feat: release 2.4.0 with original cases and automatic human review

tests/unit/agents/test_flash_runner.py

@@ -379,9 +379,13 @@ def test_flash_records_the_executors_target_semantics(mock_context):
         runner,
         "click",
         click_args,
-        metadata={"target_semantics": {"target_description": "play button"}},
+        metadata={
+            "target_semantics": {"target_description": "play button"},
+            "source": {"kind": "android", "target_id": "selected-phone", "label": "安卓屏幕"},
+        },
     )
     assert click["target_description"] == "play button"
+    assert click["source"]["target_id"] == "selected-phone"
     assert "target_text" not in click
     assert format_actions_clean(click) == "Tapped 'play button' (self-described) at [320, 399]"
 

tests/unit/agents/test_planner_node.py

@@ -124,6 +124,11 @@ async def test_planner_knows_computer_plugins_with_mobile_primary_screen(mock_co
     content = llm.astream.call_args.args[0][1].content
     text = "\n".join(part["text"] for part in content if part["type"] == "text")
     assert text.count("电脑插件：cua-driver") == 1
+    assert "规划器只使用本阶段绑定的笔记工具" in text
+    assert "不表示执行器缺少这些能力" in text
+    assert "实际加载与操作回执" in text
+    bound_names = {tool.name for tool in llm.bind_tools.call_args.args[0]}
+    assert "plugin_load" not in bound_names
     assert f"当前主设备截图（{'电脑' if target == 'computer' else '安卓'}）" in text
     assert "不决定其他步骤的执行平台" in text
 

tests/unit/agents/test_validator.py

@@ -122,6 +122,7 @@ def mock_mcp():
 async def test_validator_success(mock_mcp, mock_context, temp_screenshot):
     """Test that ValidatorNode executes actions successfully."""
     decisions = json.dumps([{"action": "tap", "coordinates": [105, 205]}])
+    mock_context.device.device_id = "selected-phone"
     state = DummyState(structured_decisions=decisions, latest_screenshot=temp_screenshot)
     state.initial_goal = "在真实审批表单上 Approve once，不要普通聊天代答或重复提交。"
 
@@ -142,6 +143,11 @@ async def test_validator_success(mock_mcp, mock_context, temp_screenshot):
     assert len(report["execution"]) == 1
     assert report["execution"][0]["action"] == "tap"
     assert "attempts" not in report["execution"][0]
+    assert report["execution"][0]["source"] == {
+        "kind": "android",
+        "target_id": "selected-phone",
+        "label": "安卓屏幕",
+    }
     # The Operator's tap verb was translated to the canonical click tool.
     assert len(mock_mcp.calls_for("click")) == 1