Unrolling the Codex agent loop
openai.com
Unrolling the Codex agent loop
1–10 of 220 posts
Re: Unrolling the Codex agent loop
#2I guess nothing super surprising or new but still valuable read. I wish it was easier/native to reflect on the loop and/or histories while using agentic coding CLIs. I've found some success with an MCP that let's me query my chat histories, but I have to be very explicit about it's use. Also, like many things, continuous learning would probably solve this.
Re: Unrolling the Codex agent loop
#3thx :)
Re: Unrolling the Codex agent loop
#4One thing that surprised me when diving into the Codex internals was that the reasoning tokens persist during the agent tool call loop, but are discarded after every user turn.
This helps preserve context over many turns, but it can also mean some context is lost between two related user turns.
A strategy that's helped me here, is having the model write progress updates (along with general plans/specs/debug/etc.) to markdown files, acting as a sort of "snapshot" that works across many context windows.
Re: Unrolling the Codex agent loop
#5The best part about this is how the program acts like a human who is learning by doing. It is not trying to be perfect on the first try, it is just trying to make progress by looking at the results. I think this method is going to make computers much more helpful because they can now handle the messy parts of solving a problem.
Re: Unrolling the Codex agent loop
#6One thing that surprised me when diving into the Codex internals was that the reasoning tokens persist during the agent tool call loop, but are discarded after every user turn. This helps preserve context over many turns, but it can also mean some context is lost between two related user turns. A strategy that's helped me here, is having the model write progress updates (along with general plans/specs/debug/etc.) to…
Same here! I think it would be good if this could be made by default by the tooling. I've seen others using SQL for the same and even the proposal for a succinct way of representing this handoff data in the most compact way.
Re: Unrolling the Codex agent loop
#7One thing that surprised me when diving into the Codex internals was that the reasoning tokens persist during the agent tool call loop, but are discarded after every user turn. This helps preserve context over many turns, but it can also mean some context is lost between two related user turns. A strategy that's helped me here, is having the model write progress updates (along with general plans/specs/debug/etc.) to…
I think this explains why I'm not getting the most out of codex, I like to interrupt and respond to things i see in reasoning tokens.
Re: Unrolling the Codex agent loop
#8One thing that surprised me when diving into the Codex internals was that the reasoning tokens persist during the agent tool call loop, but are discarded after every user turn. This helps preserve context over many turns, but it can also mean some context is lost between two related user turns. A strategy that's helped me here, is having the model write progress updates (along with general plans/specs/debug/etc.) to…
That could explain the "churn" when it gets stuck. Do you think it needs to maintain an internal state over time to keep track of longer threads, or are written notes enough to bridge the gap?
Re: Unrolling the Codex agent loop
#9Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while.
However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implying Rust==better). It's performance is quite literally insane, its UX is completely seamless. They even added small nice to haves like ctrl+left/right to skip your cursor to word boundaries.
If you haven't I genuinely think you should give it a try you'll be very surprised. Saw Theo(yc ping labs) talk about how open ai shouldn't have wasted their time optimizing the cli and made a better model or something. I highly disagree after using it.
Re: Unrolling the Codex agent loop
#10Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while. However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implyi…
Same goes for Claude Code. Literally has vim bindings for editing prompts if you want them.