feat(engine): 添加MCP连接管理和工具集成功能

- 集成MCP连接管理器，支持MCP服务器连接
- 添加多种内置工具：ClarifyTool、CronTool、DelegateTool、ExecuteCodeTool、
  PatchFileTool、ProcessTool、SendMessageTool、SpawnTool、TerminalTool、
  TodoTool、WebFetchTool、WebSearchTool、WriteFileTool等
- 实现工具注册和装配功能
- 添加技能选择上下文参数
- 支持思考模式控制参数thinking_enabled

feat(coordinator): 重构任务执行计划器参数命名

- 将learning_candidate_enabled重命名为allow_candidate_generation
- 更新TeamGraphScheduler中的参数传递
- 修改LocalAgentRunner中的相关参数处理
- 更新README文档中的相应描述

refactor(context): 标准化工具调用参数格式

- 添加_json导入用于参数序列化
- 实现_provider_tool_calls方法标准化OpenAI兼容的工具调用载荷
- 修复工具调用中参数非字符串类型的序列化问题

refactor(session): 优化消息历史记录过滤逻辑

- 修改get_messages_as_conversation为基于运行状态过滤消息
- 排除未完成、失败或错误结束的运行记录
- 改进对话历史的可见性控制机制

fix(store): 修复FTS索引重建逻辑

- 添加异常处理防止FTS索引创建失败
- 实现_rebuild_fts_index方法重新构建全文搜索索引
- 优化索引触发器和表的维护流程

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

@@ -53,7 +53,8 @@ def test_process_projection_maps_task_team_events(tmp_path: Path) -> None:
                     "node_id": "research",
                     "skill_query": "research workflow",
                     "selected_skill_names": ["research-workflow"],
-                    "generated_skill_draft_id": None,
+                    "ephemeral_guidance_id": None,
+                    "ephemeral_guidance_name": None,
                     "ephemeral_used": False,
                     "reason": "matched published skill",
                 }
@@ -80,7 +81,8 @@ def test_process_projection_maps_task_team_events(tmp_path: Path) -> None:
                     "skill_query": "research workflow",
                     "selected_skill_names": ["research-workflow"],
                     "ephemeral_skill_names": [],
-                    "generated_skill_draft_id": None,
+                    "ephemeral_guidance_id": None,
+                    "ephemeral_guidance_name": None,
                     "ephemeral_used": False,
                     "finish_reason": "stop",
                 }
@@ -118,5 +120,83 @@ def test_process_projection_maps_task_team_events(tmp_path: Path) -> None:
     sub_run = next(run for run in projection["runs"] if run["run_id"] == "sub-run")
     assert sub_run["metadata"]["selected_skill_names"] == ["research-workflow"]
     assert sub_run["metadata"]["skill_query"] == "research workflow"
+    assert sub_run["metadata"]["ephemeral_guidance_id"] is None
     assert any(event["actor_name"] == "Validator" for event in projection["events"])
     assert any(run["session_id"] == "web:test" for run in projection["runs"])
+
+
+def test_process_projection_exposes_ephemeral_guidance_artifacts(tmp_path: Path) -> None:
+    session = SessionManager(tmp_path)
+    run_store = RunMemoryStore(tmp_path / "memory" / "runs")
+    run_store.append_run_record(
+        RunRecord(
+            run_id="sub-run",
+            session_id="sub-session",
+            task_id="task-1",
+            attempt_index=1,
+            task_text="sub task",
+            started_at="2026-01-01T00:00:01+00:00",
+            ended_at="2026-01-01T00:00:02+00:00",
+            success=True,
+            finish_reason="stop",
+        )
+    )
+    session.append_message(
+        "web:test",
+        role="system",
+        event_type="task_execution_planned",
+        event_payload={
+            "task_id": "task-1",
+            "attempt_index": 1,
+            "plan_mode": "team",
+            "strategy": "sequence",
+            "node_ids": ["research"],
+            "ephemeral_guidance_ids": ["eg_123"],
+            "skill_resolution_report": [
+                {
+                    "node_id": "research",
+                    "skill_query": "research workflow",
+                    "selected_skill_names": [],
+                    "ephemeral_guidance_id": "eg_123",
+                    "ephemeral_guidance_name": "research-workflow",
+                    "ephemeral_used": True,
+                    "reason": "generated ephemeral guidance",
+                }
+            ],
+        },
+        context_visible=False,
+    )
+    session.append_message(
+        "web:test",
+        role="system",
+        event_type="task_team_run_completed",
+        event_payload={
+            "task_id": "task-1",
+            "attempt_index": 1,
+            "team_success": True,
+            "team_run_ids": ["sub-run"],
+            "node_results": [
+                {
+                    "node_id": "research",
+                    "success": True,
+                    "output_text": "evidence",
+                    "run_id": "sub-run",
+                    "skill_query": "research workflow",
+                    "selected_skill_names": [],
+                    "ephemeral_skill_names": ["ephemeral:research-workflow"],
+                    "ephemeral_guidance_id": "eg_123",
+                    "ephemeral_guidance_name": "research-workflow",
+                    "ephemeral_used": True,
+                    "finish_reason": "stop",
+                }
+            ],
+        },
+        context_visible=False,
+    )
+
+    projection = SessionProcessProjector(session, run_store).project("web:test")
+
+    sub_run = next(run for run in projection["runs"] if run["run_id"] == "sub-run")
+    assert sub_run["metadata"]["ephemeral_guidance_id"] == "eg_123"
+    assert projection["artifacts"][0]["artifact_id"] == "sub-run:ephemeral-guidance:eg_123"
+    assert projection["artifacts"][0]["metadata"]["ephemeral_guidance_name"] == "research-workflow"