feat: add traceable scoped AIOps diagnosis

2026-07-04 22:57:28 +08:00
parent 246c99b954
commit 23ee05c7c3
32 changed files with 1179 additions and 25 deletions
@@ -0,0 +1,38 @@
+# AIOps Alert Acceptance Case
+
+## Goal
+
+Validate that the legacy AIOps endpoint can act as a traceable alert-triggered diagnosis entry.
+
+## Input
+
+- Session id: `mvp-demo-aiops-payment-cpu-001`
+- Endpoint: `POST /api/ai_ops`
+- Profile: `mvp-demo`
+- Alert:
+
+```json
+{
+  "sessionId": "mvp-demo-aiops-payment-cpu-001",
+  "alertName": "HighCPUUsage",
+  "service": "payment-service",
+  "severity": "P1",
+  "description": "服务 payment-service 的 CPU 使用率持续超过 80%，当前值为 92%。实例: pod-payment-service-7d8f9c6b5-x2k4m。",
+  "timeRange": "last_15m",
+  "userRequest": "请结合 Prometheus 活动告警、system-metrics 日志和知识库生成告警分析报告。"
+}
+```
+
+## Acceptance Criteria
+
+1. The SSE stream emits a `session` message containing the requested session id.
+2. The AIOps run creates or updates `diagnosis_session` with `agent_flow = AI_OPS`.
+3. The persisted session query contains the alert name, service, severity, time range, and description.
+4. If a final report is generated, `diagnosis_session.answer` contains that report.
+5. `GET /api/diagnosis/{sessionId}/trace` returns the AIOps session, ordered agent steps, and ordered tool invocations.
+6. In payload mode, the report focuses on `HighCPUUsage/payment-service`; unrelated active alerts may appear only as related risk or context, not as separate full root-cause sections.
+
+## Known Limits
+
+- This slice does not add a Verifier Agent to AIOps.
+- Full runtime verification still depends on valid DB, Redis, Milvus/Zilliz, model, and embedding configuration.