alerting: Alertmanager + Signal relay deliver firing rules to Frank's phone
- dankclaw/observability/quadlet/alertmanager.container: loopback :9093, config from shared/prometheus/alertmanager.yml, family conventions - shared/prometheus/alertmanager.yml: single signal receiver, group_by alertname, 30s/5m/4h intervals, webhook to host.containers.internal:18093 - scripts/signal-relay.py + .service: host-side user unit, loopback :18093, 15-min dedupe, sends via signal-cli account 318311 - prometheus.yml: alerting block to alertmanager:9093; stale comments fixed - llm-fleet.yml: delivery header; LlmSpecDecodeOff annotation now drafter-agnostic - deploy.sh/deploy-remote.sh/deploy-plan.py: alertmanager service, config copy, relay install, planner routing for config + relay files - homepage: alertmanager status card (loopback probe) - tests: alertmanager in UNITS/loopback/health/PAIRS/planner + five new delivery-path seams (webhook<->relay contract, prometheus target, relay unit, signal-cli account, planner routing) - docs: Alertmanager.md component page, Observability.md, Prometheus.md, index.md, AGENTS.md delivery line
This commit is contained in:
+12
-1
@@ -38,6 +38,7 @@ SERVICE_ORDER = (
|
||||
"loki",
|
||||
"alloy",
|
||||
"node-exporter",
|
||||
"alertmanager",
|
||||
"authentik-postgres",
|
||||
"authentik-server",
|
||||
"authentik-worker",
|
||||
@@ -83,6 +84,7 @@ DANKCLAW_SERVICES = {
|
||||
"loki",
|
||||
"alloy",
|
||||
"node-exporter",
|
||||
"alertmanager",
|
||||
"authentik-postgres",
|
||||
"authentik-server",
|
||||
"authentik-worker",
|
||||
@@ -246,6 +248,10 @@ def services_for_path(path: str, target: str) -> set[str]:
|
||||
_add(services, "searxng")
|
||||
elif group == "prometheus":
|
||||
_add(services, "prometheus")
|
||||
if len(parts) >= 3 and parts[2] == "alertmanager.yml":
|
||||
# The Alertmanager config ships from this directory: a change
|
||||
# to it must redeploy the service that installs it.
|
||||
_add(services, "alertmanager")
|
||||
elif group == "loki":
|
||||
_add(services, "loki")
|
||||
elif group == "alloy":
|
||||
@@ -320,7 +326,7 @@ def services_for_path(path: str, target: str) -> set[str]:
|
||||
# consumer (prometheus before grafana, loki before alloy).
|
||||
if len(parts) >= 4 and parts[2] == "quadlet":
|
||||
name = parts[3].removesuffix(".container")
|
||||
if name in {"prometheus", "grafana", "loki", "alloy", "node-exporter"}:
|
||||
if name in {"prometheus", "grafana", "loki", "alloy", "node-exporter", "alertmanager"}:
|
||||
_add(services, name)
|
||||
return services
|
||||
if len(parts) >= 2 and parts[1] == "gitea":
|
||||
@@ -391,6 +397,11 @@ def services_for_path(path: str, target: str) -> set[str]:
|
||||
name = p.name
|
||||
if name in {"homepage-status.py", "homepage-status.service", "homepage-status.timer"}:
|
||||
_add(services, "homepage")
|
||||
if name in {"signal-relay.py", "signal-relay.service"}:
|
||||
# The Signal relay is installed by the alertmanager deploy, so a
|
||||
# change to it redeploying alertmanager is the only path that
|
||||
# reaches it on the host.
|
||||
_add(services, "alertmanager")
|
||||
if name in {"frank-small.env", "frank-small.service", "serve-frank-small.sh"}:
|
||||
# llama.cpp frank-small (2026-09-16) keeps its unit, env and serve
|
||||
# files here; each one selects frank-small only. The ik_llama.cpp
|
||||
|
||||
Reference in New Issue
Block a user