fix(install.sh): clear ExecStartPre in the run-host drop-in; don't abort before config/grant land; 0.1.4

On env-qa-02 (ziti-edge-tunnel 1.18.7) the package's ExecStartPre script is
not executable by user ziti (203/EXEC), so the unit never started, and under
set -e `systemctl enable --now` aborted install.sh before config.yaml, ACLs,
the bootstrap grant and the timer were written — a second kit was needed.

- run-host drop-in clears ExecStartPre= (run-host does not auto-enrol JWTs)
- a tunneler start failure is a WARNING until everything else is installed,
  then a hard error at the end (re-run needs no new kit)

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KLB7jieMNRkTsJ2epr4Ds1
This commit is contained in:
2026-09-07 05:58:57 +00:00
parent b08e0adf82
commit 744041ca1e
8 changed files with 33 additions and 14 deletions
+18 -7
View File
@@ -3,9 +3,9 @@
#
# T=<read-only GitLab deploy token, scope read_package_registry> # from the install kit / OpenBao
# curl -sSf -H "DEPLOY-TOKEN: $T" \
# https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.3/install.sh \
# https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.4/install.sh \
# | sudo bash -s -- --env env-qa-02 --site cbs --token "$T" --bootstrap-file bootstrap.jwt \
# [--transport sdk|proxy|system] [--version 0.1.3] [--enrol-jwt /path/monky-host.env-qa-02.jwt] \
# [--transport sdk|proxy|system] [--version 0.1.4] [--enrol-jwt /path/monky-host.env-qa-02.jwt] \
# [--laptop] [--source gitlab|gitea] [--docker-data-root /home/docker-data]
#
# --token / MONKY_DEPLOYD_TOKEN: the GitLab project is PRIVATE (its parent groups are private, so it
@@ -29,7 +29,7 @@
set -euo pipefail
umask 077
DEFAULT_VERSION="0.1.3"
DEFAULT_VERSION="0.1.4"
# Download source. PRIMARY is the GitLab project's generic package registry on scm.tikali.ai: inside
# the estate gitea.cbs.tikali.net is split-horizon to jump1's RED EIP (10.10.0.175), which has no HTTP
# ingress, so backend boxes cannot reach the Gitea mirror (cbs/iac#102); scm.tikali.ai they can. The
@@ -45,7 +45,7 @@ TOKEN="${MONKY_DEPLOYD_TOKEN:-}"
OPENZITI_SUITE="${OPENZITI_SUITE:-jammy}"
IDENTITY_DIR="/opt/openziti/etc/identities"
ETC="/etc/monky-deployd"
ENV_ID="" SITE="" TRANSPORT="sdk" DOCKER_DATA_ROOT="" DEPLOYD_VERSION="$DEFAULT_VERSION" ENROL_JWT="" BOOTSTRAP_FILE="" NO_RUN="" FORCE_CONFIG="" BAO_CA="" LAPTOP="false"
ENV_ID="" SITE="" TRANSPORT="sdk" DOCKER_DATA_ROOT="" TUNNEL_FAILED="" DEPLOYD_VERSION="$DEFAULT_VERSION" ENROL_JWT="" BOOTSTRAP_FILE="" NO_RUN="" FORCE_CONFIG="" BAO_CA="" LAPTOP="false"
usage() { if [ -f "$0" ]; then sed -n '2,28p' "$0"; else echo "monky-deployd install.sh — see README.md (Install)"; fi; exit "${1:-0}"; }
die() { echo "install.sh: $*" >&2; exit 1; }
@@ -194,14 +194,21 @@ chmod 0600 "$IDENTITY"
# ziti-edge-tunnel as a HOST (bind side, no tun/DNS) — the agent dials with the SDK or the proxy
install -d /etc/systemd/system/ziti-edge-tunnel.service.d
cat > /etc/systemd/system/ziti-edge-tunnel.service.d/run-host.conf <<'DROPIN'
# monky-deployd: run-host mode (no tun, no DNS); identities from the standard directory
# monky-deployd: run-host mode (no tun, no DNS); identities from the standard directory.
# ExecStartPre is cleared: the package's ziti-edge-tunnel.sh (auto-enrol *.jwt in the identity dir)
# is not executable by user ziti on 1.18.x (203/EXEC, env-qa-02 pilot) and run-host does not need it.
[Service]
ExecStartPre=
ExecStart=
ExecStart=/opt/openziti/bin/ziti-edge-tunnel run-host --identity-dir=/opt/openziti/etc/identities
DROPIN
systemctl daemon-reload
systemctl enable --now ziti-edge-tunnel.service
systemctl restart ziti-edge-tunnel.service || true
systemctl enable ziti-edge-tunnel.service >/dev/null 2>&1 || true
if ! systemctl restart ziti-edge-tunnel.service; then
# do NOT abort here: config, ACLs, grant and timer below must land so a re-run needs no new kit
echo "WARNING: ziti-edge-tunnel.service failed to start — see: journalctl -u ziti-edge-tunnel; continuing" >&2
TUNNEL_FAILED=1
fi
# --- 4. config, ACLs, bootstrap grant -----------------------------------------------------------------
install -d -m 0750 -o root -g monky-deployd "$ETC"
@@ -292,3 +299,7 @@ monky-deployd $DEPLOYD_VERSION installed for $ENV_ID ($SITE, transport $TRANSPOR
CHECK
CHECK_STATUS="$(monky-deployd status 2>&1 || true)"
echo "$CHECK_STATUS" | sed 's/^/ | /'
if [ -n "$TUNNEL_FAILED" ] && ! systemctl is-active --quiet ziti-edge-tunnel.service; then
echo "ERROR: ziti-edge-tunnel.service is not running; the agent cannot reach the mesh until it is. Everything else is installed — fix the unit and 'systemctl restart ziti-edge-tunnel monky-deployd'." >&2
exit 1
fi