Jeffrey Smith
c470037fb5
Branding: bulk rename across 50+ files (Go, JS, CSS, HTML, YAML, JSON, shell scripts). Fix Helm chart description and git repo URLs. Fix test helper taglines. Admin surface: strip 14 gutted tabs (providers, models, personas, roles, knowledge, memory, tasks, health, routing, capabilities, channels, dashboard, usage, stats). Collapse to 4 categories: People, Workflows, System, Monitoring. Settings surface: strip 11 gutted tabs (models, personas, providers, roles, knowledge, memory, usage, workflows, tasks, data, gitkeys). Keep: general, appearance, profile, teams, connections, notifications. Team-admin surface: strip 5 gutted tabs (personas, providers, knowledge, tasks, usage). Keep: members, groups, connections, workflows, settings, activity. Components: delete chat-pane/ (13 files, 1938 lines) and notes-pane/ (10 files, 2381 lines). main.go: remove stale Health.Prune maintenance goroutine. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
70 lines
2.4 KiB
YAML
70 lines
2.4 KiB
YAML
# Switchboard Core — PrometheusRule alerts (v0.33.0)
|
|
# Source file for the Helm template. Deploy via:
|
|
# monitoring.prometheusRule.enabled: true
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: switchboard-alerts
|
|
spec:
|
|
groups:
|
|
- name: switchboard.rules
|
|
rules:
|
|
# Pod restart (possible OOM)
|
|
- alert: SwitchboardPodRestart
|
|
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)"
|
|
description: "Container {{ $labels.container }} in pod {{ $labels.pod }} restarted."
|
|
|
|
# Provider down for 5+ minutes
|
|
- alert: SwitchboardProviderDown
|
|
expr: switchboard_provider_status > 2
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Provider {{ $labels.provider_config_id }} is down"
|
|
|
|
# DB pool >80% utilized
|
|
- alert: SwitchboardDBPoolExhaustion
|
|
expr: switchboard_db_in_use_connections / switchboard_db_open_connections > 0.8
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "DB connection pool >80% utilized"
|
|
|
|
# HTTP 5xx error rate >5%
|
|
- alert: SwitchboardHighErrorRate
|
|
expr: >
|
|
sum(rate(switchboard_http_requests_total{status=~"5.."}[5m]))
|
|
/ sum(rate(switchboard_http_requests_total[5m])) > 0.05
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "HTTP 5xx error rate exceeds 5%"
|
|
|
|
# Task failure rate >25%
|
|
- alert: SwitchboardTaskFailureRate
|
|
expr: >
|
|
rate(switchboard_task_executions_total{status="error"}[15m])
|
|
/ rate(switchboard_task_executions_total[15m]) > 0.25
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Task failure rate exceeds 25% over 15 minutes"
|
|
|
|
# No completions processed in 15 minutes (canary)
|
|
- alert: SwitchboardNoCompletions
|
|
expr: sum(rate(switchboard_completions_total[10m])) == 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "No completions processed in 15 minutes"
|