Deploy Development / deploy (push) Successful in 1m0s
Test Suite / pytest-backend (push) Successful in 50s
Test Suite / lint-backend (push) Successful in 0s
Test Suite / build-frontend (push) Successful in 16s
Test Suite / k6 /health Baseline (push) Successful in 35s
Test Suite / playwright-tests (push) Failing after 7m53s
- deploy-prod.yml (Pi): Trigger nur noch workflow_dispatch, kein Lauf bei Push auf main - deploy-prod-llm-node.yml: MEDIA_RETENTION enabled, retention-cron läuft auf llm-node - test.yml: kein workflow_run nach Deploy Production mehr, nur develop gegen Dev - PROD_DEPLOYMENTS.md, CLAUDE.md: llm-node als einzige Prod, Rückfallweg Pi version: 0.8.247 (backend) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
166 lines
6.4 KiB
YAML
166 lines
6.4 KiB
YAML
name: Deploy Production llm-node
|
|
|
|
# Prod-Deployment auf llm-node (192.168.2.144, AMD64), seit dem Cutover 2026-10-29 die einzige Prod.
|
|
# "Deploy Production" (Raspberry Pi) ist nur noch manuell startbar.
|
|
# Runner: llm-node-runner mit einzigem Label linux_host (Host-Modus).
|
|
# Der Pi-Runner (Raspi5-Paperless) hat nur ubuntu-latest und nimmt diesen Job nie an.
|
|
# Compose: docker-compose.yml + docker-compose.llm-node.yml, Konfiguration aus ENV_FILE.
|
|
# Doku: .claude/docs/technical/PROD_DEPLOYMENTS.md
|
|
|
|
on:
|
|
push:
|
|
branches: [main]
|
|
workflow_dispatch:
|
|
|
|
jobs:
|
|
deploy:
|
|
runs-on: linux_host
|
|
env:
|
|
APP_DIR: /home/llmadmin/docker/shinkan-prod
|
|
ENV_FILE: /etc/shinkan/prod.env
|
|
COMPOSE_PROJECT: shinkan-prod
|
|
REPO_URL: http://192.168.2.144:3000/Lars/shinkan-jinkendo.git
|
|
MEDIA_HOST: /srv/shinkan/prod/media
|
|
# Medienbereinigung (retention-cron): disabled | enabled.
|
|
# Seit dem Cutover führt nur llm-node den Medienbestand. Der Pi-retention-cron muss gestoppt sein:
|
|
# beide Seiten teilen den Bestand bei getrennten Datenbanken.
|
|
MEDIA_RETENTION: enabled
|
|
steps:
|
|
- name: Runner prüfen (nur llm-node)
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
if [ "$(hostname)" != "llm-node" ] || [ "$(uname -m)" != "x86_64" ]; then
|
|
echo "✗ Falscher Runner: $(hostname)/$(uname -m), erwartet llm-node/x86_64. Abbruch."
|
|
exit 1
|
|
fi
|
|
echo "✓ Runner $(hostname)/$(uname -m)"
|
|
|
|
- name: Konfiguration prüfen
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
if [ ! -r "$ENV_FILE" ]; then
|
|
echo "✗ $ENV_FILE fehlt oder ist nicht lesbar."
|
|
exit 1
|
|
fi
|
|
env_value() {
|
|
grep -E "^$1=" "$ENV_FILE" | tail -1 | cut -d= -f2- | tr -d "\"'" || true
|
|
}
|
|
if [ -z "$(env_value DB_PASSWORD)" ]; then
|
|
echo "✗ DB_PASSWORD ist in $ENV_FILE nicht gesetzt."
|
|
exit 1
|
|
fi
|
|
# Profile steuert allein MEDIA_RETENTION in diesem Workflow.
|
|
if grep -Eq "^COMPOSE_PROFILES=" "$ENV_FILE"; then
|
|
echo "✗ COMPOSE_PROFILES in $ENV_FILE entfernen; die Bereinigung schaltet MEDIA_RETENTION im Workflow."
|
|
exit 1
|
|
fi
|
|
# Override mountet fest $MEDIA_HOST -> /app/media; abweichende Werte ergäben einen zweiten Mount.
|
|
media_host="$(env_value SHINKAN_MEDIA_HOST)"
|
|
media_root="$(env_value MEDIA_ROOT)"
|
|
if [ -n "$media_host" ] && [ "$media_host" != "$MEDIA_HOST" ]; then
|
|
echo "✗ SHINKAN_MEDIA_HOST=$media_host, erwartet $MEDIA_HOST."
|
|
exit 1
|
|
fi
|
|
if [ -n "$media_root" ] && [ "$media_root" != "/app/media" ]; then
|
|
echo "✗ MEDIA_ROOT=$media_root, erwartet /app/media."
|
|
exit 1
|
|
fi
|
|
case "$MEDIA_RETENTION" in
|
|
disabled|enabled) ;;
|
|
*) echo "✗ MEDIA_RETENTION=$MEDIA_RETENTION, erlaubt: disabled | enabled."; exit 1 ;;
|
|
esac
|
|
echo "✓ $ENV_FILE geprüft, Medien $MEDIA_HOST -> /app/media, Bereinigung $MEDIA_RETENTION"
|
|
|
|
- name: Code aktualisieren
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
cd "$APP_DIR"
|
|
if [ ! -d .git ]; then
|
|
git init -q
|
|
git remote add origin "$REPO_URL"
|
|
fi
|
|
git fetch origin main
|
|
git reset --hard origin/main
|
|
git log -1 --oneline
|
|
|
|
- name: Build und Start
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
echo "=== Deploying Shinkan to PRODUCTION (llm-node) ==="
|
|
cd "$APP_DIR"
|
|
dc() {
|
|
docker compose -p "$COMPOSE_PROJECT" -f docker-compose.yml -f docker-compose.llm-node.yml \
|
|
--env-file "$ENV_FILE" "$@"
|
|
}
|
|
if [ "$MEDIA_RETENTION" = enabled ]; then
|
|
dc --profile media-retention build --no-cache
|
|
dc --profile media-retention up -d --remove-orphans
|
|
else
|
|
dc build --no-cache
|
|
dc up -d --remove-orphans
|
|
# Ein früher gestarteter retention-cron läuft sonst weiter.
|
|
dc --profile media-retention rm -s -f retention-cron
|
|
fi
|
|
|
|
- name: Healthchecks
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
cd "$APP_DIR"
|
|
dc() {
|
|
docker compose -p "$COMPOSE_PROJECT" -f docker-compose.yml -f docker-compose.llm-node.yml \
|
|
--env-file "$ENV_FILE" "$@"
|
|
}
|
|
wait_for() {
|
|
local url="$1" label="$2" i
|
|
for i in $(seq 1 60); do
|
|
if curl -sf -o /dev/null "$url"; then
|
|
echo "✓ $label healthy ($url)"
|
|
return 0
|
|
fi
|
|
sleep 3
|
|
done
|
|
echo "✗ $label nicht erreichbar ($url)"
|
|
return 1
|
|
}
|
|
# HTTP 200 reicht nicht: status=ready, database=true und schema_complete=true.
|
|
wait_ready() {
|
|
local url="$1" label="$2" i body=""
|
|
for i in $(seq 1 60); do
|
|
body="$(curl -sf "$url" || true)"
|
|
if [ -n "$body" ] && printf '%s' "$body" \
|
|
| jq -e '.status == "ready" and .database == true and .schema_complete == true' >/dev/null 2>&1; then
|
|
echo "✓ $label ready ($url)"
|
|
return 0
|
|
fi
|
|
sleep 3
|
|
done
|
|
echo "✗ $label nicht ready ($url):"
|
|
printf '%s' "$body" | jq -c '{status, database, schema_complete}' 2>/dev/null || echo " keine gültige Antwort"
|
|
return 1
|
|
}
|
|
ok=1
|
|
wait_for http://127.0.0.1:8003/api/version "PROD API (direkt)" || ok=0
|
|
if [ "$ok" = 1 ]; then
|
|
wait_ready http://127.0.0.1:8003/api/health/ready "PROD API (direkt)" || ok=0
|
|
fi
|
|
if [ "$ok" = 1 ]; then
|
|
wait_for http://127.0.0.1:3003/api/version "PROD API über Frontend-Nginx" || ok=0
|
|
fi
|
|
if [ "$ok" = 1 ]; then
|
|
wait_ready http://127.0.0.1:3003/api/health/ready "PROD API über Frontend-Nginx" || ok=0
|
|
fi
|
|
if [ "$ok" = 1 ]; then
|
|
wait_for http://127.0.0.1:3003/ "PROD Frontend" || ok=0
|
|
fi
|
|
if [ "$ok" != 1 ]; then
|
|
dc ps || true
|
|
dc logs backend --tail 120 || true
|
|
exit 1
|
|
fi
|
|
echo "=== Shinkan PROD Deploy (llm-node) complete ==="
|