update workbench example

update aksk desc

print res query logs

Fix skills exec error with action type

Update Skills

Update Skills addr

Change uni-lab. to leap-lab.
Support unit in pylabrobot

Support async func.

change to leap-lab backend. Support feedback interval. Reduce cocurrent lags.

fix create_resource_with_slot

update unilabos_formulation & batch-submit-exp

scale multi exec thread up to 48

update handle creation api

fit cocurrent gap

add running status debounce

allow non @topic_config support

update skill

add placeholder keys

always free

提交实验技能

disable samples

correct sample demo ret value

新增试剂reagent

update registry

新增manual_confirm

add workstation creation skill

add virtual_sample_demo 样品追踪测试设备

add external devices param
fix registry upload missing type

fast registry load

minor fix on skill & registry

stripe ros2 schema desc
add create-device-skill

new registry system backwards to yaml

remove not exist resource

new registry sys
exp. support with add device

correct raise create resource error

ret info fix revert

ret info fix

fix prcxi check

add create_resource schema

re signal host ready event

add websocket connection timeout and improve reconnection logic

add open_timeout parameter to websocket connection
add TimeoutError and InvalidStatus exception handling
implement exponential backoff for reconnection attempts
simplify reconnection logic flow

unilabos/app/ws_client.py

@@ -754,6 +754,32 @@ class MessageProcessor:
             req = JobAddReq(**data)
 
             job_log = format_job_log(req.job_id, req.task_id, req.device_id, req.action)
+
+            # 服务端对always_free动作可能跳过query_action_state直接发job_start，
+            # 此时job尚未注册，需要自动补注册
+            existing_job = self.device_manager.get_job_info(req.job_id)
+            if not existing_job:
+                action_name = req.action
+                device_action_key = f"/devices/{req.device_id}/{action_name}"
+                action_always_free = self._check_action_always_free(req.device_id, action_name)
+
+                if action_always_free:
+                    job_info = JobInfo(
+                        job_id=req.job_id,
+                        task_id=req.task_id,
+                        device_id=req.device_id,
+                        action_name=action_name,
+                        device_action_key=device_action_key,
+                        status=JobStatus.QUEUE,
+                        start_time=time.time(),
+                        always_free=True,
+                    )
+                    self.device_manager.add_queue_request(job_info)
+                    logger.info(f"[MessageProcessor] Job {job_log} always_free, auto-registered from direct job_start")
+                else:
+                    logger.error(f"[MessageProcessor] Job {job_log} not registered (missing query_action_state)")
+                    return
+
             success = self.device_manager.start_job(req.job_id)
             if not success:
                 logger.error(f"[MessageProcessor] Failed to start job {job_log}")
@@ -1087,7 +1113,7 @@ class MessageProcessor:
                 "task_id": task_id,
                 "job_id": job_id,
                 "free": free,
-                "need_more": need_more,
+                "need_more": need_more + 1,
             },
         }
 
@@ -1227,7 +1253,7 @@ class QueueProcessor:
                     "task_id": job_info.task_id,
                     "job_id": job_info.job_id,
                     "free": False,
-                    "need_more": 10,
+                    "need_more": 10 + 1,
                 },
             }
             self.message_processor.send_message(message)
@@ -1243,7 +1269,13 @@ class QueueProcessor:
         if not queued_jobs:
             return
 
-        logger.debug(f"[QueueProcessor] Sending busy status for {len(queued_jobs)} queued jobs")
+        queue_summary = {}
+        for j in queued_jobs:
+            key = f"{j.device_id}/{j.action_name}"
+            queue_summary[key] = queue_summary.get(key, 0) + 1
+        logger.debug(
+            f"[QueueProcessor] Sending busy status for {len(queued_jobs)} queued jobs: {queue_summary}"
+        )
 
         for job_info in queued_jobs:
             # 快照可能已过期：在遍历过程中 end_job() 可能已将此 job 移至 READY，
@@ -1260,7 +1292,7 @@ class QueueProcessor:
                     "task_id": job_info.task_id,
                     "job_id": job_info.job_id,
                     "free": False,
-                    "need_more": 10,
+                    "need_more": 10 + 1,
                 },
             }
             success = self.message_processor.send_message(message)
@@ -1343,6 +1375,10 @@ class WebSocketClient(BaseCommunicationClient):
         self.message_processor = MessageProcessor(self.websocket_url, self.send_queue, self.device_manager)
         self.queue_processor = QueueProcessor(self.device_manager, self.message_processor)
 
+        # running状态debounce缓存: {job_id: (last_send_timestamp, last_feedback_data)}
+        self._job_running_last_sent: Dict[str, tuple] = {}
+        self._job_running_debounce_interval: float = 10.0  # 秒
+
         # 设置相互引用
         self.message_processor.set_queue_processor(self.queue_processor)
         self.message_processor.set_websocket_client(self)
@@ -1442,22 +1478,32 @@ class WebSocketClient(BaseCommunicationClient):
             logger.debug(f"[WebSocketClient] Not connected, cannot publish job status for job_id: {item.job_id}")
             return
 
+        job_log = format_job_log(item.job_id, item.task_id, item.device_id, item.action_name)
+
         # 拦截最终结果状态，与原版本逻辑一致
         if status in ["success", "failed"]:
+            self._job_running_last_sent.pop(item.job_id, None)
+
             host_node = HostNode.get_instance(0)
             if host_node:
-                # 从HostNode的device_action_status中移除job_id
                 try:
                     host_node._device_action_status[item.device_action_key].job_ids.pop(item.job_id, None)
                 except (KeyError, AttributeError):
                     logger.warning(f"[WebSocketClient] Failed to remove job {item.job_id} from HostNode 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)
 
-        # 发送job状态消息
+        # running状态按job_id做debounce，内容变化时仍然上报
+        if status == "running":
+            now = time.time()
+            cached = self._job_running_last_sent.get(item.job_id)
+            if cached is not None:
+                last_ts, last_data = cached
+                if now - last_ts < self._job_running_debounce_interval and last_data == feedback_data:
+                    logger.trace(f"[WebSocketClient] Job status debounced (skip): {job_log} - {status}")
+                    return
+            self._job_running_last_sent[item.job_id] = (now, feedback_data)
+
         message = {
             "action": "job_status",
             "data": {
@@ -1473,7 +1519,6 @@ class WebSocketClient(BaseCommunicationClient):
         }
         self.message_processor.send_message(message)
 
-        job_log = format_job_log(item.job_id, item.task_id, item.device_id, item.action_name)
         logger.trace(f"[WebSocketClient] Job status published: {job_log} - {status}")
 
     def send_ping(self, ping_id: str, timestamp: float) -> None: