Using Continue with VS Code and Our Lab's AI Server

1. Install Continue Extension

1. Open VS Code
2. Go to Extensions (Ctrl+Shift+X)
3. Search for "Continue"
4. Install the extension by Continue
5. Restart VS Code if prompted

2. Configure Continue

1. Open the Continue sidebar (click the Continue icon in the left sidebar)

2. Click the gear icon to open settings, or manually edit the config file:

   • Linux/macOS: ~/.continue/config.json
   • Windows: %USERPROFILE%\.continue\config.json

3. Replace the contents with:

{
  "models": [
    {
      "title": "Qwen3 Coder Next",
      "provider": "openai",
      "model": "RedHatAI/Qwen3-Coder-Next-NVFP4",
      "apiBase": "https://chat.catholic-u.ai/api/v1",
      "apiKey": "YOUR_API_KEY"
    },
    {
      "title": "Qwen3.5 35B",
      "provider": "openai",
      "model": "Sehyo/Qwen3.5-35B-A3B-NVFP4",
      "apiBase": "https://chat.catholic-u.ai/api/v1",
      "apiKey": "YOUR_API_KEY"
    }
  ]
}

3. Using Continue

Chat

1. Open the Continue sidebar (Ctrl+L)
2. Select a model from the dropdown at the top
3. Type your question or paste code and ask for help

Inline Editing

1. Select code in the editor
2. Press Ctrl+I (or Cmd+I on macOS)
3. Type your instruction (e.g., "add error handling", "refactor this function")
4. Continue will suggest edits inline

Code Autocomplete

Continue can provide tab-autocomplete suggestions. To enable:

1. Open config.json
2. Add a tabAutocompleteModel section:

{
  "models": [
    ...
  ],
  "tabAutocompleteModel": {
    "title": "Qwen3 Coder Autocomplete",
    "provider": "openai",
    "model": "RedHatAI/Qwen3-Coder-Next-NVFP4",
    "apiBase": "https://chat.catholic-u.ai/api/v1",
    "apiKey": "YOUR_API_KEY"
  }
}

Useful Keyboard Shortcuts

4. Tips

• Select code before asking: Highlight relevant code, then press Ctrl+L to include it as context in your chat.
• Use @file to reference files: Type @filename in the chat to include a file as context.
• Switch models: Use the model dropdown at the top of the chat sidebar to switch between Qwen3 Coder Next and Qwen3.5 35B.

5. Troubleshooting

• "Could not connect" error: Make sure you are connected to the university network or VPN.
• No models in dropdown: Verify your config.json is saved correctly and restart VS Code.
• Slow responses: The server is shared — response times may vary depending on load.