LobeHub
LobeHub
Back to Home
Changelog

Claude Sonnet 4.5 and Built-in Python Plugin 馃悕

Run Python directly in chat with the new built-in plugin, navigate long conversations faster, and work with Claude Sonnet 4.5 and other new models.

Claude Sonnet 4.5 and Built-in Python Plugin 馃悕

From September through October, LobeHub added a built-in Python execution environment, integrated Claude Sonnet 4.5, and improved how you navigate and edit content in long conversations.

Run Python code directly in chat

The new built-in Python plugin lets you execute Python code without leaving the conversation. Run calculations, transform data, or test snippets and see results immediately alongside your discussion.

This keeps your workflow in one place鈥攏o need to switch to a separate notebook or terminal when you need to verify something quickly.

The new chat list minimap gives you a condensed view of long conversations, making it easier to jump to specific sections without endless scrolling.

Richer editing and content handling

The rich text editor now supports math formulas, task lists, and parallel sending. This makes it easier to draft structured messages with mixed content types.

Qwen image editing is also available鈥攅dit images through Qwen models directly in the chat interface.

Model and provider updates

Claude Sonnet 4.5 brings Anthropic's latest reasoning capabilities to LobeHub. The release also adds Vercel AI Gateway as a provider, alongside Seedream 4.0, CometAPI, and NewAPI. Gemini 2.5 video understanding capabilities are updated.

Improvements and fixes

  • Chat input is now resizable for comfortable drafting
  • Mobile title display is improved
  • Base64 image syntax is now supported
  • .doc file parsing is more reliable

Version details

Features

  • v1.133.0Add builtin Python plugin, add Claude Sonnet 4.5 model to AI chat models.
  • v1.132.0Support google video understanding.
  • v1.131.0Qwen provider add qwen-image-edit model support.
  • v1.130.0Add scroll support for pinned assistants using ScrollShadow.
  • v1.129.0Support Vercel AI Gateway provider.
  • v1.128.0ChatInput support resize.
  • v1.127.0Seedream 4.0.
  • v1.125.0Add Math and TaskList to Editor.
  • v1.124.0ChatInput support rich text and support parallel send.
  • v1.123.0Add NewAPI as a router provider for multi-model aggregation.
  • v1.122.0Refactor to speed up send message in server mode.
  • v1.121.0Add nano banana Chinese prompt notify.

What's improved

  • v1.133.5Optimized extendParams UI, update i18n.
  • v1.133.4Fix chat minimap overflow.
  • v1.133.3Refactor a ssrf-safe-fetch module.
  • v1.133.2Add minimap to chat list for quick navigation.
  • v1.133.1Update i18n.
  • v1.132.18Update i18n.
  • v1.132.14Update i18n.
  • v1.132.11Enhanced Nvidia NIM chat experience, OpenAI models in AiHubMix use Responses API.
  • v1.132.8Refactor all @/types in model runtime to @lobechat/types.
  • v1.132.5Move the ModelProvider to model-bank.
  • v1.132.4Enable thinkingBudget control for Vertex Gemini 2.5 models, update i18n.
  • v1.132.3Added AUTH_MICROSOFT_ENTRA_ID_BASE_URL routing.
  • v1.131.4Enhanced AkashChat experience.
  • v1.131.2Use ID as name if provider name is empty.
  • v1.131.1Extend custom provider runtime options, Optimized modelFetch for Vercel AI Gateway, update i18n.
  • v1.129.2Update i18n.
  • v1.129.1Update SiliconCloud reasoning models.
  • v1.128.9Improve error handle with agent config, support .doc file parse.
  • v1.128.8Enable toggling search on/off via search button click & historyCount button.
  • v1.128.6Update i18n.
  • v1.128.4Fix discover plugin link.
  • v1.128.2Update i18n, Update model configs.
  • v1.128.1Refactor message proccesser to the context engine.
  • v1.127.3Refactor model runtime folder structure and add more tests.
  • v1.127.1Update i18n.
  • v1.127.0Add hotkey tooltip to typobar actions.
  • v1.126.3Add CometAPI model provider and chat models, update i18n.
  • v1.124.3Refactor to remove edge runtime and add more tests.
  • v1.124.1Update doubao-seed-1.6-vision models.
  • v1.123.4Remove edge runtime.
  • v1.123.1Update i18n.
  • v1.122.7Make LobeNextAuthDBAdapter Edge Compatible.
  • v1.122.5Make LobeNextAuthDBAdapter Edge Compatible.
  • v1.122.4Update i18n.
  • v1.122.3Update the price of the o3 model in OpenRouter.
  • v1.120.7Update i18n.

What's fixed

  • v1.133.5Custom provider fails when client requests are enabled.
  • v1.133.4OllamaCloud error.
  • v1.133.3Fix frontend random API key config not work.
  • v1.132.18Refactor tools-engine and fix search token count.
  • v1.132.17Fix input empty group name.
  • v1.132.16Resolve qwen-image-edit imageUrls conversion issue.
  • v1.132.15Add proxyUrl configuration for NEW API provider.
  • v1.132.12Slove setting proxy page with style error.
  • v1.132.10Macos desktop sign.
  • v1.132.2Fix non stream mode in OpenAI Response API.
  • v1.132.1Fix missing provider in server message.
  • v1.131.3Update Responses search tool to web_search.
  • v1.130.1Fix oidc open direct issue.
  • v1.129.4Fix svg xss issue.
  • v1.129.3Add qwen provider support for image-edit model.
  • v1.129.2Improve db migrations sql.
  • v1.128.10Fix azure ai runtime error.
  • v1.128.5Google stream error unable to abort request.
  • v1.128.3Fix open chat page with float link modal.
  • v1.127.4Improve OpenAIStream processing to emit usage data for chunks lacking choices.
  • v1.127.2Delete files should delete chunks銆乪mbedings銆乫ileChunk.
  • v1.127.1Fix not remove message with server mode.
  • v1.126.2Fix editor key handling.
  • v1.126.1Fix Assistant List error message.
  • v1.124.4Revert V1 Mobile.
  • v1.124.2Fix ChatInput send command switch.
  • v1.124.1Enhance NewAPI with environment variables and fix routers compatibility.
  • v1.123.3Fix mobile header title to loog not ellipsis.
  • v1.123.2Not use branch topic when this topic is not save.
  • v1.122.3Support base64 image from markdown image syntax.
  • v1.121.1Fix socks5 proxy not work problem, fix virtuaso minheight was null.
LobeHub

Super-Agents on Your Team

Bring Super-Agents onto your team, starting today.