Remove OpenAI models & add Magistral model

Enable Mistral Large model & Disable GPT-5

Implement streaming support validation in completion endpoint and enhance error handling for unsupported models. Update LLMService to include streaming capability check for models, specifically marking 'gpt-5' as non-streaming. Adjust API documentation for clarity on error responses.

Update model references in enums and models to replace GPT-5 Mini with GPT-5 Chat, reflecting the latest model naming conventions and ensuring consistency across the LLMService.

Remove large PDF files and add .gitignore to respect HuggingFace Spaces 10MB limit

Refactor LLMService to handle model-specific parameters for OpenAI's `gpt-5`, using `max_completion_tokens` instead of `max_tokens` and ensuring temperature is set to 1.0 when required.

Enhance LLMService to coerce temperature to 1.0 for OpenAI models that do not support custom values, specifically for `gpt-5` models, to prevent API errors.

Update model references from GPT-5 Pro to GPT-5 across enums, models, and service files, and adjust agent registry to use the history-enabled graph creation function.

Update LLMService to correct model descriptions for GPT-5 Pro and GPT-4

FIrst Commit