feat: confluence benchmark, pattern extractor, agent KB, UX spec

- extract-patterns.js: mines layered arch, ArgoCD appsets, cloud regions,
  CIDR allocations, naming conventions, sync waves, tech stack from code
- agent-kb.js: token-efficient JSON rendering of same doc tree
- eval-confluence-ref-questions.json: 32 reference-only benchmark questions
- wiggum-v2.sh: Ralph Wiggum loop targeting confluence baseline (77.8%)
- docs/human-ux-spec.md: BMad UX designer spec for human doc structure
- Eval results: V2 at 28.7% vs confluence 77.8% baseline
- Hub/spoke ownership now correctly extracted (95% on that question)
- Naming conventions, regions, CIDRs surfaced in system-architecture.md

foxtrot-docs-v3/reference/system-architecture.md

@@ -0,0 +1,23 @@
+# System Architecture
+
+## Summary
+- **Subsystems:** 11
+- **Helm Charts:** 76
+- **Terraform Modules:** 727
+- **Cross-Cutting:** app-tools
+
+## Subsystems
+
+| Subsystem | Kind | Files | Functions |
+|---|---|---|---|
+| account-common | domain | 8 | 0 |
+| app-common | domain | 934 | 28 |
+| app-tools | cross-cutting | 17 | 92 |
+| compute-common | domain | 64 | 14 |
+| compute-tools | domain | 28 | 108 |
+| control-core | domain | 336 | 0 |
+| ipam-core | domain | 24 | 1 |
+| ipam-tools | domain | 17 | 104 |
+| network-common | domain | 24 | 0 |
+| network-core | domain | 87 | 0 |
+| runtime | domain | 16309 | 69 |