Plugins

A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

DeepSeek Harness 插件：以 MindSee 为后端，为 DeepSeek 提供图片相关能力