Codex-style local browser automation for DeepSeek Harness: open pages, interact by @e references, extract content, screenshot, and run page JS — with two backends: managed headless Playwright (fast, invisible) or CDP connected to your own Chrome (visible, and loads Chrome extensions that headless cannot).
dsh-vision-bridge:在 DeepSeek Harness 聊天框粘贴图片,任意模型都能看懂——纯文本模型自动转成图片路径并调用 vision_chat 识图,支持图片的模型直接接收原图。粘贴即用,自动识别、自动回答。dsh-vision-bridge: paste any image into the DeepSeek Harness chat box — every model can see it: text-only models get an automatic vision_chat bridge, vision-capable models receive the image directly. Paste, send, done.
在 DeepSeek Harness 侧边栏工作区的"..."菜单里,一键用文件资源管理器、VS Code 或终端打开工作区文件夹,或复制其绝对/相对路径——不用再满硬盘翻找文件夹在哪。 open your DeepSeek Harness workspace folder in File Explorer, VS Code, or a terminal — or copy its absolute/relative path — straight from the workspace row menu. No more hunting for folders.
DSH web GUI plugin: auto fold/expand the chat window — bottom checkpoints hide old pages, top-scroll expands earlier messages with the viewport anchored.
DSH web plugin: a task kanban that refines requirements into phased plans, auto-executes them in git worktrees (one session per phase), and auto-merges into the main branch on completion.