• Optimize screenshot image size
• MCP: allow to import MCP servers from JSON (stdio servers only). https://docs.chatwise.app/tools#import-from-json

• Fix screenshot for single message
• Fix styles for toast

• Chat screenshot: you can now copy screenshot for a turn, a message, or the whole chat
• MCP error handling: it will retry if the tool argument is invalid JSON, or if the tool call failed
• Free trial: now new users can enjoy 7-day ChatWise Pro free trial

• When Tools / MCP servers are enabled, you can drop a file into ChatWise and insert it as file path, useful to work with tools that requires file path as input
• Support audio / video input in Aliyun provider

• Fix MCP command on Windows

• Fix MCP with gpt-4o
• Fix shortcut Shift-Alt-ArrowUp/Down to match system default
• Allow to use any model to generate web search keywords

• macOS: fix slow app startup when MCP tools are enabled, now it should be 200ms faster to open the app
• fix app crashing when closing the window

• Add Gemini 2.5 Pro Exp (it's a reasoning model but Google's API doesn't output the thoughts, that's only available in Google AI studio
• Better error when it fails to generate web search keywords
• Fix artifacts format for Gemini

You can now right click image to copy

You can now select text and right click to quote selected text

A shortcut to stop generating response

Press Command . (mac) or Ctrl . (windows) to stop generating response.

• MCP: support image results return by tools
• MCP: now you can use env variables $HOME and $TMPDIR in the command
• Fix screenshot when the chat response contains images
• Fix OpenAI o1-pro

• Support Gemini image generation: choose the model Gemini 2.0 Flash Exp (Image Gen), currently only support the official Google AI provider
• Fix a web search issue related to port being used.
• Improve the LLM response performance (detail: previously I was using Tauri events to get streaming response, now it's replaced with Tauri channel)
• MCP: handle tool result with type: 'resource', like the repomix mcp and others

• Account: you can now log in with email + verification code
• OpenRouter: use DeepSeek V3 (free) to generate chat title and search keywords by default
• Text-to-Speech: add new OpenAI TTS model: gpt-4o-mini-tts and make it the default, you can also fine tune the voice with custom instructions now <img alt="tts" src="https://cdn.jsdelivr.net/gh/egoist-bot/images@main/uPic/g5uhhW.png" width="700">
• Add a button to expand system instruction editor <img alt="system instruction" src="https://cdn.jsdelivr.net/gh/egoist-bot/images@main/uPic/25moMZ.png">
• Data settings: you can now export and import chat history <img alt="chat history export" src="https://cdn.jsdelivr.net/gh/egoist-bot/images@main/uPic/vGHt7Z.png" width="700">

• Fix: google (free) web search sometimes returns 0 results
• Add OpenAI o1 pro model, the most expensive model so far
• Fix: prompt caching

• Fix: weird UX behavior when updating prompts / tools, fix #155
• Fix: toggling dark mode should apply to code blocks too
• Fix: MCP tool parsing error

Fix npx MCP servers on Windows.

• Implement prompt caching for OpenRouter Claude, now both Official and OpenRouter's Claude models have prompt caching by default
• Properly closing MCP servers when you close the app window
• Properly reconnect SSE MCP servers

• Fix a bug where you can't send files without text prompt
• Add "Delete response" to message context menu

• Add a button to reconnect all tools (MCP servers)
• Minor style tweaks

• Windows: fix settings layout
• Tool: fix tool result view

• Ollama gemm3 image support
• Fixes