Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-17 17:00:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

🤖 refactor: Improve Agents Memory Usage, Bump Keyv, Grok 3 (#6850)

Browse source 
* 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 2025-04-12 18:46:36 -04:00 • committed by GitHub
parent 1e6b1b9554
commit 37964975c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
68 changed files with 1796 additions and 623 deletions
Download patch file Download diff file Expand all files Collapse all files

54
api/utils/tokens.spec.js
View file

@ -517,18 +517,30 @@ describe('Grok Model Tests - Tokens', () => {
expect(getModelMaxTokens('grok-2-latest')).toBe(131072);
});
test('should return correct tokens for Grok 3 series models', () => {
expect(getModelMaxTokens('grok-3')).toBe(131072);
expect(getModelMaxTokens('grok-3-fast')).toBe(131072);
expect(getModelMaxTokens('grok-3-mini')).toBe(131072);
expect(getModelMaxTokens('grok-3-mini-fast')).toBe(131072);
});
test('should handle partial matches for Grok models with prefixes', () => {
// Vision models should match before general models
expect(getModelMaxTokens('openai/grok-2-vision-1212')).toBe(32768);
expect(getModelMaxTokens('openai/grok-2-vision')).toBe(32768);
expect(getModelMaxTokens('openai/grok-2-vision-latest')).toBe(32768);
expect(getModelMaxTokens('xai/grok-2-vision-1212')).toBe(32768);
expect(getModelMaxTokens('xai/grok-2-vision')).toBe(32768);
expect(getModelMaxTokens('xai/grok-2-vision-latest')).toBe(32768);
// Beta models
expect(getModelMaxTokens('openai/grok-vision-beta')).toBe(8192);
expect(getModelMaxTokens('openai/grok-beta')).toBe(131072);
expect(getModelMaxTokens('xai/grok-vision-beta')).toBe(8192);
expect(getModelMaxTokens('xai/grok-beta')).toBe(131072);
// Text models
expect(getModelMaxTokens('openai/grok-2-1212')).toBe(131072);
expect(getModelMaxTokens('openai/grok-2')).toBe(131072);
expect(getModelMaxTokens('openai/grok-2-latest')).toBe(131072);
expect(getModelMaxTokens('xai/grok-2-1212')).toBe(131072);
expect(getModelMaxTokens('xai/grok-2')).toBe(131072);
expect(getModelMaxTokens('xai/grok-2-latest')).toBe(131072);
// Grok 3 models
expect(getModelMaxTokens('xai/grok-3')).toBe(131072);
expect(getModelMaxTokens('xai/grok-3-fast')).toBe(131072);
expect(getModelMaxTokens('xai/grok-3-mini')).toBe(131072);
expect(getModelMaxTokens('xai/grok-3-mini-fast')).toBe(131072);
});
});
@ -545,20 +557,30 @@ describe('Grok Model Tests - Tokens', () => {
expect(matchModelName('grok-2-1212')).toBe('grok-2-1212');
expect(matchModelName('grok-2')).toBe('grok-2');
expect(matchModelName('grok-2-latest')).toBe('grok-2-latest');
// Grok 3 models
expect(matchModelName('grok-3')).toBe('grok-3');
expect(matchModelName('grok-3-fast')).toBe('grok-3-fast');
expect(matchModelName('grok-3-mini')).toBe('grok-3-mini');
expect(matchModelName('grok-3-mini-fast')).toBe('grok-3-mini-fast');
});
test('should match Grok model variations with prefixes', () => {
// Vision models should match before general models
expect(matchModelName('openai/grok-2-vision-1212')).toBe('grok-2-vision-1212');
expect(matchModelName('openai/grok-2-vision')).toBe('grok-2-vision');
expect(matchModelName('openai/grok-2-vision-latest')).toBe('grok-2-vision-latest');
expect(matchModelName('xai/grok-2-vision-1212')).toBe('grok-2-vision-1212');
expect(matchModelName('xai/grok-2-vision')).toBe('grok-2-vision');
expect(matchModelName('xai/grok-2-vision-latest')).toBe('grok-2-vision-latest');
// Beta models
expect(matchModelName('openai/grok-vision-beta')).toBe('grok-vision-beta');
expect(matchModelName('openai/grok-beta')).toBe('grok-beta');
expect(matchModelName('xai/grok-vision-beta')).toBe('grok-vision-beta');
expect(matchModelName('xai/grok-beta')).toBe('grok-beta');
// Text models
expect(matchModelName('openai/grok-2-1212')).toBe('grok-2-1212');
expect(matchModelName('openai/grok-2')).toBe('grok-2');
expect(matchModelName('openai/grok-2-latest')).toBe('grok-2-latest');
expect(matchModelName('xai/grok-2-1212')).toBe('grok-2-1212');
expect(matchModelName('xai/grok-2')).toBe('grok-2');
expect(matchModelName('xai/grok-2-latest')).toBe('grok-2-latest');
// Grok 3 models
expect(matchModelName('xai/grok-3')).toBe('grok-3');
expect(matchModelName('xai/grok-3-fast')).toBe('grok-3-fast');
expect(matchModelName('xai/grok-3-mini')).toBe('grok-3-mini');
expect(matchModelName('xai/grok-3-mini-fast')).toBe('grok-3-mini-fast');
});
});
});