dsh-model-modality
Manifest validDeclare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.
dsh-model-modality
DeepSeek Harness 插件:声明第三方模型(中转站 / 自定义提供方)是否支持图像(多模态)输入。
它做什么
DSH 运行时对图像的门禁(消息图片、read_image 工具、附件上传、子代理图像提示)都依赖模型元数据中的 inputModalities。本插件让用户直接声明某模型的输入模态,并把声明写入拥有该模型的提供方设置:
llm-deepseek(官方 / 自定义 baseURL)→models[].inputModalitiesllm-pi-ai(第三方提供方目录)→models[].input或modelOverrides[].input
写入后立即通过 llm.resolveModelInfo 校验,因此声明生效后:
- 该模型可以接收图片消息(不再被
Model does not support image input拦截); read_image等图像工具被放行;- 底层流调用不再把图片投影成文本。
声明的持久化位于提供方自己的设置(DSH 的 Models 设置页可查看/编辑),与插件本身互不影响。
安装
dsh plugin add ct-jyjntc/dsh-model-modality
安装后可用两个工具(对话中直接让 agent 调用):
declare_model_multimodal(provider, model, supportsImage)— 声明某模型是否支持图像输入,返回写入与校验结果;list_model_multimodal(provider?, model?)— 列出各可配置提供方模型的输入模态。
浏览器端 UI(可选)
设置 → 模型 → 每张提供方卡片内的「多模态(图像输入)」开关,以及 Run 卡片面板,需要会话级动态插件挂载(客户端模块未随本包发布)。需要时让 agent 挂载即可。
示例
declare_model_multimodal(provider="raincode", model="kimi-k3", supportsImage=true)
→ { ok: true, verified: true, inputModalities: ["text","image"], ... }
License
MIT
Comments
Loading…
Similar plugins
by TikaFlow
Auto-fills reasoning-efforts, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev. Also provides setting cards to control plugin'
★ 19
MIT
TypeScript
Oct 24, 2026
dsh plugin --profile web add dsh-model-fixDSH plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name
★ 0
dsh plugin --profile web add dsh-model-metadataby GaoHu1997
Third-party model settings for DeepSeek Harness: pick a provider and a model in the composer menu, gate a model's thinking level with one switch on the official Models page card, and configure per-rou
★ 4
↓ 838/wk
MIT
TypeScript
Oct 27, 2026
dsh plugin --profile web add dsh-model-think-levelby nexsjournal
Installs an image-input checkbox into the Models catalog so a custom model can declare image input and receive images directly; includes an optional BYO vision relay.
★ 3
↓ 60/wk
MIT
JavaScript
Aug 16, 2026
dsh plugin --profile web add dsh-vision-pluginby Kazusa1085
DSH插件:提供“模型能力”设置页面,用于声明模型输入模态、上下文窗口、输出上限及图像配额,无需手动编辑 `settings.yaml` 文件。
★ 0
MIT
JavaScript
Sep 9, 2026
dsh plugin --profile web add dsh-awesome-model-settingby WJZ-P
Adds an input-modality selector to custom model settings in the DeepSeek Harness Web UI.
★ 4
↓ 142/wk
MIT
JavaScript
Aug 19, 2026
dsh plugin --profile web add dsh-model-capability