Overview
@qizhen2021/dsh-plugin-vision
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.
README / EN
Package documentation
Registry summary
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.
dsh.pub verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.
Read the full README on GitHubLIMITATIONS
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。