Add GPT-5.x models with reasoning model warnings

[bharatsb]

This PR adds support for the new GPT-5.x model family and implements warning functionality for reasoning models that cannot have token usage pre-estimated.

https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure

New Models Added

• gpt-5.1: 272,000 tokens (reasoning model)
• gpt-5.1-chat: 111,616 tokens (reasoning model)
• gpt-5.2: 272,000 tokens (reasoning model)
• gpt-5.2-chat: 111,616 tokens (standard model)

Motivation and Context

Added support for new GPT-5.x model family

How Has This Been Tested?

Tested locally

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed