fix(ai): 修復假信心度 + 解除 Shadow Mode (Phase 22 P1)

1. openclaw.py: LLM 截斷時 confidence 0.82→0.0 (禁止偽造信心度)
2. prompts.py: NEMOTRON schema 範例值改用佔位符，防模型照抄 0.75
3. configmap: SHADOW_MODE_ENABLED=false，開放 low 風險自動執行
   條件門檻: confidence≥90% + trust_score≥5 + playbook_success≥95%

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

apps/api/src/services/openclaw.py

@@ -1041,9 +1041,10 @@ class OpenClawService:
             if "suggested_action" not in data:
                 data["suggested_action"] = "NO_ACTION"
 
-            # Step 2.5: 2026-03-31 ogt - 強力補全計畫 (針對 Nemo-4B 斷片)
+            # Step 2.5: 2026-04-01 Claude Code - 斷片補全 (信心度必須誠實)
+            # 🔴 禁止填入假信心度！截斷 = 0.0，讓 auto-approve 正確判斷
             if "confidence" not in data or not isinstance(data["confidence"], int | float):
-                data["confidence"] = 0.82  # 給予合理平均值而非 0
+                data["confidence"] = 0.0  # 截斷/缺失 → 0.0，不可偽造
             if "risk_level" not in data:
                 data["risk_level"] = "low"
             if "primary_responsibility" not in data: