Empty explorer.toml subagent definition file triggers bug and causes explorer agent to ignore model parameter #16893

What version of Codex CLI is running?

codex-cli 0.118.0

What subscription do you have?

ChatGPT Pro

Which model were you using?

gpt-5.4

What platform is your computer?

Darwin 24.6.0 arm64 arm

What terminal emulator and version are you using (if applicable)?

Ghostty

What issue are you seeing?

When launching subagents with a specific model selection request, the explorer agent ignores the model selection request and launches with the model that was selected when codex cli is launched.

This is due to the empty explorer.toml file, triggering a bug. Other two agents do not have toml files, so the bug is not triggered when these agents are launched.

What steps can reproduce the bug?

Request codex to
Launch three agents, one for each type with a dummy request (read only). Launch them all with gpt-5.4-mini high reasoning.
You will get 2 agents respecting the model selection, but explorer ignores it due to the bug.

• Using the requested setup now: I’ll spawn three subagents in parallel (default, explorer, worker), each with a read-only dummy task, all on gpt-5.4-mini with high reasoning.

• Spawned Bohr [default] (gpt-5.4-mini high)
  └ Dummy read-only task: inspect repository root and report the first 10 top-level entries. Do not modify any files or run destructive commands.

• Spawned Tesla [explorer] (gpt-5.3-codex medium)
  └ Dummy read-only task: find AGENTS.md files in this workspace and return their paths only. Read-only; do not modify files.

• Spawned Pasteur [worker] (gpt-5.4-mini high)
  └ Dummy read-only task: run a safe read-only check (`git status --short`) and report output summary. Do not edit files, stage changes, or run destructive comma...

What is the expected behavior?

Agents should respect the model selection passed on with the request.

Additional information

No response