
DeepSeek Harness 视觉插件:让纯文本模型拥有视觉能力 / Vision plugin for DSH: vision_analyze tool + automatic image transcription for text-only models.
Install Dsh Vision Plugin
Every command below is generated from this repository’s own package.json.
Not checked — and that is not the same as fine
package.json for this repository, so none of the publish spec rules could be applied. We do not know whether dsh plugin add activates anything here.Best-effort git install — unverified, may activate nothing
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:Xin-Zhang-IceMan/dsh-vision-plugin
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profileStep 2 is the one that matters here: if --dump-config shows no new layer after the install, this repository is not a bundle and there is nothing to activate.
Before you run it
- A plugin runs with your permissions once loaded: it can read your files, use your credentials and reach the network. Tool approvals do not sandbox it.
- Installing from git resolves a moving branch. Pin a commit —
github:Xin-Zhang-IceMan/dsh-vision-plugin#<commit-sha>— so the code you reviewed is the code you install.
Prerequisites
- API key
- Not determined from the README.
- Network access
- Not determined from the README.
- Language
- JavaScript
Install check
Every field the verdict was derived from, so you can re-derive it yourself
No check record is stored for this entry yet. That is why its verdict is Not checked — nothing was verified, which is not the same as nothing being wrong.
- Checked at
- Never — this entry has not been checked.
Topics
GitHub topics on this repository
More in Text Only Vision Model
Ranked by similarity inside the cluster, not alphabetically
Dsh Sfversion
sparkmio
SF视觉桥——给纯文本模型的 DeepSeek Harness 装上眼睛。
Dsh Vision
xiaoshihou514
DeepSeek Harness: vision
Dsh Plugin Vision
MoneShadow
一个可以让没有视觉的大模型拥有视觉能力的插件(当然,是通过外挂视觉模型实现的)
Dsh Vision Recognizer
kaixinbaba
DeepSeek Harness 识图插件:保持 DeepSeek 对话,15+ 供应商视觉模型把图片转译为文字,可在 设置→插件 配置
Dsh Vision Bridge
ximengxiaolan
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
Dsh Vision
Terry12138qy
DeepSeek Harness 识图插件:为不具备原生识图能力的模型提供识图能力(阿里云百炼 qwen3.5-omni-plus,失败自动切换智谱 glm-4.6v-flash)。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness