fix: accept sites fmt|cbs|pdx|roam (tenancy 0.7.x) and keep the identity read grant alive across tunneller rewrites — 0.1.10

deployd#3 (DD-0620): every kit for a backend registered since 2026-09-08 died at `--site`.
env-dev-08 (2026-09-11..13): two days of "identity is not readable" ticks — ziti-edge-tunnel
re-creates the file with mode 0600, the ACL mask goes to ---, group membership stops helping.
identity-acl.sh + monky-deployd-identity-acl.path re-apply the grant on every directory change.

Doc-Drift: DD-0620 fixed
Closes #3

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ASnneBmT7rfaJLE8NGNw7S

packaging/bin/identity-acl.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+# monky-deployd: (re)grant the agent read access to the host's ziti identity file(s).
+# Idempotent; safe to run at any time. Invoked by install.sh, the package postinstall and the
+# monky-deployd-identity-acl.path unit (whenever the identity directory changes).
+#
+# Why a re-runnable script and not a one-time ACL: ziti-edge-tunnel re-creates the identity on
+# every controller config update with mode 0600. On a file with an ACL that sets the mask to ---,
+# so the named-user entry AND the ziti-group read both become ineffective. Only re-applying the
+# entries after each rewrite keeps the agent alive.
+set -eu
+DIR="${1:-/opt/openziti/etc/identities}"
+[ -d "$DIR" ] || exit 0
+command -v setfacl >/dev/null 2>&1 || exit 0
+setfacl -m u:monky-deployd:rx,m::rx "$DIR" 2>/dev/null || true
+setfacl -d -m u:monky-deployd:r,m::r "$DIR" 2>/dev/null || true
+for f in "$DIR"/*.json; do
+  [ -f "$f" ] || continue
+  setfacl -m u:monky-deployd:r,m::r "$f" 2>/dev/null || true
+done
+exit 0

packaging/install.sh

@@ -4,7 +4,7 @@
 #   T=<read-only GitLab deploy token, scope read_package_registry>   # from the install kit / OpenBao
 #   curl -sSf -H "DEPLOY-TOKEN: $T" \
 #     https://scm.tikali.ai/api/v4/projects/69/packages/generic/monky-deployd/0.1.6/install.sh \
-#     | sudo bash -s -- --env env-qa-02 --site cbs --token "$T" --bootstrap-file bootstrap.jwt \
+#     | sudo bash -s -- --env env-qa-02 --site fmt --token "$T" --bootstrap-file bootstrap.jwt \
 #     [--transport sdk|proxy|system] [--version 0.1.6] [--enrol-jwt /path/monky-host.env-qa-02.jwt] \
 #     [--laptop] [--source gitlab|gitea] [--docker-data-root /home/docker-data]
 #
@@ -77,7 +77,7 @@ done
 [ -n "$SITE" ] || die "--site is required"
 [[ "$ENV_ID" =~ ^env-(dev|qa|stage|prod)-[0-9]{2,3}$|^(dev-env-2|prod-cedar)$ ]] || die "env id $ENV_ID is not env-<tier>-<nn>"
 SITE="${SITE,,}"
-[[ "$SITE" =~ ^(cbs|pdx)$ ]] || die "site must be cbs|pdx"
+[[ "$SITE" =~ ^(fmt|cbs|pdx|roam)$ ]] || die "site must be fmt|cbs|pdx|roam (tenancy issues fmt|pdx|roam; cbs = the deprecated alias of fmt)"
 [[ "$TRANSPORT" =~ ^(sdk|proxy|system)$ ]] || die "transport must be sdk|proxy|system"
 [[ "$SOURCE" =~ ^(gitlab|gitea)$ ]] || die "source must be gitlab|gitea"
 # never let the token leak through xtrace / the environment of children
@@ -219,10 +219,14 @@ install -d -m 0700 -o monky-deployd -g monky-deployd /var/lib/monky-deployd
 # window before the agent's next login and hosts where the file has another group.
 # A default ACL on the directory carries the grant onto a freshly created identity file.
 if getent group ziti >/dev/null; then usermod -a -G ziti monky-deployd || true; fi
-setfacl -m u:monky-deployd:r "$IDENTITY"
-setfacl -m u:monky-deployd:rx "$IDENTITY_DIR"
-setfacl -d -m u:monky-deployd:r "$IDENTITY_DIR" 2>/dev/null || true
 setfacl -m u:monky-deployd:x /opt/openziti/etc 2>/dev/null || true
+# The grant must OUTLIVE the tunneller: ziti-edge-tunnel re-creates the identity file on every
+# controller config update with mode 0600, which sets the ACL mask to --- and defeats both the
+# named-user entry and the ziti-group read (env-dev-08, 2026-09-11..13: two days of "identity is
+# not readable" ticks while the tunnel was healthy). identity-acl.sh re-applies the entries and the
+# mask; the .path unit re-runs it whenever the directory changes.
+/usr/share/monky-deployd/identity-acl.sh "$IDENTITY_DIR"
+systemctl enable --now monky-deployd-identity-acl.path 2>/dev/null || true
 if [ -n "$BAO_CA" ]; then
   install -m 0644 "$BAO_CA" "$ETC/openbao-ca.pem"
 fi

packaging/nfpm.yaml

@@ -33,6 +33,14 @@ contents:
     dst: /usr/lib/systemd/system/monky-deployd.timer
   - src: ./packaging/systemd/monky-deployd-proxy.service
     dst: /usr/lib/systemd/system/monky-deployd-proxy.service
+  - src: ./packaging/systemd/monky-deployd-identity-acl.path
+    dst: /usr/lib/systemd/system/monky-deployd-identity-acl.path
+  - src: ./packaging/systemd/monky-deployd-identity-acl.service
+    dst: /usr/lib/systemd/system/monky-deployd-identity-acl.service
+  - src: ./packaging/bin/identity-acl.sh
+    dst: /usr/share/monky-deployd/identity-acl.sh
+    file_info:
+      mode: 0755
   - src: ./packaging/monky-deployd.sysusers
     dst: /usr/lib/sysusers.d/monky-deployd.conf
   - src: ./packaging/monky-deployd.tmpfiles

packaging/scripts/postinstall.sh

@@ -18,6 +18,9 @@ if getent group docker >/dev/null; then usermod -a -G docker monky-deployd || tr
 # POSIX ACL granting the agent read — group membership is the grant that survives it.
 # (env-dev-08, 2026-09-09: the agent went from applied to "no intercept" 6 minutes after a refresh.)
 if getent group ziti >/dev/null; then usermod -a -G ziti monky-deployd || true; fi
+# ...and group membership does NOT survive it either once the rewrite lands with mode 0600 (the ACL
+# mask goes to ---). Re-apply the grant now and on every directory change (0.1.10, deployd#3 beat).
+[ -x /usr/share/monky-deployd/identity-acl.sh ] && /usr/share/monky-deployd/identity-acl.sh /opt/openziti/etc/identities || true
 # the venv is relocatable only to the path it was built at; refuse a broken interpreter early
 /opt/monky-deployd/venv/bin/python -c 'import monky_deployd' || { echo "monky-deployd: venv unusable (python3 mismatch?)" >&2; exit 1; }
 if [ -d /run/systemd/system ]; then
@@ -26,5 +29,7 @@ if [ -d /run/systemd/system ]; then
   # An UPGRADE is different — the timer is already enabled and must keep running, so restart the
   # long-lived proxy unit onto the new code. `try-restart` is a no-op when it is not running.
   systemctl try-restart monky-deployd-proxy.service 2>/dev/null || true
+  # an UPGRADE of a box that already has its config: arm the identity-ACL watcher
+  if [ -s /etc/monky-deployd/config.yaml ]; then systemctl enable --now monky-deployd-identity-acl.path 2>/dev/null || true; fi
 fi
 exit 0

packaging/systemd/monky-deployd-identity-acl.path

@@ -0,0 +1,11 @@
+[Unit]
+Description=Re-grant monky-deployd read access when the ziti identity directory changes
+Documentation=file:/usr/share/doc/monky-deployd/OPERATIONS.md
+
+[Path]
+PathChanged=/opt/openziti/etc/identities
+PathModified=/opt/openziti/etc/identities
+Unit=monky-deployd-identity-acl.service
+
+[Install]
+WantedBy=multi-user.target

packaging/systemd/monky-deployd-identity-acl.service

@@ -0,0 +1,6 @@
+[Unit]
+Description=Re-grant monky-deployd read access to the ziti identity file(s)
+
+[Service]
+Type=oneshot
+ExecStart=/usr/share/monky-deployd/identity-acl.sh /opt/openziti/etc/identities