fix: Sage timeout — gunicorn 300s, max_tokens 150, ZeroGPU pattern, correct torch_dtype

fix: replace git transformers with stable release, update torch for Gemma 4 build

Fix Sage/Lens silent failures and model loading on HF Space

Fix HF Space: switch from llama-cpp-python to transformers for better compatibility

Switch to HF Space as default backend, make Ollama optional

Replace cloud inference with local Ollama

feat: add anti-gaming comprehension pipeline and harden HF space integration

Add HF Space model error diagnostics

Switch HF Space to quantized Gemma 2B GGUF

Switch HF Space to transformers backend

Harden HF Space llama-cpp fallback

Add HF Space inference fallback

Fix HF Space llama-cpp startup crash

fix: use pre-built CPU wheel for llama-cpp-python to speed up HF space build

fix: cast model_path and prompt to string to resolve ValueError('not a string')

chore: migrate hf_space to CPU-friendly GGUF via llama-cpp-python

Fix HF Space inference runtime and error handling

Fix HF Space backend contract and production health diagnostics

Update app defaults and database to use US Curriculum Guide, fix HF requirements