feat(ai-governance): Sections 3-4 — Comparative Jurisdictional Analysis + Sectoral Regulations

Add Sections 3-4 to AI Governance Policy Report (~2,800 words, cumulative ~4,600).

Section 3: Comparative Analysis of Global AI Frameworks
- 3.1 Jurisdictional comparison matrix (8 dimensions × 5 jurisdictions)
  EU: AI Act (Reg. 2024/1689), 4-tier risk + GPAI overlay, 10^25 FLOP threshold
  US: EO 14110, sectoral approach, 10^26 FLOP reporting, no federal statute
  UK: Pro-innovation White Paper, AISI voluntary testing, no legislation
  China: Application-specific binding regs (generative AI, algorithmic, deep synthesis)
  Other: Canada AIDA, Japan soft-law, Singapore voluntary, G7 Hiroshima
- 3.2 EU AI Act deep-dive (Art. 51-56, CEN-CENELEC, Brussels Effect)
- 3.3 US sectoral approach (EO 14110, FDA, FTC, USAISI limitations)
- 3.4 UK pro-innovation framework (AISI, Bletchley/Seoul, voluntary constraints)
- 3.5 China application-specific regulation (CAC, algorithm registry, dual imperative)
- 3.6 Other jurisdictions and multilateral frameworks (CoE Convention, UN Advisory Body)

Section 4: Sectoral Regulations and Technical Safety Measures
- 4.1 Healthcare (FDA 950+ authorisations, EU MDR+AI Act dual layer, MHRA)
- 4.2 Financial services (SR 11-7, DORA, FCA/PRA, GenAI regulatory frontier)
- 4.3 Defence (DoD 3000.09, REAIM, CCW LAWS stalemate, dual-use porosity)
- 4.4 Technical safety (red-teaming, dangerous capability evals, alignment testing,
  incident reporting, continuous monitoring, responsible disclosure)
- 4.5 Evaluation frameworks comparison table (NIST AI RMF, ISO 42001,
  CEN-CENELEC, Responsible Scaling Policies) with critical gap analysis

New API endpoints (2):
  /api/ai-governance/jurisdictions — 8 dimensions × 5 jurisdictions comparative data
  /api/ai-governance/sectoral — 3 sectors + 4 evaluation frameworks + critical gap

Verification: 30 API endpoints all HTTP 200, 9 HTML pages zero console errors.

Author: OneFineStarstuff