* Fixed upload to provider for custom endpoints + unit tests
* fix: add support back for agents to be able to use Upload to Provider with supported providers
* ci: add test for agents endpoint still recognizing document supported providers
* chore: address ESLint suggestions
* Improved unit tests
* Linting error on unit tests fixed
---------
Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
* refactor: Restructure MCP registry system with caching
- Split MCPServersRegistry into modular components:
- MCPServerInspector: handles server inspection and health checks
- MCPServersInitializer: manages server initialization logic
- MCPServersRegistry: simplified registry coordination
- Add distributed caching layer:
- ServerConfigsCacheRedis: Redis-backed configuration cache
- ServerConfigsCacheInMemory: in-memory fallback cache
- RegistryStatusCache: distributed leader election state
- Add promise utilities (withTimeout) replacing Promise.race patterns
- Add comprehensive cache integration tests for all cache implementations
- Remove unused MCPManager.getAllToolFunctions method
* fix: Update OAuth flow to include user-specific headers
* chore: Update Jest configuration to ignore additional test files
- Added patterns to ignore files ending with .helper.ts and .helper.d.ts in testPathIgnorePatterns for cleaner test runs.
* fix: oauth headers in callback
* chore: Update Jest testPathIgnorePatterns to exclude helper files
- Modified testPathIgnorePatterns in package.json to ignore files ending with .helper.ts and .helper.d.ts for cleaner test execution.
* ci: update test mocks
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Reasoning components with independent toggle buttons
- Refactored ThinkingButton to remove unnecessary state and props.
- Updated ContentParts to simplify content rendering and remove hover handling.
- Improved Reasoning component to include independent toggle functionality for each THINK part.
- Adjusted styles for better layout consistency and user experience.
* refactor: isolate hover effects for Reasoning
- Updated ThinkingButton to improve hover effects and layout consistency.
- Refactored Reasoning component to include a new wrapper class for better styling.
- Adjusted icon visibility and transitions for a smoother user experience.
* fix: Prevent rendering of empty messages in Chat component
- Added a check to skip rendering if the message text is only whitespace, improving the user interface by avoiding empty containers.
* chore: Replace div with fragment in Thinking component for cleaner markup
* chore: move Thinking component to Content Parts directory
* refactor: prevent rendering of whitespace-only text in Part component only for edge cases
* ✨ feat: Refactor error handling and improve loading states in MessageContent component
* ✨ feat: Enhance Thinking and ContentParts components with improved hover functionality and clipboard support
* fix: Adjust padding in Thinking and ContentParts components for consistent layout
* ✨ feat: Add response label and improve message editing UI with contextual indicators
* ✨ feat: Add isEditing prop to Feedback and Fork components for improved editing state handling
* refactor: Remove isEditing prop from Feedback and Fork components for cleaner state management
* refactor: Migrate state management from Recoil to Jotai for font size and show thinking features
* refactor: Separate ToggleSwitch into RecoilToggle and JotaiToggle components for improved clarity and state management
* refactor: Remove unnecessary comments in ToggleSwitch and MessageContent components for cleaner code
* chore: reorder import statements in Thinking.tsx
* chore: reorder import statement in EditTextPart.tsx
* chore: reorder import statement
* chore: Reorganize imports in ToggleSwitch.tsx
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 🦙 fix: Ollama Custom Headers
* chore: Correct import order for resolveHeaders in OllamaClient.js
* fix: Improve error logging for Ollama API model fetch failure
* ci: update Ollama model fetch tests
* ci: Add unit test for passing headers and user object to Ollama fetchModels
* Refactored the logic for determining max output tokens in the agent initialization process.
* Changed variable names for clarity, updating from `maxTokens` to `maxOutputTokens` to better reflect their purpose.
* Adjusted calculations for `maxContextTokens` to use the new `maxOutputTokens` variable.
* 📫 refactor: Enhance OpenID email Fallback
* Updated email retrieval logic to use preferred_username or upn if email is not available.
* Adjusted logging and user data assignment to reflect the new email handling approach.
* Ensured email domain validation checks the correct email source.
* 🔄 refactor: Update Email Domain Validation Logic
* Modified `isEmailDomainAllowed` function to return true for falsy emails and missing domain restrictions.
* Added new test cases to cover scenarios with and without domain restrictions.
* Ensured proper validation when domain restrictions are present.
* fix: Sanitize LLM titles by stripping <think> tags and fix modal overflow
* chore: linting
* chore: Simplify title sanitization by removing unnecessary variable assignment and import order
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* 📦 feat: `@librechat/agents` v2.4.87 for LangFuse Support
* 📦 chore: update @librechat/agents to v2.4.88 in package.json and package-lock.json
* 📦 chore: update @librechat/agents to v2.4.89
* feat: Add runName configuration to AgentClient and Memory agent for improved tracing
* chore: correct startupConfig usage in ImportConversations component
* refactor: properly process configured speechToText and textToSpeech settings in getCustomConfigSpeech
* refactor: proxy configuration by utilizing HttpsProxyAgent for OpenAI Image Edits
* Possibility to add extra env values to the deployment
* Fix: Custom environment variables should be placed after the predefined environment variables
* chore: add i18n localization comment for AlwaysMakeProd component
* feat: enhance accessibility by adding aria-label and aria-labelledby to Switch component
* feat: add aria-labels for accessibility in Agent and Assistant avatar buttons
* fix: add switch aria-labels for accessibility in various components
* feat: add aria-labels and localization keys for accessibility in DataTable, DataTableColumnHeader, and OGDialogTemplate components
* chore: refactor out nested ternary
* feat: add aria-label to DataTable filter button for My Files modal
* feat: add aria-labels for Buttons and localization strings
* feat: add aria-labels to Checkboxes in Agent Builder
* feat: enhance accessibility by adding aria-label and aria-labelledby to Checkbox component
* feat: add aria-label to FileSearchCheckbox in Agent Builder
* feat: add aria-label to Prompts text input area
* feat: enhance accessibility by adding aria-label and aria-labelledby to TextAreaAutosize component
* feat: remove improper role: "list" prop from List in Conversations.tsx to enhance accessibility and stop aria rules conflicting within react-virtualized component
* feat: enhance accessibility by allowing tab navigation and adding ring highlights for conversation title editing accept/reject buttons
* feat: add aria-label to Copy Link button in the conversation share modal
* feat: add title to QR code svg in conversation share modal to describe the image content
* feat: enhance accessibility by making Agent Avatar upload keyboard navigable and round out highlight border on focus
* feat: enhance accessibility by adding aria attributes around alerting users with screen readers to invalid email address inputs in the Agent Builder
* feat: add aria-labels to buttons in Advanced panel of Agent Builder
* feat: enhance accessibility by making FileUpload and Clear All buttons in PresetItems keyboard navigable
* feat: enchance accessiblity by indexing view and delete button aria-labels in shared links management modal to their specific chat titles
* feat: add border highlighting on focus for AnimatedSearchInput
* feat: add category description to aria-labels for prompts in ListCard
* feat: add proper scoping to rows and columns in table headers
* feat: add localized aria-labelling to EditTextPart's TextAreaAutosize component and base dynamic paramters panel components and their supporting translation keys
* feat: add localized aria-labels and aria-labelledBy to Checkbox components without them
* feat: add localized aria-labeledBy for endpoint settings Sliders
* feat: add localized aria-labels for TextareaAutosize components
* chore: remove unused i18n string
* feat: add localized aria-label for BookmarkForm Checkbox
* fix: add stopPropagation onKeyDown for Preview and Edit menu items in prompts that was causing the prompts to inadvertently be sent when triggered with keyboard navigation when Auto-send Prompts was toggled on
* fix: switch TableCell to TableHead for title cells according to harvard issue #789
* fix: add more descriptive localization key for file filter button in DataTable
* chore: remove self-explanatory code comment from RenameForm
* fix: remove stray bg-yellow highlight that was left in during debugging
* fix: add aria-label to model configurator panel back button
* fix: undo incorrect hoist of tool name split for aria-label and span in MCPInput
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: remove `useChatContext` from `useSelectMention`, explicitly pass `conversation` object
* feat: ephemeral agents via model specs
* refactor: Sync Jotai state with ephemeral agent state, also when Ephemeral Agent has no MCP servers selected
* refactor: move `useUpdateEphemeralAgent` to store and clean up imports
* refactor: reorder imports and invalidate queries for mcpConnectionStatus in event handler
* refactor: replace useApplyModelSpecEffects with useApplyModelSpecAgents and update event handlers to use new agent template logic
* ci: update useMCPSelect test to verify mcpValues sync with empty ephemeralAgent.mcp
* filter out unavailable servers
* bump render time
* Fix import path for useGetStartupConfig
* refactor: Change configuredServers to use Set for improved filtering of available MCPs
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
* refactor: Default Model Spec Retrieval Logic, allowing last selected spec on new chat if last selection was a spec
* chore: Replace hardcoded 'new' conversation ID with Constants.NEW_CONVO for consistency
* chore: remove redundant condition for model spec preset selection in useNewConvo hook
* updated gpt5-pro
it is here and on openrouter
https://platform.openai.com/docs/models/gpt-5-pro
* feat: Add gpt-5-pro pricing
- Implemented handling for the new gpt-5-pro model in the getValueKey function.
- Updated tests to ensure correct behavior for gpt-5-pro across various scenarios.
- Adjusted token limits and multipliers for gpt-5-pro in the tokens utility files.
- Enhanced model matching functionality to include gpt-5-pro variations.
* refactor: optimize model pricing and validation logic
- Added new model pricing entries for llama2, llama3, and qwen variants in tx.js.
- Updated tokenValues to include additional models and their pricing structures.
- Implemented validation tests in tx.spec.js to ensure all models resolve correctly to pricing.
- Refactored getValueKey function to improve model matching and resolution efficiency.
- Removed outdated model entries from tokens.ts to streamline pricing management.
* fix: add missing pricing
* chore: update model pricing for qwen and gemma variants
* chore: update model pricing and add validation for context windows
- Removed outdated model entries from tx.js and updated tokenValues with new models.
- Added a test in tx.spec.js to ensure all models with pricing have corresponding context windows defined in tokens.ts.
- Introduced 'command-text' model pricing in tokens.ts to maintain consistency across model definitions.
* chore: update model names and pricing for AI21 and Amazon models
- Refactored model names in tx.js for AI21 and Amazon models to remove versioning and improve consistency.
- Updated pricing values in tokens.ts to reflect the new model names.
- Added comprehensive tests in tx.spec.js to validate pricing for both short and full model names across AI21 and Amazon models.
* feat: add pricing and validation for Claude Haiku 4.5 model
* chore: increase default max context tokens to 18000 for agents
* feat: add Qwen3 model pricing and validation tests
* chore: reorganize and update Qwen model pricing in tx.js and tokens.ts
---------
Co-authored-by: khfung <68192841+khfung@users.noreply.github.com>
* fix: reapply chat font size on load
* refactor: streamline font size handling in localStorage
* fix: update matchMedia mock to accurately reflect desktop and touchscreen capabilities
* refactor: implement Jotai for font size management and initialize on app load
- Replaced Recoil with Jotai for font size state management across components.
- Added a new `fontSize` atom to handle font size changes and persist them in localStorage.
- Implemented `initializeFontSize` function to apply saved font size on app load.
- Updated relevant components to utilize the new font size atom.
---------
Co-authored-by: ddooochii <ddooochii@gmail.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
* fix: Remove ephemeral cache control from document encoding function
* refactor: Improve document encoding types and add file context for anthropic messages api
- Added AnthropicDocumentBlock interface to define the structure for documents from the Anthropic provider.
- Updated encodeAndFormatDocuments function to utilize the new type and include optional context for filenames.
- Refactored DocumentResult to use a union type for various document formats, improving type safety and clarity.
* 🔧 feat: Enhance Redis Configuration and Connection Handling in Cache Flush Utility
- Added support for Redis username, password, and CA certificate.
- Improved Redis client creation to handle both cluster and single instance configurations.
- Implemented a helper function to read the Redis CA certificate with error handling.
- Updated connection logic to include timeout and error handling for Redis connections.
* refactor: flush cache if redis URI is defined
Remove deprecated OpenAI models and add latest GPT-5, o3/o4, and GPT-4.1 series models based on current API offerings as of October 2025.
Removed deprecated models:
- gpt-4.5-preview (deprecated July 2025)
- o1-preview, o1-mini (deprecated July/October 2025)
- gpt-4-vision-preview (shut down December 2024)
- Dated GPT-3.5 and GPT-4 variants (consolidated into base versions)
Added new flagship models:
- GPT-5 series: gpt-5, gpt-5-mini, gpt-5-nano
- o3/o4 reasoning models: o3, o4-mini, o3-pro, o3-mini
- GPT-4.1 series: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
Reorganized list with newest models first for better discoverability.
References:
- https://platform.openai.com/docs/models
- https://platform.openai.com/docs/deprecations
