Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Unrolling the Codex agent loop

openai.com

Post reply on HN
Print view View original

81–90 of 220 posts

Re: Unrolling the Codex agent loop

#81

Post by westoncb »

swalsh wrote: post #80
westoncb wrote: post #57

Interesting that compaction is done using an encrypted message that "preserves the model's latent understanding of the original conversation": > Since then, the Responses API has evolved to support a special /responses/compact endpoint (opens in a new window) that performs compaction more efficiently. It returns a list of items (opens in a new window) that can be used in place of the previous input to continue the co…

Is it possible to use the compactor endpoint independently? I have my own agent loop i maintain for my domain specific use case. We built a compaction system, but I imagine this is better performance.

I would guess you can if you're using their Responses api for inference within your agent.

Re: Unrolling the Codex agent loop

#82

Post by SafeDusk »

These can also be observed through OTEL telemetries.

I use headless codex exec a lot, but struggles with its built-in telemetry support, which is insufficient for debugging and optimization.

Thus I made codex-plus (https://github.com/aperoc/codex-plus) for myself which provides a CLI entry point that mirrors the codex exec interface but is implemented on top of the TypeScript SDK (@openai/codex-sdk).

It exports the full session log to a remote OpenTelemetry collector after each run which can then be debugged and optimized through codex-plus-log-viewer.

Re: Unrolling the Codex agent loop

#83

Post by __jl__ »

swalsh wrote: post #80
westoncb wrote: post #57

Interesting that compaction is done using an encrypted message that "preserves the model's latent understanding of the original conversation": > Since then, the Responses API has evolved to support a special /responses/compact endpoint (opens in a new window) that performs compaction more efficiently. It returns a list of items (opens in a new window) that can be used in place of the previous input to continue the co…

Is it possible to use the compactor endpoint independently? I have my own agent loop i maintain for my domain specific use case. We built a compaction system, but I imagine this is better performance.

Yes you can and I really like it as a feature. But it ties you to OpenAI…

Re: Unrolling the Codex agent loop

#84

Post by jswny »

westoncb wrote: post #57

Interesting that compaction is done using an encrypted message that "preserves the model's latent understanding of the original conversation": > Since then, the Responses API has evolved to support a special /responses/compact endpoint (opens in a new window) that performs compaction more efficiently. It returns a list of items (opens in a new window) that can be used in place of the previous input to continue the co…

How does this work for other models that aren’t OpenAI models

Re: Unrolling the Codex agent loop

#85

Post by fragmede »

atonse wrote: post #68
redox99 wrote: post #60

Earlier quoted context omitted.

For some reason a lot of people are unaware that Claude Code is proprietary.

Probably because it doesn’t matter most of the time?

If the software is, say, Audacity, who's target market isn't specifically software developers, sure, but seeing as how Claude code's target market has a lot of people who can read code and write software (some of them for a living!) it becomes material. Especially when CC has numerous bugs that have gone unaddressed for months that people in their target market could fix. I mean, I have my own beliefs as to why they haven't opened it, but at the same time, it's frustrating hitting the same bugs day after day.

Re: Unrolling the Codex agent loop

#86

Post by westoncb »

jswny wrote: post #84
westoncb wrote: post #57

Interesting that compaction is done using an encrypted message that "preserves the model's latent understanding of the original conversation": > Since then, the Responses API has evolved to support a special /responses/compact endpoint (opens in a new window) that performs compaction more efficiently. It returns a list of items (opens in a new window) that can be used in place of the previous input to continue the co…

How does this work for other models that aren’t OpenAI models

It wouldn’t work for other models if it’s encoded in a latent representation of their own models.

Re: Unrolling the Codex agent loop

#87

Post by stavros »

frumplestlatz wrote: post #62
postalcoder wrote: post #56

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

At this point I just assume Claude Code isn't OSS out of embarrassment for how poor the code actually is. I've got a $200/mo claude subscription I'm about to cancel out of frustration with just how consistently broken, slow, and annoying to use the claude CLI is.

OpenCode is amazing, though.

Re: Unrolling the Codex agent loop

#88

Post by fragmede »

mi_lk wrote: post #71
causalmodels wrote: post #66

Earlier quoted context omitted.

Yeah this has always seemed very silly. It is trivial to use claude code to reverse engineer itself.

looks like it's trivial to you because I don't know how to

If only there were some sort of artificial intelligence that could be asked about asking it to look at the minified source code of some application.

Sometimes prompt engineering is too ridiculous a term for me to believe there's anything to it, other times it does seem there is something to knowing how to ask the AI juuuust the right questions.

Re: Unrolling the Codex agent loop

#89

Post by stavros »

redox99 wrote: post #60
postalcoder wrote: post #56

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

For some reason a lot of people are unaware that Claude Code is proprietary.

Can't really fault them when this exists:

https://github.com/anthropics/claude-code

Re: Unrolling the Codex agent loop

#90

Post by bad_haircut72 »

stavros wrote: post #89
redox99 wrote: post #60

Earlier quoted context omitted.

For some reason a lot of people are unaware that Claude Code is proprietary.

Can't really fault them when this exists: https://github.com/anthropics/claude-code

What even is this repo? Its very deceptive
Post reply on HN