openai / openai/codex

Infinite loop inspecting agent status and missing functions.exec tool with GPT-5.6 model

Open
#39,004 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

What version of Codex CLI is running?

0.147

What subscription do you have?

Pay-as-you-go

Which model were you using?

5.6 sol

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?

The agent gets stuck in an infinite loop checking for "No agents completed yet" and investigating "functions.exec" when using the gpt-5.6 model. The task never completes and no error message is returned.

What steps can reproduce the bug?

• Inspecting process status and files
• Checking process completion status
• Finished waiting
└ No agents completed yet
• Planning process verification
• Investigating missing functions.exec tool
• Finished waiting
└ No agents completed yet
• Investigating missing exec tool usage
• Verifying hidden functions.exec availability
• Testing direct functions.exec usage
• Finished waiting
└ No agents completed yet
• Investigating dynamic availability of functions.exec
• Reimplementing missing functions.exec definition
• Verifying dynamic tool execution

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

Reproduce the behavior in Codex CLI 0.147 with the gpt-5.6 model, following the reported agent-status and functions.exec sequence. Trace why the process remains in the “No agents completed yet” loop; done means the task completes or returns an error instead of looping indefinitely.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
ai, cli
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.