@qizhen2021/dsh-plugin-vision

Overview

The see tool for the DeepSeek Harness: offline OCR with positions (macOS Vision) + ASCII layout art (PIL) + vision-model semantic description (mimo-v2.5 via the opencode-go gateway). Works with any model, including text-only ones.

Community · Topic auto-analysis — Automatically discovered through the dsh-plugin GitHub Topic. Static checks verified a pinned public root bundle contract and committed files without executing third-party code. This is not a human review, security audit, runtime smoke test, publisher identity check, or official endorsement.

Install

Install this bundle from GitHub

The CLI validates the bundle, invokes native DSH, then reports completion.

npx dshpub add qizhen2021/dsh-plugin-vision --ref 39fe8c475630cc1565d6e11de6ee87bf2b505710

Capabilities

What it contributes

HostCordis loadableNot inspected

Client / UIHost onlyNot inspected

Model toolsNot inspectedNot inspected

Profile stateNot inspectedNot inspected

README / EN

Package documentation

给纯文本模型一双"眼睛"。注册一个 see 工具：对任意图片输出纯文本的三通道分析——

LIMITATIONS

Known limitations

- **无截图模式**：`screencapture` 无屏幕录制权限（"could not create image from display"），v1 不做。 - **OCR 仅 macOS**（Vision 框架）；ASCII/prep/VLM 跨平台（python3 + PIL）。 - swift 首调含编译约 1–2 秒（超时 90s 已留足）；v1 不做预编译缓存。 - 通道超时与取消依赖子进程协同；网关 HTTP 请求经 AbortSignal 中断。