fix(auto-repair): 修復三個阻礙自動修復的根本原因

1. playbook_rag: Ollama embedding http_client 滾動重啟後 is_closed
   - 新增 _get_http_client() 偵測 is_closed 自動重建
   - singleton get_playbook_rag_service() 加 is_closed 重建判斷

2. telegram: 加入 ai_model 欄位顯示底層判斷模型
   - TelegramMessage.ai_model 欄位
   - format() / format_with_nemotron() 顯示 "Nemotron (nemotron-70b)"
   - openclaw proposal_dict 加入 model 欄位
   - decision_manager / send_approval_card 串接

3. DB: 清除 9 筆 3/26 殭屍 PENDING (mock_fallback CRITICAL 測試記錄)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

apps/api/src/services/openclaw.py

@@ -1553,6 +1553,7 @@ Focus on:
                 "signoz_correlation": result.signoz_correlation,
                 "from_cache": from_cache,
                 "provider": provider,
+                "model": self._get_model_name(provider),  # 2026-04-04 ogt: 底層模型名稱
                 "ai_tokens": ai_tokens,
                 "ai_cost": ai_cost,
             }