```

feat(engine): 优化智能体循环中的助手消息处理逻辑

- 在没有工具调用时才添加助手消息到上下文
- 确保工具调用响应正确添加到消息上下文中
- 修复了消息构建的条件逻辑

fix(cron): 改进定时任务调度的时间解析功能

- 添加正则表达式导入用于时间显示解析
- 实现从显示文本中提取毫秒间隔的功能
- 增强整数转换的安全性，避免类型错误
- 优化定时任务配置的解析逻辑

feat(outlook): 增强Outlook集成的功能和稳定性

- 将默认超时时间从10秒增加到180秒
- 为状态检查函数添加可选的验证参数
- 串行执行邮件概览获取操作而非并行
- 改进连接状态验证逻辑

feat(channel): 添加设备名称作为会话标识的选项

- 为终端WebSocket适配器添加新的配置选项
- 实现基于设备名称生成会话对等ID的功能
- 记录原始对等ID和设备名称的元数据
- 支持从设备名称创建会话对等ID

feat(skills): 完善技能学习评估系统和进度跟踪

- 在应用启动时自动调度待评估的技能草稿
- 为技能评估工作创建独立的循环工厂
- 实现异步技能评估任务的取消和清理机制
- 添加技能评估进度报告和状态跟踪功能
- 扩展会话列表API以包含更多详细信息
- 防止对不存在的会话进行操作
- 优化技能草稿提交和评估的业务逻辑

perf(skills): 提升技能评估的并发性能

- 实现并行技能案例评估以提高效率
- 添加最大并行案例数的环境变量控制
- 实现实时评估进度更新和回调机制
- 优化评估过程中的资源管理和同步

refactor(services): 创建隔离的智能体循环实例

- 添加创建独立智能体循环的工厂方法
- 确保新循环继承运行时服务配置
- 支持技能评估等需要隔离环境的场景
```

app-instance/backend/tests/unit/test_phase5_skills_runtime.py

@@ -27,6 +27,7 @@ class StubProvider(LLMProvider):
     def __init__(self, responses: list[LLMResponse]) -> None:
         super().__init__()
         self._responses = list(responses)
+        self.calls: list[dict] = []
 
     async def chat(
         self,
@@ -37,6 +38,16 @@ class StubProvider(LLMProvider):
         temperature: float = 0.7,
         thinking_enabled: bool | None = None,
     ) -> LLMResponse:
+        self.calls.append(
+            {
+                "messages": messages,
+                "tools": tools,
+                "model": model,
+                "max_tokens": max_tokens,
+                "temperature": temperature,
+                "thinking_enabled": thinking_enabled,
+            }
+        )
         if not self._responses:
             raise AssertionError("No stubbed provider responses left")
         return self._responses.pop(0)
@@ -704,32 +715,33 @@ def test_agent_loop_records_max_tool_iterations_as_failed_skill_effect(tmp_path:
         skill_assembler=StubSkillAssembler([skill]),
     )
     loop = AgentLoop(loader=loader)
+    provider = StubProvider(
+        [
+            LLMResponse(
+                content="Need a tool.",
+                finish_reason="tool_calls",
+                tool_calls=[_tool_call()],
+                provider_name="stub",
+                model="stub-model",
+            ),
+            LLMResponse(
+                content="Need another tool.",
+                finish_reason="tool_calls",
+                tool_calls=[_tool_call(call_id="call-2")],
+                provider_name="stub",
+                model="stub-model",
+            ),
+            LLMResponse(
+                content="Based on the available tool result, the container likely failed during startup.",
+                finish_reason="stop",
+                provider_name="stub",
+                model="stub-model",
+            ),
+        ]
+    )
     bundle = ProviderBundle(
         main_runtime=SimpleNamespace(model="stub-model", provider_name="stub"),
-        main_provider=StubProvider(
-            [
-                LLMResponse(
-                    content="Need a tool.",
-                    finish_reason="tool_calls",
-                    tool_calls=[_tool_call()],
-                    provider_name="stub",
-                    model="stub-model",
-                ),
-                LLMResponse(
-                    content="Need another tool.",
-                    finish_reason="tool_calls",
-                    tool_calls=[_tool_call(call_id="call-2")],
-                    provider_name="stub",
-                    model="stub-model",
-                ),
-                LLMResponse(
-                    content="Based on the available tool result, the container likely failed during startup.",
-                    finish_reason="stop",
-                    provider_name="stub",
-                    model="stub-model",
-                ),
-            ]
-        ),
+        main_provider=provider,
     )
 
     result = asyncio.run(
@@ -744,6 +756,21 @@ def test_agent_loop_records_max_tool_iterations_as_failed_skill_effect(tmp_path:
     assert result.finish_reason == "max_tool_iterations_finalized"
     assert "Based on the available tool result" in result.output_text
     assert "Tool loop stopped" not in result.output_text
+    finalization_messages = provider.calls[-1]["messages"]
+    assistant_tool_call_ids = [
+        call["id"]
+        for message in finalization_messages
+        for call in message.get("tool_calls", [])
+        if message.get("role") == "assistant"
+    ]
+    tool_result_ids = [
+        message.get("tool_call_id")
+        for message in finalization_messages
+        if message.get("role") == "tool"
+    ]
+    assert "call-1" in assistant_tool_call_ids
+    assert "call-2" not in assistant_tool_call_ids
+    assert set(assistant_tool_call_ids).issubset(set(tool_result_ids))
     effect_records = loaded.run_memory_store.list_skill_effects("docker-debug", version="v0007")
     assert effect_records[-1].run_id == result.run_id
     assert effect_records[-1].success is False