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/decision_manager.py

@@ -110,6 +110,7 @@ async def _push_decision_to_telegram(
         confidence = proposal_data.get("confidence", 0.0)  # 🔴 預設 0.0 表示未經 AI 分析
         source = proposal_data.get("source", "unknown")
         ai_provider = proposal_data.get("provider", "")  # 2026-03-29 ogt: AI 模型來源
+        ai_model = proposal_data.get("model", "")  # 2026-04-04 ogt: 底層模型名稱
 
         # 2026-04-02 ogt: Phase 22 Nemotron 協作資料
         nemotron_enabled = proposal_data.get("nemotron_enabled", False)
@@ -132,6 +133,7 @@ async def _push_decision_to_telegram(
             confidence=confidence,
             namespace=incident.signals[0].labels.get("namespace", "default") if incident.signals else "default",
             ai_provider=ai_provider,  # 2026-03-29 ogt: 顯示 AI 模型來源
+            ai_model=ai_model,  # 2026-04-04 ogt: 底層模型名稱
             # 2026-04-02 ogt: Phase 22 Nemotron 協作 (ADR-044)
             nemotron_enabled=nemotron_enabled,
             nemotron_tools=nemotron_tools,