Changelog

We've just released several fixes and improvements to enhance your experience:

Fixed:

• Cloud sync files size calculation now displays the correct storage usage in the cloud sync panel

• Citation annotations no longer cause incorrect output rendering formats

Improved:

• Thinking mode now supports new reasoning detail formats for more custom model providers, such as OpenRouter, Moonshot AI, etc.

These updates should make your workflow smoother. Let us know if you encounter any issues!

We've added a powerful new way to manage your AI models with Model Presets!

What's new:

• Multi-model presets in the model menu - Save your favorite model configurations with all their settings and switch between them instantly

• Save, rename, and remove presets with inline editing

• Quick apply to switch between presets seamlessly

• Sync model presets across devices - Your presets follow you everywhere

Bug fix:

• Fixed an issue where custom model parameters in Agent settings were applied incorrectly when no default model was set. Agent parameters are now only applied when default model enforcement is enabled (matches UI behavior)

We've rolled out several updates and improvements to enhance your TypingMind Teams experience!

New Features

Access & Limits Tab for Org Plugins

We've added a new Access & Limits tab for organization plugins, giving admins better control over plugin usage.

• New Access & Limits tab in organization plugin settings

• Admins can now configure access controls and usage limits for plugins at the organization level

Improvements

Thinking Options UI Improvement

When admins disable the thinking process, the related thinking options are now automatically hidden from the UI of the end users.

Bug Fixes

Fixed SSO Login Limit Issue

We've resolved an issue where existing users were encountering reaching limit errors when logging in via SSO.

• Existing users can now log in via SSO without hitting false limit restrictions

• Improved user authentication flow for SSO

We've rolled out several improvements to enhance your experience:

New AI Model Available

• Added GPT-5.2-codex model as a new model option

Better Plugin Interface

• Interactive plugin groups now expand by default for easier access

Improved Tool Compatibility

• Fixed tool compatibility handling between Thinking Mode, Web Browser, and Code Sandbox (OpenAI) to prevent conflicts when Thinking Mode is enabled

Plugin Usage Limits

You can now set usage limits for plugins to better control how they're used in your workspace.

What's new:

• Set limits for individual plugins or Model Context Protocols (MCPs)

• Limits are currently shared across all functions within a plugin

Watch the demo:

Smart Default Model Selection

TypingMind now remembers your model preferences when you start new chats.

How it works:

When you select a model (or models) before starting a new chat, TypingMind will save that as your default for future chats — no need to keep selecting the same model every time.

What this means for you:

• Works with both single model selection and multiple models

• Your preference is remembered automatically

• Only applies when you haven't set a folder-level default model

This makes starting new chats faster and more convenient!

Floating Menu Hide Option

• Added a ... button to the floating toolbar. Use the dropdown to Hide menu easily.

Clipboard Paste File Rename

• You can now rename a text file attachment after pasting it from your clipboard into the chat input.

• Added an inline rename UI (edit the name, Enter to save, Escape to cancel) with a pen icon.

• Renaming updates the attachment name directly in chat.

Fix: New Lines Not Rendered in Tables

• Fixed an issue where new lines (<br>) were not shown properly inside tables.

Code Interpreter

• You can now run code securely in a sandbox using the new Code Interpreter plugin (supported providers: OpenAI, Anthropic, Google Gemini).

• We’ve updated the tool interface: you can now see code status, expand code, copy results, and check program output more easily.

• Attachment previews are better; file chips and downloads work for more file types.

Response Block Layout Fix

• Fixed an issue where buttons sometimes covered the message text.

Summarizer ProviderInfo Fix

• Fixed a bug causing the “No target API endpoint found” error for the context

  summarizer.

We've improved the Plugins tab experience and fixed several issues to make TypingMind more stable and reliable.

What's improved:

Plugins Tab Enhancements:

• Installed items + store sections are now scrollable in a split layout

• Enable/disable toggle moved to the header for quicker access

• MCP-related panels polished: improved connection status UI, tool control layout, and new/updated connection form UX

Bug Fixes:

• Fixed background mode issues including inability to abort requests, and improper closing.

• Fixed an issue where OpenAI response streams could be aborted unexpectedly

• Improved "plugin not found" error message when the selected model doesn't support plugins