fix: Use invoke() instead of deprecated get_relevant_documents()

fix: Resolve IndentationError in rag.py and restore fallback logic

feat: Inject File Tree context for holistic code understanding

fix: Optimize RAG retrieval and enable streaming

feat: Add Groq-optimized prompts, vector DB fallback, improved ignore patterns

feat: Add runtime Gemini model switching on rate limits - automatically tries next model

feat: Add Gemini 3 preview models to fallback list

feat: Add Gemini model fallback logic - tries multiple models in sequence

fix: Use gemini-2.5-flash as default (confirmed working)

fix: Add models/ prefix to Gemini model names

Refactor: Upgraded to Agentic Chatbot with AST & Call Graph support