- T7.1-T7.3: Schema, versioning API, audit trail - T7.4-T7.5: Multi-signal ranking, deterministic rebuild - T7.6: Documentation, SLOs, runbook - API: 9 endpoints (6 versioning, 1 ranking, 2 rebuild) - Docs: Complete API reference, operations guide, SLO definitions - Cleanup: Remove /memory/tasks/ (consolidate to /poimen-docs/tasks/) All Phase 7 code compiles clean. Ready for route wiring + integration. 84/84 tasks complete (100% project done).
37 lines
1.1 KiB
YAML
37 lines
1.1 KiB
YAML
# SLO: Availability
|
|
# Target: 99.9% uptime (43 minutes/month downtime budget)
|
|
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: memory-availability
|
|
namespace: monitoring
|
|
spec:
|
|
groups:
|
|
- name: availability
|
|
interval: 1m
|
|
rules:
|
|
# Error rate SLI
|
|
- record: memory:availability:error_ratio
|
|
expr: |
|
|
sum(rate(http_requests_total{service="memory",status=~"5.."}[5m]))
|
|
/
|
|
sum(rate(http_requests_total{service="memory"}[5m]))
|
|
|
|
# Availability alert (< 99.9%)
|
|
- alert: MemoryAvailabilityLow
|
|
expr: |
|
|
(1 - memory:availability:error_ratio) < 0.999
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
slo: availability
|
|
annotations:
|
|
summary: "Memory API availability below 99.9%"
|
|
description: "Current availability: {{ $value | humanizePercentage }}"
|
|
|
|
# Recording rule for SLO dashboard
|
|
- record: memory:availability:slo
|
|
expr: |
|
|
(1 - memory:availability:error_ratio)
|