openai / openai/codex

[Bug] MultiAgentV2 developer instruction incorrectly forbids model/effort overrides with fork_turns="all"

Open
#43,888 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI subagent
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

0.153.4

What subscription do you have?

Pro

Which model were you using?

No response

What platform is your computer?

No response

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

No response

Codex doctor report

What issue are you seeing?

MultiAgentV2 injects an outdated developer instruction saying that full-history forks (fork_turns: "all") cannot override model or reasoning_effort.

However, merged PR #33631 changed the implementation to support model/reasoning overrides for full-history forks while preserving the parent context. The developer instruction was not updated accordingly.

What steps can reproduce the bug?

Using Codex CLI 0.153.4 with MultiAgentV2, ask Codex to spawn a full-history agent with a different model:

{"fork_turns":"all","model":""}

Codex may refuse because the injected developer instruction says this is unsupported, even though the current implementation supports it.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the MultiAgentV2 developer instruction that describes fork_turns="all", then compare it with the implementation change in PR #33631. Update the instruction so full-history forks can override model and reasoning_effort, and verify that the reproduced CLI request is no longer refused.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
ai-infra-agents, cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.