Just this week, for the first time, I’ve started to see that Codex CLI outputs Chinese gambling characters in the messages and code. I only noticed it because one of the responses got flagged by OpenAI, and I just saw it again reverting a file where it had written them to it. Is this something I should be concerned about? Is anyone else seeing this?
Thanks for reporting. Please feel free to share the characters and any steps to reproduce the issue.
I’ve only noticed it in passing. I did capture some of the last outputs here, but I do think both times it’s been around the use of apply patch:
ain__\“:\n+ raise SystemExit(main(_import_(\“sy s\”).argv[1:]))\n+\n*** End Patch”}Commentary to=fun ctions.apply_patch 天天中彩票有 json to=functions.apply_p atch av不卡免费播放 ＿老司机 json to=functions.apply_patch ક્ર મ 0 వ్యాఖ్యary to=functions.apply_patch ปมถวายสัตย์ ฯ json to=functions.apply_patch 彩票天天 json to=functi ons.apply_patch ￣奇米影视 json to=functions.apply_patch 天天送彩票 json to=functions.apply_patch संघर्ष to=func tions.apply_patch เงินฟรี json to=functions.apply_p atch ลุ้นบาท qq彩票 json to=functions.apply_patch 天 天 中彩票粤 json to=functions.apply_patch endif }} #!/ usr/b in/env bash
It appears that the AI is not calling the tool correctly, not emitting to the correct channel, or that the high Unicode that is appearing in the emitted strings is causing the tool parser to fail to capture the message for the tool recipient.
- What model are you using?
- Paste the entirety on the forum within a markdown code fence block like this:
```
your log
```
Then text will be shown accurately, and we can see if spaces in the internal function name were actually produced or if they were instead a side-effect of word-wrapping in a log or console.