fix: prevent timeout stalls and release 1.2.1

tests/unit/admin_console/test_automation.py

@@ -4,7 +4,7 @@ from io import BytesIO
 import json
 import sqlite3
 import time
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, Mock
 from uuid import UUID
 import zipfile
 
@@ -347,6 +347,61 @@ async def test_batch_timeout_stays_visible_in_job_report_and_history(client, iso
     )
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("stop_on_failure", [False, True])
+async def test_timed_out_case_releases_next_batch_case(isolated, monkeypatch, stop_on_failure):
+    from apps.admin_console import server
+    from artemis.runtime.device_pool import DeviceStatus
+
+    batch = service.create_batch(payload(timeout_seconds=1, stop_on_failure=stop_on_failure))
+    service.batch_action(batch["id"], "resume")
+    first = isolated.jobs(batch["id"])[0]
+    isolated.save_job({**first, "status": "running", "started_at": time.time() - 2})
+    monkeypatch.setattr(
+        service, "state", type("State", (), {"is_paused": False, "active_runs": {}})()
+    )
+    stop = Mock(return_value=True)
+    enqueue = AsyncMock(return_value={"tasks": [{"device_serial": "test-device"}]})
+    monkeypatch.setattr(server.task_queue_service, "stop_tasks", stop)
+    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")]),
+    )
+    monkeypatch.setattr(reports, "export_batch", Mock())
+
+    await service.tick_batches()
+    assert isolated.get("batch", batch["id"])["status"] == "running"
+    assert "超时" in isolated.job(first["session_id"])["error"]
+    stop.assert_called_once_with(session_id=first["session_id"])
+    await service.tick_batches()
+    stop.assert_called_once()
+
+    await service.on_terminal({"session_id": first["session_id"]}, "cancelled")
+    await service.tick_batches()
+    statuses = [job["status"] for job in isolated.jobs(batch["id"])]
+    assert statuses == (["failed", "skipped"] if stop_on_failure else ["failed", "queued"])
+    assert enqueue.await_count == (0 if stop_on_failure else 1)
+
+
+@pytest.mark.asyncio
+async def test_queued_case_does_not_consume_execution_timeout(isolated, monkeypatch):
+    from apps.admin_console import server
+
+    batch = service.create_batch(payload(timeout_seconds=1))
+    service.batch_action(batch["id"], "resume")
+    first = isolated.jobs(batch["id"])[0]
+    isolated.save_job({**first, "status": "queued", "started_at": time.time() - 30})
+    monkeypatch.setattr(service, "state", type("State", (), {"is_paused": False})())
+    stop = Mock()
+    monkeypatch.setattr(server.task_queue_service, "stop_tasks", stop)
+
+    await service.tick_batches()
+    stop.assert_not_called()
+    assert isolated.job(first["session_id"])["status"] == "queued"
+    assert isolated.get("batch", batch["id"])["status"] == "running"
+
+
 @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]

tests/unit/agents/test_flash_runner_ledger.py

@@ -636,6 +636,32 @@ async def test_run_no_tool_call_turn_is_nudged_not_terminated(mock_context):
         and any(EXECUTION_RESULT_MARKER in b.get("text", "") for b in m.content)
         for m in turn2_messages
     )
+    assert not any(
+        isinstance(m, AIMessage) and m.content == "thinking only" for m in turn2_messages
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("attempts", [1, 3])
+async def test_flash_stops_repeated_no_tool_responses(mock_context, monkeypatch, attempts):
+    from artemis.config.settings import settings
+
+    monkeypatch.setattr(settings, "ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS", attempts)
+    responses = [AIMessage(content="I will click now.", tool_calls=[]) for _ in range(attempts)]
+    with (
+        patch("artemis.controllers.unified_controller.get_driver"),
+        patch(
+            "artemis.agents.flash.runner.capture_screenshot_and_parse_ui",
+            AsyncMock(return_value=_INITIAL_OBSERVATION),
+        ),
+    ):
+        runner = _make_runner(mock_context, responses, max_turns=0)
+        result = await runner.run(State(initial_goal="Open Settings"))
+
+    assert result["status"] == "failed"
+    assert f"连续 {attempts} 次未调用工具" in result["explanation"]
+    assert runner._invoke_model.await_count == attempts
+    runner.executor.execute.assert_not_awaited()
 
 
 # ---------------------------------------------------------------------------