feat(app-instance): 集成Beaver后端并更新配置管理

集成新的Beaver后端服务到应用实例中，替换原有的nanobot实现。

主要变更包括：
- 在Dockerfile和环境配置中添加Beaver相关路径和配置变量
- 更新工作目录结构从.nanobot到.beaver
- 实现Beaver引擎加载器，支持配置文件加载和工具组装
- 添加内置工具如ListDirectoryTool、ReadFileTool、SearchFilesTool
- 更新消息处理流程，支持通道适配器和网关模式
- 重构技能系统，支持显式工具提示和嵌入式检索
- 改进错误处理和生命周期管理

此变更使应用实例能够使用统一的Beaver后端进行AI代理运行时管理。

app-instance/backend/beaver/skills/catalog/loader.py

@@ -18,6 +18,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
+import json
 from pathlib import Path
 from typing import Any
 
@@ -111,6 +112,32 @@ class SkillsLoader:
         metadata, _ = parse_frontmatter(content)
         return metadata
 
+    def get_skill_tool_hints(self, name: str) -> list[str]:
+        """读取 skill 显式声明的推荐工具。
+
+        第一版只信任显式 metadata，不从正文里猜：
+        - `tools: read_file, search_files`
+        - `tools: ["read_file", "search_files"]`
+        - YAML-like list:
+          tools:
+            - read_file
+            - search_files
+        - 兼容 metadata JSON blob 里的 `tools`
+        """
+
+        frontmatter = self.get_skill_metadata(name) or {}
+        meta_blob = parse_skill_metadata_blob(frontmatter.get("metadata", ""))
+        names = [
+            *self._coerce_tool_names(frontmatter.get("tools")),
+            *self._coerce_tool_names(meta_blob.get("tools")),
+            *self._coerce_tool_names(meta_blob.get("required_tools")),
+        ]
+        result: list[str] = []
+        for item in names:
+            if item and item not in result:
+                result.append(item)
+        return result
+
     def load_skills_for_context(self, skill_names: list[str]) -> str:
         """加载指定 skills 的正文，并整理成上下文块。"""
 
@@ -253,6 +280,26 @@ class SkillsLoader:
                 result.append(record.name)
         return result
 
+    @staticmethod
+    def _coerce_tool_names(value: Any) -> list[str]:
+        if value is None:
+            return []
+        if isinstance(value, str):
+            raw = value.strip()
+            if not raw:
+                return []
+            if raw.startswith("["):
+                try:
+                    parsed = json.loads(raw)
+                except Exception:
+                    parsed = None
+                if isinstance(parsed, list):
+                    return [str(item).strip() for item in parsed if str(item).strip()]
+            return [item.strip() for item in raw.split(",") if item.strip()]
+        if isinstance(value, (list, tuple, set)):
+            return [str(item).strip() for item in value if str(item).strip()]
+        return []
+
     def _find_record(self, name: str) -> SkillRecord | None:
         for record in self.list_skills(filter_unavailable=False):
             if record.name == name:

app-instance/backend/beaver/skills/catalog/utils.py

@@ -20,7 +20,7 @@ import shutil
 from typing import Any
 
 
-def parse_frontmatter(content: str) -> tuple[dict[str, str], str]:
+def parse_frontmatter(content: str) -> tuple[dict[str, Any], str]:
     """解析 Markdown 文件顶部的极简 frontmatter。
 
     当前先只支持最常见的：
@@ -43,12 +43,36 @@ def parse_frontmatter(content: str) -> tuple[dict[str, str], str]:
     if match is None:
         return {}, content
 
-    metadata: dict[str, str] = {}
-    for line in match.group(1).splitlines():
+    metadata: dict[str, Any] = {}
+    lines = match.group(1).splitlines()
+    index = 0
+    while index < len(lines):
+        line = lines[index]
         if ":" not in line:
+            index += 1
             continue
         key, value = line.split(":", 1)
-        metadata[key.strip()] = value.strip().strip('"\'')
+        key = key.strip()
+        value = value.strip()
+        if not value:
+            items: list[str] = []
+            lookahead = index + 1
+            while lookahead < len(lines):
+                candidate = lines[lookahead]
+                stripped = candidate.strip()
+                if not stripped:
+                    lookahead += 1
+                    continue
+                if not stripped.startswith("- "):
+                    break
+                items.append(stripped[2:].strip().strip('"\''))
+                lookahead += 1
+            if items:
+                metadata[key] = items
+                index = lookahead
+                continue
+        metadata[key] = value.strip('"\'')
+        index += 1
     body = content[match.end():].strip()
     return metadata, body