Scene-awareness probe for DSH on macOS: a privacy-first, pull-model `look` tool that reads the frontmost non-self window (app info, AX title/selection, gated local OCR), plus a summon-hotkey snapshot captured the instant you press.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-look
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:mengxiaoxian/lookover#path:/dsh-look
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
遇到“这个页面、这段文字、这个报错”，按需读取当前窗口上下文，减少复制粘贴。
属于 lookover 桌面助手组合：搭配 dsh-bubble 在工作页面旁提问，再用 dsh-expmem 保存值得复用的经验。Look 也能单独在 DSH 主窗口使用。
如何用
把目标页面放到最前、选中文字，向 Agent 说：
请用 look 读取浏览器里的选中文字，解释这一段。
文字无法通过辅助功能读取且你愿意读取画面时，可以说：
请用 look 的 OCR 看一下当前报错窗口，先说清楚读到了什么，再帮我排查。
模型根据问题调用 look；多窗口选错时可指定应用或窗口名，如 look({pick:"浏览器"})。OCR 通过 look({ocr:true}) 按需启用。本插件只读上下文，不负责点击、输入或编辑其他应用。
读得到什么
| 权限 | 内容 | 边界 |
|---|---|---|
| 无额外权限 | 应用名、窗口位置大小等基本信息 | 不能声称看到页面正文 |
| 辅助功能 | 应用暴露的标题、文档地址、选中文字、焦点文本 | 部分应用不暴露内容，失焦可能丢选区 |
| 屏幕录制且请求 OCR | 当前窗口截图、本地 macOS Vision 文字识别 | 可能截图失败或识别错误 |
读取结果提供给当前 Agent；本地 OCR 不等于所有上下文永不离开本机。云端模型会收到提供给它的文本。视觉问题如需读图，还需宿主和模型支持相应能力。
不持续监视。每次读取在 ~/.dsh/look/log.jsonl 留痕，可能包含所读文本；临时截图 10 分钟过期，按后续调用清理，不是后台定时清理。
安装
0.1.1 面向 macOS arm64、官方 DeepSeek Harness 0.2.0-rc.2。关闭 DSH 后安装，再打开：
dsh plugin --profile desktop add https://github.com/mengxiaoxian/lookover/releases/download/lookover-2026.10.12/dsh-look-0.1.1.tgz
无 dsh 命令时见官方内置 CLI 用法。
当前边界
- 自动排除官方 DSH 与气泡窗口；其他桌面壳未在本轮验收。
- 官方版通过 Agent 调用
look；旧壳的 ⌥⌘Z／新会话热键和按键快照尚未迁移。 - 选区读取取决于应用和权限；首次体验建议明确请求
look，信息不足时粘贴文本。 - 本版不发布工作区里的
operate草稿，不附带其他应用的操作能力。 - 官方工具注册及 schema（数据格式）校验已有验证；不等于各种应用的正文、选区、OCR 端到端验收。
lib/index.js 注册工具与提示，native/look.swift 读取窗口，包内附 arm64 helper。源码构建用 npm run build:native，需要 Swift 编译工具。插件不自动授予系统权限。
Links
More in this category
liustack/modlens★ 4725
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
ysr666/dsh-vision-router★ 1211
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
Anionex/dsh-vision-toolkit★ 922
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.
SAOS-3624/dsh-video-storyboard★ 384
Turns a video (a local file, or a Bilibili/yt-dlp link) into one addressable storyboard grid — numbered cells with exact timestamps, per-cell transcript and an audio envelope on the same timeline — and video_zoom re-reads any window at higher resolution, so a text-only model can look at the video instead of reading a summary.
dickpy/dsh-imagegen★ 167
AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.
fandc520/dsh-comfyui★ 159
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.