feat(tasks): add cluster:gpu task and wire e2e:gpu to use it

[elezar]

Summary

Adds a cluster:gpu mise task that bootstraps the cluster with NVIDIA GPU passthrough enabled (--gpu flag), and updates e2e:python:gpu to depend on it instead of the plain cluster task. Also updates gpu_sandbox_spec in the e2e conftest to default to an empty image string, deferring image resolution to the server.

Related Issue

Changes

• tasks/cluster.toml: add cluster:gpu task with CLUSTER_GPU=1 env var
• tasks/scripts/cluster-bootstrap.sh: pass --gpu to openshell gateway start when CLUSTER_GPU=1
• tasks/test.toml: wire e2e:python:gpu to depend on cluster:gpu instead of cluster
• e2e/python/conftest.py: default GPU sandbox image to "" so the server resolves the configured default; allow override via OPENSHELL_E2E_GPU_IMAGE

Testing

• mise run pre-commit passes
• Unit tests added/updated (not applicable)
• E2E tests added/updated (if applicable)

Checklist

• Follows Conventional Commits
• Commits are signed off (DCO)
• Architecture docs updated (if applicable)

[pimlock]

Thank you, this is going to be very handy for GPU cluster dev.

Could you please replace the separate cluster:gpu task with an env var?

[pimlock]

Overall, we prefer not adding new tasks, unless really necessary. In this case, we could drop the extra task and add env var in here directly (this is supported by mise).

Suggested change

	depends = ["python:proto", "cluster:gpu"]
	depends = ["python:proto", "CLUSTER_GPU=1 cluster"]

[pimlock]

We can remove this as a separate task and use the env var instead.