feat: improve batch task controls and release 1.2.0

tests/unit/admin_console/test_automation.py

@@ -2,8 +2,10 @@
 
 from io import BytesIO
 import json
+import sqlite3
 import time
 from unittest.mock import AsyncMock
+from uuid import UUID
 import zipfile
 
 from docx import Document
@@ -125,19 +127,44 @@ def test_preferences_and_required_device(client):
     assert client.post("/api/automation/batches", json=payload(device_serial="")).status_code == 422
 
 
-def test_batch_delete_retains_executed_task_and_prevents_request_replay(client, isolated):
+def test_batch_delete_removes_tasks_and_files_and_prevents_request_replay(client, isolated):
     created = client.post(
         "/api/automation/batches", json=payload(request_id="delete-example")
     ).json()
     first, second = isolated.jobs(created["id"])
     isolated.save_job({**first, "status": "completed"})
+    trace_dir = reports.TRACES_PATH / first["session_id"]
+    trace_dir.mkdir(parents=True)
+    (trace_dir / "result.json").write_text("{}", encoding="utf-8")
+    report_dir = reports.EXPORT_ROOT / "sessions" / first["session_id"]
+    report_dir.mkdir(parents=True)
+    (report_dir / "任务报告.docx").write_bytes(b"report")
+    batch_dir = reports.EXPORT_ROOT / "batches" / created["id"]
+    batch_dir.mkdir(parents=True)
+    (batch_dir / "批次报告.zip").write_bytes(b"zip")
+    mcp_task_dir = reports.EXPORT_ROOT.parent / "mcp_exports" / "sessions" / first["session_id"]
+    mcp_task_dir.mkdir(parents=True)
+    (mcp_task_dir / "报告.docx").write_bytes(b"report")
+    mcp_batch_dir = reports.EXPORT_ROOT.parent / "mcp_exports" / "batches" / created["id"]
+    mcp_batch_dir.mkdir(parents=True)
+    (mcp_batch_dir / "批次.zip").write_bytes(b"zip")
+    unrelated = reports.TRACES_PATH / "unrelated-task"
+    unrelated.mkdir()
+    (unrelated / "keep.txt").write_text("keep", encoding="utf-8")
 
     response = client.delete(f"/api/automation/batches/{created['id']}")
     assert response.status_code == 200
     assert client.get(f"/api/automation/batches/{created['id']}").status_code == 404
-    assert isolated.job(first["session_id"])["case"]["name"] == "用例甲"
+    assert isolated.job(first["session_id"]) is None
     assert isolated.job(second["session_id"]) is None
-    assert reports.session_report(first["session_id"])["name"] == "用例甲"
+    assert not trace_dir.exists()
+    assert not report_dir.exists()
+    assert not batch_dir.exists()
+    assert not mcp_task_dir.exists()
+    assert not mcp_batch_dir.exists()
+    assert (unrelated / "keep.txt").read_text(encoding="utf-8") == "keep"
+    with pytest.raises(ValueError, match="不存在"):
+        reports.session_report(first["session_id"])
     assert (
         client.post(
             "/api/automation/batches", json=payload(request_id="delete-example")
@@ -158,6 +185,49 @@ def test_batch_delete_rejects_active_jobs(client, isolated, status):
     assert len(isolated.jobs(batch["id"])) == 2
 
 
+def test_batch_deletion_reservation_blocks_new_dispatch(isolated):
+    batch = service.create_batch(payload())
+    job = isolated.jobs(batch["id"])[0]
+
+    isolated.begin_delete_batch(batch["id"])
+
+    with pytest.raises(ValueError, match="正在删除"):
+        isolated.save_job({**job, "status": "queued"})
+    with pytest.raises(ValueError, match="正在删除"):
+        isolated.put("batch", batch["id"], {**batch, "status": "running"})
+    assert isolated.jobs_for_sessions([job["session_id"]])[job["session_id"]]["status"] == "pending"
+
+
+def test_batch_deletion_preserves_shared_screenshot_until_last_task(client, isolated):
+    first_batch = service.create_batch(payload())
+    second_batch = service.create_batch(payload(name="另一批次"))
+    first = isolated.jobs(first_batch["id"])[0]
+    other = isolated.jobs(second_batch["id"])[0]
+    shared_hash = "a" * 64
+    storage = StorageManager(isolated.path, reports.TRACES_PATH)
+    image_file = reports.TRACES_PATH / "images" / f"{shared_hash}.jpg"
+    image_file.parent.mkdir(parents=True)
+    image_file.write_bytes(b"shared image")
+    with sqlite3.connect(isolated.path) as conn:
+        conn.execute("INSERT INTO images(image_name) VALUES (?)", (shared_hash,))
+        for job in (first, other):
+            conn.execute(
+                "INSERT INTO sessions(session_id,initial_goal,start_time,status,device_info) "
+                "VALUES (?,?,?,?,?)",
+                (job["session_id"], "观察设置", 1.0, "completed", "{}"),
+            )
+            conn.execute(
+                "INSERT INTO steps(step_id,session_id,pre_image_name) VALUES (?,?,?)",
+                (job["session_id"], job["session_id"], shared_hash),
+            )
+
+    assert client.delete(f"/api/automation/batches/{first_batch['id']}").status_code == 200
+    assert image_file.read_bytes() == b"shared image"
+    assert storage.get_session(UUID(other["session_id"])) is not None
+    assert client.delete(f"/api/automation/batches/{second_batch['id']}").status_code == 200
+    assert not image_file.exists()
+
+
 def test_restart_never_repeats_started_work(isolated):
     batch = service.create_batch(payload())
     service.batch_action(batch["id"], "resume")
@@ -260,6 +330,41 @@ async def test_report_failure_does_not_strand_job(isolated, monkeypatch):
     assert "disk full" in saved["report_error"]
 
 
+@pytest.mark.asyncio
+async def test_batch_timeout_stays_visible_in_job_report_and_history(client, isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job(
+        {**job, "status": "running", "timed_out": True, "error": "任务执行超时（30 秒）"}
+    )
+    await service.on_terminal({"session_id": job["session_id"]}, "cancelled")
+    saved = isolated.job(job["session_id"])
+    assert saved["status"] == "failed"
+    assert "超时" in saved["error"]
+    assert "超时" in reports.session_report(job["session_id"])["error"]
+    history = client.get("/api/automation/history").json()["items"]
+    assert any(
+        item["session_id"] == job["session_id"] and "超时" in item["error"] for item in history
+    )
+
+
+@pytest.mark.asyncio
+async def test_model_timeout_from_runner_log_reaches_failed_task_and_report(isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "stderr.log").write_text(
+        "TimeoutError: model request timed out after 300 seconds\n", encoding="utf-8"
+    )
+
+    await service.on_terminal({"session_id": job["session_id"]}, "failed")
+
+    saved = isolated.job(job["session_id"])
+    assert saved["status"] == "failed"
+    assert "超时" in saved["error"]
+    assert reports.session_report(job["session_id"])["status"] == "failed"
+    assert "超时" in reports.session_report(job["session_id"])["error"]
+
+
 def test_reports_do_not_execute_formulas_or_invent_pass(isolated):
     batch = service.create_batch(payload())
     job = isolated.jobs(batch["id"])[0]
@@ -296,6 +401,7 @@ def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolat
     assert "abc123secret" not in reports.failure_reason(
         folder, "failed", "认证失败 OPENAI_API_KEY=abc123secret Authorization: Bearer abc123secret"
     )
+    assert "超时" not in reports.failure_reason(folder, "failed", "LLMExhaustedError: 额度不足")
     paths = reports.export_session(job["session_id"])
     doc = Document(next(path for path in paths if path.suffix == ".docx"))
     assert doc.styles["Normal"].font.name == "Microsoft YaHei"
@@ -325,6 +431,7 @@ def test_task_material_zip_contains_ordered_evidence_and_reports(
     client, isolated, tmp_path, monkeypatch
 ):
     job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "case": {**job["case"], "case_id": "1.1"}})
     evidence = tmp_path / "evidence"
     evidence.mkdir()
     first = evidence / "first.png"
@@ -343,14 +450,16 @@ def test_task_material_zip_contains_ordered_evidence_and_reports(
     assert response.status_code == 200
     with zipfile.ZipFile(BytesIO(response.content)) as archive:
         files = archive.namelist()
+        assert all(name.startswith("1.1/") for name in files)
         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 files.index("1.1/步骤截图/0001_步骤0001_操作前.png") < files.index(
+            "1.1/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 archive.read("1.1/任务录屏/0001_recording.mp4") == b"recording.mp4"
+        manifest = json.loads(archive.read("1.1/文件清单.json"))
         assert manifest["session_id"] == job["session_id"]
+    assert "1.1-all.zip" in response.headers["content-disposition"]
 
 
 def test_history_filters_all_persisted_rows_and_escapes_like(client, isolated):

tests/unit/admin_console/test_session_list_batching.py

@@ -5,6 +5,14 @@ import pytest
 from apps.admin_console.routers import sessions as sessions_router
 
 
+@pytest.fixture(autouse=True)
+def isolate_jobs(monkeypatch):
+    mocked = MagicMock()
+    mocked.jobs_for_sessions.return_value = {}
+    monkeypatch.setattr(sessions_router, "store", mocked)
+    return mocked
+
+
 @pytest.mark.asyncio
 async def test_list_sessions_uses_batched_history_metadata(monkeypatch):
     repo = MagicMock()
@@ -96,3 +104,42 @@ async def test_list_sessions_extracts_device_serial(monkeypatch):
     assert result[0]["device_id"] == "63191FDKX00062"
     assert result[1]["device_serial"] == "emulator-5554"
     assert result[1]["device_id"] == "emulator-5554"
+
+
+@pytest.mark.asyncio
+async def test_list_sessions_uses_batch_title_and_timeout_error(monkeypatch, isolate_jobs):
+    repo = MagicMock()
+    repo.get_all_sessions.return_value = [
+        {
+            "session_id": "session-case",
+            "status": "completed",
+            "start_time": 1.0,
+            "initial_goal": "打开设置并检查页面",
+            "device_info": '{"profile":"flash"}',
+        }
+    ]
+    repo.get_video_recordings_map.return_value = {}
+    repo.get_latest_video_recordings_map.return_value = {}
+    repo.get_agent_trace_names_map.return_value = {}
+    monkeypatch.setattr(sessions_router, "session_repo", repo)
+    monkeypatch.setattr(
+        sessions_router.media_service, "build_video_index", MagicMock(return_value={})
+    )
+    isolate_jobs.jobs_for_sessions.return_value = {
+        "session-case": {
+            "session_id": "session-case",
+            "status": "failed",
+            "ended_at": 65.0,
+            "error": "任务执行超时（60 秒）",
+            "case": {"case_id": "1.1", "name": "打开并核对设置", "goal": "打开设置并检查页面"},
+        }
+    }
+
+    result = await sessions_router.list_sessions()
+
+    isolate_jobs.jobs_for_sessions.assert_called_once_with(["session-case"])
+    assert result[0]["display_name"] == "1.1 打开并核对设置"
+    assert result[0]["initial_goal"] == "打开设置并检查页面"
+    assert result[0]["status"] == "failed"
+    assert result[0]["end_time"] == 65.0
+    assert "超时" in result[0]["error"]