Kilo Code

Kilo Code is an open-source AI programming assistant that supports two usage modes: the VS Code extension and the CLI.

Prerequisites

• You have activated a TCB environment and obtained the environment ID cloudBaseEnvID.

• Enable the required model in the AI console.

• Obtain the Base URL and API Key in the AI console.

Configuration Steps

Kilo Code provides both an IDE extension and a CLI tool. If you have installed Kilo CLI, you can add or modify the provider through the model configuration file.

IDE Plugin

The example uses VS Code.

1. Open VS Code, click the Kilo Code icon in the sidebar, click the settings icon at the top of the panel, go to the Model settings, select Custom provider, and click Connect.

2. Fill in the custom large model configuration.

The meanings of each field are as follows:

Field to Enter	Explanation
Provider ID	The vendor ID, which can be any value. In the screenshot example, cloudbase is entered for distinction.
Display name	The display name, which can be any value. In the screenshot example, cloudbase is entered for distinction.
BaseURL	The Base URL for the large model, which is obtained from the AI console.
API key	The API key for calling the large model, which is obtained from the AI console.
models.ID	The large model ID. Copy the identifier of an enabled large model from the model list in the AI console and enter it here.
models.Name	The display name of the large model, which can be filled in arbitrarily.

3. Click Save, select the custom model you added from the conversation model list, and then you can start a conversation.

Via Model Configuration File

1. Open the configuration file.

note

If you use your file browser to locate files, note that the file browser hides files with names starting with a period (.) by default. You may need to enable the hidden files option in your file browser to view them.

On macOS, use the Finder shortcut Command + Shift + . to show hidden files. On Windows, you can select "File Explorer - View - Show - Hidden items". Open.

• Configuration Path for Windows

C:\Users\<YourUsername>\.config\kilo\kilo.jsonc

• Configuration Path for Mac/Linux

~/.config/kilo/kilo.jsonc

2. Edit or add the provider field.

Field	Explanation
Subfield name of the provider object	The vendor ID, which can be any value. In the example, cloudbase is entered for distinction.
provider.cloudbase.name	The display name, which can be any value. In the example, cloudbase is entered for distinction.
provider.cloudbase.options.baseURL	The Base URL for the large model, which is obtained from the AI console.
provider.cloudbase.options.apiKey	The API Key for calling the large model, which is obtained from the AI console.
Subfield name of the provider.cloudbase.models	The large model ID. Copy the identifier of an enabled large model from the model list in the AI console and enter it here.
provider.cloudbase.models.hy3-preview.name	The display name for the large model

{
  "provider": {
    "cloudbase": {
      "name": "cloudbase",
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://{{cloudBaseEnvID}}.api.tcloudbasegateway.com/v1/ai/cloudbase",
        "apiKey": "eyJhbGciOiJSUzI1..."
      },
      "models": {
        "hy3-preview": {
          "name": "hy3-preview"
        }
      }
    }
  }
}