dsh-llm-codebuddy
Run the following command in DeepSeek Harness:
dsh plugin install Axiaohungry/dsh-llm-codebuddy
Paste the following prompt into your AI chat to install this plugin:
Install the dsh-llm-codebuddy plugin in DeepSeek Harness from https://github.com/Axiaohungry/dsh-llm-codebuddy.
About this plugin
dsh-llm-codebuddy makes it easier to use CodeBuddy China models inside DeepSeek Harness by registering CodeBuddy China as a provider and handling the configuration flow through the DSH WebUI. Instead of manually wiring up authentication and model catalogs, users can add the provider and manage it within DSH.
The plugin supports two credential paths: a WorkBuddy API key or CodeBuddy China site token login. Token login can open the official web authentication flow, then reuse and refresh the token automatically. It can also fetch available models, edit model IDs, names, context windows, and maximum output tokens, maintain custom catalogs, and expose model-specific reasoning levels declared by the model catalog. If the remote catalog is unavailable, a built-in fallback keeps basic configuration working.
This is a good fit for developers or teams who want to run CodeBuddy China model inference through DSH while keeping provider setup, model selection, and credential modes manageable in the WebUI. It is a third-party adapter, not an official plugin from WorkBuddy, CodeBuddy, or DSH.
Screenshots
Use Cases
- Add and configure CodeBuddy China in the DSH WebUI.
- Use a WorkBuddy API key or CodeBuddy China token to authenticate.
- Edit model catalogs, context windows, and maximum output limits.
Best For
- Developers who want to use CodeBuddy China models in DSH.
- Users who need to manage model catalogs through the WebUI.
- Teams that want flexible switching between API keys and token login.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.