MIT 协议的 DeepSeek Harness 视觉插件：一条 dsh plugin 命令装入 DSH Web profile，把图片轮次路由到免密钥的免费视觉链，并提供定位、裁剪、像素 diff、OCR、SVG 矢量化等 14 个像素级工具。
DSH 适配
原生运行时
作者声明
安全审计
未审计
最后核验
2026-08-21
许可证
MIT
01它能帮你完成什么？
Give text-only DeepSeek Harness agents pixel-level image understanding
Image Q&A answers, original-pixel grounding boxes, zoomed crops, OCR text, dominant colors, SVG traces and cutouts, all as ordinary tool calls
DSH users on text-only DeepSeek / opencode routes who need the coding agent to actually see pasted screenshots and design images
Verify UI rebuilds against a reference design with a measurable pixel loop
HTML screenshots plus per-pixel diff reports — diff ratio, red heatmap PNG and worst-region ranking — repeated until the mismatch converges
Frontend and coding-agent workflows restoring web UI from reference screenshots who want pixel-verified results instead of eyeballing
Run AI vision out of the box without API keys or paid accounts
A keyless anonymous OVHcloud fallback chain (five models, about 10 RPM in theory) with automatic classified failover, optionally fronted by user-configured or local backends
Hobbyists and teams who want image understanding in DSH immediately, before configuring any vision provider
02如何接入 DeepSeek Harness？
前置条件
- DeepSeek Harness Web profile (normal installs use `npx @deepseek-ai/dsh`; source checkouts use `pnpm dsh`)
- Node ≥ 22 on the host
- No API key for the default free chain; Chrome / Chromium / Edge only for `vision_html_screenshot`; Tesseract optional (OCR falls back to the vision model)
安装步骤
- 01
Run `npx @deepseek-ai/dsh plugin --profile web add dsh-vision-router` (from a DeepSeek Harness source checkout: `pnpm dsh plugin --profile web add dsh-vision-router`)
$ npx @deepseek-ai/dsh plugin --profile web add dsh-vision-router
- 02
Start or reload DSH Web; if installing into an already long-running Web process, let it reload once so the plugin bundle is discovered
- 03
Open the model selector in the lower-right corner of the chat composer and choose a group marked '+ Auto Vision'
- 04
Paste or upload an image normally — the agent can immediately use `vision_describe`, `vision_ground`, `vision_crop` and the other tools across multiple steps
验证接入成功
- `npx @deepseek-ai/dsh --profile web --dump-config | grep vision-router` (source checkout: `pnpm dsh --profile web --dump-config | grep vision-router`)
回滚
- Run `npx @deepseek-ai/dsh plugin --profile web remove dsh-vision-router` — removes the dependency and the bundle layer; if you disabled the stock DeepSeek row manually, re-enable it in your profile patch
- Or set `disabled: true` for `vision-router` in the profile patch to unload wrapper routes, tools, skill and settings card (cached artifact files remain)
03DSH 适配与能力边界
DSH Web profile plugin installed via the official dsh CLI; ships its own composition bundle patch and registers '+ Auto Vision' wrapper model groups inside DeepSeek Harness
Automatic vision routing ('+ Auto Vision' groups)
image turns in any DSH Web chat session→image turns are answered through a vision model while text turns keep using the daily model; original model groups are never modified
registers an admission wrapper and '+ Auto Vision' wrapper model groups in the DSH profileoptional stealth mode can take over the official deepseek-official route (off by default, explicit opt-in)Fourteen pixel-level vision tools
image attachments or local image files→grounding boxes, crops, pixel-diff heatmaps + JSON reports, OCR text, dominant colors, SVG traces, foreground cutouts and HTML screenshots — no Python required
artifacts are written under `<workspace>/.dsh-vision-router/artifacts``vision_screenshot` desktop capture is disabled by default and requires an explicit privacy opt-inMulti-backend fallback chain with keyless free endpoint
any vision tool call→backends tried in order — user vision models, optional local Ollama / LM Studio, custom HTTP endpoints, then the anonymous OVHcloud fallback — with classified errors and Retry-After-aware cooldowns
network calls to the configured vision provider hosts (optional proxy applies to vision hosts only; DeepSeek stays direct)the anonymous OVH endpoint is limited to 2 requests/minute per IP per modelImage memory (content-hash caching)
images discussed in the session→vision answers cached by attachment content hash; later text turns reuse the recorded description (marked as untrusted evidence) without re-spending vision calls
04适合谁？何时不该用？
适合
- DSH users on text-only DeepSeek / opencode routes who need the coding agent to actually see pasted screenshots and design images
- Frontend and coding-agent workflows restoring web UI from reference screenshots who want pixel-verified results instead of eyeballing
- Hobbyists and teams who want image understanding in DSH immediately, before configuring any vision provider
不适合
- The built-in free fallback is the anonymous OVHcloud endpoint, capped at 2 requests/minute per IP per model (about 10 RPM in theory across five models); heavier use needs one of the README's free key channels or a local backend.
- Requires a DeepSeek Harness Web profile and Node ≥ 22 on the host; Oh-DSH Desktop ≤ 0.1.5 needs plugin v1.4.2+ (earlier versions crash its bundled runtime), and Linux desktop capture needs ImageMagick `import` or `scrot`.
- Mixing legacy manual `cordis.patch.yml` plugin rows with `dsh plugin add` can register the plugin twice; upgrading from a pre-bundle-patch v0.x install requires deleting the old manual row or `dsh web` fails at startup.
05兼容性、维护与安全提示
- The built-in free fallback is the anonymous OVHcloud endpoint, capped at 2 requests/minute per IP per model (about 10 RPM in theory across five models); heavier use needs one of the README's free key channels or a local backend.
- Requires a DeepSeek Harness Web profile and Node ≥ 22 on the host; Oh-DSH Desktop ≤ 0.1.5 needs plugin v1.4.2+ (earlier versions crash its bundled runtime), and Linux desktop capture needs ImageMagick `import` or `scrot`.
- Mixing legacy manual `cordis.patch.yml` plugin rows with `dsh plugin add` can register the plugin twice; upgrading from a pre-bundle-patch v0.x install requires deleting the old manual row or `dsh web` fails at startup.
MIT · actively maintained (latest release v1.7.3, 2026-08-20)
06常见问题
如何把 dsh-vision-router 安装到 DeepSeek Harness？
它是原生 DSH 插件：运行 `npx @deepseek-ai/dsh plugin --profile web add dsh-vision-router`（源码检出版本用 `pnpm dsh plugin --profile web add dsh-vision-router`），重载 DSH Web 后在右下角模型选择器里选择带“+ Auto Vision”标记的模型组。插件自带组合补丁，无需手动编辑任何文件。
识图功能需要自己的 API key 吗？
不需要。视觉链末端内置匿名 OVHcloud 免费回退——无需注册、无需密钥，限速为每 IP 每模型 2 次/分钟。你可以在它之前加入自己的视觉模型、本地 Ollama 或 LM Studio，或使用 README 列出的免费密钥渠道获取更高配额。
它会改动我日常使用的 DeepSeek 模型吗？
不会。原有模型组完全不被修改——插件只创建同名的“+ Auto Vision”入口，文本轮次在模型、费用和上下文上保持原样。接管官方路由的隐身模式默认关闭，需要显式开启。
我的图片和数据会发送到哪里？
上传时只把所选图片和你的问题发送给已配置的视觉服务商主机（可选代理只作用于视觉主机，DeepSeek 保持直连）。生成的产物文件写入本地 `<workspace>/.dsh-vision-router/artifacts`，图片中的文字一律按不可信证据处理。
主要限制有哪些？
匿名免费回退限速为每 IP 每模型 2 次/分钟（五个模型合计约 10 RPM）；宿主机需要 Node ≥ 22；只有 `vision_html_screenshot` 需要 Chrome / Chromium / Edge；桌面截图工具默认禁用，需手动开启。
07相关的 DSH 工作流
modlens
作者 liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
agent-vision-toolkit
作者 anionex
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
dsh-vision-toolkit
作者 anionex
[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
dsh-image-gen
作者 shanliuling
直接在 DeepSeek Harness 对话中生成图片，无需切换外部工具。
08数据与来源
The package ships its own composition patch (`dsh.bundle.patch`): `dsh plugin add` wires the row, the admission wrapper…
npx @deepseek-ai/dsh plugin --profile web add dsh-vision-router
the plugin discovers the model groups enabled under **Settings → Models** and creates same-name auto-vision entries.
页面基于项目公开文档、仓库元数据和 DSH Plugins 的结构化解析生成；最后核验于 2026-08-21。发现错误？提交更正。
最佳 DeepSeek Harness 插件
从全目录挑出的 12 个值得优先安装的插件，覆盖各个分类。