fix(metrics): refresh alert chain timestamp from durable evidence
All checks were successful
Code Review / ai-code-review (push) Successful in 9s
CD Pipeline / tests (push) Successful in 5m53s
CD Pipeline / build-and-deploy (push) Successful in 4m13s
CD Pipeline / post-deploy-checks (push) Successful in 1m29s

This commit is contained in:
Your Name
2026-05-19 17:55:47 +08:00
parent f0a9b1e00a
commit c516f9fc71
3 changed files with 218 additions and 0 deletions

View File

@@ -97,6 +97,7 @@ from src.routers import proposals as proposals_router
# Legacy route imports (to be migrated)
from src.routes import agent, notifications, pipelines, plugins
from src.services.adr100_slo_metrics_service import get_adr100_slo_metrics_service
from src.services.alert_chain_metrics_service import get_alert_chain_metrics_service
from src.services.executor import close_executor
from src.services.flywheel_stats_service import get_flywheel_stats_service
@@ -1025,6 +1026,15 @@ app.include_router(platform_v1.router, prefix="/api/v1/platform", tags=["AwoooP
@app.get("/metrics", include_in_schema=False)
async def prometheus_metrics() -> Response:
"""Prometheus metrics endpoint for alerting"""
# 2026-05-19 Codex — T85 Alert Chain DB evidence refresh.
# record_alert_chain_success() 是 process-local gauge部署後第一個 scrape
# 可能尚未收到新 webhook導致 smoke test 誤判 metric 不存在。
# 先用 AwoooP inbound / alert_operation_log 的 durable evidence 回填 last_success。
try:
await get_alert_chain_metrics_service().refresh_last_success_gauge()
except Exception as exc:
logger.warning("prometheus_metrics_alert_chain_evidence_error", error=str(exc))
content = generate_latest().decode("utf-8")
# 2026-05-07 ogt + Claude Sonnet 4.6 — INC-20260507-99ADF2 修復
# 飛輪指標awoooi_flywheel_*)原本只在 /api/v1/stats/flywheel/metrics 暴露,