openvibers/openvibe.host Commits
alerts: ticket when an AI provider balance is under $2 (#299)
Changes
@@@ -27,6 +27,15 @@ groups:labels: { severity: page }annotations:summary: "The readiness check has not completed a run for more than 20 minutes (openvibe-readyhealth.timer; check systemctl status openvibe-readyhealth.service)"++ # OpenVibe.AI's hourly balance probe (AI server/providers/balance.js; DeepSeek). Below $2 the owner must++ # top the provider up before every AI feature on the network starts failing. A ticket (bell), not a page:++ # the account still answers until it reaches zero.++ - alert: OpenVibeAiProviderBalanceLow++ expr: ai_provider_balance_usd < 2++ for: 10m++ labels: { severity: ticket }++ annotations:++ summary: "OpenVibe.AI provider {{ $labels.provider }} balance is ${{ $value | humanize }} (below $2): top it up before AI stops answering"- alert: HighErrorRateexpr: |sum by (service) (rate(http_requests_total{status=~"5.."}[10m]))
@@ -27,6 +27,15 @@ groups:
@@ -27,6 +27,15 @@ groups:
labels: { severity: page }
labels: { severity: page }
annotations:
annotations:
summary: "The readiness check has not completed a run for more than 20 minutes (openvibe-readyhealth.timer; check systemctl status openvibe-readyhealth.service)"
summary: "The readiness check has not completed a run for more than 20 minutes (openvibe-readyhealth.timer; check systemctl status openvibe-readyhealth.service)"
+ # OpenVibe.AI's hourly balance probe (AI server/providers/balance.js; DeepSeek). Below $2 the owner must
+ # top the provider up before every AI feature on the network starts failing. A ticket (bell), not a page:
+ # the account still answers until it reaches zero.
+ - alert: OpenVibeAiProviderBalanceLow
+ expr: ai_provider_balance_usd < 2
+ for: 10m
+ labels: { severity: ticket }
+ annotations:
+ summary: "OpenVibe.AI provider {{ $labels.provider }} balance is ${{ $value | humanize }} (below $2): top it up before AI stops answering"
- alert: HighErrorRate
- alert: HighErrorRate
expr: |
expr: |
sum by (service) (rate(http_requests_total{status=~"5.."}[10m]))
sum by (service) (rate(http_requests_total{status=~"5.."}[10m]))