Dev backward (#228)

* Workbench example, adjust log level, and ci check (#220) * TestLatency Return Value Example & gitignore update * Adjust log level & Add workbench virtual example & Add not action decorator & Add check_mode & * Add CI Check * CI Check Fix 1 * CI Check Fix 2 * CI Check Fix 3 * CI Check Fix 4 * CI Check Fix 5 * Upgrade to py 3.11.14; ros 0.7; unilabos 0.10.16 * Update to ROS2 Humble 0.7 * Fix Build 1 * Fix Build 2 * Fix Build 3 * Fix Build 4 * Fix Build 5 * Fix Build 6 * Fix Build 7 * ci(deps): bump actions/configure-pages from 4 to 5 (#222) Bumps [actions/configure-pages](https://github.com/actions/configure-pages) from 4 to 5. - [Release notes](https://github.com/actions/configure-pages/releases) - [Commits](https://github.com/actions/configure-pages/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/configure-pages dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * ci(deps): bump actions/upload-artifact from 4 to 6 (#224) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 4 to 6. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v4...v6) --- updated-dependencies: - dependency-name: actions/upload-artifact dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * ci(deps): bump actions/upload-pages-artifact from 3 to 4 (#225) Bumps [actions/upload-pages-artifact](https://github.com/actions/upload-pages-artifact) from 3 to 4. - [Release notes](https://github.com/actions/upload-pages-artifact/releases) - [Commits](https://github.com/actions/upload-pages-artifact/compare/v3...v4) --- updated-dependencies: - dependency-name: actions/upload-pages-artifact dependency-version: '4' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * ci(deps): bump actions/checkout from 4 to 6 (#223) Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v4...v6) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Fix Build 8 * Fix Build 9 * Fix Build 10 * Fix Build 11 * Fix Build 12 * Fix Build 13 * v0.10.17 (cherry picked from commit 176de521b4) * CI Check use production mode * Fix OT2 & ReAdd Virtual Devices * add msg goal * transfer liquid handles * gather query * add unilabos_class * Support root node change pos * save class name when deserialize & protocol execute test * fix upload workflow json * workflow upload & set liquid fix & add set liquid with plate * speed up registry load --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: hanhua@dp.tech <2509856570@qq.com>
2026-02-06 06:25:06 +00:00 · 2026-02-02 23:57:13 +08:00
parent c4a3be1498
commit e30c01d54e
65 changed files with 4603 additions and 1655 deletions
--- a/unilabos/app/main.py
+++ b/unilabos/app/main.py
@@ -7,7 +7,6 @@ import sys
 import threading
 import time
 from typing import Dict, Any, List
-
 import networkx as nx
 import yaml

@@ -17,9 +16,9 @@ unilabos_dir = os.path.dirname(os.path.dirname(current_dir))
 if unilabos_dir not in sys.path:
    sys.path.append(unilabos_dir)

+from unilabos.app.utils import cleanup_for_restart
 from unilabos.utils.banner_print import print_status, print_unilab_banner
 from unilabos.config.config import load_config, BasicConfig, HTTPConfig
-from unilabos.app.utils import cleanup_for_restart

 # Global restart flags (used by ws_client and web/server)
 _restart_requested: bool = False
@@ -161,6 +160,12 @@ def parse_args():
        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(
        "--no_update_feedback",
        action="store_true",
@@ -211,7 +216,10 @@ def main():
    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):
+    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

        if not check_environment(auto_install=True):
@@ -222,7 +230,21 @@ def main():

    # 加载配置文件，优先加载config，然后从env读取
    config_path = args_dict.get("config")
-    if os.getcwd().endswith("unilabos_data"):
+
+    if check_mode:
+        args_dict["working_dir"] = os.path.abspath(os.getcwd())
+    # 当 skip_env_check 时，默认使用当前目录作为 working_dir
+    if skip_env_check and not args_dict.get("working_dir") and not config_path:
+        working_dir = os.path.abspath(os.getcwd())
+        print_status(f"跳过环境检查模式：使用当前目录作为工作目录 {working_dir}", "info")
+        # 检查当前目录是否有 local_config.py
+        local_config_in_cwd = os.path.join(working_dir, "local_config.py")
+        if os.path.exists(local_config_in_cwd):
+            config_path = local_config_in_cwd
+            print_status(f"发现本地配置文件: {config_path}", "info")
+        else:
+            print_status(f"未指定config路径，可通过 --config 传入 local_config.py 文件路径", "info")
+    elif os.getcwd().endswith("unilabos_data"):
        working_dir = os.path.abspath(os.getcwd())
    else:
        working_dir = os.path.abspath(os.path.join(os.getcwd(), "unilabos_data"))
@@ -241,7 +263,7 @@ def main():
        working_dir = os.path.dirname(config_path)
    elif os.path.exists(working_dir) and os.path.exists(os.path.join(working_dir, "local_config.py")):
        config_path = os.path.join(working_dir, "local_config.py")
-    elif not config_path and (
+    elif not skip_env_check and not config_path and (
        not os.path.exists(working_dir) or not os.path.exists(os.path.join(working_dir, "local_config.py"))
    ):
        print_status(f"未指定config路径，可通过 --config 传入 local_config.py 文件路径", "info")
@@ -255,9 +277,11 @@ def main():
            print_status(f"已创建 local_config.py 路径： {config_path}", "info")
        else:
            os._exit(1)
-    # 加载配置文件
+
+    # 加载配置文件 (check_mode 跳过)
    print_status(f"当前工作目录为 {working_dir}", "info")
-    load_config_from_file(config_path)
+    if not check_mode:
+        load_config_from_file(config_path)

    # 根据配置重新设置日志级别
    from unilabos.utils.log import configure_logger, logger
@@ -313,6 +337,7 @@ def main():
    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,
@@ -331,10 +356,14 @@ def main():
    # 显示启动横幅
    print_unilab_banner(args_dict)

-    # 注册表
-    lab_registry = build_registry(
-        args_dict["registry_path"], args_dict.get("complete_registry", False), BasicConfig.upload_registry
-    )
+    # 注册表 - check_mode 时强制启用 complete_registry
+    complete_registry = args_dict.get("complete_registry", False) or check_mode
+    lab_registry = build_registry(args_dict["registry_path"], complete_registry, BasicConfig.upload_registry)
+
+    # Check mode: complete_registry 完成后直接退出，git diff 检测由 CI workflow 执行
+    if check_mode:
+        print_status("Check mode: complete_registry 完成，退出", "info")
+        os._exit(0)

    if BasicConfig.upload_registry:
        # 设备注册到服务端 - 需要 ak 和 sk
--- a/unilabos/app/utils.py
+++ b/unilabos/app/utils.py
@@ -4,8 +4,40 @@ UniLabOS 应用工具函数
 提供清理、重启等工具函数
 """

-import gc
+import glob
 import os
+import shutil
+import sys
+
+
+def patch_rclpy_dll_windows():
+    """在 Windows + conda 环境下为 rclpy 打 DLL 加载补丁"""
+    if sys.platform != "win32" or not os.environ.get("CONDA_PREFIX"):
+        return
+    try:
+        import rclpy
+
+        return
+    except ImportError as e:
+        if not str(e).startswith("DLL load failed"):
+            return
+    cp = os.environ["CONDA_PREFIX"]
+    impl = os.path.join(cp, "Lib", "site-packages", "rclpy", "impl", "implementation_singleton.py")
+    pyd = glob.glob(os.path.join(cp, "Lib", "site-packages", "rclpy", "_rclpy_pybind11*.pyd"))
+    if not os.path.exists(impl) or not pyd:
+        return
+    with open(impl, "r", encoding="utf-8") as f:
+        content = f.read()
+    lib_bin = os.path.join(cp, "Library", "bin").replace("\\", "/")
+    patch = f'# UniLabOS DLL Patch\nimport os,ctypes\nos.add_dll_directory("{lib_bin}") if hasattr(os,"add_dll_directory") else None\ntry: ctypes.CDLL("{pyd[0].replace(chr(92),"/")}")\nexcept: pass\n# End Patch\n'
+    shutil.copy2(impl, impl + ".bak")
+    with open(impl, "w", encoding="utf-8") as f:
+        f.write(patch + content)
+
+
+patch_rclpy_dll_windows()
+
+import gc
 import threading
 import time

--- a/unilabos/app/web/client.py
+++ b/unilabos/app/web/client.py
@@ -359,9 +359,7 @@ class HTTPClient:
        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,
--- a/unilabos/app/web/controller.py
+++ b/unilabos/app/web/controller.py
@@ -58,14 +58,14 @@ class JobResultStore:
                feedback=feedback or {},
                timestamp=time.time(),
            )
-            logger.debug(f"[JobResultStore] Stored result for job {job_id[:8]}, status={status}")
+            logger.trace(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]}")
+                logger.trace(f"[JobResultStore] Retrieved and removed result for job {job_id[:8]}")
            return result

    def get_result(self, job_id: str) -> Optional[JobResult]:
--- a/unilabos/app/ws_client.py
+++ b/unilabos/app/ws_client.py
@@ -23,7 +23,7 @@ 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.ros.nodes.presets.host_node import HostNode
@@ -154,7 +154,7 @@ 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:
@@ -210,8 +210,9 @@ 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}")
@@ -227,7 +228,7 @@ 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
@@ -268,7 +269,7 @@ 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]:
@@ -281,7 +282,7 @@ 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
@@ -295,7 +296,7 @@ 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)
@@ -494,8 +495,12 @@ class MessageProcessor:
                        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')}")
+                            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:
@@ -565,7 +570,7 @@ 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":
@@ -637,13 +642,13 @@ 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:
@@ -847,9 +852,7 @@ 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")
@@ -863,7 +866,9 @@ 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():
@@ -911,13 +916,13 @@ class MessageProcessor:

        # 发送确认消息
        if self.websocket_client:
-            await self.websocket_client.send_message({
-                "action": "restart_acknowledged",
-                "data": {"reason": reason, "delay": delay}
-            })
+            await self.websocket_client.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

@@ -927,10 +932,12 @@ class MessageProcessor:
        # 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:
@@ -1128,7 +1135,7 @@ 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}")

@@ -1151,7 +1158,7 @@ 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)
@@ -1171,8 +1178,8 @@ 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()
@@ -1314,7 +1321,7 @@ 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)
@@ -1381,7 +1388,9 @@ class WebSocketClient(BaseCommunicationClient):
            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
@@ -1395,14 +1404,16 @@ class WebSocketClient(BaseCommunicationClient):
                                "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: