Merge error_details instead of replacing them in _run_execute_with_actor
(formerly _run_execute_with_stub), preserving strategy_decisions_json
stored by run_strategize. On execute retry, _build_decisions now finds
the full decision hierarchy instead of falling back to definition_of_done
parsing.
- Merge error_details on both success and failure paths
- Report type(self._execute_actor).__name__ instead of hardcoded 'stub'
- Rename _run_execute_with_stub to _run_execute_with_actor
- Add 4 Behave scenarios verifying preservation and mode reporting
ISSUES CLOSED: #10874