* 📎 feat: Direct Provider Attachment Support for Multimodal Content
* 📑 feat: Anthropic Direct Provider Upload (#9072)
* feat: implement Anthropic native PDF support with document preservation
- Add comprehensive debug logging throughout PDF processing pipeline
- Refactor attachment processing to separate image and document handling
- Create distinct addImageURLs(), addDocuments(), and processAttachments() methods
- Fix critical bugs in stream handling and parameter passing
- Add streamToBuffer utility for proper stream-to-buffer conversion
- Remove api/agents submodule from repository
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: remove out of scope formatting changes
* fix: stop duplication of file in chat on end of response stream
* chore: bring back file search and ocr options
* chore: localize upload to provider string in file menu
* refactor: change createMenuItems args to fit new pattern introduced by anthropic-native-pdf-support
* feat: add cache point for pdfs processed by anthropic endpoint since they are unlikely to change and should benefit from caching
* feat: combine Upload Image into Upload to Provider since they both perform direct upload and change provider upload icon to reflect multimodal upload
* feat: add citations support according to docs
* refactor: remove redundant 'document' check since documents are handled properly by formatMessage in the agents repo now
* refactor: change upload logic so anthropic endpoint isn't exempted from normal upload path using Agents for consistency with the rest of the upload logic
* fix: include width and height in return from uploadLocalFile so images are correctly identified when going through an AgentUpload in addImageURLs
* chore: remove client specific handling since the direct provider stuff is handled by the agent client
* feat: handle documents in AgentClient so no need for change to agents repo
* chore: removed unused changes
* chore: remove auto generated comments from OG commit
* feat: add logic for agents to use direct to provider uploads if supported (currently just anthropic)
* fix: reintroduce role check to fix render error because of undefined value for Content Part
* fix: actually fix render bug by using proper isCreatedByUser check and making sure our mutation of formattedMessage.content is consistent
---------
Co-authored-by: Andres Restrepo <andres@thelinuxkid.com>
Co-authored-by: Claude <noreply@anthropic.com>
📁 feat: Send Attachments Directly to Provider (OpenAI) (#9098)
* refactor: change references from direct upload to direct attach to better reflect functionality
since we are just using base64 encoding strategy now rather than Files/File API for sending our attachments directly to the provider, the upload nomenclature no longer makes sense. direct_attach better describes the different methods of sending attachments to providers anyways even if we later introduce direct upload support
* feat: add upload to provider option for openai (and agent) ui
* chore: move anthropic pdf validator over to packages/api
* feat: simple pdf validation according to openai docs
* feat: add provider agnostic validatePdf logic to start handling multiple endpoints
* feat: add handling for openai specific documentPart formatting
* refactor: move require statement to proper place at top of file
* chore: add in openAI endpoint for the rest of the document handling logic
* feat: add direct attach support for azureOpenAI endpoint and agents
* feat: add pdf validation for azureOpenAI endpoint
* refactor: unify all the endpoint checks with isDocumentSupportedEndpoint
* refactor: consolidate Upload to Provider vs Upload image logic for clarity
* refactor: remove anthropic from anthropic_multimodal fileType since we support multiple providers now
🗂️ feat: Send Attachments Directly to Provider (Google) (#9100)
* feat: add validation for google PDFs and add google endpoint as a document supporting endpoint
* feat: add proper pdf formatting for google endpoints (requires PR #14 in agents)
* feat: add multimodal support for google endpoint attachments
* feat: add audio file svg
* fix: refactor attachments logic so multi-attachment messages work properly
* feat: add video file svg
* fix: allows for followup questions of uploaded multimodal attachments
* fix: remove incorrect final message filtering that was breaking Attachment component rendering
fix: manualy rename 'documents' to 'Documents' in git since it wasn't picked up due to case insensitivity in dir name
fix: add logic so filepicker for a google agent has proper filetype filtering
🛫 refactor: Move Encoding Logic to packages/api (#9182)
* refactor: move audio encode over to TS
* refactor: audio encoding now functional in LC again
* refactor: move video encode over to TS
* refactor: move document encode over to TS
* refactor: video encoding now functional in LC again
* refactor: document encoding now functional in LC again
* fix: extend file type options in AttachFileMenu to include 'google_multimodal' and update dependency array to include agent?.provider
* feat: only accept pdfs if responses api is enabled for openai convos
chore: address ESLint comments
chore: add missing audio mimetype
* fix: type safety for message content parts and improve null handling
* chore: reorder AttachFileMenuProps for consistency and clarity
* chore: import order in AttachFileMenu
* fix: improve null handling for text parts in parseTextParts function
* fix: remove no longer used unsupported capability error message for file uploads
* fix: OpenAI Direct File Attachment Format
* fix: update encodeAndFormatDocuments to support OpenAI responses API and enhance document result types
* refactor: broaden providers supported for documents
* feat: enhance DragDrop context and modal to support document uploads based on provider capabilities
* fix: reorder import statements for consistency in video encoding module
---------
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
* WIP: conversion of `ocr` to `context`
* refactor: make `primeResources` backwards-compatible for `ocr` tool_resources
* refactor: Convert legacy `ocr` tool resource to `context` in agent updates
- Implemented conversion logic to replace `ocr` with `context` in both incoming updates and existing agent data.
- Merged file IDs and files from `ocr` into `context` while ensuring deduplication.
- Updated tools array to reflect the change from `ocr` to `context`.
* refactor: Enhance context file handling in agent processing
- Updated the logic for managing context files by consolidating file IDs from both `ocr` and `context` resources.
- Improved backwards compatibility by ensuring that context files are correctly populated and handled.
- Simplified the iteration over context files for better readability and maintainability.
* refactor: Enhance tool_resources handling in primeResources
- Added tests to verify the deletion behavior of tool_resources fields, ensuring original objects remain unchanged.
- Implemented logic to delete `ocr` and `context` fields after fetching and re-categorizing files.
- Preserved context field when the context capability is disabled, ensuring correct behavior in various scenarios.
* refactor: Replace `ocrEnabled` with `contextEnabled` in AgentConfig
* refactor: Adjust legacy tool handling order for improved clarity
* refactor: Implement OCR to context conversion functions and remove original conversion logic in update agent handling
* refactor: Move contextEnabled declaration to maintain consistent order in capabilities
* refactor: Update localization keys for file context to improve clarity and accuracy
* chore: Update localization key for file context information to improve clarity
* refactor: agent tool permissions to support ephemeral agent settings
* ci: rename render tests and correct typing for `useAgentToolPermissions` hook
* refactor: implement `DragDropContext` to minimize effect of `useChatContext` in `DragDropModal`
* feat: init @librechat/client
* feat: Add common types and interfaces for accessibility, agents, artifacts, assistants, and tools
* feat: Add jotai as a peer dependency
* fix build client package
* feat: cleanup unused types from common/index.ts
- Remove 104 unused type exports from packages/client/src/common/index.ts
- Keep only 7 actually used exports (93% reduction)
- Add cleanup script with enhanced import pattern detection
- Support both named imports and namespace imports (* as t)
- Create automatic backups and comprehensive documentation
- Maintain type safety with build verification
- No breaking changes to existing code
Kept exports:
- TShowToast, Option, OptionWithIcon, DropdownValueSetter
- MentionOption, NotificationSeverity, MenuItemProps
Scripts: cleanup-common-types-safe.js, README-CLEANUP.md
* fix: cleanup
* fix: package; refactor: tsconfig
* feat: add back `recoil`
* fix: move dependencies to peerDependencies in client package
* feat: add @librechat/client as a dependency in package.json and package-lock.json
* feat: update client package configuration and dependencies
- Added new dependencies for Rollup plugins and updated existing ones in package.json and package-lock.json.
- Introduced a new Rollup configuration file for building the client package.
- Refactored build scripts to include a dedicated build command for the client.
- Updated TypeScript configuration for improved module resolution and type declaration output.
- Integrated a Toast component from the client package into the main App component.
* feat: enhance Rollup configuration for client package
- Updated terser plugin settings to preserve directives like 'use client'.
- Added custom warning handler to ignore "use client" directive warnings during the build process.
* chore: rename package/client build script command
* feat: update client package dependencies and Rollup configuration
- Added rollup-plugin-postcss to package.json and updated package-lock.json.
- Enhanced Rollup configuration to include postcss plugin for CSS handling.
- Updated index.ts to export all components from the components directory for better modularity.
* feat: add client package directory to update configuration
- Included the 'client' package directory in the update.js configuration to ensure it is recognized during updates.
* feat: export Toast component in client package
- Added export for the Toast component in index.ts to enhance modularity and accessibility of components.
* feat: /client transition to @librechat/client
* chore: fixed formatting issues
* fix: update peer dependencies in @librechat/client to prevent bundling them
* fix: correct useSprings implementation in SplitText component
* fix: circular dependencies in DataTable
* fix: add remaining peer dependencies and match actual versions previously used in `client/package.json`
* fix: correct frontend:ci script to include client package build
* chore: enhance unused package detection for @librechat/client and improve dependency extraction
* fix: add missing peer dependency for @radix-ui/react-collapsible
* chore: include "packages/client" in unused i18next keys detection
* test: update AgentFooter tests to use document.querySelector for spinner checks
test: mock window.matchMedia in setupTests.js for consistent test environment
* feat: add react-hook-form dependency and update FormInput component to use its types
* chore: linting
* refactor: remove unused defaultSelectedValues prop from MCPSelect and MultiSelect components
* chore: linting
* feat: update GitHub Actions workflow to publish @librechat/client
* chore: update GitHub Actions workflow to install and build data-provider and client dependencies
* chore: add missing @testing-library/react dependency to client package
* chore: update tsconfig.json to exclude additional test files
* chore: fix build issues, resolve latest LC changes
* chore: move MCP components outside of `~/components/ui`
* feat: implement dynamic theme system with environment variable support and Tailwind CSS integration
* chore: remove unnecessary logging of sttExternal and ttsExternal in Speech component
* chore: squashed cleanup commits
chore: move @tanstack/react-virtual to dependencies and remove recoil from package.json
chore: move dependencies to peerDependencies in package.json
feat: update package.json and rollup.config.js to include jotai and enhance bundling configuration
feat: update package.json and rollup.config.js to include jotai and enhance bundling configuration
refactor: reorganize exports in index.ts for improved clarity
refactor: remove unused types and interfaces from common files
refactor: update peer dependencies and improve component typings
- Removed duplicate peer dependencies from package.json and organized them.
- Updated rollup.config.js to disable TypeScript checking during the build process.
- Modified AnimatedTabs component to use React.ReactNode for label and content types, and added TypeScript workarounds for compatibility.
- Enhanced Label and Separator components to accept an optional className prop and improved prop spreading.
- Updated Slider component to include an optional className prop and refined prop handling for better type safety.
refactor: clean up client workflow and update package dependencies
refactor: update package dependencies and improve PostCSS and Rollup configurations
chore: bump version to 0.1.2 in package.json
chore: bump client version to 0.1.2 in package-lock.json
chore: bump client version to 0.1.3 and update dependencies
chore: bump client version to 0.1.4 and update @react-spring dependencies
chore: update package version to 0.1.5 and adjust peer dependencies
- Bump version in package.json from 0.1.4 to 0.1.5.
- Update peer dependency for @tanstack/react-query to allow version 5.0.0.
- Add @tanstack/react-table and @tanstack/react-virtual as dependencies.
- Update various dependencies to their latest compatible versions.
- Simplify postcss.config.js by removing unnecessary options.
- Clean up rollup.config.js by removing ignored PostCSS warnings.
- Update CheckboxButton component to cast icon as React JSX element.
- Adjust Combobox component's class names for better styling.
- Change DropdownPopup component to use React's namespace import.
- Modify InputOTP component to use 'any' type for OTPInputContext.
- Ensure displayLabel and value in ModelParameters are converted to strings.
- Update MultiSearch component's placeholder to ensure it's a string.
- Cast selectIcon in MultiSelect as React JSX element for consistency.
- Update OGDialogTemplate to cast selectText as React JSX element.
- Initialize animationRef in PixelCard with undefined for clarity.
- Add TypeScript ignore comments in Select and SelectDropDown components for Radix UI type conflicts.
- Ensure title in SelectDropDown is a string and adjust rendering of options.
- Update useLocalize hook to cast options as any for compatibility.
refactor: code structure; chore: translations cleanup
chore: remove unused imports and clean up code in NewChat component
refactor: enhance Menu component to support custom render functions for menu items
style: update itemClassName in ToolsDropdown for improved UI consistency
fix: merge conflicts
chore: update @radix-ui/react-accordion to version 1.2.11
* refactor: remove unnecessary TypeScript type assertions in AnimatedTabs, Label, Separator, and Slider components
* feat: enhance theme system with localStorage persistence and new theme atoms
* chore: bump version of @librechat/client to 0.1.7
* chore: fix ci/cd warnings/errors related to linting and unused localization keys
* chore: update dependencies for class-variance-authority, clsx, and match-sorter
* chore: bump @librechat/client to v0.1.8
* feat: add utility colors for theme customization and remove unused tailwindConfig
* v0.1.9
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
* 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
* refactor: streamline model preset handling in conversation setup
* refactor: integrate navigation and location hooks in chat functions and event handlers, prevent cache from fetching on final event handling
* fix: prevent adding code interpreter non-image output to file list on message attachment event, fix all unhandled edge cases when this is done (treating the file download as an image attachment, undefined fields, message tokenCount issues, use of `startsWith` on undefined "text") although it is now prevent altogether
* chore: remove unused jailbreak prop from MinimalIcon component in EndpointIcon
* feat: add new SVG icons (MobileSidebar, Sidebar, XAIcon), fix: xAI styling in dark vs. light modes, adjust styling of Landing icons
* fix: open conversation in new tab on navigation with ctrl/meta key
* refactor: update Nav & Header to use close/open sidebar buttons, as well as redesign "New Chat"/"Bookmarks" buttons to the top of the Nav, matching the latest design of ChatGPT for simplicity and to free up space
* chore: remove unused isToggleHovering state and simplify opacity logic in Nav component
* style: match mobile nav to mobile header
* refactor: move `loadAuthValues` to `~/services/Tools/credentials`
* feat: add createAxiosInstance function to configure axios with proxy support
* WIP: First pass mistral ocr
* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic
* refactor: improve document formatting in encodeAndFormat function
* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)
* fix: update getFiles call to include files with `text` property as well
* refactor: move file handling to `initializeAgentOptions`
* refactor: enhance addImageURLs method to handle OCR text and improve message formatting
* refactor: update message formatting to handle OCR text in various content types
* refactor: remove unused resendFiles property from compactAgentsSchema
* fix: add error handling for Mistral OCR document upload and logging
* refactor: integrate OCR capability into file upload options and configuration
* refactor: skip processing for text source files in delete request, as they are directly tied to database
* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling
* fix: source icon styling
* wip: first pass, frontend file context agent resources
* refactor: add hover card with contextual information for File Context (OCR) in FileContext component
* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization
* feat: implement OCR config; fix: agent resource deletion for ocr files
* feat: enhance agent initialization by adding OCR capability check in resource priming
* ci: fix `~/config` module mock
* ci: add OCR property expectation in AppService tests
* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed
* ci: add unit test to ensure environment variable references are not parsed in OCR config
* refactor: disable base64 image inclusion in OCR request
* refactor: enhance OCR configuration handling by validating environment variables and providing defaults
* refactor: use file stream from disk for mistral ocr api
* WIP: end session endpoint
* refactor: move useGetBannerQuery outside of package
* refactor: add queriesEnabled and move useGetEndpointsConfigQuery to data-provider (local)
* refactor: move useGetEndpointsQuery import to data-provider
* refactor: relocate useGetEndpointsQuery import to improve module organization
* refactor: move `useGetStartupConfig` from package to `~/data-provider`
* refactor: move useGetUserBalance to data-provider and update imports
* refactor: update query enabled conditions to include config check
* refactor: remove unused useConfigOverride import from useAppStartup
* refactor: integrate queriesEnabled state into file and search queries and move useGetSearchEnabledQuery to data-provider (local)
* refactor: move useGetUserQuery to data-provider and update imports
* refactor: enhance loginUser mutation with success and error handling as pass in options to hook
* refactor: update enabled condition in queries to handle undefined config
* refactor: enhance authentication mutations with queriesEnabled state management
* refactor: improve conditional rendering for error messages and feature flags in Login component
* refactor: remove unused queriesEnabled state from AuthContextProvider
* refactor: implement queriesEnabled state management in LoginLayout with timeout handling
* refactor: add conditional check for end session endpoint in OpenID strategy
* ci: fix tests after changes
* refactor: remove endSessionEndpoint from user schema and update logoutController to use OpenID issuer's end_session_endpoint
* refactor: update logoutController to use end_session_endpoint from issuer metadata
