Oskar Kapala
20f6761a67
- shared aiohttp ClientSession in HAClient (Phase 1 Flag #2 fixed): make_session() factory, session injected at startup, closed on shutdown - Check.run() → list[CheckResult]: clean multi-event interface - first real diagnostic check: entity unavailable > 24h (INSERT OR IGNORE baseline preserves first-seen timestamp) - root cause grouping: emit ha_integration_failed instead of N entity events when ≥50% of integration's entities are unavailable (≥3 min) - alert deduplication via SQLite cooldown window (default 6h) - recovery clears baseline + dedup for immediate re-alert - configurable thresholds: duration, integration %, cooldown - 38 unit tests + 7 integration tests (42 pass, 3 skip w/o live HA) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
43 lines
1.4 KiB
YAML
43 lines
1.4 KiB
YAML
service:
|
|
name: ha-diag-agent
|
|
# Deployed per-host: piha (site: ken) and chelsty-infra (site: chelsty)
|
|
owner_node: per-host
|
|
exposure: local-only
|
|
monitor: true
|
|
|
|
dependencies:
|
|
- homeassistant
|
|
|
|
ports:
|
|
- 8087
|
|
|
|
healthcheck:
|
|
type: http
|
|
path: /health
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 20s
|
|
|
|
restart_policy: unless-stopped
|
|
|
|
persistence:
|
|
paths:
|
|
- /opt/homelab/events
|
|
- /var/lib/ha-diag-agent
|
|
|
|
runtime:
|
|
env_vars:
|
|
- HA_TOKEN # long-lived HA access token (required)
|
|
- HA_URL # http://homeassistant.local:8123
|
|
- NODE_NAME # canonical node name: piha, chelsty-infra
|
|
- LOCATION_TAG # human site label: ken, chelsty
|
|
- CHECK_INTERVAL # heartbeat interval seconds (default: 60)
|
|
- CHECK_INTERVAL_UNAVAILABLE # entity check interval seconds (default: 3600)
|
|
- UNAVAILABLE_THRESHOLD_HOURS # alert threshold (default: 24)
|
|
- INTEGRATION_FAILURE_THRESHOLD_PCT # fraction threshold (default: 0.5)
|
|
- INTEGRATION_FAILURE_MIN_ENTITIES # min count for integration event (default: 3)
|
|
- ALERT_COOLDOWN_HOURS # re-alert suppression (default: 6)
|
|
- PORT # FastAPI port (default: 8087)
|
|
- LOG_LEVEL # default: info
|