dsh-read-image：为纯文本 DeepSeek Harness 提供即插即用读图
`dsh-read-image`是DeepSeek Harness（DSH）的一款MIT开源插件，旨在解决纯文本模型无法直接读取图片像素的痛点。该插件允许文本路由接受图片输入，将图片块投影为`[Image #N]`文本占位符，并自动注册`read_image`工具。通过该工具，开发者可调用可配置的视觉模型读取会话中的指定图片或文件路径，将其内容转换为文本供模型推理。若路由本身支持原生多模态，插件会智能回退至内置工具以避免冲突。插件提供“Read image”设置区块，支持配置视觉模型及提示词等参数。安装需DSH版本0.1.0-rc.6以上，通过命令行添加后重启即可。插件具备环境自检和失败安全机
Read MoreUsing dsh-read-image to enable plain-text DeepSeek Harness models to read images
### 翻译版本1（正式技术文档风格，符合开源项目译法惯例）： `dsh-read-image` is a session and messaging DeepSeek Harness plugin maintained by OoWJZZoO, licensed under MIT. It prevents plaintext routing from intercepting pasted images by projecting pixels into `[Image #N]`, then reads them back via the configurable vision-model-backed `read_image` tool, with no preset modifications required. This article verifies the installation commands, configuration items, usage methods and self-check boundaries against the community directory page and GitHub README. --- ### 翻译版本2（更贴合国内开源社区常见译法，口语化稍弱）： The `dsh-read-image` is a DeepSeek Harness plugin for sessions and messages, maintained by OoWJZZoO and released under the MIT license. This plugin stops plaintext routing from blocking pasted images, by converting image pixels into the format `[Image #N]`, then retrieving the image content through the `read_image` tool powered by configurable vision models — all without needing to edit any presets. This paper checks the installation commands, configuration options, usage guidelines and self-test boundaries against the community directory page and GitHub README.
Read More