dchain/deploy/single/update.sh

#!/usr/bin/env bash
# deploy/single/update.sh — pull-and-restart update for a DChain single node.
#
# Modes
# ─────
# 1. RELEASE mode (preferred):   DCHAIN_UPDATE_SOURCE_URL is set, node has
#    /api/update-check — we trust that endpoint to tell us what's latest,
#    then git-checkout the matching tag.
# 2. BRANCH mode (fallback):     follow origin/main HEAD.
#
# Both modes share the same safety flow:
#   - Fast-forward check (no auto-rewriting local history).
#   - Smoke-test the new binary BEFORE killing the running container.
#   - Pre-restart best-effort health probe.
#   - Poll /api/netstats after restart, fail loud if unhealthy in 60s.
#
# Semver guard
# ────────────
# If UPDATE_ALLOW_MAJOR=false (default), the script refuses to cross a major
# version boundary (v1.x → v2.y). Operator must flip the env var or bump
# manually, avoiding surprise breaking changes from unattended restarts.
#
# Exit codes:
#   0 — up to date or successfully updated
#   1 — new container didn't become healthy
#   2 — smoke test of new image failed
#   3 — git state issue (fetch failed, not fast-forwardable, etc.)
#   4 — semver guard blocked the update

set -euo pipefail

REPO_DIR="${REPO_DIR:-/opt/dchain}"
COMPOSE_FILE="${COMPOSE_FILE:-$REPO_DIR/deploy/single/docker-compose.yml}"
IMAGE_NAME="${IMAGE_NAME:-dchain-node-slim}"
CONTAINER="${CONTAINER:-dchain_node}"
HEALTH_URL="${HEALTH_URL:-http://127.0.0.1:8080/api/netstats}"
UPDATE_CHECK_URL="${UPDATE_CHECK_URL:-http://127.0.0.1:8080/api/update-check}"
GIT_REMOTE="${GIT_REMOTE:-origin}"
GIT_BRANCH="${GIT_BRANCH:-main}"
UPDATE_ALLOW_MAJOR="${UPDATE_ALLOW_MAJOR:-false}"

log() { printf '%s %s\n' "$(date -Iseconds)" "$*"; }
die() { log "ERROR: $*"; exit "${2:-1}"; }

command -v docker >/dev/null || die "docker not on PATH" 3
command -v git    >/dev/null || die "git not on PATH"    3
command -v curl   >/dev/null || die "curl not on PATH"   3

cd "$REPO_DIR" || die "cannot cd to REPO_DIR=$REPO_DIR" 3

# ── Auth header for /api/update-check + /api/netstats on private nodes ────
auth_args=()
[[ -n "${DCHAIN_API_TOKEN:-}" ]] && auth_args=(-H "Authorization: Bearer ${DCHAIN_API_TOKEN}")

# ── 1. Discover target version ────────────────────────────────────────────
target_tag=""
target_commit=""

if [[ -n "${DCHAIN_UPDATE_SOURCE_URL:-}" ]]; then
    log "querying release source via $UPDATE_CHECK_URL"
    check_json=$(curl -fsS -m 10 "${auth_args[@]}" "$UPDATE_CHECK_URL" 2>/dev/null || echo "")
    if [[ -n "$check_json" ]]; then
        # Minimal grep-based JSON extraction — avoids adding a jq dependency.
        # The shape is stable: we defined it in api_update_check.go.
        target_tag=$(printf '%s' "$check_json" | grep -o '"tag":"[^"]*"' | head -1 | sed 's/"tag":"\(.*\)"/\1/')
        update_available=$(printf '%s' "$check_json" | grep -o '"update_available":\(true\|false\)' | head -1 | cut -d: -f2)
        if [[ "$update_available" != "true" ]]; then
            log "up to date according to release source ($target_tag) — nothing to do"
            exit 0
        fi
        log "release source reports new tag: $target_tag"
    else
        log "release source query failed — falling back to git branch mode"
    fi
fi

# ── 2. Fetch git ──────────────────────────────────────────────────────────
log "fetching $GIT_REMOTE"
git fetch --quiet --tags "$GIT_REMOTE" "$GIT_BRANCH" || die "git fetch failed" 3

local_sha=$(git rev-parse HEAD)
if [[ -n "$target_tag" ]]; then
    # Release mode: target is the tag we just read from the API.
    if ! git rev-parse --verify "refs/tags/$target_tag" >/dev/null 2>&1; then
        die "release tag $target_tag unknown to local git — fetch may have missed it" 3
    fi
    target_commit=$(git rev-parse "refs/tags/$target_tag^{commit}")
else
    # Branch mode: target is remote branch HEAD.
    target_commit=$(git rev-parse "$GIT_REMOTE/$GIT_BRANCH")
    target_tag=$(git describe --tags --abbrev=0 "$target_commit" 2>/dev/null || echo "$target_commit")
fi

if [[ "$local_sha" == "$target_commit" ]]; then
    log "up to date at $local_sha — nothing to do"
    exit 0
fi
log "updating $local_sha → $target_commit ($target_tag)"

# ── 3. Semver guard ───────────────────────────────────────────────────────
# Extract major components from vX.Y.Z tags; refuse to cross boundary unless
# operator opts in. Treats non-semver tags (e.g. raw SHA in branch mode) as
# unversioned — guard is a no-op there.
current_tag=$(cat "$REPO_DIR/.last-update" 2>/dev/null || echo "")
if [[ -z "$current_tag" ]]; then
    current_tag=$(git describe --tags --abbrev=0 "$local_sha" 2>/dev/null || echo "")
fi
current_major=$(printf '%s' "$current_tag" | sed -nE 's/^v([0-9]+)\..*/\1/p')
target_major=$(printf '%s' "$target_tag"  | sed -nE 's/^v([0-9]+)\..*/\1/p')
if [[ -n "$current_major" && -n "$target_major" && "$current_major" != "$target_major" ]]; then
    if [[ "$UPDATE_ALLOW_MAJOR" != "true" ]]; then
        die "major version jump $current_tag → $target_tag blocked — set UPDATE_ALLOW_MAJOR=true to override" 4
    fi
    log "semver guard: accepting major jump $current_tag → $target_tag (UPDATE_ALLOW_MAJOR=true)"
fi

# ── 4. Fast-forward / checkout ────────────────────────────────────────────
if [[ -n "$target_tag" ]] && git rev-parse --verify "refs/tags/$target_tag" >/dev/null 2>&1; then
    # Release mode: check out the tag in detached HEAD.
    git checkout --quiet "$target_tag" || die "checkout $target_tag failed" 3
else
    git merge --ff-only "$GIT_REMOTE/$GIT_BRANCH" || die "cannot fast-forward — manual merge required" 3
fi

# ── 5. Build image with version metadata ──────────────────────────────────
version_tag="$target_tag"
version_commit="$target_commit"
version_date=$(date -u +%Y-%m-%dT%H:%M:%SZ)
version_dirty=$(git diff --quiet HEAD -- 2>/dev/null && echo false || echo true)

log "building image $IMAGE_NAME:$version_commit ($version_tag)"
docker build --quiet \
    --build-arg "VERSION_TAG=$version_tag" \
    --build-arg "VERSION_COMMIT=$version_commit" \
    --build-arg "VERSION_DATE=$version_date" \
    --build-arg "VERSION_DIRTY=$version_dirty" \
    -t "$IMAGE_NAME:$version_commit" \
    -t "$IMAGE_NAME:latest" \
    -f deploy/prod/Dockerfile.slim . \
    || die "docker build failed" 2

# ── 6. Smoke-test the new binary ──────────────────────────────────────────
log "smoke-testing new image"
smoke=$(docker run --rm --entrypoint /usr/local/bin/node "$IMAGE_NAME:$version_commit" --version 2>&1) \
    || die "new image --version failed: $smoke" 2
log "smoke ok: $smoke"

# ── 7. Recreate the container ─────────────────────────────────────────────
log "recreating container $CONTAINER"
docker compose -f "$COMPOSE_FILE" up -d --force-recreate node \
    || die "docker compose up failed" 1

# ── 8. Wait for health ────────────────────────────────────────────────────
log "waiting for health at $HEALTH_URL"
for i in $(seq 1 30); do
    if curl -fsS -m 3 "${auth_args[@]}" "$HEALTH_URL" >/dev/null 2>&1; then
        log "node healthy after $((i*2))s — update done ($version_tag @ ${version_commit:0:8})"
        printf '%s\n' "$version_tag" > .last-update
        exit 0
    fi
    sleep 2
done

log "new container did not become healthy in 60s — dumping logs"
docker logs --tail 80 "$CONTAINER" || true
exit 1