feat: Introduce unified tooling system for plugins and MCP

- Added a new `tooling` module to define a unified model for tool declarations, invocations, and execution results, facilitating compatibility between plugins, legacy actions, and MCP tools.
- Implemented `ToolProvider` interface for various tool providers including built-in tools, MCP tools, and plugin runtime tools.
- Enhanced `MCPManager` and `MCPConnection` to support unified tool invocation and execution results.
- Updated `ComponentRegistry` and related classes to accommodate the new tool specifications and descriptions.
- Refactored existing components to utilize the new tooling system, ensuring backward compatibility with legacy actions.
- Improved error handling and logging for tool invocations across different providers.

src/maisaka/tool_provider.py

@@ -0,0 +1,64 @@
+"""Maisaka 内置工具 Provider。"""
+
+from __future__ import annotations
+
+from collections.abc import Awaitable, Callable
+from typing import Dict, Optional
+
+from src.core.tooling import ToolExecutionContext, ToolExecutionResult, ToolInvocation, ToolProvider, ToolSpec
+
+from .builtin_tools import get_builtin_tool_specs
+
+BuiltinToolHandler = Callable[[ToolInvocation, Optional[ToolExecutionContext]], Awaitable[ToolExecutionResult]]
+
+
+class MaisakaBuiltinToolProvider(ToolProvider):
+    """Maisaka 内置工具提供者。"""
+
+    provider_name = "maisaka_builtin"
+    provider_type = "builtin"
+
+    def __init__(self, handlers: Optional[Dict[str, BuiltinToolHandler]] = None) -> None:
+        """初始化内置工具 Provider。
+
+        Args:
+            handlers: 工具名到异步处理器的映射。
+        """
+
+        self._handlers = dict(handlers or {})
+
+    async def list_tools(self) -> list[ToolSpec]:
+        """列出全部内置工具。"""
+
+        return list(get_builtin_tool_specs())
+
+    async def invoke(
+        self,
+        invocation: ToolInvocation,
+        context: Optional[ToolExecutionContext] = None,
+    ) -> ToolExecutionResult:
+        """执行指定内置工具。
+
+        Args:
+            invocation: 工具调用请求。
+            context: 执行上下文。
+
+        Returns:
+            ToolExecutionResult: 工具执行结果。
+        """
+
+        handler = self._handlers.get(invocation.tool_name)
+        if handler is None:
+            return ToolExecutionResult(
+                tool_name=invocation.tool_name,
+                success=False,
+                error_message=f"未找到内置工具处理器：{invocation.tool_name}",
+            )
+        return await handler(invocation, context)
+
+    async def close(self) -> None:
+        """关闭 Provider。
+
+        内置 Provider 无需释放额外资源。
+        """
+