• Fix: only use Responses API for OpenAI models when native search is enabled
• Fix: disable reasoning effort for OpenAI gpt-5-chat
• Fix: disable OpenAI reasoning summary when reasoning effort is turned off

• Support reasoning effort in OpenAI GPT-5
• Fix max output tokens with OpenAI GPT-5
• Support reasoning summary for OpenAI GPT-5
• Enable native web search for OpenAI models

Fix OpenAI GPT-5 temperature setting.

Fix: show Ollama GPT-OSS thinking content

Support chatwise://mcp/add?json=<base64 encoded mcp json config> for adding MCP servers

• New provider: Poe (https://x.com/poe_platform/status/1950967460125131047)
• Allow to hide menubar icon on macOS:

• Support fetching ZhiPu (bigmodel.cn) models, open sourced at https://github.com/egoist/chatwise-models
• Fix Anthropic oauth status display error
• Fix assistant sorting on Windows

Fix Claude Pro/Max error.

Claude Pro/Max

Now you can authenticate Anthropic with your Claude Pro/Max subscription

Tray/Menubar

Now ChatWise lives in your system tray or menubar, click the icon to open window, or right click for more options

More

• You can use Command+P (mac) or Ctrl+P (windows) to open the command center now, the old hotkey Command+K still works
• Fix spinner bug

• New: allow to specify model in prompt settings
• Fix: JSON comment support when importing mcp from clipboard

Fix settings window glitching on macOS.

• OpenRouter: allow adding custom models
• Together AI: allow adding custom models
• New provider: Hyperbolic
• New Provider: Cerebras

• fix web search: change default openrouter web search model to openrouter-qwen/qwen3-14b:free
• fix image support: support uppercase filename

Auxiliary Visual Model

For models that don't support image input, like Kimi K2, you can select an auxiliary visual model in Settings > Extensions > Auxiliary Visual Model to get visual description for the images you attached

Docs: https://docs.chatwise.app/auxiliary-visual.html

Fix typo.

• Fix: remove instruction when using custom openai model in text-to-speech settings
• New: add groq to text-to-speech settings
• New shortcuts: CommandOrControl+Shift+C to copy recent response, CommandOrControl+R to regenerate response. (Command on Mac and Control on Windows)
• Add an option to hide reasoning content by default

• tts: allow to use a custom model for the openai provider
• chatwise search: previously when a web page is too long it would use the first 4000 characters, now we added an option to summarize web pages with AI first
• new provider: 302.ai

• MCP: allow to import HTTP MCP servers from clipboard JSON
• Press Arrow-Up (↑) in an empty input box to enter the last user message
• Support native search grounding (model's built-in search tool) if available, currently we've added support for Google Gemini, xAI Grok, and Perplexity Sonar, with more to come.

• Data Export: export the order of assistants in the sidebar
• Custom Provider: allow to select the models you want to add, instead of adding all fetched models

Added new providers: Kimi, ZhiPu

Add Long-running option for stdio MCP servers to always keep them connected in the background, useful for servers like @playwright/mcp where you don't want to close the browser after each response.

MCP optimization

For stdio and sse MCP servers, now it will not be kept running in the background when it's not used, MCP servers are only connected when a tool needs to be called during a conversation, and all MCP server connections will be terminated when the conversation is finished.

• Fix MCP env variable support in stdio command: so something like $HOME/.local/bin/uv --directory $HOME/dev/mcp-ical run mcp-ical could work (previously you could only add a single variable)
• Fix: allow ChatWise to access Apple Calendars

• Fix duplicated reasoning content in OpenRouter Gemini 2.5
• GitHub Copilot: fetch latest models from GitHub Copilot API instead of using hard-coded ones

• Disable Image Generation, MCP for OpenAI Deep Research Models (web search is always enabled through OpenAI's own web search tool, MCP is not yet supported when using Deep Research models)
• Add Dart syntax highlighting

Fix AiHubMix with OpenAI Responses API. (btw you get 10% off from the official price when consuming AiHubMix API in ChatWise now)

• Add basic support for OpenAI o3-deep-research and o4-mini-deep-research, they are the same as the Deep Research feature in the official ChatGPT app, but ChatWise doesn't display research progress YET, expect very slow response for now!
• Now every user can add MCP servers and use tools, but free users are limited to 5 MCP servers.

• Remember last visited provider tab in settings windows
• Improve chat history search: replace in-memory search with a SQLite query

Fix AiHubMix with o1-pro, o3-pro etc which use the new responses API.

Update MCP spec to the latest version (2025-03-26)