Error running remote compact task: timeout waiting for child process to exit #17802

What version of Codex CLI is running?

0.120.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.4

What platform is your computer?

Linux 6.17.0-20-generic x86_64 x86_64

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

Ghostty & t3code

What issue are you seeing?

Once thread is about to compact for its first time it gets errored. Can't run /compact, /feedback. Sometimes it goes through tho, but not very often.

What steps can reproduce the bug?

Fill the context to the top.

What is the expected behavior?

Compact.

Additional information

Codex said:
The failing turn shows a large Neon MCP doc fetch, not a ctx7 CLI/plugin call:

• The last big payload before compaction was server":"Neon","tool":"get_doc_resource" for docs/auth/production-checklist.md at /home/kox/.t3/userdata/logs/provider/aa59955c-ee49-4b6d-8a39-07ae0234c689.log:3006.
• Compaction started immediately after at /home/kox/.t3/userdata/logs/provider/aa59955c-ee49-4b6d-8a39-07ae0234c689.log:3007.
• Then Codex failed with compact_error=timeout waiting for child process to exit at /home/kox/.t3/userdata/logs/provider/aa59955c-
  ee49-4b6d-8a39-07ae0234c689.log:3008.

So the mechanism is:

• Large tool output gets added to the thread’s model-visible history.
• Codex notices the thread is getting too large.
• Codex runs internal contextCompaction.
• That internal compaction worker times out.