WorkBuddy family
Configure WorkBuddy for your enterprise and verify the request in your console logs.
Configuration
Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model
- In the WorkBuddy desktop app, open Settings → Models → Add Model and choose Custom as the provider.
- Enter the full Chat Completions endpoint, the enterprise API key and the authorized model ID, then save.
- In CodeBuddy IDE, add an OpenAI-compatible model in model settings and enter the full request URL. For CodeBuddy Code, merge the example into ~/.codebuddy/models.json and have your secret manager inject the environment variable.
- For LearnBuddy, confirm that your enterprise edition exposes custom models and check how it handles endpoint URLs and credentials.
| API protocol | Address to enter |
|---|---|
| Chat Completions | Full URLhttps://tokenpyxis.com/v1/chat/completions |
{
"models": [
{
"id": "YOUR_CHAT_MODEL_ID",
"name": "Token Pyxis",
"vendor": "Token Pyxis",
"url": "https://tokenpyxis.com/v1/chat/completions",
"apiKey": "${TOKEN_PYXIS_API_KEY}"
}
]
}Verification
Select the custom model in WorkBuddy or CodeBuddy. Verify a short text reply before testing any image or tool features that your workflow uses.
Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps
Troubleshooting
On a 404, check that the API address includes the full /v1/chat/completions path. If the custom provider option is missing, check the edition and enterprise policy.
