Add lifecycle management for beads-mcp processes (bd-148)

- Register atexit handler to close daemon connections
- Add signal handlers for SIGTERM/SIGINT for graceful shutdown
- Implement cleanup() to close all daemon client connections
- Track daemon clients globally for cleanup
- Add close() method to BdDaemonClient (no-op since connections are per-request)
- Register client on first use via _get_client()
- Add comprehensive lifecycle tests

This prevents MCP server processes from accumulating without cleanup.
Each tool invocation will now properly clean up on exit.

Amp-Thread-ID: https://ampcode.com/threads/T-05d76b8e-dac9-472b-bfd0-afe10e3457cd
Co-authored-by: Amp <amp@ampcode.com>

integrations/beads-mcp/src/beads_mcp/bd_daemon_client.py

@@ -424,3 +424,14 @@ class BdDaemonClient(BdClientBase):
             return True
         except (DaemonNotRunningError, DaemonConnectionError, DaemonError):
             return False
+
+    def close(self) -> None:
+        """Close daemon client connections and cleanup resources.
+        
+        This is called during MCP server shutdown to ensure clean termination.
+        Since we use asyncio.open_unix_connection which closes per-request,
+        there's no persistent connection to close. This method is a no-op
+        but exists for API consistency.
+        """
+        # No persistent connections to close - each request opens/closes its own
+        pass