Improvements
- GPT models on Messages endpoints now receive their configured effort setting via
output_config.effort.
Documentation
- Updated gateway routing documentation to clarify how GPT model IDs and effort settings are sent.
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>
Thanks to zxz8009195489, whose reports and code went into this release. Everyone who helped: contributors.
Improvements
- GPT 模型在 Messages 端点上现在通过
output_config.effort接收其配置的 effort 设置。
Documentation
- 更新了网关路由文档，以澄清 GPT 模型 ID 和 effort 设置是如何发送的。
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。
感谢 zxz8009195489：这次更新里有你的反馈与代码。所有贡献者见贡献墙。