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/beaver/skills/publisher/service.py

@@ -2,6 +2,9 @@
 
 from __future__ import annotations
 
+import shutil
+from pathlib import Path
+
 from beaver.skills.catalog.utils import strip_frontmatter
 from beaver.skills.specs import SkillDraft, SkillReviewState, SkillSpec, SkillSpecStore, SkillStatus, SkillVersion
 from beaver.skills.specs.serialization import canonical_hash, normalize_frontmatter, summarize_skill_content
@@ -44,6 +47,7 @@ class SkillPublisher:
             },
         )
         self.store.write_skill_version(version, content)
+        self._copy_uploaded_supporting_files(draft, next_version)
         self.store.set_current_version(skill_name, next_version)
 
         spec = self.store.get_skill_spec(skill_name)
@@ -169,6 +173,27 @@ class SkillPublisher:
         self.store.update_index("published", published)
         self.store.update_index("disabled", disabled)
 
+    def _copy_uploaded_supporting_files(self, draft: SkillDraft, version: str) -> None:
+        for evidence in draft.evidence_refs:
+            if not isinstance(evidence, dict) or evidence.get("kind") != "upload":
+                continue
+            raw_dir = evidence.get("supporting_upload_dir")
+            if not raw_dir:
+                continue
+            source_root = Path(str(raw_dir))
+            if not source_root.exists() or not source_root.is_dir():
+                continue
+            target_root = self.store.root / draft.skill_name / "versions" / version
+            for source in sorted(source_root.rglob("*")):
+                if not source.is_file() or source.is_symlink():
+                    continue
+                relative = source.relative_to(source_root)
+                if any(part in {"", ".", ".."} for part in relative.parts):
+                    continue
+                target = target_root / relative
+                target.parent.mkdir(parents=True, exist_ok=True)
+                shutil.copyfile(source, target)
+
     def _require_draft(self, skill_name: str, draft_id: str) -> SkillDraft:
         draft = self.store.read_draft(skill_name, draft_id)
         if draft is None: