Merge branch 'dev' into prcix9320

unilabos/app/main.py

@@ -1,8 +1,10 @@
 import argparse
 import asyncio
 import os
+import platform
 import shutil
 import signal
+import subprocess
 import sys
 import threading
 import time
@@ -24,6 +26,84 @@ from unilabos.config.config import load_config, BasicConfig, HTTPConfig
 _restart_requested: bool = False
 _restart_reason: str = ""
 
+RESTART_EXIT_CODE = 42
+
+
+def _build_child_argv():
+    """Build sys.argv for child process, stripping supervisor-only arguments."""
+    result = []
+    skip_next = False
+    for arg in sys.argv:
+        if skip_next:
+            skip_next = False
+            continue
+        if arg in ("--restart_mode", "--restart-mode"):
+            continue
+        if arg in ("--auto_restart_count", "--auto-restart-count"):
+            skip_next = True
+            continue
+        if arg.startswith("--auto_restart_count=") or arg.startswith("--auto-restart-count="):
+            continue
+        result.append(arg)
+    return result
+
+
+def _run_as_supervisor(max_restarts: int):
+    """
+    Supervisor process that spawns and monitors child processes.
+
+    Similar to Uvicorn's --reload: the supervisor itself does no heavy work,
+    it only launches the real process as a child and restarts it when the child
+    exits with RESTART_EXIT_CODE.
+    """
+    child_argv = [sys.executable] + _build_child_argv()
+    restart_count = 0
+
+    print_status(
+        f"[Supervisor] Restart mode enabled (max restarts: {max_restarts}), "
+        f"child command: {' '.join(child_argv)}",
+        "info",
+    )
+
+    while True:
+        print_status(
+            f"[Supervisor] Launching process (restart {restart_count}/{max_restarts})...",
+            "info",
+        )
+
+        try:
+            process = subprocess.Popen(child_argv)
+            exit_code = process.wait()
+        except KeyboardInterrupt:
+            print_status("[Supervisor] Interrupted, terminating child process...", "info")
+            process.terminate()
+            try:
+                process.wait(timeout=10)
+            except subprocess.TimeoutExpired:
+                process.kill()
+                process.wait()
+            sys.exit(1)
+
+        if exit_code == RESTART_EXIT_CODE:
+            restart_count += 1
+            if restart_count > max_restarts:
+                print_status(
+                    f"[Supervisor] Maximum restart count ({max_restarts}) reached, exiting",
+                    "warning",
+                )
+                sys.exit(1)
+            print_status(
+                f"[Supervisor] Child requested restart ({restart_count}/{max_restarts}), restarting in 2s...",
+                "info",
+            )
+            time.sleep(2)
+        else:
+            if exit_code != 0:
+                print_status(f"[Supervisor] Child exited with code {exit_code}", "warning")
+            else:
+                print_status("[Supervisor] Child exited normally", "info")
+            sys.exit(exit_code)
+
 
 def load_config_from_file(config_path):
     if config_path is None:
@@ -65,6 +145,13 @@ def parse_args():
         action="append",
         help="Path to the registry directory",
     )
+    parser.add_argument(
+        "--devices",
+        type=str,
+        default=None,
+        action="append",
+        help="Path to Python code directory for AST-based device/resource scanning",
+    )
     parser.add_argument(
         "--working_dir",
         type=str,
@@ -154,18 +241,18 @@ def parse_args():
         action="store_true",
         help="Skip environment dependency check on startup",
     )
-    parser.add_argument(
-        "--complete_registry",
-        action="store_true",
-        default=False,
-        help="Complete registry information",
-    )
     parser.add_argument(
         "--check_mode",
         action="store_true",
         default=False,
         help="Run in check mode for CI: validates registry imports and ensures no file changes",
     )
+    parser.add_argument(
+        "--complete_registry",
+        action="store_true",
+        default=False,
+        help="Complete and rewrite YAML registry files using AST analysis results",
+    )
     parser.add_argument(
         "--no_update_feedback",
         action="store_true",
@@ -177,6 +264,30 @@ def parse_args():
         default=False,
         help="Test mode: all actions simulate execution and return mock results without running real hardware",
     )
+    parser.add_argument(
+        "--external_devices_only",
+        action="store_true",
+        default=False,
+        help="Only load external device packages (--devices), skip built-in unilabos/devices/ scanning and YAML device registry",
+    )
+    parser.add_argument(
+        "--extra_resource",
+        action="store_true",
+        default=False,
+        help="Load extra lab_ prefixed labware resources (529 auto-generated definitions from lab_resources.py)",
+    )
+    parser.add_argument(
+        "--restart_mode",
+        action="store_true",
+        default=False,
+        help="Enable supervisor mode: automatically restart the process when triggered via WebSocket",
+    )
+    parser.add_argument(
+        "--auto_restart_count",
+        type=int,
+        default=500,
+        help="Maximum number of automatic restarts in restart mode (default: 500)",
+    )
     # workflow upload subcommand
     workflow_parser = subparsers.add_parser(
         "workflow_upload",
@@ -227,16 +338,28 @@ def main():
     args = parser.parse_args()
     args_dict = vars(args)
 
+    # Supervisor mode: spawn child processes and monitor for restart
+    if args_dict.get("restart_mode", False):
+        _run_as_supervisor(args_dict.get("auto_restart_count", 5))
+        return
+
     # 环境检查 - 检查并自动安装必需的包 (可选)
     skip_env_check = args_dict.get("skip_env_check", False)
     check_mode = args_dict.get("check_mode", False)
 
     if not skip_env_check:
-        from unilabos.utils.environment_check import check_environment
+        from unilabos.utils.environment_check import check_environment, check_device_package_requirements
 
         if not check_environment(auto_install=True):
             print_status("环境检查失败，程序退出", "error")
             os._exit(1)
+
+        # 第一次设备包依赖检查：build_registry 之前，确保 import map 可用
+        devices_dirs_for_req = args_dict.get("devices", None)
+        if devices_dirs_for_req:
+            if not check_device_package_requirements(devices_dirs_for_req):
+                print_status("设备包依赖检查失败，程序退出", "error")
+                os._exit(1)
     else:
         print_status("跳过环境依赖检查", "warning")
 
@@ -357,46 +480,63 @@ def main():
     BasicConfig.test_mode = args_dict.get("test_mode", False)
     if BasicConfig.test_mode:
         print_status("启用测试模式：所有动作将模拟执行，不调用真实硬件", "warning")
+    BasicConfig.extra_resource = args_dict.get("extra_resource", False)
+    if BasicConfig.extra_resource:
+        print_status("启用额外资源加载：将加载lab_开头的labware资源定义", "info")
     BasicConfig.communication_protocol = "websocket"
-    machine_name = os.popen("hostname").read().strip()
+    machine_name = platform.node()
     machine_name = "".join([c if c.isalnum() or c == "_" else "_" for c in machine_name])
     BasicConfig.machine_name = machine_name
     BasicConfig.vis_2d_enable = args_dict["2d_vis"]
     BasicConfig.check_mode = check_mode
 
-    from unilabos.resources.graphio import (
-        read_node_link_json,
-        read_graphml,
-        dict_from_graph,
-    )
-    from unilabos.app.communication import get_communication_client
     from unilabos.registry.registry import build_registry
-    from unilabos.app.backend import start_backend
-    from unilabos.app.web import http_client
-    from unilabos.app.web import start_server
-    from unilabos.app.register import register_devices_and_resources
-    from unilabos.resources.graphio import modify_to_backend_format
-    from unilabos.resources.resource_tracker import ResourceTreeSet, ResourceDict
 
     # 显示启动横幅
     print_unilab_banner(args_dict)
 
-    # 注册表 - check_mode 时强制启用 complete_registry
+    # Step 0: AST 分析优先 + YAML 注册表加载
+    # check_mode 和 upload_registry 都会执行实际 import 验证
+    devices_dirs = args_dict.get("devices", None)
     complete_registry = args_dict.get("complete_registry", False) or check_mode
-    lab_registry = build_registry(args_dict["registry_path"], complete_registry, BasicConfig.upload_registry)
+    external_only = args_dict.get("external_devices_only", False)
+    lab_registry = build_registry(
+        registry_paths=args_dict["registry_path"],
+        devices_dirs=devices_dirs,
+        upload_registry=BasicConfig.upload_registry,
+        check_mode=check_mode,
+        complete_registry=complete_registry,
+        external_only=external_only,
+    )
 
-    # Check mode: complete_registry 完成后直接退出，git diff 检测由 CI workflow 执行
+    # Check mode: 注册表验证完成后直接退出
     if check_mode:
-        print_status("Check mode: complete_registry 完成，退出", "info")
+        device_count = len(lab_registry.device_type_registry)
+        resource_count = len(lab_registry.resource_type_registry)
+        print_status(f"Check mode: 注册表验证完成 ({device_count} 设备, {resource_count} 资源)，退出", "info")
         os._exit(0)
 
+    # 以下导入依赖 ROS2 环境，check_mode 已退出不需要
+    from unilabos.resources.graphio import (
+        read_node_link_json,
+        read_graphml,
+        dict_from_graph,
+        modify_to_backend_format,
+    )
+    from unilabos.app.communication import get_communication_client
+    from unilabos.app.backend import start_backend
+    from unilabos.app.web import http_client
+    from unilabos.app.web import start_server
+    from unilabos.app.register import register_devices_and_resources
+    from unilabos.resources.resource_tracker import ResourceTreeSet, ResourceDict
+
+    # Step 1: 上传全部注册表到服务端，同步保存到 unilabos_data
     if BasicConfig.upload_registry:
-        # 设备注册到服务端 - 需要 ak 和 sk
         if BasicConfig.ak and BasicConfig.sk:
-            print_status("开始注册设备到服务端...", "info")
+            # print_status("开始注册设备到服务端...", "info")
             try:
                 register_devices_and_resources(lab_registry)
-                print_status("设备注册完成", "info")
+                # print_status("设备注册完成", "info")
             except Exception as e:
                 print_status(f"设备注册失败: {e}", "error")
         else:
@@ -481,12 +621,16 @@ def main():
             continue
 
     # 如果从远端获取了物料信息，则与本地物料进行同步
-    if request_startup_json and "nodes" in request_startup_json:
+    if file_path is not None and request_startup_json and "nodes" in request_startup_json:
         print_status("开始同步远端物料到本地...", "info")
         remote_tree_set = ResourceTreeSet.from_raw_dict_list(request_startup_json["nodes"])
         resource_tree_set.merge_remote_resources(remote_tree_set)
         print_status("远端物料同步完成", "info")
 
+    # 第二次设备包依赖检查：云端物料同步后，community 包可能引入新的 requirements
+    # TODO: 当 community device package 功能上线后，在这里调用
+    #   install_requirements_txt(community_pkg_path / "requirements.txt", label="community.xxx")
+
     # 使用 ResourceTreeSet 代替 list
     args_dict["resources_config"] = resource_tree_set
     args_dict["devices_config"] = resource_tree_set
@@ -578,6 +722,10 @@ def main():
             open_browser=not args_dict["disable_browser"],
             port=BasicConfig.port,
         )
+        if restart_requested:
+            print_status("[Main] Restart requested, cleaning up...", "info")
+            cleanup_for_restart()
+            os._exit(RESTART_EXIT_CODE)
 
 
 if __name__ == "__main__":

unilabos/app/register.py

@@ -1,9 +1,8 @@
-import json
 import time
-from typing import Optional, Tuple, Dict, Any
+from typing import Any, Dict, Optional, Tuple
 
 from unilabos.utils.log import logger
-from unilabos.utils.type_check import TypeEncoder
+from unilabos.utils.tools import normalize_json as _normalize_device
 
 
 def register_devices_and_resources(lab_registry, gather_only=False) -> Optional[Tuple[Dict[str, Any], Dict[str, Any]]]:
@@ -11,50 +10,63 @@ def register_devices_and_resources(lab_registry, gather_only=False) -> Optional[
     注册设备和资源到服务器（仅支持HTTP）
     """
 
-    # 注册资源信息 - 使用HTTP方式
     from unilabos.app.web.client import http_client
 
     logger.info("[UniLab Register] 开始注册设备和资源...")
 
-    # 注册设备信息
     devices_to_register = {}
     for device_info in lab_registry.obtain_registry_device_info():
-        devices_to_register[device_info["id"]] = json.loads(
-            json.dumps(device_info, ensure_ascii=False, cls=TypeEncoder)
-        )
-        logger.debug(f"[UniLab Register] 收集设备: {device_info['id']}")
+        devices_to_register[device_info["id"]] = _normalize_device(device_info)
+        logger.trace(f"[UniLab Register] 收集设备: {device_info['id']}")
 
     resources_to_register = {}
     for resource_info in lab_registry.obtain_registry_resource_info():
         resources_to_register[resource_info["id"]] = resource_info
-        logger.debug(f"[UniLab Register] 收集资源: {resource_info['id']}")
+        logger.trace(f"[UniLab Register] 收集资源: {resource_info['id']}")
 
     if gather_only:
         return devices_to_register, resources_to_register
-    # 注册设备
+
     if devices_to_register:
         try:
             start_time = time.time()
-            response = http_client.resource_registry({"resources": list(devices_to_register.values())})
+            response = http_client.resource_registry(
+                {"resources": list(devices_to_register.values())},
+                tag="device_registry",
+            )
             cost_time = time.time() - start_time
-            if response.status_code in [200, 201]:
-                logger.info(f"[UniLab Register] 成功注册 {len(devices_to_register)} 个设备 {cost_time}s")
+            res_data = response.json() if response.status_code == 200 else {}
+            skipped = res_data.get("data", {}).get("skipped", False)
+            if skipped:
+                logger.info(
+                    f"[UniLab Register] 设备注册跳过（内容未变化）"
+                    f" {len(devices_to_register)} 个 {cost_time:.3f}s"
+                )
+            elif response.status_code in [200, 201]:
+                logger.info(f"[UniLab Register] 成功注册 {len(devices_to_register)} 个设备 {cost_time:.3f}s")
             else:
-                logger.error(f"[UniLab Register] 设备注册失败: {response.status_code}, {response.text} {cost_time}s")
+                logger.error(f"[UniLab Register] 设备注册失败: {response.status_code}, {response.text} {cost_time:.3f}s")
         except Exception as e:
             logger.error(f"[UniLab Register] 设备注册异常: {e}")
 
-    # 注册资源
     if resources_to_register:
         try:
             start_time = time.time()
-            response = http_client.resource_registry({"resources": list(resources_to_register.values())})
+            response = http_client.resource_registry(
+                {"resources": list(resources_to_register.values())},
+                tag="resource_registry",
+            )
             cost_time = time.time() - start_time
-            if response.status_code in [200, 201]:
-                logger.info(f"[UniLab Register] 成功注册 {len(resources_to_register)} 个资源 {cost_time}s")
+            res_data = response.json() if response.status_code == 200 else {}
+            skipped = res_data.get("data", {}).get("skipped", False)
+            if skipped:
+                logger.info(
+                    f"[UniLab Register] 资源注册跳过（内容未变化）"
+                    f" {len(resources_to_register)} 个 {cost_time:.3f}s"
+                )
+            elif response.status_code in [200, 201]:
+                logger.info(f"[UniLab Register] 成功注册 {len(resources_to_register)} 个资源 {cost_time:.3f}s")
             else:
-                logger.error(f"[UniLab Register] 资源注册失败: {response.status_code}, {response.text} {cost_time}s")
+                logger.error(f"[UniLab Register] 资源注册失败: {response.status_code}, {response.text} {cost_time:.3f}s")
         except Exception as e:
             logger.error(f"[UniLab Register] 资源注册异常: {e}")
-
-    logger.info("[UniLab Register] 设备和资源注册完成.")

unilabos/app/web/api.py

@@ -1052,7 +1052,7 @@ async def handle_file_import(websocket: WebSocket, request_data: dict):
                                 "result": {},
                                 "schema": lab_registry._generate_unilab_json_command_schema(v["args"], k),
                                 "goal_default": {i["name"]: i["default"] for i in v["args"]},
-                                "handles": [],
+                                "handles": {},
                             }
                             # 不生成已配置action的动作
                             for k, v in enhanced_info["action_methods"].items()
@@ -1340,5 +1340,5 @@ def setup_api_routes(app):
     # 启动广播任务
     @app.on_event("startup")
     async def startup_event():
-        asyncio.create_task(broadcast_device_status())
-        asyncio.create_task(broadcast_status_page_data())
+        asyncio.create_task(broadcast_device_status(), name="web-api-startup-device")
+        asyncio.create_task(broadcast_status_page_data(), name="web-api-startup-status")

unilabos/app/web/client.py

@@ -3,11 +3,13 @@ HTTP客户端模块
 
 提供与远程服务器通信的客户端功能，只有host需要用
 """
-
+import gzip
 import json
 import os
 from typing import List, Dict, Any, Optional
 
+from unilabos.utils.tools import fast_dumps as _fast_dumps, fast_dumps_pretty as _fast_dumps_pretty
+
 import requests
 from unilabos.resources.resource_tracker import ResourceTreeSet
 from unilabos.utils.log import info
@@ -280,22 +282,54 @@ class HTTPClient:
             )
         return response
 
-    def resource_registry(self, registry_data: Dict[str, Any] | List[Dict[str, Any]]) -> requests.Response:
+    def resource_registry(
+        self, registry_data: Dict[str, Any] | List[Dict[str, Any]], tag: str = "registry",
+    ) -> requests.Response:
         """
-        注册资源到服务器
+        注册资源到服务器，同步保存请求/响应到 unilabos_data
 
         Args:
             registry_data: 注册表数据，格式为 {resource_id: resource_info} / [{resource_info}]
+            tag: 保存文件的标签后缀 (如 "device_registry" / "resource_registry")
 
         Returns:
             Response: API响应对象
         """
+        # 序列化一次，同时用于保存和发送
+        json_bytes = _fast_dumps(registry_data)
+
+        # 保存请求数据到 unilabos_data
+        req_path = os.path.join(BasicConfig.working_dir, f"req_{tag}_upload.json")
+        try:
+            os.makedirs(BasicConfig.working_dir, exist_ok=True)
+            with open(req_path, "wb") as f:
+                f.write(_fast_dumps_pretty(registry_data))
+            logger.trace(f"注册表请求数据已保存: {req_path}")
+        except Exception as e:
+            logger.warning(f"保存注册表请求数据失败: {e}")
+
+        compressed_body = gzip.compress(json_bytes)
+        headers = {
+            "Authorization": f"Lab {self.auth}",
+            "Content-Type": "application/json",
+            "Content-Encoding": "gzip",
+        }
         response = requests.post(
             f"{self.remote_addr}/lab/resource",
-            json=registry_data,
-            headers={"Authorization": f"Lab {self.auth}"},
+            data=compressed_body,
+            headers=headers,
             timeout=30,
         )
+
+        # 保存响应数据到 unilabos_data
+        res_path = os.path.join(BasicConfig.working_dir, f"res_{tag}_upload.json")
+        try:
+            with open(res_path, "w", encoding="utf-8") as f:
+                f.write(f"{response.status_code}\n{response.text}")
+            logger.trace(f"注册表响应数据已保存: {res_path}")
+        except Exception as e:
+            logger.warning(f"保存注册表响应数据失败: {e}")
+
         if response.status_code not in [200, 201]:
             logger.error(f"注册资源失败: {response.status_code}, {response.text}")
         if response.status_code == 200:

unilabos/app/web/server.py

@@ -86,7 +86,7 @@ def setup_server() -> FastAPI:
     # 设置页面路由
     try:
         setup_web_pages(pages)
-        info("[Web] 已加载Web UI模块")
+        # info("[Web] 已加载Web UI模块")
     except ImportError as e:
         info(f"[Web] 未找到Web页面模块: {str(e)}")
     except Exception as e:
@@ -138,7 +138,7 @@ def start_server(host: str = "0.0.0.0", port: int = 8002, open_browser: bool = T
     server_thread = threading.Thread(target=server.run, daemon=True, name="uvicorn_server")
     server_thread.start()
 
-    info("[Web] Server started, monitoring for restart requests...")
+    # info("[Web] Server started, monitoring for restart requests...")
 
     # 监控重启标志
     import unilabos.app.main as main_module

unilabos/app/ws_client.py

@@ -23,9 +23,10 @@ from typing import Optional, Dict, Any, List
 from urllib.parse import urlparse
 from enum import Enum
 
-from jedi.inference.gradual.typing import TypedDict
+from typing_extensions import TypedDict
 
 from unilabos.app.model import JobAddReq
+from unilabos.resources.resource_tracker import ResourceDictType
 from unilabos.ros.nodes.presets.host_node import HostNode
 from unilabos.utils.type_check import serialize_result_info
 from unilabos.app.communication import BaseCommunicationClient
@@ -164,7 +165,7 @@ class DeviceActionManager:
             job_info.set_ready_timeout(10)  # 设置10秒超时
             self.active_jobs[device_key] = job_info
             job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
-            logger.info(f"[DeviceActionManager] Job {job_log} can start immediately for {device_key}")
+            logger.trace(f"[DeviceActionManager] Job {job_log} can start immediately for {device_key}")
             return True
 
     def start_job(self, job_id: str) -> bool:
@@ -231,8 +232,9 @@ class DeviceActionManager:
                 job_info.update_timestamp()
                 # 从all_jobs中移除已结束的job
                 del self.all_jobs[job_id]
-                job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
-                logger.info(f"[DeviceActionManager] Job {job_log} ended for {device_key}")
+                # job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
+                # logger.debug(f"[DeviceActionManager] Job {job_log} ended for {device_key}")
+                pass
             else:
                 job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
                 logger.warning(f"[DeviceActionManager] Job {job_log} was not active for {device_key}")
@@ -248,7 +250,7 @@ class DeviceActionManager:
                 next_job_log = format_job_log(
                     next_job.job_id, next_job.task_id, next_job.device_id, next_job.action_name
                 )
-                logger.info(f"[DeviceActionManager] Next job {next_job_log} can start for {device_key}")
+                logger.trace(f"[DeviceActionManager] Next job {next_job_log} can start for {device_key}")
                 return next_job
 
             return None
@@ -302,7 +304,7 @@ class DeviceActionManager:
                 # 从all_jobs中移除
                 del self.all_jobs[job_id]
                 job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
-                logger.info(f"[DeviceActionManager] Active job {job_log} cancelled for {device_key}")
+                logger.trace(f"[DeviceActionManager] Active job {job_log} cancelled for {device_key}")
 
                 # 启动下一个任务
                 if device_key in self.device_queues and self.device_queues[device_key]:
@@ -315,7 +317,7 @@ class DeviceActionManager:
                     next_job_log = format_job_log(
                         next_job.job_id, next_job.task_id, next_job.device_id, next_job.action_name
                     )
-                    logger.info(f"[DeviceActionManager] Next job {next_job_log} can start after cancel")
+                    logger.trace(f"[DeviceActionManager] Next job {next_job_log} can start after cancel")
                 return True
 
             # 如果是排队中的任务
@@ -329,7 +331,7 @@ class DeviceActionManager:
                     job_log = format_job_log(
                         job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name
                     )
-                    logger.info(f"[DeviceActionManager] Queued job {job_log} cancelled for {device_key}")
+                    logger.trace(f"[DeviceActionManager] Queued job {job_log} cancelled for {device_key}")
                     return True
 
             job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
@@ -407,6 +409,7 @@ class MessageProcessor:
         # 线程控制
         self.is_running = False
         self.thread = None
+        self._loop = None  # asyncio event loop引用，用于外部关闭websocket
         self.reconnect_count = 0
 
         logger.info(f"[MessageProcessor] Initialized for URL: {websocket_url}")
@@ -433,22 +436,31 @@ class MessageProcessor:
     def stop(self) -> None:
         """停止消息处理线程"""
         self.is_running = False
+        # 主动关闭websocket以快速中断消息接收循环
+        ws = self.websocket
+        loop = self._loop
+        if ws and loop and loop.is_running():
+            try:
+                asyncio.run_coroutine_threadsafe(ws.close(), loop)
+            except Exception:
+                pass
         if self.thread and self.thread.is_alive():
             self.thread.join(timeout=2)
         logger.info("[MessageProcessor] Stopped")
 
     def _run(self):
         """运行消息处理主循环"""
-        loop = asyncio.new_event_loop()
+        self._loop = asyncio.new_event_loop()
         try:
-            asyncio.set_event_loop(loop)
-            loop.run_until_complete(self._connection_handler())
+            asyncio.set_event_loop(self._loop)
+            self._loop.run_until_complete(self._connection_handler())
         except Exception as e:
             logger.error(f"[MessageProcessor] Thread error: {str(e)}")
             logger.error(traceback.format_exc())
         finally:
-            if loop:
-                loop.close()
+            if self._loop:
+                self._loop.close()
+            self._loop = None
 
     async def _connection_handler(self):
         """处理WebSocket连接和重连逻辑"""
@@ -465,8 +477,10 @@ class MessageProcessor:
                 async with websockets.connect(
                     self.websocket_url,
                     ssl=ssl_context,
+                    open_timeout=20,
                     ping_interval=WSConfig.ping_interval,
                     ping_timeout=10,
+                    close_timeout=5,
                     additional_headers={
                         "Authorization": f"Lab {BasicConfig.auth_secret()}",
                         "EdgeSession": f"{self.session_id}",
@@ -477,77 +491,94 @@ class MessageProcessor:
                     self.connected = True
                     self.reconnect_count = 0
 
-                    logger.trace(f"[MessageProcessor] Connected to {self.websocket_url}")
+                    logger.info(f"[MessageProcessor] 已连接到 {self.websocket_url}")
 
                     # 启动发送协程
-                    send_task = asyncio.create_task(self._send_handler())
+                    send_task = asyncio.create_task(self._send_handler(), name="websocket-send_task")
+
+                    # 每次连接（含重连）后重新向服务端注册，
+                    # 否则服务端不知道客户端已上线，不会推送消息。
+                    if self.websocket_client:
+                        self.websocket_client.publish_host_ready()
 
                     try:
                         # 接收消息循环
                         await self._message_handler()
                     finally:
+                        # 必须在 async with __aexit__ 之前停止 send_task，
+                        # 否则 send_task 会在关闭握手期间继续发送数据，
+                        # 干扰 websockets 库的内部清理，导致 task 泄漏。
+                        self.connected = False
                         send_task.cancel()
                         try:
                             await send_task
                         except asyncio.CancelledError:
                             pass
-                        self.connected = False
 
             except websockets.exceptions.ConnectionClosed:
-                logger.warning("[MessageProcessor] Connection closed")
-                self.connected = False
+                logger.warning("[MessageProcessor] 与服务端连接中断")
+            except TimeoutError:
+                logger.warning(
+                    f"[MessageProcessor] 与服务端连接通信超时 (已尝试 {self.reconnect_count + 1} 次)，请检查您的网络状况"
+                )
+            except websockets.exceptions.InvalidStatus as e:
+                logger.warning(
+                    f"[MessageProcessor] 收到服务端注册码 {e.response.status_code}, 上一进程可能还未退出"
+                )
             except Exception as e:
-                logger.error(f"[MessageProcessor] Connection error: {str(e)}")
                 logger.error(traceback.format_exc())
-                self.connected = False
+                logger.error(f"[MessageProcessor] 尝试重连时出错 {str(e)}")
             finally:
+                self.connected = False
                 self.websocket = None
 
             # 重连逻辑
-            if self.is_running and self.reconnect_count < WSConfig.max_reconnect_attempts:
+            if not self.is_running:
+                break
+            if self.reconnect_count < WSConfig.max_reconnect_attempts:
                 self.reconnect_count += 1
+                backoff = WSConfig.reconnect_interval
                 logger.info(
-                    f"[MessageProcessor] Reconnecting in {WSConfig.reconnect_interval}s "
-                    f"(attempt {self.reconnect_count}/{WSConfig.max_reconnect_attempts})"
+                    f"[MessageProcessor] 即将在 {backoff} 秒后重连 (已尝试 {self.reconnect_count}/{WSConfig.max_reconnect_attempts})"
                 )
-                await asyncio.sleep(WSConfig.reconnect_interval)
-            elif self.reconnect_count >= WSConfig.max_reconnect_attempts:
+                await asyncio.sleep(backoff)
+            else:
                 logger.error("[MessageProcessor] Max reconnection attempts reached")
                 break
-            else:
-                self.reconnect_count -= 1
 
     async def _message_handler(self):
-        """处理接收到的消息"""
+        """处理接收到的消息。
+
+        ConnectionClosed 不在此处捕获，让其向上传播到 _connection_handler，
+        以便 async with websockets.connect() 的 __aexit__ 能感知连接已断，
+        正确清理内部 task，避免 task 泄漏。
+        """
         if not self.websocket:
             logger.error("[MessageProcessor] WebSocket connection is None")
             return
 
-        try:
-            async for message in self.websocket:
-                try:
-                    data = json.loads(message)
-                    message_type = data.get("action", "")
-                    message_data = data.get("data")
-                    if self.session_id and self.session_id == data.get("edge_session"):
-                        await self._process_message(message_type, message_data)
+        async for message in self.websocket:
+            try:
+                data = json.loads(message)
+                message_type = data.get("action", "")
+                message_data = data.get("data")
+                if self.session_id and self.session_id == data.get("edge_session"):
+                    await self._process_message(message_type, message_data)
+                else:
+                    if message_type.endswith("_material"):
+                        logger.trace(
+                            f"[MessageProcessor] 收到一条归属 {data.get('edge_session')} 的旧消息：{data}"
+                        )
+                        logger.debug(
+                            f"[MessageProcessor] 跳过了一条归属 {data.get('edge_session')} 的旧消息: {data.get('action')}"
+                        )
                     else:
-                        if message_type.endswith("_material"):
-                            logger.trace(f"[MessageProcessor] 收到一条归属 {data.get('edge_session')} 的旧消息：{data}")
-                            logger.debug(f"[MessageProcessor] 跳过了一条归属 {data.get('edge_session')} 的旧消息: {data.get('action')}")
-                        else:
-                            await self._process_message(message_type, message_data)
-                except json.JSONDecodeError:
-                    logger.error(f"[MessageProcessor] Invalid JSON received: {message}")
-                except Exception as e:
-                    logger.error(f"[MessageProcessor] Error processing message: {str(e)}")
-                    logger.error(traceback.format_exc())
-
-        except websockets.exceptions.ConnectionClosed:
-            logger.info("[MessageProcessor] Message handler stopped - connection closed")
-        except Exception as e:
-            logger.error(f"[MessageProcessor] Message handler error: {str(e)}")
-            logger.error(traceback.format_exc())
+                        await self._process_message(message_type, message_data)
+            except json.JSONDecodeError:
+                logger.error(f"[MessageProcessor] Invalid JSON received: {message}")
+            except Exception as e:
+                logger.error(f"[MessageProcessor] Error processing message: {str(e)}")
+                logger.error(traceback.format_exc())
 
     async def _send_handler(self):
         """处理发送队列中的消息"""
@@ -596,6 +627,7 @@ class MessageProcessor:
 
         except asyncio.CancelledError:
             logger.debug("[MessageProcessor] Send handler cancelled")
+            raise
         except Exception as e:
             logger.error(f"[MessageProcessor] Fatal error in send handler: {str(e)}")
             logger.error(traceback.format_exc())
@@ -604,7 +636,7 @@ class MessageProcessor:
 
     async def _process_message(self, message_type: str, message_data: Dict[str, Any]):
         """处理收到的消息"""
-        logger.debug(f"[MessageProcessor] Processing message: {message_type}")
+        logger.trace(f"[MessageProcessor] Processing message: {message_type}")
 
         try:
             if message_type == "pong":
@@ -627,6 +659,10 @@ class MessageProcessor:
             # elif message_type == "session_id":
             #     self.session_id = message_data.get("session_id")
             #     logger.info(f"[MessageProcessor] Session ID: {self.session_id}")
+            elif message_type == "add_device":
+                await self._handle_device_manage(message_data, "add")
+            elif message_type == "remove_device":
+                await self._handle_device_manage(message_data, "remove")
             elif message_type == "request_restart":
                 await self._handle_request_restart(message_data)
             else:
@@ -698,13 +734,13 @@ class MessageProcessor:
             await self._send_action_state_response(
                 device_id, action_name, task_id, job_id, "query_action_status", True, 0
             )
-            logger.info(f"[MessageProcessor] Job {job_log} can start immediately")
+            logger.trace(f"[MessageProcessor] Job {job_log} can start immediately")
         else:
             # 需要排队
             await self._send_action_state_response(
                 device_id, action_name, task_id, job_id, "query_action_status", False, 10
             )
-            logger.info(f"[MessageProcessor] Job {job_log} queued")
+            logger.trace(f"[MessageProcessor] Job {job_log} queued")
 
             # 通知QueueProcessor有新的队列更新
             if self.queue_processor:
@@ -718,6 +754,32 @@ class MessageProcessor:
             req = JobAddReq(**data)
 
             job_log = format_job_log(req.job_id, req.task_id, req.device_id, req.action)
+
+            # 服务端对always_free动作可能跳过query_action_state直接发job_start，
+            # 此时job尚未注册，需要自动补注册
+            existing_job = self.device_manager.get_job_info(req.job_id)
+            if not existing_job:
+                action_name = req.action
+                device_action_key = f"/devices/{req.device_id}/{action_name}"
+                action_always_free = self._check_action_always_free(req.device_id, action_name)
+
+                if action_always_free:
+                    job_info = JobInfo(
+                        job_id=req.job_id,
+                        task_id=req.task_id,
+                        device_id=req.device_id,
+                        action_name=action_name,
+                        device_action_key=device_action_key,
+                        status=JobStatus.QUEUE,
+                        start_time=time.time(),
+                        always_free=True,
+                    )
+                    self.device_manager.add_queue_request(job_info)
+                    logger.info(f"[MessageProcessor] Job {job_log} always_free, auto-registered from direct job_start")
+                else:
+                    logger.error(f"[MessageProcessor] Job {job_log} not registered (missing query_action_state)")
+                    return
+
             success = self.device_manager.start_job(req.job_id)
             if not success:
                 logger.error(f"[MessageProcessor] Failed to start job {job_log}")
@@ -911,9 +973,7 @@ class MessageProcessor:
                         device_action_groups[key_add] = []
                     device_action_groups[key_add].append(item["uuid"])
 
-                    logger.info(
-                        f"[资源同步] 跨站Transfer: {item['uuid'][:8]} from {device_old_id} to {device_id}"
-                    )
+                    logger.info(f"[资源同步] 跨站Transfer: {item['uuid'][:8]} from {device_old_id} to {device_id}")
                 else:
                     # 正常update
                     key = (device_id, "update")
@@ -927,7 +987,9 @@ class MessageProcessor:
                     device_action_groups[key] = []
                 device_action_groups[key].append(item["uuid"])
 
-        logger.trace(f"[资源同步] 动作 {action} 分组数量: {len(device_action_groups)}, 总数量: {len(resource_uuid_list)}")
+        logger.trace(
+            f"[资源同步] 动作 {action} 分组数量: {len(device_action_groups)}, 总数量: {len(resource_uuid_list)}"
+        )
 
         # 为每个(device_id, action)创建独立的更新线程
         for (device_id, actual_action), items in device_action_groups.items():
@@ -963,45 +1025,77 @@ class MessageProcessor:
             )
             thread.start()
 
+    async def _handle_device_manage(self, device_list: list[ResourceDictType], action: str):
+        """Handle add_device / remove_device from LabGo server."""
+        if not device_list:
+            return
+
+        for item in device_list:
+            target_node_id = item.get("target_node_id", "host_node")
+
+            def _notify(target_id: str, act: str, cfg: ResourceDictType):
+                try:
+                    host_node = HostNode.get_instance(timeout=5)
+                    if not host_node:
+                        logger.error(f"[DeviceManage] HostNode not available for {act}_device")
+                        return
+                    success = host_node.notify_device_manage(target_id, act, cfg)
+                    if success:
+                        logger.info(f"[DeviceManage] {act}_device completed on {target_id}")
+                    else:
+                        logger.warning(f"[DeviceManage] {act}_device failed on {target_id}")
+                except Exception as e:
+                    logger.error(f"[DeviceManage] Error in {act}_device: {e}")
+                    logger.error(traceback.format_exc())
+
+            thread = threading.Thread(
+                target=_notify,
+                args=(target_node_id, action, item),
+                daemon=True,
+                name=f"DeviceManage-{action}-{item.get('id', '')}",
+            )
+            thread.start()
+
     async def _handle_request_restart(self, data: Dict[str, Any]):
         """
         处理重启请求
-        
+
         当LabGo发送request_restart时，执行清理并触发重启
         """
         reason = data.get("reason", "unknown")
         delay = data.get("delay", 2)  # 默认延迟2秒
         logger.info(f"[MessageProcessor] Received restart request, reason: {reason}, delay: {delay}s")
-        
+
         # 发送确认消息
-        if self.websocket_client:
-            await self.websocket_client.send_message({
-                "action": "restart_acknowledged",
-                "data": {"reason": reason, "delay": delay}
-            })
-        
+        self.send_message(
+            {"action": "restart_acknowledged", "data": {"reason": reason, "delay": delay}}
+        )
+
         # 设置全局重启标志
         import unilabos.app.main as main_module
+
         main_module._restart_requested = True
         main_module._restart_reason = reason
-        
+
         # 延迟后执行清理
         await asyncio.sleep(delay)
-        
+
         # 在新线程中执行清理，避免阻塞当前事件循环
         def do_cleanup():
             import time
+
             time.sleep(0.5)  # 给当前消息处理完成的时间
             logger.info(f"[MessageProcessor] Starting cleanup for restart, reason: {reason}")
             try:
                 from unilabos.app.utils import cleanup_for_restart
+
                 if cleanup_for_restart():
                     logger.info("[MessageProcessor] Cleanup successful, main() will restart")
                 else:
                     logger.error("[MessageProcessor] Cleanup failed")
             except Exception as e:
                 logger.error(f"[MessageProcessor] Error during cleanup: {e}")
-        
+
         cleanup_thread = threading.Thread(target=do_cleanup, name="RestartCleanupThread", daemon=True)
         cleanup_thread.start()
         logger.info(f"[MessageProcessor] Restart cleanup scheduled")
@@ -1077,6 +1171,7 @@ class QueueProcessor:
     def stop(self) -> None:
         """停止队列处理线程"""
         self.is_running = False
+        self.queue_update_event.set()  # 立即唤醒等待中的线程
         if self.thread and self.thread.is_alive():
             self.thread.join(timeout=2)
         logger.info("[QueueProcessor] Stopped")
@@ -1197,7 +1292,7 @@ class QueueProcessor:
             success = self.message_processor.send_message(message)
             job_log = format_job_log(job_info.job_id, job_info.task_id, job_info.device_id, job_info.action_name)
             if success:
-                logger.debug(f"[QueueProcessor] Sent busy/need_more for queued job {job_log}")
+                logger.trace(f"[QueueProcessor] Sent busy/need_more for queued job {job_log}")
             else:
                 logger.warning(f"[QueueProcessor] Failed to send busy status for job {job_log}")
 
@@ -1220,7 +1315,7 @@ class QueueProcessor:
             job_info.action_name,
         )
 
-        logger.info(f"[QueueProcessor] Job {job_log} completed with status: {status}")
+        logger.trace(f"[QueueProcessor] Job {job_log} completed with status: {status}")
 
         # 结束任务，获取下一个可执行的任务
         next_job = self.device_manager.end_job(job_id)
@@ -1240,8 +1335,8 @@ class QueueProcessor:
                 },
             }
             self.message_processor.send_message(message)
-            next_job_log = format_job_log(next_job.job_id, next_job.task_id, next_job.device_id, next_job.action_name)
-            logger.info(f"[QueueProcessor] Notified next job {next_job_log} can start")
+            # next_job_log = format_job_log(next_job.job_id, next_job.task_id, next_job.device_id, next_job.action_name)
+            # logger.debug(f"[QueueProcessor] Notified next job {next_job_log} can start")
 
             # 立即触发下一轮状态检查
             self.notify_queue_update()
@@ -1330,8 +1425,8 @@ class WebSocketClient(BaseCommunicationClient):
                 message = {"action": "normal_exit", "data": {"session_id": session_id}}
                 self.message_processor.send_message(message)
                 logger.info(f"[WebSocketClient] Sent normal_exit message with session_id: {session_id}")
-                # 给一点时间让消息发送出去
-                time.sleep(1)
+                # send_handler 每100ms检查一次队列，等300ms足以让消息发出
+                time.sleep(0.3)
             except Exception as e:
                 logger.warning(f"[WebSocketClient] Failed to send normal_exit message: {str(e)}")
 
@@ -1383,7 +1478,7 @@ class WebSocketClient(BaseCommunicationClient):
                 except (KeyError, AttributeError):
                     logger.warning(f"[WebSocketClient] Failed to remove job {item.job_id} from HostNode status")
 
-            logger.info(f"[WebSocketClient] Intercepting final status for job_id: {item.job_id} - {status}")
+            # logger.debug(f"[WebSocketClient] Intercepting final status for job_id: {item.job_id} - {status}")
 
             # 通知队列处理器job完成（包括timeout的job）
             self.queue_processor.handle_job_completed(item.job_id, status)
@@ -1444,15 +1539,17 @@ class WebSocketClient(BaseCommunicationClient):
         # 收集设备信息
         devices = []
         machine_name = BasicConfig.machine_name
-        
+
         try:
             host_node = HostNode.get_instance(0)
             if host_node:
                 # 获取设备信息
                 for device_id, namespace in host_node.devices_names.items():
-                    device_key = f"{namespace}/{device_id}" if namespace.startswith("/") else f"/{namespace}/{device_id}"
+                    device_key = (
+                        f"{namespace}/{device_id}" if namespace.startswith("/") else f"/{namespace}/{device_id}"
+                    )
                     is_online = device_key in host_node._online_devices
-                    
+
                     # 获取设备的动作信息
                     actions = {}
                     for action_id, client in host_node._action_clients.items():
@@ -1463,16 +1560,18 @@ class WebSocketClient(BaseCommunicationClient):
                                 "action_path": action_id,
                                 "action_type": str(type(client).__name__),
                             }
-                    
-                    devices.append({
-                        "device_id": device_id,
-                        "namespace": namespace,
-                        "device_key": device_key,
-                        "is_online": is_online,
-                        "machine_name": host_node.device_machine_names.get(device_id, machine_name),
-                        "actions": actions,
-                    })
-                
+
+                    devices.append(
+                        {
+                            "device_id": device_id,
+                            "namespace": namespace,
+                            "device_key": device_key,
+                            "is_online": is_online,
+                            "machine_name": host_node.device_machine_names.get(device_id, machine_name),
+                            "actions": actions,
+                        }
+                    )
+
                 logger.info(f"[WebSocketClient] Collected {len(devices)} devices for host_ready")
         except Exception as e:
             logger.warning(f"[WebSocketClient] Error collecting device info: {e}")