If AI writes code, should the session be part of the commit? • Hacker News Board

Re: If AI writes code, should the session be part of the commit?

#31

Post by fragmede » Mon, Mar 02, 2026, 2:54 AM UTC

natex84 wrote: post #19

If the model in use is managed by a 3rd party, can be updated at will, and also gives different output each time it is interacted with, what is the main benefit? If I chat with an agent and give an initial prompt, and it gets "aspect A" (some arbitrary aspect of the expected code) wrong, I'll iterate to get "aspect A" corrected. Other aspects of the output may have exactly matched my (potentially unstated) expectatio…

Because intent matters and 6 months or 3 years down the line and it's time to refactor, and the original human author is long gone, there's a difference if the prompt was "I need a login screen" vs "I need a login screen, it should support magic link login and nothing else".

Re: If AI writes code, should the session be part of the commit?

#32

Post by denismi » Mon, Mar 02, 2026, 2:54 AM UTC

mandel_x wrote: post #2

I’ve been thinking about a simple problem: We’re increasingly merging AI-assisted code into production, but we rarely preserve the thing that actually produced it — the session. Six months later, when debugging or reviewing history, the only artifact left is the diff. So I built git-memento. It attaches AI session transcripts to commits using Git notes.

> the only artifact left is the diff

You also have code comments, docs in the repo, the commit message, the description and comments on the PR, the description and comments on your Issue tracker.

Providing context for a change is a solved problem, and there is relatively mature MCP for all common tooling.

Re: If AI writes code, should the session be part of the commit?

#33

Post by hsuduebc2 » Mon, Mar 02, 2026, 2:54 AM UTC

I must say that would certainly show some funny converstaions in a log.

Re: If AI writes code, should the session be part of the commit?

#34

Post by reg_dunlop » Mon, Mar 02, 2026, 2:55 AM UTC

jiveturkey wrote: post #18

https://entire.io thinks so

Thank you! Was looking for this company. Founder was high up at GitHub. Really an interesting proposition

Re: If AI writes code, should the session be part of the commit?

#35

Post by aspenmartin » Mon, Mar 02, 2026, 2:56 AM UTC

rfw300 wrote: post #14

Why should it be? The agent session is a messy intermediate output, not an artifact that should be part of the final product. If the "why" of a code change is important, have your agent write a commit message or a documentation file that is polished and intended for consumption.

post mortems / bug hunting -- pinpointing what part of the logic was to blame for a certain problem.

Re: If AI writes code, should the session be part of the commit?

#36

Post by rcy » Mon, Mar 02, 2026, 2:56 AM UTC

I haven't adopted this yet, but have a feeling that something like this is the right level of recording the llm contribution / session https://blog.bryanl.dev/posts/change-intent-records

Re: If AI writes code, should the session be part of the commit?

#37

Post by causal » Mon, Mar 02, 2026, 2:56 AM UTC

If a car is used to get you somewhere, should you put the exhaust in bags to bring with you?

Re: If AI writes code, should the session be part of the commit?

#38

Post by xboxnolifes » Mon, Mar 02, 2026, 2:57 AM UTC

AndrewKemendo wrote: post #29

rfw300 wrote: post #14

Why should it be? The agent session is a messy intermediate output, not an artifact that should be part of the final product. If the "why" of a code change is important, have your agent write a commit message or a documentation file that is polished and intended for consumption.

How’s it any different than a diff log?

Better question: how is it in any way similar?

Re: If AI writes code, should the session be part of the commit?

#39

Post by foamzou » Mon, Mar 02, 2026, 2:59 AM UTC

No. Prompt-like document is enough. (e.g. skills, AGENTS.md)

Re: If AI writes code, should the session be part of the commit?

#40

Post by daxfohl » Mon, Mar 02, 2026, 3:01 AM UTC

I think so. If nothing else, when you deploy and see a bug, you can have a script that revives the LLMs of the last N commits and ask "would your change have caused this?" Probably wouldn't work or be any more efficient than a new debugging agent most of the time, but it might sometimes and you'd have a fix PR ready before you even answered the pager, and a postmortem that includes WHY it did so, and a prompt to prevent that behavior in the future. And it's cheap, so why not.

Maybe not a permanent part of the commit, but something stored on the side for a few weeks at a time. Or even permanently, it could be useful to go back and ask, "why did you do it that way?", and realize that the reason is no longer relevant and you can simplify the design without worrying you're breaking something.