ATOCore/deploy/dalidou/deploy.sh

#!/usr/bin/env bash
#
# deploy/dalidou/deploy.sh
# -------------------------
# One-shot deploy script for updating the running AtoCore container
# on Dalidou from the current Gitea main branch.
#
# The script is idempotent and safe to re-run. It handles both the
# first-time deploy (where /srv/storage/atocore/app may not yet be
# a git checkout) and the ongoing update case (where it is).
#
# Usage
# -----
#
#   # Normal update from main (most common)
#   bash deploy/dalidou/deploy.sh
#
#   # Deploy a specific branch or tag
#   ATOCORE_BRANCH=codex/some-feature bash deploy/dalidou/deploy.sh
#
#   # Dry-run: show what would happen without touching anything
#   ATOCORE_DEPLOY_DRY_RUN=1 bash deploy/dalidou/deploy.sh
#
# Environment variables
# ---------------------
#
#   ATOCORE_APP_DIR      default /srv/storage/atocore/app
#   ATOCORE_GIT_REMOTE   default http://dalidou:3000/Antoine/ATOCore.git
#   ATOCORE_BRANCH       default main
#   ATOCORE_DEPLOY_DRY_RUN  if set to 1, report only, no mutations
#   ATOCORE_HEALTH_URL   default http://127.0.0.1:8100/health
#
# Safety rails
# ------------
#
# - If the app dir exists but is NOT a git repo, the script renames
#   it to <dir>.pre-git-<timestamp> before re-cloning, so you never
#   lose the pre-existing snapshot to a git clobber.
# - If the health check fails after restart, the script exits
#   non-zero and prints the container logs tail for diagnosis.
# - Dry-run mode is the default recommendation for the first deploy
#   on a new environment: it shows the planned git operations and
#   the compose command without actually running them.
#
# What this script does NOT do
# ----------------------------
#
# - Does not manage secrets / .env files. The caller is responsible
#   for placing deploy/dalidou/.env before running.
# - Does not run a backup before deploying. Run the backup endpoint
#   first if you want a pre-deploy snapshot.
# - Does not roll back on health-check failure. If deploy fails,
#   the previous container is already stopped; you need to redeploy
#   a known-good commit to recover.
# - Does not touch the database. The Phase 9 schema migrations in
#   src/atocore/models/database.py::_apply_migrations are idempotent
#   ALTER TABLE ADD COLUMN calls that run at service startup via the
#   lifespan handler. Stale pre-Phase-9 schema is upgraded in place.

set -euo pipefail

APP_DIR="${ATOCORE_APP_DIR:-/srv/storage/atocore/app}"
GIT_REMOTE="${ATOCORE_GIT_REMOTE:-http://dalidou:3000/Antoine/ATOCore.git}"
BRANCH="${ATOCORE_BRANCH:-main}"
HEALTH_URL="${ATOCORE_HEALTH_URL:-http://127.0.0.1:8100/health}"
DRY_RUN="${ATOCORE_DEPLOY_DRY_RUN:-0}"
COMPOSE_DIR="$APP_DIR/deploy/dalidou"

log() { printf '==> %s\n' "$*"; }
run() {
    if [ "$DRY_RUN" = "1" ]; then
        printf '    [dry-run] %s\n' "$*"
    else
        eval "$@"
    fi
}

log "AtoCore deploy starting"
log "  app dir:    $APP_DIR"
log "  git remote: $GIT_REMOTE"
log "  branch:     $BRANCH"
log "  health url: $HEALTH_URL"
log "  dry run:    $DRY_RUN"

# ---------------------------------------------------------------------
# Step 1: make sure $APP_DIR is a proper git checkout of the branch
# ---------------------------------------------------------------------

if [ -d "$APP_DIR/.git" ]; then
    log "Step 1: app dir is already a git checkout; fetching latest"
    run "cd '$APP_DIR' && git fetch origin '$BRANCH'"
    run "cd '$APP_DIR' && git reset --hard 'origin/$BRANCH'"
else
    log "Step 1: app dir is NOT a git checkout; converting"
    if [ -d "$APP_DIR" ]; then
        BACKUP="${APP_DIR}.pre-git-$(date -u +%Y%m%dT%H%M%SZ)"
        log "       backing up existing snapshot to $BACKUP"
        run "mv '$APP_DIR' '$BACKUP'"
    fi
    log "       cloning $GIT_REMOTE -> $APP_DIR (branch: $BRANCH)"
    run "git clone --branch '$BRANCH' '$GIT_REMOTE' '$APP_DIR'"
fi

# ---------------------------------------------------------------------
# Step 2: show what we're deploying
# ---------------------------------------------------------------------

log "Step 2: deployable commit"
if [ "$DRY_RUN" != "1" ] && [ -d "$APP_DIR/.git" ]; then
    ( cd "$APP_DIR" && git log --oneline -1 )
    ( cd "$APP_DIR" && git rev-parse HEAD > /tmp/atocore-deploying-sha.txt )
    DEPLOYING_SHA="$(cat /tmp/atocore-deploying-sha.txt | cut -c1-7)"
    log "  commit: $DEPLOYING_SHA"
else
    log "  [dry-run] would read git log from $APP_DIR"
    DEPLOYING_SHA="dry-run"
fi

# ---------------------------------------------------------------------
# Step 3: preserve the .env file (it's not in git)
# ---------------------------------------------------------------------

ENV_FILE="$COMPOSE_DIR/.env"
if [ "$DRY_RUN" != "1" ] && [ ! -f "$ENV_FILE" ]; then
    log "Step 3: WARNING — $ENV_FILE does not exist"
    log "       the compose workflow needs this file to map mount points"
    log "       copy deploy/dalidou/.env.example to $ENV_FILE and edit it"
    log "       before re-running this script"
    exit 2
fi

# ---------------------------------------------------------------------
# Step 4: rebuild and restart the container
# ---------------------------------------------------------------------

log "Step 4: rebuilding and restarting the atocore container"
run "cd '$COMPOSE_DIR' && docker compose up -d --build"

if [ "$DRY_RUN" = "1" ]; then
    log "dry-run complete — no mutations performed"
    exit 0
fi

# ---------------------------------------------------------------------
# Step 5: wait for the service to come up and pass the health check
# ---------------------------------------------------------------------

log "Step 5: waiting for /health to respond"
for i in 1 2 3 4 5 6 7 8 9 10; do
    if curl -fsS "$HEALTH_URL" > /tmp/atocore-health.json 2>/dev/null; then
        log "       service is responding"
        break
    fi
    log "       not ready yet ($i/10); waiting 3s"
    sleep 3
done

if ! curl -fsS "$HEALTH_URL" > /tmp/atocore-health.json 2>/dev/null; then
    log "FATAL: service did not come up within 30 seconds"
    log "       container logs (last 50 lines):"
    cd "$COMPOSE_DIR" && docker compose logs --tail=50 atocore || true
    exit 3
fi

# ---------------------------------------------------------------------
# Step 6: verify the deployed version matches expectations
# ---------------------------------------------------------------------

log "Step 6: verifying deployed version"
log "  /health response:"
if command -v jq >/dev/null 2>&1; then
    jq . < /tmp/atocore-health.json | sed 's/^/    /'
    REPORTED_VERSION="$(jq -r '.code_version // .version' < /tmp/atocore-health.json)"
else
    cat /tmp/atocore-health.json | sed 's/^/    /'
    echo
    REPORTED_VERSION="$(grep -o '"code_version":"[^"]*"' /tmp/atocore-health.json | head -1 | cut -d'"' -f4)"
    if [ -z "$REPORTED_VERSION" ]; then
        REPORTED_VERSION="$(grep -o '"version":"[^"]*"' /tmp/atocore-health.json | head -1 | cut -d'"' -f4)"
    fi
fi

EXPECTED_VERSION="$(grep -oE "__version__ = \"[^\"]+\"" "$APP_DIR/src/atocore/__init__.py" | head -1 | cut -d'"' -f2)"

log "  expected code_version: $EXPECTED_VERSION (from $APP_DIR/src/atocore/__init__.py)"
log "  reported code_version: $REPORTED_VERSION (from live /health)"

if [ "$REPORTED_VERSION" != "$EXPECTED_VERSION" ]; then
    log "WARNING: deployed version mismatch"
    log "         the container may not have picked up the new image"
    log "         try: docker compose down && docker compose up -d --build"
    exit 4
fi

log "Deploy complete."
log "  commit:       $DEPLOYING_SHA"
log "  code_version: $REPORTED_VERSION"
log "  health:       ok"