Changelog

Here's what's new in this update:

• GPT Image 2 model support: The GPT Image Editor plugin now supports the gpt-image-2 model, giving you access to OpenAI's latest image generation capabilities directly within the plugin.

• Resizable sidebar: You can now drag to resize the sidebar to your preferred width. The size is saved and persists across app reloads.

• Custom body parameters in model settings: You can now add custom request body parameters directly in a model's settings. This enables use cases such as setting service_tier: "priority" to help reduce 429 rate-limit errors on models like Gemini 3.1 Pro.

Claude Opus 4.7 is now available on TypingMind!

• Better at complex coding work

• More reliable on long tasks

• Check its own work before answering

• Produce more polished professional outputs like UIs, slides, and documents.

Try now!

Other updates:

- Added support for xhigh thinking effort for Claude Opus 4.7
- Treated xhigh as max thinking effort for other Claude models

New

• Users can now permanently delete files stored in cloud storage.

Fixes and Improvements

• Fix “Request exceeds the maximum size” errors when sending large PDF files to Claude models by lowering the PDF size limit to preserve request headroom.

• Added support for welcome/prefill messages for Gemini image models.

• You can now assign provider tools for AI Agents (TypingMind Team)

• Provider code execution now reuses the active Claude container for improved execution efficiency.

Here’s what’s new in this update:

• External URL Support for Gemini: Gemini now supports external URLs for file handling, with optimized uploads that use less bandwidth and improve response speed.

• Unify Reasoning Controls: The thinking level button is now synced with the Reasoning effort setting in Chat Settings for a more consistent reasoning control experience.

• Restore Deleted Items: You can now restore more recently deleted items, including agents, plugins, prompts, and folders.

Improvements & Bug Fixes

• Gemini large file handling: Fixed an issue where Gemini could fail when processing large files via external URLs because documents were incorrectly detected as having no pages.

• User’s last login for OAuth & SSO tracking: Fixed an issue where the user’s last login wasn’t being tracked for OAuth and SSO authentication.
  

Here's what's new in this update:

Prompt Library (Teams) — New UI: The Team Prompt Library has been redesigned with a refreshed interface and new capabilities:

• Duplicate & Share as JSON: Quickly duplicate any prompt or export it as JSON for easy sharing.

• Bulk Delete: Select and remove multiple prompts at once.

• Sorting Options: Sort prompts by title, date created, or date modified.

Deprecating Chat Widget (Teams): The Chat Widget feature is being deprecated. Existing embeds will remain available until June 01, 2026, with a new widget system coming soon. The per-agent "Embed the chat widget" snippet has been removed (direct URL and public API guidance remain available).

Improvements & Bug Fixes

• Shared Links (Teams self-hosted): Fixed an issue where Shared Links didn't appear in the Cloud Sync screen on the self-hosted version.

• OpenRouter streaming: Prevents the format field from being incorrectly repeated when using OpenRouter in streaming mode.

• Model/Plugin limits (Teams): Fixed an issue where model and plugin limits were being incorrectly overridden.

• OpenAI reasoning: Messages are now kept as stateless as possible to prevent caching errors.

• Chat Share button (Teams): Fixed the Share button displaying incorrectly in the UI.

Here's what's new in this update:

✨ New

GPT-5.4 Mini & GPT-5.4 Nano are now available in TypingMind.

🛠 Improvements & Bug Fixes

• Large chat performance: Optimized performance for large chats by removing unused OpenRouter annotations data that could be very large.

• Claude Opus 4.6 pricing: Fixed estimated cost so pricing now shows correctly for Claude Opus 4.6 and Claude Opus 4.6 1M models.

Here's what's new in this update:

✨ New

• A new Provider UI

  A new UI has been added for configuring providers and their API keys, with unified Enter API Key widgets across all providers.

• Read specific files in Knowledge Base (KB)
  You can now read specific files in your Knowledge Base directly.

🛠 Improvements & Bug Fixes

• OpenRouter API streaming: Improved handling of OpenRouter response API streaming.

• Fixed an issue where redundant newline characters caused invalid Claude prompt cache entries.

Here's what's new in this update:

✨ New

Claude automatic prompt caching: TypingMind now applies Claude's new automatic prompt caching, improving response efficiency for repeated or similar prompts.

Plugin Execution Timeout (Self-Hosted Teams): Admins can now set a custom timeout limit for plugin execution via an environment variable. The value should be specified in milliseconds.

🛠 Improvements & Bug Fixes

Agents/MCPs avatars: Fixed an issue where agents/MCPs avatars could not load.

Custom params in multi-model responses: Fixed an issue where custom params were not applied in some multi-model response generation cases.