Sessions just broke all the time for me. The one time I dug into it, it ended up being a known issue where if codex returned over 10k characters for a turn it breaks the session. Because docker agent does not use protocols like ACP, instead trying to parse Codex's internal state in a brittle manner.

I tried not to do anything too crazy, but even use using an API key in the docker agent natively was getting me sessions that would hang and couldn't be recovered.

▲

aheritier an hour ago | parent | next [-]

In your use case you wanted to control codex from docker agent thus you used our harness integration ( https://docker.github.io/docker-agent/features/harnesses/ ). It was not codex calling docker agent which should work with ACP ( https://docker.github.io/docker-agent/features/acp/ ). We could effectively look at using ACP from docker-agent to control others harnesses if it's useful.

▲

dgageot 2 hours ago | parent | prev [-]

Combination with Codex is indeed not the most common use case around us. I'll see what can be improved. Sorry that it broke your workflow!

▲

nujabe 2 hours ago | parent [-]

How is not using it with the most popular coding agent not a common use case?

	▲	girvo an hour ago \| parent [-]
		Not the most common use case around them: likely meaning that the Codex harness isn’t used that often internally at Docker, is what I would surmise, at least that is how I read it. I work at another big tech company, and up until recently that would’ve been true for us as well (but it’s changed now, we partnered with OpenAI)