dsh-img：为 DeepSeek Harness 提供图片理解与本地视觉工具
dsh-img 是 DeepSeek Harness 的社区视觉插件，旨在为纯文本模型提供图片理解能力。它通过接入视觉后端或本地像素工具，实现 `analyze_image` 图片问答、OCR、布局理解及 `vision_ground` 元素定位。插件支持智谱 GLM-4V-Flash、通义 Qwen-VL、Ollama 本地模型及 OpenAI 兼容端点，并内置免 key 的本地工具如 `vision_crop`、`vision_ocr` 等。 安装需 Node.js >= 20 及 dsh 本体，通过 `pnpm add` 安装至指定 profile。使用 API 后端时需将 key 注入
Read Moredsh-image-plugins：为 DeepSeek Harness 接入看图与生图
DeepSeek Harness多模态插件dsh-image-plugins为DSH Web端提供图片理解与生成能力。该插件包含understand_image和generate_image两个独立工具，分别支持读取工作区图片并返回文字描述，以及根据提示词生成并保存图片。插件支持OpenAI-compatible端点及DashScope原生API，其中DashScope图片生成需使用native Model Studio API以规避404错误。安装后需通过Web设置面板或配置文件独立启用vision和image功能，并配置相应的baseUrl、apiKey和model。密钥支持明文、环境变量
Read Moredsh-tool-describe-image：给 DSH 增加图片理解能力
`sala003/dsh-tool-describe-image` 是 DSH 生态下的 MIT 许可插件，旨在为文本模型赋予图片处理能力。它通过接入任意 OpenAI 兼容视觉端点（如百炼、智谱等），将图片转化为文字描述或结构化 HTML，供 DeepSeek 使用。核心功能包括：Web 界面粘贴即识别、按路径调用工具描述图片、查询 DeepSeek 账户余额，以及提供可定制的鲸鱼娘桌宠入口。插件支持零配置启动，后续可通过环境变量或设置面板补配 API Key。安装需 DSH 0.1.0-rc.6+，通过 npm 全局安装并启用。支持 PNG、JPG、WebP、GIF 格式，单张上限 8Mi
Read Moredsh-dseyes：给 DeepSeek Harness 的纯文本模型提供原生图片上传体验
dsh-dseyes 是 DeepSeek Harness (DSH) 的一个 MIT 许可插件，旨在解决纯文本模型无法直接处理图片的问题。该插件允许用户在 Web GUI 中粘贴或拖入图片，以附件形式显示并保留原图。在请求发送给 DeepSeek 之前，宿主端自动调用智谱 GLM 免费视觉模型（如 glm-4v-flash）识别图片内容，生成文字描述并替换原图片块，使文本模型基于描述进行回答。 插件支持自动降级链、结果复用及诊断接口，读图失败时对话不中断。安装需 Node >= 22，配置 GLM_API_KEY 或 ZHIPU_API_KEY，并通过 `dsh plugin --profi
Read Moredsh-vision-tools：给 DSH 会话增加图片理解能力
dsh-vision-tools 是 DSH 生态中的视觉插件，由 moon09300731 维护（MIT 许可）。它提供全局 `vision_understand` 工具，通过 OpenAI 兼容 API（支持智谱、阿里、硅基流动、OpenAI）理解本地图片，实现画面描述、文字识别及基于图片的回答。图片可通过粘贴、拖拽或按钮选择方式送入，自动保存至指定目录并填入提示词。插件支持限流自动降级、全局及项目级配置实时生效，并在 Web 界面提供“识图”入口。安装命令为 `dsh plugin --profile web add dsh-vision-tools`，需重启 `dsh web`。配置需
Read MoreDSH-Vision-Plugin: Adding Image Understanding Capabilities to DSH
dsh-vision-plugin is a plugin developed specifically for DeepSeek Harness (DSH), designed to address the limitation that pure text models cannot directly process images. This plugin leverages OpenRouter's free multimodal models (`:free`) to automatically convert images into text descriptions before sending, thereby endowing text-based models like DeepSeek with image understanding capabilities, all at zero API cost. Key features include: providing a `describe_image` tool to read local images; intercepting and converting images automatically via the `llm/stream` hook when the model does not support image inputs; and automatically writing a `deepseek-vision` provider pointing to OpenRouter into the configuration file on first startup.
Read Moredsh-vision: Adding Image Understanding to DeepSeek Harness's Plain-Text DeepSeek
dsh-vision is a DeepSeek Harness plugin developed by 54xee, designed to add image understanding capabilities to the pure text model DeepSeek. It wraps adapters to convert images into text placeholders and backfills the recognition results for model processing. The plugin defaults to using the Doubao Web channel, requiring only a browser login, with no API key needed and zero cost. It also supports multiple access methods, including Reverse Gravity IDE, Gemini API, Cockpit reverse proxy, aicode direct connection, and any IDE CLI. Core features include visual evidence memory, content hash caching, automatic tier upgrades, and four task modes. Installation is simple, configuration is flexible, and it is suitable for developers who wish to add visual capabilities to DSH at a low cost or those who already have relevant IDE/API quotas. Please note that you need to check...
Read MoreAchieving Native-Level Image Understanding in DeepSeek Harness with dsh-vision
DSH-Vision is a DeepSeek Harness plugin maintained by Oil-Oil, open-sourced under the MIT License, currently at version 0.1.0, and compatible with DSH 0.1.0-rc.6. When the main model can process images, it directly sends the original image. For pure-text DeepSeek interactions, it submits the original image to ZenMux, Bailian, TokenDance or OpenRouter for analysis, then returns the results to the original model as untrusted context for answering. It also supports see-skill and local OCR. This article verifies the installation, configuration and security boundaries based on the table of contents and the GitHub README.
Read More