supersealwqas/dsh-custom-provider-settings1

dsh-custom-provider-settings

Request headers, image input, and reasoning settings for custom DeepSeek Harness providers

AI Analysis

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+。

Package
dsh-custom-provider-settings
Version
0.4.0
License
MIT
Last updated
Aug 17, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:supersealwqas/dsh-custom-provider-settings

Usage

  1. Open Settings > Models.
  2. Edit a provider carrying the Custom tag that already contains a model, or choose Add provider > Add a custom provider and enter its models.
  3. In the inserted Request headers area, enter a User-Agent and any other headers required by the endpoint. Leave the fields empty to retain the Harness defaults.
  4. 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.
  5. Select the enabled reasoning levels and enter the exact API value for each one. Choose a default level if required.
  6. Use the original Apply or Create provider button. The plugin saves its fields after the Harness form succeeds.
  7. 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.