bug: calling o1 or o3 causes NeMo to use deprecated chat completion API

[Headless-Sourceman]

Did you check docs and existing issues?

• I have read all the NeMo-Guardrails docs
• I have updated the package to the latest version before submitting this issue
• (optional) I have used the develop branch
• I have searched the existing issues of NeMo-Guardrails

Python version (python --version)

Python 3.10.11

Operating system/version

Microsoft Windows 11 Enterprise

NeMo-Guardrails version (if you must use a specific version and not the latest

0.11.1

Describe the bug

Trying to use Azure OpenAI o3-mini (or any o1 model) causes a bad request error.

Steps To Reproduce

1. Put this model into config.yml

type: main
    engine: azure
    model: o3-mini
    api_version: 2024-12-01-preview
    ...

2. Start a chat with
   nemoguardrails chat --config your/path --verbose --debug-level=DEBUG

3. Ask anything that uses the main model.

Expected Behavior

Receive a chat completion without error.

Actual Behavior

HTTPStatusError: Client error '400 Bad Request' for url
                             'https://...openai.azure.com/openai/.../o3-mini/completions?api-version=...'

Stack trace ends with
nemoguardrails.actions.llm.utils.LLMCallException: LLM Call Exception: Error code: 400 - {'error': {'code': 'OperationNotSupported', 'message': 'The completion operation does not work with the specified model, o3-mini. Please choose different model and try again. You can learn more about which models can be used with each operation here: https://go.microsoft.com/fwlink/?linkid=2197993.'}}