WorkBuddy Custom Model Setup Guide
Step 1: Preparation
Before you start, prepare your TaoDock API key, sufficient account quota and an exact model ID from the model catalog. See the quick start if this is your first integration.
Install the desktop application from the WorkBuddy website and sign in. Configure a TaoDock model inside WorkBuddy as follows.
Add the TaoDock model
- Open Settings → Model → Custom Models → Add Model. You can also open custom model configuration from the conversation's model selector.
- Choose Custom as the provider and enter the values below.
- Save, return to the conversation, and explicitly select the new entry in the Custom Models group when you want to use TaoDock.
| Setting | Value |
|---|---|
| Provider | Custom |
| URL | https://taodock.com/v1 |
| API Key | Your TaoDock API key |
| Model name / Model ID | gpt-6.1-sol, or an exact chat model ID available to your key |
| Custom protocol | Off, using default Chat Completions path completion |
This produces https://taodock.com/v1/chat/completions. If Custom protocol is on in advanced settings, enter the complete URL https://taodock.com/v1/chat/completions instead of the base address. See the official URL handling rules.
Follow Figure 1: From top to bottom, select Custom (自定义), enter https://taodock.com/v1, paste your API key, and enter gpt-6.1-sol. Keep Custom protocol (自定义协议) unchecked, confirm supported capabilities, and click Save (保存). Then select the saved model in the conversation's model selector.
Start using it
Send “Reply only: connection successful,” then try the first Agent task. Configure tool calling and image input according to the model's actual capabilities; a connection check does not validate every capability.
Add and save each additional model using its exact ID. If custom model configuration is absent, check that you are using a desktop version supporting it. The current mobile application cannot add custom models; see its model guide. See WorkBuddy's desktop model configuration for the interface.
Verify a real request
Select a model under the TaoDock connection and send a short test message. Confirm that a normal response arrives and that a matching request appears in TaoDock request logs. Loading a model list verifies model discovery; sending a message may consume quota.
For Agent workflows, also follow the file tool verification. A normal text reply alone does not establish tool support.
Troubleshooting
| Symptom | What to check |
|---|---|
| HTML response or 404 | Use the API domain, check protocol selection and avoid duplicated version or endpoint paths |
| 401 or invalid key | Copy your complete, active TaoDock API key |
| Missing or unavailable model | Copy the exact model ID and check key restrictions and the selected group |
| Insufficient quota | Check both the account balance and API key quota |
| Chat works but tools fail | Verify the protocol, model capability and the application's tool permissions |
Return to all client integration guides or see the FAQ for more help.