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 Autoswitch — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-vision-autoswitch

Vision Autoswitch

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

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

npx -y @deepseek-ai/dsh plugin --profile web add dsh-vision-autoswitch@0.1.2
READMECompatibilityVersions

Compatibility and provenance

Vision Autoswitch is published as dsh-vision-autoswitch and currently resolves to version 0.1.2. 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

0.1.2stable
9/2/2026

Related plugins

Loading related plugins…

Latest
0.1.2
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
19.7 kB
Files
6
Surface
any
License
MIT
Source
npm
GitHub
★ 0
Weekly downloads
51
Last push
9/2/2026
View source ↗
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-autoswitch

DeepSeek 的"自动挡":有图切 Vision,无图回 Pro/Flash,一键都不用点。

DeepSeek's "automatic transmission": image in → Vision, image out → back to Pro/Flash — not a single click.

DeepSeek Harness 插件:当输入包含图片时,临时把当前回合切换到视觉模型 deepseek-v4-flash-vision-exp 处理;该回合结束后自动回落到你原来的模型。 模型栏所见即所得(visibleSwitch 默认开启),当前实际模型与 UI 显示始终一致。

A DeepSeek Harness plugin: when a request carries an image, route that turn to the vision model deepseek-v4-flash-vision-exp, then automatically fall back to your original model when the turn ends. The model bar always reflects the actual model in use (WYSIWYG).

功能 / Features

  • 图片 → 视觉模型:当前回合出现图片(用户附件或工具结果里的截图)即切到 deepseek-v4-flash-vision-exp,让图片真正被理解。
  • 回合结束即回落:turn/end 后立即回到你原选的模型,不依赖下一条输入再检测; 长对话也不失灵。
  • 所见即所得:模型栏同步显示切换与回落;实际分发模型与 UI 一致,不会卡在视觉模型。
  • 无需改模型选择:不写入你原本的模型选择,纯文本回合仍由你选的高能力模型承担。
  • 回落目标跟随你的选择:回落回到你当前手动选择的模型(不写死某个模型)。

工作原理 / How it works

  1. 在 agent/request 阶段检测当前回合是否含图(contentHasImage),含图则把 provider/model 改写为视觉模型;
  2. 按会话记住最近一次「非视觉模型」作为回落目标(避免被视觉请求头污染);
  3. 监听 turn/end,回合结束后写入 model/selection 恢复原模型。

安装 / Install

把插件装入 profile 的 node_modules,并在该 profile 的 cordis.patch.yml 追加:

- insert:
    - id: vision-autoswitch
      name: 'dsh-vision-autoswitch'

profile 默认 patchReload: live,保存后约 1 秒热重载;改插件代码需重启 DSH Desktop。

配置 / Config

字段默认值说明
enabledtrue总开关
visionProviderdeepseek-official视觉模型所属 provider
visionModeldeepseek-v4-flash-vision-exp视觉模型
providers["deepseek-official"]允许拦截的 provider
visibleSwitchtrue模型栏跟随切换/回落(所见即所得)

License

MIT