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 Opencode — DSH Plugin for DeepSeek Harness
← Plugins
V

dsh-vision-opencode

Vision Opencode

DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:poiuyjie/dsh-vision-opencode#1ab7e5502b969c20d38e7d269ed1f1c4d8aa3e24
READMECompatibilityVersions
dsh-vision-opencode 演示

Compatibility and provenance

Vision Opencode is published as dsh-vision-opencode and currently resolves to version 0.4.4. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
9/9/2026

Versions

0.4.4stable
9/9/2026
0.4.3stable
8/30/2026
0.4.2stable
8/22/2026
Show 1 more versionCollapse versions
0.4.0stable
8/20/2026

Related plugins

Loading related plugins…

Latest
0.4.4
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 13
Weekly downloads
0
Last push
9/9/2026
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
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

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 CLIDeepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Imagegen@dickpy/dsh-imagegenAI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana a

README

dsh-vision-opencode

中文 | English

DeepSeek 不认图?OpenCode 多模态平替方案:给纯文本主模型加一个可配置的识图模型。

dsh-vision-opencode 演示

它能做什么

  • 聊天里发图 → 先交给视觉模型(如 MiMo-V2.5)转成文字,主模型照常回复,不用换模型
  • 输入框右侧「识图模型」下拉,自动列出所有供应商中支持图片的模型
  • 设置 → Vision 独立管理模型;vision_read_image 工具 / vision-image-analysis skill 支持 OCR、图表、截图理解
  • 异常兜底:单次 60s 超时、失败重试 1 次、重试耗尽降级为占位文本,不拖垮回合

安装

方式一(DSH 原生,推荐):

dsh plugin --profile web add -w github:poiuyjie/dsh-vision-opencode

方式二:一键脚本(Ubuntu install.sh / Windows install.ps1):

curl -fsSL https://raw.githubusercontent.com/poiuyjie/dsh-vision-opencode/main/scripts/install.sh | bash

装完重启 dsh,在输入框右侧选择识图模型。

卸载:dsh plugin --profile web remove -w dsh-vision-opencode(或 uninstall.sh)。

卸载前先备份包含图片的会话——卸载后这些旧会话可能无法再发给纯文本主模型。

配置

编辑 ~/.dsh/settings.yaml(也可用设置 → Vision 图形化管理):

vision-opencode:
  provider: ''       # 识图模型供应商;空 = 未选择
  model: ''          # 识图模型 id;空 = 未选择
  autoConvert: true  # 发图自动转换开关;出问题可改 false 关掉

插件自动识别纯文本主模型并接管图片;原生多模态模型保留 DSH 原生链路,无需改模型目录。

渠道状态圆点

设置 → Vision 的渠道(提供方分组)名称旁有状态圆点,与官方「模型」页同款:

  • 🟢 已配置 API 密钥(宿主路由的 apiKeyEnv 或插件写入的 <PROVIDER>_API_KEY 任一可用即绿)
  • 🔴 明确未配置密钥
  • 不显示 = 状态未知(凭据服务不可用等)

识图模型的推理关闭

设置 → Vision 里每个模型有一行「推理」策略:

选项含义
默认跟随供应商默认档位,正常思考
关闭不思考,更快更省;仅当供应商真实声明 off 时提供(如 hy3 off:"none")
强制关闭尽力关掉思考(如 reasoning_effort:"none"),不保证成功;MiMo 这类未声明 off 的只能选这个

有「关闭」档的模型很少,没有时界面显示「默认 / 强制关闭」并标注「不保证成功」。关掉思考一般能明显降低首 token 延迟和花费(MiMo 实测 reasoning_effort:"none" 可真正关掉)。

推理关闭设置

⚠️ 各供应商对「关闭思考」的声明很混乱(off:"none" / off:null / 无字段各不相同),插件只能尽力按厂商目录区分「关闭」与「强制关闭」并试参数,不保证每个供应商都能真正关掉。

常见问题

  • 只想关掉自动转换(保留工具和选择器):vision-opencode.autoConvert: false 后重启
  • 图片转换异常/选择器不出现:多半是识图模型未选或版本差异,看浏览器控制台报错发 issue
  • 纯文本与多模态主模型自动区分,切换供应商无需再改配置

开发规范

  • 每次推送必须打 tag:git push 前先创建对应版本的 tag 并推送(如 git tag v0.4.0 && git push origin v0.4.0),保证远端每次更新都有可追溯的版本标记。

License

MIT