* feat: Google Model Parameters
* fix: dynamic input number value, previously coerced by zod schema
* refactor: support openrouter reasoning tokens and XML for thinking directive to conform to ollama
* fix: virtualize combobox to prevent performance drop on re-renders of long model/agent/assistant lists
* refactor: simplify Fork component by removing unnecessary chat context index
* fix: prevent rendering of Thinking component when children are null
* refactor: update Markdown component to replace <think> tags and simplify remarkPlugins configuration
* refactor: reorder remarkPlugins to improve plugin configuration in Markdown component
* fix: google-thinking model safety settings fix
* chore: update pricing/context for deepseek models
* ci: update Deepseek model token limits to use dynamic mapping
* 🔄 refactor: frontend and backend share link logic; feat: qrcode for share link; feat: refresh link
* 🐛 fix: Conditionally render shared link and refactor share link creation logic
* 🐛 fix: Correct conditional check for shareId in ShareButton component
* 🔄 refactor: Update shared links API and data handling; improve query parameters and response structure
* 🔄 refactor: Update shared links pagination and response structure; replace pageNumber with cursor for improved data fetching
* 🔄 refactor: DataTable performance optimization
* fix: delete shared link cache update
* 🔄 refactor: Enhance shared links functionality; add conversationId to shared link model and update related components
* 🔄 refactor: Add delete functionality to SharedLinkButton; integrate delete mutation and confirmation dialog
* 🔄 feat: Add AnimatedSearchInput component with gradient animations and search functionality; update search handling in API and localization
* 🔄 refactor: Improve SharedLinks component; enhance delete functionality and loading states, optimize AnimatedSearchInput, and refine DataTable scrolling behavior
* fix: mutation type issues with deleted shared link mutation
* fix: MutationOptions types
* fix: Ensure only public shared links are retrieved in getSharedLink function
* fix: `qrcode.react` install location
* fix: ensure non-public shared links are not fetched when checking for existing shared links, and remove deprecated .exec() method for queries
* fix: types and import order
* refactor: cleanup share button UI logic, make more intuitive
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🔧 refactor: Remove unused penalties and enhance reasoning token handling in OpenAIClient
* 🔧 refactor: `addInstructions` default to adding instructions at index 0, flag for legacy behavior
* chore: remove long placeholder
* chore: update localization strings across multiple languages
* ci: adjust tests for new `addInstructions` behavior
* ✨ feat: Add OpenWeather Tool for Weather Data Retrieval 🌤️
* chore: linting
* chore: move test files
* fix: tool icon, allow user-provided keys, conform to app key assignment pattern
* chore: linting not included in #5212
---------
Co-authored-by: Jonathan Addington <jonathan.addington@jmaddington.com>
* fix: Include iconURL in Bedrock client initialization
* fix: unnecessary filtering for agent file_search files
* chore: use theme bg colors
* refactor: rely on endpoint config for enabling builder links in side navigation instead of parameters
* fix: remove unnecessary keyProvided check for agent builder link
The `express-session` library comes with a session storage meant for
testing by default. That is why you get a message like this when you
start up LibreChat with OIDC enabled:
Warning: connect.session() MemoryStore is not
designed for a production environment, as it will leak
memory, and will not scale past a single process.
LibreChat can already use Redis as a session storage, although Redis support
is still marked as experimental. It also makes the set-up more complex, since
you will need to configure and run yet another service.
This pull request provides a simple alternative by using a in-memory session
store marked as a production-ready alternative by the guys from
`express-session`¹. You can still configure Redis, but this provides a simple,
good default for everyone else.
See also https://github.com/danny-avila/LibreChat/discussions/1014
¹⁾ https://github.com/expressjs/session?tab=readme-ov-file#compatible-session-stores
* 🐛 fix: default modelSpecs not being set
* feat: Add imageDetail parameter for OpenAI endpoints in tQueryParamsSchema
* feat: Implement processModelSpecs function to enhance model specs processing from configuration
* feat: Refactor configuration schemas and types for improved structure and clarity
* feat: Add append_current_datetime parameter to tQueryParamsSchema for enhanced endpoint functionality
* fix: Add endpointType to getSaveOptions and enhance endpoint handling in Settings component
* fix: Change endpointType to be nullable and optional in tConversationSchema for improved flexibility
* fix: allow save & submit for google endpoint
* fix: agent modelSpec iconURLs not being recorded
* fix: prioritize message properties over conversation defaults in icon data
* fix: determine endpoint type from endpointsConfig
* chore: type issue with setting.columnSpan
* chore: remove redundant key indexing for keySchema
* chore: bump version to 0.7.691 in package.json
* chore: add stricter remark-gfm and mdast-util-gfm resolutions/overrides
* chore: remove rollup override and bump vite-plugin-pwa
* chore: reinstall remark-gfm for correct module resolution
* chore: reinstall vite-plugun-pwa
* chore: bump @librechat/agents to v1.9.8 for rscript support
* chore: fix @langchain/google-genai dep., match agents
* chore: fix @langchain/google-vertexai to v0.1.5, match with agents
* chore: bump @librechat/agents to v1.9.9
* chore: update @librechat/agents to v1.9.91 and @langchain/google-vertexai to v0.1.6
* chore: increase MAX_FILE_SIZE to 150MB for file uploads
* chore: bump @librechat/agents to v1.9.92
* feat: support `recursionLimit` for agents
* chore: update configuration version to 1.2.1 in librechat.yaml and config.ts
* feat: add R language SVG icon to the assets and include it in ApiKeyDialog
* feat: add support for new vision model 'o1' and exclude 'o1-mini'
This commit updates the cache stores in the `getLogStores.js` file to use Redis as the store if the `USE_REDIS` environment variable is enabled. It also adds a new environment variable `DEBUG_MEMORY_CACHE` to enable debugging of the memory cache.
* feat: Refactor ModelEndHandler to collect usage metadata only if it exists
* feat: google tool end handling, custom anthropic class for better token ux
* refactor: differentiate between client <> request options
* feat: initial support for google agents
* feat: only cache messages with non-empty text
* feat: Cache non-empty messages in chatV2 controller
* fix: anthropic llm client options llmConfig
* refactor: streamline client options handling in LLM configuration
* fix: VertexAI Agent Auth & Tool Handling
* fix: additional fields for llmConfig, however customHeaders are not supported by langchain, requires PR
* feat: set default location for vertexai LLM configuration
* fix: outdated OpenAI Client options for getLLMConfig
* chore: agent provider options typing
* chore: add note about currently unsupported customHeaders in langchain GenAI client
* fix: skip transaction creation when rawAmount is NaN
* 🔒 fix: update refresh token handling to use plain token instead of hashed token
* 🔒 fix: simplify logoutUser by using plain refresh token for session lookup
* ✨ feat: Implement session management with CRUD operations and integrate into user workflows
* ✨ refactor: Update session model import paths and enhance session creation logic in AuthService
* ✨ refactor: Validate session and user ID formats in session management functions
* ✨ style: Enhance UI components with improved styling and accessibility features
* chore: Update login form tests to use getByTestId instead of getByRole, remove console.log()
* chore: Update login form tests to use getByTestId instead of getByRole
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* docs: Update README to include Model Context Protocol support and enhance access descriptions
* fix: Update civic integrity threshold to use 'BLOCK_NONE' as default
* fix: Update GOOGLE_MODELS in .env.example and adjust civic integrity threshold for new model compatibility
* ✨ v0.7.6
* feat: Add 'gemini-2.0-flash-thinking-exp' model to googleModels context windows
* 📝 chore: Add comment to clarify purpose of check_updates.sh script
* feat: mcp package
* feat: add librechat-mcp package and update dependencies
* feat: refactor MCPConnectionSingleton to handle transport initialization and connection management
* feat: change private methods to public in MCPConnectionSingleton for improved accessibility
* feat: filesystem demo
* chore: everything demo and move everything under mcp workspace
* chore: move ts-node to mcp workspace
* feat: mcp examples
* feat: working sse MCP example
* refactor: rename MCPConnectionSingleton to MCPConnection for clarity
* refactor: replace MCPConnectionSingleton with MCPConnection for consistency
* refactor: manager/connections
* refactor: update MCPConnection to use type definitions from mcp types
* refactor: update MCPManager to use winston logger and enhance server initialization
* refactor: share logger between connections and manager
* refactor: add schema definitions and update MCPManager to accept logger parameter
* feat: map available MCP tools
* feat: load manifest tools
* feat: add MCP tools delimiter constant and update plugin key generation
* feat: call MCP tools
* feat: update librechat-data-provider version to 0.7.63 and enhance StdioOptionsSchema with additional properties
* refactor: simplify typing
* chore: update types/packages
* feat: MCP Tool Content parsing
* chore: update dependencies and improve package configurations
* feat: add 'mcp' directory to package and update configurations
* refactor: return CONTENT_AND_ARTIFACT format for MCP callTool
* chore: bump @librechat/agents
* WIP: MCP artifacts
* chore: bump @librechat/agents to v1.8.7
* fix: ensure filename has extension when saving base64 image
* fix: move base64 buffer conversion before filename extension check
* chore: update backend review workflow to install MCP package
* fix: use correct `mime` method
* fix: enhance file metadata with message and tool call IDs in image saving process
* fix: refactor ToolCall component to handle MCP tool calls and improve domain extraction
* fix: update ToolItem component for default isInstalled value and improve localization in ToolSelectDialog
* fix: update ToolItem component to use consistent text color for tool description
* style: add theming to ToolSelectDialog
* fix: improve domain extraction logic in ToolCall component
* refactor: conversation item theming, fix rename UI bug, optimize props, add missing types
* feat: enhance MCP options schema with base options (iconPath to start) and make transport type optional, infer based on other option fields
* fix: improve reconnection logic with parallel init and exponential backoff and enhance transport debug logging
* refactor: improve logging format
* refactor: improve logging of available tools by displaying tool names
* refactor: improve reconnection/connection logic
* feat: add MCP package build process to Dockerfile
* feat: add fallback icon for tools without an image in ToolItem component
* feat: Assistants Support for MCP Tools
* fix(build): configure rollup to use output.dir for dynamic imports
* chore: update @librechat/agents to version 1.8.8 and add @langchain/anthropic dependency
* fix: update CONFIG_VERSION to 1.2.0
