Replace Novita AI with ZeroGPU Chat API (RunPod)

Update token allocation for DeepSeek R1 128K context window - Set NOVITA_MODEL_CONTEXT_WINDOW to 128000 (128K tokens) - Increase USER_INPUT_MAX_TOKENS to 32000 - Increase CONTEXT_PREPARATION_BUDGET to 115000 - Increase CONTEXT_PRUNING_THRESHOLD to 115000 - Update validators to support larger token limits

Fix max_tokens calculation to respect model context window (5000 tokens) - Add dynamic max_tokens calculation based on input size - Add novita_model_context_window configuration - Prevents 400 errors when input tokens exceed available output space

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

Fix: Cache directory permissions and gated repository handling

Update model IDs to use Cerebras deployment and add gated repository error handling

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

Initial commit: Research AI Assistant API