debug('[/ask/gptPlugins]', response);
const { conversation = {} } = await response.databasePromise;
delete response.databasePromise;
conversation.title =
conversation && !conversation.title ? null : conversation?.title || 'New Chat';
sendMessage(res, {
title: conversation.title,
final: true,
conversation,
requestMessage: userMessage,
responseMessage: response,
});
res.end();
if (parentMessageId === Constants.NO_PARENT && newConvo) {
addTitle(req, {
text,
response,
client,
});
}
response.plugins = plugins.map((p) => ({ ...p, loading: false }));
if (response.plugins?.length > 0) {
await updateMessage(
req,
{ ...response, user },
{ context: 'api/server/routes/ask/gptPlugins.js - save plugins used' },
);
}
} catch (error) {
const partialText = getPartialText();
handleAbortError(res, req, error, {
partialText,
conversationId,
sender,
messageId: responseMessageId,
parentMessageId: userMessageId ?? parentMessageId,
});
}
},
);
module.exports = router;