Fix CSS: serve self-contained HTML via ASGI wrapper to bypass Gradio

UX overhaul + Gradio migration + remove llama.cpp

Remove llama-cpp-python and lighten Dockerfile; Modal handles inference

Add Modal GPU inference support for faster LLM responses

fix: restore llama.cpp with source build, use fine-tuned GGUF model

refactor: remove llama-cpp entirely, use deterministic mock-only mode

fix: load LLM in background thread so Space stays healthy during 2.84 GB cold start

fix: eagerly load LLM at startup so /api/health surfaces the real error

fix: correct LLM model path default, fix chat 'error: format only' leak, surface load errors

feat: browser-local engine, Zerodha dashboard, historical events, chatbot, per-user isolation

fix: harden LLM calls, cast numpy to native floats, pin llama-cpp-python wheel

fix: accept percent value (0-100) for trades, add MOCK_LLM flag, full Playwright E2E

fix: resolve asset name mismatch, add E2E tests, 10-year game loop

fix: serve static files, switch to FastAPI, add CRT terminal styling

Use uvicorn for Space deployment; pin model filename

Add model download, split requirements, prepare for Modal training

Phase 2/3: Gradio Server backend, CRT frontend, engine, agents, mentor, tests, CI/CD