fix(api): 移除 Consensus Engine 假信心分數

🔴 違反鐵律: feedback_confidence_truthfulness.md
Expert System 必須 confidence = 0.0，禁止假裝 AI 仲裁

修正:
- SREAgent: 0.85/0.80/0.75/0.60 → 0.0
- SecurityAgent: 0.70/0.85 → 0.0
- CostAgent: 0.75 → 0.0
- PerformanceAgent: 0.80/0.70 → 0.0

所有規則匹配現在正確顯示為「⚙️ 規則匹配」而非「🤖 AI 仲裁」

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

apps/api/src/services/consensus_engine.py

@@ -196,22 +196,22 @@ class SREAgent(ExpertAgent):
         if any(kw in alert_names for kw in ["crash", "restart", "oom", "killed"]):
             action = "重新啟動服務以恢復穩定性"
             kubectl = f"kubectl rollout restart deployment/{target} -n awoooi-prod"
-            confidence = 0.85
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "medium"
         elif any(kw in alert_names for kw in ["latency", "slow", "timeout"]):
             action = "擴展副本數以分散負載"
             kubectl = f"kubectl scale deployment/{target} --replicas=3 -n awoooi-prod"
-            confidence = 0.80
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "low"
         elif any(kw in alert_names for kw in ["cpu", "memory", "resource"]):
             action = "調整資源限制或擴展副本"
             kubectl = f"kubectl scale deployment/{target} --replicas=2 -n awoooi-prod"
-            confidence = 0.75
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "medium"
         else:
             action = "進行安全重啟以排除未知問題"
             kubectl = f"kubectl rollout restart deployment/{target} -n awoooi-prod"
-            confidence = 0.60
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "medium"
 
         return AgentOpinion(
@@ -250,11 +250,11 @@ class SecurityAgent(ExpertAgent):
 
         if security_concerns:
             action = "建議先隔離受影響服務，啟用 NetworkPolicy 限制"
-            confidence = 0.70
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "critical"
         else:
             action = "無明顯資安風險，建議 SRE 處理"
-            confidence = 0.85
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
             risk = "low"
 
         return AgentOpinion(
@@ -289,7 +289,7 @@ class CostAgent(ExpertAgent):
             agent_type=self.agent_type,
             action=action,
             reasoning="FinOps 分析: 使用 HPA 可在負載降低後自動縮減，相比固定擴容可節省約 40% 成本",
-            confidence=0.75,
+            confidence=0.0,  # 🔴 規則匹配，非 AI 分析
             risk_assessment="成本風險: low，使用 HPA 可自動調節",
             kubectl_command=kubectl,
             priority=4,
@@ -313,11 +313,11 @@ class PerformanceAgent(ExpertAgent):
         if any(kw in alert_names for kw in ["latency", "p99", "slow"]):
             action = "建議增加資源限制並啟用 PodDisruptionBudget"
             kubectl = f"kubectl patch deployment/{target} -n awoooi-prod -p '{{\"spec\":{{\"template\":{{\"spec\":{{\"containers\":[{{\"name\":\"{target}\",\"resources\":{{\"limits\":{{\"cpu\":\"2\",\"memory\":\"2Gi\"}}}}}}]}}}}}}}}'"
-            confidence = 0.80
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
         else:
             action = "當前效能指標正常，建議觀察"
             kubectl = None
-            confidence = 0.70
+            confidence = 0.0  # 🔴 規則匹配，非 AI 分析
 
         return AgentOpinion(
             agent_type=self.agent_type,