chengyongru 4fad19dc17 fix: use sequential MCP server connections to prevent CPU spin
asyncio.create_task in connect_mcp_servers creates child tasks for
each MCP server, but close_mcp calls stack.aclose() from the main
task. anyio CancelScope requires enter/exit in the same task, so the
cross-task exit raises RuntimeError which gets silently caught. The
orphaned cancel scope keeps retrying via call_soon on every event
loop tick, consuming 100% CPU.

Fix: remove create_task/gather and connect servers sequentially in the
caller task. MCP servers are typically 1-2, so parallel connection
provides negligible benefit while introducing the cancel scope hazard.

Closes #3638
2026-05-06 21:18:51 +08:00
..
2026-04-25 15:46:47 +00:00
2026-04-30 13:45:40 +08:00