MIT 授權的 DeepSeek Harness 視覺外掛：一個 dsh plugin 指令裝入 DSH Web profile，將圖片輪次路由到免金鑰的免費視覺鏈，並提供定位、裁切、像素 diff、OCR、SVG 向量化等 14 個像素級工具。
DSH 整合
原生執行環境
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
MIT
01它能幫你完成什麼？
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如何將外掛接入 DeepSeek Harness？
先決條件
- 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)
安裝步驟
- 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
驗證整合成功
- `npx @deepseek-ai/dsh --profile web --dump-config | grep vision-router` (source checkout: `pnpm dsh --profile web --dump-config | grep vision-router`)
復原
- 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 整合程度與能力邊界
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適合誰？何時不該用？
適合
- 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
不適合
- 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相容性、維護與安全提醒
- 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常見問題
如何把 dsh-vision-router 安裝到 DeepSeek Harness？
它是原生 DSH 外掛：執行 `npx @deepseek-ai/dsh plugin --profile web add dsh-vision-router`（原始碼簽出版本用 `pnpm dsh plugin --profile web add dsh-vision-router`），重新載入 DSH Web 後，在右下角模型選擇器選取標示「+ Auto Vision」的模型群組。外掛自帶組合修補檔，無需手動編輯任何檔案。
辨識圖片需要自己的 API 金鑰嗎？
不需要。視覺鏈結末端內建匿名 OVHcloud 免費回退——免註冊、免金鑰，限速為每 IP 每模型 2 次/分鐘。你可以在它之前加入自己的視覺模型、本機 Ollama 或 LM Studio，或使用 README 列出的免費金鑰管道取得更高配額。
它會改動我日常使用的 DeepSeek 模型嗎？
不會。原有模型群組完全不被修改——外掛只建立同名的「+ Auto Vision」項目，文字輪次在模型、費用與上下文上維持原樣。接管官方路由的隱身模式預設關閉，需明確開啟。
我的圖片和資料會被傳到哪裡？
上傳時只把所選圖片和你的問題傳送給已設定的視覺服務商主機（選用的 Proxy 只作用於視覺主機，DeepSeek 保持直連）。產生的成品檔寫入本機 `<workspace>/.dsh-vision-router/artifacts`，圖片中的文字一律視為不可信證據處理。
主要限制有哪些？
匿名免費回退限速為每 IP 每模型 2 次/分鐘（五個模型合計約 10 RPM）；主機需要 Node ≥ 22；只有 `vision_html_screenshot` 需要 Chrome / Chromium / Edge；桌面截圖工具預設停用，需手動開啟。
07相關的 DSH 工作流程
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). | 全網最強 DeepSeek Harness 外掛視覺外掛，為 DeepSeek、GLM 等純文本模型外掛視覺能力，貼上圖片即得結構化 JSON 證據（OCR、版面、語義）。
agent-vision-toolkit
作者 anionex
為純文本模型"看圖“設計更好的視覺工具箱和技能，支援多圖理解，圖片問答，前端UI還原、GUI 自動化等，並可選無縫接入多個主流agent，直接識別貼上圖片｜ 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]為純文本模型設計更強大的視覺工具箱：一行安裝使用、貼上圖片直接識別、多張圖片問答、截圖到前端UI 還原等｜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 對話中生成圖片，無需切換外部工具。
08資料與來源
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.
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。