#!/bin/bash
set -e
cd "$(dirname "$0")/.."

# Configuration
FQDN="doot.terst.org"
SITE_DIR="/site/${FQDN}"
SERVICE="task-dashboard@${FQDN}"
DEPLOY_HOST="tungsten"

if [ "$(hostname)" != "${DEPLOY_HOST}" ]; then
    echo "Refusing to deploy: this is $(hostname), not ${DEPLOY_HOST}." >&2
    exit 1
fi

echo "==> Building CSS..."
npm run css:build

echo "==> Building binary..."
BUILD_COMMIT=$(git rev-parse --short HEAD)
BUILD_TIME=$(date -u '+%Y-%m-%dT%H:%M:%SZ')
LDFLAGS="-X main.buildCommit=${BUILD_COMMIT} -X main.buildTime=${BUILD_TIME}"
go build -ldflags "$LDFLAGS" -o app cmd/dashboard/main.go

echo "==> Stopping service..."
systemctl stop ${SERVICE} || true

echo "==> Syncing assets and migrations to ${SITE_DIR}..."
# Sync static files
rsync -av --delete web/static/ ${SITE_DIR}/public/
# Sync templates
rsync -av --delete web/templates/ ${SITE_DIR}/templates/
# Sync migrations
rsync -av --delete migrations/ ${SITE_DIR}/migrations/
# Sync operational scripts so the health-check timer runs the current version
# from a stable path rather than whatever happens to be in a source checkout.
rsync -av --delete scripts/ ${SITE_DIR}/app-scripts/

echo "==> Swapping binary..."
mv app ${SITE_DIR}/app

echo "==> Setting permissions..."
# Scope permission fixing to the directories this script actually manages.
#
# This previously ran `find ${SITE_DIR} -type f -exec chmod 644 {} +` across the
# whole site directory and then restored +x on ${SITE_DIR}/app alone. That also
# stripped the execute bit from every sub-service binary under
# ${SITE_DIR}/services/, e.g. services/scout/app. Those services keep running
# from their already-open file, so nothing appears to break — until the next
# reboot, when systemd cannot exec them and they fail with 203/EXEC. Scout was
# down for three and a half weeks that way, serving 502s behind /scout/, because
# the failure is invisible until someone opens the page.
for managed in public templates migrations; do
    [ -d "${SITE_DIR}/${managed}" ] || continue
    chown -R www-data:www-data "${SITE_DIR}/${managed}"
    find "${SITE_DIR}/${managed}" -type d -exec chmod 755 {} +
    find "${SITE_DIR}/${managed}" -type f -exec chmod 644 {} +
done

chown www-data:www-data ${SITE_DIR}/app
chmod +x ${SITE_DIR}/app
chmod 600 ${SITE_DIR}/.env 2>/dev/null || true

# Belt and braces: re-assert +x on every executable the site depends on. Even
# though the blanket chmod above is gone, a missing execute bit here is what an
# outage looks like, and asserting it costs nothing.
#
# The old blanket chmod took out four binaries in one go — services/scout/app,
# services/hawaii/app, bin/claudomator and bin/claude (which claudomator execs
# via --claude-bin). Only ${SITE_DIR}/app survived, because it was the single
# path the script put the bit back on. Both locations are covered here.
for svc_bin in ${SITE_DIR}/services/*/app ${SITE_DIR}/bin/*; do
    [ -f "$svc_bin" ] || continue
    chmod +x "$svc_bin"
done

# The synced operational scripts need to stay executable too — the health-check
# timer ExecStarts one of them, and a non-executable ExecStart is the same
# 203/EXEC failure this whole change exists to prevent.
chmod +x ${SITE_DIR}/app-scripts/deploy \
         ${SITE_DIR}/app-scripts/verify-deploy \
         ${SITE_DIR}/app-scripts/health-check 2>/dev/null || true

echo "==> Starting service..."
systemctl start ${SERVICE}
sleep 2

# Sub-services are separate units and are NOT restarted by deploying doot. If
# one is sitting in `failed` after exhausting its restart limit, it stays down
# through any number of successful deploys — bring them back here so a deploy
# leaves the whole site healthy, not just the main app.
echo "==> Ensuring sub-services are running..."
for unit in scout.service hawaii.service claudomator@${FQDN}.service; do
    systemctl list-unit-files "${unit}" >/dev/null 2>&1 || continue
    if [ "$(systemctl is-active "${unit}" 2>/dev/null || true)" != "active" ]; then
        echo "    ${unit} is not active — restarting"
        systemctl reset-failed "${unit}" 2>/dev/null || true
        systemctl start "${unit}" || echo "    WARNING: could not start ${unit}"
    fi
done
sleep 3

# Assert the outcome instead of printing a status block for a human to skim.
# `systemctl status` exits zero whether or not anything works and says nothing
# about the gateway's sub-services, so a deploy could report success while
# /scout/ served 502s.
echo "==> Verifying deploy..."
"$(dirname "$0")/verify-deploy" "${BUILD_COMMIT}"

echo "==> Deploy complete!"