Introduction¶

DeepSeek Harness (DSH) adopts a plugin-based architecture. When an agent needs to handle domain-specific logic (for example, calculating odor levels based on parameters and providing recommendations), writing a plugin directly is the most efficient approach. The following section introduces a plugin named dsh-odor-removal.

What Is This¶

dsh-odor-removal is an odor removal tool. This plugin is maintained by developer uckkk. It is mainly used for precise parameter-based calculations and returns clear recommendations. Technically, this is a pure Node.js project with no network requests.

Core Features¶

This plugin registers the following tool:

odor_removal: Odor removal. Performs precise calculations based on parameters and returns clear recommendations.

Installation and Enabling¶

Installing this plugin requires the official command:

dsh plugin add github:uckkk/dsh-odor-removal

Before installation, make sure the environment meets the following dependency version requirements:
* @deepseek-ai/cordis: Version must be ^4.0.1 or higher
* @deepseek-ai/dsh-tools: Version must be >=0.1.0-rc.6 or higher

Typical Usage¶

After installation, you can directly invoke the tool registered by this plugin in a DSH session.

Applicable Scenarios and Notes¶

This plugin is suitable for scenarios that require local calculation and do not need network access. The plugin runs within the permission context of the current DSH process. It is recommended to review the source code and license (MIT) before use.

Short Conclusion¶

This plugin provides a lightweight odor removal solution with clear parameter calculation and recommendation output. To view the source code or submit issues, you can visit its GitHub repository or community directory page.

dsh-odor-removal: Odor Removal Plugin