AI Agent Hub
Back to plugins
🧰

dsh-model-meta-autofill

Web Tools Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install QJAG1024/dsh-model-meta-autofill

Paste the following prompt into your AI chat to install this plugin:

To install this plugin in DeepSeek Harness, run the command dsh plugin install QJAG1024/dsh-model-meta-autofill, with the full source code available at https://github.com/QJAG1024/dsh-model-meta-autofill.

About this plugin

In DeepSeek Harness (DSH), models configured in custom providers often only have IDs, lacking essential metadata like context window, output limits, and display names, which leads to incomplete interface displays and hinders DSH's capacity scheduling. The dsh-model-meta-autofill plugin solves this by automatically filling in missing metadata from models.dev, a standard model metadata registry, without overwriting user-set values. Its core capabilities include intelligent detection of missing fields, offline indexing, real-time refresh for up-to-date data, and a user-friendly web interface with HTTP endpoints for easy management. This plugin is ideal for developers and advanced users who use custom providers in DSH, offering a way to streamline model configuration, save manual effort, and enhance overall productivity.

Use Cases

  • Automatically fill metadata for custom provider models
  • View and manage model information in the DSH interface
  • Batch update model configurations via HTTP endpoints

Best For

  • Developers using DSH custom providers
  • Users managing metadata for multiple models
  • Advanced users seeking automated model configuration