supersealwqas/dsh-custom-provider-settings ↗★ 1
dsh-custom-provider-settings
Request headers, image input, and reasoning settings for custom DeepSeek Harness providers
AI 분석
核心用途是扩展自定义 API 渠道的模型兼容性与高级配置。适合需要接入第三方 OpenAI 兼容接口、配置 User-Agent 或启用多模态/推理功能的用户。需要 Node.js 22+。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:supersealwqas/dsh-custom-provider-settingsUsage
- Open Settings > Models.
- Edit a provider carrying the Custom tag that already contains a model, or choose Add provider > Add a custom provider and enter its models.
- In the inserted Request headers area, enter a
User-Agentand any other headers required by the endpoint. Leave the fields empty to retain the Harness defaults. - Under Model capabilities, choose each model's input and reasoning capabilities. Select Text and images only when both the API and model support image input.
- Select the enabled reasoning levels and enter the exact API value for each one. Choose a default level if required.
- Use the original Apply or Create provider button. The plugin saves its fields after the Harness form succeeds.
- Start a new conversation, select the custom model, and choose one of its configured reasoning levels.
Fetch available models uses the request-header values currently entered in the same form, including values that have not been saved yet. This allows model discovery to work with endpoints that require a particular User-Agent or another custom header.