dsh-read-image: Plug-and-play Image Reading for Text-only DeepSeek Harness
`dsh-read-image` is an MIT-licensed open-source plugin for DeepSeek Harness (DSH) designed to address the pain point where pure text models cannot directly read image pixels. This plugin enables text routing to accept image inputs, projects image chunks into `[Image #N]` text placeholders, and automatically registers the `read_image` tool. Through this tool, developers can invoke a configurable vision model to read specified images or file paths within a session, converting their content into text for model inference. If the routing itself supports native multimodality, the plugin intelligently falls back to the built-in tool to avoid conflicts. The plugin provides a "Read image" settings block, supporting the configuration of parameters such as the vision model and prompts. Installation requires DSH version 0.1.0-rc.6 or higher; simply add it via the command line and restart. The plugin features environment self-check and failure-safe mechanisms.
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