Introduce typed error classes with metadata

Summary

Replace generic exceptions with SDK-native error classes that include useful metadata like fault attribution, retryability, and HTTP details.

Problem

The SDK currently raises generic exceptions from various layers (httpx, anyio, task groups) with no context about:

• Whether the error is retryable
• Who is at fault (client, server, network, protocol violation)
• HTTP status codes and response bodies (often discarded)

This makes it hard for users to build robust error handling.

Goal

A hierarchy of typed errors like:

• McpError (base) with fault, is_retryable, http_status_code, response_body
• McpTransportError for connection/network issues
• McpProtocolError for invalid JSON-RPC responses
• McpAuthError for 401/403 responses

_{AI Disclaimer}

首先追蹤 SDK 目前在哪些位置暴露來自 httpx、anyio 和工作群組的泛型例外。定義提議的 McpError 階層結構之範圍與中繼資料需求，包括錯誤歸因、可重試性、HTTP 狀態碼及回應本文。當設計已確定，且受影響的錯誤路徑一致地暴露具型別的 SDK 原生錯誤時，即表示完成。