Files
ml 8adbd3fac4 Add Clay agent interface, fix registry UI routing, and misc improvements
- Deploy Clay (claude Code web UI) at agent.ladkau.de behind basic auth;
  Traefik proxies to clay's HTTPS port 2633 with insecureSkipVerify
- Document MCP server persistence: binaries need to be baked into the
  Dockerfile, config in /opt/clay/data survives rebuilds
- Document scheduled agent workflows via Gitea Actions on.schedule with
  email reporting via Gmail SMTP
- Fix registry UI: split /v2/ (registry) and / (UI) into separate Traefik
  routers; add registry_internal network
- Add weekly registry GC cron job (/usr/local/bin/registry-gc)
- Remove rate-limit middleware from Gitea router (act_runner polling
  exceeded 60 req/min limit)
- Set Traefik websecure readTimeout: 0 to fix large layer upload 499s
2026-08-01 07:55:20 +02:00

64 lines
2.0 KiB
Bash

#!/usr/bin/env bash
# Checks that all service endpoints are reachable and return the expected HTTP
# status code. Run this after provisioning, before configuring individual services.
# Usage: bash scripts/check-services.sh
set -uo pipefail
# "url expected_status timeout_seconds" tuples
# Nextcloud runs its first-time installation on the initial request (1-2 min),
# so it gets a much longer timeout than the other services.
CHECKS=(
"https://cloud.ladkau.de/dashboard/ 401 10"
"https://gitea.ladkau.de 200 10"
"https://nextcloud.ladkau.de 200 180"
"https://sso.ladkau.de/realms/master 200 10"
"https://mail.ladkau.de 200 10"
"https://cr.ladkau.de/v2/ 401 10"
"https://k8s.ladkau.de 200 10"
"https://vault.ladkau.de 200 10"
"https://dl.ladkau.de 200 10"
"https://agent.ladkau.de 401 10"
)
if ! command -v curl &>/dev/null; then
echo "ERROR: curl not found — install with: apt install curl or brew install curl" >&2
exit 1
fi
echo "==> Checking service endpoints"
FAILED=()
for check in "${CHECKS[@]}"; do
read -r url expected timeout <<< "$check"
if [ "$timeout" -gt 10 ]; then
printf " ... %s (first-run setup may take up to %d s)\n" "$url" "$timeout"
fi
actual=$(curl -sL -o /dev/null -w "%{http_code}" --max-time "$timeout" "$url" 2>/dev/null) || actual="000"
if [ "$actual" = "$expected" ]; then
printf " OK %s (%s)\n" "$url" "$actual"
else
printf " FAIL %s (expected %s, got %s)\n" "$url" "$expected" "$actual"
FAILED+=("$url")
fi
done
echo ""
if [ ${#FAILED[@]} -gt 0 ]; then
echo "ERROR: ${#FAILED[@]} endpoint(s) did not return the expected status:" >&2
for url in "${FAILED[@]}"; do
echo " - ${url}" >&2
done
echo "" >&2
echo " Check container status on the server: docker ps" >&2
echo " Check container logs: docker logs <container>" >&2
echo " Note: Keycloak and Nextcloud may take longer >90s on first boot — wait and retry." >&2
exit 1
fi
echo " All services are reachable."