fix(api): Fix potential thread leak in MCP `BaseSession` (#22169)
The `BaseSession` class in the `core/mcp/session` package uses `ThreadPoolExecutor`
to run the receive loop but fails to properly clean up the executor and receiver
future, leading to potential thread leaks.
This PR addresses this issue by:
- Initializing `_executor` and `_receiver_future` attributes to `None` for proper cleanup checks
- Adding graceful shutdown with a 5-second timeout in the `__exit__` method
- Ensuring the ThreadPoolExecutor is properly shut down to prevent resource leaks
This fix prevents memory leaks and hanging threads in long-running scenarios where
multiple MCP sessions are created and destroyed.
Signed-off-by: neatguycoding <15627489+NeatGuyCoding@users.noreply.github.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
willzhao
Will
crazywoola
Asuka Minato
NeatGuyCoding
Novice