* adding youtube tool
* refactor: use short `url` param instead of `videoUrl`
* refactor: move API key retrieval to a separate credentials module
* refactor: remove unnecessary `isEdited` message property
* refactor: remove unnecessary `isEdited` message property pt. 2
* refactor: YouTube Tool with new `tool()` generator, handle tools already created by new `tool` generator
* fix: only reset request data for multi-convo messages
* refactor: enhance YouTube tool by adding transcript parsing and returning structured JSON responses
* refactor: update transcript parsing to handle raw response and clean up text output
* feat: support toolkits and refactor YouTube tool as a toolkit for better LLM usage
* refactor: remove unused OpenAPI specs and streamline tools transformation in loadAsyncEndpoints
* refactor: implement manifestToolMap for better tool management and streamline authentication handling
* feat: support toolkits for assistants
* refactor: rename loadedTools to toolDefinitions for clarity in PluginController and assistant controllers
* feat: complete support of toolkits for assistants
---------
Co-authored-by: Danilo Pejakovic <danilo.pejakovic@leoninestudios.com>
* implemented Apple Auth login.
Closes: #3438
TODO:
- write config Doc
* removed some comments
* removed comment
* Add unit tests for Apple login strategy
Introduce comprehensive tests for the Apple login strategy, covering new user creation, existing user updates, and error handling scenarios during the authentication flow. Mocks implemented for external dependencies to ensure isolated testing.
* Remove unnecessary blank line in socialLogins.js
* feat: allows admin to see and edits all actions
* feat: allows admin to see and edits all actions
* rollback: admins can edit all actions, no configuration
* fix: admins don't override the user of existing actions and they preserve the user of the assistant when creating a new action
---------
Co-authored-by: Olivier Schiavo <olivier.schiavo@wengo.com>
* chore: remove all bing code
* chore: remove bing code and auto-focus effects
* chore: add back escapeRegExp helper function for regex special character handling
* chore: remove deprecated fields from settings and conversation schema
* fix: ensure default endpoint is set correctly in conversation setup
* feat: add disableFocus option to newConversation for improved search behavior
* ✨ feat: Implement Show Thinking feature; refactor: testing thinking render optimizations
* ✨ feat: Refactor Thinking component styles and enhance Markdown rendering
* chore: add back removed code, revert type changes
* chore: Add back resetCounter effect to Markdown component for improved code block indexing
* chore: bump @librechat/agents and google langchain packages
* WIP: reasoning type updates
* WIP: first pass, reasoning content blocks
* chore: revert code
* chore: bump @librechat/agents
* refactor: optimize reasoning tag handling
* style: ul indent padding
* feat: add Reasoning component to handle reasoning display
* feat: first pass, content reasoning part styling
* refactor: add content placeholder for endpoints using new stream handler
* refactor: only cache messages when requesting stream audio
* fix: circular dep.
* fix: add default param
* refactor: tts, only request after message stream, fix chrome autoplay
* style: update label for submitting state and add localization for 'Thinking...'
* fix: improve global audio pause logic and reset active run ID
* fix: handle artifact edge cases
* fix: remove unnecessary console log from artifact update test
* feat: add support for continued message handling with new streaming method
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* 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
