Commit graph

1025 commits

Author SHA1 Message Date
Danny Avila
851938e7a6
🔧 fix: Agent Resource Form, Convo Menu Style, Ensure Draft Clears on Submission (#6925)
*  style: Adjust z-index for popover UI and update className in ConvoOptions

*  feat: Add 'spec' field to conversation query selection

* 🛠️ fix: add back conversationId to use Constants.PENDING_CONVO in useSSE hook on submission to allow text drafts to clear

*  chore: add .clineignore to .gitignore for Cline configuration

*  refactor: memoize FileSearchCheckbox component for performance optimization

* fix: agent resource management by adding tool_resource to agent's tools if missing
2025-04-16 18:14:34 -04:00
Marco Beretta
000f3a3733
📢 fix: Invalid engineTTS and Conversation State on Navigation (#6904)
* fix: handle invalid engineTTS values and prevent VoiceDropdown render errors

* refactor: add verbose developer logging for debugging conversation state issues

* refactor: remove unnecessary effect for conversationId changes

* chore: imports

* fix: include model and entity IDs in conversation query selection

* feat: add fetchFreshData function to retrieve conversation data on navigation

* fix: remove unnecessary comment in fetchFreshData function

* chore: reorder imports in useNavigateToConvo for consistency

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-04-15 21:00:06 -04:00
Danny Avila
d32f34e5d7
📝 fix: Mistral OCR Image Support and Azure Agent Titles (#6901)
* fix: azure title model

* refactor: typing for uploadMistralOCR

* fix: update conversation ID handling in useSSE for better state management, only use PENDING_CONVO for new conversations

* fix: streamline conversation ID handling in useSSE for simplicity, only needs state update to prevent draft from applying

* fix: update performOCR and tests to support document and image URLs with appropriate types
2025-04-15 18:03:56 -04:00
Marco Beretta
650e9b4f6c
📜 refactor: Optimize Conversation History Nav with Cursor Pagination (#5785)
*  feat: improve Nav/Conversations/Convo/NewChat component performance

*  feat: implement cursor-based pagination for conversations API

* 🔧 refactor: remove createdAt from conversation selection in API and type definitions

* 🔧 refactor: include createdAt in conversation selection and update related types

*  fix: search functionality and bugs with loadMoreConversations

* feat: move ArchivedChats to cursor and DataTable standard

* 🔧 refactor: add InfiniteQueryObserverResult type import in Nav component

* feat: enhance conversation listing with pagination, sorting, and search capabilities

* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable

* 🔧 refactor: remove unused translation keys for archived chats and search results

* 🔧 fix: Archived Chats, Delete Convo, Duplicate Convo

* 🔧 refactor: improve conversation components with layout adjustments and new translations

* 🔧 refactor: simplify archive conversation mutation and improve unarchive handling; fix: update fork mutation

* 🔧 refactor: decode search query parameter in conversation route; improve error handling in unarchive mutation; clean up DataTable component styles

* 🔧 refactor: remove unused translation key for empty archived chats

* 🚀 fix: `archivedConversation` query key not updated correctly while archiving

* 🧠 feat: Bedrock Anthropic Reasoning & Update Endpoint Handling (#6163)

* feat: Add thinking and thinkingBudget parameters for Bedrock Anthropic models

* chore: Update @librechat/agents to version 2.1.8

* refactor: change region order in params

* refactor: Add maxTokens parameter to conversation preset schema

* refactor: Update agent client to use bedrockInputSchema and improve error handling for model parameters

* refactor: streamline/optimize llmConfig initialization and saving for bedrock

* fix: ensure config titleModel is used for all endpoints

* refactor: enhance OpenAIClient and agent initialization to support endpoint checks for OpenRouter

* chore: bump @google/generative-ai

*  feat: improve Nav/Conversations/Convo/NewChat component performance

* 🔧 refactor: remove unnecessary comment regarding lodash/debounce in ArchivedChatsTable

* 🔧 refactor: update translation keys for clarity; simplify conversation query parameters and improve sorting functionality in SharedLinks component

* 🔧 refactor: optimize conversation loading logic and improve search handling in Nav component

* fix: package-lock

* fix: package-lock 2

* fix: package lock 3

* refactor: remove unused utility files and exports to clean up the codebase

* refactor: remove i18n and useAuthRedirect modules to streamline codebase

* refactor: optimize Conversations component and remove unused ToggleContext

* refactor(Convo): add RenameForm and ConvoLink components; enhance Conversations component with responsive design

* fix: add missing @azure/storage-blob dependency in package.json

* refactor(Search): add error handling with toast notification for search errors

* refactor: make createdAt and updatedAt fields of tConvoUpdateSchema less restrictive if timestamps are missing

* chore: update @azure/storage-blob dependency to version 12.27.0, ensure package-lock is correct

* refactor(Search): improve conversation handling server side

* fix: eslint warning and errors

* refactor(Search): improved search loading state and overall UX

* Refactors conversation cache management

Centralizes conversation mutation logic into dedicated utility functions for adding, updating, and removing conversations from query caches.

Improves reliability and maintainability by:
- Consolidating duplicate cache manipulation code
- Adding type safety for infinite query data structures
- Implementing consistent cache update patterns across all conversation operations
- Removing obsolete conversation helper functions in favor of standardized utilities

* fix: conversation handling and SSE event processing

- Optimizes conversation state management with useMemo and proper hook ordering
- Improves SSE event handler documentation and error handling
- Adds reset guard flag for conversation changes
- Removes redundant navigation call
- Cleans up cursor handling logic and document structure

Improves code maintainability and prevents potential race conditions in conversation state updates

* refactor: add type for SearchBar `onChange`

* fix: type tags

* style: rounded to xl all Header buttons

* fix: activeConvo in Convo not working

* style(Bookmarks): improved UI

* a11y(AccountSettings): fixed hover style not visible when using light theme

* style(SettingsTabs): improved tab switchers and dropdowns

* feat: add translations keys for Speech

* chore: fix package-lock

* fix(mutations): legacy import after rebase

* feat: refactor conversation navigation for accessibility

* fix(search): convo and message create/update date not returned

* fix(search): show correct iconURL and endpoint for searched messages

* fix: small UI improvements

* chore: console.log cleanup

* chore: fix tests

* fix(ChatForm): improve conversation ID handling and clean up useMemo dependencies

* chore: improve typing

* chore: improve typing

* fix(useSSE): clear conversation ID on submission to prevent draft restoration

* refactor(OpenAIClient): clean up abort handler

* refactor(abortMiddleware): change handleAbort to use function expression

* feat: add PENDING_CONVO constant and update conversation ID checks

* fix: final event handling on abort

* fix: improve title sync and query cache sync on final event

* fix: prevent overwriting cached conversation data if it already exists

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-04-15 04:04:00 -04:00
Danny Avila
c49f883e1a
🔁 refactor: Token Event Handler and Standardize maxTokens Key (#6886)
* refactor: agent token handling to use createHandleLLMNewToken for improved closure

* refactor: update llmConfig to use maxTokens instead of max_tokens for consistency
2025-04-14 22:38:35 -04:00
Danny Avila
52b3ed54ca
🤖 feat: GPT-4.1 (#6880)
* fix: Agent Builder setting not applying in useSideNavLinks

* fix: Remove unused type imports in useSideNavLinks

* feat: gpt-4.1

* fix: Update getCacheMultiplier and getMultiplier tests to use dynamic token values

* feat: Add gpt-4.1 to the list of vision models

* chore: Bump version of librechat-data-provider to 0.7.792
2025-04-14 14:55:59 -04:00
Danny Avila
64bd373bc8
🔧 fix: Keyv and Proxy Issues, and More Memory Optimizations (#6867)
* chore: update @librechat/agents dependency to version 2.4.15

* refactor: Prevent memory leaks by nullifying boundModel.client in disposeClient function

* fix: use of proxy, use undici

* chore: update @librechat/agents dependency to version 2.4.16

* Revert "fix: use of proxy, use undici"

This reverts commit 83153cd582.

* fix: ensure fetch is imported for HTTP requests

* fix: replace direct OpenAI import with CustomOpenAIClient from @librechat/agents

* fix: update keyv peer dependency to version 5.3.2

* fix: update keyv dependency to version 5.3.2

* refactor: replace KeyvMongo with custom implementation and update flow state manager usage

* fix: update @librechat/agents dependency to version 2.4.17

* ci: update OpenAIClient tests to use CustomOpenAIClient from @librechat/agents

* refactor: remove KeyvMongo mock and related dependencies
2025-04-13 23:01:55 -04:00
Danny Avila
339882eea4
💾 refactor: Enhance Memory In Image Encodings & Client Disposal (#6852)
* 💾 chore: Clear Additional Properties in `disposeClient`

* refactor: stream handling and base64 conversion in encode.js to better free memory
2025-04-12 20:53:38 -04:00
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
Danny Avila
12f4dbb8c5
feat: Self-hosted Artifacts Static Bundler URL (#6827)
* v0.7.791

* feat: configuration via `SANDPACK_STATIC_BUNDLER_URL` env var and update bundlerURL logic in Artifact components

* fix: update minimum length requirement for auth fields from 10 to 1 character
2025-04-10 15:37:23 -04:00
Danny Avila
e16a6190a5
💾 chore: Enhance Local Storage Handling and Update MCP SDK (#6809)
* feat: Update MCP package version and dependencies; refactor ToolContentPart type

* refactor: Change module type to commonjs and update rollup configuration, remove unused dev dependency

* refactor: Change async calls to synchronous for MCP and FlowStateManager retrieval

* chore: Add eslint disable comment for i18next rule in DropdownPopup component

* fix: improve statefulness of mcp servers selected if some were removed since last session

* feat: implement conversation storage cleanup functions and integrate them into mutation success handlers

* feat: enhance storage condition logic in useLocalStorageAlt to prevent unnecessary local storage writes

* refactor: streamline local storage update logic in useLocalStorageAlt
2025-04-09 18:38:48 -04:00
Danny Avila
24c0433dcf
🖥️ feat: Code Interpreter API for Non-Agent Endpoints (#6803)
* fix: Prevent parsing 'undefined' string in useLocalStorage initialization

* feat: first pass, code interpreter badge

* feat: Integrate API key authentication and default checked value in Code Interpreter Badge

* refactor: Rename showMCPServers to showEphemeralBadges and update related components, memoize values in useChatBadges

* refactor: Enhance AttachFileChat to support ephemeral agents in file attachment logic

* fix: Add baseURL configuration option to legacy function call

* refactor: Update dependency array in useDragHelpers to include handleFiles

* refactor: Update isEphemeralAgent function to accept optional endpoint parameter

* refactor: Update file handling to support ephemeral agents in AttachFileMenu and useDragHelpers

* fix: improve compatibility issues with OpenAI usage field handling in createRun function

* refactor: usage field compatibility

* fix: ensure mcp servers are no longer "selected" if mcp servers are now unavailable
2025-04-09 16:11:16 -04:00
Danny Avila
5d668748f9
🗃️ feat: Code Interpreter File Persistence between Sessions (#6790)
* refactor: Enhance FileContainer with customizable button and container styles, onClick button handling, and type override

* refactor: Update file type handling to support partial file objects

* refactor: Extract download handling into a custom hook for improved reusability

* refactor: Replace LogContent with Stdout component and enhance Attachment rendering for added visibility

* feat: Update @librechat/agents to version 2.4.1 for referencing generated files in subsequent code interpreter uses

* feat: Add support for tab-separated values (TSV) in mime type handling and improve error logging for regex patterns

* chore: Update @librechat/agents to version 2.4.11 for better `session_id` instructions when wanting to persist files between executions

* chore: Update @librechat/agents to version 2.4.12 for improved functionality

* fix: Enhance argument parsing in useParseArgs to support JSON input and improve code extraction

* refactor: Update input handling in useAutoSave to require more than one character before saving to local storage
2025-04-08 23:18:50 -04:00
Danny Avila
910c73359b
🔦 feat: MCP Support for Non-Agent Endpoints (#6775)
* wip: mcp select

* refactor: Update useAvailableToolsQuery to support generic data types

* feat: Enhance MCPSelect to dynamically load server options and improve MultiSelect component styling

* WIP: ephemeral agents

* wip: Add null check for MCPSelect and improve MultiSelect focus handling

* feat: Pass conversationId prop to MCPSelect in BadgeRow to optimize badge rendering

* feat: useApplyNewAgentTemplate hook to manage ephemeral agent upon conversation creation

* WIP: eph. agent payload

* refactor(OpenAIClient): streamline message processing by replacing content handling with parseTextParts function

* feat: enhance applyAgentTemplate function to accept source conversation ID for improved template application

* feat(parsers): add skipReasoning parameter to parseTextParts for conditional reasoning handling

* WIP: first pass, ephemeral agent backend processing

* chore: import order

* feat: update loadEphemeralAgent and loadAgent functions to accept model_parameters for enhanced agent configuration

* feat: add showMCPServers prop to BadgeRow for conditional rendering of MCPSelect, fix react rule violation

* feat: enhance MCPSelect with localized placeholder and custom icon, add renderSelectedValues callback

* feat: simplify message processing in AnthropicClient by replacing content handling with parseTextParts function

* feat: implement useLocalStorage hook for managing MCP values and update MCPSelect to utilize it

* chore: remove chatGPTBrowserSchema from endpoint schemas and update types for improved schema management

* chore: remove compactChatGPTSchema from endpoint schemas and update types for better schema management

* refactor: rename schemas for clarity and improve schema management

* feat: extend model detection to include 'codestral' alongside 'mistral'

* feat: add endpointType parameter to buildOptions and initializeClient functions

* fix: update condition for handling completion in BaseClient to include agents client

* refactor: simplify payload parsing logic in AgentClient and remove unused providerParsers

* refactor: change useSetRecoilState to useRecoilState for better state management in MCPSelect component

* refactor: streamline chat route handlers by consolidating middleware and improving endpoint structure

* style: update MCPSelect and MultiSelect components for improved layout in mobile view

* v0.7.790

* feat: add getMessageMapMethod to process message text and content in GoogleClient

* chore: include LAST_MCP_ key prefix in clearLocalStorage function for proper teardown on logout
2025-04-07 19:16:56 -04:00
Danny Avila
4afab52fc5
🪺 fix: Update Role Handling due to New Schema Shape (#6774)
* 📝 fix: Update translation for shared agent message in English locale

* 🪺 fix: Migrate role schema to new nested structure and update permissions handling where missed
2025-04-07 14:48:11 -04:00
Danny Avila
9b0678da16
⚙️ refactor: OAuth Flow Signal, Type Safety, Tool Progress & Updated Packages (#6752)
* chore: bump @librechat/agents and related packages

* refactor: update message state for tool calls run step, in case no tool call chunks are received

* fix: avoid combining finalized args createContentAggregator for tool calls

* chore: bump @librechat/agents to version 2.3.99

* feat: add support for aborting flows with AbortSignal in createFlow methods

* fix: improve handling of tool call arguments in useStepHandler

* chore: bump @librechat/agents to version 2.4.0

* fix: update flow identifier format for OAuth login in createActionTool to allow uniqueness per run

* fix: improve error message handling for aborted flows in FlowStateManager

* refactor: allow possible multi-agent cross-over for oauth login

* fix: add type safety for Sandpack files in ArtifactCodeEditor
2025-04-06 03:28:05 -04:00
Ruben Talstra
0551a562d8
🪺 refactor: Nest Permission fields for Roles (#6487)
* 🏗️ feat: Add Group model and schema with GroupType enum

* 🏗️ feat: Introduce Permissions module and refactor role-based access control

* 🏗️ feat: Refactor permissions handling and consolidate permission schemas

* 🏗️ feat: Refactor role permissions handling and improve role initialization logic

* 🏗️ feat: Update Role.spec.js to improve imports and enhance test structure

* 🏗️ feat: Update access control logic to ensure proper permission checks in role handling

* 🏗️ chore: Bump versions for librechat-data-provider to 0.7.75 and @librechat/data-schemas to 0.0.6

* 🏗️ feat: Improve role permissions handling by ensuring defaults are applied correctly

* 🏗️ feat: Update role permissions schema to comment out unused SHARE permission

* 🏗️ chore: Bump version of librechat-data-provider to 0.7.77 and remove unused groups field from IUser interface

* 🏗️ chore: Downgrade version of librechat-data-provider to 0.7.76

* 🔧 chore: Bump versions for librechat-data-provider to 0.7.77 and data-schemas to 0.0.6

* 🏗️ chore: Update version of librechat-data-provider to 0.7.789

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-04-04 19:47:14 -04:00
RedwindA
93e679e173
🪙 chore: Update Gemini Pricing (#6731) 2025-04-04 11:55:07 -04:00
Danny Avila
cff392e578
🔧 fix: Agent Capability Checks & DocumentDB Compatibility for Agent Resource Removal (#6726)
* fix: tool capability checks in loadAgentTools function

* fix: enhance atomicity in removing agent resource files and add concurrency tests, improve documentdb compatibility
2025-04-04 10:33:53 -04:00
Danny Avila
953e9732d9
🔧 fix: Chat Middleware, Zod Conversion, Auto-Save and S3 URL Refresh (#6720)
* 🔧 feat: Add configurable S3 URL refresh expiry time

* fix: Set default width and height for URLIcon component in case container style results in NaN

* refactor: Enhance auto-save functionality with debounced restore methods

* feat: Add support for additionalProperties in JSON schema conversion to Zod

* test: Add tests for additionalProperties handling in JSON schema to Zod conversion

* chore: Reorder import statements for better readability in ask route

* fix: Handle additional successful response status code (200) in SSE error handler

* fix: add missing rate limiting middleware for bedrock and agent chat routes

* fix: update moderation middleware to check feature flag before processing requests

* fix: add moderation middleware to chat routes for text moderation

* Revert "refactor: Enhance auto-save functionality with debounced restore methods"

This reverts commit d2e4134d1f.

* refactor: Move base64 encoding/decoding functions to top-level scope and optimize input handling
2025-04-03 20:42:56 -04:00
Danny Avila
c4f1da26b3
🔄 fix: Avatar & Error Handling Enhancements (#6687)
* fix: Ensure safe access to agent capabilities in AgentConfig

* fix: don't show agent builder if agents endpoint is not enabled

* fix: Improve error logging for MCP tool calls

* fix: Enhance error message for MCP tool failures

* feat: Add optional spec and iconURL properties to TEndpointOption type

* chore: Update condition to use constant for new conversation parameter

* feat: Enhance abort error handling with additional endpoint options to properly render error message fields

* fix: Throw error instead of returning message for failed MCP tool calls

* refactor: separate logic to generate new S3 URLs for expired links

* feat: Implement S3 URL refresh for user avatars with error handling

* fix: authcontext error in chats where agent chain is used

* refactor: streamline balance configuration logic in getBalanceConfig function

* fix: enhance icon resolution logic in SpecIcon component

* fix: allow null values for spec and iconURL in TEndpointOption type

* fix: update balance check to allow null tokenCredits
2025-04-02 18:44:13 -04:00
Danny Avila
d8337e00d2
refactor: DocumentDB Compatibility for Balance Updates (#6673)
* fix: Implement optimistic concurrency control for balance updates in Transaction model to allow for documentdb compatibility

* test: Add concurrent balance increase test for auto refill transactions
2025-04-01 23:09:24 -04:00
Danny Avila
0865bc4a72
🪙 feat: Sync Balance Config on Login (#6671)
* chore: Add deprecation warnings for environment variables in checks

* chore: Change deprecatedVariables to a const declaration in checks.js

* fix: Add date validation in checkBalanceRecord to prevent invalid date errors

* feat: Add setBalanceConfig middleware to synchronize user balance settings

* chore: Reorder middleware imports in oauth.js for better readability
2025-04-01 21:19:42 -04:00
Danny Avila
0ac07ace26
🤖 fix: Gemini 2.5 Vision Support (#6663)
* 🤖 fix: Gemini 2.5 Vision Support

* 🐛 fix: Update defaultVisionModel logic to handle excluded GenAI models
2025-04-01 15:21:45 -04:00
Sean McGrath
677423d82c
🐛 fix: Safeguard against undefined length for addedEndpoints in modelSpecs processing (#6654) 2025-04-01 08:06:25 -04:00
Danny Avila
90b8769ef3
🚀 feat: Use Model Specs + Specific Endpoints, Limit Providers for Agents (#6650)
* 🔧 refactor: Remove modelSpecs prop from ModelSelector and related components

* fix: Update submission.conversationId references in SSE hooks and data types as was incorrectly typed

* feat: Allow showing specific endpoints alongside model specs via `addedEndpoints` field

* feat: allowed agents providers via `agents.allowedProviders` field

* fix: bump dicebear/sharp dependencies to resolve CVE-2024-12905 and improve avatar gen logic

* fix: rename variable for clarity in loadDefaultInterface function

* fix: add keepAddedConvos option to newConversation calls for modular chat support

* fix: include model information in endpoint selection for improved context

* fix: update data-provider version to 0.7.78 and increment config version to 1.2.4
2025-04-01 03:50:32 -04:00
Danny Avila
3c91f7b0b7
🚀 feat: Enhance S3 URL Expiry with Refresh; fix: S3 File Deletion (#6647)
* refactor: Improve error logging in image fetching to base64 conversion

* fix: Add error handling for custom endpoint configuration retrieval

* fix: Update audio stream processing to parse text parts from complex message content

* chore: import order in streamAudio

* fix: S3 file deletion and optimize file upload

* feat: Implement S3 URL refresh mechanism and add cache for expiry check intervals

* feat: Add S3 URL refresh functionality for agent avatars

* chore: remove unnecessary console.log in MultiMessage component

* chore: update version of librechat-data-provider to 0.7.77
2025-03-31 18:40:06 -04:00
Ruben Talstra
bc039cea29
🔧 fix: Azure Blob Integration and File Source References (#6575)
* 🔧 fix: Update file source references to include 'azure_blob' for correct service initialization

* 🔧 fix: Add Azure Blob Storage Emulator entries to .gitignore

* fix: Update file source references to include 'azure_blob' for correct service initialization

* fix: Refactor Azure Blob Storage functions to use environment variables for access control and container name, fix deletion improper logging and improper params

* fix: Add basePath determination for agent file uploads based on MIME type

* fix: Implement file streaming to Azure Blob Storage to optimize memory usage during uploads (non-images)

* fix: Update SourceIcon to include 'azure_blob' class and adjust model setting in useSelectorEffects for assistants

* chore: import order

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-03-31 13:44:20 -04:00
Danny Avila
d60f2ed50b
✉️ fix: Fallback For User Name In Email Templates (#6620) 2025-03-29 15:02:59 -04:00
Danny Avila
c381fc3ff0
🔧 fix: Ensure continuation in Image processing on base64 encoding from Blob Storage (#6619) 2025-03-29 14:48:35 -04:00
Danny Avila
a10bc87979
🚀 feat: Enhance MCP Connections For Multi-User Support (#6610)
* feat: first pass, multi-user connections

* 🔧 refactor: Enhance MCPConnection logging with user-specific prefixes

* 🔧 chore: Update @modelcontextprotocol/sdk dependency to version 1.8.0

* feat: idle timeout for user mcp connections

* chore: increase user connection idle timeout to 15 minutes

* feat: implement graceful shutdown for MCP servers on termination signal

* feat: implement user idle timeout management and last activity tracking

* feat: enhance MCP options to support custom headers and user ID in environment variable processing

* feat: update user last activity tracking in MCPManager

* refactor: remove default OpenRouter completions URL from OpenAIClient

* refactor: simplify log messages by removing redundant 'App' prefix in MCPManager

* refactor: show Agents Builder even if not using Agents endpoint

* refactor: remove redundant 'App' prefix from disconnect error log messages in MCPManager

* refactor: remove 'App' prefix from log prefix in MCPConnection

* chore: remove unecessary comment

* fix: allow error propagation during MCPManager initialization
2025-03-28 15:21:10 -04:00
Danny Avila
b9ebdd4aa5
🔧 fix: Consolidate Text Parsing and TTS Edge Initialization (#6582)
* 🔧 fix: Update useTextToSpeechExternal to include loading state and improve text parsing logic

* fix: update msedge-tts and prevent excessive initialization attempts

* fix: Refactor text parsing logic in mongoMeili model to use parseTextParts function
2025-03-27 17:09:46 -04:00
Danny Avila
a6f062e468
🚀 feat: Add Gemini 2.5 Token/Context Values, Increase Max Possible Output to 64k (#6563)
* feat: Add Gemini 2.5 token values, increase max output param, context window

* 🔧 fix: Update Gemini API model names in .env.example

* 🔧 fix: Add button type attribute to AttachFile component
2025-03-27 11:09:20 -04:00
Danny Avila
7ca5650840
🔧 fix: Mistral type strictness for usage & update token values/windows (#6562)
* 🔧 fix: Resolve Mistral type strictness for OpenAI usage field

* chore: Enable usage tracking for Mistral endpoint in OpenAI configuration

* chore: Add new token values and context windows for latest premier Mistral models
2025-03-27 01:57:25 -04:00
Danny Avila
ea2cbc55a7
🔧 fix: S3 Download Stream with Key Extraction and Blob Storage Encoding for Vision (#6557) 2025-03-26 15:04:01 -04:00
Danny Avila
299cabd6ed
🔧 refactor: Consolidate Logging, Model Selection & Actions Optimizations, Minor Fixes (#6553)
* 🔧 feat: Enhance logging configuration for production and debug environments

* 🔒 feat: Implement encryption and decryption functions for sensitive values in ActionService with URL encoding/decoding

* refactor: optimize action service for agent tools

* refactor: optimize action processing for Assistants API

* fix: handle case where agent is not found in loadAgent function

* refactor: improve error handling in API calls by throwing new Error with logAxiosError output

* chore: bump @librechat/agents to 2.3.95, fixes "Invalid tool call structure: No preceding AIMessage with tool_call_ids"

* refactor: enhance error logging in logAxiosError function to include response status

* refactor: remove unused useModelSelection hook from Endpoint

* refactor: add support for assistants in useSelectorEffects hook

* refactor: replace string easing with imported easings in Landing component

* chore: remove duplicate translation

* refactor: update model selection logic and improve localization for UI elements

* refactor: replace endpoint value checks with helper functions for agents and assistants

* refactor: optimize display value logic and utilize useMemo for performance improvements

* refactor: clean up imports and optimize display/icon value logic in endpoint components, fix spec selection

* refactor: enhance error logging in axios utility to include stack traces for better debugging

* refactor: update logging configuration to use DEBUG_LOGGING and streamline log level handling

* refactor: adjust className for export menu button to improve layout consistency and remove unused title prop from ShareButton

* refactor: update import path for logAxiosError utility to improve module organization and clarity

* refactor: implement debounced search value setter in ModelSelectorContext for improved performance
2025-03-26 14:10:52 -04:00
Marco Beretta
7f29f2f676
🎨 feat: UI Refresh for Enhanced UX (#6346)
*  feat: Add Expand Chat functionality and improve UI components

*  feat: Introduce Chat Badges feature with editing capabilities and UI enhancements

*  feat: re-implement file attachment functionality with new components and improved UI

*  feat: Enhance BadgeRow component with drag-and-drop functionality and add animations for better user experience

*  feat: Add useChatBadges hook and enhance Badge component with animations and toggle functionality

* feat: Improve Add/Delete Badges + style and bug fixes

*  feat: Refactor EditBadges component and optimize useChatBadges hook for improved performance and readability

*  feat: Add type definition for LucideIcon in EditBadges component

* refactor: Clean up BadgeRow component by removing outdated comment and improving code readability

* refactor: Rename app-icon class to badge-icon for consistency and improve badge styling

* feat: Add Center Chat Input toggle and update related components for improved UI/UX

* refactor: Simplify ChatView and MessagesView components for improved readability and performance

* refactor: Improve layout and positioning of scroll button in MessagesView component

* refactor: Adjust scroll button position in MessagesView component for better visibility

* refactor: Remove redundant background class from Badge component for cleaner styling

* feat: disable chat badges

* refactor: adjust positioning of scroll button and popover for improved layout

* refactor: simplify class names in ChatForm and RemoveFile components for cleaner code

* refactor: move Switcher to HeaderOptions from SidePanel

* fix(Landing): duplicate description

* feat: add SplitText component for animated text display and update Landing component to use it

* feat(Chat): add ConversationStarters component and integrate it into ChatView; remove ConvoStarter component

* feat(Chat): enhance Message component layout and styling for improved readability

* feat(ControlCombobox, Select): enhance styling and add animation for improved UI experience

* feat(Chat): update Header and HeaderNewChat components for improved layout and styling

* feat(Chat): add ModelDropdown (now includes both endpoint and model) and refactor Menu components for improved UI

* feat(ModelDropdown): add Agent Select; removed old AgentSwitcher components

* feat(ModelDropdown): add settings button for user key configuration

* fix(ModelDropdown): the model dropdown wasn't opening automatically when opening the endpoint one

* refactor(Chat): remove unused EndpointsMenu and related components to streamline codebase

* feat: enhance greeting message and improve accessibility fro ModelDropdown

* refactor(Endpoints): add new hooks and components for endpoint management

* feat(Endpoint): add support for modelSpecs

* feat(Endpoints): add mobile support

* fix: type issues

* fix(modelSpec): type issue

* fix(EndpointMenuDropdown): double overflow scroller in mobile model list

* fix: search model on mobile

* refactor: Endpoint/Model/modelSpec dropdown

* refactor: reorganize imports in Endpoint components

* refactor: remove unused translation keys from English locale

* BREAKING: moving to ariakit with new CustomMenu

* refactor: remove unnecessary comments

* refactor: remove EndpointItem, ModelDropdownButton, SpecIcon, and SpecItem components

* 🔧 fix: AI Icon bump when regenerating message

* wip: chat UI refactoring, fix issues

* chore: add recent update to useAutoSave

* feat: add access control for agent permissions in useMentions hook

* refactor: streamline ModelSelector by removing unused endpoints logic

* refactor: enhance ModelSelector and context by integrating endpointsConfig and improving type usage

* feat: update ModelSelectorContext to utilize conversation data for initial state

* feat: add selector effects for synced endpoint handling

* feat: add guard clause for conversation endpoint in useSelectorEffects hook

* fix: safely call onSelectMention and add autofocus to mention input

* chore: typing

* refactor: ModelSelector to streamline key dialog handling and improve endpoint rendering

* refactor: extract SettingsButton component for cleaner endpoint item rendering

* wip: first pass, expand set api key

* wip: first pass, expanding set key

* refactor: update EndpointItem styles for improved layout and hover effects

* refactor: adjust padding in EndpointItem for improved layout consistency

* refactor: update preset structure in useSelectMention to include spec as null

* refactor: rename setKeyDialogOpen to onOpenChange for clarity and consistency, bring focus back to button that opened dialog

* feat: add SpecIcon component for dynamic model spec icons in menu, adjust icon styling

* refactor: update getSelectedIcon to accept additional parameters and improve icon rendering logic

* fix: adjust padding in MessageRender for improved layout

* refactor: remove inline style for menu width in CustomMenu component

* refactor: enhance layout and styling in ModelSpecItem component for better responsiveness

* refactor: update getDefaultModelSpec to accept startupConfig and improve model spec retrieval logic

* refactor: improve key management and default values in ModelSelector and related components

* refactor: adjust menu width and improve responsiveness in CustomMenu and EndpointItem components

* refactor: enhance focus styles and responsiveness in EndpointItem component

* refactor: improve layout and spacing in Header and ModelSelector components for better responsiveness

* refactor: adjust button styles for consistency and improved layout in AddMultiConvo and PresetsMenu components

* fix: initial fix of assistant names

* fix: assistants handling

* chore: update version of librechat-data-provider to 0.7.75 and add 'spec' to excludedKeys

* fix: improve endpoint filtering logic based on interface configuration and access rights

* fix: remove unused HeaderOptions import and set spec to null in presets and mentions

* fix: ensure currentExample is always an object when updating examples

* fix: update interfaceConfig checks to ensure modelSelect is considered for rendering components

* fix: update model selection logic to consider interface configuration when prioritizing model specs

* fix: add missing localizations

* fix: remove unused agent and assistant selection translations

* fix: implement debounced state updates for selected values in useSelectorEffects

* style: minor style changes related to the ModelSelector

* fix: adjust maximum height for popover and set fixed height for model item

* fix: update placeholders for model and endpoint search inputs

* fix: refactor MessageRender and ContentRender components to better match each other

* fix: remove convo fallback for iconURL in MessageRender and ContentRender components

* fix: update handling of spec, iconURL, and modelLabel in conversation presets, to allow better interchangeability

* fix: replace chatGptLabel with modelLabel in OpenAI settings configuration (fully deprecate chatGptLabel)

* fix: remove console log for assistantNames in useEndpoints hook

* refactor: add cleanInput and cleanOutput options to default conversation handling

* chore: update bun.lockb

* fix: set default value for showIconInHeader in getSelectedIcon function

* refactor: enhance error handling in message processing when latest message has existing content blocks

* chore: allow import/no-cycle for messages

* fix: adjust flex properties in BookmarkMenu for better layout

* feat: support both 'prompt' and 'q' as query parameters in useQueryParams hook

* feat: re-enable Badges components

* refactor: disable edit badge component

* chore: rename assistantMap to assistantsMap for consistency

* chore: rename assistantMap to assistantsMap for consistency in Mention component

* feat: set staleTime for various queries to improve data freshness

* feat: add spec field to tQueryParamsSchema for model specification

* feat: enhance useQueryParams to handle model specs

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-03-25 18:50:58 -04:00
Danny Avila
c4fea9cd79
🔃 refactor: Allow streaming for o1 models in OpenAIClient and agent runs (#6509) 2025-03-24 09:03:46 -04:00
Danny Avila
4b85fe9206
🔃 fix: Draft Clearing, Claude Titles, Remove Default Vision Max Tokens (#6501)
* refactor: remove legacy max_tokens setting for vision models in OpenAIClient (intended for gpt-4-preview)

* refactor: streamline capability checks in loadAgentTools function, still allow actions if tools are disabled

* fix: enhance error handling for token limits in AnthropicClient and update error message in translations

* feat: append timestamp to cloned agent names for better identification

* chore: update @librechat/agents dependency to version 2.3.94

* refactor: remove clearDraft helper from useSubmitMessage and centralize draft clearing logic to SSE handling, helps prevent user message loss if logout occurs

* refactor: increase debounce time for clearDraft function to improve auto-save performance
2025-03-23 18:47:40 -04:00
Marco Beretta
20f353630e
🗣️ feat: add support for gpt-4o-transcribe models (#6483) 2025-03-23 11:26:06 -04:00
Danny Avila
842b68fc32
🏗️ fix: Agents Token Spend Race Conditions, Add Auto-refill Tx, Add Relevant Tests (#6480)
* 🏗️ refactor: Improve spendTokens logic to handle zero completion tokens and enhance test coverage

* 🏗️ test: Add tests to ensure balance does not go below zero when spending tokens

* 🏗️ fix: Ensure proper continuation in AgentClient when handling errors

* fix: spend token race conditions

* 🏗️ test: Add test for handling multiple concurrent transactions with high balance

* fix: Handle Omni models prompt prefix handling for user messages with array content in OpenAIClient

* refactor: Update checkBalance import paths to use new balanceMethods module

* refactor: Update checkBalance imports and implement updateBalance function for atomic balance updates

* fix: import from replace method

* feat: Add createAutoRefillTransaction method to handle non-balance updating transactions

* refactor: Move auto-refill logic to balanceMethods and enhance checkBalance functionality

* feat: Implement logging for auto-refill transactions in balance checks

* refactor: Remove logRefill calls from multiple client and handler files

* refactor: Move balance checking and auto-refill logic to balanceMethods for improved structure

* refactor: Simplify balance check calls by removing unnecessary balanceRecord assignments

* fix: Prevent negative rawAmount in spendTokens when promptTokens is zero

* fix: Update balanceMethods to use Balance model for findOneAndUpdate

* chore: import order

* refactor: remove unused txMethods file to streamline codebase

* feat: enhance updateBalance and createAutoRefillTransaction methods to support additional parameters for improved balance management
2025-03-22 17:54:25 -04:00
Danny Avila
2ecb167761
🏃‍♂️ refactor: More Agent Context Improvements during Run (#6477)
* fix: Add optional chaining utility and update agent parameter types

* v2.3.9

* chore: Update @librechat/agents version to 2.3.93
2025-03-22 12:38:44 -04:00
Ruben Talstra
3a62a2633d
💵 feat: Add Automatic Balance Refill (#6452)
* 🚀 feat: Add automatic refill settings to balance schema

* 🚀 feat: Refactor balance feature to use global interface configuration

* 🚀 feat: Implement auto-refill functionality for balance management

* 🚀 feat: Enhance auto-refill logic and configuration for balance management

* 🚀 chore: Bump version to 0.7.74 in package.json and package-lock.json

* 🚀 chore: Bump version to 0.0.5 in package.json and package-lock.json

* 🚀 docs: Update comment for balance settings in librechat.example.yaml

* chore: space in `.env.example`

* 🚀 feat: Implement balance configuration loading and refactor related components

* 🚀 test: Refactor tests to use custom config for balance feature

* 🚀 fix: Update balance response handling in Transaction.js to use Balance model

* 🚀 test: Update AppService tests to include balance configuration in mock setup

* 🚀 test: Enhance AppService tests with complete balance configuration scenarios

* 🚀 refactor: Rename balanceConfig to balance and update related tests for clarity

* 🚀 refactor: Remove loadDefaultBalance and update balance handling in AppService

* 🚀 test: Update AppService tests to reflect new balance structure and defaults

* 🚀 test: Mock getCustomConfig in BaseClient tests to control balance configuration

* 🚀 test: Add get method to mockCache in OpenAIClient tests for improved cache handling

* 🚀 test: Mock getCustomConfig in OpenAIClient tests to control balance configuration

* 🚀 test: Remove mock for getCustomConfig in OpenAIClient tests to streamline configuration handling

* 🚀 fix: Update balance configuration reference in config.js for consistency

* refactor: Add getBalanceConfig function to retrieve balance configuration

* chore: Comment out example balance settings in librechat.example.yaml

* refactor: Replace getCustomConfig with getBalanceConfig for balance handling

* fix: tests

* refactor: Replace getBalanceConfig call with balance from request locals

* refactor: Update balance handling to use environment variables for configuration

* refactor: Replace getBalanceConfig calls with balance from request locals

* refactor: Simplify balance configuration logic in getBalanceConfig

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2025-03-21 17:48:11 -04:00
Danny Avila
cbba914290
🛠 feat: Enhance Redis Integration, Rate Limiters & Log Headers (#6462)
* feat: Implement Redis-based rate limiting, initially import limits

* feat: Enhance rate limiters with Redis support and custom prefixes

* chore: import orders

* chore: update JSDoc for next middleware parameter type in ban and limiter middleware

* feat: add logHeaders middleware to log forwarded headers in requests

* refactor: change log level from info to debug for Redis rate limiters

* feat: increase Redis max listeners and refactor session storage to use Keyv
2025-03-21 14:14:45 -04:00
Ruben Talstra
b70d9f1a82
🚀 feat: Add support for LDAP STARTTLS in LDAP Auth (#6438) 2025-03-21 07:55:09 -04:00
Danny Avila
bc88ac846d
🏃‍♂️ refactor: Improve Agent Run Context & Misc. Changes (#6448)
* chore: bump Model Context Protocol SDK dependencies

* fix: correct indentation in MCPConnection class

* refactor: enhance SSE transport with abort controller and add error handling for empty results

* chore: remove outdated Model Context Protocol SDK dependency

* chore: update @modelcontextprotocol/sdk dependency to version 1.7.0

* chore: add debugging comments for PingRequest handling in MCPConnection class

* refactor: update callTool method to accept structured arguments and options

* refactor: simplify maxContextTokens calculation in initializeAgentOptions

* chore: update @babel/runtime dependency to version 7.26.10

* chore: update @librechat/agents dependency to version 2.2.9

* chore: update @librechat/agents dependency to version 2.3.6

* refactor: imports and prevent s3 initialization if strategy not configured

* refactor: mark redis as non-experimental

* refactor: add missing `maxContextTokens` for OpenAI parameters

* refactor: improve log message for Redis initialization

* chore: update @librechat/agents dependency to version 2.3.8

* refactor: extend `streamBuffer` condition to include BEDROCK provider as easily gets throttled by AWS

* refactor: filter out 'think' parts from message content in Anthropic and OpenAI clients
2025-03-20 22:56:57 -04:00
Ruben Talstra
e768a07738
🔐 fix: Invalid Key Length in 2FA Encryption (#6432)
* 🚀 feat: Implement v3 encryption and decryption methods for TOTP secrets

* 🚀 feat: Refactor Two-Factor Authentication methods and enhance 2FA verification process

* 🚀 feat: Update encryption methods to use hex decoding for legacy keys and improve error handling for AES-256-CTR

* 🚀 feat: Update import paths in TwoFactorController for consistency and clarity
2025-03-20 16:46:11 -04:00
Ruben Talstra
692fba51d8
🚀 feat: Add support for custom AWS endpoint in S3 initialization (#6431) 2025-03-20 09:00:59 -04:00
Ruben Talstra
0a4a16d1f7
🚀 feat: Integrate Azure Blob Storage for file handling and image uploads (#6153)
* 🚀 feat: Integrate Azure Blob Storage for file handling and image uploads

* 🐼 refactor: Correct module import case for Azure in strategies.js

* 🚀 feat: Add Azure support in SourceIcon component

* 🚀 feat: Enhance Azure Blob Service initialization with Managed Identity support

* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json

* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json

* 🐼 refactor: Remove unused Azure dependencies from package.json and package-lock.json

* 🚀 feat: Add Azure SDK dependencies for identity and storage blob

* 🔧 fix: Reorganize imports in strategies.js for better clarity

* 🔧 fix: Correct comment formatting in strategies.js for consistency

* 🔧 fix: Improve comment formatting in strategies.js for consistency
2025-03-19 10:45:52 -04:00
heptapod
f95d5aaf4d
🔒feat: Enable OpenID Auto-Redirect (#6066)
* added feature for oidc auto redirection

* Added Cooldown logic for OIDC auto redirect for failed login attempts

* 🔧 feat: Implement custom logout redirect handling and enhance OpenID auto-redirect logic

* 🔧 refactor: Update getLoginError to use TranslationKeys for improved type safety

* 🔧 feat: Localize redirect message to OpenID provider in Login component

---------

Co-authored-by: Ruben Talstra <RubenTalstra1211@outlook.com>
2025-03-19 09:51:56 -04:00