Segfault when running numpy in sandbox #6420
Description
What version of Codex is running?
0.56.0
What subscription do you have?
Enterprise
Which model were you using?
No response
What platform is your computer?
Darwin 24.6.0 arm64 arm
What issue are you seeing?
Segfault when importing numpy in the sandbox:
❯ codex debug seatbelt python -c 'import numpy'
❯ echo $?
139
or
OpenAI Codex v0.56.0 (research preview)
--------
workdir: /tmp
model: gpt-5-codex
provider: openai
approval: never
sandbox: workspace-write [workdir, /tmp, $TMPDIR]
reasoning effort: none
reasoning summaries: auto
session id: 019a67ee-bbc5-77a1-bd31-23f22da627b7
--------
user
run python -c "import numpy"
thinking
**Preparing to run shell command**
exec
bash -lc 'python -c "import numpy"' in /tmp exited -1 in 0ms:
execution error: Sandbox(Signal(11))
thinking
**Reporting command failure due to segfault**
codex
Tried `python -c "import numpy"` and it crashed with signal 11 inside the sandbox (likely a segfault in the local Python/Numpy build). Let me know if you want to gather more diagnostics or try a different environment.
tokens used
554
Tried `python -c "import numpy"` and it crashed with signal 11 inside the sandbox (likely a segfault in the local Python/Numpy build). Let me know if you want to gather more diagnostics or try a different environment.
What steps can reproduce the bug?
uv init foobar
cd foobar
uv add "numpy<2"
uv run codex debug seatbelt python -c 'import numpy'
What is the expected behavior?
No response
Additional information
No response