Ops-dashboard/ops-agent/commands.yml.example

# Whitelist of allowed commands for ops-agent.
# Copy to /etc/ops-agent/commands.yml on the host.
# Restart ops-agent after changes.
#
# Schema per command:
#   cmd:         required — command + static args as array (no shell, no interpolation)
#   cwd:         optional — working directory for the subprocess
#   cwd_pattern: optional — working directory as a glob/pattern (resolved at runtime)
#   args:
#     allowed:   optional — whitelist of argument values accepted from the caller
#                If absent or empty, the command takes no extra arguments.
#   description: optional — human-readable description

commands:
  docker_ps:
    cmd: ["docker", "ps", "--format", "table"]
    description: "List running Docker containers"

  git_status:
    cmd: ["git", "status", "--short", "--branch"]
    cwd_pattern: "/srv/"
    description: "Git status with branch info (first arg = repo path, must start with /srv/)"

  git_log_ahead:
    cmd: ["git", "log", "@{upstream}..HEAD", "--oneline"]
    cwd_pattern: "/srv/"
    description: "Local commits not yet pushed (first arg = repo path)"

  git_diff:
    cmd: ["git", "diff", "HEAD"]
    cwd_pattern: "/srv/"
    description: "Uncommitted diff against HEAD (first arg = repo path)"

  git_fetch:
    cmd: ["git", "fetch", "--quiet"]
    cwd_pattern: "/srv/"
    description: "Fetch all remotes silently (first arg = repo path)"

  systemctl_status:
    cmd: ["systemctl", "status", "--no-pager", "-l"]
    args:
      allowed:
        - scrum4me-web
        - ops-agent
        - caddy
        - docker
        - nginx
        - postgresql
    description: "Show systemctl status for an allowed service"

  journalctl_recent:
    cmd: ["journalctl", "--since", "1 hour ago", "-n", "100", "--no-pager", "-u"]
    args:
      allowed:
        - scrum4me-web
        - ops-agent
        - caddy
        - docker
        - nginx
        - postgresql
    description: "Last 100 journal lines from the past hour for an allowed service"

  caddy_show_config:
    cmd: ["caddy", "fmt", "/etc/caddy/Caddyfile"]
    description: "Print the formatted Caddy config"

  caddy_list_certs:
    cmd:
      - sh
      - -c
      - "for f in /data/caddy/certificates/*/*.crt; do [ -f \"$f\" ] || continue; echo \"CERTFILE:$f\"; openssl x509 -noout -subject -issuer -dates -in \"$f\" 2>&1; echo \"CERTEND\"; done"
    description: "List TLS cert info (subject, issuer, validity dates) from Caddy certificate store"

  # ── Destructive / write commands ──────────────────────────────────────────

  docker_compose_restart:
    cmd: ["docker", "compose", "restart"]
    cwd: "/srv/scrum4me/compose"
    args:
      allowed:
        - scrum4me-web
        - worker-idea
        - ops-dashboard
        - caddy
        - postgres
    description: "Restart a docker compose service (ops-agent user must be in the docker group)"

  docker_compose_stop:
    cmd: ["docker", "compose", "stop"]
    cwd: "/srv/scrum4me/compose"
    args:
      allowed:
        - scrum4me-web
        - worker-idea
        - ops-dashboard
        - caddy
        - postgres
    description: "Stop a docker compose service"

  docker_compose_build:
    cmd: ["docker", "compose", "build"]
    cwd: "/srv/scrum4me/compose"
    args:
      allowed:
        - scrum4me-web
        - worker-idea
        - ops-dashboard
    description: "Build a docker compose service image"

  docker_compose_up:
    cmd: ["docker", "compose", "up", "-d"]
    cwd: "/srv/scrum4me/compose"
    args:
      allowed:
        - scrum4me-web
        - worker-idea
        - ops-dashboard
    description: "Start or recreate a docker compose service in detached mode"

  docker_compose_up_recreate:
    cmd: ["docker", "compose", "up", "-d", "--force-recreate"]
    cwd: "/srv/scrum4me/compose"
    args:
      allowed:
        - scrum4me-web
        - worker-idea
        - ops-dashboard
    description: "Force-recreate a docker compose service (picks up a rebuilt image)"

  git_pull:
    cmd: ["git", "pull", "--ff-only"]
    cwd_pattern: "/srv/"
    preconditions:
      - git_status_clean
    description: "Fast-forward pull — refused when working tree is dirty"

  systemctl_restart:
    # Requires /etc/sudoers.d/ops-agent (see deploy/ops-agent/sudoers).
    cmd: ["sudo", "/usr/bin/systemctl", "restart"]
    args:
      allowed:
        - scrum4me-web
        - ops-agent
        - caddy
    description: "Restart an allowed systemd service via sudo"

  caddy_validate:
    cmd: ["caddy", "validate", "--config", "/srv/scrum4me/caddy/Caddyfile"]
    description: "Validate /srv/scrum4me/caddy/Caddyfile without reloading"

  caddy_reload:
    cmd: ["caddy", "reload", "--config", "/srv/scrum4me/caddy/Caddyfile"]
    description: "Reload Caddy with /srv/scrum4me/caddy/Caddyfile"

  caddy_write_config:
    # Writes stdin to Caddyfile.new first; mv is atomic on the same filesystem.
    # ops-agent user must own /srv/scrum4me/caddy/.
    cmd:
      - sh
      - -c
      - "cat > /srv/scrum4me/caddy/Caddyfile.new && mv /srv/scrum4me/caddy/Caddyfile.new /srv/scrum4me/caddy/Caddyfile"
    stdin_from_body: true
    description: "Atomically replace /srv/scrum4me/caddy/Caddyfile (write stdin to .new, then mv)"

  # ── Smoke tests / health checks ───────────────────────────────────────────

  curl_smoke_scrum4me_web:
    cmd: ["curl", "-sf", "--max-time", "10", "https://scrum4me.com"]
    description: "HTTP smoke test — fails (non-zero) if the site is unreachable or returns a non-2xx status"

  docker_compose_ps_worker:
    cmd: ["docker", "compose", "ps", "--filter", "status=running", "worker-idea"]
    cwd: "/srv/scrum4me/compose"
    description: "Verify worker-idea container is in the running state"

  wait_for_health_worker:
    cmd:
      - sh
      - -c
      - "timeout 60 sh -c 'until grep -q \"pre-flight passed\" /var/log/agent/current 2>/dev/null; do sleep 3; done && echo \"pre-flight passed\"'"
    description: "Wait up to 60s for MCP worker pre-flight check (/var/log/agent/current)"

  # ── Scrum4Me web deployment steps ────────────────────────────────────────

  npm_ci:
    cmd: ["npm", "ci"]
    cwd: "/srv/scrum4me/repos/Scrum4Me"
    description: "Install production dependencies for Scrum4Me web (npm ci)"

  prisma_migrate_deploy:
    cmd: ["npx", "prisma", "migrate", "deploy"]
    cwd: "/srv/scrum4me/repos/Scrum4Me"
    description: "Apply pending Prisma migrations for Scrum4Me web"

  npm_run_build:
    cmd: ["npm", "run", "build"]
    cwd: "/srv/scrum4me/repos/Scrum4Me"
    description: "Build the Scrum4Me web application (next build)"

  curl_smoke_scrum4me_thuis:
    cmd:
      - sh
      - -c
      - "code=$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 https://thuis.jp-visser.nl/api/products); echo \"HTTP $code\"; [ \"$code\" = \"200\" ] || [ \"$code\" = \"401\" ]"
    description: "Smoke test: /api/products must return 200 or 401"