feat(api): ADR-030 Phase 2 診斷資料收集強化

實作智能自動修復系統的資料收集層：

1. k8s_diagnostics.py - K8s 診斷服務
   - Pod Events/Logs/ResourceUsage 收集
   - CrashLoopBackOff/OOM/ImagePull 偵測
   - 非同步並行收集 + 錯誤容忍

2. diagnosis_aggregator.py - 診斷聚合器
   - 整合 K8s + SignOz + Expert Rules
   - DiagnosisContext 提供結構化 LLM Prompt
   - DiagnosisSignal 信號分析

3. decision_manager.py - 決策引擎整合
   - Step 2.5 加入診斷收集
   - 傳遞 diagnosis_context 給 LLM

4. openclaw.py - LLM Prompt 增強
   - 整合 K8s/SignOz 深度診斷上下文
   - 支援 diagnosis_signals 摘要

ADR-030 架構: 診斷先行，根因分析，非盲目重啟

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

apps/api/src/services/decision_manager.py

@@ -31,6 +31,7 @@ from src.core.config import settings
 from src.core.redis_client import get_redis
 from src.models.incident import Incident
 from src.models.playbook import SymptomPattern
+from src.services.diagnosis_aggregator import get_diagnosis_aggregator
 from src.services.openclaw import get_openclaw
 from src.services.playbook_service import get_playbook_service
 
@@ -600,7 +601,36 @@ class DecisionManager:
             )
             return expert_result
 
-        # Step 3: 準備 LLM 上下文 (含 Expert 診斷)
+        # Step 2.5: ADR-030 診斷資料收集 (Phase 2)
+        # 使用 DiagnosisAggregator 收集 K8s + SignOz 診斷資料
+        diagnosis_context = None
+        target = incident.affected_services[0] if incident.affected_services else None
+        if target:
+            try:
+                aggregator = get_diagnosis_aggregator()
+                diagnosis_context = await aggregator.collect_pod_diagnosis(
+                    pod_name=target,
+                    namespace="awoooi-prod",
+                    include_signoz=True,
+                    include_error_logs=True,
+                    expert_match=expert_result,
+                )
+                logger.info(
+                    "dual_engine_diagnosis_collected",
+                    incident_id=incident.incident_id,
+                    target=target,
+                    signals_count=len(diagnosis_context.signals),
+                    highest_severity=diagnosis_context.highest_severity.value,
+                )
+            except Exception as e:
+                logger.warning(
+                    "dual_engine_diagnosis_failed",
+                    incident_id=incident.incident_id,
+                    error=str(e),
+                )
+                # 診斷收集失敗不影響主流程，繼續使用 expert_result
+
+        # Step 3: 準備 LLM 上下文 (含 Expert 診斷 + K8s/SignOz 診斷)
         signals_dict = [s.model_dump() for s in incident.signals]
         expert_context = {
             "initial_diagnosis": expert_result.get("matched_rule"),
@@ -610,6 +640,11 @@ class DecisionManager:
             "requires_human_review": expert_result.get("human_review_required", False),
         }
 
+        # 加入診斷上下文 (如果有)
+        if diagnosis_context:
+            expert_context["diagnosis_context"] = diagnosis_context.get_llm_prompt_context()
+            expert_context["diagnosis_signals"] = [s.to_dict() for s in diagnosis_context.signals]
+
         # Step 4: LLM 分析 (帶上 Expert 上下文)
         try:
             llm_result, provider, success = await self._openclaw.generate_incident_proposal(