fix(happy-path): Happy Path 全境加固 — INVALID_TARGET + critical NO_ACTION + 空指令攔截
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
問題 1 (P0) — deployment/unknown 無效重啟: - alert_rule_engine: 追蹤 _invalid_target flag,回傳 blocked_reason="INVALID_TARGET-..." - decision_manager: auto_execute 路徑偵測 INVALID_TARGET → 提早返回 + TYPE-4 人工確認 - auto_approve: 新增條件 1c — action 為空字串直接拒絕,防止誤報「即將執行」 問題 2 (P1) — critical+NO_ACTION 靜默: - decision_manager: blocked_reason 感知層重構 ① INVALID_TARGET → TYPE-4 ② NO_ACTION + critical → TYPE-4(升級,SRE 不可錯過) ③ NO_ACTION + 非 critical → TYPE-1(維持純資訊卡) 問題 3 (P1) — 規則匹配信心黑洞: - auto_approve 條件 1c 確保空 action 不通過 auto-approve 即便 is_rule_based=True 也無法在無指令時自動執行 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -372,6 +372,7 @@ def match_rule(alert_context: dict) -> dict[str, Any] | None:
|
||||
# GAP-A4 (2026-04-14 Claude Sonnet 4.6): 後置驗證 — 垃圾 target 丟棄 command
|
||||
# 避免 `kubectl rollout restart deployment unknown/HostHighCpuLoad/...` 這類無效指令
|
||||
# 清空 kubectl_command 讓 decision_manager 降級給 LLM 處理
|
||||
_invalid_target = False
|
||||
if kubectl_command and _is_bad_target(vars["target"], alertname):
|
||||
logger.warning(
|
||||
"rule_kubectl_command_discarded_bad_target",
|
||||
@@ -382,6 +383,7 @@ def match_rule(alert_context: dict) -> dict[str, Any] | None:
|
||||
original_command=kubectl_command[:120],
|
||||
)
|
||||
kubectl_command = ""
|
||||
_invalid_target = True
|
||||
|
||||
# 還有 {var} 殘留 → 模板變數未被 _fill 填滿(可能 vars 缺少對應 key)
|
||||
if kubectl_command and ("{" in kubectl_command or "}" in kubectl_command):
|
||||
@@ -391,6 +393,15 @@ def match_rule(alert_context: dict) -> dict[str, Any] | None:
|
||||
command=kubectl_command[:120],
|
||||
)
|
||||
kubectl_command = ""
|
||||
_invalid_target = True
|
||||
|
||||
# 2026-04-16 ogt + Claude Sonnet 4.6: blocked_reason 讓 decision_manager 感知 target 失敗
|
||||
# 根因:rule engine 清空 kubectl_command 但不告訴下游原因 → decision_manager 繼續嘗試執行
|
||||
# 修復:設定 blocked_reason="INVALID_TARGET - ..." 讓 auto_execute 路徑提早返回 + TYPE-4
|
||||
_blocked_reason_out = (
|
||||
f"INVALID_TARGET - target='{vars['target']}' 未解析為有效 Deployment,需 SRE 人工確認"
|
||||
if _invalid_target else ""
|
||||
)
|
||||
|
||||
return {
|
||||
"rule_id": matched_rule["id"],
|
||||
@@ -416,6 +427,7 @@ def match_rule(alert_context: dict) -> dict[str, Any] | None:
|
||||
"confidence": 0.0, # 🔴 規則匹配固定 0.0,禁止偽造
|
||||
"affected_services": [vars["target"]],
|
||||
"signoz_correlation": "",
|
||||
"blocked_reason": _blocked_reason_out, # "" 正常 | "INVALID_TARGET - ..." 目標解析失敗
|
||||
}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user