fix(monitoring): fix production monitoring startup, alertmanager configuration, prometheus alert syntax, and mcp healthcheck

2026-05-30 11:42:32 +00:00
parent c266359f63
commit ff0fae9ae7
4 changed files with 30 additions and 32 deletions
--- a/monitoring/alerts.yml
+++ b/monitoring/alerts.yml
@@ -37,7 +37,7 @@ groups:
          severity: warning
        annotations:
          summary: "⚠️ Disk space below 15%"
-          description: "Only {{ humanizePercentage (div (node_filesystem_avail_bytes{mountpoint='/'}) (node_filesystem_size_bytes{mountpoint='/'})) }} disk space remaining."
+          description: "Only {{ $value | humanizePercentage }} disk space remaining."

      - alert: DiskSpaceCritical
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.05