- **Unified UI Components**: Replace custom MCPVariableEditor with CustomUserVarsSection and ServerInitializationSection for consistent design across all MCP interfaces
- **Real-Time Status Indicators**: Add live connection status badges and set/unset authentication pills to match MCPConfigDialog functionality
- **Enhanced OAuth Support**: Integrate ServerInitializationSection for proper OAuth flow handling in side panel
- **Real-Time Connection Status**: New backend APIs and React Query hooks provide live MCP server connection monitoring with automatic UI updates
- **OAuth Flow Components**: Complete MCPConfigDialog, ServerInitializationSection, and CustomUserVarsSection with OAuth URL handling and polling-based completion
- **Enhanced Server Selection**: MCPSelect component with connection-aware filtering, visual status indicators, and better credential management UX
(still needs a lot of refinement since there is bloat/unused vars and functions leftover from the ideation phase on how to approach OAuth and connection statuses)
* ✨ feat: Add MCP Reinitialization to MCPPanel
- Refactored tool caching to include user-specific tools in various service files.
- Refactored MCPManager class for clarity
- Added a new endpoint for reinitializing MCP servers, allowing for dynamic updates of server configurations.
- Enhanced the MCPPanel component to support server reinitialization with user feedback.
* 🔃 refactor: Simplify Plugin Deduplication and Clear Cache Post-MCP Initialization
- Replaced manual deduplication of tools with the dedicated `filterUniquePlugins` function for improved readability.
- Added back cache clearing for tools after MCP initialization to ensure fresh data is used.
- Removed unused exports from `PluginController.js` to clean up the codebase.
* refactor: Move draft-related utilities to a new `drafts.ts` file
* refactor: auto-save draft logic to use new get/set functions
* fix: Ensure `getDraft` properly decodes stored draft values
* fix: Handle edge case where stream is cancelled before any response, which creates a blank page
- Updated the logic to auto-enable the Responses API when web search is enabled, specifically for OpenAI, Azure, and Custom endpoints.
- Added import for EModelEndpoint to facilitate endpoint compatibility checks.
* 🌊 feat: Add Disable Streaming Option in Configuration
- Introduced a new setting to disable streaming responses in openAI, Azure, and custom endpoint parameter panels.
- Updated translation files to include labels and descriptions for the disable streaming feature.
- Modified relevant schemas and parameter settings to support the new disable streaming functionality.
* 🔧 fix: disableStreaming state not persisting when returning to a conversation
- Added disableStreaming field to the IPreset interface and conversationPreset.
- Moved toggles and sliders around for nicer left-right UI split in parameters panel.
- Removed old reference to 'grounding' ub conversationPreset (now web_search) and added web_search to IPreset.
* fix: Add `isRegenerate` flag to chat payload to avoid saving temporary response IDs
* fix: Remove unused `isResubmission` flag
* ci: Add tests for responseMessageId regeneration logic in BaseClient
* 🔧 fix: Handle optional arguments in `useParseArgs` and improve tool call condition
* chore: Remove math plugins from `MarkdownLite`
* ✨ feat: Add Error Boundary to Markdown Component for Enhanced Error Handling
- Introduced `MarkdownErrorBoundary` to catch and display errors during Markdown rendering.
- Updated the `Markdown` component to utilize the new error boundary, improving user experience by handling rendering issues gracefully.
* Revert "chore: Remove math plugins from `MarkdownLite`"
This reverts commit d393099d52.
* ✨ feat: Introduce MarkdownErrorBoundary for improved error handling in Markdown components
* refactor: include most markdown elements in error boundary fallback, aside from problematic plugins
* Updated the PATCH /memories/:key endpoint to allow key changes while ensuring no duplicate keys exist.
* Improved error handling in MemoryCreateDialog and MemoryEditDialog for key validation and duplication scenarios.
* Added a new translation for memory key validation error in translation.json.
* chore: bump @librechat/agents to ^2.4.54 for anthropic web search support
* WIP: hardcoded web search tool usage
* feat: Implement web search functionality in Anthropic integration
- Updated parameters panel to include web search for anthropic models.
- Updated necessary schemas to accomodate toggle functionality
* chore: Set default web search option to false in anthropicSettings
* refactor: Rename webSearch to web_search for consistency across settings and schemas
* chore: bump @librechat/agents to v2.4.55
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* 🔍 feat: Add SearXNG Web Search support and enhance ApiKeyDialog
- Updated WebSearch component to include authentication data for web search functionality so it won't show badge after being revoked
- Refactored ApiKeyDialog to streamline provider, scraper, and reranker selection with new InputSection component
- Added support for SearXNG as a search provider and updated translation files accordingly
- Improved form handling in useAuthSearchTool to accommodate new API keys and URLs
* 📜 chore: remove unused i18next key
* 📦 chore: address comments (swap API key and URL fields in SearXNG config, change input fields to 'text' from 'password'
* 📦 chore: make URL fields go first in ApiKeyDialog
* chore: bump @librechat/agents to v2.4.52
* ci: update webSearch configuration to include searxng fields in AppService.spec.js
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* chore: Improve error logging for fetching conversations, and use new TS packages for utils
* feat: Implement fork limiters for conversation forking requests
* chore: error message for conversation index deletion to clarify syncing behavior
* feat: Enhance error handling for forking with rate limit message
* feat: add useAgentCapabilities hook to manage agent capabilities
* refactor: move agents and endpoints configuration to AgentPanel context provider
* refactor: implement useGetAgentsConfig hook for consolidated agents and endpoints management
* refactor: enhance ToolsDropdown to utilize agent capabilities and streamline dropdown item rendering
* chore: reorder return values in useAgentCapabilities for improved clarity
* refactor: enhance agent capabilities handling in AttachFileMenu and update file handling logic to allow capabilities to be used for non-agents endpoints
* 🔧 fix: Update type annotations in useEventHandlers for better type safety
* 🔧 refactor: `useToolToggle` for improved localStorage synchronization and allow string/falsy values for setting to storage
* ✨ feat: Implement Artifacts badge to BadgeRow with toggle options and UI components
- Added Artifacts component to manage artifacts state and options.
- Introduced ArtifactsSubMenu for additional settings related to artifacts.
- Integrated artifacts functionality into BadgeRow and ToolsDropdown components.
- Updated localStorage handling for artifacts state persistence.
- Enhanced localization for artifacts-related strings in translation files.
- Refactored Agent model to include artifacts in the ephemeral agent response.
* fix: set ephemeral agent state for conversation on finalization
* chore: remove beta settings dialog tab
* refactor: improve Ephemeral Agent statefulness
* fix: update setValue parameter to use 'value' instead of 'isChecked' in CheckboxButton
* refactor: update color classes for Artifact toggle and order of dropdown components
* chore: remove unused i18n localization
* 🔍 feat: Introduce Web Search Functionality for OpenAI API
- Added a new web_search parameter to enable web search capabilities in the OpenAI configuration.
- Updated the DynamicSlider component for improved styling.
- Enhanced the useSetIndexOptions hook to auto-enable the Responses API when web search is activated.
- Modified relevant schemas, types, and translation files to support the new web search feature.
* chore: remove comments
* refactor: tool handling in initializeAgent for better clarity and functionality and reflection of openai features
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* ✨ feat: Add Google Search Grounding Feature and Update Agent Tool Initialization
- Introduced a new grounding option in the Google configuration to enable real-time web search results.
- Updated the agent initialization to concatenate additional tools from options.
- Enhanced translation files to include descriptions for the new grounding feature.
- Modified relevant schemas and parameter settings to support the grounding functionality.
* 🔑 chore: Update @librechat/agents dependency to version 2.4.50
* ✅ fix: Ensure tools array is initialized before concatenation in initializeAgent function
* chore: Update version of librechat-data-provider to 0.7.899 and add GOOGLE_TOOL_CONFLICT error type
* fix: Adjust label class for better text wrapping in DynamicSwitch component
* fix: Handle Google tool conflict error and update error messages in translation
* fix: Restore grounding setting in googleCol2 configuration
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🐛 fix: Enhance provider validation and error handling in getProviderConfig function
* WIP: edit text part
* refactor: Allow updating of both TEXT and THINK content types in message updates
* WIP: first pass, save & submit
* chore: remove legacy generation user message field
* feat: merge edited content
* fix: update placeholder and description for bedrock setting
* fix: remove unsupported warning message for AI resubmission
* chore: update @librechat/agents to v2.4.47
* WIP: temporary auto-toggle responses api for o1/o3-pro
* feat: Enable Responses API for OpenAI models
- Updated the OpenAI client initialization to check for the useResponsesApi parameter in model options.
- Added translations for enabling the Responses API in the UI.
- Introduced useResponsesApi parameter in data provider settings and schemas.
- Updated relevant schemas to include useResponsesApi for conversation and preset configurations.
* refactor: Remove useResponsesApi check from OpenAI client initialization and update translation for Responses API
- Removed the check for useResponsesApi in the OpenAI client initialization.
- Updated the translation for enabling the Responses API to clarify its functionality.
* chore: update @librechat/agents dependency to version 2.4.48
* chore: update @librechat/agents dependency to version 2.4.49
* chore: linting
* chore: linting
* feat: Enhance DynamicSlider and validation for enumMappings
- Added support for enumMappings in DynamicSlider to display values correctly based on enum settings.
- Implemented validation for enumMappings in the generate function to ensure all options have corresponding mappings.
- Added tests for handling empty string options and incomplete enumMappings in the generate.spec.ts file.
* feat: Enhance DynamicSlider localization support
- Added localization handling for mapped values in DynamicSlider when using enumMappings.
- Updated the logic to check if the mapped value is a localization key and return the localized string if applicable.
- Adjusted dependencies in useCallback hooks to include localize for proper functionality.
* feat: Add reasoning summary and effort options to OpenAI configuration and UI
* feat: Add enumMappings for ImageDetail options in parameter settings
* style: Improve styling for DynamicSlider component labels and inputs
* chore: Update reasoning effort description and parameter order for OpenAI params
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* refactor: access control logic to TypeScript
* chore: Change EndpointURLs to a constant object for improved type safety
* 🐛 fix: Enhance agent access control by adding skipAgentCheck functionality
* 🐛 fix: Add endpointFileConfig prop to AttachFileMenu and update file handling logic
* 🐛 fix: Update tool handling logic to support optional groupedTools and improve null checks, add dedicated tool dialog for Assistants
* chore: Export Accordion component from UI index for improved modularity
* feat: Add ActivePanelContext for managing active panel state across components
* chore: Replace string IDs with EModelEndpoint constants for assistants and agents in useSideNavLinks
* fix: Integrate access checks for agent creation and deletion routes in actions.js
* feat: support thinking budget parameter for Gemini 2.5 series (#6949, #7542)
https://ai.google.dev/gemini-api/docs/thinking#set-budget
* refactor: update thinking budget minimum value to -1 for dynamic thinking
- see: https://ai.google.dev/gemini-api/docs/thinking#set-budget
* chore: bump @librechat/agents to v2.4.43
* refactor: rename LLMConfigOptions to OpenAIConfigOptions for clarity and consistency
- Updated type definitions and references in initialize.ts, llm.ts, and openai.ts to reflect the new naming convention.
- Ensured that the OpenAI configuration options are consistently used across the relevant files.
* refactor: port Google LLM methods to TypeScript Package
* chore: update @librechat/agents version to 2.4.43 in package-lock.json and package.json
* refactor: update thinking budget description for clarity and adjust placeholder in parameter settings
* refactor: enhance googleSettings default value for thinking budget to support dynamic adjustment
* chore: update @librechat/agents to v2.4.44 for Vertex Dynamic Thinking workaround
* refactor: rename google config function, update `createRun` types, use `reasoning` as `reasoningKey` for Google
* refactor: simplify placeholder handling in DynamicInput component
* refactor: enhance thinking budget description for clarity and allow automatic decision by setting to "-1"
* refactor: update text styling in OptionHover component for improved readability
* chore: update @librechat/agents dependency to v2.4.46 in package.json and package-lock.json
* chore: update @librechat/api version to 1.2.5 in package.json and package-lock.json
* refactor: enhance `clientOptions` handling by filtering `omitTitleOptions`, add `json` field for Google models
---------
Co-authored-by: ciffelia <15273128+ciffelia@users.noreply.github.com>
* 🔧 fix: Adjust typography and border styles for improved readability in markdown components
* 🔧 fix: Enhance code block styling in markdown for better visibility and consistency
* 🔧 fix: Adjust margins and line heights for improved readability in markdown elements
* 🔧 fix: Adjust spacing for horizontal rules in markdown for improved consistency
* 🔧 fix: Refactor DialogImage component for improved quality styling and layout consistency
* 🔧 fix: Enhance zoom and pan functionality in DialogImage component with improved controls and user experience
* 🔧 fix: Improve zoom and pan functionality in DialogImage component with enhanced controls and reset zoom feature
* new env variable for mcp label
* 🔄 refactor: Update MCPSelect placeholderText to draw from interface section of librechat.yaml rather than .env
* 🧹 chore: extract mcpServers schema for better maintainability
* 🔄 refactor: Update MCPSelect and useMCPSelect to utilize TPlugin type for better type consistency
* 🔄 refactor: Pass placeholder from startupConfig to MCPSubMenu for improved localization
* 🔄 refactor: Integrate startupConfig into BadgeRowContext and related components for enhanced configuration management
---------
Co-authored-by: mwbrandao <mariana.brandao@nos.pt>
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor(buildEndpointOption): Improve error logging in middleware, consolidate `isAgents` builder logic, remove adding `modelsConfig` to `endpointOption`
* refactor: parameter extraction and organization in agent services, minimize redundancy of shared fields across objects, make clear distinction of parameters processed uniquely by LibreChat vs LLM Provider Configs
* refactor(createPayload): streamline all endpoints to agent route
* fix: add `modelLabel` to response sender options for agent initialization
* chore: correct log message context in EditController abort controller cleanup
* chore: remove unused abortRequest hook
* chore: remove unused addToCache module and its dependencies
* refactor: remove AskController and related routes, update endpoint URLs (now all streamlined to agents route)
* chore: remove unused bedrock route and its related imports
* refactor: simplify response sender logic for Google endpoint
* chore: add `modelDisplayLabel` handling for agents endpoint
* feat: add file search capability to ephemeral agents, update code interpreter selection based of file upload, consolidate main upload menu for all endpoints
* feat: implement useToolToggle hook for managing tool toggle state, refactor CodeInterpreter and WebSearch components to utilize new hook
* feat: add ToolsDropdown component to BadgeRow for enhanced tool options
* feat: introduce BadgeRowContext and BadgeRowProvider for managing conversation state, refactor related components to utilize context
* feat: implement useMCPSelect hook for managing MCP selection state, refactor MCPSelect component to utilize new hook
* feat: enhance BadgeRowContext with MCPSelect and tool toggle functionality, refactor related components to utilize updated context and hooks
* refactor: streamline useToolToggle hook by integrating setEphemeralAgent directly into toggle logic and removing redundant setValue function
* refactor: consolidate codeApiKeyForm and searchApiKeyForm from CodeInterpreter and WebSearch to utilize new context properties
* refactor: update CheckboxButton to support controlled state and enhance ToolsDropdown with permission-based toggles for web search and code interpreter
* refactor: conditionally render CheckboxButton in CodeInterpreter and WebSearch components for improved UI responsiveness
* chore: add jotai dependency to package.json and package-lock.json
* chore: update brace-expansion package to version 2.0.2 in package-lock.json due to CVE-2025-5889
* Revert "chore: add jotai dependency to package.json and package-lock.json"
This reverts commit 69b6997396.
* refactor: add pinning functionality to CodeInterpreter and WebSearch components, and enhance ToolsDropdown with pin toggle for web search and code interpreter
* chore: move MCPIcon to correct location, remove duplicate
* fix: update MCP import to use type-only import from librechat-data-provider
* feat: implement MCPSubMenu component and integrate pinning functionality into ToolsDropdown
* fix: cycling to submenu by using parent menu context
* feat: add FileSearch component and integrate it into BadgeRow and ToolsDropdown
* chore: import order
* chore: remove agent specific logic that would block functionality for streamlined endpoints
* chore: linting for `createContextHandlers`
* chore: ensure ToolsDropdown doesn't show up for agents
* chore: ensure tool resource is selected when dragged to UI
* chore: update file search behavior to simulate legacy functionality
* feat: ToolDialogs with multiple trigger references, add settings to tool dropdown
* refactor: simplify web search and code interpreter settings checks
* chore: simplify local storage key for pinned state in useToolToggle
* refactor: reinstate agent check in AttachFileChat component, as individual providers will ahve different file configurations
* ci: increase timeout for MongoDB connection in Agent tests
* chore: update peer dependency for @librechat/agents to version 2.4.41
* 🔧 chore: proxy handling in OpenAI endpoint to use undici
* 🔧 chore: update @anthropic-ai/sdk to version 0.52.0 and refactor proxy handling to use undici
* 🔧 chore: update globIgnores in vite.config.ts to exclude index.html from caching
* 🔧 ci: update proxy handling in getLLMConfig to use fetchOptions and ProxyAgent
* 🔧 chore: refactor proxy handling in Anthropic and OpenAI clients to use fetchOptions
* refactor: agent initialization to streamline model parameters and resendFiles handling
* chore: update @google/generative-ai to version 0.24.0
* fix: Use mutable version of conversation in useChatFunctions
* fix: Use cloneDeep for conversation in useChatFunctions to ensure immutability
---------
Co-authored-by: lucioperca <lucioperca@users.noreply.github.com>
* 🗝️ feat: Per-User Credentials for MCP Servers
chore: add aider to gitignore
feat: fill custom variables to MCP server
feat: replace placeholders with custom user MCP variables
feat: handle MCP install/uninstall (uses pluginauths)
feat: add MCP custom variables dialog to MCPSelect
feat: add MCP custom variables dialog to the side panel
feat: do not require to fill MCP credentials for in tools dialog
feat: add translations keys (en+cs) for custom MCP variables
fix: handle LIBRECHAT_USER_ID correctly during MCP var replacement
style: remove unused MCP translation keys
style: fix eslint for MCP custom vars
chore: move aider gitignore to AI section
* feat: Add Plugin Authentication Methods to data-schemas
* refactor: Replace PluginAuth model methods with new utility functions for improved code organization and maintainability
* refactor: Move IPluginAuth interface to types directory for better organization and update pluginAuth schema to use the new import
* refactor: Remove unused getUsersPluginsAuthValuesMap function and streamline PluginService.js; add new getPluginAuthMap function for improved plugin authentication handling
* chore: fix typing for optional tools property with GenericTool[] type
* chore: update librechat-data-provider version to 0.7.88
* refactor: optimize getUserMCPAuthMap function by reducing variable usage and improving server key collection logic
* refactor: streamline MCP tool creation by removing customUserVars parameter and enhancing user-specific authentication handling to avoid closure encapsulation
* refactor: extract processSingleValue function to streamline MCP environment variable processing and enhance readability
* refactor: enhance MCP tool processing logic by simplifying conditions and improving authentication handling for custom user variables
* ci: fix action tests
* chore: fix imports, remove comments
* chore: remove non-english translations
* fix: remove newline at end of translation.json file
---------
Co-authored-by: Aleš Kůtek <kutekales@gmail.com>
* ✨ feat: Enhance Agent Panel with Tool Grouping
* 🧰 feat: Added support for grouping tools in the Agent Panel, allowing for better organization and management of related tools.
* 💡 feat: Added hovercards for tools belonging to a group which display their tool descriptions when their help icon is hovered over.
* 🧹 chore: Updated the AgentPanelContext to include grouped tools and their metadata.
* 🔨 refactor: Refactored AgentConfig and AgentTool components to utilize the new tool structure and enhance rendering logic.
* 🔍 feat: Improved the ToolSelectDialog to filter and display tools based on user input, including searching for tools within a group, and limits viewport height to prevent overflowing vertically on smaller screens.
This update enhances the overall functionality and usability of the Agent Panel, making it easier for users to interact with tools.
* Potential fix for code scanning alert no. 6217: Disallow unused variables
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* fix: Agent tool type mismatches
* fix: accessibility issues and mcp tool overflow issue
* fix: enhance keyboard accessibility and prevent event propagation in AgentTool
* chore: WIP types
* chore: address comments and fix accordian collapse bug
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Markdown LaTeX processing
- Added micromark-extension-llm-math as a dependency in package.json and package-lock.json.
- Updated Vite configuration to alias micromark-extension-math.
- Modified Markdown components to use singleDollarTextMath: false for improved LaTeX rendering.
- Refactored latex utility functions to enhance LaTeX processing and escaping mechanisms.
* chore: linting of `EditTextPart`
* fix: handle key up to initiate edit of latest user message by adding id prop to Edit Message HoverButton
* chore: linting in Artifact component
* refactor: enhance LaTeX preprocessing functionality
- Updated `preprocessLaTeX` to improve handling of currency and LaTeX expressions.
- Introduced optimized regex patterns for better performance.
- Added support for escaping mhchem commands and handling code blocks.
- Enhanced tests for various LaTeX scenarios, including currency and special characters.
- Refactored existing tests to align with new preprocessing logic.
* chore: filter out false positives in unused packages workflow
- Added a grep command to exclude the micromark-extension-llm-math package from the list of unused dependencies in the GitHub Actions workflow.
