Adding gpt-5 support by updating REASONING_MODELS, MULTIMODAL_MODELS

[rajatkhanduja]

Features

• GPT-5 was recently launched but is not included in the list of reasoning models or multi-modal models.
• This change adds support for the new models.

Influence

• Before this change, when attempting to use GPT-5, the following error would be thrown

2025-08-09 16:09:49.810 | ERROR    | app.llm:ask_tool:756 - OpenAI API error: Error code: 400 - {'error': {'message': "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", 'type': 'invalid_request_error', 'param': 'max_tokens', 'code': 'unsupported_parameter'}}

• With this change, the above issue is addressed and the tool supports call to GPT-5 models.
• Adding both gpt-5 and gpt-5-mini models