fix(aiops): fallback and escalate automation blockers

apps/api/src/api/v1/drift.py

@@ -180,6 +180,7 @@ async def _analyze_and_notify(report: DriftReport) -> None:
 
         # 2026-04-24: 嘗試低風險自動採納
         auto_adopted = False
+        auto_block_reason = ""
         try:
             adopt_svc = get_drift_adopt_service()
             auto_result = await adopt_svc.auto_adopt_if_safe(report)
@@ -197,19 +198,28 @@ async def _analyze_and_notify(report: DriftReport) -> None:
                     pr_url=auto_result.get("pr_url"),
                 )
             else:
+                auto_block_reason = auto_result.get("reason", "") or "auto adopt skipped"
                 _logger.info(
                     "drift_auto_adopt_skipped",
                     report_id=report.report_id,
-                    reason=auto_result.get("reason", ""),
+                    reason=auto_block_reason,
                     skipped=auto_result.get("skipped", True),
                 )
         except Exception as e:
+            auto_block_reason = f"auto adopt error: {str(e)[:120]}"
             _logger.warning("drift_auto_adopt_error", report_id=report.report_id, error=str(e))
 
         if auto_adopted:
             # 自動採納成功，Telegram 通知已在 auto_adopt_if_safe 內發出，不再推送按鈕卡片
             return
 
+        if auto_block_reason:
+            await _escalate_drift_auto_adopt_blocked(
+                report=report,
+                reason=auto_block_reason,
+                interpretation=interpretation,
+            )
+
         # ADR-075: drift_narrator_service 負責發送 TYPE-4D 卡片（含按鈕）
         # 舊的 send_text() 已移除，改由 narrate_and_notify() 統一處理
         try:
@@ -224,6 +234,25 @@ async def _analyze_and_notify(report: DriftReport) -> None:
         structlog.get_logger(__name__).error("drift_analyze_notify_failed", error=str(e))
 
 
+async def _escalate_drift_auto_adopt_blocked(
+    *,
+    report: DriftReport,
+    reason: str,
+    interpretation,
+) -> None:
+    """Delegate drift emergency escalation to the service layer."""
+
+    from src.services.emergency_escalation_service import (
+        escalate_drift_auto_adopt_blocked,
+    )
+
+    await escalate_drift_auto_adopt_blocked(
+        report=report,
+        reason=reason,
+        interpretation=interpretation,
+    )
+
+
 async def _run_full_scan(namespaces: list[str]) -> None:
     """背景：完整漂移掃描"""
     detector = get_drift_detector()

apps/api/src/api/v1/webhooks.py

@@ -110,6 +110,34 @@ def _should_bypass_alertmanager_llm(
         and alert_category == "host_resource"
     )
 
+
+async def _escalate_auto_repair_unavailable(
+    *,
+    incident_id: str,
+    approval_id: str,
+    alert_type: str,
+    target_resource: str,
+    namespace: str,
+    failure_reason: str,
+    attempted_actions: str,
+) -> None:
+    """Delegate automation-blocker escalation to the service layer."""
+
+    from src.services.emergency_escalation_service import (
+        escalate_auto_repair_unavailable,
+    )
+
+    await escalate_auto_repair_unavailable(
+        incident_id=incident_id,
+        approval_id=approval_id,
+        alert_type=alert_type,
+        target_resource=target_resource,
+        namespace=namespace,
+        failure_reason=failure_reason,
+        attempted_actions=attempted_actions,
+    )
+
+
 async def _try_auto_repair_background(
     incident_id: str,
     approval_id: str,
@@ -165,6 +193,15 @@ async def _try_auto_repair_background(
                     "playbook_id": decision.playbook.playbook_id if decision.playbook else None,
                 },
             )
+            await _escalate_auto_repair_unavailable(
+                incident_id=incident_id,
+                approval_id=approval_id,
+                alert_type=alert_type,
+                target_resource=target_resource,
+                namespace=namespace,
+                failure_reason=decision.reason,
+                attempted_actions=f"evaluate_auto_repair -> blocked:{decision.blocked_by}",
+            )
             return
 
         # 記錄自動修復觸發 (Sprint 5.1 Q10: 加入 Langfuse trace_id 追蹤)
@@ -228,6 +265,16 @@ async def _try_auto_repair_background(
                     "namespace": namespace,
                 },
             )
+            if not result.success:
+                await _escalate_auto_repair_unavailable(
+                    incident_id=incident_id,
+                    approval_id=approval_id,
+                    alert_type=alert_type,
+                    target_resource=target_resource,
+                    namespace=namespace,
+                    failure_reason=result.error or "auto repair execution failed",
+                    attempted_actions=f"execute_auto_repair playbook:{result.playbook_id}",
+                )
 
         # ADR-073 Phase 2-3: 自動修復結果 → 寫入 Incident outcome (2026-04-12 ogt)
         # 讓 KMConversionService 可依 outcome 判斷是否為 EXECUTION_SUCCESS