Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

Some envs are blank, e.g. RBG_ROLE_INDEX.

And some could not be marshaled, e.g. RBG_LWP_LEADER_ADDRESS

root@serving-v2hbfa5wai-rbg-integrate-0-0:/# env | grep ROLE
RBG_ROLE_INSTANCE_NAME=serving-v2hbfa5wai-rbg-integrate-0
RBG_ROLE_INDEX=
RBG_ROLE_NAME=integrate
RBG_LWP_LEADER_ADDRESS=$(RBG_ROLE_INSTANCE_NAME)-0.s-serving-v2hbfa5wai-rbg-integrate.project-infra

Root Cause

• RBG_ROLE_INDEX: hardcoded apps.kubernetes.io/pod-index label, should use
  rbg.workloads.x-k8s.io/role-instance-index for RoleInstanceSet.
• RBG_LWP_LEADER_ADDRESS: env merge logic used a map + sort, which broke
  Kubernetes's sequential $(VAR) resolution order.

Reproduction

any RBG using roleinstance with stateful pattern

Environment

latest 0.7.0 alpha1