research(kv-cache): TriAttention + TurboQuant stacked compression analysis

Add deep research into three-axis KV cache compression:
- TriAttention (arXiv:2604.04921): trigonometric RoPE-based token sparsity, 10.7x
- Stacked compression: TriAttention × TurboQuant for ~50x KV reduction
- ADR-147: formal architecture decision with GOAP implementation plan

No published work combines these orthogonal methods. First-mover opportunity
for ruvLLM edge inference (128K context in 175MB on Pi 5).

Co-Authored-By: claude-flow <ruv@ruv.net>

Author: Reuven