#!/usr/bin/env bash
# Open SWE EC2 user-data — PROVISIONING-ONLY (runs once, at first boot).
#
# This is the rationale for `userDataCausesReplacement: true` in CDK: user-data
# does FIRST-BOOT provisioning, never durable runtime config. Editing it is a
# deliberate instance replacement. Durable runtime config is fetched fresh on
# every service start by deploy/seahaven/fetch-config.sh (ExecStartPre).
#
# The box holds NO durable state of its own:
#   - secrets/config  -> Secrets Manager + SSM, materialized to a tmpfs .env at boot
#   - app artifact    -> pulled from S3 (open-swe-<env>-assets) via the instance role
#   - store state     -> reseeded by seed_store.sh (ExecStartPost) on every start
# => there is no RETAIN volume to protect; replacement is tolerated. The EBS
#    discipline (snapshot root + wait state=completed BEFORE any replacing deploy)
#    is the safety net, not durable on-box state. See README "EBS discipline".
#
# Tokens (@@...@@) are substituted by CDK when it renders this script into the
# launch template. region is read from IMDSv2 as a fallback.

set -euo pipefail
exec > >(tee -a /var/log/open-swe-user-data.log) 2>&1
echo "==> open-swe user-data start $(date -u +%FT%TZ)"

# --- CDK-rendered values -----------------------------------------------------
# NOTE: CDK-substituted tokens use %%...%% (rendered by app-service.ts), DISTINCT
# from the @@...@@ tokens this script seds into the baked systemd/nginx templates.
# The two MUST NOT share a delimiter: a shared @@OPENSWE_ENV@@ / @@SERVER_NAME@@
# let CDK clobber the sed PATTERN, leaving the unit's token unsubstituted.
OPENSWE_ENV="%%OPENSWE_ENV%%"               # dev | prod
ASSETS_BUCKET="%%ASSETS_BUCKET%%"           # open-swe-<env>-assets
SERVER_NAME="%%SERVER_NAME%%"               # openswe[-dev].seahaven.com
ARTIFACT_PREFIX="%%ARTIFACT_PREFIX%%"       # e.g. releases/latest

# --- fixed layout (must match provision.sh + templates) ----------------------
SERVICE_USER="openswe"
APP_DIR="/opt/open-swe/app"
VENV="${APP_DIR}/.venv"
WWW_ROOT="/var/www/open-swe"
TEMPLATE_DIR="/opt/open-swe/templates"
ENV_FILE="/run/open-swe/.env"
PORT="2024"
FETCH_CONFIG="${APP_DIR}/deploy/seahaven/fetch-config.sh"
SEED_STORE="${APP_DIR}/deploy/seahaven/seed_store.sh"

# region from IMDSv2
TOKEN="$(curl -fsS -X PUT "http://169.254.169.254/latest/api/token" \
  -H "X-aws-ec2-metadata-token-ttl-seconds: 300" || true)"
AWS_REGION="$(curl -fsS -H "X-aws-ec2-metadata-token: ${TOKEN}" \
  http://169.254.169.254/latest/meta-data/placement/region || echo us-east-1)"
export AWS_DEFAULT_REGION="$AWS_REGION"
echo "env=${OPENSWE_ENV} region=${AWS_REGION} bucket=${ASSETS_BUCKET} host=${SERVER_NAME}"

# --- boot.env: non-secret pointers fetch-config.sh reads ---------------------
install -d -o root -g root -m 0755 /etc/open-swe
cat >/etc/open-swe/boot.env <<EOF
OPENSWE_ENV=${OPENSWE_ENV}
AWS_REGION=${AWS_REGION}
ASSETS_BUCKET=${ASSETS_BUCKET}
ARTIFACT_PREFIX=${ARTIFACT_PREFIX}
ENV_FILE=${ENV_FILE}
SECRETS_PREFIX=open-swe-${OPENSWE_ENV}
SSM_PREFIX=/open-swe-${OPENSWE_ENV}
EOF
chmod 0644 /etc/open-swe/boot.env

# --- ensure the tmpfs for the materialized .env is mounted -------------------
# (baked into /etc/fstab by the AMI; mount it now in case it isn't yet.)
install -d -o root -g root -m 0755 /run/open-swe || true
mountpoint -q /run/open-swe || mount /run/open-swe || mount -t tmpfs \
  -o rw,nosuid,nodev,noexec,mode=0700,uid=${SERVICE_USER},gid=${SERVICE_USER},size=8m \
  tmpfs /run/open-swe

# --- install the deploy script (single source of the app-deploy procedure) ---
# deploy.sh (deploy/ami/deploy.sh) pulls the release from S3, builds the venv with
# `uv sync`, and restarts the service. CDK base64-renders the file into the
# %%DEPLOY_SH_B64%% token below so it is a normal reviewable repo file, not an
# inline heredoc. The `open-swe-<env>-deploy` SSM document runs this same script
# for every subsequent release.
echo "==> install /opt/open-swe/bin/deploy.sh"
install -d -o root -g root -m 0755 /opt/open-swe/bin
base64 -d >/opt/open-swe/bin/deploy.sh <<'DEPLOY_SH_B64'
%%DEPLOY_SH_B64%%
DEPLOY_SH_B64
chmod 0755 /opt/open-swe/bin/deploy.sh

# --- render + install the systemd unit ---------------------------------------
echo "==> install systemd unit"
sed \
  -e "s|@@SERVICE_USER@@|${SERVICE_USER}|g" \
  -e "s|@@APP_DIR@@|${APP_DIR}|g" \
  -e "s|@@VENV@@|${VENV}|g" \
  -e "s|@@PORT@@|${PORT}|g" \
  -e "s|@@ENV_FILE@@|${ENV_FILE}|g" \
  -e "s|@@OPENSWE_ENV@@|${OPENSWE_ENV}|g" \
  -e "s|@@FETCH_CONFIG@@|${FETCH_CONFIG}|g" \
  -e "s|@@SEED_STORE@@|${SEED_STORE}|g" \
  "${TEMPLATE_DIR}/open-swe.service" >/etc/systemd/system/open-swe.service
systemctl daemon-reload

# --- render + install the nginx site -----------------------------------------
echo "==> install nginx site"
sed \
  -e "s|@@SERVER_NAME@@|${SERVER_NAME}|g" \
  -e "s|@@WWW_ROOT@@|${WWW_ROOT}|g" \
  -e "s|@@BACKEND_ADDR@@|127.0.0.1:${PORT}|g" \
  "${TEMPLATE_DIR}/open-swe.nginx.conf" >/etc/nginx/sites-available/open-swe
ln -sfn /etc/nginx/sites-available/open-swe /etc/nginx/sites-enabled/open-swe
rm -f /etc/nginx/sites-enabled/default
nginx -t

# --- CloudWatch agent: 30-day log retention ----------------------------------
echo "==> configure CloudWatch agent (30-day retention)"
sed -e "s|@@OPENSWE_ENV@@|${OPENSWE_ENV}|g" \
  "${TEMPLATE_DIR}/amazon-cloudwatch-agent.json" \
  >/opt/aws/amazon-cloudwatch-agent/etc/open-swe-cw.json
/opt/aws/amazon-cloudwatch-agent/bin/amazon-cloudwatch-agent-ctl \
  -a fetch-config -m ec2 -s \
  -c file:/opt/aws/amazon-cloudwatch-agent/etc/open-swe-cw.json

# --- start nginx FIRST (the security boundary + health surface) --------------
# NOTE: intentionally NO swapfile here. The 8 GB-swapfile OOM hack existed only
# for the on-box Nitro SPA build, which now runs in GitHub Actions -> S3.
# nginx is brought up BEFORE the app is deployed so the ALB target-group health
# check (static `/healthz` -> 200) passes and the box is a healthy target even on
# the very first boot, before any release is published. open-swe.service is
# enabled (boot persistence) but STARTED by deploy.sh once the app is on disk.
echo "==> start nginx"
systemctl enable --now nginx
systemctl reload nginx
systemctl enable open-swe.service

# --- deploy the app (NON-FATAL on first boot) --------------------------------
# deploy.sh pulls the release, builds the venv, and starts open-swe.service. On a
# brand-new env no release exists yet, so this is allowed to fail WITHOUT aborting
# user-data: nginx is already up (healthy target), and the first `build-artifacts`
# run + `open-swe-<env>-deploy` SSM command will bring the app up. A failure here
# is logged, not fatal.
echo "==> initial app deploy (non-fatal if no release is published yet)"
if /opt/open-swe/bin/deploy.sh; then
  echo "==> initial app deploy succeeded"
else
  echo "==> no release yet (or deploy failed): open-swe.service deferred to the next SSM deploy"
fi

echo "==> open-swe user-data done $(date -u +%FT%TZ)"