DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Vision Proxy Route — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-vision-proxy-route

Vision Proxy Route

DeepSeek Harness plugin: a configurable provider route that transcribes pasted images via free Zhipu GLM vision models before delegating to a text-only adapter.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add dsh-vision-proxy-route@0.1.4
READMECompatibilityVersions

Compatibility and provenance

Vision Proxy Route is published as dsh-vision-proxy-route and currently resolves to version 0.1.4. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
npm
Registry updated
9/20/2026

Versions

0.1.4stable
9/5/2026
0.1.3stable
8/26/2026
0.1.2stable
8/19/2026
Show 2 more versionsCollapse versions
0.1.1stable
8/19/2026
0.1.0stable
8/17/2026

Related plugins

Loading related plugins…

Latest
0.1.4
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
31.7 kB
Files
6
Surface
any
License
MIT
Source
npm
GitHub
★ 3
Weekly downloads
85
Last push
9/5/2026
View source ↗Project homepage ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIVision Toolkit@anionex/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.Deepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

README

dsh-vision-proxy-route — 贴图自动转译路由(vision-route 包)

给 DeepSeek Harness(DSH)注册一个自动识图包装路由:声明图像输入(inputModalities: ['text','image']), 粘贴到 Web GUI 的图片在请求流里被免费的智谱 GLM 视觉模型(glm-4v-flash 降级链)转译成文字,再委派给真正的 目标适配器。默认是 deepseek-official → deepseek-vision,也可包裹火山方舟等自定义 provider。 完整说明见仓库根目录的 README。

安装(发布后)

dsh plugin --profile web add dsh-vision-proxy-route

或在 profile 的 cordis.patch.yml 中追加:

- insert:
    - id: dsh-vision-proxy-route
      name: dsh-vision-proxy-route

前提

  • DSH 0.1.0-rc.8、0.1.1-rc.1 或 0.1.1-rc.2(均通过一次性 Web Profile 安装、启动与卸载验收)
  • 智谱 GLM 免费 key:环境变量 GLM_API_KEY 或 ZHIPU_API_KEY(Windows 也可 setx GLM_API_KEY "id.secret",插件自动读注册表)

插件通过 DSH 注入的 llm / attachments 服务使用结构化 adapter 契约,不安装或直接导入 @deepseek-ai/dsh-llm、@deepseek-ai/dsh-attachment 等官方运行时包。

权限与证据边界

  • 只通过 DSH attachments 服务读取当前请求或明确追问引用的图片,并只向固定的智谱 HTTPS 端点 发送图片字节。
  • 只读取 GLM 环境变量;Windows 环境变量缺失时使用固定参数执行系统自带的只读 reg query, 不使用 shell 字符串,也不记录或持久化 Key。
  • 无 npm 运行依赖和安装期生命周期脚本;只新增 dsh-vision-proxy-route Entry ID,不写 DSH Profile 或替换官方组件。完整边界见 SECURITY.md。
  • 已验证三个声明版本的一次性 Web Profile 安装、配置合成、冷启动和卸载;rollback、真实用户 Profile、带真实 GLM Key 的端到端结果、Windows 运行和独立安全审计仍未验证。下一验收门槛是 推送固定 Commit 后取得公开 CI 运行记录;这些低层证据不会被表述成真实 Profile 或安全审计通过。

使用

模型选择器切到「DeepSeek + 自动识图」,直接粘贴图片/截图并附带问题即可。后续可用“这张图” “上一张”“第一张”或“两张图对比”等方式追问;路由会在有限的最近用户轮次内选择对应 attachment, 带上本次问题重新分析,并按顺序编号后注入当前消息。弱指代只关联紧邻图片,无关的“登录页面” 或“这个问题”不会触发旧图重传。主模型不需要 DSH 内部绝对路径,用户也无需重复上传图片。

视觉描述会被标成不可信观察数据;图片里的命令或提示词只作为可见文字,不会成为下游模型指令。 临时网络、Key 或限流错误不会进入缓存,恢复后同一问题可以直接重试。

转译失败会替换为 [图片转译失败: ...] 文本,对话不卡死。

自定义 provider

目标 provider 须先在 DSH 中配置并可正常完成纯文本请求。然后为本插件设置:

- insert:
    - id: dsh-vision-proxy-route-ark
      name: dsh-vision-proxy-route
      config:
        targetProvider: volcengine-ark
        provider: volcengine-ark-vision
        displayName: 火山方舟 + 自动识图
config默认值说明
targetProviderdeepseek-official真正处理转译后文字请求的 provider
providerdeepseek-vision新包装路由的 ID,必须与目标不同
displayNameDeepSeek + 自动识图模型选择器显示名称;自定义目标时默认使用 <targetProvider> + 自动识图

包装路由会在模型枚举、模型解析、重试策略和流请求阶段把自身 provider 映射回 targetProvider, 因此可委派给 dsh-llm-pi-ai 这类同时服务多个 provider 的适配器。