WorkBuddy Setup Guide
Using third-party clients
For a more consistent and complete experience, we recommend using each model in its provider’s official client.
Third-party apps update at different speeds and may adapt APIs differently. Compatibility issues can include cache misses, unavailable tools, or request errors. If you encounter a problem, first check the client version, configuration, and model support.
This guide focuses on simple, quick setup for basic use. Advanced features and custom workflows are welcome to explore, but usually require technical knowledge and fall outside our standard support scope. Our support team may offer suggestions where practical, but cannot guarantee troubleshooting or a solution for every issue.
This guide uses WorkBuddy 5.5.6 for Windows to connect to CCTQ through a custom model. Install and sign in to WorkBuddy, and prepare your own token key. The screenshots show the Chinese interface.
1. Open settings
Click your avatar in the bottom-left and select Settings (设置) from the menu.
2. Add a model
Select Models (模型) in the Settings sidebar, then click Add Model (添加模型).
3. Select a custom provider
Open the Provider (供应商) dropdown and select Custom (自定义). This guide uses the OpenAI-compatible API format.
4. Configure the model
Enter the following:
| Setting | Value |
|---|---|
| API URL (接口地址) | https://www.cctq.ai/v1, including /v1 |
| API Key | Your own token key created on CCTQ |
| Model name (模型名称) | Copy it from the CCTQ Model Marketplace, e.g. gpt-6-astra |
Enable Tool Calling (工具调用) and Image Input (图片输入) as shown. Your model and endpoint must support these capabilities. Leave the other options at their defaults, keep Custom Protocol (自定义协议) off, and click Save (保存). You can use Test Connection (测试连接) to check connectivity.
5. Select the model you added
Return to the main screen and open the model selector at the bottom-right of the message box (shown as Fast / 快速 in the screenshot). Choose your model under Custom Models (自定义模型).
6. Send a test message
Send a simple message such as Hello. A normal reply with the selected model shown underneath confirms that basic text conversations are working.
Use a model supported by your key, and keep your real key private. If a request fails, check the API URL, key, and model name.