Replace Novita AI with ZeroGPU Chat API (RunPod)

Integrate Novita AI as exclusive inference provider - Add Novita AI API integration with DeepSeek-R1-Distill-Qwen-7B model - Remove all local model dependencies - Optimize token allocation for user inputs and context - Add Anaconda environment setup files - Add comprehensive test scripts and documentation

Phase 1: Remove HF API inference - Local models only

Add initialization diagnostics and background initialization

Improve orchestrator initialization error handling and diagnostics

Security Enhancements: Production WSGI, Rate Limiting, Security Headers, Secure Logging

Add context mode endpoints (fresh vs relevant) and update API documentation

Add input validation for chat endpoint - length limits and type checking

Initial commit: Research AI Assistant API