Feat rebrand armature (#43)
All checks were successful
CI/CD / detect-changes (push) Successful in 3s
CI/CD / test-frontend (push) Successful in 5s
CI/CD / test-go-pg (push) Successful in 2m34s
CI/CD / test-sqlite (push) Successful in 2m46s
CI/CD / build-and-deploy (push) Successful in 1m55s

Co-authored-by: Jeffrey Smith <jasafpro@gmail.com>
Co-committed-by: Jeffrey Smith <jasafpro@gmail.com>
This commit was merged in pull request #43.
This commit is contained in:
2026-03-31 23:25:37 +00:00
committed by xcaliber
parent fb5284f667
commit 680ec3b897
321 changed files with 956 additions and 1033 deletions

View File

@@ -2,57 +2,57 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: {{ include "switchboard.fullname" . }}-alerts
name: {{ include "armature.fullname" . }}-alerts
labels:
{{- include "switchboard.labels" . | nindent 4 }}
{{- include "armature.labels" . | nindent 4 }}
{{- with .Values.monitoring.prometheusRule.labels }}
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
groups:
- name: switchboard.rules
- name: armature.rules
rules:
- alert: SwitchboardPodRestart
- alert: ArmaturePodRestart
expr: increase(kube_pod_container_status_restarts_total{container="backend"}[1h]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: "Switchboard backend pod restarted (possible OOM)"
- alert: SwitchboardProviderDown
expr: switchboard_provider_status > 2
summary: "Armature backend pod restarted (possible OOM)"
- alert: ArmatureProviderDown
expr: armature_provider_status > 2
for: 5m
labels:
severity: critical
annotations:
summary: "Provider {{`{{ $labels.provider_config_id }}`}} is down"
- alert: SwitchboardDBPoolExhaustion
expr: switchboard_db_in_use_connections / switchboard_db_open_connections > 0.8
- alert: ArmatureDBPoolExhaustion
expr: armature_db_in_use_connections / armature_db_open_connections > 0.8
for: 5m
labels:
severity: warning
annotations:
summary: "DB connection pool >80% utilized"
- alert: SwitchboardHighErrorRate
- alert: ArmatureHighErrorRate
expr: |
sum(rate(switchboard_http_requests_total{status=~"5.."}[5m]))
/ sum(rate(switchboard_http_requests_total[5m])) > 0.05
sum(rate(armature_http_requests_total{status=~"5.."}[5m]))
/ sum(rate(armature_http_requests_total[5m])) > 0.05
for: 5m
labels:
severity: warning
annotations:
summary: "HTTP 5xx error rate exceeds 5%"
- alert: SwitchboardTaskFailureRate
- alert: ArmatureTaskFailureRate
expr: |
rate(switchboard_task_executions_total{status="error"}[15m])
/ rate(switchboard_task_executions_total[15m]) > 0.25
rate(armature_task_executions_total{status="error"}[15m])
/ rate(armature_task_executions_total[15m]) > 0.25
for: 10m
labels:
severity: warning
annotations:
summary: "Task failure rate exceeds 25%"
- alert: SwitchboardNoCompletions
expr: sum(rate(switchboard_completions_total[10m])) == 0
- alert: ArmatureNoCompletions
expr: sum(rate(armature_completions_total[10m])) == 0
for: 15m
labels:
severity: critical