fix(aiops): suppress repeated llm alert loops

apps/api/src/services/alertmanager_llm_guard.py

@@ -0,0 +1,45 @@
+"""Alertmanager LLM storm guards.
+
+Service-layer Redis helpers used by webhook routers to avoid spawning duplicate
+LLM analysis tasks for the same Alertmanager fingerprint.
+"""
+
+from src.core.logging import get_logger
+from src.core.redis_client import get_redis
+
+logger = get_logger("awoooi.alertmanager_llm_guard")
+
+ALERTMANAGER_LLM_INFLIGHT_LOCK_TTL_SECONDS = 600
+
+
+def alertmanager_llm_inflight_key(fingerprint: str) -> str:
+    """Return the Redis lock key for one Alertmanager fingerprint entering AI analysis."""
+
+    return f"alertmanager:llm_inflight:{fingerprint}"
+
+
+async def try_acquire_alertmanager_llm_lock(
+    fingerprint: str,
+    alert_id: str,
+    *,
+    ttl_seconds: int = ALERTMANAGER_LLM_INFLIGHT_LOCK_TTL_SECONDS,
+) -> bool:
+    """Prevent same-second duplicate Alertmanager deliveries from spawning LLM calls."""
+
+    try:
+        redis = get_redis()
+        acquired = await redis.set(
+            alertmanager_llm_inflight_key(fingerprint),
+            alert_id,
+            ex=ttl_seconds,
+            nx=True,
+        )
+        return bool(acquired)
+    except Exception as exc:
+        logger.warning(
+            "alertmanager_llm_inflight_lock_failed_fail_open",
+            fingerprint=fingerprint,
+            alert_id=alert_id,
+            error=str(exc),
+        )
+        return True

apps/api/src/services/openclaw.py

@@ -124,6 +124,21 @@ def _backfill_kubectl_command(proposal: dict, tools: list) -> None:
 # OpenClaw Service
 # =============================================================================
 
+def _build_alert_cache_context_hash(alert_context: dict | None) -> str:
+    """Build a stable LLM cache scope for repeat alerts without dynamic annotations."""
+
+    if not alert_context:
+        return ""
+
+    alertname = alert_context.get("alertname") or alert_context.get("alert_type", "")
+    category = alert_context.get("alert_category", "")
+    namespace = alert_context.get("namespace", "")
+    target = alert_context.get("target_resource", "")
+    severity = alert_context.get("severity", "")
+    fingerprint = alert_context.get("fingerprint", "")
+    return f"{alertname}:{category}:{namespace}:{target}:{severity}:{fingerprint}"
+
+
 class OpenClawService:
     """
     OpenClaw AI 決策服務 - True LLM + SignOz Integration
@@ -727,9 +742,19 @@ class OpenClawService:
         """
         生成 LLM 快取鍵
 
-        使用 prompt 內容的 SHA256 作為快取鍵，確保相同問題不重複呼叫 LLM
+        有告警上下文時，使用 prompt family + 穩定告警維度，避免 annotations /
+        SignOz 即時數值讓同一告警每 20 秒打穿快取；沒有上下文時仍用完整 prompt。
         """
-        content = f"{prompt}:{context_hash}"
+        if context_hash:
+            prompt_family_source = (
+                "openclaw_alert_analysis"
+                if "## Alert Data:" in prompt
+                else prompt[:512]
+            )
+            prompt_family = hashlib.sha256(prompt_family_source.encode()).hexdigest()[:8]
+            content = f"{prompt_family}:{context_hash}"
+        else:
+            content = prompt
         hash_digest = hashlib.sha256(content.encode()).hexdigest()[:16]
         return f"llm_cache:{hash_digest}"
 
@@ -760,12 +785,7 @@ class OpenClawService:
         # 2026-04-16 ogt + Claude Sonnet 4.6: 修復 — alertname 才是主要識別符
         # 舊版用 alert_type:target_resource → 不同告警 (e.g. PostgreSQLDiskGrowth vs PodCrashLoop)
         # 在 alert_type="custom" 時共用同一快取鍵 → 全部回傳相同 LLM 結果
-        context_hash = ""
-        if alert_context:
-            # alertname 優先；無 alertname 時 fallback 到 alert_type
-            _alertname = alert_context.get("alertname") or alert_context.get("alert_type", "")
-            _target = alert_context.get("target_resource", "")
-            context_hash = f"{_alertname}:{_target}"
+        context_hash = _build_alert_cache_context_hash(alert_context)
 
         cache_key = self._generate_cache_key(prompt, context_hash)