fix: verify MindSpace service replacement

CI run 1063 passed. Required release safety fix for the image_make production canary.

release-goosed-remount-guard.test.mjs

@@ -6,6 +6,10 @@ const releaseScript = fs.readFileSync(
   new URL('./scripts/release-portal-runtime-prod.sh', import.meta.url),
   'utf8',
 );
+const mindSpaceReleaseScript = fs.readFileSync(
+  new URL('./scripts/release-mindspace-service-prod.sh', import.meta.url),
+  'utf8',
+);
 
 test('103 release remounts goosed after swapping the live directory', () => {
   assert.match(releaseScript, /remount_goosed_after_live_swap\(\)/);
@@ -23,3 +27,43 @@ test('103 release remounts goosed after swapping the live directory', () => {
   assert.ok(remountIndex > swapIndex, 'goosed remount must happen after the live swap');
   assert.ok(portalStartIndex > remountIndex, 'Portal must start only after goosed remount succeeds');
 });
+
+test('MindSpace release preserves runtime data and returns it during rollback', () => {
+  assert.match(mindSpaceReleaseScript, /PERSISTED_DATA_MOVED=0/);
+  assert.match(mindSpaceReleaseScript, /PERSISTED_USERS_MOVED=0/);
+  assert.match(mindSpaceReleaseScript, /mv "\$\{OLD_APP_ARCHIVE\}\/data" "\$\{APP_DIR\}\/data"/);
+  assert.match(mindSpaceReleaseScript, /mv "\$\{OLD_APP_ARCHIVE\}\/users" "\$\{APP_DIR\}\/users"/);
+  assert.match(mindSpaceReleaseScript, /mv "\$\{APP_DIR\}\/data" "\$\{OLD_APP_ARCHIVE\}\/data"/);
+  assert.match(mindSpaceReleaseScript, /mv "\$\{APP_DIR\}\/users" "\$\{OLD_APP_ARCHIVE\}\/users"/);
+});
+
+test('MindSpace release waits for the old listener and verifies the new launchd job', () => {
+  const bootoutIndex = mindSpaceReleaseScript.indexOf(
+    'launchctl bootout "${LAUNCHD_GUI}/${SERVICE_LABEL}"',
+  );
+  const listenerWaitIndex = mindSpaceReleaseScript.indexOf('lsof -nP -iTCP:8082', bootoutIndex);
+  const swapIndex = mindSpaceReleaseScript.indexOf('mv "${NEW_DIR}" "${APP_DIR}"');
+  const bootstrapIndex = mindSpaceReleaseScript.indexOf(
+    'launchctl bootstrap "${LAUNCHD_GUI}" "${SERVICE_PLIST}"',
+    swapIndex,
+  );
+  const portalRestartIndex = mindSpaceReleaseScript.indexOf(
+    'launchctl kickstart -k "${LAUNCHD_GUI}/${PORTAL_LABEL}"',
+    bootstrapIndex,
+  );
+  const finalServiceCheckIndex = mindSpaceReleaseScript.indexOf('service_is_running', portalRestartIndex);
+
+  assert.ok(bootoutIndex >= 0, 'old MindSpace launchd job must be stopped');
+  assert.ok(listenerWaitIndex > bootoutIndex, 'release must wait for the old 8082 listener to exit');
+  assert.ok(swapIndex > listenerWaitIndex, 'runtime swap must happen after the old listener exits');
+  assert.ok(bootstrapIndex > swapIndex, 'new launchd job must start after the runtime swap');
+  assert.doesNotMatch(
+    mindSpaceReleaseScript.slice(bootstrapIndex, bootstrapIndex + 120),
+    /\|\| true/,
+    'launchctl bootstrap failures must not be ignored',
+  );
+  assert.ok(
+    finalServiceCheckIndex > portalRestartIndex,
+    'MindSpace launchd state must be rechecked after Portal restarts',
+  );
+});

scripts/release-mindspace-service-prod.sh

@@ -196,11 +196,17 @@ SERVICE_STARTED=0
 PORTAL_TOUCHED=0
 APP_MOVED=0
 HAD_OLD_APP=0
+PERSISTED_DATA_MOVED=0
+PERSISTED_USERS_MOVED=0
 
 say() {
   printf '\n[remote %s] %s\n' "$(date +%H:%M:%S)" "$*"
 }
 
+service_is_running() {
+  launchctl print "${LAUNCHD_GUI}/${SERVICE_LABEL}" 2>/dev/null | grep -q 'state = running'
+}
+
 rollback() {
   set +e
   say "rollback: restoring previous state"
@@ -217,6 +223,16 @@ rollback() {
     rm -f "${SERVICE_PLIST}"
   fi
   if [[ "${APP_MOVED}" == "1" ]]; then
+    if [[ "${HAD_OLD_APP}" == "1" ]]; then
+      if [[ "${PERSISTED_DATA_MOVED}" == "1" && ( -e "${APP_DIR}/data" || -L "${APP_DIR}/data" ) ]]; then
+        rm -rf "${OLD_APP_ARCHIVE}/data"
+        mv "${APP_DIR}/data" "${OLD_APP_ARCHIVE}/data"
+      fi
+      if [[ "${PERSISTED_USERS_MOVED}" == "1" && ( -e "${APP_DIR}/users" || -L "${APP_DIR}/users" ) ]]; then
+        rm -rf "${OLD_APP_ARCHIVE}/users"
+        mv "${APP_DIR}/users" "${OLD_APP_ARCHIVE}/users"
+      fi
+    fi
     rm -rf "${APP_DIR}"
     if [[ "${HAD_OLD_APP}" == "1" && -d "${OLD_APP_ARCHIVE}" ]]; then
       mv "${OLD_APP_ARCHIVE}" "${APP_DIR}"
@@ -302,6 +318,16 @@ EOF
 
 say "切换 MindSpace service live 目录"
 launchctl bootout "${LAUNCHD_GUI}/${SERVICE_LABEL}" >/dev/null 2>&1 || true
+for _ in $(seq 1 60); do
+  if ! lsof -nP -iTCP:8082 -sTCP:LISTEN >/dev/null 2>&1; then
+    break
+  fi
+  sleep 1
+done
+if lsof -nP -iTCP:8082 -sTCP:LISTEN >/dev/null 2>&1; then
+  echo "旧 MindSpace service 未在超时内退出，拒绝切换 runtime" >&2
+  exit 1
+fi
 rm -rf "${OLD_APP_ARCHIVE}"
 if [[ -d "${APP_DIR}" ]]; then
   mv "${APP_DIR}" "${OLD_APP_ARCHIVE}"
@@ -309,21 +335,34 @@ fi
 mv "${NEW_DIR}" "${APP_DIR}"
 APP_MOVED=1
 
+say "继承 MindSpace 持久目录"
+if [[ "${HAD_OLD_APP}" == "1" && ( -e "${OLD_APP_ARCHIVE}/data" || -L "${OLD_APP_ARCHIVE}/data" ) ]]; then
+  rm -rf "${APP_DIR}/data"
+  mv "${OLD_APP_ARCHIVE}/data" "${APP_DIR}/data"
+  PERSISTED_DATA_MOVED=1
+fi
+if [[ "${HAD_OLD_APP}" == "1" && ( -e "${OLD_APP_ARCHIVE}/users" || -L "${OLD_APP_ARCHIVE}/users" ) ]]; then
+  rm -rf "${APP_DIR}/users"
+  mv "${OLD_APP_ARCHIVE}/users" "${APP_DIR}/users"
+  PERSISTED_USERS_MOVED=1
+fi
+
 say "启动 MindSpace service"
 mkdir -p "${APP_DIR}/data/mindspace" "${APP_DIR}/users"
-launchctl bootstrap "${LAUNCHD_GUI}" "${SERVICE_PLIST}" >/dev/null 2>&1 || true
-launchctl enable "${LAUNCHD_GUI}/${SERVICE_LABEL}" >/dev/null 2>&1 || true
-launchctl kickstart -k "${LAUNCHD_GUI}/${SERVICE_LABEL}" >/dev/null 2>&1 || true
+launchctl bootstrap "${LAUNCHD_GUI}" "${SERVICE_PLIST}" >/dev/null
 SERVICE_STARTED=1
+launchctl enable "${LAUNCHD_GUI}/${SERVICE_LABEL}" >/dev/null
+launchctl kickstart -k "${LAUNCHD_GUI}/${SERVICE_LABEL}" >/dev/null
 
 for _ in $(seq 1 30); do
   code="$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8082/health || true)"
-  if [[ "${code}" == "200" ]]; then
+  if [[ "${code}" == "200" ]] && service_is_running; then
     break
   fi
   sleep 1
 done
 [[ "$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8082/health || true)" == "200" ]]
+service_is_running
 [[ "$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8082/mindspace/v1/contract || true)" == "200" ]]
 
 set_env() {
@@ -371,6 +410,9 @@ for _ in $(seq 1 30); do
   sleep 1
 done
 [[ "$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8081/api/status || true)" == "200" ]]
+sleep 3
+[[ "$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8082/health || true)" == "200" ]]
+service_is_running
 
 trap - ERR
 
@@ -379,7 +421,7 @@ printf 'release_id=%s\n' "${RELEASE_ID}"
 printf 'service_root=%s\n' "${APP_DIR}"
 printf 'service_backup=%s\n' "${APP_BACKUP}"
 printf 'env_backup=%s\n' "${ENV_BACKUP}"
-printf 'service_health=%s\n' "$(curl -s http://127.0.0.1:8082/health)"
+printf 'service_health=%s\n' "$(curl -fsS http://127.0.0.1:8082/health)"
 REMOTE
 
 say "发布完成"