test(deploy): add opt-in display-device scenarios to the split smoke

Reproduction harness for what the first production Signage deployment
found. With EKKLESIA_SMOKE_DISPLAY_DEVICE=1, the split smoke starts a
second headless Chromium (the "kiosk") whose profile directory is a
Docker volume. It pairs that kiosk through the real flow, closes it
cleanly, restarts it on the same profile, and then runs injected-failure
scenarios: two pages on one credential, a connectivity blip, one refused
viewer-session request, one refused realtime connection, a cross-origin
image-caching probe, a full realtime recycle, and revocation.

Every DevTools command and page-side request has its own deadline, and
each step has a budget. A step that overruns prints the exact call it
was waiting for. The proxy's "aborting with incomplete response" lines
are listed afterwards by UTC time and path only.

Off by default: several scenarios expect Signage and fail on today's
v0.1.1, by design.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

scripts/smoke-deploy.sh

@@ -15,6 +15,12 @@
 # With EKKLESIA_SMOKE_IMAGE, the given image is used as is in either topology; a split run then
 # exercises whichever of its modules publishes UI and a display.
 #
+# Opt-in, split topology only: EKKLESIA_SMOKE_DISPLAY_DEVICE=1 adds the display-device scenarios in
+# scripts/lib/deploy-smoke-display.mjs (pairing a kiosk browser with a persistent profile, a clean
+# restart, two pages, injected network failures, revocation), each with its own time budget.
+# EKKLESIA_SMOKE_DISPLAY_SCENARIOS selects a subset; EKKLESIA_SMOKE_WATCH_MS and
+# EKKLESIA_SMOKE_RECYCLE_WATCH_MS change how long they watch. Several scenarios expect Signage.
+#
 # TEST-ONLY: the proxy runs with Caddy's internal CA (`local_certs`) instead of ACME, because a test
 # run has no public hostname. Never use that option in an installation.
 #
@@ -141,6 +147,12 @@ cleanup() {
   if [[ -n "$browser_container" ]]; then
     docker rm --force "$browser_container" >/dev/null 2>&1 || true
   fi
+  if [[ -n "${kiosk_container:-}" ]]; then
+    docker ps --all --quiet --filter "name=${project}-display-" | xargs -r docker rm --force \
+      >/dev/null 2>&1 || true
+    docker rm --force "$kiosk_container" >/dev/null 2>&1 || true
+    docker volume rm --force "$kiosk_volume" >/dev/null 2>&1 || true
+  fi
   if [[ -f "$work/compose.env" ]]; then
     "${compose[@]}" --profile ops down --volumes --remove-orphans --timeout 10 >/dev/null 2>&1 || status=1
   fi
@@ -404,6 +416,81 @@ if [[ "$topology" == split ]]; then
     -e SMOKE_OWNER_EMAIL="$owner_email" -e SMOKE_OWNER_PASSWORD="$owner_password" \
     -v "$daemon_work/browser.mjs:/smoke/browser.mjs:ro" \
     --entrypoint node "$image" /smoke/browser.mjs || fail "browser checks failed."
+
+  if [[ -n "${EKKLESIA_SMOKE_DISPLAY_DEVICE:-}" ]]; then
+    # A kiosk: a second browser whose profile directory is a volume, so it outlives the container
+    # exactly as a kiosk's --user-data-dir outlives a browser restart.
+    kiosk_container="${project}-kiosk"
+    kiosk_volume="${project}-kiosk-profile"
+    kiosk_address="10.249.${octet}.250"
+    docker volume create "$kiosk_volume" >/dev/null
+    start_kiosk() {
+      docker run --detach --rm --name "$kiosk_container" \
+        --cap-drop ALL --security-opt no-new-privileges --tmpfs /tmp \
+        --network "$edge_network" --ip "$kiosk_address" "${host_mappings[@]}" \
+        -v "${kiosk_volume}:/profile" \
+        "$browser_image" \
+        "--ignore-certificate-errors-spki-list=${spki}" \
+        --user-data-dir=/profile >/dev/null || fail "the kiosk browser did not start."
+    }
+    wait_kiosk_exit() {
+      for _ in $(seq 1 60); do
+        docker inspect "$kiosk_container" >/dev/null 2>&1 || return 0
+        sleep 0.5
+      done
+      fail "the kiosk browser did not exit after a clean close."
+    }
+    cp scripts/lib/deploy-smoke-display.mjs "$work/display.mjs"
+    stage display.mjs
+    # display_driver <budget seconds> <step>: one scenario with a hard budget. The driver enforces it
+    # itself and names whatever call was still waiting; `timeout` is the backstop if it cannot.
+    display_driver() {
+      local budget="$1" step_name="$2" driver="${project}-display-${2}"
+      timeout --signal=TERM "$((budget + 30))" \
+        docker run --rm --name "$driver" --read-only --cap-drop ALL --security-opt no-new-privileges \
+        --network "$edge_network" \
+        -e SMOKE_CDP_ADDRESS="${browser_address}:9222" \
+        -e SMOKE_KIOSK_CDP_ADDRESS="${kiosk_address}:9222" \
+        -e SMOKE_STEP_BUDGET_MS="$((budget * 1000))" \
+        -e SMOKE_WATCH_MS="${EKKLESIA_SMOKE_WATCH_MS:-120000}" \
+        -e SMOKE_RECYCLE_WATCH_MS="${EKKLESIA_SMOKE_RECYCLE_WATCH_MS:-330000}" \
+        -e SMOKE_HOSTNAME="$hostname" -e SMOKE_DASHBOARD_HOSTNAME="$dashboard_hostname" \
+        -e SMOKE_OWNER_EMAIL="$owner_email" -e SMOKE_OWNER_PASSWORD="$owner_password" \
+        -v "$daemon_work/display.mjs:/smoke/display.mjs:ro" \
+        --entrypoint node "$image" /smoke/display.mjs "$step_name"
+      local status=$?
+      if ((status == 124)); then
+        echo "FAIL ${step_name}: the driver did not stop within its budget plus 30s; removed it"
+        docker rm --force "$driver" >/dev/null 2>&1 || true
+      fi
+      return "$status"
+    }
+    display_status=0
+    step "Pairing a kiosk display, then closing its browser cleanly"
+    start_kiosk
+    display_driver 180 pair || display_status=1
+    wait_kiosk_exit
+    step "Restarting the kiosk browser on the same profile"
+    start_kiosk
+    display_driver 120 restart || display_status=1
+    for scenario in ${EKKLESIA_SMOKE_DISPLAY_SCENARIOS:-two-pages connectivity-blip session-blip stream-failure caching-probe stream-recycle revoke}; do
+      case "$scenario" in
+      two-pages) budget=240 ;;
+      stream-recycle) budget=420 ;;
+      revoke) budget=210 ;;
+      *) budget=150 ;;
+      esac
+      step "Display scenario: ${scenario} (budget ${budget}s)"
+      display_driver "$budget" "$scenario" || display_status=1
+    done
+    step "Proxy: streams aborted with an incomplete response (UTC time, path only)"
+    # Captured, never printed: only each line's time and path (no query, so no signature) leave it.
+    proxy_logs="$("${compose[@]}" logs --no-color proxy 2>/dev/null)" || proxy_logs=""
+    grep -o '{.*"aborting with incomplete response".*}' <<<"$proxy_logs" |
+      sed -E 's/.*"ts":([0-9]+)[^,]*,.*"uri":"([^"?]*)[^"]*".*/\1 \2/' |
+      while read -r ts uri; do echo "     $(date -u -d "@${ts}" +%T) ${uri}"; done || true
+    ((display_status == 0)) || fail "display-device checks failed."
+  fi
 fi
 
 step "Proving the API's database connection is certificate-verified TLS"