Merge dev branch: Add battery resources, bioyond_cell device registry, and fix file path resolution

unilabos/app/communication.py

@@ -141,7 +141,7 @@ class CommunicationClientFactory:
         """
         if cls._client_cache is None:
             cls._client_cache = cls.create_client(protocol)
-            logger.info(f"[CommunicationFactory] Created {type(cls._client_cache).__name__} client")
+            logger.trace(f"[CommunicationFactory] Created {type(cls._client_cache).__name__} client")
 
         return cls._client_cache
 

unilabos/app/main.py

@@ -20,6 +20,7 @@ if unilabos_dir not in sys.path:
 from unilabos.utils.banner_print import print_status, print_unilab_banner
 from unilabos.config.config import load_config, BasicConfig, HTTPConfig
 
+
 def load_config_from_file(config_path):
     if config_path is None:
         config_path = os.environ.get("UNILABOS_BASICCONFIG_CONFIG_PATH", None)
@@ -41,7 +42,7 @@ def convert_argv_dashes_to_underscores(args: argparse.ArgumentParser):
     for i, arg in enumerate(sys.argv):
         for option_string in option_strings:
             if arg.startswith(option_string):
-                new_arg = arg[:2] + arg[2:len(option_string)].replace("-", "_") + arg[len(option_string):]
+                new_arg = arg[:2] + arg[2 : len(option_string)].replace("-", "_") + arg[len(option_string) :]
                 sys.argv[i] = new_arg
                 break
 
@@ -49,6 +50,8 @@ def convert_argv_dashes_to_underscores(args: argparse.ArgumentParser):
 def parse_args():
     """解析命令行参数"""
     parser = argparse.ArgumentParser(description="Start Uni-Lab Edge server.")
+    subparsers = parser.add_subparsers(title="Valid subcommands", dest="command")
+
     parser.add_argument("-g", "--graph", help="Physical setup graph file path.")
     parser.add_argument("-c", "--controllers", default=None, help="Controllers config file path.")
     parser.add_argument(
@@ -105,7 +108,7 @@ def parse_args():
     parser.add_argument(
         "--port",
         type=int,
-        default=8002,
+        default=None,
         help="Port for web service information page",
     )
     parser.add_argument(
@@ -153,21 +156,54 @@ def parse_args():
         default=False,
         help="Complete registry information",
     )
+    # workflow upload subcommand
+    workflow_parser = subparsers.add_parser(
+        "workflow_upload",
+        aliases=["wf"],
+        help="Upload workflow from xdl/json/python files",
+    )
+    workflow_parser.add_argument(
+        "-f",
+        "--workflow_file",
+        type=str,
+        required=True,
+        help="Path to the workflow file (JSON format)",
+    )
+    workflow_parser.add_argument(
+        "-n",
+        "--workflow_name",
+        type=str,
+        default=None,
+        help="Workflow name, if not provided will use the name from file or filename",
+    )
+    workflow_parser.add_argument(
+        "--tags",
+        type=str,
+        nargs="*",
+        default=[],
+        help="Tags for the workflow (space-separated)",
+    )
+    workflow_parser.add_argument(
+        "--published",
+        action="store_true",
+        default=False,
+        help="Whether to publish the workflow (default: False)",
+    )
     return parser
 
 
 def main():
     """主函数"""
     # 解析命令行参数
-    args = parse_args()
-    convert_argv_dashes_to_underscores(args)
-    args_dict = vars(args.parse_args())
+    parser = parse_args()
+    convert_argv_dashes_to_underscores(parser)
+    args = parser.parse_args()
+    args_dict = vars(args)
 
     # 环境检查 - 检查并自动安装必需的包 (可选)
     if not args_dict.get("skip_env_check", False):
         from unilabos.utils.environment_check import check_environment
 
-        print_status("正在进行环境依赖检查...", "info")
         if not check_environment(auto_install=True):
             print_status("环境检查失败，程序退出", "error")
             os._exit(1)
@@ -218,19 +254,20 @@ def main():
 
     if hasattr(BasicConfig, "log_level"):
         logger.info(f"Log level set to '{BasicConfig.log_level}' from config file.")
-        configure_logger(loglevel=BasicConfig.log_level)
+    configure_logger(loglevel=BasicConfig.log_level, working_dir=working_dir)
 
-    if args_dict["addr"] == "test":
-        print_status("使用测试环境地址", "info")
-        HTTPConfig.remote_addr = "https://uni-lab.test.bohrium.com/api/v1"
-    elif args_dict["addr"] == "uat":
-        print_status("使用uat环境地址", "info")
-        HTTPConfig.remote_addr = "https://uni-lab.uat.bohrium.com/api/v1"
-    elif args_dict["addr"] == "local":
-        print_status("使用本地环境地址", "info")
-        HTTPConfig.remote_addr = "http://127.0.0.1:48197/api/v1"
-    else:
-        HTTPConfig.remote_addr = args_dict.get("addr", "")
+    if args.addr != parser.get_default("addr"):
+        if args.addr == "test":
+            print_status("使用测试环境地址", "info")
+            HTTPConfig.remote_addr = "https://uni-lab.test.bohrium.com/api/v1"
+        elif args.addr == "uat":
+            print_status("使用uat环境地址", "info")
+            HTTPConfig.remote_addr = "https://uni-lab.uat.bohrium.com/api/v1"
+        elif args.addr == "local":
+            print_status("使用本地环境地址", "info")
+            HTTPConfig.remote_addr = "http://127.0.0.1:48197/api/v1"
+        else:
+            HTTPConfig.remote_addr = args.addr
 
     # 设置BasicConfig参数
     if args_dict.get("ak", ""):
@@ -239,9 +276,12 @@ def main():
     if args_dict.get("sk", ""):
         BasicConfig.sk = args_dict.get("sk", "")
         print_status("传入了sk参数，优先采用传入参数！", "info")
+    BasicConfig.working_dir = working_dir
+
+    workflow_upload = args_dict.get("command") in ("workflow_upload", "wf")
 
     # 使用远程资源启动
-    if args_dict["use_remote_resource"]:
+    if not workflow_upload and args_dict["use_remote_resource"]:
         print_status("使用远程资源启动", "info")
         from unilabos.app.web import http_client
 
@@ -252,7 +292,8 @@ def main():
         else:
             print_status("远程资源不存在，本地将进行首次上报！", "info")
 
-    BasicConfig.working_dir = working_dir
+    BasicConfig.port = args_dict["port"] if args_dict["port"] else BasicConfig.port
+    BasicConfig.disable_browser = args_dict["disable_browser"] or BasicConfig.disable_browser
     BasicConfig.is_host_mode = not args_dict.get("is_slave", False)
     BasicConfig.slave_no_host = args_dict.get("slave_no_host", False)
     BasicConfig.upload_registry = args_dict.get("upload_registry", False)
@@ -281,9 +322,31 @@ def main():
 
     # 注册表
     lab_registry = build_registry(
-        args_dict["registry_path"], args_dict.get("complete_registry", False), args_dict["upload_registry"]
+        args_dict["registry_path"], args_dict.get("complete_registry", False), BasicConfig.upload_registry
     )
 
+    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")
+            try:
+                register_devices_and_resources(lab_registry)
+                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:
+            print_status("未提供 ak 和 sk，跳过设备注册", "info")
+    else:
+        print_status("本次启动注册表不报送云端，如果您需要联网调试，请在启动命令增加--upload_registry", "warning")
+
+    # 处理 workflow_upload 子命令
+    if workflow_upload:
+        from unilabos.workflow.wf_utils import handle_workflow_upload_command
+
+        handle_workflow_upload_command(args_dict)
+        print_status("工作流上传完成，程序退出", "info")
+        os._exit(0)
+
     if not BasicConfig.ak or not BasicConfig.sk:
         print_status("后续运行必须拥有一个实验室，请前往 https://uni-lab.bohrium.com 注册实验室！", "warning")
         os._exit(1)
@@ -291,7 +354,9 @@ def main():
     resource_tree_set: ResourceTreeSet
     resource_links: List[Dict[str, Any]]
     request_startup_json = http_client.request_startup_json()
-    if args_dict["graph"] is None:
+
+    file_path = args_dict.get("graph", BasicConfig.startup_json_path)
+    if file_path is None:
         if not request_startup_json:
             print_status(
                 "未指定设备加载文件路径，尝试从HTTP获取失败，请检查网络或者使用-g参数指定设备加载文件路径", "error"
@@ -301,7 +366,38 @@ def main():
             print_status("联网获取设备加载文件成功", "info")
         graph, resource_tree_set, resource_links = read_node_link_json(request_startup_json)
     else:
-        file_path = args_dict["graph"]
+        if not os.path.isfile(file_path):
+            # 尝试从 main.py 向上两级目录查找
+            temp_file_path = os.path.abspath(str(os.path.join(__file__, "..", "..", file_path)))
+            if os.path.isfile(temp_file_path):
+                print_status(f"使用相对路径{temp_file_path}", "info")
+                file_path = temp_file_path
+            else:
+                # 尝试在 working_dir 中查找
+                working_dir_file_path = os.path.join(working_dir, file_path)
+                if os.path.isfile(working_dir_file_path):
+                    print_status(f"在工作目录中找到文件: {working_dir_file_path}", "info")
+                    file_path = working_dir_file_path
+                else:
+                    # 尝试使用文件名在 working_dir 中查找
+                    file_name = os.path.basename(file_path)
+                    working_dir_file_path = os.path.join(working_dir, file_name)
+                    if os.path.isfile(working_dir_file_path):
+                        print_status(f"在工作目录中找到文件: {working_dir_file_path}", "info")
+                        file_path = working_dir_file_path
+        # 最终检查文件是否存在
+        if not os.path.isfile(file_path):
+            print_status(
+                f"无法找到设备加载文件: {file_path}\n"
+                f"已尝试在以下位置查找:\n"
+                f"  1. 原始路径: {args_dict.get('graph', BasicConfig.startup_json_path)}\n"
+                f"  2. 相对路径: {os.path.abspath(str(os.path.join(__file__, '..', '..', args_dict.get('graph', BasicConfig.startup_json_path) or '')))}\n"
+                f"  3. 工作目录: {os.path.join(working_dir, args_dict.get('graph', BasicConfig.startup_json_path) or '')}\n"
+                f"  4. 工作目录(仅文件名): {os.path.join(working_dir, os.path.basename(args_dict.get('graph', BasicConfig.startup_json_path) or ''))}\n"
+                f"请使用 -g 参数指定正确的文件路径，或在工作目录 {working_dir} 中放置文件",
+                "error"
+            )
+            os._exit(1)
         if file_path.endswith(".json"):
             graph, resource_tree_set, resource_links = read_node_link_json(file_path)
         else:
@@ -354,20 +450,6 @@ def main():
     args_dict["devices_config"] = resource_tree_set
     args_dict["graph"] = graph_res.physical_setup_graph
 
-    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")
-            try:
-                register_devices_and_resources(lab_registry)
-                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:
-            print_status("未提供 ak 和 sk，跳过设备注册", "info")
-    else:
-        print_status("本次启动注册表不报送云端，如果您需要联网调试，请在启动命令增加--upload_registry", "warning")
-
     if args_dict["controllers"] is not None:
         args_dict["controllers_config"] = yaml.safe_load(open(args_dict["controllers"], encoding="utf-8"))
     else:
@@ -382,6 +464,7 @@ def main():
         comm_client = get_communication_client()
         if "websocket" in args_dict["app_bridges"]:
             args_dict["bridges"].append(comm_client)
+
             def _exit(signum, frame):
                 comm_client.stop()
                 sys.exit(0)
@@ -413,26 +496,39 @@ def main():
             server_thread = threading.Thread(
                 target=start_server,
                 kwargs=dict(
-                    open_browser=not args_dict["disable_browser"],
-                    port=args_dict["port"],
+                    open_browser=not BasicConfig.disable_browser,
+                    port=BasicConfig.port,
                 ),
             )
             server_thread.start()
             asyncio.set_event_loop(asyncio.new_event_loop())
-            resource_visualization.start()
+            try:
+                resource_visualization.start()
+            except OSError as e:
+                if "AMENT_PREFIX_PATH" in str(e):
+                    print_status(f"ROS 2环境未正确设置，跳过3D可视化启动。错误详情: {e}", "warning")
+                    print_status(
+                        "建议解决方案：\n"
+                        "1. 激活Conda环境: conda activate unilab\n"
+                        "2. 或使用 --backend simple 参数\n"
+                        "3. 或使用 --visual disable 参数禁用可视化",
+                        "info",
+                    )
+                else:
+                    raise
             while True:
                 time.sleep(1)
         else:
             start_backend(**args_dict)
             start_server(
                 open_browser=not args_dict["disable_browser"],
-                port=args_dict["port"],
+                port=BasicConfig.port,
             )
     else:
         start_backend(**args_dict)
         start_server(
             open_browser=not args_dict["disable_browser"],
-            port=args_dict["port"],
+            port=BasicConfig.port,
         )
 
 

unilabos/app/model.py

@@ -51,21 +51,25 @@ class Resp(BaseModel):
 class JobAddReq(BaseModel):
     device_id: str = Field(examples=["Gripper"], description="device id")
     action: str = Field(examples=["_execute_driver_command_async"], description="action name", default="")
-    action_type: str = Field(examples=["unilabos_msgs.action._str_single_input.StrSingleInput"], description="action name", default="")
-    action_args: dict = Field(examples=[{'string': 'string'}], description="action name", default="")
-    task_id: str = Field(examples=["task_id"], description="task uuid")
-    job_id: str = Field(examples=["job_id"], description="goal uuid")
-    node_id: str = Field(examples=["node_id"], description="node uuid")
-    server_info: dict = Field(examples=[{"send_timestamp": 1717000000.0}], description="server info")
+    action_type: str = Field(
+        examples=["unilabos_msgs.action._str_single_input.StrSingleInput"], description="action type", default=""
+    )
+    action_args: dict = Field(examples=[{"string": "string"}], description="action arguments", default_factory=dict)
+    task_id: str = Field(examples=["task_id"], description="task uuid (auto-generated if empty)", default="")
+    job_id: str = Field(examples=["job_id"], description="goal uuid (auto-generated if empty)", default="")
+    node_id: str = Field(examples=["node_id"], description="node uuid", default="")
+    server_info: dict = Field(
+        examples=[{"send_timestamp": 1717000000.0}],
+        description="server info (auto-generated if empty)",
+        default_factory=dict,
+    )
 
-    data: dict = Field(examples=[{"position": 30, "torque": 5, "action": "push_to"}], default={})
+    data: dict = Field(examples=[{"position": 30, "torque": 5, "action": "push_to"}], default_factory=dict)
 
 
 class JobStepFinishReq(BaseModel):
     token: str = Field(examples=["030944"], description="token")
-    request_time: str = Field(
-        examples=["2024-12-12 12:12:12.xxx"], description="requestTime"
-    )
+    request_time: str = Field(examples=["2024-12-12 12:12:12.xxx"], description="requestTime")
     data: dict = Field(
         examples=[
             {
@@ -83,9 +87,7 @@ class JobStepFinishReq(BaseModel):
 
 class JobPreintakeFinishReq(BaseModel):
     token: str = Field(examples=["030944"], description="token")
-    request_time: str = Field(
-        examples=["2024-12-12 12:12:12.xxx"], description="requestTime"
-    )
+    request_time: str = Field(examples=["2024-12-12 12:12:12.xxx"], description="requestTime")
     data: dict = Field(
         examples=[
             {
@@ -102,9 +104,7 @@ class JobPreintakeFinishReq(BaseModel):
 
 class JobFinishReq(BaseModel):
     token: str = Field(examples=["030944"], description="token")
-    request_time: str = Field(
-        examples=["2024-12-12 12:12:12.xxx"], description="requestTime"
-    )
+    request_time: str = Field(examples=["2024-12-12 12:12:12.xxx"], description="requestTime")
     data: dict = Field(
         examples=[
             {
@@ -133,6 +133,10 @@ class JobData(BaseModel):
         default=0,
         description="0:UNKNOWN, 1:ACCEPTED, 2:EXECUTING, 3:CANCELING, 4:SUCCEEDED, 5:CANCELED, 6:ABORTED",
     )
+    result: dict = Field(
+        default_factory=dict,
+        description="Job result data (available when status is SUCCEEDED/CANCELED/ABORTED)",
+    )
 
 
 class JobStatusResp(Resp):

unilabos/app/oss_upload.py

@@ -1,161 +1,158 @@
 import argparse
 import os
 import time
-from typing import Dict, Optional, Tuple
+from datetime import datetime
+from pathlib import Path
+from typing import Dict, Optional, Tuple, Union
 
 import requests
 
-from unilabos.config.config import OSSUploadConfig
+from unilabos.app.web.client import http_client, HTTPClient
+from unilabos.utils import logger
 
 
-def _init_upload(file_path: str, oss_path: str, filename: Optional[str] = None,
-                process_key: str = "file-upload", device_id: str = "default",
-                expires_hours: int = 1) -> Tuple[bool, Dict]:
+def _get_oss_token(
+    filename: str,
+    driver_name: str = "default",
+    exp_type: str = "default",
+    client: Optional[HTTPClient] = None,
+) -> Tuple[bool, Dict]:
     """
-    初始化上传过程
+    获取OSS上传Token
 
     Args:
-        file_path: 本地文件路径
-        oss_path: OSS目标路径
-        filename: 文件名，如果为None则使用file_path的文件名
-        process_key: 处理键
-        device_id: 设备ID
-        expires_hours: 链接过期小时数
+        filename: 文件名
+        driver_name: 驱动名称
+        exp_type: 实验类型
+        client: HTTPClient实例，如果不提供则使用默认的http_client
 
     Returns:
-        (成功标志, 响应数据)
+        (成功标志, Token数据字典包含token/path/host/expires)
     """
-    if filename is None:
-        filename = os.path.basename(file_path)
+    # 使用提供的client或默认的http_client
+    if client is None:
+        client = http_client
 
-    # 构造初始化请求
-    url = f"{OSSUploadConfig.api_host}{OSSUploadConfig.init_endpoint}"
-    headers = {
-        "Authorization": OSSUploadConfig.authorization,
-        "Content-Type": "application/json"
-    }
+    # 构造scene参数: driver_name-exp_type
+    sub_path = f"{driver_name}-{exp_type}"
 
-    payload = {
-        "device_id": device_id,
-        "process_key": process_key,
-        "filename": filename,
-        "path": oss_path,
-        "expires_hours": expires_hours
-    }
+    # 构造请求URL，使用client的remote_addr（已包含/api/v1/）
+    url = f"{client.remote_addr}/applications/token"
+    params = {"sub_path": sub_path, "filename": filename, "scene": "job"}
 
     try:
-        response = requests.post(url, headers=headers, json=payload)
-        if response.status_code == 201:
-            result = response.json()
-            if result.get("code") == "10000":
-                return True, result.get("data", {})
+        logger.info(f"[OSS] 请求预签名URL: sub_path={sub_path}, filename={filename}")
+        response = requests.get(url, params=params, headers={"Authorization": f"Lab {client.auth}"}, timeout=10)
 
-        print(f"初始化上传失败: {response.status_code}, {response.text}")
+        if response.status_code == 200:
+            result = response.json()
+            if result.get("code") == 0:
+                data = result.get("data", {})
+
+                # 转换expires时间戳为可读格式
+                expires_timestamp = data.get("expires", 0)
+                expires_datetime = datetime.fromtimestamp(expires_timestamp)
+                expires_str = expires_datetime.strftime("%Y-%m-%d %H:%M:%S")
+
+                logger.info(f"[OSS] 获取预签名URL成功")
+                logger.info(f"[OSS]   - URL: {data.get('url', 'N/A')}")
+                logger.info(f"[OSS]   - Expires: {expires_str} (timestamp: {expires_timestamp})")
+
+                return True, data
+
+        logger.error(f"[OSS] 获取预签名URL失败: {response.status_code}, {response.text}")
         return False, {}
     except Exception as e:
-        print(f"初始化上传异常: {str(e)}")
+        logger.error(f"[OSS] 获取预签名URL异常: {str(e)}")
         return False, {}
 
 
 def _put_upload(file_path: str, upload_url: str) -> bool:
     """
-    执行PUT上传
+    使用预签名URL上传文件到OSS
 
     Args:
         file_path: 本地文件路径
-        upload_url: 上传URL
+        upload_url: 完整的预签名上传URL
 
     Returns:
         是否成功
     """
     try:
+        logger.info(f"[OSS] 开始上传文件: {file_path}")
+
         with open(file_path, "rb") as f:
-            response = requests.put(upload_url, data=f)
+            # 使用预签名URL上传，不需要额外的认证header
+            response = requests.put(upload_url, data=f, timeout=300)
+
             if response.status_code == 200:
+                logger.info(f"[OSS] 文件上传成功")
                 return True
 
-        print(f"PUT上传失败: {response.status_code}, {response.text}")
+        logger.error(f"[OSS] 上传失败: {response.status_code}")
+        logger.error(f"[OSS] 响应内容: {response.text[:500] if response.text else '无响应内容'}")
         return False
     except Exception as e:
-        print(f"PUT上传异常: {str(e)}")
+        logger.error(f"[OSS] 上传异常: {str(e)}")
         return False
 
 
-def _complete_upload(uuid: str) -> bool:
-    """
-    完成上传过程
-
-    Args:
-        uuid: 上传的UUID
-
-    Returns:
-        是否成功
-    """
-    url = f"{OSSUploadConfig.api_host}{OSSUploadConfig.complete_endpoint}"
-    headers = {
-        "Authorization": OSSUploadConfig.authorization,
-        "Content-Type": "application/json"
-    }
-
-    payload = {
-        "uuid": uuid
-    }
-
-    try:
-        response = requests.post(url, headers=headers, json=payload)
-        if response.status_code == 200:
-            result = response.json()
-            if result.get("code") == "10000":
-                return True
-
-        print(f"完成上传失败: {response.status_code}, {response.text}")
-        return False
-    except Exception as e:
-        print(f"完成上传异常: {str(e)}")
-        return False
-
-
-def oss_upload(file_path: str, oss_path: str, filename: Optional[str] = None,
-              process_key: str = "file-upload", device_id: str = "default") -> bool:
+def oss_upload(
+    file_path: Union[str, Path],
+    filename: Optional[str] = None,
+    driver_name: str = "default",
+    exp_type: str = "default",
+    max_retries: int = 3,
+    client: Optional[HTTPClient] = None,
+) -> Dict:
     """
     文件上传主函数，包含重试机制
 
     Args:
         file_path: 本地文件路径
-        oss_path: OSS目标路径
         filename: 文件名，如果为None则使用file_path的文件名
-        process_key: 处理键
-        device_id: 设备ID
+        driver_name: 驱动名称，用于构造scene
+        exp_type: 实验类型，用于构造scene
+        max_retries: 最大重试次数
+        client: HTTPClient实例，如果不提供则使用默认的http_client
 
     Returns:
-        是否成功上传
+        Dict: {
+            "success": bool,  # 是否上传成功
+            "original_path": str,  # 原始文件路径
+            "oss_path": str  # OSS路径（成功时）或空字符串（失败时）
+        }
     """
-    max_retries = OSSUploadConfig.max_retries
+    file_path = Path(file_path)
+    if filename is None:
+        filename = os.path.basename(file_path)
+
+    if not os.path.exists(file_path):
+        logger.error(f"[OSS] 文件不存在: {file_path}")
+        return {"success": False, "original_path": file_path, "oss_path": ""}
+
     retry_count = 0
+    oss_path = ""
 
     while retry_count < max_retries:
         try:
-            # 步骤1：初始化上传
-            init_success, init_data = _init_upload(
-                file_path=file_path,
-                oss_path=oss_path,
-                filename=filename,
-                process_key=process_key,
-                device_id=device_id
+            # 步骤1：获取预签名URL
+            token_success, token_data = _get_oss_token(
+                filename=filename, driver_name=driver_name, exp_type=exp_type, client=client
             )
 
-            if not init_success:
-                print(f"初始化上传失败，重试 {retry_count + 1}/{max_retries}")
+            if not token_success:
+                logger.warning(f"[OSS] 获取预签名URL失败，重试 {retry_count + 1}/{max_retries}")
                 retry_count += 1
-                time.sleep(1)  # 等待1秒后重试
+                time.sleep(1)
                 continue
 
-            # 获取UUID和上传URL
-            uuid = init_data.get("uuid")
-            upload_url = init_data.get("upload_url")
+            # 获取预签名URL和OSS路径
+            upload_url = token_data.get("url")
+            oss_path = token_data.get("path", "")
 
-            if not uuid or not upload_url:
-                print(f"初始化上传返回数据不完整，重试 {retry_count + 1}/{max_retries}")
+            if not upload_url:
+                logger.warning(f"[OSS] 无法获取上传URL，API未返回url字段")
                 retry_count += 1
                 time.sleep(1)
                 continue
@@ -163,69 +160,82 @@ def oss_upload(file_path: str, oss_path: str, filename: Optional[str] = None,
             # 步骤2：PUT上传文件
             put_success = _put_upload(file_path, upload_url)
             if not put_success:
-                print(f"PUT上传失败，重试 {retry_count + 1}/{max_retries}")
-                retry_count += 1
-                time.sleep(1)
-                continue
-
-            # 步骤3：完成上传
-            complete_success = _complete_upload(uuid)
-            if not complete_success:
-                print(f"完成上传失败，重试 {retry_count + 1}/{max_retries}")
+                logger.warning(f"[OSS] PUT上传失败，重试 {retry_count + 1}/{max_retries}")
                 retry_count += 1
                 time.sleep(1)
                 continue
 
             # 所有步骤都成功
-            print(f"文件 {file_path} 上传成功")
-            return True
+            logger.info(f"[OSS] 文件 {file_path} 上传成功")
+            return {"success": True, "original_path": file_path, "oss_path": oss_path}
 
         except Exception as e:
-            print(f"上传过程异常: {str(e)}，重试 {retry_count + 1}/{max_retries}")
+            logger.error(f"[OSS] 上传过程异常: {str(e)}，重试 {retry_count + 1}/{max_retries}")
             retry_count += 1
             time.sleep(1)
 
-    print(f"文件 {file_path} 上传失败，已达到最大重试次数 {max_retries}")
-    return False
+    logger.error(f"[OSS] 文件 {file_path} 上传失败，已达到最大重试次数 {max_retries}")
+    return {"success": False, "original_path": file_path, "oss_path": oss_path}
 
 
 if __name__ == "__main__":
-    # python -m unilabos.app.oss_upload -f /path/to/your/file.txt
+    # python -m unilabos.app.oss_upload -f /path/to/your/file.txt --driver HPLC --type test
+    # python -m unilabos.app.oss_upload -f /path/to/your/file.txt --driver HPLC --type test \
+    #        --ak xxx --sk yyy --remote-addr http://xxx/api/v1
     # 命令行参数解析
-    parser = argparse.ArgumentParser(description='文件上传测试工具')
-    parser.add_argument('--file', '-f', type=str, required=True, help='要上传的本地文件路径')
-    parser.add_argument('--path', '-p', type=str, default='/HPLC1/Any', help='OSS目标路径')
-    parser.add_argument('--device', '-d', type=str, default='test-device', help='设备ID')
-    parser.add_argument('--process', '-k', type=str, default='HPLC-txt-result', help='处理键')
+    parser = argparse.ArgumentParser(description="文件上传测试工具")
+    parser.add_argument("--file", "-f", type=str, required=True, help="要上传的本地文件路径")
+    parser.add_argument("--driver", "-d", type=str, default="default", help="驱动名称")
+    parser.add_argument("--type", "-t", type=str, default="default", help="实验类型")
+    parser.add_argument("--ak", type=str, help="Access Key，如果提供则覆盖配置")
+    parser.add_argument("--sk", type=str, help="Secret Key，如果提供则覆盖配置")
+    parser.add_argument("--remote-addr", type=str, help="远程服务器地址（包含/api/v1），如果提供则覆盖配置")
 
     args = parser.parse_args()
 
     # 检查文件是否存在
     if not os.path.exists(args.file):
-        print(f"错误：文件 {args.file} 不存在")
+        logger.error(f"错误：文件 {args.file} 不存在")
         exit(1)
 
-    print("=" * 50)
-    print(f"开始上传文件: {args.file}")
-    print(f"目标路径: {args.path}")
-    print(f"设备ID: {args.device}")
-    print(f"处理键: {args.process}")
-    print("=" * 50)
+    # 如果提供了ak/sk/remote_addr，创建临时HTTPClient
+    temp_client = None
+    if args.ak and args.sk:
+        import base64
+
+        auth = base64.b64encode(f"{args.ak}:{args.sk}".encode("utf-8")).decode("utf-8")
+        remote_addr = args.remote_addr if args.remote_addr else http_client.remote_addr
+        temp_client = HTTPClient(remote_addr=remote_addr, auth=auth)
+        logger.info(f"[配置] 使用自定义配置: remote_addr={remote_addr}")
+    elif args.remote_addr:
+        temp_client = HTTPClient(remote_addr=args.remote_addr, auth=http_client.auth)
+        logger.info(f"[配置] 使用自定义remote_addr: {args.remote_addr}")
+    else:
+        logger.info(f"[配置] 使用默认配置: remote_addr={http_client.remote_addr}")
+
+    logger.info("=" * 50)
+    logger.info(f"开始上传文件: {args.file}")
+    logger.info(f"驱动名称: {args.driver}")
+    logger.info(f"实验类型: {args.type}")
+    logger.info(f"Scene: {args.driver}-{args.type}")
+    logger.info("=" * 50)
 
     # 执行上传
-    success = oss_upload(
+    result = oss_upload(
         file_path=args.file,
-        oss_path=args.path,
         filename=None,  # 使用默认文件名
-        process_key=args.process,
-        device_id=args.device
+        driver_name=args.driver,
+        exp_type=args.type,
+        client=temp_client,
     )
 
     # 输出结果
-    if success:
-        print("\n√ 文件上传成功！")
+    if result["success"]:
+        logger.info(f"\n√ 文件上传成功！")
+        logger.info(f"原始路径: {result['original_path']}")
+        logger.info(f"OSS路径: {result['oss_path']}")
         exit(0)
     else:
-        print("\n× 文件上传失败！")
+        logger.error(f"\n× 文件上传失败！")
+        logger.error(f"原始路径: {result['original_path']}")
         exit(1)
-

unilabos/app/web/api.py

@@ -9,13 +9,22 @@ import asyncio
 
 import yaml
 
-from unilabos.app.web.controler import devices, job_add, job_info
+from unilabos.app.web.controller import (
+    devices,
+    job_add,
+    job_info,
+    get_online_devices,
+    get_device_actions,
+    get_action_schema,
+    get_all_available_actions,
+)
 from unilabos.app.model import (
     Resp,
     RespCode,
     JobStatusResp,
     JobAddResp,
     JobAddReq,
+    JobData,
 )
 from unilabos.app.web.utils.host_utils import get_host_node_info
 from unilabos.registry.registry import lab_registry
@@ -1234,6 +1243,65 @@ def get_devices():
     return Resp(data=dict(data))
 
 
+@api.get("/online-devices", summary="Online devices list", response_model=Resp)
+def api_get_online_devices():
+    """获取在线设备列表
+
+    返回当前在线的设备列表，包含设备ID、命名空间、机器名等信息
+    """
+    isok, data = get_online_devices()
+    if not isok:
+        return Resp(code=RespCode.ErrorHostNotInit, message=data.get("error", "Unknown error"))
+
+    return Resp(data=data)
+
+
+@api.get("/devices/{device_id}/actions", summary="Device actions list", response_model=Resp)
+def api_get_device_actions(device_id: str):
+    """获取设备可用的动作列表
+
+    Args:
+        device_id: 设备ID
+
+    返回指定设备的所有可用动作，包含动作名称、类型、是否繁忙等信息
+    """
+    isok, data = get_device_actions(device_id)
+    if not isok:
+        return Resp(code=RespCode.ErrorInvalidReq, message=data.get("error", "Unknown error"))
+
+    return Resp(data=data)
+
+
+@api.get("/devices/{device_id}/actions/{action_name}/schema", summary="Action schema", response_model=Resp)
+def api_get_action_schema(device_id: str, action_name: str):
+    """获取动作的Schema详情
+
+    Args:
+        device_id: 设备ID
+        action_name: 动作名称
+
+    返回动作的参数Schema、默认值、类型等详细信息
+    """
+    isok, data = get_action_schema(device_id, action_name)
+    if not isok:
+        return Resp(code=RespCode.ErrorInvalidReq, message=data.get("error", "Unknown error"))
+
+    return Resp(data=data)
+
+
+@api.get("/actions", summary="All available actions", response_model=Resp)
+def api_get_all_actions():
+    """获取所有设备的可用动作
+
+    返回所有已注册设备的动作列表，包含设备信息和各动作的状态
+    """
+    isok, data = get_all_available_actions()
+    if not isok:
+        return Resp(code=RespCode.ErrorHostNotInit, message=data.get("error", "Unknown error"))
+
+    return Resp(data=data)
+
+
 @api.get("/job/{id}/status", summary="Job status", response_model=JobStatusResp)
 def job_status(id: str):
     """获取任务状态"""
@@ -1244,11 +1312,22 @@ def job_status(id: str):
 @api.post("/job/add", summary="Create job", response_model=JobAddResp)
 def post_job_add(req: JobAddReq):
     """创建任务"""
-    device_id = req.device_id
-    if not req.data:
-        return Resp(code=RespCode.ErrorInvalidReq, message="Invalid request data")
+    # 检查必要参数：device_id 和 action
+    if not req.device_id:
+        return JobAddResp(
+            data=JobData(jobId="", status=6),
+            code=RespCode.ErrorInvalidReq,
+            message="device_id is required",
+        )
+
+    action_name = req.data.get("action", req.action) if req.data else req.action
+    if not action_name:
+        return JobAddResp(
+            data=JobData(jobId="", status=6),
+            code=RespCode.ErrorInvalidReq,
+            message="action is required",
+        )
 
-    req.device_id = device_id
     data = job_add(req)
     return JobAddResp(data=data)
 

unilabos/app/web/client.py

@@ -76,7 +76,8 @@ class HTTPClient:
             Dict[str, str]: 旧UUID到新UUID的映射关系 {old_uuid: new_uuid}
         """
         with open(os.path.join(BasicConfig.working_dir, "req_resource_tree_add.json"), "w", encoding="utf-8") as f:
-            f.write(json.dumps({"nodes": [x for xs in resources.dump() for x in xs], "mount_uuid": mount_uuid}, indent=4))
+            payload = {"nodes": [x for xs in resources.dump() for x in xs], "mount_uuid": mount_uuid}
+            f.write(json.dumps(payload, indent=4))
         # 从序列化数据中提取所有节点的UUID（保存旧UUID）
         old_uuids = {n.res_content.uuid: n for n in resources.all_nodes}
         if not self.initialized or first_add:
@@ -331,6 +332,67 @@ class HTTPClient:
                 logger.error(f"响应内容: {response.text}")
         return None
 
+    def workflow_import(
+        self,
+        name: str,
+        workflow_uuid: str,
+        workflow_name: str,
+        nodes: List[Dict[str, Any]],
+        edges: List[Dict[str, Any]],
+        tags: Optional[List[str]] = None,
+        published: bool = False,
+    ) -> Dict[str, Any]:
+        """
+        导入工作流到服务器
+
+        Args:
+            name: 工作流名称（顶层）
+            workflow_uuid: 工作流UUID
+            workflow_name: 工作流名称（data内部）
+            nodes: 工作流节点列表
+            edges: 工作流边列表
+            tags: 工作流标签列表，默认为空列表
+            published: 是否发布工作流，默认为False
+
+        Returns:
+            Dict: API响应数据，包含 code 和 data (uuid, name)
+        """
+        # target_lab_uuid 暂时使用默认值，后续由后端根据 ak/sk 获取
+        payload = {
+            "target_lab_uuid": "28c38bb0-63f6-4352-b0d8-b5b8eb1766d5",
+            "name": name,
+            "data": {
+                "workflow_uuid": workflow_uuid,
+                "workflow_name": workflow_name,
+                "nodes": nodes,
+                "edges": edges,
+                "tags": tags if tags is not None else [],
+                "published": published,
+            },
+        }
+        # 保存请求到文件
+        with open(os.path.join(BasicConfig.working_dir, "req_workflow_upload.json"), "w", encoding="utf-8") as f:
+            f.write(json.dumps(payload, indent=4, ensure_ascii=False))
+
+        response = requests.post(
+            f"{self.remote_addr}/lab/workflow/owner/import",
+            json=payload,
+            headers={"Authorization": f"Lab {self.auth}"},
+            timeout=60,
+        )
+        # 保存响应到文件
+        with open(os.path.join(BasicConfig.working_dir, "res_workflow_upload.json"), "w", encoding="utf-8") as f:
+            f.write(f"{response.status_code}" + "\n" + response.text)
+
+        if response.status_code == 200:
+            res = response.json()
+            if "code" in res and res["code"] != 0:
+                logger.error(f"导入工作流失败: {response.text}")
+            return res
+        else:
+            logger.error(f"导入工作流失败: {response.status_code}, {response.text}")
+            return {"code": response.status_code, "message": response.text}
+
 
 # 创建默认客户端实例
 http_client = HTTPClient()

unilabos/app/web/controler.py

@@ -1,45 +0,0 @@
-
-import json
-import traceback
-import uuid
-from unilabos.app.model import JobAddReq, JobData
-from unilabos.ros.nodes.presets.host_node import HostNode
-from unilabos.utils.type_check import serialize_result_info
-
-
-def get_resources() -> tuple:
-    if HostNode.get_instance() is None:
-        return False, "Host node not initialized"
-
-    return True, HostNode.get_instance().resources_config
-
-def devices() -> tuple:
-    if HostNode.get_instance() is None:
-        return False, "Host node not initialized"
-    
-    return True, HostNode.get_instance().devices_config
-
-def job_info(id: str):
-    get_goal_status = HostNode.get_instance().get_goal_status(id)
-    return JobData(jobId=id, status=get_goal_status)
-
-def job_add(req: JobAddReq) -> JobData:
-    if req.job_id is None:
-        req.job_id = str(uuid.uuid4())
-    action_name = req.data["action"]
-    action_type = req.data.get("action_type", "LocalUnknown")
-    action_args = req.data.get("action_kwargs", None)  # 兼容老版本，后续删除
-    if action_args is None:
-        action_args = req.data.get("action_args")
-    else:
-        if "command" in action_args:
-            action_args = action_args["command"]
-    # print(f"job_add:{req.device_id} {action_name} {action_kwargs}")
-    try:
-        HostNode.get_instance().send_goal(req.device_id, action_type=action_type, action_name=action_name, action_kwargs=action_args, goal_uuid=req.job_id, server_info=req.server_info)
-    except Exception as e:
-        for bridge in HostNode.get_instance().bridges:
-            traceback.print_exc()
-            if hasattr(bridge, "publish_job_status"):
-                bridge.publish_job_status({}, req.job_id, "failed", serialize_result_info(traceback.format_exc(), False, {}))
-    return JobData(jobId=req.job_id)

unilabos/app/web/controller.py

@@ -0,0 +1,587 @@
+"""
+Web API Controller
+
+提供Web API的控制器函数，处理设备、任务和动作相关的业务逻辑
+"""
+
+import threading
+import time
+import traceback
+import uuid
+from dataclasses import dataclass, field
+from typing import Optional, Dict, Any, Tuple
+
+from unilabos.app.model import JobAddReq, JobData
+from unilabos.ros.nodes.presets.host_node import HostNode
+from unilabos.utils import logger
+
+
+@dataclass
+class JobResult:
+    """任务结果数据"""
+
+    job_id: str
+    status: int  # 4:SUCCEEDED, 5:CANCELED, 6:ABORTED
+    result: Dict[str, Any] = field(default_factory=dict)
+    feedback: Dict[str, Any] = field(default_factory=dict)
+    timestamp: float = field(default_factory=time.time)
+
+
+class JobResultStore:
+    """任务结果存储（单例）"""
+
+    _instance: Optional["JobResultStore"] = None
+    _lock = threading.Lock()
+
+    def __init__(self):
+        if not hasattr(self, "_initialized"):
+            self._results: Dict[str, JobResult] = {}
+            self._results_lock = threading.RLock()
+            self._initialized = True
+
+    def __new__(cls):
+        if cls._instance is None:
+            with cls._lock:
+                if cls._instance is None:
+                    cls._instance = super().__new__(cls)
+        return cls._instance
+
+    def store_result(
+        self, job_id: str, status: int, result: Optional[Dict[str, Any]], feedback: Optional[Dict[str, Any]] = None
+    ):
+        """存储任务结果"""
+        with self._results_lock:
+            self._results[job_id] = JobResult(
+                job_id=job_id,
+                status=status,
+                result=result or {},
+                feedback=feedback or {},
+                timestamp=time.time(),
+            )
+            logger.debug(f"[JobResultStore] Stored result for job {job_id[:8]}, status={status}")
+
+    def get_and_remove(self, job_id: str) -> Optional[JobResult]:
+        """获取并删除任务结果"""
+        with self._results_lock:
+            result = self._results.pop(job_id, None)
+            if result:
+                logger.debug(f"[JobResultStore] Retrieved and removed result for job {job_id[:8]}")
+            return result
+
+    def get_result(self, job_id: str) -> Optional[JobResult]:
+        """仅获取任务结果（不删除）"""
+        with self._results_lock:
+            return self._results.get(job_id)
+
+    def cleanup_old_results(self, max_age_seconds: float = 3600):
+        """清理过期的结果"""
+        current_time = time.time()
+        with self._results_lock:
+            expired_jobs = [
+                job_id for job_id, result in self._results.items() if current_time - result.timestamp > max_age_seconds
+            ]
+            for job_id in expired_jobs:
+                del self._results[job_id]
+                logger.debug(f"[JobResultStore] Cleaned up expired result for job {job_id[:8]}")
+
+
+# 全局结果存储实例
+job_result_store = JobResultStore()
+
+
+def store_job_result(
+    job_id: str, status: str, result: Optional[Dict[str, Any]], feedback: Optional[Dict[str, Any]] = None
+):
+    """存储任务结果（供外部调用）
+
+    Args:
+        job_id: 任务ID
+        status: 状态字符串 ("success", "failed", "cancelled")
+        result: 结果数据
+        feedback: 反馈数据
+    """
+    # 转换状态字符串为整数
+    status_map = {
+        "success": 4,  # SUCCEEDED
+        "failed": 6,  # ABORTED
+        "cancelled": 5,  # CANCELED
+        "running": 2,  # EXECUTING
+    }
+    status_int = status_map.get(status, 0)
+
+    # 只存储最终状态
+    if status_int in (4, 5, 6):
+        job_result_store.store_result(job_id, status_int, result, feedback)
+
+
+def get_resources() -> Tuple[bool, Any]:
+    """获取资源配置
+
+    Returns:
+        Tuple[bool, Any]: (是否成功, 资源配置或错误信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, "Host node not initialized"
+
+    return True, host_node.resources_config
+
+
+def devices() -> Tuple[bool, Any]:
+    """获取设备配置
+
+    Returns:
+        Tuple[bool, Any]: (是否成功, 设备配置或错误信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, "Host node not initialized"
+
+    return True, host_node.devices_config
+
+
+def job_info(job_id: str, remove_after_read: bool = True) -> JobData:
+    """获取任务信息
+
+    Args:
+        job_id: 任务ID
+        remove_after_read: 是否在读取后删除结果（默认True）
+
+    Returns:
+        JobData: 任务数据
+    """
+    # 首先检查结果存储中是否有已完成的结果
+    if remove_after_read:
+        stored_result = job_result_store.get_and_remove(job_id)
+    else:
+        stored_result = job_result_store.get_result(job_id)
+
+    if stored_result:
+        # 有存储的结果，直接返回
+        return JobData(
+            jobId=job_id,
+            status=stored_result.status,
+            result=stored_result.result,
+        )
+
+    # 没有存储的结果，从 HostNode 获取当前状态
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return JobData(jobId=job_id, status=0)
+
+    get_goal_status = host_node.get_goal_status(job_id)
+    return JobData(jobId=job_id, status=get_goal_status)
+
+
+def check_device_action_busy(device_id: str, action_name: str) -> Tuple[bool, Optional[str]]:
+    """检查设备动作是否正在执行（被占用）
+
+    Args:
+        device_id: 设备ID
+        action_name: 动作名称
+
+    Returns:
+        Tuple[bool, Optional[str]]: (是否繁忙, 当前执行的job_id或None)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, None
+
+    device_action_key = f"/devices/{device_id}/{action_name}"
+
+    # 检查 _device_action_status 中是否有正在执行的任务
+    if device_action_key in host_node._device_action_status:
+        status = host_node._device_action_status[device_action_key]
+        if status.job_ids:
+            # 返回第一个正在执行的job_id
+            current_job_id = next(iter(status.job_ids.keys()), None)
+            return True, current_job_id
+
+    return False, None
+
+
+def _get_action_type(device_id: str, action_name: str) -> Optional[str]:
+    """从注册表自动获取动作类型
+
+    Args:
+        device_id: 设备ID
+        action_name: 动作名称
+
+    Returns:
+        动作类型字符串，未找到返回None
+    """
+    try:
+        from unilabos.ros.nodes.base_device_node import registered_devices
+
+        # 方法1: 从运行时注册设备获取
+        if device_id in registered_devices:
+            device_info = registered_devices[device_id]
+            base_node = device_info.get("base_node_instance")
+            if base_node and hasattr(base_node, "_action_value_mappings"):
+                action_mappings = base_node._action_value_mappings
+                # 尝试直接匹配或 auto- 前缀匹配
+                for key in [action_name, f"auto-{action_name}"]:
+                    if key in action_mappings:
+                        action_type = action_mappings[key].get("type")
+                        if action_type:
+                            # 转换为字符串格式
+                            if hasattr(action_type, "__module__") and hasattr(action_type, "__name__"):
+                                return f"{action_type.__module__}.{action_type.__name__}"
+                            return str(action_type)
+
+        # 方法2: 从lab_registry获取
+        from unilabos.registry.registry import lab_registry
+
+        host_node = HostNode.get_instance(0)
+        if host_node and lab_registry:
+            devices_config = host_node.devices_config
+            device_class = None
+
+            for tree in devices_config.trees:
+                node = tree.root_node
+                if node.res_content.id == device_id:
+                    device_class = node.res_content.klass
+                    break
+
+            if device_class and device_class in lab_registry.device_type_registry:
+                device_type_info = lab_registry.device_type_registry[device_class]
+                class_info = device_type_info.get("class", {})
+                action_mappings = class_info.get("action_value_mappings", {})
+
+                for key in [action_name, f"auto-{action_name}"]:
+                    if key in action_mappings:
+                        action_type = action_mappings[key].get("type")
+                        if action_type:
+                            if hasattr(action_type, "__module__") and hasattr(action_type, "__name__"):
+                                return f"{action_type.__module__}.{action_type.__name__}"
+                            return str(action_type)
+
+    except Exception as e:
+        logger.warning(f"[Controller] Failed to get action type for {device_id}/{action_name}: {str(e)}")
+
+    return None
+
+
+def job_add(req: JobAddReq) -> JobData:
+    """添加任务（检查设备是否繁忙，繁忙则返回失败）
+
+    Args:
+        req: 任务添加请求
+
+    Returns:
+        JobData: 任务数据（包含状态）
+    """
+    # 服务端自动生成 job_id 和 task_id
+    job_id = str(uuid.uuid4())
+    task_id = str(uuid.uuid4())
+
+    # 服务端自动生成 server_info
+    server_info = {"send_timestamp": time.time()}
+
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        logger.error(f"[Controller] Host node not initialized for job: {job_id[:8]}")
+        return JobData(jobId=job_id, status=6)  # 6 = ABORTED
+
+    # 解析动作信息
+    action_name = req.data.get("action", req.action) if req.data else req.action
+    action_args = req.data.get("action_kwargs") or req.data.get("action_args") if req.data else req.action_args
+
+    if action_args is None:
+        action_args = req.action_args or {}
+    elif isinstance(action_args, dict) and "command" in action_args:
+        action_args = action_args["command"]
+
+    # 自动获取 action_type
+    action_type = _get_action_type(req.device_id, action_name)
+    if action_type is None:
+        logger.error(f"[Controller] Action type not found for {req.device_id}/{action_name}")
+        return JobData(jobId=job_id, status=6)  # ABORTED
+
+    # 检查设备动作是否繁忙
+    is_busy, current_job_id = check_device_action_busy(req.device_id, action_name)
+
+    if is_busy:
+        logger.warning(
+            f"[Controller] Device action busy: {req.device_id}/{action_name}, "
+            f"current job: {current_job_id[:8] if current_job_id else 'unknown'}"
+        )
+        # 返回失败状态，status=6 表示 ABORTED
+        return JobData(jobId=job_id, status=6)
+
+    # 设备空闲，提交任务执行
+    try:
+        from unilabos.app.ws_client import QueueItem
+
+        device_action_key = f"/devices/{req.device_id}/{action_name}"
+        queue_item = QueueItem(
+            task_type="job_call_back_status",
+            device_id=req.device_id,
+            action_name=action_name,
+            task_id=task_id,
+            job_id=job_id,
+            device_action_key=device_action_key,
+        )
+
+        host_node.send_goal(
+            queue_item,
+            action_type=action_type,
+            action_kwargs=action_args,
+            server_info=server_info,
+        )
+
+        logger.info(f"[Controller] Job submitted: {job_id[:8]} -> {req.device_id}/{action_name}")
+        # 返回已接受状态，status=1 表示 ACCEPTED
+        return JobData(jobId=job_id, status=1)
+
+    except ValueError as e:
+        # ActionClient not found 等错误
+        logger.error(f"[Controller] Action not available: {str(e)}")
+        return JobData(jobId=job_id, status=6)  # ABORTED
+
+    except Exception as e:
+        logger.error(f"[Controller] Error submitting job: {str(e)}")
+        traceback.print_exc()
+        return JobData(jobId=job_id, status=6)  # ABORTED
+
+
+def get_online_devices() -> Tuple[bool, Dict[str, Any]]:
+    """获取在线设备列表
+
+    Returns:
+        Tuple[bool, Dict]: (是否成功, 在线设备信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, {"error": "Host node not initialized"}
+
+    try:
+        from unilabos.ros.nodes.base_device_node import registered_devices
+
+        online_devices = {}
+        for device_key in host_node._online_devices:
+            # device_key 格式: "namespace/device_id"
+            parts = device_key.split("/")
+            if len(parts) >= 2:
+                device_id = parts[-1]
+            else:
+                device_id = device_key
+
+            # 获取设备详细信息
+            device_info = registered_devices.get(device_id, {})
+            machine_name = host_node.device_machine_names.get(device_id, "未知")
+
+            online_devices[device_id] = {
+                "device_key": device_key,
+                "namespace": host_node.devices_names.get(device_id, ""),
+                "machine_name": machine_name,
+                "uuid": device_info.get("uuid", "") if device_info else "",
+                "node_name": device_info.get("node_name", "") if device_info else "",
+            }
+
+        return True, {
+            "online_devices": online_devices,
+            "total_count": len(online_devices),
+            "timestamp": time.time(),
+        }
+
+    except Exception as e:
+        logger.error(f"[Controller] Error getting online devices: {str(e)}")
+        traceback.print_exc()
+        return False, {"error": str(e)}
+
+
+def get_device_actions(device_id: str) -> Tuple[bool, Dict[str, Any]]:
+    """获取设备可用的动作列表
+
+    Args:
+        device_id: 设备ID
+
+    Returns:
+        Tuple[bool, Dict]: (是否成功, 动作列表信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, {"error": "Host node not initialized"}
+
+    try:
+        from unilabos.ros.nodes.base_device_node import registered_devices
+        from unilabos.app.web.utils.action_utils import get_action_info
+
+        # 检查设备是否已注册
+        if device_id not in registered_devices:
+            return False, {"error": f"Device not found: {device_id}"}
+
+        device_info = registered_devices[device_id]
+        actions = device_info.get("actions", {})
+
+        actions_list = {}
+        for action_name, action_server in actions.items():
+            try:
+                action_info = get_action_info(action_server, action_name)
+                # 检查动作是否繁忙
+                is_busy, current_job = check_device_action_busy(device_id, action_name)
+                actions_list[action_name] = {
+                    **action_info,
+                    "is_busy": is_busy,
+                    "current_job_id": current_job[:8] if current_job else None,
+                }
+            except Exception as e:
+                logger.warning(f"[Controller] Error getting action info for {action_name}: {str(e)}")
+                actions_list[action_name] = {
+                    "type_name": "unknown",
+                    "action_path": f"/devices/{device_id}/{action_name}",
+                    "is_busy": False,
+                    "error": str(e),
+                }
+
+        return True, {
+            "device_id": device_id,
+            "actions": actions_list,
+            "action_count": len(actions_list),
+        }
+
+    except Exception as e:
+        logger.error(f"[Controller] Error getting device actions: {str(e)}")
+        traceback.print_exc()
+        return False, {"error": str(e)}
+
+
+def get_action_schema(device_id: str, action_name: str) -> Tuple[bool, Dict[str, Any]]:
+    """获取动作的Schema详情
+
+    Args:
+        device_id: 设备ID
+        action_name: 动作名称
+
+    Returns:
+        Tuple[bool, Dict]: (是否成功, Schema信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, {"error": "Host node not initialized"}
+
+    try:
+        from unilabos.registry.registry import lab_registry
+        from unilabos.ros.nodes.base_device_node import registered_devices
+
+        result = {
+            "device_id": device_id,
+            "action_name": action_name,
+            "schema": None,
+            "goal_default": None,
+            "action_type": None,
+            "is_busy": False,
+        }
+
+        # 检查动作是否繁忙
+        is_busy, current_job = check_device_action_busy(device_id, action_name)
+        result["is_busy"] = is_busy
+        result["current_job_id"] = current_job[:8] if current_job else None
+
+        # 方法1: 从 registered_devices 获取运行时信息
+        if device_id in registered_devices:
+            device_info = registered_devices[device_id]
+            base_node = device_info.get("base_node_instance")
+
+            if base_node and hasattr(base_node, "_action_value_mappings"):
+                action_mappings = base_node._action_value_mappings
+                if action_name in action_mappings:
+                    mapping = action_mappings[action_name]
+                    result["schema"] = mapping.get("schema")
+                    result["goal_default"] = mapping.get("goal_default")
+                    result["action_type"] = str(mapping.get("type", ""))
+
+        # 方法2: 从 lab_registry 获取注册表信息（如果运行时没有）
+        if result["schema"] is None and lab_registry:
+            # 尝试查找设备类型
+            devices_config = host_node.devices_config
+            device_class = None
+
+            # 从配置中获取设备类型
+            for tree in devices_config.trees:
+                node = tree.root_node
+                if node.res_content.id == device_id:
+                    device_class = node.res_content.klass
+                    break
+
+            if device_class and device_class in lab_registry.device_type_registry:
+                device_type_info = lab_registry.device_type_registry[device_class]
+                class_info = device_type_info.get("class", {})
+                action_mappings = class_info.get("action_value_mappings", {})
+
+                # 尝试直接匹配或 auto- 前缀匹配
+                for key in [action_name, f"auto-{action_name}"]:
+                    if key in action_mappings:
+                        mapping = action_mappings[key]
+                        result["schema"] = mapping.get("schema")
+                        result["goal_default"] = mapping.get("goal_default")
+                        result["action_type"] = str(mapping.get("type", ""))
+                        result["handles"] = mapping.get("handles", {})
+                        result["placeholder_keys"] = mapping.get("placeholder_keys", {})
+                        break
+
+        if result["schema"] is None:
+            return False, {"error": f"Action schema not found: {device_id}/{action_name}"}
+
+        return True, result
+
+    except Exception as e:
+        logger.error(f"[Controller] Error getting action schema: {str(e)}")
+        traceback.print_exc()
+        return False, {"error": str(e)}
+
+
+def get_all_available_actions() -> Tuple[bool, Dict[str, Any]]:
+    """获取所有设备的可用动作
+
+    Returns:
+        Tuple[bool, Dict]: (是否成功, 所有设备的动作信息)
+    """
+    host_node = HostNode.get_instance(0)
+    if host_node is None:
+        return False, {"error": "Host node not initialized"}
+
+    try:
+        from unilabos.ros.nodes.base_device_node import registered_devices
+        from unilabos.app.web.utils.action_utils import get_action_info
+
+        all_actions = {}
+        total_action_count = 0
+
+        for device_id, device_info in registered_devices.items():
+            actions = device_info.get("actions", {})
+            device_actions = {}
+
+            for action_name, action_server in actions.items():
+                try:
+                    action_info = get_action_info(action_server, action_name)
+                    is_busy, current_job = check_device_action_busy(device_id, action_name)
+                    device_actions[action_name] = {
+                        "type_name": action_info.get("type_name", ""),
+                        "action_path": action_info.get("action_path", ""),
+                        "is_busy": is_busy,
+                        "current_job_id": current_job[:8] if current_job else None,
+                    }
+                    total_action_count += 1
+                except Exception as e:
+                    logger.warning(f"[Controller] Error processing action {device_id}/{action_name}: {str(e)}")
+
+            if device_actions:
+                all_actions[device_id] = {
+                    "actions": device_actions,
+                    "action_count": len(device_actions),
+                    "machine_name": host_node.device_machine_names.get(device_id, "未知"),
+                }
+
+        return True, {
+            "devices": all_actions,
+            "device_count": len(all_actions),
+            "total_action_count": total_action_count,
+            "timestamp": time.time(),
+        }
+
+    except Exception as e:
+        logger.error(f"[Controller] Error getting all available actions: {str(e)}")
+        traceback.print_exc()
+        return False, {"error": str(e)}

unilabos/app/ws_client.py

@@ -261,29 +261,28 @@ class DeviceActionManager:
             device_key = job_info.device_action_key
 
             # 如果是正在执行的任务
-            if (
-                device_key in self.active_jobs and self.active_jobs[device_key].job_id == job_id
-            ):  # 后面需要和cancel_goal进行联动，而不是在这里进行处理，现在默认等待这个job结束
-                # del self.active_jobs[device_key]
-                # job_info.status = JobStatus.ENDED
-                # # 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}")
+            if device_key in self.active_jobs and self.active_jobs[device_key].job_id == job_id:
+                # 清理active job状态
+                del self.active_jobs[device_key]
+                job_info.status = JobStatus.ENDED
+                # 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}")
 
-                # # 启动下一个任务
-                # if device_key in self.device_queues and self.device_queues[device_key]:
-                #     next_job = self.device_queues[device_key].pop(0)
-                #     # 将下一个job设置为READY状态并放入active_jobs
-                #     next_job.status = JobStatus.READY
-                #     next_job.update_timestamp()
-                #     next_job.set_ready_timeout(10)
-                #     self.active_jobs[device_key] = next_job
-                #     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")
-                #     return True
-                pass
+                # 启动下一个任务
+                if device_key in self.device_queues and self.device_queues[device_key]:
+                    next_job = self.device_queues[device_key].pop(0)
+                    # 将下一个job设置为READY状态并放入active_jobs
+                    next_job.status = JobStatus.READY
+                    next_job.update_timestamp()
+                    next_job.set_ready_timeout(10)
+                    self.active_jobs[device_key] = next_job
+                    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")
+                return True
 
             # 如果是排队中的任务
             elif device_key in self.device_queues:
@@ -360,6 +359,7 @@ class MessageProcessor:
         self.device_manager = device_manager
         self.queue_processor = None  # 延迟设置
         self.websocket_client = None  # 延迟设置
+        self.session_id = ""
 
         # WebSocket连接
         self.websocket = None
@@ -389,7 +389,7 @@ class MessageProcessor:
         self.is_running = True
         self.thread = threading.Thread(target=self._run, daemon=True, name="MessageProcessor")
         self.thread.start()
-        logger.info("[MessageProcessor] Started")
+        logger.trace("[MessageProcessor] Started")
 
     def stop(self) -> None:
         """停止消息处理线程"""
@@ -428,14 +428,17 @@ class MessageProcessor:
                     ssl=ssl_context,
                     ping_interval=WSConfig.ping_interval,
                     ping_timeout=10,
-                    additional_headers={"Authorization": f"Lab {BasicConfig.auth_secret()}"},
+                    additional_headers={
+                        "Authorization": f"Lab {BasicConfig.auth_secret()}",
+                        "EdgeSession": f"{self.session_id}",
+                    },
                     logger=ws_logger,
                 ) as websocket:
                     self.websocket = websocket
                     self.connected = True
                     self.reconnect_count = 0
 
-                    logger.info(f"[MessageProcessor] Connected to {self.websocket_url}")
+                    logger.trace(f"[MessageProcessor] Connected to {self.websocket_url}")
 
                     # 启动发送协程
                     send_task = asyncio.create_task(self._send_handler())
@@ -500,7 +503,7 @@ class MessageProcessor:
 
     async def _send_handler(self):
         """处理发送队列中的消息"""
-        logger.debug("[MessageProcessor] Send handler started")
+        logger.trace("[MessageProcessor] Send handler started")
 
         try:
             while self.connected and self.websocket:
@@ -573,6 +576,9 @@ class MessageProcessor:
                 await self._handle_resource_tree_update(message_data, "update")
             elif message_type == "remove_material":
                 await self._handle_resource_tree_update(message_data, "remove")
+            elif message_type == "session_id":
+                self.session_id = message_data.get("session_id")
+                logger.info(f"[MessageProcessor] Session ID: {self.session_id}")
             else:
                 logger.debug(f"[MessageProcessor] Unknown message type: {message_type}")
 
@@ -741,31 +747,51 @@ class MessageProcessor:
                 job_info.action_name if job_info else "",
             )
 
-            # 按job_id取消单个job
+            # 先通知HostNode取消ROS2 action（如果存在）
+            host_node = HostNode.get_instance(0)
+            ros_cancel_success = False
+            if host_node:
+                ros_cancel_success = host_node.cancel_goal(job_id)
+                if ros_cancel_success:
+                    logger.info(f"[MessageProcessor] ROS2 cancel request sent for job {job_log}")
+                else:
+                    logger.debug(
+                        f"[MessageProcessor] Job {job_log} not in ROS2 goals " "(may be queued or already finished)"
+                    )
+
+            # 按job_id取消单个job（清理状态机）
             success = self.device_manager.cancel_job(job_id)
             if success:
-                # 通知HostNode取消
-                host_node = HostNode.get_instance(0)
-                if host_node:
-                    host_node.cancel_goal(job_id)
-                logger.info(f"[MessageProcessor] Job {job_log} cancelled")
+                logger.info(f"[MessageProcessor] Job {job_log} cancelled from queue/active list")
 
                 # 通知QueueProcessor有队列更新
                 if self.queue_processor:
                     self.queue_processor.notify_queue_update()
             else:
-                logger.warning(f"[MessageProcessor] Failed to cancel job {job_log}")
+                logger.warning(f"[MessageProcessor] Failed to cancel job {job_log} from queue")
 
         elif task_id:
-            # 按task_id取消所有相关job
+            # 先通知HostNode取消所有ROS2 actions
+            # 需要先获取所有相关job_ids
+            jobs_to_cancel = []
+            with self.device_manager.lock:
+                jobs_to_cancel = [
+                    job_info for job_info in self.device_manager.all_jobs.values() if job_info.task_id == task_id
+                ]
+
+            host_node = HostNode.get_instance(0)
+            if host_node and jobs_to_cancel:
+                ros_cancelled_count = 0
+                for job_info in jobs_to_cancel:
+                    if host_node.cancel_goal(job_info.job_id):
+                        ros_cancelled_count += 1
+                logger.info(
+                    f"[MessageProcessor] Sent ROS2 cancel for " f"{ros_cancelled_count}/{len(jobs_to_cancel)} jobs"
+                )
+
+            # 按task_id取消所有相关job（清理状态机）
             cancelled_job_ids = self.device_manager.cancel_jobs_by_task_id(task_id)
             if cancelled_job_ids:
-                # 通知HostNode取消所有job
-                host_node = HostNode.get_instance(0)
-                if host_node:
-                    for cancelled_job_id in cancelled_job_ids:
-                        host_node.cancel_goal(cancelled_job_id)
-
                 logger.info(f"[MessageProcessor] Cancelled {len(cancelled_job_ids)} jobs for task_id: {task_id}")
 
                 # 通知QueueProcessor有队列更新
@@ -913,7 +939,7 @@ class QueueProcessor:
         # 事件通知机制
         self.queue_update_event = threading.Event()
 
-        logger.info("[QueueProcessor] Initialized")
+        logger.trace("[QueueProcessor] Initialized")
 
     def set_websocket_client(self, websocket_client: "WebSocketClient"):
         """设置WebSocket客户端引用"""
@@ -928,7 +954,7 @@ class QueueProcessor:
         self.is_running = True
         self.thread = threading.Thread(target=self._run, daemon=True, name="QueueProcessor")
         self.thread.start()
-        logger.info("[QueueProcessor] Started")
+        logger.trace("[QueueProcessor] Started")
 
     def stop(self) -> None:
         """停止队列处理线程"""
@@ -939,7 +965,7 @@ class QueueProcessor:
 
     def _run(self):
         """运行队列处理主循环"""
-        logger.debug("[QueueProcessor] Queue processor started")
+        logger.trace("[QueueProcessor] Queue processor started")
 
         while self.is_running:
             try:
@@ -1056,11 +1082,19 @@ class QueueProcessor:
         """处理任务完成"""
         # 获取job信息用于日志
         job_info = self.device_manager.get_job_info(job_id)
+
+        # 如果job不存在，说明可能已被手动取消
+        if not job_info:
+            logger.debug(
+                f"[QueueProcessor] Job {job_id[:8]} not found in manager " "(may have been cancelled manually)"
+            )
+            return
+
         job_log = format_job_log(
             job_id,
-            job_info.task_id if job_info else "",
-            job_info.device_id if job_info else "",
-            job_info.action_name if job_info else "",
+            job_info.task_id,
+            job_info.device_id,
+            job_info.action_name,
         )
 
         logger.info(f"[QueueProcessor] Job {job_log} completed with status: {status}")
@@ -1141,7 +1175,6 @@ class WebSocketClient(BaseCommunicationClient):
         else:
             url = f"{scheme}://{parsed.netloc}/api/v1/ws/schedule"
 
-        logger.debug(f"[WebSocketClient] URL: {url}")
         return url
 
     def start(self) -> None:
@@ -1154,13 +1187,11 @@ class WebSocketClient(BaseCommunicationClient):
             logger.error("[WebSocketClient] WebSocket URL not configured")
             return
 
-        logger.info(f"[WebSocketClient] Starting connection to {self.websocket_url}")
-
         # 启动两个核心线程
         self.message_processor.start()
         self.queue_processor.start()
 
-        logger.info("[WebSocketClient] All threads started")
+        logger.trace("[WebSocketClient] All threads started")
 
     def stop(self) -> None:
         """停止WebSocket客户端"""
@@ -1169,6 +1200,18 @@ class WebSocketClient(BaseCommunicationClient):
 
         logger.info("[WebSocketClient] Stopping connection")
 
+        # 发送 normal_exit 消息
+        if self.is_connected():
+            try:
+                session_id = self.message_processor.session_id
+                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)
+            except Exception as e:
+                logger.warning(f"[WebSocketClient] Failed to send normal_exit message: {str(e)}")
+
         # 停止两个核心线程
         self.message_processor.stop()
         self.queue_processor.stop()
@@ -1268,3 +1311,19 @@ class WebSocketClient(BaseCommunicationClient):
             logger.info(f"[WebSocketClient] Job {job_log} cancelled successfully")
         else:
             logger.warning(f"[WebSocketClient] Failed to cancel job {job_log}")
+
+    def publish_host_ready(self) -> None:
+        """发布host_node ready信号"""
+        if self.is_disabled or not self.is_connected():
+            logger.debug("[WebSocketClient] Not connected, cannot publish host ready signal")
+            return
+
+        message = {
+            "action": "host_node_ready",
+            "data": {
+                "status": "ready",
+                "timestamp": time.time(),
+            },
+        }
+        self.message_processor.send_message(message)
+        logger.info("[WebSocketClient] Host node ready signal published")