feat(coordinator): 添加团队节点默认最大工具迭代次数配置

添加 DEFAULT_TEAM_NODE_MAX_TOOL_ITERATIONS 配置项以控制团队节点的最大工具迭代次数，
并修改 LocalAgentRunner 中的逻辑来使用此默认值当 envelope 中未指定时。

fix(runtime): 修复团队节点运行成功判断逻辑

更新运行成功判断条件，将 finish_reason 为 "max_tool_iterations_finalized" 的情况
视为运行失败，并添加对原始工具调用输出的检测，避免将其误判为成功完成。

feat(mcp): 添加团队工作流MCP工具类别支持

增加新的本地MCP工具类别 "team_workflow" 及其对应的工具创建功能，
为团队工作流提供本地工具支持。

refactor(engine): 调整AgentLoop最大工具迭代次数设置

将 AgentProfile 中的默认 max_tool_iterations 从 30 增加到 100，
同时移除 TaskExecutionPlanner 构造函数中的重复参数传递。

perf(mcp): 优化MCP连接管理避免重复连接

添加 mcp_connected 标志来跟踪MCP连接状态，确保 connect_all 只执行一次，
提高性能并避免不必要的重复连接。

refactor(skills): 移除技能团队模板相关功能

移除与技能团队模板相关的代码，包括解析、存储和处理逻辑，
简化技能记录结构和加载流程。

feat(process): 增强会话过程投影器功能

添加技能激活快照事件处理，改进团队运行完成消息显示，
并增强技能激活事件的时间戳记录功能。

refactor(tasks): 简化任务尝试编排器团队执行逻辑

移除团队执行相关代码，将所有任务统一按单步执行处理，
简化任务编排器的复杂度并提升执行效率。

fix(evidence): 修复节点证据评估中需求验证逻辑

更新节点证据评估逻辑，跳过自然语言证据需求的确定性验证，
只执行机器可读的需求验证，避免因自然语言需求导致的节点失败。

app-instance/backend/tests/unit/test_agent_team_v1.py

@@ -15,6 +15,7 @@ from beaver.engine import AgentLoop, EngineLoader
 from beaver.engine.context import SkillContext
 from beaver.engine.providers.base import LLMProvider, LLMResponse
 from beaver.engine.providers.factory import ProviderBundle
+from beaver.engine.session.manager import SessionManager
 from beaver.services.team_service import TeamService
 from beaver.skills.assembler import SkillAssemblyResult
 from beaver.skills.drafts import DraftService
@@ -232,9 +233,9 @@ def test_unknown_evidence_requirement_makes_node_partial(tmp_path: Path) -> None
 
     result = asyncio.run(LocalAgentRunner(loop).run(envelope, provider_bundle=_bundle(provider)))
 
-    assert result.success is False
-    assert result.completion_status == "partial"
-    assert result.evidence_gaps == ["unsupported evidence requirement: unknown_type"]
+    assert result.success is True
+    assert result.completion_status == "succeeded"
+    assert result.evidence_gaps == []
 
 
 def test_team_node_preserves_evidence_when_finish_reason_is_not_stop(tmp_path: Path) -> None:
@@ -257,6 +258,90 @@ def test_team_node_preserves_evidence_when_finish_reason_is_not_stop(tmp_path: P
     assert result.evidence.finish_reason == "max_tool_iterations"
 
 
+def test_team_node_accepts_finalized_tool_budget_output(tmp_path: Path) -> None:
+    loop = _loop(tmp_path)
+    provider = RecordingProvider([_response("usable finalized output", finish_reason="max_tool_iterations_finalized")])
+    envelope = DelegationEnvelope(
+        parent_task_id="task-parent",
+        parent_session_id="session-root",
+        parent_run_id="run-root",
+        agent=AgentDescriptor(name="researcher", role="research"),
+        task="research the requested topic",
+        node_id="research",
+    )
+
+    result = asyncio.run(LocalAgentRunner(loop).run(envelope, provider_bundle=_bundle(provider)))
+
+    assert result.success is True
+    assert result.completion_status == "succeeded"
+    assert result.finish_reason == "max_tool_iterations_finalized"
+
+
+def test_team_node_rejects_finalized_raw_tool_call_output(tmp_path: Path) -> None:
+    loop = _loop(tmp_path)
+    provider = RecordingProvider(
+        [
+            _response(
+                '<｜｜DSML｜｜tool_calls><｜｜DSML｜｜invoke name="web_fetch"></｜｜DSML｜｜invoke></｜｜DSML｜｜tool_calls>',
+                finish_reason="max_tool_iterations_finalized",
+            )
+        ]
+    )
+    envelope = DelegationEnvelope(
+        parent_task_id="task-parent",
+        parent_session_id="session-root",
+        parent_run_id="run-root",
+        agent=AgentDescriptor(name="researcher", role="research"),
+        task="research the requested topic",
+        node_id="research",
+    )
+
+    result = asyncio.run(LocalAgentRunner(loop).run(envelope, provider_bundle=_bundle(provider)))
+
+    assert result.success is False
+    assert result.completion_status == "failed"
+    assert result.error == "finalized output is a raw tool call"
+
+
+def test_team_node_defaults_to_larger_tool_iteration_budget(tmp_path: Path) -> None:
+    session_manager = SessionManager(tmp_path)
+    captured_kwargs: dict[str, object] = {}
+
+    class CapturingLoop:
+        profile = SimpleNamespace()
+        loader = None
+        is_running = False
+
+        async def process_direct(self, task: str, **kwargs: object) -> SimpleNamespace:
+            captured_kwargs.update(kwargs)
+            session_id = str(kwargs["session_id"])
+            run_id = "run-captured"
+            session_manager.ensure_session(session_id, source="test")
+            return SimpleNamespace(
+                session_id=session_id,
+                run_id=run_id,
+                output_text="done",
+                finish_reason="stop",
+            )
+
+        def boot(self) -> SimpleNamespace:
+            return SimpleNamespace(session_manager=session_manager)
+
+    envelope = DelegationEnvelope(
+        parent_task_id="task-parent",
+        parent_session_id="session-root",
+        parent_run_id="run-root",
+        agent=AgentDescriptor(name="researcher", role="research"),
+        task="research the requested topic",
+        node_id="research",
+    )
+
+    result = asyncio.run(LocalAgentRunner(CapturingLoop()).run(envelope))
+
+    assert result.success is True
+    assert captured_kwargs["max_tool_iterations"] == 100
+
+
 def test_pinned_skill_is_injected_into_delegated_run(tmp_path: Path) -> None:
     _publish_skill(
         tmp_path,