feat(auto-repair): 所有操作強制寫入 DB — auto_repair_executions 表

統帥指令: 所有自動修復操作（成功/失敗）必須持久化

變更:
- migrations/phase10_auto_repair_executions.sql: 新增表 + 4 個索引
- db/models.py: 新增 AutoRepairExecution SQLAlchemy model
- repositories/audit_log_repository.py: 新增 AutoRepairExecutionRepository (create/list_by_incident/get_stats)
- auto_repair_service.py: execute_auto_repair 成功/失敗分支都寫入 DB
  - 新增 similarity_score 參數傳遞
  - AutoRepairDecision 新增 similarity_score 欄位
- webhooks.py: 傳入 similarity_score 到 execute_auto_repair

已執行 migration: awoooi_prod@192.168.0.188:5432 ✅

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

apps/api/migrations/phase10_auto_repair_executions.sql

@@ -0,0 +1,38 @@
+-- Phase 10: Auto Repair Executions 操作記錄表
+-- 建立時間: 2026-04-08 (台北時區)
+-- 建立者: Claude Code — 統帥指令「所有操作都必須被記錄，寫入資料庫」
+--
+-- 設計說明:
+--   自動修復每次執行（成功或失敗）都寫入此表
+--   不依賴 approval_id（自動修復不需要人工批准）
+--   支援查詢: 按 incident / playbook / 時間範圍 / 成功率
+
+CREATE TABLE IF NOT EXISTS auto_repair_executions (
+    -- 主鍵
+    id              VARCHAR(36) PRIMARY KEY DEFAULT gen_random_uuid()::text,
+
+    -- 關聯
+    incident_id     VARCHAR(30) NOT NULL,
+    playbook_id     VARCHAR(36) NOT NULL,
+    playbook_name   VARCHAR(200) NOT NULL,
+
+    -- 執行結果
+    success         BOOLEAN NOT NULL DEFAULT FALSE,
+    executed_steps  JSONB NOT NULL DEFAULT '[]',   -- list of step result strings
+    error_message   TEXT,
+
+    -- 執行上下文
+    triggered_by    VARCHAR(50) NOT NULL DEFAULT 'auto_repair',  -- auto_repair / cold_start_trust
+    similarity_score NUMERIC(5,4),                               -- 匹配相似度
+    risk_level      VARCHAR(20),                                  -- LOW / MEDIUM / HIGH
+    execution_time_ms INTEGER,
+
+    -- 時間戳 (台北時區)
+    created_at      TIMESTAMPTZ NOT NULL DEFAULT NOW()
+);
+
+-- 索引
+CREATE INDEX IF NOT EXISTS ix_are_incident_id   ON auto_repair_executions (incident_id);
+CREATE INDEX IF NOT EXISTS ix_are_playbook_id   ON auto_repair_executions (playbook_id);
+CREATE INDEX IF NOT EXISTS ix_are_created_at    ON auto_repair_executions (created_at DESC);
+CREATE INDEX IF NOT EXISTS ix_are_success       ON auto_repair_executions (success);

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

@@ -209,6 +209,7 @@ async def _try_auto_repair_background(
             incident=incident,
             playbook=decision.playbook,
             is_cold_start=decision.is_cold_start,
+            similarity_score=decision.similarity_score,
         )
 
         logger.info(

apps/api/src/db/models.py

@@ -352,6 +352,50 @@ class AuditLog(Base):
     )
 
 
+# =============================================================================
+# AutoRepairExecution - Phase 10 操作記錄
+# 2026-04-08 Claude Code: 統帥指令「所有操作都必須被記錄，寫入資料庫」
+# =============================================================================
+
+class AutoRepairExecution(Base):
+    """
+    自動修復執行記錄
+
+    每次 evaluate_auto_repair 觸發並執行 (成功或失敗) 都寫入此表。
+    不依賴 approval_id（自動修復不需人工批准）。
+    """
+    __tablename__ = "auto_repair_executions"
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=generate_uuid)
+
+    # 關聯
+    incident_id: Mapped[str] = mapped_column(String(30), nullable=False, index=True)
+    playbook_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
+    playbook_name: Mapped[str] = mapped_column(String(200), nullable=False)
+
+    # 執行結果
+    success: Mapped[bool] = mapped_column(default=False, nullable=False)
+    executed_steps: Mapped[list] = mapped_column(JSON, default=list, nullable=False)
+    error_message: Mapped[str | None] = mapped_column(Text, nullable=True)
+
+    # 執行上下文
+    triggered_by: Mapped[str] = mapped_column(
+        String(50), default="auto_repair", nullable=False,
+        comment="auto_repair / cold_start_trust",
+    )
+    similarity_score: Mapped[float | None] = mapped_column(nullable=True)
+    risk_level: Mapped[str | None] = mapped_column(String(20), nullable=True)
+    execution_time_ms: Mapped[int | None] = mapped_column(Integer, nullable=True)
+
+    # 時間戳 (台北時區)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=taipei_now)
+
+    __table_args__ = (
+        Index("ix_are_created_at", "created_at"),
+        Index("ix_are_success", "success"),
+    )
+
+
 # =============================================================================
 # IncidentRecord - Phase 6.2 Episodic Memory (PostgreSQL)
 # =============================================================================

apps/api/src/repositories/audit_log_repository.py

@@ -15,7 +15,7 @@ import structlog
 from sqlalchemy import func, select
 
 from src.db.base import get_db_context
-from src.db.models import AuditLog
+from src.db.models import AuditLog, AutoRepairExecution
 
 logger = structlog.get_logger(__name__)
 
@@ -157,6 +157,97 @@ class AuditLogRepository:
             }
 
 
+# =============================================================================
+# AutoRepairExecutionRepository
+# 2026-04-08 Claude Code: 統帥指令「所有操作都必須被記錄，寫入資料庫」
+# =============================================================================
+
+
+class AutoRepairExecutionRepository:
+    """自動修復執行記錄 Repository"""
+
+    async def create(
+        self,
+        incident_id: str,
+        playbook_id: str,
+        playbook_name: str,
+        success: bool,
+        executed_steps: list[str],
+        error_message: str | None = None,
+        triggered_by: str = "auto_repair",
+        similarity_score: float | None = None,
+        risk_level: str | None = None,
+        execution_time_ms: int | None = None,
+    ) -> AutoRepairExecution:
+        """寫入一筆自動修復執行記錄"""
+        async with get_db_context() as db:
+            record = AutoRepairExecution(
+                incident_id=incident_id,
+                playbook_id=playbook_id,
+                playbook_name=playbook_name,
+                success=success,
+                executed_steps=executed_steps,
+                error_message=error_message,
+                triggered_by=triggered_by,
+                similarity_score=similarity_score,
+                risk_level=risk_level,
+                execution_time_ms=execution_time_ms,
+            )
+            db.add(record)
+            await db.flush()
+            await db.refresh(record)
+            return record
+
+    async def list_by_incident(self, incident_id: str) -> list[AutoRepairExecution]:
+        """查詢某 incident 的所有修復記錄"""
+        async with get_db_context() as db:
+            result = await db.execute(
+                select(AutoRepairExecution)
+                .where(AutoRepairExecution.incident_id == incident_id)
+                .order_by(AutoRepairExecution.created_at.desc())
+            )
+            return list(result.scalars().all())
+
+    async def get_stats(self, since_hours: int = 24) -> dict[str, Any]:
+        """統計最近 N 小時的自動修復執行情況"""
+        from datetime import timedelta
+        from src.utils.timezone import now_taipei
+
+        since = now_taipei() - timedelta(hours=since_hours)
+        async with get_db_context() as db:
+            total_r = await db.execute(
+                select(func.count(AutoRepairExecution.id))
+                .where(AutoRepairExecution.created_at >= since)
+            )
+            total = total_r.scalar() or 0
+
+            success_r = await db.execute(
+                select(func.count(AutoRepairExecution.id))
+                .where(AutoRepairExecution.created_at >= since)
+                .where(AutoRepairExecution.success.is_(True))
+            )
+            success_count = success_r.scalar() or 0
+
+            return {
+                "total": total,
+                "success_count": success_count,
+                "failure_count": total - success_count,
+                "success_rate": round(success_count / total * 100, 1) if total > 0 else 0,
+                "since_hours": since_hours,
+            }
+
+
+_auto_repair_execution_repo: AutoRepairExecutionRepository | None = None
+
+
+def get_auto_repair_execution_repository() -> AutoRepairExecutionRepository:
+    """取得 AutoRepairExecutionRepository 實例 (Singleton)"""
+    global _auto_repair_execution_repo
+    if _auto_repair_execution_repo is None:
+        _auto_repair_execution_repo = AutoRepairExecutionRepository()
+    return _auto_repair_execution_repo
+
+
 # =============================================================================
 # Singleton
 # =============================================================================

apps/api/src/services/auto_repair_service.py

@@ -63,6 +63,8 @@ class AutoRepairDecision:
     blocked_by: str | None = None  # 阻擋原因 (如 HIGH_RISK, P1_SEVERITY)
     # 2026-04-07 Claude Code: Sprint 4 B2 — 追蹤首次信任
     is_cold_start: bool = False
+    # 2026-04-08 Claude Code: 傳入 execute_auto_repair 供 DB 記錄
+    similarity_score: float | None = None
 
 
 @dataclass
@@ -280,9 +282,10 @@ class AutoRepairService:
         return AutoRepairDecision(
             can_auto_repair=True,
             playbook=best_match.playbook,
-            reason=f"匹配高品質 Playbook: {best_match.playbook.name} (成功率 {best_match.playbook.success_rate:.0%})",
+            reason=f"匹配 Playbook: {best_match.playbook.name} (相似度 {best_match.similarity_score:.0%})",
             risk_level=max_risk,
             is_cold_start=_is_cold_start,
+            similarity_score=best_match.similarity_score,
         )
 
     async def execute_auto_repair(
@@ -290,13 +293,14 @@ class AutoRepairService:
         incident: Incident,
         playbook: Playbook,
         is_cold_start: bool = False,
+        similarity_score: float | None = None,
     ) -> AutoRepairResult:
         """
         執行自動修復
 
         流程:
         1. 依序執行 Playbook 中的 repair_steps
-        2. 記錄執行結果
+        2. 記錄執行結果到 DB (auto_repair_executions)
         3. 更新 Playbook 統計
         4. 記錄處置類型 (Sprint 4 B1/B2)
         """
@@ -351,6 +355,24 @@ class AutoRepairService:
                 execution_time_ms=execution_time,
             )
 
+            # 2026-04-08 Claude Code: 統帥指令「所有操作都必須被記錄，寫入資料庫」
+            try:
+                from src.repositories.audit_log_repository import get_auto_repair_execution_repository
+                max_risk = self._get_max_risk_level(playbook)
+                await get_auto_repair_execution_repository().create(
+                    incident_id=incident.incident_id,
+                    playbook_id=playbook.playbook_id,
+                    playbook_name=playbook.name,
+                    success=True,
+                    executed_steps=executed_steps,
+                    triggered_by="cold_start_trust" if is_cold_start else "auto_repair",
+                    similarity_score=similarity_score,
+                    risk_level=max_risk.value if max_risk else None,
+                    execution_time_ms=execution_time,
+                )
+            except Exception as _db_e:
+                logger.error("auto_repair_db_write_failed", error=str(_db_e))
+
             # 2026-04-07 Claude Code: Sprint 4 B1/B2 — 記錄處置類型
             # P0-1 Fix: 統一使用 AnomalyCounter.hash_signature()
             try:
@@ -407,6 +429,25 @@ class AutoRepairService:
                 execution_time_ms=execution_time,
             )
 
+            # 2026-04-08 Claude Code: 失敗也必須寫入 DB
+            try:
+                from src.repositories.audit_log_repository import get_auto_repair_execution_repository
+                max_risk = self._get_max_risk_level(playbook)
+                await get_auto_repair_execution_repository().create(
+                    incident_id=incident.incident_id,
+                    playbook_id=playbook.playbook_id,
+                    playbook_name=playbook.name,
+                    success=False,
+                    executed_steps=executed_steps,
+                    error_message=str(e),
+                    triggered_by="cold_start_trust" if is_cold_start else "auto_repair",
+                    similarity_score=similarity_score,
+                    risk_level=max_risk.value if max_risk else None,
+                    execution_time_ms=execution_time,
+                )
+            except Exception as _db_e:
+                logger.error("auto_repair_db_write_failed", error=str(_db_e))
+
             # 2026-04-04 Claude Code: Phase 25 P1 — 失敗修復後 fire-and-forget 生成 ANTI_PATTERN
             # 2026-04-05 Claude Code: I1 修正 — 補齊 _pending_tasks GC 防護（對稱化）
             try: