Bug Fixes
- Fixed an issue where text-only models in agents could reject images and say they don’t support image input, even when Vision was enabled. When a vision describer is available, agents now correctly list all models as accepting images.
Install
Download from usemagpie.ai, or curl -fsSL https://usemagpie.ai/install.sh | sh. An installed magpie updates itself.
- macOS (Apple Silicon):
magpie-darwin-arm64.dmg - macOS (Intel):
magpie-darwin-amd64.dmg - Windows:
magpie-windows-amd64.exe(ARM:magpie-windows-arm64.exe) - Linux:
magpie-linux-amd64/magpie-linux-arm64(needs GTK 3 and WebKitGTK 4.1) - Terminal only:
magpie-cli-<os>-<arch>
错误修复
- 修复了即使启用了 Vision，代理中的纯文本模型也可能拒绝图像并声称不支持图像输入的问题。当视觉描述器可用时，代理现在会正确地将所有模型列为接受图像。
安装
从 usemagpie.ai 下载，或运行 curl -fsSL https://usemagpie.ai/install.sh | sh。已安装的 magpie 会自动更新。