Codex exec stalled after turn.started

Open 💬 1 comment Opened Jun 16, 2026 by thojanssens

What version of Codex CLI is running?

0.139.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.5 xhigh

What platform is your computer?

Darwin arm64

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

Terminal app

Codex doctor report

What issue are you seeing?

codex exec intermittently stalls after starting a turn. The process stays alive but produces no further stdout/stderr or last-message output until my watchdog kills it (after 15 mins waiting).

I can share the affected session ID privately with an OpenAI employee.

Details:
Codex CLI: codex-cli 0.139.0
OS: Darwin arm64
Mode: codex exec --json --output-last-message …
Approval policy: never
Last observed JSONL output:
{"type":"thread.started","thread_id":"…"}
{"type":"turn.started"}

Expected: the run completes, fails, or emits a diagnosable error.
Actual: no more output after "turn.started"; stderr and last-message remained empty.

What steps can reproduce the bug?

codex exec …

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗