/new fails to load STDIO MCP and requires /mcp reload

Describe the bug

I'm seeing an issue after upgrading to 1.0.8x. My custom STDIO MCP server is failing to load after a /new. It works fine when loading from Copilot CLI in a fresh session.

Affected version

GitHub Copilot CLI 1.0.83.

Steps to reproduce the behavior

1. In an existing Copilot CLI session, type /new
2. An error will surface:

Failed to connect to MCP server "<insert MCP name here>": MCP server "<insert MCP name here>" connection was cancelled. Execute '/mcp show <insert MCP name here>' to inspect or check the logs

3. Trigger /mcp reload and it works

Expected behavior

/new should not fail to load servers due to a race.

Additional context

No response

まず、既存の Copilot CLI セッションで /new を使って失敗を再現し、次に /mcp reload と比較して報告されたログを調べます。セッションのリセット前後における STDIO MCP 接続のライフサイクルを追跡します。/new でキャンセルや手動の reload を必要とせずにサーバーが読み込まれれば完了です。