ci(experimental): GraalPy workers exhaust their heap in the long shards #2713

On main at 57a6c366d, the GraalPy experimental leg loses xdist workers: 8 crashes ("node down: Not properly terminated"). It is non-blocking, so the job stays green with a warning. Every complete run since 16ccc4373 has lost workers, and a25eb0e39 lost none.

• Cause (inferred): each GraalPy process runs with --vm.Xmx2g --vm.XX:+ExitOnOutOfMemoryError. Every worker that died was in one of the four long shards (tests/foundation, tests/protocols/internet, tests/protocols/[a-m]*, tests/protocols), at 2.7–2.9 GiB RSS. Those shards have grown since test: sort the remaining GraalPy-only failures into defects and gates #1963 sized them. There was no kernel or scope OOM (oom_kills=0).
• The crash-attributed tests are victims. All of them pass alone and in earlier GraalPy JUnit artifacts.
• Fix: split those shards in the SHARDS env of the Run unit tests step, keeping tests/project/test_graalpy_shards_1963.py in step. Re-measure the test: sort the remaining GraalPy-only failures into defects and gates #1963 numbers in workflows.rst. The leg took 4510 s against its 6600 s timeout.