Add comprehensive GPT model support - Fix issue #475

[Likheet]

• Add support for 5 new GPT model variants:

  • GPT-3.5 Turbo: gpt-3.5-turbo-0125 (16K tokens)
  • GPT-4 Turbo: gpt-4-turbo-2024-04-09 (128K tokens)
  • GPT-4o variants: gpt-4o-2024-05-13, gpt-4o-2024-08-06 (128K tokens each)
  • GPT-4o Mini: gpt-4o-mini, gpt-4o-mini-2024-07-18 (128K tokens each)

• Create robust helper functions in Models class:

  • is_gpt4_model() - Detects any GPT-4 variant including GPT-4o
  • is_high_context_model() - Identifies models with >8K token support
  • get_max_tokens() - Centralized token limit retrieval

• Replace hardcoded model checks across 7 files with centralized functions

• Update model collections with proper token mappings

• Fix type annotations and syntax errors

Resolves #475: '/index chat' command now works with gpt-4o and other new models