›_ Codex Issues
Codex Issues / #34399

spawn_agent model allowlist omits gpt-5.6-luna

Resolved 💬 2 comments Opened Jul 20, 2026 by ohyeh Closed Jul 20, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

Codex version

Codex CLI 0.144.6, Codex Desktop on macOS.

What happened

The runtime model catalog exposes gpt-5.6-luna, and the Desktop create_thread / send_message_to_thread schemas also accept it, but the native multi-agent spawn_agent tool rejects the same model:

Unknown model `gpt-5.6-luna` for spawn_agent. Available models: gpt-5.6-sol, gpt-5.6-terra

Reproduction

  1. Confirm the host catalog:
codex debug models | jq -r '.models[].slug'

Key output includes:

gpt-5.6-sol
gpt-5.6-terra
gpt-5.6-luna
  1. In a Codex Desktop task with native collaboration enabled, call spawn_agent with model gpt-5.6-luna and low reasoning.
  2. Observe the allowlist rejection above.

Expected behavior

spawn_agent should accept gpt-5.6-luna when the calling host reports it as available, matching the host model catalog and the other Desktop thread tools. This is useful for low-cost supervision-only sub-agents that mainly execute shell commands, monitor external workers, and summarize progress.

Additional context

gpt-5.6-terra works as a fallback. Using an external codex -m gpt-5.6-luna process is not equivalent because it does not create a native child thread and therefore does not appear in the Codex App Subagents panel.

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 1 month ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #34301
  • #34024

Powered by Codex Action

enzopresbiteris-rgb · 1 month ago

Still reproducible on Windows with the next stable release.

Environment:

  • Codex App: 26.715.9868.0
  • Standalone CLI used by the app via CODEX_CLI_PATH: codex-cli 0.145.0
  • Windows 11 Pro x64, build 26200
  • multi_agent = true
  • multi_agent_v2 = true
  • The app was fully restarted after enabling MultiAgent V2

Reproduction request:

{
  "fork_turns": "none",
  "model": "gpt-5.6-luna",
  "reasoning_effort": "xhigh"
}

The native tool still returns:

Unknown model `gpt-5.6-luna` for spawn_agent. Available models: gpt-5.6-sol, gpt-5.6-terra

The desktop log confirms it is spawning the external 0.145.0 CLI, so this is not caused by the older bundled binary. No child agent is created.

Since this issue is currently closed as completed, could the maintainers please confirm whether Luna is intentionally excluded by the active backend/account catalog, or reopen this if the allowlist fix has not reached 0.145.0?