Phase 3 Closure & Phase 4 Preparation

Summary:
- Phase 3 optimization complete (cumulative +8.93%)
- D1 promoted to default (HAKMEM_FREE_STATIC_ROUTE=1, +2.19%)
- D2 frozen (NO-GO, -1.44% regression)
- Phase 4 instructions prepared (D3/Alloc Gate Specialization)

Results:
  B3 (Routing shape): +2.89%
  B4 (Wrapper split): +1.47%
  C3 (Static routing): +2.20%
  C1 (TLS prefetch): NEUTRAL (-0.34%, research box)
  C2 (Metadata cache): NEUTRAL (-0.45%, research box)
  D1 (Free route cache): +2.19% (now default)
  D2 (Wrapper env cache): NO-GO (-1.44%, frozen)
  MID_V3 fix: +13% (structural)

Total Phase 2-3 gain: ~8.93% (37.5M → 51M ops/s)

Updated:
- CURRENT_TASK.md: Phase 3 final results + D3 conditions
- ENV_PROFILE_PRESETS.md: Active optimizations listed
- PHASE3_CACHE_LOCALITY_NEXT_INSTRUCTIONS.md: Phase 3→4 transition
- PHASE4_ALLOC_GATE_SPECIALIZATION_NEXT_INSTRUCTIONS.md: D3 execution plan
- PHASE3_BASELINE_AND_CANDIDATES.md: Post-validation status

Next phase: Phase 4 D3 - Alloc Gate Specialization
- Requires: tiny_alloc_gate_fast self% ≥5% from perf
- Design SSOT: PHASE3_D3_ALLOC_GATE_SPECIALIZATION_1_DESIGN.md
- Execution: PHASE4_ALLOC_GATE_SPECIALIZATION_NEXT_INSTRUCTIONS.md

🤖 Generated with Claude Code

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

docs/analysis/ENV_PROFILE_PRESETS.md

@@ -41,6 +41,7 @@ HAKMEM_BENCH_MAX_SIZE=1024
 - `HAKMEM_WRAP_SHAPE=1`（Phase 2 B4: wrapper hot/cold split を default ON）
 - `HAKMEM_TINY_ALLOC_ROUTE_SHAPE=1`（Phase 2 B3: alloc の route dispatch 形を最適化）
 - `HAKMEM_TINY_STATIC_ROUTE=1`（Phase 3 C3: policy_snapshot bypass を default ON）
+- `HAKMEM_FREE_STATIC_ROUTE=1`（Phase 3 D1: free path route cache を default ON）
 - `HAKMEM_MID_V3_ENABLED=0`（Mixed 本線では OFF。C6-heavy のみ推奨ON）
 - `HAKMEM_MID_V3_CLASSES=0x0`（Mixed 本線では未使用）
 - `HAKMEM_MID_V35_ENABLED=0`（Phase v11a-5: Mixed では MID v3.5 OFF が最速）