feat: refine ISAC design and prepare production deployment

deploy/bootstrap-production.sh

@@ -0,0 +1,29 @@
+#!/bin/sh
+set -eu
+
+bundle_path=${1:-}
+deployment_directory=${2:-/opt/shd-build-production}
+if [ -z "$bundle_path" ] || [ ! -f "$bundle_path" ]; then
+	echo "Usage: bootstrap-production.sh <bootstrap-bundle.json> [deployment-directory]" >&2
+	exit 2
+fi
+
+compose_file="$deployment_directory/compose.production.yml"
+deploy_environment="$deployment_directory/.env.deploy"
+compose() {
+	docker compose --env-file "$deploy_environment" -f "$compose_file" "$@"
+}
+restart_services() {
+	compose up -d --no-build app scheduler
+}
+trap restart_services EXIT
+
+echo "Stopping production before the one-time database bootstrap."
+compose stop scheduler app || true
+compose run --rm --no-deps \
+	-e ALLOW_PRODUCTION_BOOTSTRAP=true \
+	-v "$bundle_path:/import/production-bootstrap.json:ro" \
+	app node scripts/environment-bootstrap-import.mjs \
+	/import/production-bootstrap.json --target production --confirm-empty-target-replace
+
+echo "Production bootstrap completed."

deploy/compose.production.yml

@@ -0,0 +1,55 @@
+name: shd-build-production
+
+services:
+  app:
+    image: ${SHD_IMAGE:-shd-build-production:local}
+    restart: unless-stopped
+    init: true
+    env_file:
+      - .env.production.runtime
+    environment:
+      HOST: 0.0.0.0
+      PORT: 3000
+      BODY_SIZE_LIMIT: 6M
+      SKIP_DEFAULT_USERS: "true"
+      TDR_DATABASE_PATH: /app/data/shd-build-production.db
+      TDR_AVATAR_STORAGE_PATH: /app/data/avatars
+      TDR_GAME_ICON_STORAGE_PATH: /app/data/game-icons
+      APP_ORIGIN: https://shd.build
+      ORIGIN: https://shd.build
+      PASSKEY_RP_ID: shd.build
+      DISCORD_REDIRECT_URI: https://shd.build/auth/discord/callback
+    ports:
+      - "0.0.0.0:${SHD_PRODUCTION_PORT:-3102}:3000"
+    volumes:
+      - shd_production_data:/app/data
+    healthcheck:
+      test:
+        - CMD
+        - node
+        - -e
+        - fetch('http://127.0.0.1:3000/api/health/database').then(r=>{if(!r.ok)process.exit(1)}).catch(()=>process.exit(1))
+      interval: 15s
+      timeout: 5s
+      retries: 8
+      start_period: 30s
+    stop_grace_period: 30s
+
+  scheduler:
+    image: ${SHD_IMAGE:-shd-build-production:local}
+    restart: unless-stopped
+    init: true
+    command:
+      - scheduler
+    env_file:
+      - .env.production.runtime
+    environment:
+      SCHEDULER_URL: http://app:3000/api/internal/scheduler
+    depends_on:
+      app:
+        condition: service_healthy
+    stop_grace_period: 30s
+
+volumes:
+  shd_production_data:
+    name: shd-build-production-data

deploy/deploy-production.sh

@@ -0,0 +1,51 @@
+#!/bin/sh
+set -eu
+
+deployment_directory=${1:-/opt/shd-build-production}
+source_directory=${2:-}
+candidate_image=${3:-}
+if [ -z "$source_directory" ] || [ ! -f "$source_directory/Dockerfile" ] || [ -z "$candidate_image" ]; then
+	echo "Usage: deploy-production.sh <deployment-directory> <source-directory> <candidate-image>" >&2
+	exit 2
+fi
+compose_file="$deployment_directory/compose.production.yml"
+deploy_environment="$deployment_directory/.env.deploy"
+
+compose() {
+	docker compose --env-file "$deploy_environment" -f "$compose_file" "$@"
+}
+
+echo "Building the candidate image while production remains online."
+docker build --label org.opencontainers.image.title=shd-build -t "$candidate_image" "$source_directory"
+
+echo "Stopping only SHD production processes before accessing the embedded database."
+compose stop scheduler app || true
+
+echo "Creating a timestamped production backup when the database exists."
+compose run --rm --no-deps app sh -c \
+	'if [ -f "$TDR_DATABASE_PATH" ]; then node scripts/db-backup.mjs; else echo "No production database exists yet; skipping backup."; fi'
+
+echo "Applying additive schema migrations."
+compose run --rm --no-deps app node scripts/db-migrate.mjs
+
+echo "Starting production."
+compose up -d --no-build --remove-orphans app scheduler
+
+container_id=$(compose ps -q app)
+attempt=0
+while [ "$attempt" -lt 30 ]; do
+	status=$(docker inspect --format '{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}' "$container_id")
+	if [ "$status" = "healthy" ]; then
+		echo "SHD production deployment is healthy."
+		exit 0
+	fi
+	if [ "$status" = "unhealthy" ] || [ "$status" = "exited" ] || [ "$status" = "dead" ]; then
+		break
+	fi
+	attempt=$((attempt + 1))
+	sleep 2
+done
+
+echo "SHD production failed its health check."
+compose logs --tail=150 app
+exit 1

deploy/sync-production-isac-to-staging.sh

@@ -0,0 +1,43 @@
+#!/bin/sh
+set -eu
+
+production_directory=${1:-/opt/shd-build-production}
+staging_directory=${2:-/opt/shd-build-stage}
+confirmation=${3:-}
+if [ "$confirmation" != "--confirm-replace-staging-isac-data" ]; then
+	echo "Usage: sync-production-isac-to-staging.sh [production-dir] [staging-dir] --confirm-replace-staging-isac-data" >&2
+	exit 2
+fi
+
+production_compose_file="$production_directory/compose.production.yml"
+production_environment="$production_directory/.env.deploy"
+staging_compose_file="$staging_directory/compose.staging.yml"
+staging_environment="$staging_directory/.env.deploy"
+snapshot_name="isac-production-$(date -u +%Y-%m-%dT%H-%M-%SZ).json"
+snapshot_path="/tmp/$snapshot_name"
+
+production_compose() {
+	docker compose --env-file "$production_environment" -f "$production_compose_file" "$@"
+}
+staging_compose() {
+	docker compose --env-file "$staging_environment" -f "$staging_compose_file" "$@"
+}
+restart_services() {
+	production_compose up -d --no-build app scheduler || true
+	staging_compose up -d --no-build app scheduler || true
+	rm -f "$snapshot_path"
+}
+trap restart_services EXIT
+
+echo "Stopping production writers for a consistent canonical export."
+production_compose stop scheduler app
+production_compose run --rm --no-deps -v "/tmp:/export" app \
+	node scripts/isac-data-export.mjs "/export/$snapshot_name"
+production_compose up -d --no-build app scheduler
+
+echo "Stopping staging writers before its automatic full and ISAC safety backups."
+staging_compose stop scheduler app
+staging_compose run --rm --no-deps -v "/tmp:/import:ro" app \
+	node scripts/isac-data-import.mjs "/import/$snapshot_name" --confirm-replace-isac-data
+
+echo "Production ISAC data was safely synchronized into staging."