8f0b915f4b
Lane D deliverable: reproducible execution-plane deployment on a fresh Debian dedicated server (~12 cores, 40 GB RAM, single-node). Artifacts: - bootstrap.sh: Docker Engine, Bun, repo clone, build, systemd install, firewall (deny-by-default), optional Tailscale, disk monitor cron - .env.template: all 8 environment groups documented (Convex, Gitea, model gateway, AgentOS/RivetKit, Zopu agent, daemon, Docker sandbox, service auth) - systemd units: zopu-daemon, zopu-agent (both Restart=always), zopu-health timer (60s), zopu-docker-cleanup timer (daily) - scripts: health-check, update, rollback, docker-cleanup, disk-monitor - Caddyfile: optional reverse proxy (documentation-only by default) - README.md: full runbook with start/stop/log/update/rollback/cleanup procedures, topology documentation, and boundary notes Verified topology (from installed RivetKit source): - registry.start() boots an in-process RivetKit engine (envoy mode) with a native Rust sidecar at http://localhost:6420 (DEFAULT_ENDPOINT in chunk-YDUQHING.js line 4751). createClient() connects back to it. - No separate Rivet Engine process required for single-node operation. - Linux x64 sidecar packages (@rivet-dev/agentos-sidecar-linux-x64-gnu) are available as optional dependencies. Docker / Orb boundary: - Docker Engine installed and zopu user in docker group. - No Docker-backed sandbox code wired; Orb lane contract not yet landed. - Volume pruning omitted from docker-cleanup.sh to protect durable data. Validated: bash -n on all 6 shell scripts; mocked health-check smoke (nc-based TCP probes, mocked systemctl/docker); systemd unit structural checks. No JS/TS/agent files changed.
123 lines
4.0 KiB
Bash
Executable File
123 lines
4.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
#
|
|
# health-check.sh — Probe the Zopu execution plane.
|
|
#
|
|
# Checks (TCP/process-level; no assumed HTTP health routes):
|
|
# 1. zopu-daemon systemd unit is active
|
|
# 2. zopu-agent systemd unit is active
|
|
# 3. RivetKit engine TCP port (RIVET_ENDPOINT, default 6420) accepts connections
|
|
# 4. Flue agent TCP port (PORT, default 3583) accepts connections
|
|
# 5. Docker daemon is reachable
|
|
#
|
|
# Flue does not expose a health endpoint by design. RivetKit's health route
|
|
# is internal to the registry runtime. We use TCP connection checks only.
|
|
#
|
|
# Usage:
|
|
# health-check.sh # print results
|
|
# health-check.sh --quiet # suppress output, exit 0 only if all healthy
|
|
#
|
|
# Exit codes: 0 = all healthy, 1 = one or more unhealthy
|
|
|
|
set -euo pipefail
|
|
|
|
QUIET=false
|
|
[[ "${1:-}" == "--quiet" ]] && QUIET=true
|
|
|
|
GREEN='\033[0;32m'
|
|
RED='\033[0;31m'
|
|
NC='\033[0m'
|
|
|
|
pass() { $QUIET || echo -e " ${GREEN}PASS${NC} $*"; }
|
|
fail() { echo -e " ${RED}FAIL${NC} $*" >&2; FAILURES=$((FAILURES + 1)); }
|
|
|
|
FAILURES=0
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Load environment
|
|
# ---------------------------------------------------------------------------
|
|
ENV_FILE="${ENV_FILE:-/opt/zopu/.env}"
|
|
if [[ -f "$ENV_FILE" ]]; then
|
|
# shellcheck source=/dev/null
|
|
set -a
|
|
. "$ENV_FILE"
|
|
set +a
|
|
fi
|
|
|
|
RIVET_PORT="6420"
|
|
if [[ -n "${RIVET_ENDPOINT:-}" ]]; then
|
|
RIVET_PORT=$(echo "$RIVET_ENDPOINT" | sed -n 's|.*://[^:]*:\([0-9]*\).*|\1|p')
|
|
[[ -z "$RIVET_PORT" ]] && RIVET_PORT="6420"
|
|
fi
|
|
|
|
AGENT_PORT="${PORT:-3583}"
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# TCP probe helper: works on Debian (nc from netcat-openbsd) and macOS.
|
|
# Falls back to bash /dev/tcp if nc is unavailable.
|
|
# ---------------------------------------------------------------------------
|
|
tcp_probe() {
|
|
local host="$1" port="$2"
|
|
if command -v nc &>/dev/null; then
|
|
nc -z -w 5 "$host" "$port" 2>/dev/null
|
|
else
|
|
timeout 5 bash -c "echo > /dev/tcp/${host}/${port}" 2>/dev/null
|
|
fi
|
|
}
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 1. Daemon systemd unit
|
|
# ---------------------------------------------------------------------------
|
|
if systemctl is-active --quiet zopu-daemon 2>/dev/null; then
|
|
pass "zopu-daemon service is active"
|
|
else
|
|
fail "zopu-daemon service is not active"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 2. Agent systemd unit
|
|
# ---------------------------------------------------------------------------
|
|
if systemctl is-active --quiet zopu-agent 2>/dev/null; then
|
|
pass "zopu-agent service is active"
|
|
else
|
|
fail "zopu-agent service is not active"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 3. RivetKit engine TCP port
|
|
# ---------------------------------------------------------------------------
|
|
if tcp_probe localhost "$RIVET_PORT"; then
|
|
pass "RivetKit engine port ${RIVET_PORT} is accepting connections"
|
|
else
|
|
fail "RivetKit engine port ${RIVET_PORT} is not accepting connections"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 4. Flue agent TCP port
|
|
# ---------------------------------------------------------------------------
|
|
if tcp_probe localhost "$AGENT_PORT"; then
|
|
pass "Flue agent port ${AGENT_PORT} is accepting connections"
|
|
else
|
|
fail "Flue agent port ${AGENT_PORT} is not accepting connections"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 5. Docker daemon
|
|
# ---------------------------------------------------------------------------
|
|
if docker info &>/dev/null; then
|
|
pass "Docker daemon is reachable"
|
|
else
|
|
fail "Docker daemon is not reachable"
|
|
fi
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Summary
|
|
# ---------------------------------------------------------------------------
|
|
$QUIET || echo ""
|
|
if [[ "$FAILURES" -eq 0 ]]; then
|
|
$QUIET || echo -e "${GREEN}All checks passed.${NC}"
|
|
exit 0
|
|
else
|
|
echo -e "${RED}${FAILURES} check(s) failed.${NC}" >&2
|
|
exit 1
|
|
fi
|