DeepSeek Harness follows the design philosophy of “everything is a plugin.” When developing agents, it is often necessary to provide precise tool capabilities for specific domains or scenarios. The following introduces dsh-blender, which returns usage plans for small kitchen appliances based on parameters.

Plugin Positioning

This plugin is named “Blender,” and its core function is to return usage plans for small kitchen appliances based on parameters. It is maintained by uckkk, is a pure Node.js implementation, and has no network dependency at runtime. This means it does not rely on external APIs and works stably in offline or intranet environments.

Installation and Activation

  1. Run the official installation command:
   dsh plugin add github:uckkk/dsh-blender
  1. After installation, the tool registered by the plugin automatically appears in the current session, with no additional configuration required.

Core Functionality

The plugin registers a tool named blender. When calling this tool, pass the relevant parameters, and it returns usage plans for small kitchen appliances. As a pure Node implementation, it requires no network request configuration, resulting in efficient execution and good environment compatibility.

Dependencies and Constraints

Before use, ensure that your current environment meets the following dependency version requirements:

{
  "peerDependencies": {
    "@deepseek-ai/cordis": "^4.0.1",
    "@deepseek-ai/dsh-tools": ">=0.1.0-rc.6"
  }
}

The plugin is open-sourced under the MIT license.

Applicable Scenarios

After installing, simply call the tool registered by the plugin in the session. It is suitable for scenarios that require quickly obtaining operational guidance for a specific appliance.

Summary

dsh-blender provides a lightweight way to handle questions related to small kitchen appliances. For more details and source code, refer to the plugin directory or the GitHub repository.