awoooi/apps/api/scripts/update_playbook_alert_variants.py

"""
Phase 2 飛輪修復：補齊 Playbook alertname 變體
=================================================
直接更新 Redis 裡的 Playbook symptom_pattern.alert_names，
並重建 playbook:index:alert:* 索引。

用法（在 API pod 內執行）:
    python scripts/update_playbook_alert_variants.py

或從本機執行（需能連 Redis）:
    AWOOOI_REDIS_URL=redis://192.168.0.188:6380/10 python scripts/update_playbook_alert_variants.py

2026-04-10 Asia/Taipei — Claude Sonnet 4.6
"""

import asyncio
import json
import os
import sys

import redis

# Playbook 補充的 alertname 變體
# key: playbook name (用於搜尋), value: 新增的 alertname list
VARIANTS: dict[str, list[str]] = {
    "high-cpu-restart": [
        "HighCPUUsage",
        "ContainerCpuUsageSecondsTotal",
        "HostHighCpuLoad",
        "NodeCPUUsageHigh",
        "CPUThrottlingHigh",
        "KubeCPUOvercommit",
    ],
    "crashloop-pod-delete": [
        "KubePodCrashLooping",
        "PodCrashLoopBackOff",
        "KubernetesPodCrashLooping",
    ],
    "oom-killed-pod-delete": [
        "PodOOMKilled",
        "KubePodOOMKilled",
        "KubernetesMemoryPressure",
        "NodeMemoryUsageHigh",
        "HighMemoryUsage",
    ],
    "k8s-pod-not-ready-restart": [
        "KubePodNotReady",
        "PodNotReady",
        "KubernetesDeploymentReplicasMismatch",
    ],
    "insufficient-replicas-scale": [
        "KubeDeploymentReplicasMismatch",
        "InsufficientReplicas",
        "KubernetesReplicasMismatch",
    ],
}

PLAYBOOK_KEY_PREFIX = "playbook:"
PLAYBOOK_INDEX_ALERT_PREFIX = "playbook:index:alert:"
PLAYBOOK_TTL_SECONDS = 86400 * 30  # 30 天


def get_redis_client() -> redis.Redis:
    url = os.environ.get("AWOOOI_REDIS_URL", "redis://192.168.0.188:6380/10")
    return redis.Redis.from_url(url)


def update_playbooks(r: redis.Redis) -> None:
    # 掃描所有 Playbook keys
    all_keys = [k.decode() for k in r.keys(f"{PLAYBOOK_KEY_PREFIX}PB-*")]
    print(f"Found {len(all_keys)} playbook keys in Redis")

    updated = 0
    skipped = 0

    for key in all_keys:
        raw = r.get(key)
        if not raw:
            continue

        pb = json.loads(raw)
        pb_name = pb.get("name", "")

        if pb_name not in VARIANTS:
            skipped += 1
            continue

        target_alerts = VARIANTS[pb_name]
        sp = pb.get("symptom_pattern", {})
        current_alerts: list[str] = sp.get("alert_names", [])

        # 合併（保留現有 + 加入新的，去重）
        merged = list(dict.fromkeys(current_alerts + target_alerts))

        if merged == current_alerts:
            print(f"  {pb_name}: already up to date, skip")
            skipped += 1
            continue

        sp["alert_names"] = merged
        pb["symptom_pattern"] = sp

        # 寫回 Redis
        r.set(key, json.dumps(pb, ensure_ascii=False), ex=PLAYBOOK_TTL_SECONDS)

        # 重建 alert index
        pb_id = pb.get("playbook_id", key.replace(PLAYBOOK_KEY_PREFIX, ""))
        for alert_name in merged:
            idx_key = f"{PLAYBOOK_INDEX_ALERT_PREFIX}{alert_name}"
            r.sadd(idx_key, pb_id)
            r.expire(idx_key, PLAYBOOK_TTL_SECONDS)

        added = [a for a in merged if a not in current_alerts]
        print(f"  {pb_name}: added {added}")
        updated += 1

    print(f"\nDone: {updated} updated, {skipped} skipped")

    # 驗證
    print("\nVerification:")
    for check_alert in [
        "HostHighCpuLoad", "KubernetesPodCrashLooping",
        "NodeMemoryUsageHigh", "HighMemoryUsage",
        "KubernetesReplicasMismatch",
    ]:
        idx_key = f"{PLAYBOOK_INDEX_ALERT_PREFIX}{check_alert}"
        members = [m.decode() for m in r.smembers(idx_key)]
        status = "✅" if members else "❌"
        print(f"  {status} {check_alert} → {members}")


if __name__ == "__main__":
    r = get_redis_client()
    try:
        r.ping()
        print(f"Redis connected: {os.environ.get('AWOOOI_REDIS_URL', 'redis://192.168.0.188:6380/10')}\n")
    except Exception as e:
        print(f"Redis connection failed: {e}")
        sys.exit(1)

    update_playbooks(r)