From 96b1ceeb97605ccb4909087a887d9cdf0a349519 Mon Sep 17 00:00:00 2001
From: Brad Stein <Brad.Stein@gmail.com>
Date: Thu, 29 Jan 2026 13:07:37 -0300
Subject: [PATCH] monitoring: stabilize alert queries

---
 services/monitoring/grafana-alerting-config.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/services/monitoring/grafana-alerting-config.yaml b/services/monitoring/grafana-alerting-config.yaml
index 517553f..3f816be 100644
--- a/services/monitoring/grafana-alerting-config.yaml
+++ b/services/monitoring/grafana-alerting-config.yaml
@@ -145,7 +145,7 @@ data:
                 model:
                   intervalMs: 60000
                   maxDataPoints: 43200
-                  expr: avg_over_time((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100)[10m:1m] * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")
+                  expr: avg_over_time((1 - avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) * 100)[10m:1m] * on(instance) group_left(node) label_replace(node_uname_info{nodename!=""}, "node", "$1", "nodename", "(.*)")
                   legendFormat: '{{instance}}'
                   datasource:
                     type: prometheus
@@ -549,7 +549,7 @@ data:
                 model:
                   intervalMs: 60000
                   maxDataPoints: 43200
-                  expr: postmark_api_up
+                  expr: min_over_time(max by (instance) (postmark_api_up)[5m])
                   legendFormat: api up
                   datasource:
                     type: prometheus