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_process_projection.py

@@ -205,6 +205,7 @@ def test_process_projection_maps_failed_task_team_events(tmp_path: Path) -> None
 
     team_event = next(event for event in projection["events"] if event["kind"] == "agent_team_created")
     assert team_event["status"] == "error"
+    assert team_event["text"] == "Team 执行未完成 / 子节点失败"
     assert team_event["metadata"]["timeline_type"] == "agent_team"
     assert team_event["metadata"]["team_run_ids"] == ["failed-sub-run"]
 
@@ -297,6 +298,101 @@ def test_process_projection_emits_skill_card_from_main_run_receipts(tmp_path: Pa
     assert skill_events
     assert skill_events[0]["metadata"]["timeline_type"] == "skill"
     assert skill_events[0]["metadata"]["skill_names"] == ["web-operation"]
+    assert skill_events[0]["created_at"] == "2026-01-01T00:00:03+00:00"
+
+
+def test_process_projection_prefers_skill_activation_snapshot_over_synthesis_fallback(tmp_path: Path) -> None:
+    session = SessionManager(tmp_path)
+    run_store = RunMemoryStore(tmp_path / "memory" / "runs")
+    run_store.append_run_record(
+        RunRecord(
+            run_id="main-run",
+            session_id="web:test",
+            task_id="task-1",
+            attempt_index=1,
+            task_text="main task",
+            started_at="2026-01-01T00:00:03+00:00",
+            ended_at="2026-01-01T00:00:04+00:00",
+            success=True,
+            finish_reason="stop",
+            activated_skills=[
+                SkillActivationReceipt(
+                    run_id="main-run",
+                    session_id="web:test",
+                    skill_name="web-operation",
+                    skill_version="1",
+                    content_hash="hash",
+                    activated_at="2026-01-01T00:00:03+00:00",
+                    activation_reason="Needs live web lookup.",
+                )
+            ],
+        )
+    )
+    session.append_message(
+        "web:test",
+        role="system",
+        event_type="task_execution_planned",
+        event_payload={
+            "task_id": "task-1",
+            "attempt_index": 1,
+            "plan_mode": "single",
+            "strategy": "single",
+            "selected_skill_names": [],
+        },
+        context_visible=False,
+    )
+    session.append_message(
+        "web:test",
+        run_id="main-run",
+        role="system",
+        event_type="skill_activation_snapshotted",
+        event_payload={
+            "task_id": "task-1",
+            "attempt_index": 1,
+            "receipts": [
+                {
+                    "run_id": "main-run",
+                    "session_id": "web:test",
+                    "skill_name": "web-operation",
+                    "skill_version": "1",
+                    "content_hash": "hash",
+                    "activated_at": "2026-01-01T00:00:03+00:00",
+                    "activation_reason": "Needs live web lookup.",
+                }
+            ],
+        },
+        context_visible=False,
+    )
+    session.append_message(
+        "web:test",
+        run_id="main-run",
+        role="assistant",
+        event_type="assistant_message_added",
+        event_payload={"task_id": "task-1", "attempt_index": 1},
+        content="Searching",
+        tool_calls=[{"id": "call-1", "name": "web_fetch", "arguments": {"url": "https://example.com"}}],
+        context_visible=False,
+    )
+    session.append_message(
+        "web:test",
+        role="system",
+        event_type="task_synthesis_completed",
+        event_payload={"task_id": "task-1", "attempt_index": 1, "main_run_id": "main-run"},
+        context_visible=False,
+    )
+
+    projection = SessionProcessProjector(session, run_store).project("web:test")
+
+    skill_events = [
+        event
+        for event in projection["events"]
+        if event["kind"] == "skill_selected" and event["run_id"] == "main-run"
+    ]
+    assert len(skill_events) == 1
+    assert skill_events[0]["event_id"].endswith(":skill-activation")
+    assert skill_events[0]["created_at"] == "2026-01-01T00:00:03+00:00"
+    tool_event = next(event for event in projection["events"] if event["kind"] == "tool_call_started")
+    assert projection["events"].index(skill_events[0]) < projection["events"].index(tool_event)
 
 
 def test_process_projection_emits_tool_cards_from_run_messages(tmp_path: Path) -> None: