CD/CD consolidation
This commit is contained in:
62
devops/observability/triage-alerts.yaml
Normal file
62
devops/observability/triage-alerts.yaml
Normal file
@@ -0,0 +1,62 @@
|
||||
groups:
|
||||
- name: triage-ttfs
|
||||
rules:
|
||||
- alert: TriageTtfsFirstEvidenceP95High
|
||||
expr: histogram_quantile(0.95, sum(rate(stellaops_ttfs_first_evidence_seconds_bucket[5m])) by (le)) > 1.5
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "TTFS first evidence p95 high"
|
||||
description: "TTFS first-evidence p95 exceeds 1.5s for 10m (triage experience degraded)."
|
||||
|
||||
- alert: TriageTtfsSkeletonP95High
|
||||
expr: histogram_quantile(0.95, sum(rate(stellaops_ttfs_skeleton_seconds_bucket[5m])) by (le)) > 0.2
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "TTFS skeleton p95 high"
|
||||
description: "TTFS skeleton p95 exceeds 200ms for 10m."
|
||||
|
||||
- alert: TriageTtfsFullEvidenceP95High
|
||||
expr: histogram_quantile(0.95, sum(rate(stellaops_ttfs_full_evidence_seconds_bucket[5m])) by (le)) > 1.5
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "TTFS full evidence p95 high"
|
||||
description: "TTFS full-evidence p95 exceeds 1.5s for 10m."
|
||||
|
||||
- alert: TriageClicksToClosureMedianHigh
|
||||
expr: histogram_quantile(0.50, sum(rate(stellaops_clicks_to_closure_bucket[5m])) by (le)) > 6
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "Clicks-to-closure median high"
|
||||
description: "Median clicks-to-closure exceeds 6 for 15m."
|
||||
|
||||
- alert: TriageEvidenceCompletenessAvgLow
|
||||
expr: (sum(rate(stellaops_evidence_completeness_score_sum[15m])) / clamp_min(sum(rate(stellaops_evidence_completeness_score_count[15m])), 1)) < 3.6
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "Evidence completeness below target"
|
||||
description: "Average evidence completeness score below 3.6 (90%) for 30m."
|
||||
|
||||
- alert: TriageBudgetViolationRateHigh
|
||||
expr: sum(rate(stellaops_performance_budget_violations_total[5m])) by (phase) > 0.05
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
service: triage
|
||||
annotations:
|
||||
summary: "Performance budget violations elevated"
|
||||
description: "Performance budget violation rate exceeds 0.05/s for 10m."
|
||||
Reference in New Issue
Block a user