zcXie777/dsh-image-reader

Name: zcXie777/dsh-image-reader
Author: zcXie777

插件Plugin 原生Native ⭐ 2 MIT cat_label.deepseekcat_label.deepseek cat_label.deepseek-harnesscat_label.deepseek-harness cat_label.dsh-pluginscat_label.dsh-plugins

为DeepSeek Harness代理提供原生图像读取能力：一个由任意兼容OpenAI视觉接口支持的read_image工具。

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

dsh-image-reader 是为 DeepSeek Harness 文本代理增加视觉能力的插件，提供一个模型可调用的 read_image 工具，按工作区路径向任意 OpenAI 兼容视觉端点发起多模态请求。在需要让代理解读截图、图表或照片时使用。需要 baseUrl、model 与 VISION_API_KEY 环境变量；目前尚未对真实视觉端点做过端到端验证，建议先用真实密钥冒烟测试一次。

dsh-image-reader is a DeepSeek Harness plugin that adds image understanding to a text-only agent by exposing a single read_image tool, which sends a workspace-path image to any OpenAI-compatible vision endpoint. Use it when the agent must answer questions about screenshots, diagrams, or photos instead of plain text. It requires provider baseUrl, model, and a VISION_API_KEY environment variable. End-to-end testing against a live vision model has not yet been performed, so run a smoke test with a real key before depending on it.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【dsh-image-reader】【https://github.com/zcXie777/dsh-image-reader】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

或使用命令行安装（适合开发者）Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add "$PWD/dsh-image-reader"

把 zcXie777/dsh-image-reader 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.0 KB · 缓存于 2026-08-23 03:42:26 · 3.0 KB

dsh-image-reader

Give a text-only DeepSeek Harness agent the ability to read images directly: one model-facing read_image tool that asks any OpenAI-compatible vision endpoint about an image by its workspace path.

Why

DeepSeek Harness is "everything is a plugin". This bundle mounts a single tool so the model can look at a screenshot, diagram, or photograph and answer questions about it, instead of only ever reasoning over text.

Verification status

Verified locally: npm run typecheck, npm run build, and npm test (16 tests) all pass.
Not yet verified: a real end-to-end read against a live vision endpoint. The request/response logic is covered by a mocked-fetch unit test, but the plugin has not been smoke-tested inside a running dsh profile against a real multimodal model. Do that once with a real VISION_API_KEY before relying on it.

Install

git clone https://github.com/zcXie777/dsh-image-reader.git
cd dsh-image-reader
npm install
npm run build          # lib/ is not committed; build once after cloning
cd ..
dsh plugin --profile web add "$PWD/dsh-image-reader"
dsh plugin --profile headless add "$PWD/dsh-image-reader"
dsh --profile web --dump-config | grep image-reader

Restart a running Web profile after installing.

Configure

provider.baseUrl and provider.model are required; the plugin never assumes a vendor. Override them in the profile patch row with the same id:

- id: image-reader
  config:
    provider:
      baseUrl: https://api.openai.com/v1
      model: gpt-4o-mini
      apiKeyEnv: VISION_API_KEY
    lang: zh
    timeoutMs: 60000
    maxImageBytes: 10485760
    allowedDirs: []

Set the key in the environment before starting the profile:

export VISION_API_KEY=sk-...

Use

In a conversation, point the model at an image path and ask:

read_image image="screenshot.png" query="What error is shown in this dialog?"
read_image image="diagram.png"

Configuration fields

Field	Default	Contract
`provider.baseUrl`	— (required)	OpenAI-compatible `chat/completions` base URL
`provider.model`	— (required)	Multimodal model name
`provider.apiKeyEnv`	`VISION_API_KEY`	Environment variable holding the API key
`lang`	`zh`	Answer language: `zh` or `en`
`timeoutMs`	`60000`	Whole-request deadline, 1000–600000 ms
`maxImageBytes`	`10485760`	Encoded-byte limit per image
`allowedDirs`	`[]`	Extra realpath-resolved input roots; the workspace is always allowed

Security

Inputs resolve against the workspace and allowedDirs through realpath, so a symlink cannot escape the fence.
Images are size-limited and extension-checked before upload.
The key is read from the environment per call, never stored in config.

Development

npm install
npm run typecheck
npm run build

Publish

Tag the repo with the dsh-plugin topic so it is discoverable, and publish to npm when ready.

License

MIT

渲染基于仓库 zcXie777/dsh-image-reader 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install