Skip to content

Handle environment manager capacity limits - #7

Draft
zhenyusteven wants to merge 1 commit into
StigLidu:mainfrom
zhenyusteven:codex/env-manager-capacity
Draft

Handle environment manager capacity limits#7
zhenyusteven wants to merge 1 commit into
StigLidu:mainfrom
zhenyusteven:codex/env-manager-capacity

Conversation

@zhenyusteven

Copy link
Copy Markdown

What changed

  • Allow the environment manager and spawned environment servers to bind through SERVER_BIND_HOST while preserving the existing IPv6 default.
  • Return HTTP 503 when environment capacity is exhausted instead of surfacing an unstructured internal error.

Why

Large asynchronous RL rollouts can temporarily consume every configured environment slot. Callers need a retryable capacity response, and some cluster deployments require an explicit bind host.

Impact

Existing deployments retain the :: bind default. Capacity-aware clients can now distinguish temporary resource exhaustion and retry safely.

Validation

  • python3 -m py_compile online_server/online_server/env_instance_manager.py
  • git diff --check

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant