feat: improve batch task controls and release 1.2.0

apps/admin_console/routers/automation.py

@@ -128,7 +128,7 @@ def delete_batch(batch_id: str):
     except ValueError as exc:
         raise HTTPException(400, str(exc)) from exc
     try:
-        if not store.delete_batch(key):
+        if not service.delete_batch(key):
             raise HTTPException(404, "批次不存在")
     except ValueError as exc:
         raise HTTPException(409, str(exc)) from exc
@@ -166,7 +166,8 @@ async def download_report(
     try:
         if fmt in {"screenshots", "video", "all"}:
             path = await asyncio.to_thread(report_export.export_session_media, session_id, fmt)
-            return FileResponse(path, filename=f"任务{session_id[:8]}-{fmt}.zip")
+            label = report_export.archive_case_name(report_export.session_report(session_id))
+            return FileResponse(path, filename=f"{label}-{fmt}.zip")
         paths = await asyncio.to_thread(report_export.export_session, session_id, [fmt])
         return FileResponse(paths[0], filename=f"任务报告-{session_id[:8]}.{fmt}")
     except ValueError as exc:
@@ -184,13 +185,15 @@ def history(
 ):
     # SQL filtering/pagination searches the entire persisted history, not a UI cache.
     query = """WITH history AS (
-      SELECT s.session_id, s.initial_goal, s.start_time, s.end_time,
+      SELECT s.session_id, s.initial_goal, s.start_time,
+        COALESCE(json_extract(j.payload,'$.ended_at'),s.end_time) end_time,
         COALESCE(j.status,s.status) status, COALESCE(json_extract(j.payload,'$.case.name'),s.initial_goal) name,
         COALESCE(json_extract(j.payload,'$.case.tags'),'') tags,
         COALESCE(json_extract(j.payload,'$.case.case_id'),'') case_id,
         COALESCE(json_extract(j.payload,'$.case.category'),'') category,
         COALESCE(json_extract(j.payload,'$.case.subcategory'),'') subcategory,
-        COALESCE(json_extract(j.payload,'$.case.preconditions'),'') preconditions
+        COALESCE(json_extract(j.payload,'$.case.preconditions'),'') preconditions,
+        COALESCE(json_extract(j.payload,'$.error'),'') error
       FROM sessions s LEFT JOIN automation_jobs j ON s.session_id=j.session_id
       UNION ALL
       SELECT j.session_id,json_extract(j.payload,'$.case.goal'),
@@ -200,7 +203,8 @@ def history(
         COALESCE(json_extract(j.payload,'$.case.case_id'),''),
         COALESCE(json_extract(j.payload,'$.case.category'),''),
         COALESCE(json_extract(j.payload,'$.case.subcategory'),''),
-        COALESCE(json_extract(j.payload,'$.case.preconditions'),'')
+        COALESCE(json_extract(j.payload,'$.case.preconditions'),''),
+        COALESCE(json_extract(j.payload,'$.error'),'')
       FROM automation_jobs j WHERE NOT EXISTS (SELECT 1 FROM sessions s WHERE s.session_id=j.session_id)
     ) """
     where = " WHERE status IN ('completed','success','failed','cancelled','interrupted','skipped')"
@@ -226,4 +230,8 @@ def history(
             + " ORDER BY start_time DESC,session_id LIMIT ? OFFSET ?",
             [*args, size, (page - 1) * size],
         ).fetchall()
-    return {"items": [dict(r) for r in rows], "total": total, "page": page, "size": size}
+    items = [dict(row) for row in rows]
+    for item in items:
+        if item["case_id"]:
+            item["name"] = task_import.case_title(item)
+    return {"items": items, "total": total, "page": page, "size": size}

apps/admin_console/routers/sessions.py

@@ -27,12 +27,16 @@ try:
     from admin_console.database.repositories.trace_repository import trace_repo
     from admin_console.services.media_service import media_service
     from admin_console.services.model_service import model_service
+    from admin_console.services.automation_store import store
+    from admin_console.services.task_import import case_title
 except ImportError:
     from apps.admin_console.core.state import state
     from apps.admin_console.database.repositories.session_repository import session_repo
     from apps.admin_console.database.repositories.trace_repository import trace_repo
     from apps.admin_console.services.media_service import media_service
     from apps.admin_console.services.model_service import model_service
+    from apps.admin_console.services.automation_store import store
+    from apps.admin_console.services.task_import import case_title
 
 
 router = APIRouter(tags=["sessions"])
@@ -52,6 +56,7 @@ async def list_sessions():
 
 def _list_sessions_sync():
     rows = session_repo.get_all_sessions()
+    jobs_by_id = store.jobs_for_sessions([str(row.get("session_id")) for row in rows])
     video_rec_map = session_repo.get_video_recordings_map()
     latest_recordings = session_repo.get_latest_video_recordings_map()
     agent_names_by_session = session_repo.get_agent_trace_names_map()
@@ -74,6 +79,15 @@ def _list_sessions_sync():
 
     for row_dict in rows:
         s_id = str(row_dict.get("session_id"))
+        job = jobs_by_id.get(s_id)
+        if job:
+            case = job.get("case") or {}
+            row_dict["case_id"] = case.get("case_id") or ""
+            row_dict["display_name"] = case_title(case) or row_dict.get("initial_goal")
+            row_dict["error"] = job.get("error") or ""
+            if job.get("status") in {"completed", "failed", "cancelled", "interrupted", "skipped"}:
+                row_dict["status"] = job["status"]
+                row_dict["end_time"] = job.get("ended_at") or row_dict.get("end_time")
         recording = latest_recordings.get(s_id)
         d_info_raw = row_dict.get("device_info")
         device_id = None

apps/admin_console/services/automation_service.py

@@ -3,11 +3,13 @@
 import asyncio
 import logging
 import os
+import shutil
 import time
+from uuid import UUID
 
 from apps.admin_console.core.state import state
 from apps.admin_console.services.automation_store import store, new_id
-from apps.admin_console.services.task_import import case_goal
+from apps.admin_console.services.task_import import case_goal, case_title
 
 logger = logging.getLogger(__name__)
 TERMINAL = {"completed", "failed", "cancelled", "skipped", "interrupted"}
@@ -82,9 +84,9 @@ async def on_terminal(item: dict, status: str):
         job = store.job(sid)
     if job is None:
         raise RuntimeError("任务元数据写入失败")
-    job.update(status="finalizing", ended_at=time.time())
     if job.get("timed_out"):
         status = "failed"
+    job.update(status="finalizing", terminal_status=status, ended_at=time.time())
     store.save_job(job)
     try:
         job["status"] = status
@@ -99,7 +101,9 @@ async def on_terminal(item: dict, status: str):
             }
         ):
             job["status"] = "failed"
-            job["error"] = "任务执行结束，但业务检查未通过"
+            job["error"] = job.get("error") or "任务执行结束，但业务检查未通过"
+        elif job["status"] == "failed" and report.get("error") and not job.get("error"):
+            job["error"] = report["error"]
         # 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"])
@@ -107,6 +111,7 @@ async def on_terminal(item: dict, status: str):
     except Exception as exc:
         logger.exception("Report finalization failed for %s", sid)
         job["report_error"] = str(exc)[:500]
+    job.pop("terminal_status", None)
     store.save_job(job)
 
 
@@ -138,7 +143,9 @@ async def tick_batches():
                     and not job.get("timed_out")
                     and time.time() - job.get("started_at", time.time()) - excluded > limit
                 ):
-                    job.update(error="任务达到批次配置的执行时限", timed_out=True)
+                    job.update(
+                        error=f"任务执行超时（{limit} 秒，不含暂停/排队时间）", timed_out=True
+                    )
                     store.save_job(job)
                     task_queue_service.stop_tasks(session_id=job["session_id"])
                     batch.update(status="paused", reason="任务超时，已暂停剩余任务；请确认设备状态")
@@ -202,6 +209,7 @@ async def tick_batches():
                 runtime_overrides=options,
                 session_id=job["session_id"],
                 ingress="batch",
+                display_name=case_title(job["case"]),
             )
             if response.get("status") == "rejected" or not response.get("tasks"):
                 raise ValueError(response.get("error") or "队列拒绝接收任务")
@@ -265,6 +273,35 @@ def create_batch(payload: dict) -> dict:
     return store.create_batch(batch, jobs, payload)
 
 
+def delete_batch(batch_id: str) -> bool:
+    """Delete an inactive batch, its sessions and its generated reports."""
+    from artemis.data_engine.storage import StorageManager
+    from apps.admin_console.services import report_export
+
+    jobs = store.begin_delete_batch(batch_id)
+    if jobs is None:
+        return False
+    storage = StorageManager(store.path, report_export.TRACES_PATH)
+    mcp_exports = report_export.EXPORT_ROOT.parent / "mcp_exports"
+    with report_export.EXPORT_LOCK:
+        for job in jobs:
+            session_id = str(UUID(job["session_id"]))
+            storage.delete_session(UUID(session_id))
+            report_dir = report_export.EXPORT_ROOT / "sessions" / session_id
+            if report_dir.is_dir():
+                shutil.rmtree(report_dir)
+            mcp_session_dir = mcp_exports / "sessions" / session_id
+            if mcp_session_dir.is_dir():
+                shutil.rmtree(mcp_session_dir)
+        batch_dir = report_export.EXPORT_ROOT / "batches" / batch_id
+        if batch_dir.is_dir():
+            shutil.rmtree(batch_dir)
+        mcp_batch_dir = mcp_exports / "batches" / batch_id
+        if mcp_batch_dir.is_dir():
+            shutil.rmtree(mcp_batch_dir)
+        return store.delete_batch(batch_id)
+
+
 def batch_action(batch_id: str, action: str) -> dict:
     batch = store.get("batch", batch_id)
     if not batch:

apps/admin_console/services/automation_store.py

@@ -54,6 +54,13 @@ class AutomationStore:
 
     def put(self, kind: str, key: str, payload: dict) -> dict:
         with self.connection() as conn:
+            if kind == "batch":
+                conn.execute("BEGIN IMMEDIATE")
+                row = conn.execute(
+                    "SELECT payload FROM automation_records WHERE kind='batch' AND id=?", (key,)
+                ).fetchone()
+                if row is None or json.loads(row[0]).get("status") == "deleting":
+                    raise ValueError("批次正在删除或已删除，不能继续更新")
             conn.execute(
                 "INSERT INTO automation_records VALUES (?,?,?,?) ON CONFLICT(kind,id) DO UPDATE SET payload=excluded.payload,updated_at=excluded.updated_at",
                 (kind, key, json.dumps(payload, ensure_ascii=False), time.time()),
@@ -78,6 +85,14 @@ class AutomationStore:
 
     def save_job(self, payload: dict) -> dict:
         with self.connection() as conn:
+            conn.execute("BEGIN IMMEDIATE")
+            if batch_id := payload.get("batch_id"):
+                row = conn.execute(
+                    "SELECT payload FROM automation_records WHERE kind='batch' AND id=?",
+                    (batch_id,),
+                ).fetchone()
+                if row is None or json.loads(row[0]).get("status") == "deleting":
+                    raise ValueError("批次正在删除，不能继续派发任务")
             conn.execute(
                 "INSERT INTO automation_jobs VALUES (?,?,?,?,?,?) ON CONFLICT(session_id) DO UPDATE SET payload=excluded.payload,status=excluded.status,updated_at=excluded.updated_at",
                 (
@@ -106,6 +121,25 @@ class AutomationStore:
             )
         return [{**json.loads(row[0]), "status": row[1]} for row in rows]
 
+    def jobs_for_sessions(self, session_ids: list[str]) -> dict[str, dict]:
+        """Load only metadata belonging to the sessions shown in history."""
+        result = {}
+        with self.connection() as conn:
+            for offset in range(0, len(session_ids), 400):
+                chunk = session_ids[offset : offset + 400]
+                markers = ",".join("?" for _ in chunk)
+                rows = conn.execute(
+                    f"SELECT session_id,payload,status FROM automation_jobs WHERE session_id IN ({markers})",
+                    chunk,
+                ).fetchall()
+                result.update(
+                    {
+                        row["session_id"]: {**json.loads(row["payload"]), "status": row["status"]}
+                        for row in rows
+                    }
+                )
+        return result
+
     def preferences(self) -> dict:
         return self.get("settings", "reports") or {"formats": ["docx", "xlsx"]}
 
@@ -164,8 +198,38 @@ class AutomationStore:
             conn.commit()
         return batch
 
+    def begin_delete_batch(self, batch_id: str) -> list[dict] | None:
+        """Reserve an inactive batch for cleanup before any more jobs can start."""
+        with self.connection() as conn:
+            conn.execute("BEGIN IMMEDIATE")
+            row = conn.execute(
+                "SELECT payload FROM automation_records WHERE kind='batch' AND id=?",
+                (batch_id,),
+            ).fetchone()
+            if row is None:
+                return None
+            batch = json.loads(row[0])
+            active = conn.execute(
+                "SELECT 1 FROM automation_jobs WHERE batch_id=? AND status IN "
+                "('queued','running','task_paused','resuming','finalizing') LIMIT 1",
+                (batch_id,),
+            ).fetchone()
+            if batch["status"] == "running" or active:
+                raise ValueError("批次仍有任务执行中或排队中，请等待完成后删除")
+            batch["status"] = "deleting"
+            conn.execute(
+                "UPDATE automation_records SET payload=?,updated_at=? WHERE kind='batch' AND id=?",
+                (json.dumps(batch, ensure_ascii=False), time.time(), batch_id),
+            )
+            jobs = conn.execute(
+                "SELECT payload,status FROM automation_jobs WHERE batch_id=? ORDER BY position",
+                (batch_id,),
+            ).fetchall()
+            conn.commit()
+        return [{**json.loads(job[0]), "status": job[1]} for job in jobs]
+
     def delete_batch(self, batch_id: str) -> bool:
-        """Remove a batch record; retain executed job metadata and its reports."""
+        """Remove a batch record and all of its jobs after cleanup."""
         with self.connection() as conn:
             conn.execute("BEGIN IMMEDIATE")
             row = conn.execute(
@@ -175,17 +239,9 @@ class AutomationStore:
             if row is None:
                 return False
             batch = json.loads(row[0])
-            active = conn.execute(
-                "SELECT 1 FROM automation_jobs WHERE batch_id=? AND status IN "
-                "('queued','running','task_paused','resuming','finalizing') LIMIT 1",
-                (batch_id,),
-            ).fetchone()
-            if batch["status"] == "running" or active:
-                raise ValueError("批次仍有任务执行中或排队中，请等待完成后删除")
-            conn.execute(
-                "DELETE FROM automation_jobs WHERE batch_id=? AND status='pending'",
-                (batch_id,),
-            )
+            if batch.get("status") != "deleting":
+                raise ValueError("批次尚未准备删除")
+            conn.execute("DELETE FROM automation_jobs WHERE batch_id=?", (batch_id,))
             conn.execute(
                 "DELETE FROM automation_records WHERE kind='batch' AND id=?",
                 (batch_id,),

apps/admin_console/services/report_export.py

@@ -22,6 +22,7 @@ from artemis.config import IMAGES_DIR, TRACES_PATH, WORKSPACE_ROOT
 from apps.admin_console.database.repositories.session_repository import SessionRepository
 from apps.admin_console.database.repositories.step_repository import StepRepository
 from apps.admin_console.services.automation_store import store, identifier
+from apps.admin_console.services.task_import import case_title
 
 EXPORT_ROOT = WORKSPACE_ROOT / "artifacts" / "reports"
 EXPORT_LOCK = threading.RLock()
@@ -40,6 +41,14 @@ STATUS = {
 }
 
 
+def archive_case_name(report: dict) -> str:
+    """Keep case identifiers readable without allowing ZIP paths or Windows-invalid names."""
+    fallback = str(report.get("id") or "task")[:8]
+    candidate = str(report.get("case_id") or fallback).strip()
+    candidate = re.sub(r'[\\/:*?"<>|\x00-\x1f]', "_", candidate).strip(" .")
+    return candidate[:80] or fallback
+
+
 def read_json(path: Path, fallback=None):
     try:
         return json.loads(path.read_text(encoding="utf-8"))
@@ -83,6 +92,9 @@ def failure_reason(directory: Path, status: str, recorded: str | None) -> str:
         return redact(recorded)
     if status not in {"failed", "interrupted"}:
         return ""
+    state = read_json(directory / "status.json", {})
+    if isinstance(state, dict) and state.get("error"):
+        return redact(state["error"])
     for name in ("stdout.log", "stderr.log"):
         path = directory / name
         try:
@@ -96,6 +108,8 @@ def failure_reason(directory: Path, status: str, recorded: str | None) -> str:
             match = re.search(r"Error running automation:\s*(.+)", line)
             if match:
                 return redact(match.group(1))
+            if re.search(r"(?i)(?:timeout|timed out|超时|deadline exceeded)", line):
+                return redact("模型请求或任务执行超时：" + line.strip())
     return "任务未完成，运行日志中没有可提取的具体异常；请查看执行步骤。"
 
 
@@ -142,7 +156,7 @@ def session_report(session_id: str, db_path=None) -> dict:
         )
     return {
         "id": session_id,
-        "name": case.get("name") or session.get("initial_goal", session_id)[:120],
+        "name": case_title(case) or session.get("initial_goal", session_id)[:120],
         "goal": case.get("goal") or session.get("initial_goal", ""),
         "expected": case.get("expected", ""),
         "status": status,
@@ -638,15 +652,18 @@ def export_session_media(session_id: str, kind: str) -> Path:
             "videos": [name for _, name in videos],
             "note": "录屏按时间顺序分段；暂停期间未占用设备，也未录制其他任务。",
         }
+        prefix = archive_case_name(report) + "/" if kind == "all" else ""
         with zipfile.ZipFile(temporary, "w", zipfile.ZIP_DEFLATED) as archive:
             if kind == "all":
                 for path in export_session(session_id, ["docx", "xlsx"]):
-                    archive.write(path, path.name)
+                    archive.write(path, prefix + path.name)
             for source, name in images:
-                archive.write(source, f"步骤截图/{name}")
+                archive.write(source, f"{prefix}步骤截图/{name}")
             for source, name in videos:
-                archive.write(source, f"任务录屏/{name}")
-            archive.writestr("文件清单.json", json.dumps(manifest, ensure_ascii=False, indent=2))
+                archive.write(source, f"{prefix}任务录屏/{name}")
+            archive.writestr(
+                prefix + "文件清单.json", json.dumps(manifest, ensure_ascii=False, indent=2)
+            )
         temporary.replace(target)
         return target
 
@@ -691,6 +708,8 @@ def export_batch(batch_id: str) -> Path:
                 archive.write(path, path.name)
             for number, report in enumerate(records, 1):
                 for path in export_session(report["id"], formats):
-                    archive.write(path, f"任务报告/{number:04d}_{report['id']}/{path.name}")
+                    archive.write(
+                        path, f"任务报告/{number:04d}_{archive_case_name(report)}/{path.name}"
+                    )
         temporary.replace(target)
         return target

apps/admin_console/services/task_import.py

@@ -177,3 +177,10 @@ def parse_workbook(data: bytes) -> dict:
 def case_goal(case: dict) -> str:
     """Execution gets the prompt verbatim; metadata stays outside model input."""
     return case["goal"]
+
+
+def case_title(case: dict) -> str:
+    """Human-facing title; never prepend metadata to the model prompt."""
+    case_id = str(case.get("case_id") or "").strip()
+    name = str(case.get("name") or "").strip()
+    return " ".join(part for part in (case_id, name) if part)

apps/admin_console/services/task_queue_service.py

@@ -1133,6 +1133,7 @@ class TaskQueueService:
         verification_level: str | None = None,
         explorer_mode: str | None = None,
         runtime_overrides: dict[str, Any] | None = None,
+        display_name: str | None = None,
     ) -> dict[str, Any]:
         """Enqueues one or more goals and wakes up the background worker.
 
@@ -1189,6 +1190,8 @@ class TaskQueueService:
             )
             if runtime_overrides:
                 task_item["runtime_overrides"] = runtime_overrides
+            if display_name:
+                task_item["display_name"] = display_name
             state.queue_items.append(task_item)
             enqueued_tasks.append(task_item)
             cls._broadcast_startup_progress(