When a sandbox container crashes (e.g. due to an internal error), the
agent enters a connection-refused loop because AioSandboxProvider.get()
returns a cached but dead sandbox object. Add a liveness check in get()
that detects crashed containers via backend.is_alive() and evicts them
from all caches, allowing ensure_sandbox_initialized() to transparently
recreate a fresh container on the next acquire().
The behavior is controlled by a new config option
(default: true). Set to false to skip health checks and preserve the
old behavior of returning stale cached sandboxes.
Closes#2788
Willem Jiang