dwb 2 days ago
I get enough of this with a pre/post tool hook that takes a jj snapshot and teaching the agent about `jj evolog`.
vcryan 2 days ago
My entire repo is an audit trail of AI coding-agent edits
giancarlostoro 2 days ago
Not only that, but Claude can undo its own changes I just never use the feature because git has me covered...
joshka 2 days ago
Yuck. Use jj for this instead of a custom thing.
joaoreis81 2 days ago
And what if the changes are remote?
Joker_vD 2 days ago
Not to be confused with "Ponytail", an award-winning puzzle-platform game by Jonathan Blow.
benny_s 2 days ago
Have you heard of git?
1997roylee 2 days ago
Hi everyone, I built Ponytrail, a small CLI and bundled agent skill for making AI coding sessions easier to inspect and undo.

The problem I kept hitting: git diff shows what changed, but not why the agent changed it, what outcome it expected, what check it planned to run, or how to roll back one specific action. Final summaries are often too coarse, especially after a long coding session.

Ponytrail adds a small local trail around file mutations. Before an agent creates, edits, moves, deletes, formats, or generates files, it records a pre-change snapshot: action, purpose, reason, files, expected outcome, verification plan, rollback path

After the edit, it records a post-change snapshot with what changed, what checks ran, and the result.

Everything is stored locally under .pony-trail/ as JSONL, session trees, and small before/after file copies. It does not replace git. It is more like per-action intent and rollback context for agent work.

p1024k 2 days ago
This project looks pretty interesting! Could you share 1-2 use cases? That would help people quickly understand what it does and get started.
altmanaltman 2 days ago
Why does this project look interesting? Very sus comment from a new account
rootnod3 2 days ago
And why does it sound like LLM output?
p1024k 19 hours ago
I’m really confused—why would a totally normal comment get misread? And why does it feel so unwelcoming here?
altmanaltman 4 hours ago
Because you are using AI ton write comments and not interact with people. Which makes this super sus. Instead of answering a question asked in good faith, you are deflecting and blaming others now.