WorkBuddy/CodeBuddy
Tencent's AI coding assistant powered by DeepSeek and other models.
1. Install WorkBuddy/CodeBuddy
- Install and log in to WorkBuddy/CodeBuddy.
- Open your project directory at least once to allow the application to create local configuration directories.
- Go to the DeepSeek Platform to get your API Key.
2. Configure Local Models
Create or edit the user-level configuration file:
C:\Users\<your-username>\.codebuddy\models.json
If you only want the configuration to apply to a specific project, you can create a project-level configuration file:
<your-project>\.codebuddy\models.json
First, set your DeepSeek API Key as an environment variable:
setx DEEPSEEK_API_KEY "<your DeepSeek API Key>"
Then, write the following configuration into models.json:
{
"models": [
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"vendor": "DeepSeek",
"url": "https://api.deepseek.com/v1/chat/completions",
"apiKey": "${DEEPSEEK_API_KEY}",
"maxInputTokens": 128000,
"maxOutputTokens": 8192,
"supportsToolCall": true,
"supportsImages": false,
"relatedModels": { "lite": "deepseek-v4-flash", "reasoning": "deepseek-v4-pro" }
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"vendor": "DeepSeek",
"url": "https://api.deepseek.com/v1/chat/completions",
"apiKey": "${DEEPSEEK_API_KEY}",
"maxInputTokens": 128000,
"maxOutputTokens": 8192,
"supportsToolCall": true,
"supportsImages": false
}
],
"availableModels": [ "deepseek-v4-pro", "deepseek-v4-flash" ]
}
Save models.json as UTF-8 without BOM. Some desktop versions might fail to read local model configurations if the JSON file includes a UTF-8 BOM header.
3. Restart and Select the Model
Completely exit WorkBuddy/CodeBuddy and reopen it. In the model selector, choose DeepSeek V4 Pro or DeepSeek V4 Flash.