feat: add dynamic variables and startup result handling in batch run schemas

- Introduced dynamic_variables field in BatchRunCreate schema to support flexible input types.
- Added BatchStartupResult schema to encapsulate startup state, including greeting and auto-confirmed messages.
- Updated BatchRunCaseOut schema to include startup results, enhancing the structure for test run outputs.
- Enhanced test run orchestration to prepare and validate dynamic configurations, ensuring isolated variable management across test cases.
- Implemented changes in the frontend to accommodate new data structures for improved test case execution and result tracking.

backend/services/brains/prompt_brain.py

@@ -681,17 +681,10 @@ class PromptBrain(BaseBrain):
         else:
             raise ValueError(f"未知系统工具: {kind}")
 
-        if runtime.tool_executor_factory is None:
-            return schema, handler
-
-        async def mock_system_tool(params: FunctionCallParams) -> None:
-            result = await self._tools.execute(
-                tool,
-                dict(params.arguments or {}),
-            )
-            await params.result_callback(result)
-
-        return schema, mock_system_tool
+        # System tools are platform-owned deterministic behavior. Keep their
+        # lifecycle and state semantics identical across production and tests;
+        # only external HTTP, MCP, and client tools use an injected executor.
+        return schema, handler
 
     def _make_update_state_tool(self, tool, runtime: BrainRuntime):
         """更新已声明的动态变量(会话状态),并让模型继续当前回答。"""