feat: Variet Engine v1.0 + 5-model tuning complete

Phase 01 (LLM Tuning):
- Gemma4 26B: 74.65 t/s (fast)
- Qwen 35B: 61.62 t/s (balanced)
- Gemma4 31B: 16.0 t/s (deep-coder)
- Qwen 27B: 16.7 t/s (deep-logic)
- Qwen 122B: 8.95 t/s (ultra, GPU 1 only)

Phase 02 (API Engine):
- FastAPI reverse proxy on port 8000
- /engine/switch hot-swap with 503 protection
- config/engine_models.json as single source of truth
- Replaced 4 individual .bat files with unified engine

File cleanup:
- scripts/ 85 files -> 9 + _archive/
- Root .bat files -> _archive/

start_variet_engine.bat

@@ -0,0 +1,14 @@
+@echo off
+chcp 65001 >nul
+echo ══════════════════════════════════════════════════════
+echo 🚀 Variet LLM Engine v1.0
+echo ══════════════════════════════════════════════════════
+echo  [SYSTEM] Booting default AI Model (Fast / Gemma 26B)...
+echo  [SYSTEM] API Gateway active on Port 8000
+echo  [SYSTEM] Ready for OpenClaude and VS Code AI Core.
+echo ══════════════════════════════════════════════════════
+echo.
+
+C:\ProgramData\miniforge3\envs\variet-llm\python.exe engine\variet_engine.py
+
+pause