以原生方式掛載到 dsh 的視覺外掛:註冊 view_image 工具,將圖片與問題轉發給任意 OpenAI 相容 VLM,答案以文字回傳,所有入口同時獲得視覺。
DSH 整合
原生執行環境
作者聲明
安全稽核
未稽核
最後核實
2026-09-03
授權條款
BSD-3-Clause
01它能幫你完成什麼?
Let text-only DeepSeek answer visual questions about images (OCR, counting, chart reading, UI layout)
A `view_image` tool the model calls with an image path and a question; returns the answer as text
DeepSeek Harness (dsh) users who need vision on a text-only model across web / TUI / remote channels
Route image understanding to any OpenAI-compatible VLM backend (free Zhipu, Qwen, Doubao, local Ollama)
Configurable baseURL + apiKey + model; automatic free-tier fallback chain keeps zero-config answers working
Users who want to keep their own BYOK / local VLM endpoint instead of a paid hosted vision service
02如何將外掛接入 DeepSeek Harness?
先決條件
- DeepSeek Harness (dsh) installed and on PATH
- A VLM endpoint (default uses free Zhipu glm-4.6v-flash; other backends need an API key or a local endpoint)
安裝步驟
- 01
Clone the plugin: `git clone https://github.com/dsh-external/dsh-vision ~/dsh-plugins/dsh-vision`
$ git clone https://github.com/dsh-external/dsh-vision ~/dsh-plugins/dsh-vision
- 02
Symlink host dependencies (@deepseek-ai/dsh-tools and schemastery) into the plugin's node_modules
- 03
Append the mount block to ~/.dsh/config.yaml and restart dsh
驗證整合成功
- Ask dsh about an image, e.g. "what error is in ~/Desktop/error.png"; the model should call view_image and return text
03DSH 整合程度與能力邊界
以原生方式掛載進 dsh 個人設定覆蓋層(~/.dsh/config.yaml),不依賴任何第三方管理程式,以原生 cordis 外掛形態運行。
view_image tool
image path / URL + natural-language question→text answer returned to the model
Multi-backend routing
configured baseURL + apiKey + model→forwards image + question to the VLM endpoint, returns text
sends image data to an external OpenAI-compatible VLM endpoint (or a local endpoint)Free-tier fallback chain
rate-limited default model (HTTP 429)→auto-downgrades glm-4.6v-flash → glm-4.1v-thinking-flash → glm-4v-flash
Zero-dependency cordis bridge
OpenAI-compatible /chat/completions + image_url→native TypeScript cordis plugin, no Python / uv / MCP
strips <think> reasoning blocks from thinking modelsauto-redacts API key in error messages
04適合誰?何時不該用?
適合
- DeepSeek Harness (dsh) users who need vision on a text-only model across web / TUI / remote channels
- Users who want to keep their own BYOK / local VLM endpoint instead of a paid hosted vision service
不適合
- Before marisa#2 is fixed, you must manually symlink the host dsh node_modules (@deepseek-ai/dsh-tools and schemastery) or the plugin fails to load.
05相容性、維護與安全提醒
- Images are forwarded to an external OpenAI-compatible VLM endpoint, so the plugin needs network access and (for non-local backends) an API key. Localhost endpoints need no key.
- Before marisa#2 is fixed, you must manually symlink the host dsh node_modules (@deepseek-ai/dsh-tools and schemastery) or the plugin fails to load.
- Zhipu's free model is rate-limited (429) on a shared pool; the plugin auto-downgrades across three free models to keep zero-config answers working.
BSD-3-Clause · no releases yet (curated; latest push 2026-08-13)
06常見問題
dsh-vision 是做什麼的?
它註冊一個 view_image 工具,讓純文字的 DeepSeek 也能看圖——OCR、數數、讀圖表、看 UI 佈局等任意視覺問題——把圖片與問題轉發給任意 OpenAI 相容的 VLM,答案以文字回傳。
怎麼安裝?
預設是原生掛載:複製倉庫,把宿主 dsh 的 node_modules(@deepseek-ai/dsh-tools 與 schemastery)軟連結進外掛,再把掛載區塊附加到 ~/.dsh/config.yaml 並重啟 dsh。DSH Companion 已隨應用內建、零安裝。
支援哪些視覺後端?
任意 OpenAI 相容 VLM:智譜 glm-4.6v-flash(預設免費)、通義 qwen vl 系列、火山豆包、本機 Ollama 等——一套 baseURL+apiKey+model 通吃。本機端點無需 key。
免費方案被限流怎麼辦?
預設設定會自動依序降級 glm-4.6v-flash → glm-4.1v-thinking-flash → glm-4v-flash,確保零設定也能隨時得到答案;可用 fallbackModels 覆寫。
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-router
作者 ysr666
為純文本 DeepSeek Harness 智慧體提供「視覺」能力,內建免金鑰視覺鏈路與畫素級視覺工具,一條命令安裝,無需 Python。
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.
08資料與來源
给纯文本的 DeepSeek 加上眼睛。Vision for text-only DeepSeek.
本插件注册一个 `view_image` 工具:模型带着问题调用它(OCR、数数、读图表、看 UI 布局……任意视觉问题)
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 2026-09-03。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。
