fix(mcp): set _preserve_managed_process before finally in cold-start path (#2309)

_ColdStartRetry was caught in _lifecycle_loop_with_retry which set
_preserve_managed_process = True — but by then the finally block inside
_lifecycle_loop had already run and called _cleanup_box_stdio_session(),
stopping the live managed process (return_code=143 SIGTERM). The cold-start
retry then restarted a fresh process, eliminating the warm-up advantage.

Fix: add an explicit except _ColdStartRetry in _lifecycle_loop that sets
_preserve_managed_process = True before re-raising. The finally block then
sees the flag and skips stop_managed_process, leaving the live process
untouched for the next handshake attempt.

Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>

src/langbot/pkg/provider/tools/loaders/mcp.py

@@ -439,6 +439,12 @@ class RuntimeMCPSession:
             else:
                 await self._shutdown_event.wait()
 
+        except _ColdStartRetry:
+            # Cold-start in progress: set the preserve flag BEFORE the finally
+            # block runs so it does not stop the live managed process. The outer
+            # _lifecycle_loop_with_retry will reuse it on the next attempt.
+            self._preserve_managed_process = True
+            raise
         except Exception as e:
             self.status = MCPSessionStatus.ERROR
             self.error_message = str(e)