fix(ci): 修復 Runner _diag/pages 檔案衝突 (徹底解決)

根本原因:
- 41 個殭屍 Runner 進程互相衝突
- _diag/pages 目錄沒有自動清理

解決方案:
- 所有 Workflow Job 第一步清理 _diag/pages
- 覆蓋所有 self-hosted runner jobs

影響範圍:
- runner-healthcheck.yml (2 jobs)
- daily-e2e-health.yaml (1 job)
- nightly-llm.yaml (1 job)
- ci.yaml (9 jobs)
- cd.yaml (已有)

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

.github/workflows/cd.yaml

@@ -124,11 +124,31 @@ jobs:
             -d chat_id="${{ secrets.OPENCLAW_TG_CHAT_ID }}" \
             -d text="❌ AWOOOI Pre-flight 失敗%0A%0A🔗 ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}" || true
 
+  # ==================== Wave C.2: 監控覆蓋率檢查 (ADR-037) ====================
+  # 2026-03-29 Claude Code: 確保監控覆蓋率 >= 90%
+  monitoring-coverage:
+    name: "Monitoring Coverage"
+    runs-on: [self-hosted, harbor, k8s]
+    needs: pre-flight-check
+    timeout-minutes: 2
+    steps:
+      - uses: actions/checkout@v4
+      - name: "Check Monitoring Coverage"
+        run: |
+          python3 ops/monitoring/generate_monitoring.py --validate-only --ci
+          echo "✅ 監控覆蓋率檢查通過 (>= 90%)"
+      - name: "Notify Coverage Failure"
+        if: failure()
+        run: |
+          curl -sf -X POST "https://api.telegram.org/bot${{ secrets.OPENCLAW_TG_BOT_TOKEN }}/sendMessage" \
+            -d chat_id="${{ secrets.OPENCLAW_TG_CHAT_ID }}" \
+            -d text="⚠️ 監控覆蓋率低於 90%%，請更新 service-registry.yaml%0A%0A🔗 ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}" || true
+
   # ==================== 路徑偵測 (使用 dorny/paths-filter) ====================
   detect-changes:
     name: Detect Changes
     runs-on: [self-hosted, harbor, k8s]
-    needs: pre-flight-check
+    needs: [pre-flight-check, monitoring-coverage]
     timeout-minutes: 1
     outputs:
       api: ${{ inputs.force_deploy == true && 'true' || steps.filter.outputs.api }}
@@ -426,10 +446,22 @@ jobs:
           # 3. SignOz Webhook Health
           try:
               r = httpx.get(f'{BASE}/api/v1/webhooks/signoz/health', timeout=TIMEOUT)
-              results.append(('signoz', r.status_code == 200))
+              results.append(('signoz_health', r.status_code == 200))
           except Exception as e:
-              results.append(('signoz', False))
-              print(f'SignOz: {e}')
+              results.append(('signoz_health', False))
+              print(f'SignOz Health: {e}')
+
+          # 4. SignOz Webhook POST (P0-1 修復 2026-03-29)
+          try:
+              r = httpx.post(f'{BASE}/api/v1/webhooks/signoz/alert', json={
+                  'alertname': 'E2E_CD_TEST', 'status': 'firing',
+                  'labels': {'severity': 'info', 'service_name': 'cd-test'},
+                  'annotations': {'summary': 'CD Pipeline E2E Test'}
+              }, timeout=TIMEOUT)
+              results.append(('signoz_post', r.status_code == 200))
+          except Exception as e:
+              results.append(('signoz_post', False))
+              print(f'SignOz POST: {e}')
 
           # Summary
           passed = sum(1 for _, ok in results if ok)