WorkBuddy/CodeBuddy

WorkBuddy/CodeBuddy is one of Tencent's AI agent and coding assistant. Although WorkBuddy/CodeBuddy supports custom models through local configuration files, pointing it to Tresor gives you:

• Centralized management of different models and providers. No need to re-configure WorkBuddy when you switch LLM providers, just change the activated model in the alias group of Tresor.
• No need to worry about the different API format underlying model is using, Tresor will auto-translate between the OpenAI Chat Completion API (WorkBuddy) to other API formats (e.g., Anthropic messages for Claude models).

However, it also comes with drawbacks:

• If you use alias to map model names in Tresor, it will lead to less precise control over model-specific configurations, like the reasoning effort and context length.

This page shows how to wire WorkBuddy/CodeBuddy to Tresor.

✅ Prerequisites

• Installed Tresor following installation guide.
• WorkBuddy/CodeBuddy installed.

1. Configure Tresor

There are two ways to prepare Tresor:

1.1 Option 1: via Web UI

Web UI is more intuitive, but require more manual operations.

1. In "Downstreams" tab

   • Click + Add Provider to add the LLM provider you are about to use.

2. In "Aliases" tab

   • Click + New Alias Group
     • Input Model ID: model-workbuddy
     • Leave "Regex Pattern" unchecked.
     • Select the Downstream and Output Model IDs you added previously.
   • (Optional) Repeat the above steps to add model-codebuddy.

3. In "Settings" tab

   • Click + Add API Key under "Proxy Authentication" section (e.g, sk-proxy-123). Copy it, and we are about to fill it into apiKey in the following section.

1.2 Option 2: via config.yaml

Editing yaml is less intuitive, but require less manual operations.

The following example config.yaml uses 3 downstream providers. Replace them based on your actual providers.

~/.config/tresor/config.yaml

bind_addr: 127.0.0.1:11510
proxy_api_keys:
  - sk-proxy-123
... # Omitted showing other settings here
downstreams:
    - id: llama-cpp
      name: llama.cpp
      base_url: http://127.0.0.1:3000 # change to your actual llama.cpp listening port
      api_formats:
        - openai
        - anthropic
      output_model_ids:
        - qwen3.6:27b-mtp:instruct
    - id: deepseek
      name: DeepSeek
      base_url: https://api.deepseek.com/anthropic
      api_formats:
        - anthropic
      output_model_ids:
        - deepseek-v4-flash
        - deepseek-v4-pro
    - id: minimax
      name: MiniMax
      base_url: https://api.minimaxi.com/anthropic
      api_formats:
        - anthropic
      output_model_ids:
        - MiniMax-M2.5
        - MiniMax-M2.7
        - MiniMax-M3
aliases:
    - input_model_id: model-codebuddy
      options:
        - id: alias-deepseek-pro
          downstream_id: deepseek
          output_model_id: deepseek-v4-pro
        - id: alias-minimax-m3
          downstream_id: minimax
          output_model_id: MiniMax-M3
    - input_model_id: model-workbuddy
      options:
        - id: alias-deepseek-flash
          downstream_id: deepseek
          output_model_id: deepseek-v4-flash
        - id: alias-minimax-m2-7
          downstream_id: minimax
          output_model_id: MiniMax-M2.7
        - id: alias-llama-cpp-qwen-instruct
          downstream_id: llama-cpp
          output_model_id: qwen3.6:27b-mtp:instruct

CodeBuddy is more programming-oriented, while WorkBuddy is for general everyday tasks. Therefore, the example config use more powerful models for CodeBuddy by default. Adjust per your need.

Restart Tresor to apply the changes in yaml.

2. Configure WorkBuddy/CodeBuddy

WorkBuddy/CodeBuddy supports custom models through local models.json configuration files. Point it at your Tresor instance:

Create or edit the user-level configuration file:

C:\Users\<your-username>\.codebuddy\models.json

To apply the configuration only to one project, create the project-level configuration file instead:

<your-project>\.codebuddy\models.json

Then add the following configuration:

~/.codebuddy/models.json

{
  "models": [
    {
      "id": "model-workbuddy",
      "name": "model-workbuddy",
      "vendor": "Tresor",
      "url": "http://127.0.0.1:11510/v1/chat/completions",
      "apiKey": "sk-proxy-123",
      "maxInputTokens": 262144,
      "maxOutputTokens": 32000,
      "supportsToolCall": true,
      "supportsImages": true,
      "relatedModels": {
        "lite": "model-codebuddy",
        "reasoning": "model-workbuddy"
      }
    },
    {
      "id": "model-codebuddy",
      "name": "model-codebuddy",
      "vendor": "Tresor",
      "url": "http://127.0.0.1:11510/v1/chat/completions",
      "apiKey": "sk-proxy-123",
      "maxInputTokens": 262144,
      "maxOutputTokens": 32000,
      "supportsToolCall": true,
      "supportsImages": true
    }
  ],
  "availableModels": [
    "model-workbuddy",
    "model-codebuddy"
  ]
}

Note: Save models.json as UTF-8 without BOM. Some desktop versions may fail to read local model configuration files saved with a UTF-8 BOM header.

3. Restart and Select the Model

Fully quit WorkBuddy/CodeBuddy, then open it again.

In the model selector, choose:

model-workbuddy

WorkBuddy/CodeBuddy will send the model name model-workbuddy to Tresor, which will forward the request to the active downstream for that alias.

4. Hot-switch from the web UI

Open http://127.0.0.1:11510 in a browser, go to the Aliases tab, and click any sibling option card to make it active. WorkBuddy/CodeBuddy's next request will be routed to the new downstream — no restart of either Tresor or WorkBuddy/CodeBuddy is required. 🎉

For example, flip model-workbuddy from deepseek-v4-pro to MiniMax-M3 with a single click, and the agent immediately starts using MiniMax on the following turn.

🔧 Troubleshooting

Symptom	Likely cause	Fix
Authentication Fails or 401 from Tresor	proxy_api_keys is set but apiKey doesn't match	Set apiKey to one of the keys in proxy_api_keys, or empty the list in config.yaml

📚 See also

• DeepSeek guide for WorkBuddy/CodeBuddy