mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-21 10:50:14 +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:
Danny Avila
GitHub
parent
1e6b1b9554
commit
37964975c1
68 changed files with 1796 additions and 623 deletions
|
|
@ -28,15 +28,10 @@ class BaseClient {
|
|||
month: 'long',
|
||||
day: 'numeric',
|
||||
});
|
||||
this.fetch = this.fetch.bind(this);
|
||||
/** @type {boolean} */
|
||||
this.skipSaveConvo = false;
|
||||
/** @type {boolean} */
|
||||
this.skipSaveUserMessage = false;
|
||||
/** @type {ClientDatabaseSavePromise} */
|
||||
this.userMessagePromise;
|
||||
/** @type {ClientDatabaseSavePromise} */
|
||||
this.responsePromise;
|
||||
/** @type {string} */
|
||||
this.user;
|
||||
/** @type {string} */
|
||||
|
|
@ -564,6 +559,8 @@ class BaseClient {
|
|||
}
|
||||
|
||||
async sendMessage(message, opts = {}) {
|
||||
/** @type {Promise<TMessage>} */
|
||||
let userMessagePromise;
|
||||
const { user, head, isEdited, conversationId, responseMessageId, saveOptions, userMessage } =
|
||||
await this.handleStartMethods(message, opts);
|
||||
|
||||
|
|
@ -625,11 +622,11 @@ class BaseClient {
|
|||
}
|
||||
|
||||
if (!isEdited && !this.skipSaveUserMessage) {
|
||||
this.userMessagePromise = this.saveMessageToDatabase(userMessage, saveOptions, user);
|
||||
userMessagePromise = this.saveMessageToDatabase(userMessage, saveOptions, user);
|
||||
this.savedMessageIds.add(userMessage.messageId);
|
||||
if (typeof opts?.getReqData === 'function') {
|
||||
opts.getReqData({
|
||||
userMessagePromise: this.userMessagePromise,
|
||||
userMessagePromise,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
|
@ -655,7 +652,9 @@ class BaseClient {
|
|||
|
||||
/** @type {string|string[]|undefined} */
|
||||
const completion = await this.sendCompletion(payload, opts);
|
||||
this.abortController.requestCompleted = true;
|
||||
if (this.abortController) {
|
||||
this.abortController.requestCompleted = true;
|
||||
}
|
||||
|
||||
/** @type {TMessage} */
|
||||
const responseMessage = {
|
||||
|
|
@ -703,7 +702,13 @@ class BaseClient {
|
|||
if (usage != null && Number(usage[this.outputTokensKey]) > 0) {
|
||||
responseMessage.tokenCount = usage[this.outputTokensKey];
|
||||
completionTokens = responseMessage.tokenCount;
|
||||
await this.updateUserMessageTokenCount({ usage, tokenCountMap, userMessage, opts });
|
||||
await this.updateUserMessageTokenCount({
|
||||
usage,
|
||||
tokenCountMap,
|
||||
userMessage,
|
||||
userMessagePromise,
|
||||
opts,
|
||||
});
|
||||
} else {
|
||||
responseMessage.tokenCount = this.getTokenCountForResponse(responseMessage);
|
||||
completionTokens = responseMessage.tokenCount;
|
||||
|
|
@ -712,8 +717,8 @@ class BaseClient {
|
|||
await this.recordTokenUsage({ promptTokens, completionTokens, usage });
|
||||
}
|
||||
|
||||
if (this.userMessagePromise) {
|
||||
await this.userMessagePromise;
|
||||
if (userMessagePromise) {
|
||||
await userMessagePromise;
|
||||
}
|
||||
|
||||
if (this.artifactPromises) {
|
||||
|
|
@ -728,7 +733,11 @@ class BaseClient {
|
|||
}
|
||||
}
|
||||
|
||||
this.responsePromise = this.saveMessageToDatabase(responseMessage, saveOptions, user);
|
||||
responseMessage.databasePromise = this.saveMessageToDatabase(
|
||||
responseMessage,
|
||||
saveOptions,
|
||||
user,
|
||||
);
|
||||
this.savedMessageIds.add(responseMessage.messageId);
|
||||
delete responseMessage.tokenCount;
|
||||
return responseMessage;
|
||||
|
|
@ -749,9 +758,16 @@ class BaseClient {
|
|||
* @param {StreamUsage} params.usage
|
||||
* @param {Record<string, number>} params.tokenCountMap
|
||||
* @param {TMessage} params.userMessage
|
||||
* @param {Promise<TMessage>} params.userMessagePromise
|
||||
* @param {object} params.opts
|
||||
*/
|
||||
async updateUserMessageTokenCount({ usage, tokenCountMap, userMessage, opts }) {
|
||||
async updateUserMessageTokenCount({
|
||||
usage,
|
||||
tokenCountMap,
|
||||
userMessage,
|
||||
userMessagePromise,
|
||||
opts,
|
||||
}) {
|
||||
/** @type {boolean} */
|
||||
const shouldUpdateCount =
|
||||
this.calculateCurrentTokenCount != null &&
|
||||
|
|
@ -787,7 +803,7 @@ class BaseClient {
|
|||
Note: we update the user message to be sure it gets the calculated token count;
|
||||
though `AskController` saves the user message, EditController does not
|
||||
*/
|
||||
await this.userMessagePromise;
|
||||
await userMessagePromise;
|
||||
await this.updateMessageInDatabase({
|
||||
messageId: userMessage.messageId,
|
||||
tokenCount: userMessageTokenCount,
|
||||
|
|
@ -853,7 +869,7 @@ class BaseClient {
|
|||
}
|
||||
|
||||
const savedMessage = await saveMessage(
|
||||
this.options.req,
|
||||
this.options?.req,
|
||||
{
|
||||
...message,
|
||||
endpoint: this.options.endpoint,
|
||||
|
|
@ -877,7 +893,7 @@ class BaseClient {
|
|||
const existingConvo =
|
||||
this.fetchedConvo === true
|
||||
? null
|
||||
: await getConvo(this.options.req?.user?.id, message.conversationId);
|
||||
: await getConvo(this.options?.req?.user?.id, message.conversationId);
|
||||
|
||||
const unsetFields = {};
|
||||
const exceptions = new Set(['spec', 'iconURL']);
|
||||
|
|
@ -897,7 +913,7 @@ class BaseClient {
|
|||
}
|
||||
}
|
||||
|
||||
const conversation = await saveConvo(this.options.req, fieldsToKeep, {
|
||||
const conversation = await saveConvo(this.options?.req, fieldsToKeep, {
|
||||
context: 'api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo',
|
||||
unsetFields,
|
||||
});
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue