fix(api): 全面清除假信心分數 - 遵循 feedback_confidence_truthfulness.md

🔴 違規修正: 規則匹配/Expert System 不是 AI 分析，confidence 必須 = 0.0

修正檔案:
- agents/action_planner.py: 0.9 → 0.0
- agents/blast_radius.py: 0.85/0.5/0.9 → 0.0
- agents/security.py: 計算公式 → 0.0
- signoz_webhook.py: 0.7 → 0.0
- auto_approve.py: default 0.5 → 0.0
- ci_auto_repair.py: 整個計算函數 → return 0.0
- error_analyzer_service.py: default 0.5 → 0.0
- intent_classifier.py: 計算公式 → 0.0
- openclaw.py: default 0.5 → 0.0
- resource_resolver.py: 0.8 → 0.0
- k8s_naming.py: 0.9/0.7 → 0.0

只有 LLM 真實分析返回的 confidence 才能 > 0

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

apps/api/src/agents/action_planner.py

@@ -389,7 +389,7 @@ class ActionPlannerAgent(BaseAgent[ActionPlan]):
             result = ActionPlan(
                 agent_name=self.AGENT_NAME,
                 status=AgentStatus.SUCCESS,
-                confidence=0.9,
+                confidence=0.0,  # 🔴 規則匹配/模板，非 AI 分析
                 analysis=analysis,
                 latency_ms=latency_ms,
                 action_type=template["action_type"],

apps/api/src/agents/blast_radius.py

@@ -270,7 +270,7 @@ class BlastRadiusAgent(BaseAgent[BlastRadiusResult]):
             result = BlastRadiusResult(
                 agent_name=self.AGENT_NAME,
                 status=AgentStatus.SUCCESS,
-                confidence=0.85,  # 基於依賴圖的信心分數
+                confidence=0.0,  # 🔴 規則/圖譜分析，非 AI
                 analysis=analysis,
                 latency_ms=latency_ms,
                 impact_level=impact_level,
@@ -331,7 +331,7 @@ class BlastRadiusAgent(BaseAgent[BlastRadiusResult]):
             affected.append(AffectedService(
                 name=target_service,
                 impact_type="direct",
-                confidence=0.5,
+                confidence=0.0,  # 🔴 規則推斷，非 AI
                 reason="未知服務，無法確定依賴關係",
             ))
             return affected, 1000, [target_service]
@@ -391,7 +391,8 @@ class BlastRadiusAgent(BaseAgent[BlastRadiusResult]):
             chain.append(dep)
 
             impact_type = "indirect" if depth == 0 else "transitive"
-            confidence = 0.9 - (depth * 0.1)
+            # 🔴 規則/圖譜推斷，非 AI 分析
+            confidence = 0.0
 
             affected.append(AffectedService(
                 name=dep,

apps/api/src/agents/security.py

@@ -279,8 +279,8 @@ class SecurityAgent(BaseAgent[SecurityResult]):
             risk_factors.append("未偵測到明顯風險因素")
             max_risk_score = 2.0  # 基礎低風險
 
-        # 計算信心分數 (規則匹配越多，信心越高)
-        confidence = min(0.95, 0.7 + len(risk_factors) * 0.05)
+        # 🔴 規則匹配，非 AI 分析，信心度設 0
+        confidence = 0.0
 
         # 生成分析摘要
         if max_risk_score >= 8.0: