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>
This commit is contained in:
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user