I 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.
One 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.
Sonnet has the same behavior: drops thinking on user message. Curiously in the latest Opus they have removed this behavior and all thinking tokens are preserved.
I think it might be a good decision though, as it might keep the context aligned with what the user sees.
If the reasoning tokens where persisted, I imagine it would be possible to build up more and more context that's invisible to the user and in the worst case, the model's and the user's "understanding" of the chat might diverge.
E.g. image a chat where the user just wants to make some small changes. The model asks whether it should also add test cases. The user declines and tells the model to not ask about it again.
The user asks for some more changes - however, invisibly to the user, the model keeps "thinking" about test cases, but never telling outside of reasoning blocks.
So suddenly, from the model's perspective, a lot of the context is about test cases, while from the user's POV, it was only one irrelevant question at the beginning.
The 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.
Has 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.
I asked Claude to summarize the article and it was blocked haha. Fortunately, I have the Claude plugin in chrome installed and it used the plugin to read the contents of the page.
What I really want from Codex is checkpoints ala Copilot. There are a couple of issues [0][1] opened about on GitHub, but it doesn't seem a priority for the team.
I use 2 cli - Codex and Amp. Almost every time I need a quick change, Amp finishes the task in the time it takes Codex to build context. I think it’s got a lot to do with the system prompt and a the “read loop” as well, amp would read multiple files in one go and get to the task, but codex would crawl the files almost one by one. Anyone noticed this?
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.
This came as a big surprise to me last year. I remember they announced that Codex CLI is opensource, and the codex-rs [0] from TypeScript to Rust, with the entire CLI now open source. This is a big deal and very useful for anyone wanting to learn how coding agents work, especially coming from a major lab like OpenAI. I've also contributed some improvements to their CLI a while ago and have been following their releases and PRs to broaden my knowledge.
Is it just a frontend CLI calling remote external logic for the bulk of operations, or does it come with everything needed to run lovely offline? Does it provide weights under FLOW license? Does it document the whole build process and how to redo and go further on your own?
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 conversation while freeing up the context window. This list includes a special type=compaction item with an opaque encrypted_content item that preserves the model’s latent understanding of the original conversation. Now, Codex automatically uses this endpoint to compact the conversation when the auto_compact_limit (opens in a new window) is exceeded.
I like it but wonder why it seems so slow compared to the chatgpt web interface. I still find myself more productive copying and pasting from chat much of the time. You get virtually instant feedback, and it feels far more natural when you're tossing around ideas, seeing what different approaches look like, trying to understand the details, etc. Going back to codex feels like you're waiting a lot longer for it to do the wrong thing anyway, so the feedback cycle is way slower and more frustrating. Specifically I hate when I ask a question, and it goes and starts editing code, which is pretty frequent. That said, it's great when it works. I just hope that someday it'll be as easy and snappy to chat with as the web interface, but still able to perform local tasks.
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.
The "Listen to article" media player at the top of the post -- was super quick to load on mobile but took two attempts and a page refresh to load on desktop.
If I want to listen as well as read the article ... the media player scrolls out of view along with the article title as we scroll down ..leaving us with no way to control (pause/play) the audio if needed.
There are no playback controls other than pause and speed selector. So we cannot seek or skip forward/backward if we miss a sentence. the time display on the media player is also minimal. Wish these were a more accessible standardized feature set available on demand and not limited by what the web designer of each site decides.
I asked "Claude on Chrome" extension to fix the media player to the top. It took 2 attempts to get it right. (It was using Haiku by default -- may be a larger model was needed for this task). I think there is scope to create a standard library for such client side tweaks to web pages -- sort of like greasemonkey user scripts but at a slightly higher level of abstraction with natural language prompts.
Codex is extremely bad to the point it is almost useless.
Claude Code is very effective. Opus is a solid model and claude very reliably solves problems and is generally efficient and doesn't get stuck in weird loops or go off in insane tangents too often. You can be very very efficient with claude code.
Gemini-cli is quite good. If you set `--model gemini-3-pro-preview` it is quite usable, but the flash model is absolute trash. Overall gemini-3-pro-preview is 'smarter' than opus, but the tooling here is not as good as claude code so it tends to get stuck in loops, or think for 5 minutes, or do weird extreme stuff. When Gemini is on point it is very very good, but it is inconsistent and likely to mess up so much that it's not as productive to use as claude.
Codex is trash. It is slow, tends to fail to solve problems, gets stuck in weird places, and sometimes has to puzzle on something simple for 15 minutes. The codex models are poor, and forcing the 5.2 model is expensive, and even then the tooling is incredibly bad and tends to just fail a lot. I check in to see if codex is any good from time to time and every time it is laughably bad compared to the other two.
I completely agree. I use the Codex for complex, hard-to-handle problems and use OpenCode alongside other models for development tasks. The Codex handles things quite well, including how it handles hooks, memory, etc.
Regarding the user instruction aggregation process in the agent loop, I'm curious how you manage context retention in multi-turn interactions. Have you explored any techniques for dynamically adjusting the context based on the evolving user requirements?
33 comments
[ 3.6 ms ] story [ 56.0 ms ] threadThis 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.
If the reasoning tokens where persisted, I imagine it would be possible to build up more and more context that's invisible to the user and in the worst case, the model's and the user's "understanding" of the chat might diverge.
E.g. image a chat where the user just wants to make some small changes. The model asks whether it should also add test cases. The user declines and tells the model to not ask about it again.
The user asks for some more changes - however, invisibly to the user, the model keeps "thinking" about test cases, but never telling outside of reasoning blocks.
So suddenly, from the model's perspective, a lot of the context is about test cases, while from the user's POV, it was only one irrelevant question at the beginning.
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.
This is the biggest UX killer，unfortunately
[0] https://github.com/openai/codex/issues/2788
[1] https://github.com/openai/codex/issues/3585
Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs.
https://github.com/openai/codex
[0] https://github.com/openai/codex/tree/main/codex-rs
> 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 conversation while freeing up the context window. This list includes a special type=compaction item with an opaque encrypted_content item that preserves the model’s latent understanding of the original conversation. Now, Codex automatically uses this endpoint to compact the conversation when the auto_compact_limit (opens in a new window) is exceeded.
Or am I not understanding this right?
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.
The "Listen to article" media player at the top of the post -- was super quick to load on mobile but took two attempts and a page refresh to load on desktop.
If I want to listen as well as read the article ... the media player scrolls out of view along with the article title as we scroll down ..leaving us with no way to control (pause/play) the audio if needed.
There are no playback controls other than pause and speed selector. So we cannot seek or skip forward/backward if we miss a sentence. the time display on the media player is also minimal. Wish these were a more accessible standardized feature set available on demand and not limited by what the web designer of each site decides.
I asked "Claude on Chrome" extension to fix the media player to the top. It took 2 attempts to get it right. (It was using Haiku by default -- may be a larger model was needed for this task). I think there is scope to create a standard library for such client side tweaks to web pages -- sort of like greasemonkey user scripts but at a slightly higher level of abstraction with natural language prompts.
Claude Code is very effective. Opus is a solid model and claude very reliably solves problems and is generally efficient and doesn't get stuck in weird loops or go off in insane tangents too often. You can be very very efficient with claude code.
Gemini-cli is quite good. If you set `--model gemini-3-pro-preview` it is quite usable, but the flash model is absolute trash. Overall gemini-3-pro-preview is 'smarter' than opus, but the tooling here is not as good as claude code so it tends to get stuck in loops, or think for 5 minutes, or do weird extreme stuff. When Gemini is on point it is very very good, but it is inconsistent and likely to mess up so much that it's not as productive to use as claude.
Codex is trash. It is slow, tends to fail to solve problems, gets stuck in weird places, and sometimes has to puzzle on something simple for 15 minutes. The codex models are poor, and forcing the 5.2 model is expensive, and even then the tooling is incredibly bad and tends to just fail a lot. I check in to see if codex is any good from time to time and every time it is laughably bad compared to the other two.
Why wouldnt they just expose the files directly? Having the model ask for them as regular files sounds a bit odd