放宽后台Agent工具计划环路测试超时口径

- final reply 请求捕获改用 wait_for_captured_mock_request 10 秒轮询预算，取代手写 recv_timeout 2 秒，消除持久化动作批次管线开销导致的单测 flaky
- 收尾等待改用 wait_for_agent_runtime_terminal_and_lane_release，确认 lane 释放、不留僵尸 worker
- 批量并行跑时的跨测试污染为既有系统性问题，本次不处理

apps/ai-game-creator-shell/src-tauri/src/tests/runtime_actions/planning_strategy/tool_planning.rs

@@ -1260,25 +1260,20 @@ async fn background_agent_runtime_task_executes_plan_tool_observation_loop() {
     assert!(plan_request.contains("后台分析当前玩法循环"));
     assert!(!plan_request.contains("核心循环：收集月光食材并躲避暗影"));
     assert!(!plan_request.contains("黑板：必须先确认核心循环"));
-    let final_request = receiver
-        .recv_timeout(Duration::from_secs(2))
-        .expect("final reply llm request");
+    let final_request =
+        wait_for_captured_mock_request(&receiver, "final reply llm request").await;
     assert!(final_request.contains("工具观察"));
     assert!(final_request.contains("核心循环：收集月光食材并躲避暗影"));
     assert!(final_request.contains("黑板：必须先确认核心循环"));
 
-    let mut runtime = read_game_creator_agent_runtime_at(&root, "design-director")
-        .expect("read runtime")
-        .state;
-    for _ in 0..250 {
-        if runtime.status == "idle" {
-            break;
-        }
-        std::thread::sleep(Duration::from_millis(20));
-        runtime = read_game_creator_agent_runtime_at(&root, "design-director")
-            .expect("read runtime")
-            .state;
-    }
+    let runtime = wait_for_agent_runtime_terminal_and_lane_release(
+        &root,
+        "design-director",
+        "design-loop-run",
+        "idle",
+        "completed",
+    )
+    .state;
 
     assert_eq!(runtime.status, "idle");
     assert_eq!(runtime.phase, "completed");