Use prebuilt CPU wheel index for llama-cpp-python

Bump llama-cpp-python to 0.3.29 to support minicpm3

Revert llama-cpp-python to 0.2.90 to support Nemotron model architecture

Fix requirements.txt structure and pin llama-cpp-python to CPU pre-built version 0.2.62

Update requirements.txt

Update requirements.txt

refactor: remove experimental test files and enable production mode in Dockerfile

refactor: replace FastAPI/Static setup with custom Gradio UI and update task generation with grammar-enforced inference and semantic repetition checks.

docs: update project documentation to reflect fine-tuned model integration and remove standalone model dependencies

feat: add environment variable support and expand grammar allowed character set

feat: harden Step-Zero demo runtime and trace export