Changelog

v3.9.0

• Add support for web search to <AiChat /> component.

• Add showSources, showRetrievals and showReasoning props to <AiChat /> component to determine how sources, retrievals and reasoning are displayed respectively.

• Disable AI chat composers when AI service is not available.

• Add query filter subscribed on the useThreads hook.

• Add useUrlMetadata hook to get metadata for a given URL.

• Expose disconnected status in useAiChatStatus to indicate when AI service is not available.

• Add query filter subscribed on the room.getThreads method.

• Update createAiCopilot and updateAiCopilot to include web search in provider options for OpenAI and Anthropic.

• Remove all schema validation related client methods that should no longer be used. Schema validation was sunsetted on May 1st, 2025.

Dashboard

• Greatly improved “Notifications” flow, making it much clearer how they're linked to webhooks.
  • New “Kinds” tab, allowing you to define batching per kind.
  • See the status of your webhooks from here.
  • Warnings when no webhooks are set up, and shortcuts to get started.
• Improved “Webhooks” page.
  • Set a rate limit for your webhooks when creating them.
  • More detailed error messages when creating webhooks.
  • Better UX on the URL input.
• Improved UX when creating projects
  • New polished project cards displaying more info such as region restrictions.
  • More clarity in project creation dialog boxes.
• Improved team/project selectors with UI polish and better accessibility.
• Improved MAU usage cards showing your team’s personalized limits.
• More clarity in project settings regarding environment and regions not being editable.
• Fixed problem downloading examples with create-liveblocks-app integration.

Documentation

• New sections on notification batching.
• Better clarity on Storage/Yjs limits.

Contributors

Contributors include:

8 authors

v3.8.1

• Add chatId prop to RegisterAiKnowledge to scope knowledge to a specific chat, similar to RegisterAiTool. This is the same as using the knowledge prop on AiChat.

• Fix issue where useAiChat() didn't re-render correctly when chat title gets updated.

• Fix issue where tenantId was not being passed to the request when using Liveblocks.createRoom().

• Add comments:write to the list of possible room permissions.

Examples

New example: AI app builder. New example: AI calendar.

Contributors

Contributors include:

6 authors

v3.8.0

• LiveMap and LiveObject deletions now report which item got deleted in the update notifications. LiveLists already did this.

• Support numerical operators gt, lt, gte, and lte in room.getThreads metadata query filters.

• Add new hook useAiChatStatus that offers a convenient way to get the current generation status for an AI chat, indicating whether the chat is idle, currently generating contents, and, if so, what type of content is currently generating.

• Fixes an issue where useUnreadInboxNotificationsCount wasn't returning the proper count if there were more than a page of unread notifications.

• Support numerical operators gt, lt, gte, and lte in useThreads metadata query filters.

• Add responseTimeout property to AiChat to allow customization of the default 30 seconds timeout.

• The title prop on AiTool now accepts ReactNode, not just strings.

• Fix a bug where AiChat would not always scroll in the same way when sending new messages.

• Add new method Liveblocks.prewarmRoom(roomId, options). This method can prewarm a room from your backend, preparing it for connectivity and making the eventual connection from the frontend faster.

Website

• Blog post: Why we built our AI agents on WebSockets instead of HTTP.

Contributors

Contributors include:

6 authors

Website

• Blog post: What's the best vector database for building AI products?.
• Blog post: What's new in Liveblocks: August 2025.

Contributors

Contributors include:

2 authors

v3.7.1

• Add query filters roomId and kind on the useUnreadInboxNotificationsCount hook.

v3.7.0

This release introduces group mentions (e.g. @engineering) across all packages and first-class support for tenants. Learn more about group mentions and tenants in the docs.

• Add new resolveGroupsInfo resolver to provide information about groups (e.g. name, avatar, etc) similar to resolveUsers.

• Support returning group mention suggestions in resolveMentionSuggestions.

• Support group mentions in stringifyCommentBody, it now accepts a resolveGroupsInfo option that passes the results to mentions as group.

• Add query filters roomId and kind on the getInboxNotifications method.

• Add useGroupInfo hook to use resolveGroupsInfo in React, same as useUser for resolveUsers.

• Add query filters roomId and kind on the useInboxNotifications hook.

• Support group mentions in default components (mentions suggestions dropdowns, Thread, Composer, InboxNotification, etc).

• Support group mentions in text editors and comments-related components.

• Support group mentions in text editors.

• Add methods to manage groups on Liveblocks (e.g. createGroup, getUserGroups).

• Add tenantId parameters to methods that need it when using tenants.

• Mark getThreadParticipants as deprecated, use thread subscriptions or getMentionsFromCommentBody instead.

• Support group mentions in stringifyCommentBody, it now accepts a resolveGroupsInfo option that passes the results to mentions as group.

• Support group mentions in email notifications helpers. These functions now accept a resolveGroupsInfo option that passes the results to mentions as group.

3.6.2

• Rename budgetToken to budgetTokens in AnthropicProviderOptions.

v3.6.1

• Fixes a bug where a specific combination of concurrent LiveList mutations could break eventual consistency (two clients disagreeing on the final document state).

• Only show retrieval and reasoning durations in AiChat when they are 3 seconds or longer.

• Make AiTool titles selectable.

Website

• AI assistant has been added to the documentation and dashboard pages. It can answer questions on anything related to Liveblocks, such as code, recommendations, bugs, billing, usage, and project information. It's powered by AiChat.

Contributors

Contributors include:

7 authors

v3.6.0

• Auto-abort this client's tool calls on page unload to prevent hanging chats.

• Reasoning in AiChat now displays how long it took.

• AiChat nows shows when a copilot is searching its knowledge defined on the dashboard, as a "Searching 'What is RAG?'…" indicator. It also displays how long it took.

• Add Duration primitive to display formatted durations, similar to the existing Timestamp primitive.

• Better type safety for copilot creation and update options.

• Add missing type export for AI Copilot and knowledge sources.

v3.5.4

• Throttle incoming AI delta updates to prevent excessive re-renders during fast streaming.

• Optimized partial JSON parser for improved tool invocation streaming performance.

• Fixes a bug where the a comment could not be selected if it was within a previously deleted comment.

Dashboard

• Add API reference modal to AI Copilot detail pages, with React, Node.js, and REST API snippets to get started quickly.

Contributors

Contributors include:

5 authors

v3.5.1

• Fixes a bug where deleting a thread/comment from Tiptap would also remove any comments contained within it.

v3.5.0

• Add the following methods for managing AI copilots and knowledge sources:
  • getAiCopilots
  • createAiCopilot
  • getAiCopilot
  • updateAiCopilot
  • deleteAiCopilot
  • createWebKnowledgeSource
  • createFileKnowledgeSource
  • deleteFileKnowledgeSource
  • deleteWebKnowledgeSource
  • getKnowledgeSources
  • getKnowledgeSource
  • getFileKnowledgeSourceMarkdown
  • getWebKnowledgeSourceLinks

v3.4.2

• Fix improved Markdown streaming in AiChat only being enabled in reasoning blocks, it’s now enabled for all Markdown.

v3.4.1

• Fix a bug where copilot id wasn't passed when setting tool call result if a tool call was defined with execute callback.

• Update useSendAiMessage to use the the last used copilot id in a chat when no copilot id is passed to the hook or the method returned by the hook.

Website

• New blog post: Mock up AI agents in your product with the Liveblocks Collaboration Kit for Figma.

Contributors

Contributors include:

5 authors

v3.4.0

Tool calls will now stream in while under construction. This means that tools will render sooner and more often re-render, while partialArgs are streaming in.

New behavior (v3.4 and higher):

• 1st render: { stage: "receiving", partialArgs: {} }
• 2nd render: { stage: "receiving", partialArgs: { cities: [] } }
• 3rd render: { stage: "receiving", partialArgs: { cities: [""] } }
• 4th render: { stage: "receiving", partialArgs: { cities: ["Pa"] } }
• 5th render: { stage: "receiving", partialArgs: { cities: ["Paris"] } }
• etc.
• Then { stage: "executing", args: { cities: "Paris" } } (same as before)
• And { stage: "executed", args, result } (same as before)

Before (v3.3 and lower):

• Stage "receiving" would never happen
• 1st render would be with { stage: "executing", args: { cities: ["Paris"] } }
• 2nd render would be with { stage: "executed", args, result }

• In RoomProvider, initialPresence and initialStorage now get re-evaluated whenever the room ID (the id prop) changes.

• Add a minimal appearance to AiTool via a new variant prop.

• Improve Markdown rendering during streaming in AiChat: incomplete content is now handled gracefully so things like bold, links, or tables all render instantly without seeing partial Markdown syntax first.

• Render all messages in AiChat as Markdown, including ones from the user.

• Fix Markdown rendering of HTML tags in AiChat. (e.g. "Use the <AiChat /> component" would render as "Use the `` component")

• Improve shimmer animation visible on elements like the "Thinking…"/"Reasoning…" placeholders in AiChat.

Infrastructure

• Improved LiveList conflict resolution that will keep the conflicting element closer to its intended destination.

Contributors

Contributors include:

2 authors

v3.3.4

• Fix race condition where AI tools were not always executing. This could happen when using useSendAiMessage first and then immediately opening the <AiChat /> afterwards.

• Scroll thread annotations into view when a thread in AnchoredThreads is selected, similarly to @liveblocks/react-lexical.

v3.3.1

• Fix Composer uploading attachments on drop when showAttachments is set to false.

All versions

• Fix attachment names showing URL-encoded characters. (e.g. a%20file.txt instead of a file.txt)

Infrastructure

• Fixed a bug that caused unreliable storage updates under high concurrency.
• Fixed an issue that could cause LLM responses to appear to "hang" if the token limit got exceeded during the response generation. If this now happens, the response will indicate a clear error to the user.

Dashboard

• New knowledge prompt option when configuring AI copilots, allowing you to customize when back-end knowledge is fetched.

Documentation

• More info on styling AI chat components.
• Disambiguate semantics for LiveList.delete().

Contributors

Contributors include:

5 authors

v3.3.0

• Add maxVisibleComments prop to Thread to control the maximum number of comments to show. When comments are hidden, a "Show more replies" button is shown to allow users to expand the thread.

• Add onComposerSubmit callback to AiChat triggered when a new message is sent. It can also be used to customize message submission by calling useSendAiMessage yourself.

• Overrides and CSS classes for AiChat's composer have been renamed:

  • Overrides: AI_CHAT_COMPOSER_SEND → AI_COMPOSER_PLACEHOLDER
  • CSS classes: .lb-ai-chat-composer-form → .lb-ai-composer-form

• Fix: knowledge passed as a prop to AiChat no longer leaks that knowledge to other instances of AiChat that are currently mounted on screen.

• Add query option to useAiChats to filter the current user’s AI chats by metadata. Supports exact matches for string values, "contains all" for string arrays, and filtering by absence using null (e.g. { metadata: { archived: null } }).

• useSendAiMessage now accepts passing the chat ID and/or options to the function rather than the hook. This can be useful in dynamic scenarios where the chat ID might not be known when calling the hook for example.

• useCreateAiChat now accepts a chat ID as a string instead of { id: "chat-id" }.

• Allow using custom composers in FloatingComposer via the components={{ Composer }} prop.

• Add ATTACH_THREAD_COMMAND command to manually create a thread attached to the current selection.

Dashboard

• Support SAML Single Sign-On for enterprise customers.
• Allow editing first and last name in personal settings.

Contributors

Contributors include:

6 authors