fix(runtime): recover awake ownership and batch model failures

apps/admin_console/services/automation_service.py

@@ -15,6 +15,7 @@ from artemis.runtime.task_limits import task_timeout
 
 logger = logging.getLogger(__name__)
 TERMINAL = {"completed", "failed", "cancelled", "skipped", "interrupted"}
+MODEL_PAUSE_REASON = "模型请求已暂停，请先恢复模型连接再继续批次"
 background_tasks: set[asyncio.Task] = set()
 
 
@@ -123,7 +124,9 @@ def recover_batches():
             if any(str(job["session_id"]) in live_sessions for job in store.jobs(batch["id"])):
                 continue
             batch.update(
-                status="paused", reason="服务已重启；请检查中断任务，点击继续执行未开始任务"
+                status="paused",
+                reason="服务已重启；请检查中断任务，点击继续执行未开始任务",
+                pause_source="recovery",
             )
             for job in store.jobs(batch["id"]):
                 if job["status"] in {"running", "queued", "finalizing", "task_paused", "resuming"}:
@@ -164,9 +167,29 @@ async def on_terminal(item: dict, status: str):
             }
         ):
             job["status"] = "failed"
-            job["error"] = job.get("error") or "任务执行结束，但业务检查未通过"
+            job["error"] = (
+                job.get("error")
+                or report.get("error")
+                or (report.get("test_result") or {}).get("reason")
+                or "任务未完成或验证未通过，请查看报告中的具体原因"
+            )
         elif job["status"] == "failed" and report.get("error") and not job.get("error"):
             job["error"] = report["error"]
+        if job["status"] == "failed" and report["outcome"].get("code") == "initialization_failed":
+            job["failure_code"] = "initialization_failed"
+            batch = store.get("batch", job.get("batch_id")) if job.get("batch_id") else None
+            if (
+                batch
+                and (batch["status"] == "running" or batch.get("pause_source") == "model")
+                and any(j["status"] == "pending" for j in store.jobs(batch["id"]))
+            ):
+                batch.update(
+                    status="paused",
+                    pause_source="initialization",
+                    reason="任务初始化失败；请处理环境问题后继续剩余用例："
+                    + (job.get("error") or "请查看任务报告"),
+                )
+                store.put("batch", batch["id"], batch)
         # Persist terminal classification before export, but the coordinator waits for finalization.
         store.save_job({**job, "status": "finalizing", "terminal_status": job["status"]})
         await asyncio.to_thread(export_session, sid, job["formats"])
@@ -217,10 +240,18 @@ async def tick_batches():
         if batch["status"] not in {"running", "paused"}:
             continue
         jobs = store.jobs(batch["id"])
+        if (
+            batch["status"] == "paused"
+            and batch.get("pause_source") == "model"
+            and not state.is_paused
+        ):
+            batch.update(status="running", reason="")
+            batch.pop("pause_source", None)
+            store.put("batch", batch["id"], batch)
         active = [j for j in jobs if j["status"] in {"running", "queued", "finalizing"}]
         if active:
-            if state.is_paused:
-                batch.update(status="paused", reason="模型请求已暂停，请先恢复模型连接再继续批次")
+            if state.is_paused and batch["status"] == "running":
+                batch.update(status="paused", reason=MODEL_PAUSE_REASON, pause_source="model")
                 store.put("batch", batch["id"], batch)
             for job in active:
                 # The queue records started_at at submission, then replaces it
@@ -284,7 +315,7 @@ async def tick_batches():
             store.put("batch", batch["id"], batch)
             continue
         if state.is_paused:
-            batch.update(status="paused", reason="模型请求已暂停，请先恢复模型连接再继续批次")
+            batch.update(status="paused", reason=MODEL_PAUSE_REASON, pause_source="model")
             store.put("batch", batch["id"], batch)
             continue
         job = pending[0]
@@ -438,11 +469,14 @@ def batch_action(batch_id: str, action: str) -> dict:
     if action == "pause":
         if batch["status"] not in {"running", "paused"}:
             raise ValueError("只能暂停正在执行的批次")
-        batch.update(status="paused", reason="用户暂停；当前任务继续，后续任务等待")
+        batch.update(
+            status="paused", reason="用户暂停；当前任务继续，后续任务等待", pause_source="user"
+        )
     elif action == "resume":
         if batch["status"] not in {"draft", "paused"}:
             raise ValueError("只能开始草稿或继续已暂停批次")
         batch.update(status="running", reason="")
+        batch.pop("pause_source", None)
     elif action == "retry_failed":
         if batch["status"] == "running":
             raise ValueError("请先暂停批次")