feat(adr-080): Phase 0 防護欄建立 — AI 自主化飛輪啟動

- docs/superpowers/specs/2026-04-15-MASTER-ai-autonomous-flywheel-v2.md
  (1456 行，§0-§8 全填完：42-cell 戰術矩陣、7 Phase 計畫、7 ADR 摘要、
   15 KPI、21 Feature Flags、10 風險場景)

- docs/adr/ADR-080-ai-autonomy-flywheel-overview.md
  (7 Phase 結構 + 4 北極星 + 7 架構師 Review Gates + Phase 退出條件)

- apps/api/src/core/feature_flags.py
  (AIOpsFeatureFlags: P1~P6 總開關全 False + 15 細粒度子開關
   is_phase_enabled() / is_sub_flag_enabled() + bool cast 安全)

- apps/api/src/jobs/__init__.py + baseline_snapshot.py
  (Phase 0 基線快照 Job：MCP calls / Playbook confidence / general 比例
   / learning loop rate / auto_repair — 寫入 aiops:baseline:latest)

- apps/api/tests/test_feature_flags.py  (21 tests — 全綠)

- docs/HARD_RULES.md → v1.9
  (新增 Phase 退出條件鐵律：禁止未過 exit conditions 宣告 Phase 完成)

- CLAUDE.md 防失憶閘門 1：強制讀 MASTER §0 Session Resume Protocol

Gate 0 Pass — 21/21 tests green

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

apps/api/src/core/feature_flags.py

@@ -0,0 +1,240 @@
+"""
+AWOOOI AIOps Feature Flags
+==========================
+AI 自主化飛輪 Phase 0-6 功能開關
+
+ADR-080: AI 自主化飛輪總綱
+MASTER: docs/superpowers/specs/2026-04-15-MASTER-ai-autonomous-flywheel-v2.md
+
+安全規則：
+- 所有 flag 預設 False — 任何 Phase 必須明確開啟才生效
+- Phase 總開關 = False 時，該 Phase 所有子開關均視為 False
+- 自我降級後 (D6) 不得自動反向升級，升級必須人工設定 env var
+
+回滾方式：
+    kubectl set env deployment/awoooi-api AIOPS_P1_ENABLED=false
+    # 或修改 .env 後重部署
+
+2026-04-15 ogt: Phase 0 — 初始建立，ADR-080 批准後啟用
+"""
+
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class AIOpsFeatureFlags(BaseSettings):
+    """
+    AI 自主化飛輪 Feature Flag 集合
+
+    每個 Phase 一個總開關 + 細粒度子開關。
+    讀取順序：環境變數 > .env 檔 > 預設值（全 False）。
+    """
+
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=True,
+        extra="ignore",
+    )
+
+    # ==========================================================================
+    # Phase 總開關（Phase N 退出條件達到後才設 True）
+    # ==========================================================================
+
+    AIOPS_P1_ENABLED: bool = Field(
+        default=False,
+        description="Phase 1 感官縱深：PreDecisionInvestigator + EvidenceSnapshot + PostExecutionVerifier",
+    )
+    AIOPS_P2_ENABLED: bool = Field(
+        default=False,
+        description="Phase 2 多 Agent 協作：5 角色全部上線（Diagnostician/Solver/Reviewer/Critic/Coordinator）",
+    )
+    AIOPS_P3_ENABLED: bool = Field(
+        default=False,
+        description="Phase 3 學習閉環重建：3 根因修復 + EWMA + Evolver + Fine-tune pipeline",
+    )
+    AIOPS_P4_ENABLED: bool = Field(
+        default=False,
+        description="Phase 4 動態異常偵測：Holt-Winters + Drain3 + Prophet + 主動巡檢",
+    )
+    AIOPS_P5_ENABLED: bool = Field(
+        default=False,
+        description="Phase 5 修復抽象化：Declarative + Blast Radius 四級分控 + GitOps PR",
+    )
+    AIOPS_P6_ENABLED: bool = Field(
+        default=False,
+        description="Phase 6 自我治理閉環：SLO + Trust Drift + KB Rot + 離線回放 + 自我降級",
+    )
+
+    # ==========================================================================
+    # Phase 1 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P1_PRE_DECISION_INVESTIGATOR: bool = Field(
+        default=False,
+        description="P1: PreDecisionInvestigator 是否在決策前執行 MCP 感官蒐集（可獨立關閉）",
+    )
+    AIOPS_P1_POST_EXECUTION_VERIFIER: bool = Field(
+        default=False,
+        description="P1: PostExecutionVerifier 是否在每次執行後驗證狀態",
+    )
+
+    # ==========================================================================
+    # Phase 2 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P2_CRITIC_ENABLED: bool = Field(
+        default=False,
+        description="P2: Critic Agent 是否啟用辯證挑戰（關閉可降低延遲但失去質疑機制）",
+    )
+    AIOPS_P2_AGENT_TIMEOUT_SEC: int = Field(
+        default=5,
+        description="P2: 單 Agent 熔斷閾值（秒），超時則 Coordinator 降級處理",
+    )
+
+    # ==========================================================================
+    # Phase 3 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P3_FINETUNE_EXPORT: bool = Field(
+        default=False,
+        description="P3: Fine-tune JSONL 每週匯出到 MinIO 是否執行",
+    )
+    AIOPS_P3_EVOLVER_ENABLED: bool = Field(
+        default=False,
+        description="P3: Evolver Agent 是否執行 Playbook 自動合併與封存",
+    )
+    AIOPS_P3_KNOWLEDGE_DECAY: bool = Field(
+        default=False,
+        description="P3: 30 天知識遺忘 job 是否執行（標 decayed，降到 cold index）",
+    )
+
+    # ==========================================================================
+    # Phase 4 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P4_DYNAMIC_BASELINE: bool = Field(
+        default=False,
+        description="P4: Holt-Winters 動態基線服務是否啟用",
+    )
+    AIOPS_P4_LOG_ANOMALY: bool = Field(
+        default=False,
+        description="P4: Drain3 日誌異常偵測是否啟用",
+    )
+    AIOPS_P4_TREND_PREDICTOR: bool = Field(
+        default=False,
+        description="P4: Prophet 趨勢預測是否啟用（預測 4h 內超閾值風險）",
+    )
+    AIOPS_P4_PROACTIVE_INSPECTOR: bool = Field(
+        default=False,
+        description="P4: 主動巡檢每 5min 是否執行",
+    )
+
+    # ==========================================================================
+    # Phase 5 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P5_BLAST_RADIUS_CHECK: bool = Field(
+        default=False,
+        description="P5: Blast Radius 評估是否執行（False = 全部視為低風險自動執行，危險）",
+    )
+    AIOPS_P5_GITOPS_PR: bool = Field(
+        default=False,
+        description="P5: 高風險修復（Blast Radius > 50）是否走 GitOps Gitea PR 流程",
+    )
+    AIOPS_P5_DRY_RUN_ENFORCED: bool = Field(
+        default=False,
+        description="P5: Declarative apply 前是否強制 dry-run（False = 跳過 dry-run，危險）",
+    )
+
+    # ==========================================================================
+    # Phase 6 細粒度子開關
+    # ==========================================================================
+
+    AIOPS_P6_SELF_DEMOTION: bool = Field(
+        default=False,
+        description="P6: 自我降級邏輯是否啟用（SLO 違反 → 自動提高信心閾值）",
+    )
+    AIOPS_P6_OFFLINE_REPLAY: bool = Field(
+        default=False,
+        description="P6: 週度離線回放 100 案是否執行",
+    )
+    AIOPS_P6_KB_ROT_CLEANER: bool = Field(
+        default=False,
+        description="P6: 月度 KB 腐爛清理 job 是否執行",
+    )
+    AIOPS_P6_TRUST_DRIFT_DETECTOR: bool = Field(
+        default=False,
+        description="P6: Playbook trust 分布漂移偵測是否啟用",
+    )
+
+    def is_phase_enabled(self, phase: int) -> bool:
+        """
+        檢查指定 Phase 的總開關是否啟用。
+
+        Args:
+            phase: Phase 編號（1-6）
+
+        Returns:
+            bool: 該 Phase 是否開啟
+
+        Usage:
+            if flags.is_phase_enabled(1):
+                await pre_decision_investigator.investigate(...)
+        """
+        phase_flags = {
+            1: self.AIOPS_P1_ENABLED,
+            2: self.AIOPS_P2_ENABLED,
+            3: self.AIOPS_P3_ENABLED,
+            4: self.AIOPS_P4_ENABLED,
+            5: self.AIOPS_P5_ENABLED,
+            6: self.AIOPS_P6_ENABLED,
+        }
+        return phase_flags.get(phase, False)
+
+    def is_sub_flag_enabled(self, flag_name: str) -> bool:
+        """
+        檢查細粒度子開關（自動驗證父 Phase 開關）。
+
+        Args:
+            flag_name: 子開關名稱，例如 "AIOPS_P1_PRE_DECISION_INVESTIGATOR"
+
+        Returns:
+            bool: 子開關 AND 父 Phase 開關都為 True 才回 True
+
+        Usage:
+            if flags.is_sub_flag_enabled("AIOPS_P1_PRE_DECISION_INVESTIGATOR"):
+                ...
+        """
+        # 解析 Phase 編號
+        parts = flag_name.split("_")
+        if len(parts) < 3 or not parts[1].startswith("P"):
+            return False
+
+        try:
+            phase = int(parts[1][1:])
+        except ValueError:
+            return False
+
+        # 父 Phase 必須開啟
+        if not self.is_phase_enabled(phase):
+            return False
+
+        return bool(getattr(self, flag_name, False))
+
+
+# Singleton — 與 core/config.py 的 settings 相同模式
+# 使用：from src.core.feature_flags import aiops_flags
+aiops_flags = AIOpsFeatureFlags()
+
+
+def get_aiops_flags() -> AIOpsFeatureFlags:
+    """
+    FastAPI dependency injection 用。
+
+    Usage:
+        @router.get("/status")
+        async def status(flags: AIOpsFeatureFlags = Depends(get_aiops_flags)):
+            return {"p1": flags.AIOPS_P1_ENABLED}
+    """
+    return aiops_flags

apps/api/src/jobs/__init__.py

@@ -0,0 +1,15 @@
+"""
+AWOOOI AIOps Jobs
+==================
+定時任務（非 Redis Streams Worker）
+
+目前包含：
+- baseline_snapshot: Phase 0 觀測基線快照
+- knowledge_decay_job: Phase 3 30 天知識遺忘 (待建)
+- detection_feedback_writer: Phase 3 誤判告警回寫 (待建)
+- offline_replay_service: Phase 6 週度離線回放 (待建)
+- kb_rot_cleaner: Phase 6 月度 KB 腐爛清理 (待建)
+
+ADR-080: AI 自主化飛輪總綱
+2026-04-15 ogt: Phase 0 — 初始建立
+"""

apps/api/src/jobs/baseline_snapshot.py

@@ -0,0 +1,338 @@
+"""
+AWOOOI AIOps Phase 0 — 基線快照 Job
+=====================================
+拍攝 AI 自主化飛輪「啟動前現況」，作為 Phase 0→1 進展衡量基準。
+
+快照涵蓋 ADR-080 診斷表中的 6 大指標：
+  1. MCP 呼叫次數/24h（目標：> 0；現況預估：0）
+  2. Playbook trust/confidence 分佈（目標：動態；現況：全靜態）
+  3. 學習閉環觸發率（目標：≥ 99%；現況：0%，fire-and-forget）
+  4. 告警分類 general 比例（目標：< 10%；現況：~ 41%）
+  5. 修復動作 RESTART 比例（目標：< 40%；現況：~ 68%）
+  6. 自動執行成功次數/24h（目標：> 0；現況：0）
+
+儲存策略：
+  - Redis Key `aiops:baseline:{timestamp_iso}` — 最新快照（TTL 永不過期）
+  - Redis Key `aiops:baseline:latest` — 指向最新快照的時間戳（方便 API 讀取）
+
+使用方式：
+  python -m src.jobs.baseline_snapshot          # 直接執行（一次性）
+  await take_baseline_snapshot()                 # 從程式碼呼叫
+
+ADR-080: AI 自主化飛輪總綱
+MASTER: docs/superpowers/specs/2026-04-15-MASTER-ai-autonomous-flywheel-v2.md §5 Phase 0
+
+2026-04-15 ogt + Claude Sonnet 4.6 (亞太): Phase 0 — 初始建立
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+from datetime import timedelta
+
+import structlog
+from sqlalchemy import func, select, text
+
+from src.core.redis_client import get_redis
+from src.db.base import get_db_context
+from src.db.models import (
+    AutoRepairExecution,
+    IncidentRecord,
+    KnowledgeEntryRecord,
+)
+from src.utils.timezone import now_taipei
+
+logger = structlog.get_logger(__name__)
+
+# Redis 鍵
+BASELINE_KEY_PREFIX = "aiops:baseline:"
+BASELINE_LATEST_KEY = "aiops:baseline:latest"
+
+# Playbook Redis 前綴（同 playbook_repository.py）
+PLAYBOOK_KEY_PREFIX = "playbook:"
+
+
+async def take_baseline_snapshot() -> dict:
+    """
+    拍攝一次完整基線快照並寫入 Redis。
+
+    Returns:
+        dict: 快照內容（含 snapshot_at 時間戳）
+    """
+    now = now_taipei()
+    since_24h = now - timedelta(hours=24)
+    ts_iso = now.isoformat()
+
+    logger.info("baseline_snapshot_start", snapshot_at=ts_iso)
+
+    snapshot = {
+        "snapshot_at": ts_iso,
+        "phase": "P0",
+        "description": "AI 自主化飛輪 Phase 0 啟動前基線",
+        "metrics": {},
+    }
+
+    # ── 1. MCP 呼叫次數/24h ───────────────────────────────────────────────
+    # Phase 0 時 MCP 尚未接入任何決策流程 → 預期為 0
+    # Phase 1 完成後此數字應 > 0（PreDecisionInvestigator 開始呼叫）
+    mcp_calls_24h = await _count_mcp_calls_24h(since_24h)
+    snapshot["metrics"]["mcp_calls_24h"] = mcp_calls_24h
+
+    # ── 2. Playbook confidence 分佈（Redis 掃描）──────────────────────────
+    playbook_stats = await _playbook_confidence_stats()
+    snapshot["metrics"]["playbook"] = playbook_stats
+
+    # ── 3. 學習閉環觸發率 + 其他 DB 指標 ─────────────────────────────────
+    db_metrics = await _db_metrics(since_24h)
+    snapshot["metrics"].update(db_metrics)
+
+    # ── 4. 計算衍生指標 ───────────────────────────────────────────────────
+    snapshot["metrics"]["learning_loop_rate"] = _compute_learning_rate(
+        db_metrics.get("auto_repair_24h", 0),
+        db_metrics.get("learning_writes_24h", 0),
+    )
+
+    # ── 寫入 Redis ─────────────────────────────────────────────────────────
+    await _persist_to_redis(ts_iso, snapshot)
+
+    logger.info(
+        "baseline_snapshot_done",
+        snapshot_at=ts_iso,
+        mcp_calls_24h=mcp_calls_24h,
+        playbook_total=playbook_stats.get("total", 0),
+        incidents_24h=db_metrics.get("incidents_24h", 0),
+        auto_repair_success_24h=db_metrics.get("auto_repair_success_24h", 0),
+    )
+
+    return snapshot
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Internal helpers
+# ─────────────────────────────────────────────────────────────────────────────
+
+
+async def _count_mcp_calls_24h(since_24h) -> int:
+    """
+    MCP 呼叫次數/24h。
+
+    Phase 0：無 MCP Calls Table → 從 audit_logs 嘗試計數。
+    Phase 1 建立 PreDecisionInvestigator 後，此處改為查 mcp_tool_calls 表。
+    """
+    try:
+        async with get_db_context() as db:
+            # audit_logs 中 action='mcp_call' — Phase 0 預期 0 筆
+            result = await db.execute(
+                text(
+                    "SELECT COUNT(*) FROM audit_logs "
+                    "WHERE action = 'mcp_call' AND created_at >= :since"
+                ),
+                {"since": since_24h},
+            )
+            return result.scalar_one_or_none() or 0
+    except Exception:
+        logger.exception("baseline_mcp_count_error")
+        return 0
+
+
+async def _playbook_confidence_stats() -> dict:
+    """
+    掃描 Redis 中全部 Playbook，統計 ai_confidence 分佈。
+
+    指標診斷：
+    - avg_confidence ≈ 0.3 → 佐證「全靜態」現況（Phase 0 基線）
+    - Phase 3 EWMA 上線後，此值應動態分散（std_dev 升高、avg 可能提升）
+    """
+    stats = {
+        "total": 0,
+        "approved": 0,
+        "avg_confidence": 0.0,
+        "min_confidence": None,
+        "max_confidence": None,
+        "never_used": 0,       # success_count + failure_count == 0
+        "action_type_dist": {},
+    }
+
+    try:
+        redis = get_redis()
+        confidences: list[float] = []
+        action_counts: dict[str, int] = {}
+
+        async for key in redis.scan_iter(match=f"{PLAYBOOK_KEY_PREFIX}PB-*", count=200):
+            raw = await redis.get(key)
+            if not raw:
+                continue
+            try:
+                pb = json.loads(raw)
+            except json.JSONDecodeError:
+                continue
+
+            stats["total"] += 1
+
+            if pb.get("status") == "approved":
+                stats["approved"] += 1
+
+            conf = pb.get("ai_confidence", 0.0) or 0.0
+            confidences.append(conf)
+
+            used = (pb.get("success_count", 0) or 0) + (pb.get("failure_count", 0) or 0)
+            if used == 0:
+                stats["never_used"] += 1
+
+            # 統計 repair_steps 中首個 action_type（代表主要修復動作）
+            steps = pb.get("repair_steps", [])
+            if steps:
+                first_action = steps[0].get("action_type", "unknown")
+                action_counts[first_action] = action_counts.get(first_action, 0) + 1
+
+        if confidences:
+            stats["avg_confidence"] = round(sum(confidences) / len(confidences), 4)
+            stats["min_confidence"] = round(min(confidences), 4)
+            stats["max_confidence"] = round(max(confidences), 4)
+
+        # RESTART 比例：佐證 ADR-080 診斷（目標 < 40%）
+        total_actions = sum(action_counts.values())
+        restart_count = action_counts.get("restart_service", 0)
+        stats["restart_ratio"] = round(restart_count / total_actions, 4) if total_actions else 0.0
+        stats["action_type_dist"] = action_counts
+
+    except Exception:
+        logger.exception("baseline_playbook_stats_error")
+
+    return stats
+
+
+async def _db_metrics(since_24h) -> dict:
+    """
+    從 PostgreSQL 取得核心計數指標。
+    """
+    metrics: dict = {
+        "incidents_24h": 0,
+        "incidents_total": 0,
+        "general_alert_ratio": 0.0,
+        "auto_repair_24h": 0,
+        "auto_repair_success_24h": 0,
+        "km_total": 0,
+        "km_vectorized": 0,
+        "learning_writes_24h": 0,
+        "audit_logs_24h": 0,
+    }
+
+    try:
+        async with get_db_context() as db:
+            # Incident 數量（24h + 總計）
+            r = await db.execute(
+                select(func.count(IncidentRecord.incident_id)).where(
+                    IncidentRecord.created_at >= since_24h
+                )
+            )
+            metrics["incidents_24h"] = r.scalar_one_or_none() or 0
+
+            r = await db.execute(select(func.count(IncidentRecord.incident_id)))
+            metrics["incidents_total"] = r.scalar_one_or_none() or 0
+
+            # general 告警比例（alert_category = 'general'）
+            r = await db.execute(
+                select(func.count()).where(
+                    IncidentRecord.alert_category == "general"
+                )
+            )
+            general_count = r.scalar_one_or_none() or 0
+            total = metrics["incidents_total"]
+            metrics["general_alert_ratio"] = round(general_count / total, 4) if total else 0.0
+
+            # 自動修復執行（24h）
+            r = await db.execute(
+                select(func.count(AutoRepairExecution.id)).where(
+                    AutoRepairExecution.created_at >= since_24h
+                )
+            )
+            metrics["auto_repair_24h"] = r.scalar_one_or_none() or 0
+
+            r = await db.execute(
+                select(func.count(AutoRepairExecution.id)).where(
+                    AutoRepairExecution.created_at >= since_24h,
+                    AutoRepairExecution.success.is_(True),
+                )
+            )
+            metrics["auto_repair_success_24h"] = r.scalar_one_or_none() or 0
+
+            # KM 數量 + 向量化率
+            r = await db.execute(select(func.count(KnowledgeEntryRecord.id)))
+            metrics["km_total"] = r.scalar_one_or_none() or 0
+
+            r = await db.execute(
+                select(func.count()).where(
+                    KnowledgeEntryRecord.embedding.is_not(None)
+                )
+            )
+            metrics["km_vectorized"] = r.scalar_one_or_none() or 0
+
+            # 學習寫入數（24h 內新增 KM）
+            r = await db.execute(
+                select(func.count()).where(
+                    KnowledgeEntryRecord.created_at >= since_24h
+                )
+            )
+            metrics["learning_writes_24h"] = r.scalar_one_or_none() or 0
+
+            # audit_logs 24h 計數（Phase 0 預期 = 0）
+            r = await db.execute(
+                text(
+                    "SELECT COUNT(*) FROM audit_logs WHERE created_at >= :since"
+                ),
+                {"since": since_24h},
+            )
+            metrics["audit_logs_24h"] = r.scalar_one_or_none() or 0
+
+    except Exception:
+        logger.exception("baseline_db_metrics_error")
+
+    return metrics
+
+
+def _compute_learning_rate(auto_repair_24h: int, learning_writes_24h: int) -> float:
+    """
+    學習閉環觸發率 = learning_writes_24h / auto_repair_24h。
+
+    Phase 0 診斷：fire-and-forget → 比率為 0%（即使 auto_repair > 0，learning 也可能 = 0）
+    Phase 3 修復後目標：≥ 99%
+    """
+    if auto_repair_24h == 0:
+        return 0.0
+    return round(min(learning_writes_24h / auto_repair_24h, 1.0), 4)
+
+
+async def _persist_to_redis(ts_iso: str, snapshot: dict) -> None:
+    """
+    將快照寫入 Redis：
+    - `aiops:baseline:{ts_iso}` — 歷史記錄（永不過期）
+    - `aiops:baseline:latest` — 最新快照全量（永不過期）
+    """
+    try:
+        redis = get_redis()
+        payload = json.dumps(snapshot, ensure_ascii=False)
+
+        # 歷史記錄（保留全部 snapshot）
+        await redis.set(f"{BASELINE_KEY_PREFIX}{ts_iso}", payload)
+
+        # 最新快照（供 API 快速讀取）
+        await redis.set(BASELINE_LATEST_KEY, payload)
+
+        logger.info("baseline_snapshot_persisted", key=BASELINE_LATEST_KEY)
+    except Exception:
+        logger.exception("baseline_persist_error")
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Entry point（直接執行）
+# ─────────────────────────────────────────────────────────────────────────────
+
+async def _main() -> None:
+    snapshot = await take_baseline_snapshot()
+    print(json.dumps(snapshot, indent=2, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    asyncio.run(_main())

apps/api/src/main.py

@@ -69,6 +69,7 @@ from src.api.v1 import terminal as terminal_v1  # Phase 19.1: Omni-Terminal SSE
 from src.api.v1 import timeline as timeline_v1
 from src.api.v1 import webhooks as webhooks_v1
 from src.core.config import settings
+from src.core.feature_flags import aiops_flags  # ADR-080: AI 自主化飛輪 feature flags 啟動驗證
 from src.core.http_client import close_all_http_clients, init_all_http_clients
 from src.core.logging import get_logger, setup_logging
 from src.core.redis_client import close_redis_pool, init_redis_pool