feat: Add LongCat API as primary model with Qwen fallback + cross-map fix

feat: Add 3-tier quantization with auto hardware detection

Migrate to Local Inference (Qwen-1.5B) to permanently bypass API limits: Re-added Torch/Transformers

Upgrade to Mistral-7B Serverless API for high intelligence

Fix 500 error: Add sentencepiece and optimize speed

Switch to local LLM (TinyLlama)

Initial commit of SEO Analyzer FastAPI