fix(monitoring): fix production monitoring startup, alertmanager configuration, prometheus alert syntax, and mcp healthcheck
Some checks failed
CI / Lint, Unit Tests & Build (push) Successful in 5m5s
CI / Deploy production (on server) (push) Has been cancelled

This commit is contained in:
Antigravity
2026-05-30 11:42:32 +00:00
parent c266359f63
commit ff0fae9ae7
4 changed files with 30 additions and 32 deletions

View File

@@ -37,7 +37,7 @@ groups:
severity: warning
annotations:
summary: "⚠️ Disk space below 15%"
description: "Only {{ humanizePercentage (div (node_filesystem_avail_bytes{mountpoint='/'}) (node_filesystem_size_bytes{mountpoint='/'})) }} disk space remaining."
description: "Only {{ $value | humanizePercentage }} disk space remaining."
- alert: DiskSpaceCritical
expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) < 0.05

View File

@@ -55,11 +55,14 @@ services:
image: metalmatze/alertmanager-bot:0.4.3
container_name: memento-alertmanager-telegram
restart: unless-stopped
profiles:
- telegram
environment:
TELEGRAM_TOKEN: ${TELEGRAM_BOT_TOKEN:-}
TELEGRAM_ADMIN: ${TELEGRAM_CHAT_ID:-}
TELEGRAM_TOKEN: ${TELEGRAM_BOT_TOKEN:-dummy_token}
TELEGRAM_ADMIN: ${TELEGRAM_CHAT_ID:-0}
ALERTMANAGER_URL: http://alertmanager:9093
STORE: /data/bolt.db
STORE: bolt
BOLT_PATH: /data/bolt.db
LISTEN_ADDR: 0.0.0.0:8080
volumes:
- alertmanager-bot-data:/data
@@ -91,7 +94,7 @@ services:
container_name: memento-postgres-exporter
restart: unless-stopped
env_file:
- /opt/memento/.env.docker
- ../.env.docker
environment:
DATA_SOURCE_NAME: "postgresql://${POSTGRES_USER:-memento}:${POSTGRES_PASSWORD:-memento}@memento-postgres:5432/${POSTGRES_DB:-memento}?sslmode=disable"
ports:
@@ -141,4 +144,4 @@ networks:
driver: bridge
memento-net:
external: true
name: memento_memento-network
name: ${MEMENTO_NETWORK_NAME:-memento_memento-network}