feat: add prompt-first batches and pausable task guidance

tests/unit/admin_console/test_automation.py

@@ -64,9 +64,9 @@ def workbook_bytes(rows):
 def test_template_preview_rejects_formula_and_bad_json():
     data = workbook_bytes(
         [
-            ["正常", "打开设置", "", "", "", '{"name":"测试"}', "冒烟"],
-            ["公式", "=SUM(1,2)"],
-            ["参数错误", "测试", "", "", "", "{"],
+            ["正常", "设置", "冒烟", "打开设置", "", "观察设置", '{"profile":"flash"}'],
+            ["公式", "", "", "", "", "=SUM(1,2)"],
+            ["参数错误", "", "", "", "", "测试", "{"],
         ]
     )
     result = task_import.parse_workbook(data)
@@ -75,6 +75,30 @@ def test_template_preview_rejects_formula_and_bad_json():
     assert not result["valid"]
 
 
+def test_prompt_only_and_per_row_config_validation():
+    goal = "先查看屏幕，再按实际画面判断。"
+    data = workbook_bytes(
+        [
+            [
+                "CASE-7",
+                "检查项目",
+                "子项",
+                "用例名称",
+                "仅作索引的约束",
+                goal,
+                '{"profile":"pro","model":"mimo-v2.6-flash","record_video":true}',
+            ],
+            ["CASE-8", "", "", "", "", "观察屏幕", '{"OPENAI_API_KEY":"never"}'],
+        ]
+    )
+    preview = task_import.parse_workbook(data)
+    assert [e["row"] for e in preview["errors"]] == [3]
+    case = preview["tasks"][0]
+    assert task_import.case_goal(case) == goal
+    assert case["preconditions"] == "仅作索引的约束"
+    assert case["task_config"]["record_video"] is True
+
+
 def test_invalid_archive_and_empty_template():
     with pytest.raises(ValueError):
         task_import.parse_workbook(b"not a zip")
@@ -84,7 +108,9 @@ def test_invalid_archive_and_empty_template():
 def test_preview_does_not_enqueue(client, isolated):
     response = client.post(
         "/api/automation/import/preview",
-        files={"file": ("tasks.xlsx", workbook_bytes([["案例", "观察页面"]]))},
+        files={
+            "file": ("tasks.xlsx", workbook_bytes([["案例", "", "", "观察页面", "", "观察页面"]]))
+        },
     )
     assert response.status_code == 200
     assert response.json()["valid"]
@@ -137,6 +163,30 @@ async def test_batch_admission_idempotent_and_bound_device(isolated, monkeypatch
     assert isolated.jobs(batch["id"])[1]["status"] == "pending"
 
 
+@pytest.mark.asyncio
+async def test_paused_case_yields_batch_slot_to_next_case(isolated, monkeypatch):
+    from apps.admin_console import server
+    from artemis.runtime.device_pool import DeviceStatus
+
+    batch = service.create_batch(payload())
+    service.batch_action(batch["id"], "resume")
+    first = isolated.jobs(batch["id"])[0]
+    isolated.save_job({**first, "status": "task_paused", "started_at": time.time()})
+    monkeypatch.setattr(
+        service, "state", type("State", (), {"is_paused": False, "active_runs": {}})()
+    )
+    enqueue = AsyncMock(return_value={"tasks": [{"device_serial": "test-device"}]})
+    monkeypatch.setattr(server.task_queue_service, "enqueue_tasks", enqueue)
+    monkeypatch.setattr(
+        "artemis.runtime.device_pool.try_list_devices_async",
+        AsyncMock(return_value=[DeviceStatus(serial="test-device", state="device")]),
+    )
+    await service.tick_batches()
+    assert enqueue.await_count == 1
+    assert enqueue.call_args.args[0] == ["观察首页"]
+    assert [job["status"] for job in isolated.jobs(batch["id"])] == ["task_paused", "queued"]
+
+
 @pytest.mark.asyncio
 async def test_device_outage_pauses_without_consuming_pending_case(isolated, monkeypatch):
     batch = service.create_batch(payload())
@@ -193,6 +243,38 @@ def test_reports_do_not_execute_formulas_or_invent_pass(isolated):
         assert "未验证".encode() in doc.read("word/document.xml")
 
 
+def test_task_material_zip_contains_ordered_evidence_and_reports(
+    client, isolated, tmp_path, monkeypatch
+):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    evidence = tmp_path / "evidence"
+    evidence.mkdir()
+    first = evidence / "first.png"
+    second = evidence / "second.png"
+    video = evidence / "recording.mp4"
+    for path in (first, second, video):
+        path.write_bytes(path.name.encode())
+    monkeypatch.setattr(
+        reports,
+        "session_screenshots",
+        lambda report: [(first, "0001_步骤0001_操作前.png"), (second, "0002_步骤0002_操作后.png")],
+    )
+    monkeypatch.setattr(reports, "session_videos", lambda report: [(video, "0001_recording.mp4")])
+
+    response = client.get(f"/api/automation/reports/{job['session_id']}/all")
+    assert response.status_code == 200
+    with zipfile.ZipFile(BytesIO(response.content)) as archive:
+        files = archive.namelist()
+        assert any(name.endswith(".docx") for name in files)
+        assert any(name.endswith(".xlsx") for name in files)
+        assert files.index("步骤截图/0001_步骤0001_操作前.png") < files.index(
+            "步骤截图/0002_步骤0002_操作后.png"
+        )
+        assert archive.read("任务录屏/0001_recording.mp4") == b"recording.mp4"
+        manifest = json.loads(archive.read("文件清单.json"))
+        assert manifest["session_id"] == job["session_id"]
+
+
 def test_history_filters_all_persisted_rows_and_escapes_like(client, isolated):
     batch = service.create_batch(payload())
     first, second = isolated.jobs(batch["id"])

tests/unit/admin_console/test_server_lifecycle.py

@@ -159,7 +159,7 @@ async def test_shutdown_marks_only_ui_owned_running_sessions():
     ):
         await on_shutdown()
 
-    update_status.assert_called_once_with("ui-running", "cancelled")
+    update_status.assert_called_once_with("ui-running", "interrupted")
     assert state.queue_items == []
     state.active_session_id = None
     state.is_shutting_down = False

tests/unit/admin_console/test_session_repository_liveness.py

@@ -25,7 +25,7 @@ def test_startup_cleanup_keeps_live_cross_process_session(tmp_path):
         assert repository.cleanup_orphans_on_startup() == 1
 
     assert repository.get_session_status("live") == "running"
-    assert repository.get_session_status("dead") == "failed"
+    assert repository.get_session_status("dead") == "interrupted"
 
 
 def test_session_list_harvest_rechecks_worker_liveness(tmp_path):

tests/unit/admin_console/test_task_queue_service.py

@@ -987,6 +987,7 @@ async def test_manual_stop_of_one_run_does_not_pollute_concurrent_run():
     on different devices: device A's task is stopped manually, device B's task
     then finishes normally and must still be reported as completed.
     """
+    state.is_shutting_down = False
     ended_payloads: dict[str, dict] = {}
 
     def capture(event_type, data):