My only concern with Codex is that it's not possible to delete tasks.

This is a privacy and security risk. Your code diffs and prompts are there (seemingly) forever. Best you can do is "archive" them, which is a fancy word for "put it somewhere else so it doesn't clutter the main page".

▲

Leynos 21 hours ago | parent | next [-]

Terragon is an alternative (hosts Claude and Codex using your OpenAI and Anthropic subscriptions, and also supports Google and Amp) that provides this functionality.

I use it because it works out cheaper than Codex Cloud and gives you greater flexibility. Although it doesn't have 5.2-codex yet.

▲

tgtweak 21 hours ago | parent [-]

Yes but if it's not getting removed at the origin... it's not fixing the actual issue of the context/conversation surviving past an explicit "delete" request. Also let's not forget that anyone proxying LLMs is also man in the middle to any code that goes up/down.

	▲	Leynos 20 hours ago \| parent [-]
		79a6ed87’s comment applies to Codex cloud, not the codex CLI, which is what Terragon is using.

▲

sunaookami 20 hours ago | parent | prev | next [-]

Are you talking about Codex Web? This is different from Codex CLI.

▲

moralestapia 21 hours ago | parent | prev | next [-]

`rm -rf ~/.codex/archived_sessions` does the trick

▲

79a6ed87 21 hours ago | parent [-]

Interesting. Where do I run that?

▲

zenburnmyface 19 hours ago | parent | next [-]

This is A+ satire

▲

moralestapia 20 hours ago | parent | prev [-]

Uhm ... I assumed you were on Linux or OS X, if that's the case just open a terminal and paste that, I swear it's not malicious code.

Unsure where that could be if you're using Windows.

You know what would be fun to try? Give Codex full access and then ask it to delete that folder, lol.

	▲	rolymath 9 hours ago \| parent [-]
		I think he's joking I.e that command won't delete what's on the openai servers. But I could be wrong.

▲

throwuxiytayq 21 hours ago | parent | prev [-]

It's weird, suspicious, and plain annoying. I like the the tool and my tests have shown it to be very powerful (if a bit rough and buggy), but this is ridiculous - I won't use it for any real world projects until this is fixed.

Then again, I wouldn't put much trust into OpenAI's handling of information either way.