Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions config/prometheus/vmrule.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@ spec:
for: 5m
labels:
severity: critical
service: fraud
team: platform
annotations:
summary: "Fraud operator is down"
description: "The fraud operator has been unreachable for 5+ minutes. Fraud evaluations will not be processed."
Expand All @@ -31,6 +33,8 @@ spec:
for: 5m
labels:
severity: critical
service: fraud
team: platform
annotations:
summary: "High error rate for fraud provider {{ $labels.provider }}"
description: "{{ $value | humanizePercentage }} of calls to provider {{ $labels.provider }} are failing. With FailClosed policy, evaluations will be blocked until this is resolved."
Expand All @@ -43,6 +47,8 @@ spec:
for: 5m
labels:
severity: warning
service: fraud
team: platform
annotations:
summary: "High latency for fraud provider {{ $labels.provider }}"
description: "P99 latency for provider {{ $labels.provider }} is {{ $value }}s, exceeding the 5s threshold."
Expand All @@ -57,6 +63,8 @@ spec:
for: 10m
labels:
severity: warning
service: fraud
team: platform
annotations:
summary: "High reconciliation error rate for fraud evaluations"
description: "{{ $value | humanizePercentage }} of fraud evaluation reconciliations are failing."
Expand All @@ -70,6 +78,8 @@ spec:
for: 15m
labels:
severity: warning
service: fraud
team: platform
annotations:
summary: "Fraud evaluations stuck in Error phase"
description: "{{ $value }} fraud evaluation(s) have been in the Error phase for 15+ minutes. This may indicate a persistent provider failure or misconfiguration."
Expand All @@ -80,6 +90,8 @@ spec:
for: 5m
labels:
severity: warning
service: fraud
team: platform
annotations:
summary: "Fraud evaluation {{ $labels.name }} is degraded"
description: "Fraud evaluation {{ $labels.name }} has been in a degraded state for 5+ minutes, indicating one or more providers returned errors during evaluation."
Expand All @@ -91,6 +103,8 @@ spec:
labels:
severity: warning
slack_channel: user-bot
service: fraud
team: platform
annotations:
summary: "Fraud check returned {{ $labels.decision }} for user {{ $labels.user_ref }}"
description: "FraudEvaluation {{ $labels.name }} returned decision={{ $labels.decision }} for user {{ $labels.user_ref }}. Review the user and take action if needed."
Loading