stemedb/docs/operations/monitoring/prometheus/alerts/info.yml
jml 3e7eddc074 feat: add enterprise production readiness infrastructure
This commit implements comprehensive production hardening across multiple
layers to prepare StemeDB for enterprise pilot deployments:

## API Layer
- Add rate limiting middleware with configurable limits per endpoint
- Enhance error handling with detailed context and proper HTTP status codes
- Add security hardening tests for input validation and boundary conditions
- Create store_helpers module for defensive storage access patterns

## Storage & WAL
- Optimize group commit batching for higher throughput
- Add defensive error handling in hybrid backend with proper fallbacks
- Enhance WAL journal durability guarantees with fsync validation
- Improve index store query performance with better caching

## Operations & Deployment
- Add comprehensive operations documentation (deployment, monitoring, DR)
- Create systemd units for backup, WAL archival, and verification
- Add monitoring configs (Prometheus alerts, metrics exporters)
- Implement backup/restore scripts with verification and S3 archival
- Add DR drill automation and runbook procedures
- Create load balancer configs (nginx, envoy) with health checks

## Documentation
- Update CLAUDE.md with operations and troubleshooting guides
- Expand roadmap with production readiness milestones
- Add pilot success criteria and deployment reference architecture
- Document TLS setup, monitoring integration, and incident response

## Configuration
- Add .env.example with all required environment variables
- Document resource sizing for different deployment scales
- Add configuration examples for various deployment topologies

This positions StemeDB for successful enterprise pilots with proper
operational discipline, monitoring, backup/DR, and security hardening.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-12 06:08:15 +00:00

120 lines
5.3 KiB
YAML

groups:
- name: stemedb_info
interval: 5m
rules:
- alert: CircuitBreakerOpen
expr: stemedb_circuit_breakers_open > 0
for: 10m
labels:
severity: info
component: protection
annotations:
summary: "Circuit breaker tripped for agent"
description: "Circuit breaker for {{ $labels.agent_id }} is open on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/circuit-breaker.md"
impact: "Requests from this agent are being rejected. No impact on other agents."
action: "Monitor agent behavior. Circuit will auto-reset if agent recovers."
- alert: QuarantineBacklogGrowing
expr: rate(stemedb_quarantine_entries_total[10m]) > 10
for: 30m
labels:
severity: info
component: quarantine
annotations:
summary: "Quarantine backlog growing (>10/min)"
description: "Quarantine entries increasing at {{ $value }}/min on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/quarantine-backlog.md"
impact: "Manual review queue growing. May delay assertion approval."
action: "Review quarantine entries via GET /v1/admin/quarantine"
- alert: NewNodeJoined
expr: changes(stemedb_cluster_nodes_alive[5m]) > 0
labels:
severity: info
component: cluster
annotations:
summary: "New node joined cluster"
description: "Node count changed on {{ $labels.instance }}. New node may have joined."
runbook: "https://docs.stemedb.com/operations/runbooks/node-join.md"
impact: "None. Informational alert for cluster topology changes."
action: "Verify expected scaling operation. Monitor replication to new node."
- alert: HighMemoryUsage
expr: process_resident_memory_bytes{job="stemedb"} > (0.70 * node_memory_MemTotal_bytes)
for: 30m
labels:
severity: info
component: process
annotations:
summary: "Memory usage >70%"
description: "Memory usage is {{ $value | humanize1024 }}B (70% of system memory) on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/memory-usage.md"
impact: "None yet, but approaching critical threshold."
action: "Monitor memory trend. Plan capacity increase if usage continues rising."
- alert: APIKeyRotationDue
expr: (time() - stemedb_api_key_created_timestamp) > (90 * 24 * 60 * 60)
for: 1d
labels:
severity: info
component: security
annotations:
summary: "API key older than 90 days"
description: "API key {{ $labels.key_id }} was created {{ $value | humanizeDuration }} ago on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/api-key-rotation.md"
impact: "None. Reminder to follow key rotation policy."
action: "Rotate API key via POST /v1/admin/api_keys/rotate"
- alert: GoldStandardCountLow
expr: stemedb_gold_standard_count < 3
for: 1h
labels:
severity: info
component: trust
annotations:
summary: "Gold standard count <3"
description: "Only {{ $value }} gold standards configured on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/gold-standards.md"
impact: "Trust calibration may be less accurate with fewer gold standards."
action: "Consider adding more gold standard entries for better trust ranking."
- alert: CertificateExpiringIn30Days
expr: (stemedb_tls_certificate_expiry_seconds - time()) < (30 * 24 * 60 * 60)
for: 1d
labels:
severity: info
component: tls
annotations:
summary: "TLS certificate expires in <30 days"
description: "Certificate for {{ $labels.instance }} expires in {{ $value | humanizeDuration }}."
runbook: "https://docs.stemedb.com/operations/runbooks/certificate-renewal.md"
impact: "None yet. Advance notice for renewal."
action: "Schedule certificate renewal before expiry."
- alert: WALSegmentCountHigh
expr: stemedb_wal_segments_count > 100
for: 1h
labels:
severity: info
component: wal
annotations:
summary: "WAL has >100 segments"
description: "WAL segment count is {{ $value }} on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/wal-cleanup.md"
impact: "None. May indicate cleanup not running or high write volume."
action: "Verify cleanup cron job is running. Adjust retention if needed."
- alert: LowQueryThroughput
expr: rate(stemedb_http_requests_total{path=~"/v1/query.*"}[5m]) < 0.1
for: 1h
labels:
severity: info
component: api
annotations:
summary: "Query throughput <0.1/sec for 1 hour"
description: "Query rate is {{ $value }}/sec on {{ $labels.instance }}."
runbook: "https://docs.stemedb.com/operations/runbooks/low-traffic.md"
impact: "None. May indicate low usage or upstream issue."
action: "Verify expected traffic patterns. Check client connectivity."