danny-avila/LibreChat
46.4
Weak · 14 November 2026
812.1k
lines of production code
TypeScript
with JavaScript
6
measurements over time
What this system is
Features
Add Langfuse Connection Settings
Users can now configure and test their Langfuse integration directly within the Integrations settings tab. This new component allows users to select a destination (EU or US), manage public and secret keys, and verify the connection status with real-time feedback, including handling of loading states, errors, and credential changes. Also in this area: Improved subagent guidance display and fold rail visualization.
client/src/components/Nav/SettingsTabs/Integrations · high confidence
Add MCP App Sandbox and restrict API crawling via robots.txt
The application now includes a dedicated sandbox environment for MCP Apps (client/public/mcp-sandbox.html), which provides a secure, isolated iframe-based runtime with strict origin validation and content security policy enforcement to safely render third-party applications. Additionally, a robots.txt file has been added to explicitly instruct search engines to crawl the public interface while disallowing access to the /api/ directory, improving SEO hygiene and preventing search indexing of internal endpoints.
client/public · high confidence
Add MenuSeparator component for chat menu styling
A new MenuSeparator component has been added to the chat menus UI, providing a horizontal divider with consistent spacing and border styling. This component is now exported from the UI module index, enabling its use in chat menu structures to visually separate items.
client/src/components/Chat/Menus/UI · high confidence
Add passkey management in Account settings
Users can now manage passkeys directly from the Account settings page. This change introduces a new Passkeys section where users can add, rename, and delete passkeys. The interface includes a management dialog to view existing passkeys, with options to add new ones via a separate enrollment dialog. Renaming passkeys is supported with inline editing, and deletion requires password confirmation for local accounts (with special handling for accounts without a local password). The implementation includes components for individual passkey items and the main passkeys list, along with comprehensive tests for the UI interactions.
client/src/components/Nav/SettingsTabs/Account/Passkeys · high confidence
Added Redis configuration and management scripts for development environments
The \redis-config\ directory now includes comprehensive setup files and shell scripts to support local development and testing with Redis. Users can now easily spin up a 3-node Redis cluster (ports 7001–7003) or a single Redis instance with TLS encryption (port 6380) using the provided \start-cluster.sh\ and \start-redis-tls.sh\ scripts. The directory also contains specific configuration files (\redis-7001.conf\, \redis-7002.conf\, \redis-7003.conf\, \redis-tls.conf\) and TLS certificates, along with a \stop-cluster.sh\ script for cleanup. This change provides the necessary infrastructure for developers to test caching behaviors with both standard and secure Redis connections.
redis-config · high confidence
Added client-side data provider for GitHub Pull Request integration
This change introduces the client-side data provider layer for the new Pull Request feature, enabling users to view and interact with GitHub pull requests directly within conversations. It includes a batched fetching system to efficiently load pull request data for multiple sidebar rows in a single request, React Query hooks to manage connection status and credentials (connecting/disconnecting GitHub accounts), and a sign-in watcher that polls for OAuth completion. The implementation ensures that pull request data is correctly scoped to the signed-in user and automatically refreshes when the connection state changes.
client/src/data-provider/PullRequest · high confidence
Added sample model specifications for testing
The Models menu component now includes a new \fakeData.ts\ file providing sample model specifications (such as 'Commander in Chief' and 'Vision Pro') for development and testing purposes. These entries define preset configurations for endpoints like Ollama and OpenAI, allowing developers to preview how model specs are rendered in the UI without requiring live backend data.
client/src/components/Chat/Menus/Models · high confidence
Agent API Keys management UI in Settings → Data controls
A new Agent API Keys management interface is now available in the Settings → Data controls section. Users can create new agent API keys with custom names and expiration periods (7, 30, 90, 365 days, or never), view a list of existing keys with their status (active, expiring, or expired) and last-used timestamps, and delete keys. The UI includes a dialog for creating keys, a confirmation dialog for deletion, and a secure reveal step to copy the newly generated key. Additionally, an Admin panel allows administrators to configure permissions for remote agents (use, create, share, share public).
client/src/components/Nav/SettingsTabs/ApiKeys, client/src/components/Nav/SettingsTabs/ApiKeys/\\tests\\_ · high confidence_
Agent data-provider hooks and mutations with comprehensive test coverage
The \client/src/data-provider/Agents\ module now provides React Query hooks and mutations for managing agents, including creating, updating, and deleting agents, as well as listing them with cursor-based pagination and lazy-loading version history. The implementation optimizes list performance by fetching up to 1000 agents per request and flattening pages internally. It also ensures data consistency by preserving the \isEditable\ flag from the list cache during updates and pruning stale graph edges when an agent is deleted. New hooks include \useDuplicateAgentMutation\ and marketplace-specific queries (\useGetAgentCategoriesQuery\, \useMarketplaceAgentsInfiniteQuery\). The change is accompanied by unit tests for these mutations and queries.
client/src/data-provider/Agents · high confidence
Agent version history and management panel
A new side-panel view has been added to let users browse an agent's version history, view details such as tools and capabilities, and restore previous versions. The implementation includes the VersionButton to open the panel, VersionPanel to fetch and display the history, VersionContent and VersionItem for the list UI (with loading, empty, and error states), and isActiveVersion to determine which version is currently active. Also in this area: App-Wide UI Scale Setting; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/SidePanel/Agents/Version · high confidence
Azure Assistants endpoint now supports file attachments
The Azure Assistants server endpoint has been updated to include a new \Files\ class that wraps the OpenAI API, enabling users to create, retrieve, and delete files attached to their assistants. This change adds the necessary client-side logic to manage assistant resources directly through the Azure integration.
api/server/services/Endpoints/azureAssistants · high confidence
Azure Blob Storage integration for file uploads and avatars
The file storage service now supports Azure Blob Storage as a backend for handling file uploads, image processing, and avatar management. Users can store files in Azure containers with configurable public access, upload images that are automatically resized and converted to the configured output format, and manage user avatars (including GIF support) with proper URL generation and database updates. The implementation includes utilities for streaming files, handling remote URL fetches with size limits, and consistent deletion of RAG-associated files.
api/server/services/Files/Azure · high confidence
Background execution toggle for Agent Actions
The Agent Builder now includes a background execution toggle for individual Actions. This switch allows you to opt specific Action operations into background dispatch via \tool\_options\, enabling them to run asynchronously. The toggle is automatically hidden for OAuth Actions (to avoid blocking on interactive login prompts) and for Actions where every operation already supports the background parameter. It also respects the global \backgroundToolsEnabled\ capability and is only available for non-ephemeral agents.
client/src/components/SidePanel/Agents · high confidence
Background task discovery and cancellation support
The client now includes a data-provider module for managing background tasks, introducing a query hook that automatically polls for task status with adaptive refresh intervals (faster for running or pending tasks, slower for idle ones) and a mutation hook to cancel tasks. This enables the UI to discover and display results that arrive after a submission ends and allows users to stop tasks from the chat header.
client/src/data-provider/BackgroundTasks · high confidence
Centralized model exports and database seeding entry point
The API now exposes a unified entry point at \api/models/index.js\ that consolidates Mongoose model methods via \@librechat/data-schemas\ and provides a \seedDatabase\ function. This function initializes roles, seeds default roles, ensures default categories, and seeds system grants, streamlining the database setup process for users and administrators.
api/models · high confidence
Client-side Real User Monitoring with HyperDX and Build Diagnostics
The client now includes a new RUM (Real User Monitoring) library in \client/src/lib/rum\ that integrates with HyperDX to capture page-load diagnostics, service worker status, and SPA route changes. It tags telemetry with the specific client build ID (derived from the entry script filename) and normalizes dynamic route paths (e.g., \/c/:conversationId\) to protect privacy. The implementation supports configurable authentication modes, including public tokens and an authenticated proxy mode that patches \fetch\ to attach user tokens, while ensuring that early browser events are queued and flushed only when the RUM configuration is valid.
client/src/lib/rum · high confidence
Client-side memory management hooks
Added React Query hooks for managing user memories, including fetching, creating, updating, and deleting memory entries, as well as updating memory preferences. The create mutation automatically updates the local cache to reflect new memory entries and recalculates token usage percentages against the user's token limit.
client/src/data-provider/Memories · high confidence
Firebase Storage integration for file uploads and avatars
The application now supports Firebase Storage as a backend for handling file operations. This change introduces new service modules (\crud.js\ and \images.js\) that enable uploading images and buffers to Firebase, retrieving download URLs, and securely deleting files. Users can now have their profile avatars and uploaded images stored in Firebase, with automatic image resizing and format conversion (e.g., to WebP) handled during the upload process. The implementation includes specific logic for avatar uploads, supporting GIFs and dynamic extensions, and ensures that file paths are validated against user IDs to prevent unauthorized access or deletion.
api/server/services/Files/Firebase · high confidence
Initial release of the \`librechat-data-provider\` package
The \librechat-data-provider\ package is introduced as a standalone shared module, providing the core data schemas, validation logic, and API request handling utilities used across the application. This change includes the initial implementation of the package's build configuration (Babel, Jest, Rollup) and foundational test coverage for action request execution and OpenAPI specification parsing, establishing the data-provider layer as a distinct dependency.
packages/data-provider · high confidence
Initial repository scaffolding and configuration
The repository has been initialized with essential configuration files, including a comprehensive \.env.example\ template for server and security settings, a \.dockerignore\ file to optimize Docker builds, and developer tooling configurations such as \.prettierrc\, \.npmrc\, and \.nvmrc\ (Node 24.16.0). Project structure and coding standards are now defined in \AGENTS.md\ and \CLAUDE.md\, which establish workspace boundaries, branching policies, and state management guidelines for the monorepo.
(repo-wide) · high confidence
Introduce ActionsTable component for displaying API specifications
Added a new ActionsTable component within the Side Panel Builder that renders a data table for API action specifications. The component utilizes @tanstack/react-table to display columns for Name, Method, and Path, providing a structured view of action details in the builder interface.
client/src/components/SidePanel/Builder/ActionsTable · high confidence
Introduce Agent Endpoint Service Layer with Parallel Agent and Skill Management
The \api/server/services/Endpoints/agents\ directory has been restructured into a dedicated service layer to support advanced agent capabilities. This includes \initialize.js\ and \build.js\ for core agent initialization and configuration, \addedConvo.js\ to handle parallel agent execution (allowing added agents to run alongside a primary agent), and \skillDeps.js\ to manage skill authoring, file persistence, and workspace access. The new architecture also introduces \subagentThreadStore.js\ for durable subagent thread management with Redis-based task routing, \backgroundCompletion.js\ for handling background tool completions, and \eventChildLease.js\ for managing subagent generation leases. Comprehensive test coverage is provided in \\*.spec.js\ files for these new modules.
api/server/services/Endpoints/agents · high confidence
Introduce Assistants API thread management and usage tracking
This change introduces the core server-side logic for managing OpenAI Assistants API threads within the \api/server/services/Threads\ module. It adds new files (\manage.js\, \index.js\) and corresponding test suites (\manage.spec.js\, \manage.retention.spec.js\, \processMessages.spec.js\) to handle thread initialization, message saving (both user and assistant), token usage recording, and message processing including file citation handling. The implementation ensures that message retention policies (temporary vs. general) are correctly applied and that disabled transactions are honored when recording usage, addressing previous gaps in the Assistants endpoint's data persistence and billing logic.
api/server/services/Threads · high confidence
Introduce BaseClient, OllamaClient, and TextStream modules
The \api/app/clients\ directory now includes \BaseClient.js\, \OllamaClient.js\, and \TextStream.js\. \BaseClient\ provides the core logic for handling AI requests, including file context extraction, attachment handling, and token usage tracking. \OllamaClient\ adds support for the Ollama API, enabling streaming chat completions and model fetching. \TextStream\ offers a utility for simulating text streaming with configurable chunk sizes and delays.
api/app/clients · high confidence
Introduce BookmarkMenuItems component for bookmark management
Added the BookmarkMenuItems component to the Chat Menus, providing a UI for managing conversation bookmarks. This component renders a list of existing tags and includes a new item to open a dialog for creating or editing bookmarks, utilizing the BookmarkEditDialog and OGDialogTrigger from the shared components.
client/src/components/Chat/Menus/Bookmarks · high confidence
Introduce MCP OAuth Flow State and Reconnection Management
The api/config module now initializes and exposes managers for handling MCP OAuth flows and reconnections. It creates a dedicated FlowStateManager for standard MCP OAuth with extended TTLs, a separate manager for Action OAuth with a shorter timeout, and an OAuthReconnectionManager to handle connection stability. These components are wired into the config layer to support the broader MCP integration.
api/config · high confidence
Introduce MCP UI Resource rendering with safe HTML support
Users can now display interactive UI resources within chat, share, and search views using a new MCP UI integration. The system parses text markers (e.g., \\\ui{id}\ or \\\ui{id1,id2}\) to render single resources or carousels, resolving them from conversation message attachments. To ensure safety, the rendering layer strictly limits execution to sandboxed inline HTML (\text/html\), blocking unsafe MIME types like remote DOM JavaScript and removing popup permissions from the sandbox. Also in this area: Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/MCPUIResource · high confidence
Introduce RouteErrorBoundary for improved client error handling
The application now includes a dedicated RouteErrorBoundary component that catches client-side rendering errors. When an error occurs, users are presented with a styled error page displaying the error message, HTTP status, and a collapsible stack trace. To assist with troubleshooting, the boundary provides options to copy the stack trace to the clipboard or download a detailed error log file containing browser and platform information.
client/src/routes · high confidence
Introduce Schedules side panel for automated agent runs
A new Schedules side panel has been added, allowing users to create, view, and manage automated agent runs. The panel displays a list of scheduled runs with their cadence, status, and next run time, and provides controls to enable/disable, edit, delete, or trigger runs immediately. The schedule creation and editing dialog supports various cadences (hourly, daily, weekdays, weekly, and custom cron expressions), timezone selection, and project scoping. The UI includes empty states, loading skeletons, and detailed error handling for MCP (Model Context Protocol) failures, including recovery options for re-authentication or configuration issues. Tests have been added for the schedule dialog, empty state, MCP recovery, cadence formatting, and run synchronization logic. Also in this area: Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/SidePanel/Schedules · high confidence
Introduce dedicated Artifacts panel with code editing, live previews, and version history
A new Artifacts panel has been added to the client, providing a dedicated interface for viewing and interacting with AI-generated content. This includes a Monaco-based code editor with syntax highlighting and high-contrast theme support, live preview tabs for HTML and Mermaid diagrams, and a version history dropdown for code artifacts. The panel manages artifact state via Recoil, handles file downloads, and ensures accessibility with focus trapping and screen-reader-friendly controls.
client/src/components/Artifacts · high confidence
Introduce dedicated CategoryIcon and SkeletonForm utilities for Prompts
The Prompts module now includes new utility components to improve UI consistency and accessibility. CategoryIcon renders specific icons for each prompt category using semantic color roles (e.g., text-category-icon-1) instead of hardcoded primary colors, with a fallback to secondary text for unknown categories. SkeletonForm provides a standardized loading placeholder for the prompts interface. These utilities are exported from the utils index and support the broader Prompts UI refactor.
client/src/components/Prompts/utils · high confidence
Introduce dedicated Share View components for shared conversations
This change adds a new set of components in the Share directory to render shared conversation links independently of the main chat interface. The ShareView component handles the overall layout, including fetching shared messages, managing document titles, and providing options to continue the conversation as a personal copy. The MessagesView and MultiMessage components manage the display of the message tree, while the Message component renders individual messages with appropriate labels and icons. Additionally, the ShareArtifacts component enables viewing and interacting with code artifacts within shared conversations, supporting both desktop and mobile layouts. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Share · high confidence
Introduce dedicated UI components for Two-Factor Authentication phases
Added new React components (BackupPhase, DisablePhase, QRPhase, SetupPhase, VerifyPhase) to the Two-Factor Authentication settings flow. These components provide the user interface for generating QR codes, entering verification tokens, managing backup codes, and disabling 2FA, utilizing the @librechat/client design system for consistent styling and accessibility. Also in this area: App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Nav/SettingsTabs/Account/TwoFactorPhases · high confidence
Introduce dedicated data-provider layer for scheduled chats
This change establishes a structured data-provider module for scheduled chats, replacing ad-hoc implementations with dedicated hooks for querying schedules, creating, updating, and deleting them, and triggering immediate runs. It adds an admission system that proactively fetches and caches conversation snapshots when a scheduled run starts, ensuring the sidebar updates immediately without waiting for polling. Additionally, it introduces a consent management layer for MCP (Model Context Protocol) scheduled runs, allowing users to confirm or revoke consent, and includes tests to verify cache invalidation behavior during mutations.
client/src/data-provider/Schedules · high confidence
Introduce dismissible and persistable system banners with sanitized HTML rendering
The Banners component now supports two banner modes: standard dismissible banners, which users can hide via a close button (with the dismissal state persisted in local storage), and non-dismissable 'persistable' banners that remain visible. To ensure safety, all banner messages are sanitized using a strict HTML sanitizer that allows only specific text tags and class attributes, preventing arbitrary script execution. The component also dynamically reports its height to parent layouts and uses semantic color tokens from the design system for consistent styling.
client/src/components/Banners · high confidence
Introduce dynamic, schema-driven parameter controls in the side panel
The Parameters side panel now renders settings using a new set of dynamic components (DynamicInput, DynamicSlider, DynamicCheckbox, DynamicSwitch, DynamicDropdown, DynamicCombobox, DynamicTags, DynamicTextarea) that are driven by the provider's parameter schema. This allows the UI to automatically adapt to model-specific options, ranges, and enums, while enforcing constraints like clamping numeric values to their valid range on blur and normalizing stored values when a model switch narrows the allowed range. The panel also includes a reset button to restore defaults and a Save As Preset dialog, with comprehensive tests added to verify input sanitization, range enforcement, and state synchronization.
client/src/components/SidePanel/Parameters · high confidence
Introduce opt-in Langfuse fanout gateway for central and tenant trace export
A new Langfuse fanout gateway service has been added to the OpenTelemetry infrastructure, enabling LibreChat to export agent traces to both a central Langfuse project and per-tenant Langfuse projects. The gateway handles tenant-scoped routing, media upload fanout, and structured failure logging, while an internal OpenTelemetry collector manages trace batching, memory limiting, and export to the configured central and tenant destinations. Deployment is supported via Docker Compose or Helm, with configuration for central and tenant base URLs, authentication, and Redis-backed upload plan storage.
otel · high confidence
Introduce per-agent memory partitions and admin controls in the side panel
The Memories side panel now supports per-agent memory partitions, allowing users to filter memories by specific agents or view them all together. A new partition dropdown is dynamically generated based on available agent-scoped memories. Additionally, an AdminSettings dialog has been added, enabling administrators to configure granular permissions (USE, CREATE, UPDATE, READ, OPT\_OUT) for memory operations. The UI includes new components like MemoryCard, MemoryCreateDialog, and MemoryEditDialog, which handle memory display, creation, and editing with proper access control checks.
client/src/components/SidePanel/Memories · high confidence
Introduce shared client type definitions and accessibility utilities
The \client/src/common\ directory now provides a centralized set of TypeScript types and utilities for the application. This includes accessibility helpers (\a11y.ts\) for screen-reader announcements, artifact handling types (\artifacts.ts\) for code blocks and Mermaid diagrams, and comprehensive type definitions for Agents (\agents-types.ts\) and Assistants (\assistants-types.ts\) covering form structures, capabilities, and UI options. Additionally, it exports shared interfaces for menus, selectors, and tools, along with agent category constants, consolidating these shared resources for broader client-side use.
client/src/common · high confidence
Introduces durable agent trigger service and owner contact resolution
This change adds a new server-side agent trigger service (\triggers.js\) that manages durable delivery, background tool completion wake-ups, subagent completion wake-ups, and queued turn lifecycles, wired to the \@librechat/api\ package. It also introduces \detachedActionResume.js\ to handle resumed detached agent actions and \ownerContact.js\ to resolve and attach owner contact information to agents based on ACL permissions, ensuring owner emails are not exposed for support contacts. Tests verify the composition of these services, including checkpoint deletion reclamation, detached action capability advertising, and configuration injection for idle polling and batch sizes.
api/server/services/Agents · high confidence
Major Chat Input Redesign with Advanced Steering and Agent Controls
The chat input area has been completely rebuilt to support complex agent workflows and improved user interaction. Key additions include a new \ChatForm\ component that integrates mid-run steering (interrupt, queue, and steer actions) via \DuringRunSendButton\, and an \AskUserQuestionPopover\ for handling agent-initiated pauses with keyboard navigation. The input now features dedicated menus for managing code environments (\CodeWorkspaceMenu\) and code approval modes (\CodeApprovalMenu\), allowing users to select workspaces and set approval policies directly from the composer. Additional enhancements include an \AddedConvo\ chip for tracking attached conversations, \ConversationStarters\ for quick prompts, and an \EscalateNowButton\ for interrupting queued or in-flight messages. The input also supports auto-playing audio via \AutoPlayAudio\ and handles pasted text editing through \PastedTextDialog\. Also in this area: 20 commits (8 fixes) modifying client; 12 commits (8 fixes) fixing client; Improved subagent guidance display and fold rail visualization; Fixes for authentication flow, chat navigation, and subagent content recovery; RTL support and keyboard shortcuts for tool approval cards.
client/src/components/Chat/Input · medium confidence · unverified
Manage provider API keys in a dedicated settings dialog
A new Provider Keys section has been added to the Settings UI, allowing users to view and manage API keys for endpoints configured to use user-provided credentials. The dialog lists only the endpoints the user can actually reach (respecting model specs, added endpoints, and agent access permissions) and displays the key's expiry status using the user's clock format preference. Users can set or update keys via a dialog that supports various credential types (API key, Bedrock credentials, session/bearer tokens). Also in this area: Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Nav/SettingsTabs/ProviderKeys · high confidence
Mermaid diagrams can now be exported and opened as standalone artifacts
Users can now export Mermaid diagrams as SVG or PNG files directly from the message content. Additionally, diagrams can be opened as standalone artifacts in the dedicated Artifacts pane, where they support zooming, panning, and code viewing. This change introduces a new export component and artifact integration for Mermaid diagrams, enhancing their usability and accessibility.
client/src/components/Messages/Content/Mermaid · high confidence
New API Controllers for Authentication, Permissions, and User Preferences
The \api/server/controllers\ directory now contains a suite of new controller modules that handle core application logic previously managed elsewhere or inline. \AuthController\ manages user registration, OpenID session refresh, and token validation, introducing configurable OpenID token reuse windows and tenant-aware session handling. \PermissionsController\ provides a generic interface for bulk resource permission updates, supporting granular access control for agents, groups, and public roles. \FavoritesController\ and \SkillStatesController\ expose endpoints for managing user-specific favorites and skill state overrides, including validation and pruning of orphaned states. \PluginController\ and \ModelController\ serve dynamic plugin and model configurations, with \PluginController\ specifically scoping 'agents-only' tools to the agents runtime to prevent errors in the assistants interface. Additional controllers for \Balance\, \Endpoint\, \TokenConfig\, and \TwoFactor\ authentication round out the new API surface, with comprehensive test coverage provided in corresponding \.spec.js\ files.
api/server/controllers · high confidence
New API routes for granular access permissions and Action OAuth flows
The server now exposes dedicated endpoints for managing resource-level access control and handling Action OAuth authentication. The new \accessPermissions\ routes (\/api/permissions/{resourceType}/{resourceId}\) allow users to view and update permissions for Agents, Prompt Groups, MCP Servers, Skills, Code Environments, and Shared Links, enforcing a required SHARE permission to prevent unauthorized access. Additionally, the \actions\ routes (\/api/actions/:action\_id/oauth/bind\ and \/callback\) implement a secure OAuth flow for Actions, binding the session via CSRF cookies and validating state parameters to ensure safe token exchange.
api/server/routes · high confidence
New API services for Actions, Assistants, Authentication, and Microsoft Graph integration
This change introduces several new service modules in the \api/server/services\ directory. \ActionService.js\ provides the backend logic for managing and executing user-defined Actions (custom tools), including domain name normalization and OAuth credential handling. \AssistantService.js\ implements the core runtime for OpenAI Assistants API v2, handling run polling, step processing, and tool call submission. \AuthService.js\ is a new service consolidating authentication flows, including OpenID Connect session management, token handling, and email verification. Additionally, \GraphApiService.js\ and \GraphTokenService.js\ add support for Microsoft Graph API integration, enabling Entra ID principal search and group membership resolution via On-Behalf-Of token exchange.
api/server/services · high confidence
New Actions table for displaying agent API endpoints
The Agents side panel now includes a dedicated Actions table that lists an agent's configured API actions. This table displays the endpoint name, HTTP method, and path, with the method color-coded using semantic tokens for quick recognition. A matching skeleton loader is provided to ensure a smooth layout transition while data is loading.
client/src/components/SidePanel/Agents/ActionsTable · high confidence
New Admin API Endpoints for System Management
The admin API surface now includes dedicated endpoints for managing system configuration, user roles, groups, and grants, alongside new capabilities for auditing, code environment pairing, and Langfuse integration. Administrators can now view and export audit logs, manage code environment lifecycles, and configure Langfuse connections. User management has expanded to include role and group administration, as well as the ability to list and search users. These changes introduce a more granular, capability-based access control system for administrative tasks. Also in this area: Assistant avatar updates are now bound to authorized owners; Improved reliability and security for file operations and admin configuration; Fixes for agent inference input validation, title config resolution, and MCP server access; Unseen reply indicators and request-scoped reasoning overrides.
api/server/routes/admin · high confidence
New Advanced Agent Orchestration Panel
A new Advanced settings panel has been added to the Agent Builder, providing a centralized hub for configuring multi-agent collaboration. Users can now define Agent Chains to run agents sequentially, configure Agent Handoffs to route tasks between agents, and set up Agent Subagents to spawn child agents with optional file sharing. The panel also includes a configurable Recursion Limit to control agent execution depth and a utility to copy the Agent ID to the clipboard. Also in this area: 20 commits (8 fixes) modifying client; App-Wide UI Scale Setting; Composer UI simplification and enhanced queue controls; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/SidePanel/Agents/Advanced · medium confidence · unverified
New Agent Management and Execution API Endpoints
The \api/server/routes/agents\ directory has been restructured into a modular set of route files, introducing a comprehensive suite of new endpoints for agent lifecycle management, execution, and configuration. The new \management.js\ routes provide full CRUD capabilities for agents (create, read, update, delete) along with file management for tool resources, secured by tenant-aware authentication. The \chat.js\ and \v1.js\ routes expose the core execution interfaces, including an OpenAI-compatible \/v1/chat/completions\ endpoint, a new Open Responses API (\/v1/responses\), and durable event delivery via \/v1/events\. Additionally, \actions.js\ and \tools.js\ handle agent-specific tool definitions and direct tool execution, while \skills.js\ enables skill discovery and authoring. This change consolidates agent-related logic into a dedicated, permission-scoped API layer.
api/server/routes/agents · high confidence
New Agent Marketplace with browsing, search, and detail views
The Agent Marketplace has been introduced, providing a dedicated interface for discovering and interacting with agents. Users can now browse agents by category using tabbed navigation, search for specific agents with debounced input, and view detailed information in a modal dialog. The marketplace includes features such as pinning agents to favorites, copying shareable links, and starting new chats directly from the agent card. The implementation includes responsive design, infinite scrolling for large lists, and comprehensive error handling with user-friendly messages. Admin settings allow control over marketplace access permissions. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Composer UI simplification and enhanced queue controls; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Agents · high confidence
New Assistant Actions Builder with OAuth and API Key Authentication
The Assistant Builder now includes a dedicated Actions panel for configuring external API integrations. Users can define actions by providing an OpenAPI specification, which is parsed to display available endpoints in a table. The builder supports two authentication methods: Service HTTP (API Key) and OAuth. For OAuth, the interface displays the required callback URL and provides a copy button. The implementation includes a new ActionsAuth component for managing authentication settings, an ActionsInput component for handling the OpenAPI spec and validation, and an ActionsPanel that orchestrates the creation, editing, and deletion of actions within the assistant configuration.
client/src/components/SidePanel/Builder · high confidence
New Assistant Tools Dialog and Tool Item components
Added a new AssistantToolsDialog component that allows users to search, install, and remove tools (plugins) for both Assistants and Agents endpoints, including handling authentication flows via PluginAuthForm. Introduced a corresponding ToolItem component to display individual tool details with add/remove actions and icons. These components are exported via the Tools index file, providing the UI foundation for managing tool availability and configuration within the agent/assistant setup workflow. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Tools · high confidence
New Auto-Refill Settings UI in Balance Tab
A new AutoRefillSettings component has been added to the Balance settings tab, providing users with a dedicated interface to view and manage automatic balance refill or reset configurations. This UI displays key details including the last refill/reset timestamp, the configured amount, the recurrence interval (e.g., every X days), and the next scheduled refill/reset date, with support for localized time formats and interval units.
client/src/components/Nav/SettingsTabs/Balance · high confidence
New Balance Summary component displays credits, currency, or usage percentage
A new Balance component has been added to the client interface, rendering a summary of the user's current balance status. This component supports three display modes: showing raw credit counts, converting balances to a configured currency (e.g., EUR), or displaying usage as a percentage of the total allotment. It provides visual feedback through a progress bar indicating the share of balance used, color-coded tone indicators for warnings or empty states, and text updates that dynamically reflect refill schedules (such as 'resets in 3 days' or 'refills when empty'). The component handles loading, error, and empty states gracefully, ensuring users always see relevant balance information or nothing at all if the deployment does not meter credits.
client/src/components/Balance · high confidence
New CLI scripts and tests for user management, permissions, and data migration
The config area now includes a suite of new command-line tools and their corresponding tests to manage user lifecycles and migrate legacy data. Administrators can use the new \create-user\, \ban-user\, \add-balance\, \delete-user\, and \invite-user\ scripts to perform account operations directly from the terminal. Additionally, migration scripts (\migrate-code-file-duplicates\, \migrate-prompt-permissions\, \migrate-shared-link-permissions\) are provided to handle data cleanup and permission upgrades, with comprehensive test coverage ensuring correct behavior for edge cases like schedule suspension during user deletion and partial write failures during permission migrations.
config · high confidence
New Code Interpreter Settings UI for Agent Builder
The Agent Builder now includes a dedicated Code section with three new components: a toggle to run code tools (execute\_code, bash\_tool) in the background, a file upload area for code execution resources, and a settings panel for managing stateful code sessions, environment selection, and Git identity configuration.
client/src/components/SidePanel/Agents/Code · high confidence
New Conversation Options Menu with Project, Share, and Delete Actions
A new ConvoOptions component and its sub-components (DeleteButton, ProjectButton, ShareButton, SharedLinkButton) have been introduced to manage conversation-specific actions. Users can now assign conversations to projects via a searchable dialog, manage shared links with options to include snapshot files and view QR codes, and delete conversations with a confirmation dialog. The menu also supports conversation duplication and archiving, with appropriate toast notifications for success and error states.
client/src/components/Conversations/ConvoOptions · high confidence
New Data Management Controls in Settings
The Data section of the Settings tab now includes dedicated controls for managing conversation data and account security. Users can archive all chats at once, permanently clear all conversation history, revoke all API keys, and manage uploaded files. Additionally, a new interface allows users to import conversations from JSON files, delete cached TTS responses, and view or manage their shared links.
client/src/components/Nav/SettingsTabs/Data · high confidence
New Docker build/push utilities and environment updater script
Added shell scripts for building and pushing Docker images (docker-build.sh, docker-push.sh) that support configurable tags and remote registry references, alongside a Python script (update\_env.py) that updates .env files by replacing placeholders with local environment variables, streamlining deployment workflows.
utils · high confidence
New Endpoint and Icon Components for Settings and Conversation Icons
The \client/src/components/Endpoints\ directory now includes a suite of new components to manage endpoint-specific settings and conversation icons. \EndpointSettings\ and \AlternativeSettings\ handle the rendering of configuration panels based on the current settings view and endpoint type, while \Icon\, \ConvoIcon\, \EndpointIcon\, \MinimalIcon\, and \MessageEndpointIcon\ provide specialized icon rendering for user avatars, conversation headers, and message rows, supporting custom URLs, provider logos, and entity-specific marks (like agents and assistants). Additionally, \SaveAsPresetDialog\ offers a UI for saving current configurations as presets.
client/src/components/Endpoints · high confidence
New Export Conversation dialog with format and option controls
The ExportConversation component now includes an ExportModal that lets users choose the export format (Markdown, Text, JSON, CSV, or Screenshot), customize the filename, and toggle endpoint options and message branches. Branch export is available for JSON and CSV, while endpoint options are disabled for CSV and Screenshot; a recursive export toggle appears only for JSON. The dialog manages focus on close and resets settings when the conversation changes. Also in this area: App-Wide UI Scale Setting.
client/src/components/Nav/ExportConversation · high confidence
New General Settings Controls and Admin Panel Link
The General settings tab now includes several new configuration options and UI elements. Users can manage their archived conversations via a new modal and table interface, which supports sorting, searching, and actions like unarchiving or deleting chats. A new toggle allows users to display the active chat title in the browser tab, and dropdown selectors let users customize the clock format (12h/24h/system) and the start of the week (Sunday/Monday/system). Additionally, an Admin Panel link is now visible in the General settings for users with admin privileges, providing direct access to administrative tools.
client/src/components/Nav/SettingsTabs/General · high confidence
New Insights dashboard for monitoring agent usage
A new Insights view has been added to the client, providing a dashboard for monitoring agent activity. The component displays key performance indicators (conversations, users, messages, tokens) with sparkline trends and allows filtering by specific agents and date ranges. It includes logic to handle agent filter recovery on authorization failures and supports both shortcut and custom date ranges.
client/src/components/Insights · high confidence
New LibreChat Helm Chart v2.0.14 with RAG API and Langfuse Fanout Support
The LibreChat Helm chart has been updated to version 2.0.14 (app version v0.8.8-rc4), introducing a new bundled \librechat-rag-api\ sub-chart (v0.5.3) that provides a vector database for Retrieval-Augmented Generation (RAG) using PostgreSQL. The main chart now supports custom DNS configuration (\dnsPolicy\, \dnsConfig\) and host aliases for traffic redirection, alongside an opt-in Langfuse fanout gateway with an OpenTelemetry collector sidecar for centralized trace export. Additionally, the chart enforces the use of named credential secrets for startup validation, automatically selects Generation Protocol V2, and includes a deprecation check for the renamed \env\ values field.
helm · high confidence
New MCP Server configuration hook with OBO and OAuth support
The \useMCPServerForm\ hook has been introduced to manage the creation, editing, and deletion of MCP servers within the SidePanel dialog. This hook introduces support for an 'On-Behalf-Of' (OBO) authentication type alongside existing Service HTTP and OAuth methods, allowing users to configure specific OBO scopes. It also handles OAuth token exchange methods and ensures that sensitive credentials (API keys and secrets) are never pre-filled in the form when editing existing servers, while automatically suggesting server titles based on the provided URL.
client/src/components/SidePanel/MCPBuilder/MCPServerDialog/hooks · high confidence
New MCP credential loading and search attachment streaming services
The \api/server/services/Tools\ directory now includes dedicated modules for managing tool credentials and search results. The new \credentials.js\ service introduces a \loadAuthValues\ function that securely loads authentication values from environment variables or the user database, specifically filtering out the \user\_provided\ sentinel to prevent it from being used as a credential. The \search.js\ service provides \createOnSearchResults\, which handles streaming search results as attachments in both standard and resumable (generation-scoped) modes. These are accompanied by comprehensive test suites (\credentials.spec.js\, \mcp.spec.js\, \search.spec.js\) that verify credential fallback chains, optional field handling, and attachment ownership in multi-agent scenarios.
api/server/services/Tools · high confidence
New PeoplePicker components for sharing dialogs
The PeoplePicker directory now exports a unified search interface (UnifiedPeopleSearch), a search result item renderer (PeoplePickerSearchItem), a search input wrapper (SearchPicker), and a list of selected principals (SelectedPrincipalsList). These components replace the previous implementation to provide a consistent, accessible way to search for and add users, groups, and roles to sharing permissions, including support for role assignment and insights access toggles.
client/src/components/Sharing/PeoplePicker · high confidence
New Plugin Store authentication and navigation components
The Plugins Store now includes dedicated components for managing plugin credentials and browsing: \PluginAuthForm\ handles plugin installation and credential updates with format-aware validation (e.g., hinting expected prefixes for API keys), masking for sensitive fields, and URL validation; \PluginPagination\ provides accessible page navigation for the plugin list; and \PluginTooltip\ displays contextual help. These components are exported from the Store module to support the plugin installation and configuration workflow.
client/src/components/Plugins/Store · high confidence
New Preset Management Dialog and Menu Components
The Presets menu now uses a dedicated EditPresetDialog for modifying preset details and a new PresetItems component for the menu interface. The dialog allows users to change the preset title and switch the associated endpoint, automatically resetting the model to the default if the current selection is invalid for the new endpoint. The menu component supports importing presets from JSON files, clearing all presets via a confirmation dialog, and displays the default preset status. These changes improve the usability and accessibility of preset management within the chat interface.
client/src/components/Chat/Menus/Presets · high confidence
New Project Workspace components for managing files, instructions, and conversations
This change introduces a new set of UI components in the Projects directory to support a dedicated project workspace. Users can now create, edit, and delete projects via dialog forms, manage project-specific instructions with conflict resolution and draft preservation, and attach reference files (including uploads and existing files) to projects. The workspace also features a virtualized chat list that groups and sorts conversations by date, and a ProjectBadge that provides a persistent link to the project workspace from within a conversation. Also in this area: 9 commits (4 fixes) modifying client/src; RTL support and keyboard shortcuts for tool approval cards.
client/src/components/Projects · medium confidence · unverified
New Prompt Editor with Variable Support and Markdown Preview
The Prompts editor has been replaced with a new component that allows users to edit prompt text in a textarea and preview it as formatted Markdown (including GFM, math, and syntax highlighting). A new VariablesDropdown component lets users insert special variables (e.g., system, user, assistant) into the prompt; used variables are tracked and disabled in the menu, and adding a variable triggers a live announcement. Inline code variables are highlighted, and double-clicking code copies its content. Also in this area: RTL support and keyboard shortcuts for tool approval cards. Also in this area: 9 commits (4 fixes) modifying client/src.
client/src/components/Prompts/editor · medium confidence · unverified
New Prompt Management Dialogs
The Prompts interface now includes dedicated dialogs for creating, sharing, previewing, and deleting prompts. Users can create new prompts and are automatically navigated to the resulting group page, share prompts via a permission-aware access dialog, preview prompt details in a modal, delete specific prompt versions with confirmation, and manage variables within prompts. These components consolidate prompt lifecycle actions into a consistent UI pattern. Also in this area: Improved subagent guidance display and fold rail visualization; RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting.
client/src/components/Prompts/dialogs · high confidence
New Prompts Sidebar UI Components
Added new components to the Prompts sidebar: FilterPrompts for filtering and searching prompts, GroupSidePanel for displaying the list of prompt groups with scrolling and loading states, and PromptsAccordion which combines these with an AutoSendPrompt toggle and admin settings. These components provide the UI for managing and browsing prompt groups within the sidebar. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Prompts/sidebar · high confidence
New Prompts UI components and utilities
This change introduces a new set of components and utilities for the Prompts interface. It adds button components for admin settings, toggling 'Always Make Prod', and auto-sending prompts, along with a layout view for inline prompt editing. Additionally, it includes utility components for category icons with semantic color mapping, skeleton loading states, and special variable icons, supporting a more consistent and feature-rich prompts experience. Also in this area: Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Prompts/buttons · high confidence
New SSE data-provider module with protocol negotiation and agent turn management
A new \client/src/data-provider/SSE\ module has been introduced to handle Server-Sent Events (SSE) communication, featuring a Generation Protocol v2 negotiation layer that ensures backward compatibility with legacy servers. This module provides React Query hooks and mutations for managing agent queued turns (including enqueue, cancel, and status polling), immediate and final conversation title generation, and active job tracking with robust handover and successor grace periods. Comprehensive test coverage has been added for protocol negotiation, query behavior, and turn state management to ensure reliability. Also in this area: 4 commits (4 fixes) fixing client; 20 commits (8 fixes) modifying client; App-Wide UI Scale Setting; Chat actions now route through the transport layer.
client/src/data-provider/SSE · medium confidence · unverified
New Skills View Layout for Detail, Edit, and Create Modes
A new SkillsView layout component has been introduced to manage the Skills UI routing and display logic. This component handles navigation between read-only skill details, editing, and creation modes based on the URL path, while enforcing role-based access permissions for viewing and creating skills. It also includes a mobile sidebar toggle for small screens and displays appropriate empty or error states when no skill is selected or when a skill is not found.
client/src/components/Skills/layouts · high confidence
New Skills creation and editing forms
Added a new set of UI components in the Skills forms directory to support creating and editing skills. This includes a CreateSkillForm for adding new skills, a SkillForm for editing existing ones, a CategorySelector for assigning categories, an InvocationModePicker for selecting invocation modes, and a SkillContentEditor for managing skill content with markdown support.
client/src/components/Skills/forms · high confidence
New Skills display components and file viewer
The Skills display area now includes a full set of UI components for viewing and editing skill content. SkillDetail and SkillDetailHeader present skill metadata, ownership, and action buttons (edit, delete, share, toggle active state). SkillFileViewer allows browsing and editing skill sub-files (markdown, text, images) with a rendered/source view toggle, copy-to-clipboard, and inline editing for supported files. SkillMarkdownRenderer handles markdown rendering with GFM, math, and syntax highlighting, and resolves relative links within skill files. SkillState provides empty/error placeholders, and ViewToggle offers a segmented control for switching between rendered and source views. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Skills/display · high confidence
New Skills list UI with collapsible sections and nested file trees
The Skills management interface now features a dedicated list view that organizes skills into collapsible sections. Each skill item displays a virtualized, nested file tree (built with react-vtree) that automatically includes a SKILL.md entry and groups files into folders, allowing users to browse and select specific skill files. A skeleton loading component is also provided to improve perceived performance during data fetches.
client/src/components/Skills/lists · high confidence
New Skills management buttons and controls
This change introduces a new set of UI components for managing Skills within the application. Users can now create new skills via a dropdown menu offering 'Write' or 'Upload' options, toggle the availability of a skill for the current user using a dedicated switch, and share skills with others through a permission-based dialog. Additionally, administrators gain access to a settings dialog to configure granular permissions (Use, Create, Share, Share Public) for skills. Also in this area: Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Skills/buttons · high confidence
New Skills management dialogs
Added the CreateSkillDialog, DeleteSkill, and UploadSkillDialog components to the Skills UI. These dialogs enable users to create new skills with validation, delete existing skills with confirmation, and upload skill archives with size-limit enforcement and detailed failure feedback. Also in this area: RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Skills/dialogs · high confidence
New Skills sidebar panel with search, filtering, and admin access
The Skills sidebar now features a dedicated panel that includes a search input for filtering skills by name, a 'Create Skill' menu button that is conditionally shown based on user permissions, and an admin settings footer visible only to users with the admin role. The panel supports infinite scrolling for skill lists and respects the sidebar's collapsed state to prevent unnecessary data fetching. Also in this area: 9 commits (4 fixes) modifying client/src; RTL support and keyboard shortcuts for tool approval cards; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Skills/sidebar, client/src/components/Skills/sidebar/\\tests\\_ · medium confidence · unverified_
New Speech-to-Text configuration controls in Settings
The Speech settings tab now includes a dedicated STT section with granular controls: users can enable/disable Speech-to-Text, select the STT engine (browser or external), choose from a comprehensive list of languages (including Estonian, Latvian, and Lithuanian), adjust decibel sensitivity, enable auto-transcribe audio, and configure auto-send text delay. These components are backed by Recoil state and include unit tests for the switch and selector behaviors.
client/src/components/Nav/SettingsTabs/Speech/STT · high confidence
New Structured Tools for Search, Image Generation, and Data Retrieval
Agents now have access to a suite of new structured tools for enhanced search, image generation, and data retrieval. Search capabilities include Google Search, Tavily Search (with proxy support and client identification), and Traversaal Search. Image generation is supported via OpenAI Image Tools (defaulting to GPT Image Flare), Flux API (with finetuning support), Stable Diffusion, and Gemini Image Generation (supporting both API keys and Vertex AI). Additional tools provide access to Azure AI Search, OpenWeather data, and Wolfram Alpha computations.
api/app/clients/tools/structured · high confidence
New TTS settings controls in the Speech tab
The Speech settings tab now includes dedicated controls for Text-to-Speech configuration. Users can enable or disable TTS, cache TTS responses, and use cloud-based browser voices. A dropdown allows switching between browser and external TTS engines, while a playback rate slider lets you adjust speech speed from 0.1x to 2x. Voice selection is context-aware, showing the appropriate dropdown based on the chosen engine. These settings are disabled when TTS is turned off.
client/src/components/Nav/SettingsTabs/Speech/TTS · high confidence
New Theme and Language Selectors with High Contrast Support
The Appearance component area now exports dedicated ThemeSelector and LangSelector components. The theme selector exposes options for System, Dark, Light, and two new High Contrast modes (Light and Dark), allowing users to switch to high-contrast themes for better accessibility. The language selector provides a searchable dropdown for a wide range of languages and displays a loading spinner while language resources are being fetched. Also in this area: App-Wide UI Scale Setting.
client/src/components/Appearance · high confidence
New ToggleSwitch component for Settings tabs
A new \ToggleSwitch\ component has been added to the Settings tabs navigation, providing a reusable UI element for toggling settings. It supports both Jotai and Recoil state management libraries, allowing developers to bind toggle states using either \WritableAtom\ or \RecoilState\. The component includes features for localization, optional hover card help text, badges (such as 'Beta' labels), and accessibility attributes like \aria-labelledby\. It also respects a \showSwitch\ prop to conditionally render the toggle, and supports disabled states and custom label styling.
client/src/components/Nav/SettingsTabs · high confidence
New UI components for admin settings, terms, and panel layouts
The client now ships a set of new UI components in \client/src/components/ui\ to support admin role management, terms of service acceptance, and side-panel rendering. \AdminSettingsDialog\ provides a role-based permission editor with confirmation flows for sensitive changes, while \TermsAndConditionsModal\ displays and accepts terms content via Markdown. \PanelContent\ and \PanelFooter\ standardize side-panel scrolling, loading skeletons, empty states, and sticky footers. Additional utilities include \Collapse\ for animated reveal, \CustomIcon\ for theme-adaptive SVG masking, \Description\ for safe HTML sanitization, and \LocalizedDateRangePicker\ for locale-aware date selection. Tests cover accessibility, sanitization, and interaction behavior for these components.
client/src/components/ui · high confidence
New UI components for agent handoffs, tool approvals, and user questions
The chat message content area now includes dedicated components for agent handoffs, tool approvals, and user questions. The \AgentHandoff\ component displays when an agent transfers control to another, showing the target agent's name and any associated instructions or context. The \ApprovalContext\ and related components (\AskUserQuestion\, \AskUserQuestions\, \AskUserQuestionCall\, \AskUserQuestionProgress\) manage the human-in-the-loop flow, allowing users to answer questions, approve or reject tool calls, and view the status of these interactions. The \ActivityPhaseGroup\ component provides a unified view of agent activity phases, including live updates and summaries. These changes enhance the user's ability to understand and interact with complex agent workflows directly within the chat interface.
client/src/components/Chat/Messages/Content · high confidence
New Variable Editor component with special variable insertion
A new VariableEditor component has been added to the Variables module, providing a controlled textarea for model-facing text that supports inserting special variables (such as current\_date) via a dropdown menu. The component includes an expand-to-fullscreen dialog for easier editing and integrates with react-hook-form's dirty tracking to ensure insertions are properly captured in form state. Also in this area: RTL support and keyboard shortcuts for tool approval cards.
client/src/components/Variables · high confidence
New VectorDB file service for RAG uploads and deletions
A new VectorDB service module has been introduced to handle file operations for the Retrieval-Augmented Generation (RAG) system. This service provides functions to upload files to the vector database (embedding them via the RAG API) and to delete associated vectors when files are removed. It supports entity IDs for shared resources and includes error handling for deletion failures, ensuring that file management integrates with the external RAG API using short-lived authentication tokens.
api/server/services/Files/VectorDB · high confidence
New Web Search Citation and Source Display Components
The \client/src/components/Web\ directory now contains a new suite of components to support native web search with citation references and file search source citations. This includes \Citation.tsx\ for rendering inline citations with support for file previews and relevance metrics, \Sources.tsx\ for displaying a list of web and file sources with hovercards, \SourceHovercard.tsx\ for detailed source previews, and \plugin.ts\ for parsing and processing citation markers in text content. Context management is handled by \Context.tsx\, and error resilience is provided by \SourcesErrorBoundary.tsx\. Also in this area: Fixes for mobile drawer behavior, web search scrollbars, and select styling; App-Wide UI Scale Setting; Composer UI simplification and enhanced queue controls; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Web · high confidence
New artifact parsing and update service
A new service module at api/server/services/Artifacts/update.js has been introduced to handle artifact lifecycle operations. This module exports functions for finding all artifacts within a message (findAllArtifacts) and replacing their content (replaceArtifactContent), along with boundary constants. The accompanying test suite (update.spec.js) validates that these functions correctly parse artifacts from message content and text fields, handle edge cases like unclosed artifacts, nested fenced code blocks, and multiple artifacts within a single part, ensuring robust artifact context management.
api/server/services/Artifacts · high confidence
New authentication strategies and centralized exports for Apple, Discord, Facebook, GitHub, Google, JWT, LDAP, and OpenID
The \api/strategies\ directory now contains dedicated strategy implementations for Apple, Discord, Facebook, GitHub, Google, JWT, LDAP, and OpenID authentication, each wired to the shared \socialLogin\ handler and exposing both standard and admin-only login flows. The \index.js\ entry point centralizes and exports all these strategies, making them available to the application's authentication middleware. This change introduces new login capabilities (Apple, Discord, Facebook, GitHub, Google, LDAP) and refactors existing ones (JWT, OpenID) into a consistent, modular structure with corresponding test coverage.
api/strategies · high confidence
New cache-based violation logging and user ban system
The api/cache module now includes a new banViolation.js and logViolation.js implementation that tracks user violations in cache and automatically bans users when violation counts cross configurable thresholds. When a ban is triggered, the system clears all user sessions, removes refresh tokens and OpenID cookies, and stores ban records with configurable duration. The ban logic is controlled by BAN\_VIOLATIONS and BAN\_INTERVAL environment variables, with a default interval of 20 violations before triggering a ban. Tests verify the ban threshold logic, session cleanup, and cookie clearing behavior.
api/cache · high confidence
New chat header menu components for bookmarks, presets, and navigation
The Chat/Menus directory now contains dedicated React components (BookmarkMenu, HeaderMenu, NewChat, OpenSidebar, PresetsMenu) that consolidate header actions into a unified, accessible interface. BookmarkMenu and HeaderMenu manage bookmark states and visibility using role-based permissions, while PresetsMenu provides a popover for managing conversation presets. NewChat and OpenSidebar handle new conversation creation and sidebar toggling with keyboard shortcut support. These components replace scattered inline implementations with a consistent, mobile-responsive design using Ariakit for accessibility and Radix UI for popovers.
client/src/components/Chat/Menus · high confidence
New chat settings controls for prompts, direction, and run behavior
The Chat settings tab now includes dedicated UI components for several chat behaviors: Advanced Prompts (toggle between simple and advanced prompt modes), Chat Direction (switch between LTR and RTL text direction), During-Run Action (choose whether to steer or queue messages while a run is generating), Font Size (select from XS to XL), Fork Settings (configure default fork options and split-at-target behavior), Image Resize (toggle client-side image resizing with support/enforcement status), Save Badges State (preserve badge states across sessions), and Show Thinking (toggle visibility of model reasoning/thinking content).
client/src/components/Nav/SettingsTabs/Chat · high confidence
New client-side hooks and context providers for authentication, screenshots, and performance
The \client/src/hooks\ directory now includes several new React hooks and context providers that enhance the application's core functionality. \AuthContext.tsx\ centralizes session management, handling login, logout, and token refresh flows while ensuring proper cleanup of client state during session transitions. \ScreenshotContext.tsx\ introduces a robust screenshot capture mechanism with safeguards against main-thread freezes and canvas size limits, improving the reliability of exporting conversation views. \useCatalogWarmup.ts\ implements a background warmup strategy for feature catalogs (prompts, MCP servers/tools), loading them after the first paint to optimize initial render performance. Additionally, \useAdaptiveIcon.ts\ provides logic for tinting SVG icons based on their monochrome properties, and \useKeyboardShortcuts.ts\ adds comprehensive support for customizable global keyboard shortcuts across the UI.
client/src/hooks · high confidence
New client-side utilities for agent model selection, activity labeling, and tool approval
The client now includes dedicated utility modules in \client/src/utils\ to support new agent and activity features. \agentModelSelection.ts\ and its tests validate that agent and model selections remain available or clear gracefully when providers or models are removed. \activityLabels.ts\ introduces logic to parse, group, and fold activity phases and tool calls into UI cards, including handling of synthesized and live states. \approval.ts\ and its tests implement the client-side handling for tool-approval and ask-user-question pending actions, ensuring correct tagging of tool calls (including nested subagent calls) and idempotent UI updates. Additional utilities like \artifacts.ts\, \buildDefaultConvo.ts\, \citations.ts\, and \clock.ts\ provide foundational support for artifact rendering, conversation building, citation parsing, and locale-aware time formatting.
client/src/utils · high confidence
New data-provider hooks for banner, balance, and search settings
The application now exposes dedicated React Query hooks in the Misc data-provider module to fetch the UI banner, user account balance, and search-enabled status. These hooks (\useGetBannerQuery\, \useGetUserBalance\, \useGetSearchEnabledQuery\) integrate with the global \queriesEnabled\ state to conditionally activate data fetching, allowing the UI to dynamically display balance information and adjust features based on server-side configuration.
client/src/data-provider/Misc · high confidence
New data-provider hooks for code environments, insights, traces, and health checks
The client/src/data-provider directory now includes new modules that expose React Query hooks for managing code environments (pairing, deletion, settings, and conversation attachment), fetching admin insights and access status, retrieving conversation trace records with cursor pagination, and performing periodic health checks to prevent UI inactivity errors. These additions extend the existing data layer with new capabilities for workspace management, observability, and connection stability.
client/src/data-provider · high confidence
New data-provider hooks for tool execution, MCP status, and authentication
The client now exposes dedicated React Query hooks in the Tools data-provider layer to support new runtime capabilities. Users benefit from \useToolCallMutation\ for executing tools (such as the Code Interpreter) with automatic result caching, \useVerifyAgentToolAuth\ to check agent tool authentication status, and \useGetToolCalls\ to retrieve historical tool call results for a conversation. Additionally, \useMCPConnectionStatusQuery\ and \useMCPAuthValuesQuery\ provide real-time status and authentication values for Model Context Protocol (MCP) servers, enabling the UI to manage MCP reinitialization and OAuth flows more effectively.
client/src/data-provider/Tools · high confidence
New data-provider layer for Project management and conversation assignment
This change introduces a dedicated data-provider module for Projects, adding mutations to create, update, and delete projects, as well as a specialized mutation to assign conversations to projects. The assignment logic includes serialization to prevent race conditions when multiple UI surfaces (drag-and-drop, menus) interact with the same conversation, ensuring the user's latest intent is preserved. It also handles cache invalidation for archived and pinned conversations, cancels in-flight refetches to prevent stale data overwrites, and clears project associations when a project is deleted. Additionally, new queries are provided to list projects with pagination and sorting, fetch project details, retrieve project files, and resolve project names efficiently using a context-based cache.
client/src/data-provider/Projects · high confidence
New dedicated UI component for image generation tool calls
A new \OpenAIImageGen\ component has been added to render image generation tool calls within chat messages. It displays a progress bar and contextual status text (e.g., 'Creating image', 'Final touch') that updates based on the generation phase, tool type (OpenAI, Gemini, or agent-style), and quality settings. The component handles cancellation and error states distinctly, supports model-authored intent labels, and manages image scaling and layout reservation to prevent layout shifts during generation.
client/src/components/Chat/Messages/Content/Parts/OpenAIImageGen · high confidence
New email templates for user onboarding and account management
Added new Handlebars email templates for the invite user, password reset, request password reset, and email verification flows. These templates provide a consistent, responsive design with dark mode support for system-generated notifications, enabling users to receive structured emails for account invitations and security-related actions.
api/server/utils/emails · high confidence
New file management hooks and SharePoint integration
The \client/src/hooks/Files\ directory has been reorganized into a dedicated module, introducing a suite of new hooks to handle file operations. This includes \useAttachmentPreviewSync\ to manage the lifecycle of deferred code-execution previews, \useClientResize\ to allow users to toggle client-side image resizing, and \usePastedTextEdit\ to support editing pasted text as a file. Additionally, the module adds full support for the SharePoint File Picker and Download Workflow, enabling users to select and attach files directly from SharePoint.
client/src/hooks/Files · high confidence
New file table components for chat input
Added a new set of components in the chat input file area to display files in a table format. This includes a data table with sorting, filtering, and column visibility options, along with column definitions for file details like name, date, and source. A template table and sample data are also included for reference.
client/src/components/Chat/Input/Files/Table · high confidence
New file upload routes and content filtering for profile avatars
The file upload system now includes a dedicated route for profile avatar uploads (\/files/images/avatar\) that enforces content filtering policies. Before processing an avatar, the system inspects the file's metadata (such as the filename) and content against configured PII and content filters. If a violation is detected, the upload is blocked with a 400 error and the temporary file is cleaned up, preventing sensitive or prohibited data from being stored. This change ensures that profile pictures are subject to the same content safety checks as other file uploads.
api/server/routes/files · high confidence
New file-provider module with upload normalization, preview polling, and SharePoint integration
The \client/src/data-provider/Files\ directory now provides a dedicated module for file operations. It introduces \useUploadFileMutation\, which normalizes the server's \temp\_file\_id\ to match the client-requested \file\_id\ so that uploaded files remain correctly linked to drafts after navigation or reload. File previews now use a dedicated \previewRefetchInterval\ that polls every 2.5 seconds and stops on terminal states, with a cap on consecutive errors to prevent infinite polling. Download helpers distinguish direct sources (S3, CloudFront) from proxied ones and revoke only blob URLs. A new \useFilePreviewBlob\ query shares immutable blob bytes across deduplicated requests. Additionally, SharePoint file picker support is added via \useSharePointFileDownload\ and \useSharePointBatchDownload\ with progress callbacks. Tests cover preview polling behavior, upload normalization, and blob deduplication.
client/src/data-provider/Files · high confidence
New generation control buttons with keyboard shortcut support
The generation action buttons (Regenerate, Stop) now use a shared Button component that integrates with the keyboard shortcut system, displaying relevant key combinations (e.g., for regenerating or stopping responses) directly on the buttons for discoverability.
client/src/components/Input/Generations · high confidence
New generic React hooks for UI state and layout management
Added a suite of new utility hooks in the client's Generic hooks directory to support complex UI interactions. useShiftKey tracks the Shift key state while ignoring Alt+Shift combinations to prevent conflicts with accessibility shortcuts. useElementSize monitors an element's dimensions using ResizeObserver with a fallback to offset measurements. useOuterScrollWindow calculates the visible portion of a list relative to an ancestor viewport, enabling virtualized lists to be windowed by external scroll containers. useLazyEffect provides a debounced effect execution mechanism, and useUnsavedChangesPrompt integrates with react-router-dom to warn users before navigating away with unsaved changes. Also in this area: Artifacts pane state survives host moves and conversation switches.
client/src/hooks/Generic · high confidence
New granular access-control middleware for agents, MCP servers, skills, prompts, and files
The \api/server/middleware/accessResources\ directory now provides a unified permission-checking layer. A generic \canAccessResource\ factory validates access using the \PermissionService\ and role capabilities, and is specialized for each resource type: \canAccessAgentResource\ and \canAccessAgentFromBody\ (which also enforces MULTI\_CONVO role permissions and validates addedConvo agents), \canAccessMCPServerResource\, \canAccessSkillResource\ (with read-only enforcement for deployment skills), \canAccessPromptGroupResource\, and \canAccessPromptViaGroup\ (checking permissions at the prompt-group level). File access is handled by \fileAccess\, which enforces tenant-scoped isolation and inherits permissions from attached agents. All new middleware includes corresponding test coverage.
api/server/middleware/accessResources · high confidence
New input hooks and tests for command triggers, mentions, and ask-answer flows
The \client/src/hooks/Input\ directory now exports a set of new hooks and their tests that power the chat composer's interactive features. \useHandleKeyUp\ detects command characters (\@\, \/\, \+\, \$\) to trigger their respective popovers, while \mentions.ts\ and its tests filter available endpoints for the mention menu based on user access and model specs. \useAskAnswerMode\ and \useAskQuestionsForm\ manage the state and submission for agent-initiated \ask\_user\_question\ pauses, handling both single and batched questions. Additionally, \useAutoSave\ handles draft persistence and restoration across conversation switches, and \useComposerBindings\ manages keyboard shortcut overrides for the composer.
client/src/hooks/Input · high confidence
New middleware layer for request handling and access control
This change introduces a comprehensive set of new middleware functions in the api/server/middleware directory to handle various aspects of request processing and access control. Key additions include abort handling for message generation (abortMiddleware.js), endpoint option building with model spec enforcement (buildEndpointOption.js), shared link access validation (canAccessSharedLink.js), account deletion checks with capability-based authorization (canDeleteAccount.js), ban enforcement with IP and user tracking (checkBan.js), domain validation for social logins (checkDomainAllowed.js), invite user validation (checkInviteUser.js), people picker access control (checkPeoplePickerAccess.js), and public sharing access checks (checkSharePublicAccess.js). The implementation also includes specialized abort handling for OpenAI Assistants API runs (abortRun.js) and request denial logic (denyRequest.js). These middleware components work together to provide robust security, validation, and request lifecycle management for the API server.
api/server/middleware · high confidence
New navigation components for settings, search, and keyboard shortcuts
The navigation area now includes dedicated components for account settings, conversation search, and keyboard shortcut management. The AccountSettings menu provides access to archived chats, settings, and help resources, while the SearchBar enables debounced conversation search with proper state handling. A new KeyboardShortcutsDialog allows users to view and customize keyboard shortcuts, with a ShortcutRecorder component for binding new shortcuts. Additional components include NavLink for navigation items, NavToggle for sidebar visibility, and AgentMarketplaceButton for marketplace access.
client/src/components/Nav · high confidence
New prompt field components with improved accessibility and validation
The Prompts UI now includes dedicated field components for managing prompt metadata: CategorySelector for choosing prompt categories, Command for entering command identifiers with character limits, Description for adding prompt descriptions, and PromptName for inline editing with save status feedback. These components use unique IDs to ensure proper accessibility relationships when multiple forms are mounted, and the PromptName component specifically guards against IME composition issues on Enter key presses.
client/src/components/Prompts/fields · high confidence
New prompt management forms and variable handling
The Prompts forms directory has been restructured to include dedicated components for creating prompts (CreatePromptForm), editing existing prompts with version management (PromptForm), managing prompt labels (PromptLabelsForm), and handling variable substitution (VariableForm). These components provide a unified interface for users to create, edit, and deploy prompt groups, manage labels, and input variable values with support for both text and select types, all integrated with the application's permission system and design tokens. Also in this area: Improved subagent guidance display and fold rail visualization; RTL support and keyboard shortcuts for tool approval cards. Also in this area: 9 commits (4 fixes) modifying client/src.
client/src/components/Prompts/forms · medium confidence · unverified
New prompt management hooks for categories and navigation
The Prompts module now exposes dedicated React hooks to handle category selection and prompt group navigation. The new \useCategories\ hook fetches available categories, applies localization via \useLocalize\, and maps them to display labels and icons, respecting access controls. The \usePromptGroupsNav\ hook centralizes the infinite query for prompt groups, managing state for pagination size, category filters, and name searches via Recoil, while exposing navigation helpers like \nextCursor\ and \fetchNextPage\ to support efficient list rendering and filtering.
client/src/hooks/Prompts · high confidence
New screen-reader announcement system for dynamic content
The application now includes a dedicated accessibility module in the client source that provides structured live-region announcements for screen readers. This change introduces a context provider and helper components that expose polite and assertive announcement methods, allowing parts of the UI to communicate status updates (such as start/end of operations or composition states) to assistive technologies without disrupting the user's visual focus.
client/src/a11y · high confidence
New server-side utilities for static asset handling, file metadata, and email delivery
The api/server/utils directory now includes dedicated modules for managing static assets, file operations, and email sending. The new staticCache and fallback utilities provide configurable caching headers for static files and ensure the SPA index.html is served for unmatched routes while returning 404s for missing static assets. File handling is improved with utilities to determine file types, extract image metadata, and generate RFC 8187-compliant Content-Disposition headers that properly preserve Unicode filenames. Email delivery now supports both Mailgun and SMTP (via Nodemailer), with configurable encryption, self-signed certificate handling, and automatic fallback between providers. A leaky-bucket queue utility is also added to manage API request rates.
api/server/utils · high confidence
New shared UI component library and test infrastructure in @librechat/client
The \packages/client\ package now includes a comprehensive set of shared UI components (including Accordion, Alert, AlertDialog, AnimatedTabs, Avatar, Badge, Breadcrumb, and Button) along with a ToastContext provider and common type definitions. To support this new library, dedicated Jest configuration files (jest.config.js, jest.resolver.cjs, jest.setup.ts) and a Babel configuration (babel.config.js) have been added, providing the necessary test environment and module resolution rules for the client-side codebase.
packages/client · high confidence
New sharing permission hooks for granular access control
This change introduces a new set of React hooks in the client's sharing module to support granular, resource-specific access control. The \useResourcePermissionState\ hook centralizes the management of resource permissions, including current shares, public access status, and role-based settings, while ensuring that specific permissions like 'viewInsights' are preserved in shared snapshots. The \useCanSharePublic\ hook provides a unified way to check if a user has permission to share various resource types (such as Agents, Prompts, MCP Servers, Skills, and Shared Links) publicly. Additionally, the \usePeoplePickerPermissions\ hook manages the people picker interface by filtering available principal types (Users, Groups, Roles) based on the user's specific viewing permissions, ensuring that users only see the entities they are authorized to interact with.
client/src/hooks/Sharing · high confidence
New structured logging system with sensitive data sanitization
The API now includes a new logging infrastructure in api/utils that uses Winston for console and optional file output, controlled by the LOG\_TO\_FILE environment variable. A dedicated LoggingSystem module provides structured log levels and custom helpers for function parameters, variable values, and HTTP requests, automatically redacting sensitive information such as API keys, passwords, tokens, and secrets from logs to improve security and privacy.
api/utils · high confidence
New system components for consent, language, UI scale, updates, and wake lock
The System component area now includes several new leaf components that manage specific runtime behaviors: AnalyticsConsent handles Google Tag Manager loading only after user consent via a non-blocking banner; LanguageSync synchronizes the i18n language state with the app store; UiScaleSync applies the stored UI scale setting to the DOM; Updating displays a spinner while the app reloads onto a newer version; and WakeLockManager prevents the device screen from sleeping during AI response generation when the user preference allows. Tests were added to verify the consent flow and GTM integration.
client/src/components/System · high confidence
New tool configuration sections in the Agent Builder Item Dialog
The Agent Builder's tool selection dialog now features dedicated configuration sections for different tool types. Users can configure Actions with background execution and editors, manage built-in tools (Code Interpreter, Web Search, File Search, Artifacts, Context, and Memory) with specific settings like artifact modes and memory scope, and handle MCP servers with advanced options for OAuth, tool selection, and background execution. Plugin tools now include authentication forms and background execution toggles, while Skills display their descriptions and identifiers. Also in this area: Fixes for authentication flow, chat navigation, and subagent content recovery; App-Wide UI Scale Setting; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/SidePanel/Agents/Tools/ItemDialog/sections · high confidence
New utility functions for MCP Server configuration and validation
Added new utility modules in the MCP Server Dialog to improve server setup and error handling. The \oauth.ts\ module introduces \getOAuthConfig\ to correctly serialize OAuth options, including support for explicit token exchange methods. The \error.ts\ module provides localized error messages for specific MCP server issues like API key re-entry or domain restrictions. Additionally, \urlUtils.ts\ adds helpers to validate URLs, enforce HTTPS, auto-fill server names from hostnames, and detect transport types (SSE vs HTTP) from URL patterns.
client/src/components/SidePanel/MCPBuilder/MCPServerDialog/utils · high confidence
New web search API key management in Agent Builder
The Agent Builder now includes a dedicated UI for managing web search credentials. A new Action button allows users to add or manage API keys for search providers (Serper, SearXNG, Tavily, Keenable), scrapers, and rerankers (Jina, Cohere). The ApiKeyDialog component lets users select their preferred provider and reranker, enter sensitive keys securely using SecretInput, and configure custom URLs where applicable. The interface respects system-defined versus user-provided authentication types, hiding configuration options when the provider is system-managed, and persists selections to the agent form.
client/src/components/SidePanel/Agents/Search · high confidence
OpenAI file upload, deletion, and download capabilities
The OpenAI file service now supports uploading files to OpenAI with automatic handling of image metadata (vision vs. assistants purpose), deleting files from OpenAI, and retrieving file download streams. This enables users to attach files to OpenAI assistants and vision models, with the system waiting for file processing completion before returning the result.
api/server/services/Files/OpenAI · high confidence
Passkey Authentication with WebAuthn Sign-In and 2FA Integration
Users can now sign in using passkeys via WebAuthn, with the new \usePasskey\ hook handling the authentication ceremony, including support for browser autofill and recovery of stale WebAuthn script chunks. Upon successful passkey login, the system automatically enforces two-factor authentication workflows: accounts requiring initial setup are redirected to the 2FA setup page, while enrolled accounts are directed to the 2FA code challenge, ensuring secure access consistent with existing password-based 2FA flows.
client/src/hooks/Auth · high confidence
Pull request status and details in code conversations
For conversations using a code workspace, the chat interface now displays the associated pull request (or GitLab merge request) in the sidebar row and the desktop header. A small icon with a CI status dot marks the row, and hovering or focusing reveals a card showing the PR number, title, state, CI check status, and line changes, with a link to the provider (GitHub, GitLab, or Bitbucket). The header chip provides the same details in a hovercard, and a small-screen overflow menu entry opens the card in a dialog. If the lookup fails, a warning with a retry option is shown, and the feature is gated by a provider setting and only applies to code conversations.
client/src/components/Chat/PullRequest · high confidence
Redesigned Account Settings with granular profile, 2FA, and account management controls
The Account settings tab has been rebuilt using a new modular component structure, introducing a dedicated Avatar editor that supports zoom, rotation, and drag-to-position adjustments for profile pictures. Two-Factor Authentication is now managed through a multi-phase dialog flow (Setup, QR Scan, Verify, Backup) with distinct enable/disable toggles and backup code regeneration. Account security and lifecycle are enhanced with a Delete Account flow requiring email confirmation and 2FA verification, alongside a new setting to toggle whether the username is displayed on messages. Also in this area: 12 commits (8 fixes) fixing client; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Nav/SettingsTabs/Account · medium confidence · unverified
Redesigned code blocks with inline execution, result switching, and floating controls
Code blocks in messages now feature a comprehensive UI overhaul: a persistent header bar (CodeBar) displays the language, while a floating bar appears on hover for quick access to copy, download, and run actions. Users can now execute code directly within the chat via the RunCode component, which handles state transitions (idle, loading, success, error) and debounces execution. When multiple executions occur, a ResultSwitcher allows navigation between outputs. The layout also includes a LangIcon component for language-specific branding and improved accessibility with proper ARIA labels and focus management. Also in this area: 9 commits (4 fixes) modifying client/src; App-Wide UI Scale Setting; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Messages/Content · medium confidence · unverified
Scheduled chats now support renewable MCP credentials and preflight readiness checks
Scheduled chat execution now includes a preflight check to verify MCP (Model Context Protocol) readiness before firing, ensuring that required tools and connections are available. Additionally, the system supports renewable MCP credentials, allowing scheduled jobs to maintain valid authentication tokens over time rather than failing due to token expiration. This change introduces a new service layer in \api/server/services/Schedules\ that wires up these capabilities, including access resolution and balance initialization, to improve reliability for unattended scheduled tasks. Also in this area: Enforce scheduled MCP read-only authority and tool approval modes. Also in this area: 5 commits (2 fixes) modifying api/server/services.
api/server/services/Schedules · medium confidence · unverified
Server-side GitHub Skill Sync and Management Infrastructure
The Skills service now includes server-side logic to synchronize skills from GitHub repositories, manage skill lifecycles (creation, updates, deletions), and expose these capabilities through the Management API. This change introduces a new deletion service, request handlers that enforce permission checks and terms acceptance, and a sync orchestrator that schedules and runs GitHub skill imports. Users benefit from automated skill discovery and authoring via GitHub sources, with server-side enforcement of access controls and consent requirements.
api/server/services/Skills · high confidence
SharePoint File Picker Dialog Integration
Users can now select and download files from SharePoint via a new dialog component. This change introduces the SharePointPickerDialog, which integrates the SharePoint picker via an iframe and provides a dedicated UI for tracking batch download progress, including status updates and failure notifications. The component is designed to use the application's theme overlay for its backdrop, ensuring visual consistency with other dialogs.
client/src/components/SharePoint · high confidence
Sidebar conversations restructured with filtering, sorting, and drag-and-drop filing
The sidebar's conversation list has been reorganized into a unified, scrollable surface featuring a new ChatFilterMenu that allows users to filter by status (active or archived), sort by date, title, or usage, and filter by conversation bookmarks. The list now supports drag-and-drop filing of conversations into Projects and reordering within the Pinned section, with visual feedback for drop targets. Individual conversation rows include inline renaming, unpinning, and context menus, while the UI handles virtualized rendering for performance and includes pagination controls for large lists.
client/src/components/Conversations · high confidence
Skills UI: Create, Edit, and Manage Skills with File Tree
The client now includes a dedicated Skills interface, allowing users to create, edit, and manage Skills directly from the UI. This update introduces forms for defining Skill metadata (name, description, category, and invocation mode) alongside a rich Markdown editor for content. A file tree component enables browsing, previewing, and editing individual Skill files, complete with save states and download capabilities for assets.
client · high confidence
Unified Sidebar with Resizable Panels and Mobile Drawer
The sidebar has been redesigned into a unified component that supports resizable panels on desktop and a full-screen mobile drawer. Users can now adjust the sidebar width using a drag handle or keyboard shortcuts, with the preference saved locally. The mobile experience features a swipe-to-open drawer that can be configured to cover the full screen or a partial strip, improving navigation on smaller devices. The sidebar now includes a new chat button, agent marketplace access, and a unified navigation icon strip, all integrated with the active panel system.
client/src/components/UnifiedSidebar · high confidence
Unified Tools Marketplace and Skills Management
The Agent Builder now features a redesigned, unified interface for managing tools and skills. A new Tools Marketplace dialog allows you to browse, search, and filter tools by category (Built-in, Tools, MCP, Actions) and view (Marketplace, Mine, Favorites), with the ability to add, configure, and remove them directly. A dedicated Skills section provides three modes (Off, All, Selected) to control skill availability, while a Skills dialog enables standalone skill authoring and selection. Supporting components include an Action Editor for configuring custom tool authentication and a Category Filter for refined navigation.
client/src/components/SidePanel/Agents/Tools · high confidence
Unified sidebar favorites for agents, models, and model specs
The Favorites section in the sidebar now supports pinning and managing three types of items: agents, models, and model specs. A new FavoriteItem component renders these items with appropriate icons (agent avatars, model provider art, or spec icons) and allows users to unpin them directly via an inline button. The underlying useFavoritesData hook resolves agent details from the server, merges them with the global agents map, and automatically cleans up favorites for agents that no longer exist (404/403) or model specs removed from the startup configuration.
client/src/components/Nav/Favorites · high confidence
Architecture
Introduce centralized Prompts component exports
The Prompts feature area now exposes a consolidated barrel file that aggregates its internal modules, making it easier to import specific UI elements like the prompt editor, forms, dialogs, and sidebar components from a single location.
client/src/components/Prompts · high confidence
Migrate packages/api to TypeScript
The API package has been converted from JavaScript to TypeScript, bringing stricter type safety and improved developer tooling to the backend service.
packages/api · high confidence
Refactored chat hooks into a modular, dedicated directory
The chat logic previously contained in monolithic files has been reorganized into a structured \client/src/hooks/Chat\ directory. This change introduces specialized hooks for distinct responsibilities: \useAbortCleanup\ and \useQueueDrain\ manage the lifecycle of streaming and queued messages, \useBookmarkItems\ and \useExportShare\ handle conversation metadata and sharing, and \useChatFunctions\ centralizes the core submission and regeneration logic. This modularization improves code maintainability and allows for more granular state management across the chat interface. Also in this area: RTL support and keyboard shortcuts for tool approval cards; Agent-allowed machine selection and virtualized file table; Artifacts pane state survives host moves and conversation switches.
client/src/hooks/Chat · high confidence
Behavioural changes
1 commit (0 fixes) modifying client/src/components/Responses, client/src/data-provider/Responses
A change to existing behaviour in client/src/components/Responses, client/src/data-provider/Responses — 1 commit, 9 files: “⏯️ feat: Review and Stop Background Responses (\#17613)” (refs \#17613).
client/src/components/Responses, client/src/data-provider/Responses · medium confidence · unverified
13 commits (2 fixes) modifying client/src/data-provider/Subagents
A change to existing behaviour in client/src/data-provider/Subagents — 13 commits (2 fixs), 7 files: “🦉 fix: Quiet Idle Subagent Discovery While Preserving Child Wakeups (\#16308)”; “📼 refactor: Move the Subagent Transcript Into @librechat/chat Behind a Subagents Host (\#17678)”; “🧭 refactor: Move the Pure Subagent Modules Into @librechat/chat (\#17582)”; and 10 more (refs \#16308, \#17678, \#17582, \#17633, \#17759, …).
client/src/data-provider/Subagents · medium confidence · unverified
14 commits (3 fixes) modifying client/src/components/Chat/approval
A change to existing behaviour in client/src/components/Chat/approval — 14 commits (3 fixs), 2 files: “🫰 feat: Configure Tool Approval Modes Per Agent (\#16707)”; “🗳️ fix: Defer Thread Approval Card to the Open Composer Review (\#16437)”; “⌨️ refactor: Move Composer Input Controls Into the Chat Package (\#17551)”; and 11 more (refs \#16707, \#16437, \#17551, \#16041, \#14473, …).
client/src/components/Chat/approval · medium confidence · unverified
16 commits (1 fix) modifying client/src/components/Chat/Trace
A change to existing behaviour in client/src/components/Chat/Trace — 16 commits (1 fix), 23 files: “🪶 style: Quieter Primitives, Shared Panel Headers, and Flat Management Lists (\#16244)”; “💵 feat: Show Cost per Record, Step and Response in the Trace Ledger (\#16120)”; “✂️ refactor: Name Tool Rounds From the Trace, and Match a Cut Response From Its End (\#16113)”; and 13 more (refs \#16244, \#16120, \#16113, \#16753, \#17682, …).
client/src/components/Chat/Trace · medium confidence · unverified
160 commits (20 fixes) modifying packages/chat
A change to existing behaviour in packages/chat — 160 commits (20 fixs), 628 files: “🛟 refactor: Move Resume-on-Load and Stream Steer State Into the Chat Package (\#17565)”; “🧷 refactor: Require a Mounted Steer Host Instead of a Module Default (\#17164)”; “🔁 fix: Keep the Error Card When a Stream Reattached Without Resume State Fails (\#17112)”; and 157 more (refs \#17565, \#17164, \#17112, \#17760, \#17512, …).
packages/chat · medium confidence · unverified
17 commits (5 fixes) modifying client/src/components/Chat/BackgroundTasks
A change to existing behaviour in client/src/components/Chat/BackgroundTasks — 17 commits (5 fixs), 6 files: “📬 fix: Show Background Results Still Waiting for the Agent (\#16363)”; “🧮 refactor: Move Pure Part Helpers Into the Chat Package (\#17520)”; “🎬 feat: Animate Background Tasks and Add Tool Navigation (\#16959)”; and 14 more (refs \#16363, \#17520, \#16959, \#17020, \#17582, …).
client/src/components/Chat/BackgroundTasks · medium confidence · unverified
172 commits (32 fixes) modifying client/src/Providers
A change to existing behaviour in client/src/Providers — 172 commits (32 fixs), 45 files: “🤖 feat: Streamline Endpoints to Agent Framework (\#8013)”; “✨ v0.7.5-rc2 (\#3976)”; “🛟 refactor: Move Resume-on-Load and Stream Steer State Into the Chat Package (\#17565)”; and 169 more (refs \#8013, \#3976, \#17565, \#17164, \#13045, …).
client/src/Providers · medium confidence · unverified
2 commits (0 fixes) modifying .oss-scanner
A change to existing behaviour in .oss-scanner — 2 commits, 3 files: “🦠 chore: Upgrade Node.js and Undici to Security Releases (\#18066)”; “📵 chore: Add an Offline OSS Scanner Environment (\#17645)” (refs \#18066, \#17645).
.oss-scanner · medium confidence · unverified
2 commits (0 fixes) modifying search
A change to existing behaviour in search — 2 commits, 5 files: “🐋 chore: add opt-in alternative local stack experiments (\#14678)”; “🧗 chore: Bump ClickHouse to 26.3.62.3 LTS (\#17647)” (refs \#14678, \#17647).
search · medium confidence · unverified
21 commits (0 fixes) modifying client/src/components/Chat/Input/TokenUsage
A change to existing behaviour in client/src/components/Chat/Input/TokenUsage — 21 commits, 3 files: “🧽 style: Composer, Welcome Screen and Context Panel Polish (\#15838)”; “💬 refactor: ChatForm UI redesign with unified palette (\#14473)”; “🥧 feat: Show Last-Turn Token Usage Beside Conversation Totals (\#16230)”; and 18 more (refs \#15838, \#14473, \#16230, \#15690, \#13874, …).
client/src/components/Chat/Input/TokenUsage · medium confidence · unverified
3 commits (1 fix) modifying client/src/components/Chat/Messages/ui
A change to existing behaviour in client/src/components/Chat/Messages/ui — 3 commits (1 fix), 1 file: “🧱 feat: Layered Surface Roles for the ClickHouse Theme (\#16737)”; “🦎 fix: Restore Theme Contrast in Composer and Messages (\#16624)”; “🧷 refactor: Move the Message Row Contexts into @librechat/chat (\#17674)” (refs \#16737, \#16624, \#17674).
client/src/components/Chat/Messages/ui · medium confidence · unverified
4 commits (0 fixes) modifying client/src/components/Chat/Messages/Thread
A change to existing behaviour in client/src/components/Chat/Messages/Thread — 4 commits, 3 files: “🧶 feat: Flatten Active Message Threads Behind a Flag (\#15633)”; “🎖️ perf: Promote Flat Thread Rendering to Default (\#15660)”; “🪜 refactor: Move the Thread Renderers Into @librechat/chat as the Default Thread (\#17661)”; and 1 more (refs \#15633, \#15660, \#17661, \#17562).
client/src/components/Chat/Messages/Thread · medium confidence · unverified
4 commits (1 fix) modifying client/src/components/Lia
A change to existing behaviour in client/src/components/Lia — 4 commits (1 fix), 17 files: “🖥️ feat: Show Lia on the Welcome Screen (\#16684)”; “🧠 feat: Add Lia's Behavior Engine (\#16683)”; “🪶 fix: Time Out Client Refresh and Trim Lodash Imports (\#17467)”; and 1 more (refs \#16684, \#16683, \#17467, \#16682).
client/src/components/Lia · medium confidence · unverified
48 commits (7 fixes) modifying client/src/hooks/SSE
A change to existing behaviour in client/src/hooks/SSE — 48 commits (7 fixs), 14 files: “🧵 feat: Native Background Execution for Code Interpreter Tools (\#14386)”; “🛡️ fix: Improve Error Handling and Null Safety in SSE Event Processing (\#10751)”; “🛟 refactor: Move Resume-on-Load and Stream Steer State Into the Chat Package (\#17565)”; and 45 more (refs \#14386, \#10751, \#17565, \#17658, \#10926, …).
client/src/hooks/SSE · medium confidence · unverified
5 commits (0 fixes) modifying client/src/components/Nav/SettingsTabs/About
A change to existing behaviour in client/src/components/Nav/SettingsTabs/About — 5 commits, 2 files: “🧹 refactor: Use Logical Spacing and Positioning in the App Shell (\#17269)”; “🆔 feat: Built-in Build Metadata for Support Triage (\#12756)”; “🎛️ feat: Redesign Settings with Registry-Driven Dialog, Search, and Mobile Drill-In (\#13722)”; and 2 more (refs \#17269, \#12756, \#13722, \#17771, \#14734).
client/src/components/Nav/SettingsTabs/About · medium confidence · unverified
52 commits (12 fixes) modifying client/src/components/Chat/Input/Files
A change to existing behaviour in client/src/components/Chat/Input/Files — 52 commits (12 fixs), 5 files: “🤖 feat: Streamline Endpoints to Agent Framework (\#8013)”; “☁️ fix: Enable Azure Agent Provider Uploads (\#13045)”; “🪞 fix: Prevent Revoked Blob URLs in Uploaded Images (FileRow) (\#10361)”; and 49 more (refs \#8013, \#13045, \#10361, \#15017, \#10336, …).
client/src/components/Chat/Input/Files · medium confidence · unverified
6 commits (0 fixes) modifying client/src/components/OAuth
A change to existing behaviour in client/src/components/OAuth — 6 commits, 6 files: “🔐 style: Restyle the OAuth Success and Error Pages (\#17729)”; “🎨 refactor: adopt the \@librechat/client\ design system (semantic color tokens + component migration) (\#13879)”; “🔌 feat: Add a Connected Account Setting for Pull Requests (\#16990)”; and 3 more (refs \#17729, \#13879, \#16990, \#9698, \#17811, …).
client/src/components/OAuth · medium confidence · unverified
6 commits (3 fixes) modifying api/server/routes/files/speech
A change to existing behaviour in api/server/routes/files/speech — 6 commits (3 fixs), 5 files: “🎤 feat: add custom speech config, browser TTS/STT features, and dynamic speech tab settings (\#2921)”; “🛂 feat: Filter Model-Bound Content by Source (\#14425)”; “🧯 fix: Guard SSE Writes and Interval Cleanups Against Crashes (\#17462)”; and 3 more (refs \#2921, \#14425, \#17462, \#13072, \#4705, …).
api/server/routes/files/speech · medium confidence · unverified
7 commits (2 fixes) modifying client/src/components/Chat/Subagents
A change to existing behaviour in client/src/components/Chat/Subagents — 7 commits (2 fixs), 5 files: “🗂️ refactor: Read the Parent Subagent Index Through the Stream Host (\#17633)”; “📡 refactor: Attach the Subagent Activity Feed Through the Chat Transport (\#17526)”; “🛰️ fix: Route Subagent Files Delivered After a Mid-Run Reload (\#17212)”; and 4 more (refs \#17633, \#17526, \#17212, \#17635, \#17632, …).
client/src/components/Chat/Subagents · medium confidence · unverified
8 commits (1 fix) modifying client/src/components/Skills/tree
A change to existing behaviour in client/src/components/Skills/tree — 8 commits (1 fix), 4 files: “🧹 refactor: Use Existing Variants and Drop Redundant Overrides in Nav, Skills and Prompts (\#16868)”; “🧩 fix: Paint Panel Surfaces From Theme Roles (\#16484)”; “🧹 refactor: Replace Arbitrary Values in the Agent Builder and Skills (\#16824)”; and 5 more (refs \#16868, \#16484, \#16824, \#17702, \#13879, …).
client/src/components/Skills/tree · medium confidence · unverified
9 commits (4 fixes) modifying client/src
A change to existing behaviour in client/src — 9 commits (4 fixs), 103 files: “🔐 fix: Require Typed Confirmation Before Revoking Admin Feature Access (\#18110)”; “💬 feat: Redesign the Slack Channels Setup and Management UI (\#18105)”; “🎚️ fix: Resolve Parameters for Bare Bedrock Claude Model IDs (\#18041)”; and 6 more (refs \#18110, \#18105, \#18041, \#18120, \#18104, …).
client/src/components/Channels, packages/channel-gateway · medium confidence · unverified
Agent code execution and tool configuration hooks
The client now includes a comprehensive set of hooks in the Agents directory to manage code execution decisions, tool permissions, and agent capabilities. Users benefit from persistent code approval mode preferences that remember their last selection across browser sessions, and sealed code environment decisions that prevent unintended workspace changes once a chat run is submitted. The system now dynamically determines file upload and code execution permissions based on the selected agent's capabilities and configuration, while also supporting granular tool options such as deferred loading, background execution, and programmatic calling for MCP tools. Agent capabilities are now explicitly exposed (e.g., code, memory, deferred tools, background tools), allowing the UI to adapt to what each agent supports. Additionally, workspace preferences are stored locally to remember recent workspace selections, and agent categories are fetched and translated for the marketplace interface.
client/src/hooks/Agents · high confidence
Agent-scoped file access control and retention wiring
The Files service now enforces granular access control for files attached to agents: users can only view or delete files if they have the corresponding VIEW or EDIT permissions on the agent, and access is scoped strictly to files attached via the agent's tool resources. This change also wires up retention logic so that agent file lifecycles are tied to the owning agent's retention settings, and ensures that deleting a file cleans up its references across all agents that use it.
api/server/services/Files · high confidence
Artifact download and rendering logic refactored into dedicated hooks
The artifact handling logic in the client has been reorganized into specific hooks to improve modularity and reliability. A new \useArtifactDownload\ hook now manages file downloads, intelligently choosing between downloading the original source file or exporting edited content as a blob, while providing user feedback on download success. \useArtifactProps\ centralizes the preparation of rendering properties, handling theme-aware styling for Mermaid diagrams, wrapping code artifacts in fenced blocks for proper syntax highlighting, and injecting high-contrast overrides for Office document previews. Additionally, \useArtifacts\ and \useResetArtifactsOnConversationChange\ now coordinate state management, ensuring artifacts are correctly ordered, auto-opened, and wiped when switching conversations to prevent data leakage.
client/src/hooks/Artifacts · high confidence
Assistant API v2 and Content Filtering for Actions and Chat
The assistant routes now include a new v2 API layer (v1.js and v2.js) alongside the existing v1 endpoints, with chat operations split into dedicated chatV1.js and chatV2.js routes. Both chat routes apply a PII-based message filter that blocks content matching configured patterns before reaching the controller. Assistant creation and patching (v1 and v2) now run through a content filter that inspects assistant metadata and tool/function definitions, blocking submissions that contain sensitive patterns or exceed traversal limits. The actions route enforces domain allowlisting, validates OAuth metadata, and applies the same content filtering to function parameters and descriptions before encryption or external calls.
api/server/routes/assistants · high confidence
Assistant access control now enforces private mode and authorship validation
The assistant middleware now includes validation logic to support private assistants and verify user authorship. When an endpoint is configured with private assistants, users must either hold the MANAGE\_ASSISTANTS capability or be the original author of the assistant to access it; otherwise, access is denied. Additionally, a new validation middleware checks if an assistant ID is explicitly supported or excluded by the endpoint configuration, blocking requests for unsupported or excluded assistants.
api/server/middleware/assistants · high confidence
Assistant selection now clears model spec display fields
When a user selects an assistant, the system now explicitly resets model spec display fields (such as spec, iconURL, and modelLabel) to null in the conversation and preset templates. This ensures that assistant-specific configurations do not carry over unwanted UI metadata from previous contexts, providing a cleaner and more consistent assistant interface.
client/src/hooks/Assistants · high confidence
Auth UI components migrated to the @librechat/client design system
The authentication screens (Login, Registration, Password Reset, Email Verification, and Two-Factor) have been rebuilt to use the new \@librechat/client\ design system. This introduces a consistent visual style across the auth flow, including the \SecretInput\ component for passwords, \InputOTP\ for two-factor codes, and \Alert\ for error/success messages. The layout now supports a configurable \Banner\, a \ThemeSelector\ toggle, and a \Footer\ that renders Privacy Policy and Terms of Service links from the startup configuration. Social login buttons are now rendered via a dedicated \SocialLoginRender\ component that respects the \startupConfig.socialLogins\ order, and the login form now integrates Cloudflare Turnstile CAPTCHA when enabled.
client/src/components/Auth · high confidence
Centralized app startup, state cleanup, and speech settings initialization
The application now uses a new \useAppStartup\ hook to manage initialization tasks on load, including setting the document title, configuring the default model preset, installing CloudFront image retry logic, and initializing Google Tag Manager. It also gates MCP server queries behind the \USE\ permission and ensures they only fetch when the catalog is ready, preventing unnecessary 403 errors. A new \useClearStates\ hook provides a unified way to reset conversation, submission, and various UI-related Recoil/Jotai states, along with clearing timestamped local storage. Additionally, \useSpeechSettingsInit\ ensures speech-to-text and text-to-speech settings are correctly initialized from server configuration or local storage, with fallbacks to browser engines if external ones are unavailable. Also in this area: Artifacts pane state survives host moves and conversation switches.
client/src/hooks/Config · high confidence
Centralized authentication data provider with 2FA and query control
The authentication data layer has been reorganized into a dedicated module under \client/src/data-provider/Auth\, consolidating login, logout, user management, and Two-Factor Authentication (2FA) mutations and queries. This change introduces granular control over data fetching via a \queriesEnabled\ state, which allows the application to disable automatic refetching during sensitive operations like login or logout to prevent race conditions. It also standardizes the client-side handling of 2FA workflows (enable, verify, disable, backup codes) and integrates with the global query cache to ensure user state consistency across the application.
client/src/data-provider/Auth · high confidence
Centralized provider icon resolution and endpoint selection hooks
The \client/src/hooks/Endpoint\ directory now provides a unified system for managing endpoint icons and selection state. A new \useProviderIcon\ hook and \resolveProviderIcon\ utility establish a strict precedence for icon display: custom image URLs take priority, followed by provider-specific art, server-resolved provider IDs, and first-class endpoint mappings. This logic is integrated into the \useEndpoints\ hook, which now constructs the model selector list with consistent icons and handles filtering based on user permissions (such as agent access) and model availability. Additionally, \useSelectorEffects\ manages the synchronization of selected agents and assistants with the conversation state, while \useKeyDialog\ standardizes the opening of API key configuration dialogs.
client/src/hooks/Endpoint · high confidence
Centralized rate-limiting middleware for API endpoints
The server now enforces rate limits across a broad set of endpoints—including login, registration, password reset, email verification, file uploads, conversation forking, sharing, message sending, tool calls, and text-to-speech/speech-to-text—using a new modular middleware structure in \api/server/middleware/limiters\. Limits are configurable via environment variables (e.g., \LOGIN\_MAX\, \FILE\_UPLOAD\_IP\_MAX\, \MESSAGE\_USER\_MAX\) and apply per-IP and per-user where applicable. Violations are logged and tracked with violation scores, and the login limiter now redirects OAuth browser navigations instead of returning JSON. IPv6 shared-link access is bucketed by subnet to prevent rotation-based bypass, and agent event ingestion has its own admission limiter. Tests cover the new limiters and their behaviors.
api/server/middleware/limiters · high confidence
Client application restructured with new root components and mobile styling
The client application has been restructured to improve modularity and mobile support. A new App.jsx root component now centralizes providers (React Query, Recoil, Radix Toast, DnD) and introduces a WakeLockManager to prevent screen sleep during response generation. A new LanguageSync component handles i18n updates, and a new AskOptions component standardizes the UI for user questions. Mobile-specific styles have been consolidated into a dedicated mobile.css file, and the main entry point (main.jsx) now initializes i18n before rendering. Additionally, a new test file (style.spec.ts) ensures code font consistency across platforms.
client/src · high confidence
Composer UI redesign with unified palette and chip-based controls
The Composer input area has been redesigned to use a unified palette for managing tools, skills, and files. The previous split between the attach menu and tools gear is replaced by a single Palette popup that supports searching, favoriting, and virtualized lists. Active selections are now displayed as chips in the Composer Bar, which intelligently manages layout by moving chips to a separate row when they no longer fit inline. The interface includes a new Catalog dialog for browsing skills and MCP servers, a dedicated Effort slider for reasoning control, and a Queue rail for managing staged messages with drag-and-drop reordering. Also in this area: 9 commits (4 fixes) modifying client/src; 12 commits (8 fixes) fixing client.
client/src/components/Chat/Input/Composer · medium confidence · unverified
Conversation access validation and subagent thread turn guards
The API now enforces strict authorization for conversation access via a new \validateConvoAccess\ middleware that verifies the requesting user owns the conversation, caches the result to avoid redundant database reads, and stashes the resolved conversation object for downstream handlers. Additionally, a new \subagentThreadTurn\ middleware validates subagent thread turns by checking the status of the associated generation job and ensuring the user and tenant IDs match, preventing unauthorized resume actions.
api/server/middleware/validate · high confidence
Conversation export formatting and navigation state fixes
This change introduces a new \format.ts\ module and \useExportConversation\ hook to standardize how conversation messages are exported to Markdown and text files, ensuring that reasoning content (THINK tags) is rendered as readable collapsible sections and that all content types (images, audio, tool calls, agent updates) are consistently labeled. It also adds \useNavigateToConvo\ to fix conversation navigation state issues by preventing stale records from overriding user intent and ensuring the full conversation record is loaded before switching, along with \useGetSender\ to correctly resolve sender labels based on model specs and endpoint configurations.
client/src/hooks/Conversations · high confidence
Conversation import and forking now resolve models from runtime config and enforce stricter content and retention rules
When importing or forking conversations, the system now attempts to resolve the default model and endpoint from the runtime models configuration (via \getModelsConfig\) instead of relying solely on hardcoded defaults, falling back to OpenAI defaults only when the config is unavailable. Stateful assistant endpoints are excluded as fork targets to prevent validation errors. The import pipeline now enforces file size limits, applies source-aware content filters (including legacy PII patterns) to block imports containing restricted data, and correctly handles timestamp ordering to prevent fragmented conversation trees. Additionally, forking subagent threads detaches durable runtime metadata, and retention fields are applied consistently to imported records.
api/server/utils/import · high confidence
Conversation mode switch now auto-configures speech settings
The new ConversationModeSwitch component in the Speech settings tab now automatically adjusts related speech parameters when toggled. Enabling conversation mode sets the auto-send text delay to 3 seconds, the decibel value to -45, and enables auto-transcribe audio, ensuring a consistent out-of-the-box experience for voice interactions.
client/src/components/Nav/SettingsTabs/Speech · high confidence
Endpoint Settings UI restructured with model-aware, component-driven panels
The settings UI for conversation endpoints has been restructured to use a new, model-aware configuration system. Instead of static forms, each endpoint (OpenAI, Anthropic, Google, Bedrock, Assistants) now renders its settings dynamically based on a shared schema from \librechat-data-provider\. This enables model-specific parameter adjustments, such as the new Reasoning Effort slider for GPT-6 Sol/Luna models and the Thinking/Effort controls for Claude Opus 5.5. The Google endpoint also features a multi-view layout that conditionally displays Few-Shot Examples for chat models. Additionally, the Assistants endpoint now includes dedicated controls for selecting assistants and configuring instructions.
client/src/components/Endpoints/Settings · high confidence
Enforce strict i18n key checks and add inert attribute support
The application now enforces strict key checks for internationalization resources, ensuring that all translation keys used in the codebase exactly match those defined in the locale files (specifically English), which helps prevent runtime errors from missing or misspelled keys. Additionally, TypeScript definitions have been updated to recognize the 'inert' HTML attribute on elements, allowing developers to use this attribute without type errors.
client/src/@types · high confidence
Enforces consistent code style and static checks on commit
The pre-commit hook now automatically formats, sorts imports, and lints staged files using the same configuration as the CI static checks, ensuring that code committed to the repository adheres to the project's style guide and passes linting rules before being saved. This change improves code consistency and reduces the likelihood of style-related issues in pull requests by catching errors locally.
.husky · high confidence
Explicit browser approval required for machine enrollment
The Code Setup page now requires users to explicitly approve or deny machine enrollment attempts rather than proceeding automatically. Users are presented with the machine name, verification code, key fingerprint, workspace type, and expiration time, and must actively select an authorized control plane and click Approve to proceed. The interface enforces a 10-minute expiration window, displays loading and error states, and handles Terms of Service acceptance before allowing a decision. This change is supported by a new browser enrollment protocol (version 1) in the vendor directory that defines the request, proof, and redemption structures used for this explicit consent flow.
client/src/components/Code, vendor · high confidence
File search citations now respect user permissions and tool artifacts
The file search citation system has been updated to process citations directly from tool artifacts rather than relying on separate lookups. Citations are now gated by a specific FILE\_CITATIONS permission check, ensuring users only see results they are authorized to access. Additionally, citation sources are enhanced with file metadata (such as filename and storage type) fetched from the database, and limits on the number of citations per file and total citations can be configured via the app settings.
api/server/services/Files/Citations · high confidence
Granular role-based permissions and capability-based authorization
The system now supports fine-grained, capability-based access control. Administrators can define specific permissions (such as USE, CREATE, SHARE, READ, UPDATE, and OPT\_OUT) for distinct resource types like Agents, Prompts, and Memories, allowing for more restrictive roles (e.g., 'limited') that deny specific actions even if general access is granted. This change introduces new middleware functions (\hasCapability\, \requireCapability\, \hasConfigCapability\) and a \checkAccess\ utility that enforce these granular rules, ensuring users can only perform actions explicitly permitted by their assigned role.
api/server/middleware/roles · high confidence
Improved Mermaid diagram rendering with debouncing and high-contrast support
The Mermaid rendering logic has been refactored to improve reliability and accessibility. A new \useDebouncedMermaid\ hook prevents premature rendering of incomplete diagrams (such as those still streaming) by detecting incomplete syntax patterns and applying a configurable delay, while also supporting forced retries. The core \useMermaid\ hook now integrates with the application's \ThemeContext\ to correctly handle high-contrast modes, ensuring that accessibility overrides take precedence over custom user themes. Additionally, rendering is now cached using SWR based on content, theme, and appearance state, and SVG output is sanitized to preserve necessary HTML elements while enforcing strict security levels.
client/src/hooks/Mermaid · high confidence
Improved message cache stability and memory management
The client now prevents message loss during streaming by preserving the local cache when a server refetch returns a partial result that is a prefix of the current stream. Additionally, a new retention policy automatically releases message histories for conversations the user has left, preventing memory bloat from long transcripts while keeping pinned, active, and recently visited conversations cached.
client/src/data-provider/Messages · high confidence
Improved mobile drawer swipe and toggle responsiveness
The mobile navigation drawer now features a smoother, more responsive swipe-to-open gesture and a more reliable toggle mechanism. A new pointer guard prevents accidental taps on the conversation pane while the drawer is animating, and the sidebar state flip is deferred until after the first animation frames to eliminate UI stutter on large conversations. Rapid toggles now correctly alternate the drawer's open/closed state instead of stacking on a stale value.
client/src/hooks/Nav · high confidence
Improved subagent guidance display and fold rail visualization
Subagent guidance (steers) now renders inline within the chat flow using the SteerPart component, which supports lazy-loading of truncated messages and correctly omits the receipt indicator for failed guidance. The fold rail visualization has been updated to display branching paths for nested folds, and parallel column rows are no longer incorrectly highlighted as part of the fold trunk. Additionally, the PromptGroupsContext now distinguishes external Langfuse prompts by displaying a Cloud icon and a source description, while native prompts retain their existing category icons and labels. Also in this area: Langfuse integration data provider hooks.
client/src/data-provider/Langfuse · high confidence
Introduce Artifacts Panel with resizable layout and mobile handling
The SidePanel component now includes a new ArtifactsPanel that renders alongside the main chat view using react-resizable-panels v4. On desktop, the panel is collapsible, defaults to 50% width (max 70%, min 15% when artifacts are present), and persists its layout in localStorage under the 'side-panel-layout' key. On screens narrower than 768px, the artifacts panel is hidden from the split layout and instead shown as a full-screen overlay (z-index 100) when content is present. The panel auto-expands when content arrives and manages its render state via onRenderChange callbacks. A new Nav component renders active panel content based on resolved active links, and the group exposes SidePanelGroup as the public entry point.
client/src/components/SidePanel · high confidence
Introduce MCP Builder Panel with Admin Settings and Unified Status UI
The MCP Builder side panel now features a redesigned user interface with a dedicated admin settings dialog for managing server permissions (USE, CREATE, SHARE, SHARE\_PUBLIC, CONFIGURE\_OBO). The panel includes a search filter for servers, standardized action buttons for connecting, configuring, and revoking access, and a unified status system using colored dots and badges to indicate connection states (connected, connecting, on-demand, needs auth, error). OAuth flows are now handled via an in-app dialog instead of opening new tabs, improving compatibility with iOS home-screen apps.
client/src/components/SidePanel/MCPBuilder · high confidence
Introduce dedicated Run and StreamRunManager services for OpenAI Assistants
The \api/server/services/Runs\ directory now contains a new modular architecture for handling OpenAI Assistant runs. \RunManager\ manages the retrieval and processing of run steps based on run status, while \StreamRunManager\ implements streaming logic to handle real-time events like tool calls, message creation, and progress updates. The \handle.js\ file provides the core \waitForRun\ polling mechanism and \createRun\ execution, and \methods.js\ handles low-level API retrieval with specific support for Azure OpenAI configurations. This refactors the previous monolithic run handling into distinct, reusable components for both standard and streaming assistant interactions.
api/server/services/Runs · high confidence
Introduce dedicated prompt modules for artifacts, vision, and message formatting
The \api/app/clients/prompts\ directory has been reorganized into a set of dedicated modules to improve how the system handles complex message types. A new \artifacts.js\ module defines the prompt instructions for generating and managing self-contained content artifacts (such as HTML, React components, Mermaid diagrams, and Markdown) in a separate UI window, including updated library versions (e.g., lucide-react@0.394.0, three.js, date-fns) and support for SVG and Markdown types. A new \createVisionPrompt.js\ module provides tailored instructions for users to describe visual content, while \formatMessages.js\ and \formatGoogleInputs.js\ standardize how messages are structured for different endpoints, including specific handling for OpenAI name regex constraints and Google's \struct\_val\ payload format. Additionally, \createContextHandlers.js\ centralizes RAG context retrieval logic, and \summaryPrompts.js\ manages conversation summarization templates.
api/app/clients/prompts · high confidence
Local file service now strips cache-bust query strings and enforces path traversal protection
The local file service now automatically strips cache-busting query strings (e.g., \?v=...\) from file paths before reading or encoding images, ensuring that reused code outputs resolve to the correct files on disk. Additionally, the service now strictly validates file paths to prevent directory traversal attacks, rejecting filenames containing \..\ sequences or attempting to escape the designated upload/image directories.
api/server/services/Files/Local · high confidence
Model selector UI refresh with virtualization and grouping
The model selector menu has been redesigned to improve performance and usability. It now supports grouping model specs into custom categories with dedicated icons, and includes a dedicated marketplace entry for browsing agents. To handle large lists of models (especially agents) efficiently, the selector uses virtualization, rendering only the visible rows to maintain smooth scrolling and keyboard navigation. The UI also features a single-tap selection for pinned items on touch devices, improved accessibility with correct ARIA roles for virtualized lists, and a new pin/unpin button for favoriting models and specs.
client/src/components/Chat/Menus/Endpoints/components · high confidence
Modularized Text-to-Speech logic with dedicated browser and external components
The Audio components have been refactored to separate text-to-speech functionality into distinct implementations for browser-based and external services. New files, TTS.tsx and Voices.tsx, introduce BrowserTTS and ExternalTTS components that handle audio playback and voice selection independently, each exposing their own voice dropdowns. This change supports improved browser compatibility and allows users to choose between local and external TTS engines, with settings for playback rate and voice selection now managed through specific hooks (useTTSBrowser, useTTSExternal) and UI controls.
client/src/components/Audio · high confidence
New Item Dialog for Agent Tools and Skills
The tool and skill selection interface in the Agent Builder has been refactored to use a new, unified ItemDialog component. This dialog now provides a consistent header with kind-specific labels (builtin, tool, skill, MCP, action) and icons, and routes to specialized body sections for each item type. It also includes specific layout adjustments for orchestration items (subagents and handoffs) and actions, such as preventing auto-focus issues and adjusting width constraints, to improve usability when configuring agent capabilities.
client/src/components/SidePanel/Agents/Tools/ItemDialog · high confidence
New Message UI Components and Feedback System
The chat interface now features a redesigned message row layout with a new hover-based action system. Users can provide detailed feedback on responses using a thumbs-up/down popover with specific tags (e.g., 'Incorrect', 'Harmful'). The interface also displays the elapsed time for streaming responses and offers options to fork conversations from specific messages. Additionally, message audio playback is now integrated directly into the message row, and a new navigation rail allows for easier scrolling through long conversations. Also in this area: 20 commits (8 fixes) modifying client; App-Wide UI Scale Setting; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Chat/Messages · medium confidence · unverified
New Prompt Group List Components
The Prompts sidebar now uses a new set of components (List, ListCard, ChatGroupItem, NoPromptGroup, PromptGroupSkeleton) to render prompt groups. This introduces permission-aware rendering (checking EDIT/DELETE rights), distinct handling for shared vs. global prompts, and a variable-confirmation dialog before submitting prompts that contain variables. The list also provides a dedicated empty state and a 'back to prompts' fallback when no groups are available. Also in this area: Improved subagent guidance display and fold rail visualization; RTL support and keyboard shortcuts for tool approval cards.
client/src/components/Prompts/lists · high confidence
New authentication route layouts for login, registration, and dashboard access
The application now uses dedicated layout components to manage the authentication flow and post-login navigation. The new Startup layout handles the initial configuration fetch, sets the document title, and manages redirects for already-authenticated users while preserving mandatory two-factor authentication setup screens. The Login layout ensures query capabilities are enabled upon entry, and the Dashboard layout acts as a gate, rendering content only for authenticated users.
client/src/routes/Layouts · high confidence
New bookmark management UI components
The Bookmarks area now includes a complete set of new components for managing conversation tags: BookmarkEditDialog and BookmarkForm handle creating and editing bookmarks with validation and toast feedback, BookmarkItem and BookmarkItems render the tag list with selection states and loading indicators, and DeleteBookmarkButton and EditBookmarkButton provide action buttons that trigger the respective dialogs. These components replace the previous inline or less-structured bookmark interactions with a consistent, accessible dialog-based workflow. Also in this area: App-Wide UI Scale Setting; Agent-allowed machine selection and virtualized file table; Agent Builder supports conversation starters and marketplace UI refinements.
client/src/components/Bookmarks · high confidence
New message rendering hooks and clipboard logic
The \client/src/hooks/Messages\ directory now contains a comprehensive set of new hooks that centralize message rendering logic, attachment handling, and clipboard operations. \useCopyToClipboard\ and \useCopyMessageToClipboard\ replace previous implementations to support rich text copying, citation processing, and content-type filtering. \useAttachments\ merges database-loaded attachments with live streaming data to prevent duplicate or missing files. \useMessageActions\ and \useMessageHelpers\ consolidate user interactions like editing, regenerating, and feedback submission. Additional hooks like \useMessageScrolling\, \useSmoothStreaming\, and \useProgressiveRowMount\ manage scroll behavior and rendering performance, while \useLatestMessage\ and \useBuildMessageTree\ handle branch navigation and message tree construction. Also in this area: Fixes for authentication flow, chat navigation, and subagent content recovery; App-Wide UI Scale Setting; Artifacts pane state survives host moves and conversation switches.
client/src/hooks/Messages · high confidence
New modular Speech-to-Text and Text-to-Speech service architecture
The audio processing logic has been reorganized into a dedicated \api/server/services/Files/Audio\ directory, introducing distinct service classes for Speech-to-Text (\STTService\) and Text-to-Speech (\TTSService\). This change consolidates provider handling for OpenAI, Azure OpenAI, ElevenLabs, and LocalAI, while adding robust SSRF protection for outbound requests and improved MIME type normalization for audio uploads. Additionally, a new \getCustomConfigSpeech\ utility normalizes legacy engine settings (e.g., mapping 'openai' or 'azureOpenAI' to 'external') to ensure consistent configuration reporting, and \streamAudio\ now features refined text chunking for streaming responses.
api/server/services/Files/Audio · high confidence
New modular image processing service with SSRF-safe avatar handling
The image processing logic in the API server has been reorganized into a dedicated \api/server/services/Files/images\ module, introducing separate files for avatar handling, conversion, encoding, and resizing. A key addition is the \avatar.js\ service, which implements strict SSRF protection for user profile pictures by validating protocols, blocking redirects, and capping response sizes to prevent memory exhaustion. The new \resize.js\ module standardizes image scaling with specific resolution limits for different endpoints (e.g., Anthropic vs. others) and handles EXIF rotation. The \convert.js\ module now manages image format conversion and storage based on configuration, while \encode.js\ acts as a wrapper for the core image encoding logic. This refactoring centralizes image manipulation, improves security for external URL fetching, and provides a cleaner interface for image-related operations across the application.
api/server/services/Files/images · high confidence
New plugin and tool management hooks for web search and UI state
The client now includes a new set of hooks in the Plugins directory to manage tool authentication and UI interactions. The \useAuthSearchTool\ hook centralizes the installation and removal of the web search tool, handling API keys and provider selections for services like Serper, SearXNG, Firecrawl, Tavily, and Jina. The \useSearchApiKeyForm\ hook provides a React Hook Form wrapper for this authentication flow. Additionally, \useToolToggle\ introduces support for admin-configured default pinned tools via the \defaultPinnedTools\ interface config, persisting tool states to both ephemeral agent state and local storage. The \usePluginDialogHelpers\ hook manages pagination and search logic for the plugin selection dialog, while \useToolCallsMap\ fetches and maps tool call results for a specific conversation.
client/src/hooks/Plugins · high confidence
New role-based access hooks for memory capabilities
Added \useHasAccess\ and \useHasMemoryAccess\ hooks in \client/src/hooks/Roles\ to enforce role-based access control for memory features. The \useHasMemoryAccess\ hook specifically requires the combined USE, CREATE, and UPDATE permissions for the MEMORIES permission type, ensuring that only users with full write access can interact with inline memory tools, aligning with backend validation.
client/src/hooks/Roles · high confidence
New tool manifest and agents-only tool validation
The system now uses a centralized manifest to define available tools, including new entries for Traversaal Search, Google Search, OpenAI Image Tools, Wolfram, DALL-E-3, Tavily Search, Stable Diffusion, Azure AI Search, OpenWeather, Flux, and Gemini Image Tools. A key behavioral change is the introduction of an \agentsOnly\ flag for the 'Ask User' tool, which restricts its use to the agents runtime. The \manifest\ module now includes an \isAgentsOnlyTool\ function that validates whether a tool is agents-only, ensuring that such tools are rejected in the legacy assistants runtime to prevent errors from missing pause/resume capabilities.
api/app/clients/tools · high confidence
On-demand MCP cache freshness with configurable polling
MCP server and tool data are no longer polled continuously; instead, background refreshes start only when the relevant UI surfaces are visible and stop when they are closed, keeping the client cache fresh without unnecessary network traffic. The system respects the configured refresh intervals (status and tools) and allows disabling polling by setting an interval to zero, while still allowing manual refreshes and reconciling server-side changes at bounded intervals.
client/src/data-provider/MCP · high confidence
Per-user skill activation defaults and ownership-aware permissions
The Skills hooks now manage per-user active/inactive states with ownership-aware defaults: deployment skills and skills you own are active by default, while shared skills follow the \defaultActiveOnShare\ interface config. Toggles are serialized via a per-user write queue to prevent race conditions, and the new \useSkillPermissions\ hook enforces a consistent permission model where owners and admins have full control, while other users are limited by ACL bits (view, edit, delete, share).
client/src/hooks/Skills · high confidence
Redesigned Bookmarks UI with drag-and-drop and filtering
The Bookmarks section in the side panel has been completely rebuilt to support reordering, filtering, and improved accessibility. Users can now drag and drop bookmark cards to change their display order, with changes saved automatically via the backend. A new filter input allows quick searching through bookmark tags, and empty states provide clear guidance when no bookmarks exist or when filters yield no results. The UI also includes dedicated edit and delete actions for each bookmark, with confirmation dialogs for deletions to prevent accidental data loss.
client/src/components/SidePanel/Bookmarks · high confidence
Redesigned Chat Interface with Project Scoping and Accessibility Improvements
The chat view has been rebuilt to support private project scoping, allowing users to create and manage conversations within specific projects via a new project selector chip on the landing page. The interface now features a redesigned header with a unified layout for model selection, bookmarks, and multi-conversation controls, alongside a new footer that displays operator-configured content like privacy policies and terms of service. Accessibility has been significantly improved through the adoption of Ariakit for dropdowns and tooltips, ensuring better screen reader support and keyboard navigation. Additionally, the chat now supports temporary mode for ephemeral conversations and includes a new 'Add Multi-Conversation' button for parallel agent runs.
client/src/components/Chat · high confidence
Redesigned MCP Server Configuration Dialog with Enhanced Security and Validation
The MCP Server creation and editing interface has been restructured into distinct sections (Basic Info, Connection, Transport, Auth, Trust) to improve usability and clarity. Key updates include: enforcing strict validation for server titles (supporting hyphens) and URLs, and adding a mandatory Trust checkbox to explicitly acknowledge security risks. Authentication options have been expanded to support On-Behalf-Of (OBO) token exchange, with access controlled by user permissions. Sensitive fields like API keys are now handled via a secure SecretInput component, and OAuth configuration has been hardened to allow optional client secrets and automatically discover exchange methods. Additionally, the UI now features theme-adaptive SVG icons for MCP servers and groups, with improved accessibility and standardized empty states.
client/src/components/SidePanel/MCPBuilder/MCPServerDialog/sections · high confidence
Redesigned MCP Server Configuration and Connection UI
The MCP configuration interface has been rebuilt to support a unified status system and improved connection flows. Users can now configure custom user variables with dedicated credential masking and browser autofill prevention, while request-scoped servers can be configured and initialized on-demand. The new UI includes a dedicated OAuth dialog with QR code support, clearer status indicators for connection states, and accessibility improvements such as screen-reader-friendly labels and hidden decorative icons.
client/src/components/MCP · high confidence
Redesigned Model Selector with Search and Agent Filtering
The model selector in the chat menu has been rebuilt to support searching across models, endpoints, and agents, and to filter agent options based on user permissions. The new UI includes a search bar, keyboard shortcuts, and a dialog for managing API keys, replacing the previous static list with a dynamic, accessible menu.
client/src/components/Chat/Menus/Endpoints · high confidence
Redesigned Settings dialog with registry-driven tabs, search, and mobile drill-in
The Settings interface has been rebuilt around a registry-driven architecture, replacing the previous layout with a new dialog that features a sidebar for tab navigation, a content area for settings sections, and a global search bar. This change introduces a mobile-first experience where users can drill into tabs on small screens, and it centralizes settings visibility logic (such as two-factor authentication, Langfuse connections, and stateful workspace defaults) into a single registry that respects user context and permissions. The new UI also includes dedicated controls for billing/auto-refill, code environment management, and memory preferences, all integrated into a unified, searchable settings surface. Also in this area: Improved subagent guidance display and fold rail visualization.
client/src/components/Nav/Settings, client/src/components/Nav/Settings/\\tests\\_ · high confidence_
Redesigned mobile sidebar with dedicated header and footer controls
The mobile sidebar now uses a structured layout with a dedicated header strip and a bottom bar. The header contains the close button, a panel switcher dropdown (replacing the previous icon rail), a new chat button, and account settings, ensuring controls remain consistent across panels. A new bottom bar provides a thumb-reachable search input that appears only on the default panel. Additionally, hidden shortcut target buttons are added to maintain keyboard navigation compatibility on mobile devices where the desktop rail is absent.
client/src/components/UnifiedSidebar/mobile · high confidence
Redesigned prompt display with version history and variable support
The prompt display interface has been rebuilt to include a detailed header showing category, author, and usage stats, alongside a new version history timeline that lets users switch between prompt iterations and identify the production version. The main text area now supports rich Markdown rendering with syntax highlighting and KaTeX math, and includes a copy-to-clipboard button. Additionally, a new variables panel automatically detects and displays special variables, dropdown options, and simple text variables, while the action bar now handles variable prompts via a dialog before submission. Also in this area: Improved subagent guidance display and fold rail visualization; RTL support and keyboard shortcuts for tool approval cards; App-Wide UI Scale Setting.
client/src/components/Prompts/display · high confidence
Redesigned tool output rendering with contextual icons and terminal support
The Tool Output component has been refactored to provide a richer, more structured display for tool calls. It now features contextual icons that distinguish between tool types (such as bash, code execution, web search, and MCP tools) and supports stacked icons for grouped actions. The renderer intelligently formats output, highlighting JSON as code blocks and preserving whitespace in terminal outputs. Terminal-style outputs now open at the bottom to show recent activity and automatically follow new lines until the user scrolls up. Additionally, error messages are cleaned of internal prefixes for clarity, and a hover-revealed copy button allows users to easily copy raw output.
client/src/components/Chat/Messages/Content/ToolOutput · high confidence
Refactored Assistants API controllers and added comprehensive test coverage
The Assistants chat and management endpoints have been refactored to improve code structure and reliability. The chat logic is now split into distinct \chatV1.js\ and \chatV2.js\ controllers, with \chatV2\ introducing a centralized \createErrorHandler\ utility in \errors.js\ to standardize error handling and run cancellation. Assistant creation and modification logic in \v1.js\ and \v2.js\ now explicitly filters out agents-only tools and enforces role-based permissions before sending requests to the provider. Additionally, a new \helpers.js\ module centralizes client initialization and version detection, while extensive Jest test suites (\chat.contentFilter.spec.js\, \logging.spec.js\) have been added to verify content filtering, balance checks, and secure logging practices.
api/server/controllers/assistants · high confidence
Refactored Assistants endpoint into modular service files
The Assistants endpoint logic has been reorganized into distinct modules (build, initialize, title) to improve maintainability. This change introduces specific behaviors: title generation is now skipped for temporary chats, and a content policy is enforced that replaces blocked or PII-containing titles with a default 'New Chat' label. Additionally, the initialization process now supports user-provided API keys and base URLs for the Assistants API, and the build process correctly attaches assistant metadata and artifact prompts to the endpoint options.
api/server/services/Endpoints/assistants · high confidence
Refactored SetKeyDialog with dedicated configuration components
The SetKeyDialog component has been restructured to use dedicated configuration sub-components (OpenAIConfig, GoogleConfig, BedrockConfig, CustomEndpoint, OtherConfig) for handling API key inputs specific to each endpoint. This change introduces a more modular approach to key management, supporting distinct input fields for Azure OpenAI (instance name, deployment name, API version), AWS Bedrock (access key ID, secret access key, session token, bearer token), and Google (service key file upload and API key). The dialog now utilizes a shared InputWithLabel component that leverages the @librechat/client design system for consistent styling and includes a SecretInput for sensitive fields.
client/src/components/Input/SetKeyDialog · high confidence
Refactored authentication controllers with dedicated 2FA, logout, and OAuth handling
The authentication logic in the API server has been reorganized into dedicated controllers to improve security and maintainability. The new LoginController now explicitly handles 2FA flows by issuing temporary tokens when two-factor authentication is enabled. A comprehensive LogoutController manages session termination, including revoking OpenID refresh token chains, clearing CloudFront cookies, and implementing a cascading OIDC RP-Initiated Logout strategy that prioritizes id\_token\_hint, falls back to logout\_hint for oversized URLs, and finally uses client\_id. The OAuth handler now supports cross-origin admin panel redirects via exchange codes and reuses OpenID tokens when configured. Additionally, a new TwoFactorAuthController securely verifies TOTP codes and backup codes using temporary tokens, ensuring sensitive user data like passwords and secrets are stripped before response.
api/server/controllers/auth · high confidence
Refactored browser TTS to use MediaSource for reliable audio streaming
The client's Text-to-Speech implementation has been restructured to use the MediaSource API for streaming audio chunks, replacing the previous approach. A new MediaSourceAppender class manages the lifecycle of the media source, ensuring that audio data is correctly appended to the source buffer and that the stream is properly ended even for short or empty responses. This change improves compatibility with browsers like Safari and Firefox, which previously encountered errors with the old method. The refactoring also introduces dedicated hooks for managing audio state, including useTTSBrowser and useTTSExternal for different TTS engines, useAutoplayTrigger for consistent autoplay logic, and usePauseGlobalAudio for global audio control. A new useCustomAudioRef hook provides enhanced tracking of audio playback events. Also in this area: 12 commits (8 fixes) fixing client.
client/src/hooks/Audio · medium confidence · unverified
Refactored server configuration service into modular TypeScript-ready components
The configuration logic in \api/server/services/Config\ has been reorganized into a set of specialized modules (e.g., \EndpointService\, \app\, \getCachedTools\, \loadAsyncEndpoints\) that delegate core logic to the \@librechat/api\ and \@librechat/data-schemas\ packages. This change introduces a more structured approach to loading endpoint credentials, managing tool caches, and handling custom configurations, while adding specific support for features like configurable RUM (Real User Monitoring) and LDAP settings. Users will experience improved reliability in configuration loading and caching, with better separation of concerns for environment variables and database-backed settings.
api/server/services/Config · high confidence
Refactored startup config caching to be auth-aware and shared-link scoped
The client-side data provider now uses distinct query keys for startup configuration based on authentication status and shared link context. This ensures that unauthenticated and authenticated configurations are cached independently, preventing stale unauthenticated data from persisting after a user logs in. Additionally, shared startup configs are now keyed by share ID, allowing proper isolation for shared links. The refactoring also includes normalization of model specs at the query boundary to ensure consistent data consumption.
client/src/data-provider/Endpoints · high confidence
Restrict OBO server editing and improve dialog UX
Users without the CONFIGURE\_OBO permission can no longer modify connection, transport, authentication, or trust settings for On-Behalf-Of (OBO) MCP servers; these fields are now read-only in edit mode to prevent token redirection. The dialog also returns focus to the trigger button upon closing and includes a copy button for OAuth redirect URIs that provides visual feedback without overwriting the user's clipboard.
client/src/components/SidePanel/MCPBuilder/MCPServerDialog · high confidence
Restructured MCP State Management and Connection Handling
The MCP hooks have been reorganized into a modular structure to improve connection stability, OAuth handling, and UI state synchronization. The new \useMCPServerManager\ centralizes server lifecycle management, including permission checks, OAuth polling with backoff, and reinitialization flows, while \useMCPSelect\ now handles per-conversation selection isolation and pruning of hidden servers. Connection status is tracked via \useMCPConnectionStatus\ and refreshed using configurable intervals in \useMCPRefresh\. Error handling is standardized through \errors.ts\ for reinitialization failures, and \useVisibleTools\ now correctly resolves server name aliases to prevent orphaned tool selections. These changes ensure that MCP server selections persist correctly across tabs, OAuth flows are handled with proper timeout and retry logic, and the UI accurately reflects server availability and authorization states.
client/src/hooks/MCP · high confidence
Role-based permission gating for File Search and Code Execution tools
The tool loading logic in the \api/app/clients/tools/util\ directory now enforces role-based access control for the \file\_search\ and \execute\_code\ tools. Previously, these tools were loaded regardless of user permissions; the updated \handleTools.js\ implementation checks the user's role against \FILE\_SEARCH.USE\ and \RUN\_CODE.USE\ permissions before instantiating the tools. This ensures that users without the necessary role privileges are prevented from accessing these capabilities, with the system failing closed if role lookups fail. Comprehensive tests in \handleTools.rolePermissions.test.js\ verify that tools are correctly withheld when permissions are denied.
api/app/clients/tools/util · high confidence
Server startup, shutdown, and security hardening
The server entry points now enforce stricter startup readiness by rejecting chat starts until the application is fully initialized, and they implement configurable HTTP timeouts for each worker. Graceful shutdown has been enhanced to ensure background tasks and generation jobs drain properly before the process exits. Security is improved with a nonce-based Content Security Policy for the SPA shell, authenticated access to the Prometheus metrics endpoint, and extended session lifetimes for OpenID Connect when token reuse is enabled.
api/server · high confidence
Structured error handling with actionable recovery for failed turns
The chat interface now replaces generic failure messages with specific, localized error components that provide clear guidance and recovery options. Agent failures now display actionable steps, including links to the agent builder for users with appropriate permissions. Balance errors now show detailed token usage and remaining limits. Context window errors provide specific next steps, such as suggesting context compaction. Rate-limit errors now feature a live countdown timer indicating when sending is allowed again. Provider and model errors display provider-specific details and refusal reasons. User key errors now offer a direct dialog to update missing or expired API keys. Additionally, attachment-related failures now offer recovery options, allowing users to retry without files or branch the conversation to continue without the problematic attachments.
client/src/components/Messages/Content/Error · high confidence
Tool discovery now excludes test files and adds migration checks
The server's tool loading process now explicitly skips test files (e.g., \.spec.js, \.test.js) during tool discovery to prevent them from being executed as tools, and includes a new migration check at startup to verify and log warnings for agent and prompt permissions migrations.
api/server/services/start · high confidence
Unified sharing dialog with stable identity handling and role-based access control
The Sharing area now uses a new GenericGrantAccessDialog that consolidates people-picking, public sharing, and role assignment into a single interface. It introduces a stable identity key (principalKey) to prevent duplicate rows and silent permission loss when the same user appears with different IDs across sources, and it deduplicates new shares before applying changes. Users can now select granular access roles via the new AccessRolesPicker, toggle public sharing with PublicSharingToggle, and manage admin-level people-picker permissions via PeoplePickerAdminSettings. PrincipalAvatar provides consistent visual indicators for users, groups, and roles. These components collectively replace fragmented sharing flows with a unified, type-safe, and deduplicated permission management experience.
client/src/components/Sharing · high confidence
Unified tool-call and artifact rendering in chat messages
The chat message area now uses a consistent row-based layout for tool calls and artifacts. New components in this location—such as ArtifactRow, AgentUpdate, AuthorHeader, BackgroundTaskCall, BashCall, ExecuteCode, FileAuthoringCall, and CollapsibleText—standardize how code execution, file authoring, background tasks, and agent handoffs appear inline. Artifacts and tool outputs are displayed as compact rows with glyphs, labels, and download actions, while long user messages can be optionally collapsed with a "Show more" toggle. This change improves visual consistency and readability for complex agent interactions. Also in this area: 9 commits (4 fixes) modifying client/src; Improved subagent guidance display and fold rail visualization; Fixes for authentication flow, chat navigation, and subagent content recovery; App-Wide UI Scale Setting; Composer UI simplification and enhanced queue controls; and 2 more.
client/src/components/Chat/Messages/Content/Parts · medium confidence · unverified
User-specific configuration loading with fallback
The server middleware now loads application configuration based on the current user's context, allowing for per-principal settings. If the user-specific configuration retrieval fails, the system automatically falls back to loading configuration by tenant ID, ensuring service continuity even when user-specific data is unavailable.
api/server/middleware/config · high confidence
Fixes
1 commit (1 fix) fixing client/src/lib
A fix in client/src/lib — 1 commit (1 fix), 1 file: “🛖 fix: Isolate Sandpack Console Globals From HTML Artifacts (\#18093)” (refs \#18093).
client/src/lib · medium confidence · unverified
12 commits (8 fixes) fixing client
A fix in client — 12 commits (8 fixs), 79 files: “🍡 perf: Batch Sidebar Unread Cache Scans (\#18004)”; “🌍 fix: Use Localized Button Text for Accessible Names (\#17988)”; “🪶 perf: Load MCP UI and Export Libraries on Demand (\#17975)”; and 9 more (refs \#18004, \#17988, \#17975, \#17976, \#17962, …). Also in this area: Added tests for QueryDevtoolsGate component.
client/src/components/\\tests\\_ · medium confidence · unverified_
Amazon DocumentDB compatibility audit and fixes
The data-schemas package now includes a comprehensive live-compatibility audit for Amazon DocumentDB, addressing critical incompatibilities that previously blocked logins and caused silent data drift. The \acceptTerms\ method has been rewritten to replace unsupported aggregation-pipeline updates (using \$$NOW\) with standard \$set\ operators, ensuring reliable first-acceptance stamping. Similarly, \decrementTagCounts\ and \extendFilesTTL\ have been refactored to avoid pipeline-form updates, preventing silent tag-count drift and ensuring proper TTL handling on DocumentDB. The package also introduces a \misc/documentdb\ test suite with live probes for pipeline updates, partial indexes, and other engine-specific behaviors, along with documentation detailing supported features and deployment requirements like \retryWrites=false\.
packages/data-schemas · high confidence
Auto-recovery from stale Service Worker assets after deploys
A new \heal.js\ module is added to the service worker to automatically recover users stuck on outdated assets after a deployment. When a new service worker activates, it pings all open browser windows; if a window fails to respond (indicating it is serving stale, purged chunks), the worker automatically reloads that page to fetch the latest build.
client/sw · high confidence
Fixes for agent inference input validation, title config resolution, and MCP server access
This update resolves several issues in the API layer. Agent creation and updates now use a stricter validation function that rejects unsafe inference parameters (like modelKwargs or apiKey) and rejects corrupt numeric values entirely, rather than silently sanitizing them. Title generation for conversations now resolves settings (model, prompt, method) per field across the global and endpoint-specific configuration blocks, ensuring that disabling titles on one endpoint does not inadvertently affect others. Additionally, MCP server lookups and cleanup operations now correctly respect profile-based hiding rules by including hidden servers when necessary for security checks and token revocation, and pass the requesting user's role and identity to the registry for accurate access control. Also in this area: Retire cancelled MCP OAuth state.
api/server/services/MCP · high confidence
MongoDB connection pooling and MeiliSearch sync reliability improvements
The database layer now supports configurable MongoDB connection pool settings (max/min pool size, max connecting, idle time, wait queue timeout) via environment variables, allowing better control over connection resources. Additionally, MeiliSearch synchronization has been hardened: the system now enforces a sync threshold to avoid unnecessary full re-indexing, cleans up orphaned documents missing user fields, and ensures proper model loading order to prevent startup sync failures.
api/db · high confidence
Test coverage
1 commit adding/updating tests in client/src/components/SidePanel/Builder/\_\tests\\; 11 commits adding/updating tests in client/src/components/Chat/Input/Composer/\\tests\\; 110 commits adding/updating tests in client/src/components/Chat/Input/\\tests\\; 13 commits adding/updating tests in client/src/components/Chat/Messages/ui/\\tests\\; 2 commits adding/updating tests in client/src/components/Chat/Steering; 2 commits adding/updating tests in client/src/components/SidePanel/\\tests\\; 21 commits adding/updating tests in client/src/hooks/Conversations/\\tests\\; 34 commits adding/updating tests in client/test; 4 commits adding/updating tests in client/src/\\tests\\; 4 commits adding/updating tests in client/src/components/Chat/Input/Files/\\tests\\; 6 commits adding/updating tests in api/test/app/clients/tools/structured; 6 commits adding/updating tests in client/src/components/Chat/BackgroundTasks/\\tests\\; 6 commits adding/updating tests in client/src/components/Messages/\\tests\\; 97 commits adding/updating tests in client/src/components/Chat/Messages/Content/Parts/\\tests\\_; Added activity-label evaluation harness; Added comprehensive test coverage for Agents Marketplace components; Added comprehensive test coverage for agent controller logic; Added comprehensive test coverage for agent route behaviors; Added test coverage for ChatView, Header, Footer, and subagent thread components; Added test coverage for MCP server management and selection hooks; Added test coverage for SSE streaming hooks and utilities; Added test coverage for Sharing components and logic; Added test coverage for assistant service logging, MCP tool resolution, and tool capability gates; Added test coverage for client hooks; Added test coverage for client route components; Added test coverage for conversation options components; Added test coverage for the Agent Tool Item Dialog and its sections; Added test infrastructure and coverage for orphaned agent file migration; Added test mocks for authentication, logging, and OpenID integration; Added test suite for BaseClient; Added tests for Account settings components; Added tests for BookmarkForm editing behavior; Added tests for Chat Menu components; Added tests for Citation components and SourcesErrorBoundary; Added tests for Config service caching and endpoint logic; Added tests for Input hook logic; Added tests for MCP Server dialog sections; Added tests for Skill file editing and Markdown link resolution; Added tests for UnifiedSidebar component behavior; Added tests for agent code decision, capabilities, and tool permissions; Added tests for agent data mutations and queries; Added tests for app startup, state clearing, and speech settings initialization; Added tests for artifact hook logic and lifecycle management; Added tests for client Provider contexts and boot scripts; Added tests for client utility functions; Added tests for data-provider mutations and cache reconciliation; Added tests for email sending and static asset caching; Added tests for endpoint icon rendering logic; Added tests for file attachment and preview hooks; Added tests for file citation processing logic; Added tests for file search tool authorization and error handling; Added tests for image request validation middleware; Added tests for message rendering and attachment handling hooks; Added tests for model selector icon and filtering logic; Added tests for navigation components; Added tests for search tool authentication and tool toggle persistence; Added tests for server middleware authentication, message validation, and model validation; Added tests for the Conversations sidebar components; Added tests for the Model Selector components; Added tests for the Tool Output Renderer component; Added tests for the checkBan middleware; Added unit tests for Agent Version History components; Added unit tests for Agent side-panel components; Added unit tests for Chat Messages components; Added unit tests for Skill creation and upload dialogs; Added unit tests for generation action buttons; Added unit tests for message content components; Added unit tests for the Agent Tools Marketplace UI components; Added unit tests for the Agent Tools catalog and item logic; Added unit tests for the Auth component suite; Added unit tests for the SkillsView component; Client-side Skills data provider and test coverage; Expanded test coverage for Chat hooks and facade; Expanded test coverage for server controllers; Initial API test configuration and type definitions; New Code Environment File Service and Tests; New E2E Performance Benchmarks for Mobile, Navigation, Reasoning, and Tree Rendering; New localization guide and comprehensive i18n test suite; New store tests and Jotai-based storage utilities; New test coverage for Agent Client and Callbacks; Updated conversation route test mocks to support new subagent, archival, and checkpoint features.
Dependencies
Initial release of backend and frontend dependency manifests
The project introduces the initial dependency manifests for the backend (\@librechat/backend\) and frontend (\@librechat/frontend\) packages. The backend defines its runtime requirements, including the \@librechat/agents\ SDK (v3.9.7), \express\ (v5.2.1), \mongoose\ (v8.24.1), and various cloud provider SDKs for AWS, Azure, and Google. The frontend specifies its UI and build dependencies, such as \react\ (v18.2.0), \vite\ (via \@vitejs/plugin-react\ v6.0.2), \tailwindcss\, and \@ariakit/react\ (v0.4.29).
(dependencies) · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 48 → 46 (-1.6)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 58 → 58 (+0.1)
- Architecture 54 → 56 (+2.5)
- Maturity 74 → 73 (-0.3)
- Readiness 36 → 33 (-3.2)
- Security 65 → 58 (-6.9)
- Domain Modelling 100 → 100 (+0.0)
- Accessibility 60 → 55 (-4.5)
- Performance 60 → 60 (+0.0)
Resolved (1080)
- (anonymous) (cognitive 36) (api/server/routes/messages.js)
- (anonymous) (cyclomatic 27) (api/server/routes/messages.js)
- ApiKeyDialog.ApiKeyDialog (cognitive 17) (client/src/components/SidePanel/Agents/Search/ApiKeyDialog.tsx)
- ApiKeyDialog.ApiKeyDialog (cyclomatic 24) (client/src/components/SidePanel/Agents/Search/ApiKeyDialog.tsx)
- AskUserQuestionPopover.AskUserQuestionPopoverPanel (cyclomatic 18) (client/src/components/Chat/Input/AskUserQuestionPopover.tsx)
- AssistantService.createInProgressHandler::in_progress (cyclomatic 23) (api/server/services/AssistantService.js)
- Breakdown.Breakdown (cognitive 80) (client/src/components/Chat/Input/TokenUsage/Breakdown.tsx)
- Breakdown.Breakdown (cyclomatic 90) (client/src/components/Chat/Input/TokenUsage/Breakdown.tsx)
- Change coupling: Part.tsx ↔ useToolCallState.ts (client/src/components/Chat/Messages/Content/Part.tsx)
- Change coupling: client.js ↔ addedConvo.js (api/server/controllers/agents/client.js)
- Change coupling: tailwind.preset.cjs ↔ registry.ts (packages/client/tailwind.preset.cjs)
- Change coupling: tailwind.preset.cjs ↔ theme.ts (packages/client/tailwind.preset.cjs)
- Change coupling: useToolCallState.ts ↔ ToolCall.tsx (client/src/components/Chat/Messages/Content/Parts/useToolCallState.ts)
- Change-coupling hub: Message.tsx → MessageParts.tsx, SearchMessage.tsx, MessageRender.tsx, ContentRender.tsx (client/src/components/Share/Message.tsx)
- Change-coupling hub: RedisJobStore.ts → GenerationJobManager.ts, InMemoryJobStore.ts, stream.ts (packages/api/src/stream/implementations/RedisJobStore.ts)
- ChatView.ChatView (cognitive 39) (client/src/components/Chat/ChatView.tsx)
- ChatView.ChatView (cyclomatic 41) (client/src/components/Chat/ChatView.tsx)
- ClassTooLong: Breakdown (client/src/components/Chat/Input/TokenUsage/Breakdown.tsx)
- ClassTooLong: MessageNav (client/src/components/Chat/Messages/MessageNav.tsx)
- ClassTooLong: useCodeWorkspace (client/src/hooks/Agents/useCodeWorkspace.ts)
- …and 1060 more
New (1437)
- (anonymous) (cognitive 34) (api/server/routes/messages.js)
- (anonymous) (cyclomatic 25) (api/server/routes/messages.js)
- AgentExecutionEnrollment.pauseForReview (cyclomatic 18) (packages/api/src/agents/remote/lifecycle.ts)
- AgentExecutionEnrollment.settlePause (cyclomatic 20) (packages/api/src/agents/remote/lifecycle.ts)
- ApiKeyDialog.ApiKeyDialogContent (cognitive 17) (client/src/components/SidePanel/Agents/Search/ApiKeyDialog.tsx)
- ApiKeyDialog.ApiKeyDialogContent (cyclomatic 24) (client/src/components/SidePanel/Agents/Search/ApiKeyDialog.tsx)
- ApprovalContext.useResumeSubmit.submitAskAnswer (cognitive 22) (client/src/components/Chat/Messages/Content/ApprovalContext.tsx)
- ApprovalContext.useResumeSubmit.submitAskAnswer (cyclomatic 18) (client/src/components/Chat/Messages/Content/ApprovalContext.tsx)
- Apps.Apps (cognitive 68) (client/src/components/Channels/Apps.tsx)
- Apps.Apps (cyclomatic 107) (client/src/components/Channels/Apps.tsx)
- AssistantService.createInProgressHandler.in_progress (cognitive 48) (api/server/services/AssistantService.js)
- AssistantService.createInProgressHandler.in_progress (cyclomatic 23) (api/server/services/AssistantService.js)
- Banned license: @img/sharp-libvips-darwin-arm64 (bun.lock)
- Banned license: @img/sharp-libvips-darwin-x64 (bun.lock)
- Banned license: @img/sharp-libvips-linux-arm (bun.lock)
- Banned license: @img/sharp-libvips-linux-arm64 (bun.lock)
- Banned license: @img/sharp-libvips-linux-ppc64 (bun.lock)
- Banned license: @img/sharp-libvips-linux-riscv64 (bun.lock)
- Banned license: @img/sharp-libvips-linux-s390x (bun.lock)
- Banned license: @img/sharp-libvips-linux-x64 (bun.lock)
- …and 1417 more
Changes since last survey
- 300 commits — 166 feature/other, 134 fixes
By area
- client/src — 86 commits
- packages/api — 71 commits
- packages/chat — 41 commits
- e2e/specs — 18 commits
- packages/data-schemas — 17 commits
- api/server — 13 commits
- (root) — 9 commits
- packages/channel-gateway — 6 commits
- packages/client — 6 commits
- .github/workflows — 5 commits
- e2e/setup — 4 commits
- scripts/quality — 4 commits
- .github/scripts — 3 commits
- packages/data-provider — 3 commits
- api/app — 2 commits
- client/vite.config.ts — 2 commits
- e2e/fixtures — 2 commits
- helm/librechat — 2 commits
- .github/actions — 1 commit
- .husky/pre-push — 1 commit
Notable commits
- fix: fix: Clear Slack Progress After Successful Delivery (#18040)
- fix: fix: Guard Mongo Cleanup In Api Services Tests (#17990)
- fix: fix: Guard Mongo Cleanup In Controller And Migration Tests (#17989)
- fix: fix: Guard transactional channel writes (#17770)
- fix: fix: Keep Plugin Pagination Keyboard Navigation Within Bounds (#17987)
- fix: fix: Keep Untagged Chat Code Fences Plain (#17986)
- fix: fix: Preserve Unknown-Provider MCP Display Images (#18000)
- fix: fix: Serialize MCP App Theme Variables as CSS Colors (#17999)
- fix: fix: patch glob traversal and redirect dependencies (#17964)
- fix: ⌨️ fix: Preserve User Focus During Sidebar Opening (#18001)
- fix: ⏭️ fix: Let Queued User Turns Go Before Completion Wake-ups at Run End (#18027)
- fix: ⏱️ fix: Bound Generation Status Reads So a Silent Request Cannot Strand the Pane (#17927)
- fix: ⏱️ fix: Preserve Running Tool Timers Across Disclosure Remounts (#17997)
- fix: ⏳ fix: Bound Blob Storage Image Reads by the Image Fetch Budget (#17932)
- fix: ⏳ fix: Stop the Settings Timer From Expiring a URL Auto-Submit That Waits for the Composer (#18072)
- fix: ⚓ fix: Anchor Schedule Time Popovers to Their Field (#17947)
- fix: ⚖️ fix: Apply User and Group Balance Overrides on Sign-In (#17884)
- fix: ⚙️ fix: Guard Mongo Cleanup In Package Service Tests (#17992)
- fix: ⚠️ fix: Keep Warnings That Follow a File Authoring Success Summary (#17953)
- fix: ⚡ fix: Parallelize Setup Cancel Lookups and Keep Attachment Drafts on Reload (#17963)
- …and 280 more
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
danny-avila/LibreChat was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit fad2c51da41bb46c9cdd44a720cea4df0d47876b — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-e1a3b69fc8ee.