Video yükleniyor...
Video Yüklenemedi
Your AI coding agent is slow because it keeps waiting on itself. Search, wait, read, wait, edit, wait, test, wait. So I built Turnpack. It folds those steps together. Half the round trips, roughly half the time, 36% cheaper in my test. It also lets the AI test its... show more
26,560 görüntüleme • 3 gün önce •via X (Twitter)
41 Yorum

How I got those numbers: I gave Claude Code the same small coding task 3 times with Turnpack and 3 times without, then compared. The test script is in the repo if you want to run it on your own setup. Credits: Video by fable 5.2 XH in claude app

LET'S GOOOO 🚀🚀🚀

Just getting started. Alot more coming soon :)

The test wait is usually the longest one. During the loop, have the agent run only tests related to the changed files (jest --findRelatedTests, pytest-testmon, go test on the touched packages) and save the full suite for the final check.

most of the wait is round trips where the model just needed a grep result, so folding search and read together is where the time comes back. testing edits before they land saves another full loop

Search, wait, read, wait is basically the agent version of watching a progress bar. etoro Builders feel this too when their agents loop through etoro's API and MCP while building investing tools. Which wait does Turnpack fold next?

Folding search and read into one step makes sense, most of the waiting is the model asking for one file at a time. What happens when an edit fails the test mid-batch, does the whole pack roll back?

Does folding the steps hurt when the agent needs to change plans after a read? Batching search-read-edit is great until the read shows it grabbed the wrong file, so I'm curious how often it has to unwind.

nah, cuz he woulda had to do more tool calls before hand anyways to read it regardless

folding search and read into one step is where most of the wall time goes. how do you handle it when the edit depends on what the read found?

The snap-back when a test fails is the best part. Does it run the whole suite before an edit sticks, or only the tests near the files it touched?

Folding steps together is great until a test fails halfway. Does Turnpack roll back the whole batch or keep the edits that already landed?

Ive used billions of tokens with this tech your good king

the snap-back is the part i'd actually use. worst agent mess i get isn't slowness, it's a test failing halfway through a 3-file edit and leaving things half applied. does the rollback cover files it created too, or only ones it edited?

Mine waits longest on cargo build. Fold the round trips all you want, the linker still takes four minutes.

ahh i already solved this for my own setup but i havent released the majority of my tech this was just a small freebie for opensourse. I have to decide how i wanna share the rest because i worked really hard & idk how to share it & atleast make what i spent back haha

@MiaAI_lab King!

Read the rollback section. Could the --fix / FAILED_ROLLBACK_PARTIAL case sit beside the main demo? It clarifies when edited files stay on disk.

snapping every file back when a test breaks is the bit i'd trust first, does it catch new files too?

yea, experience has been really smooth

does the saving hold when the first edit fails a test and it has to change course? that's where batching gets interesting.

Folding the steps together is smart, but cache reads are the majority of cost in a session. How does it handle over-fetching and context bloat if it tries to shove everything into context at once?

Search, wait, read, wait is painfully accurate. Watching an agent pause between every step is like a dial-up modem with opinions. Does folding steps ever trip it when one depends on the last?

Yo Claude set this up

Snap-back on failed edits is the part I'd want most. Does the rollback cover side effects outside the files too, like a migration or a package install, or just the working tree?

flash from zootopia finally got a turbo 🦥

the wait between test runs is where my whole afternoon goes

wrench read 'every file snaps back if it breaks' and asked if it works on his personality too

Interesting that re-reading context was most of the saving. With prompt caching those re-reads are already cheap, so I'd be curious whether the 36% holds on a long session or it mostly ends up as time saved.

That's a pretty smart way to eliminate unnecessary delays. Definitely worth exploring

on messy repos the slow part for me is the agent rereading the same 3 files after every edit. fix that and its way faster

Folding search, read and edit into fewer round trips makes sense. Curious how you handle a test failure in the middle of a folded step. Does it unwind or retry just that piece?

Folding those sequential waits into single steps is a smart way to fight the latency tax. Does the rollback feature trigger on a specific error code or just any failed test execution?

does folding the steps hurt when the search comes back wrong? feels like the waiting is where it catches its own mistakes

Thanks for pointing out how much time goes to the agent just waiting between steps. Folding those round trips together seems like the real speedup. Curious whether the 36% cost drop holds on longer sessions too.

The wait chain is why a lot of agent runs feel expensive. I care as much about what can run in parallel as about the model. Search and tests that block the next edit are usually the first things I'd fold together.

The rollback part matters more to me than the speed. A half-edited repo is the scary failure when you let an agent touch internal tools, and "tests pass or every file goes back" is a rule small teams can actually trust. Does ship's verify just run whatever command you pass it?

Folding the read-edit-test loop makes sense, most of the latency is round trips, not tokens. How does it handle a step that fails midway: roll back the batch or continue with partial edits?

the search, wait, read, wait loop is so real. half the time mine is just rereading the same files. curious what happens when a test fails midway, does it fall back to single steps?

Nah just fixes and moves on quickly as normal

ha fair, that's the dream honestly. mine still panics and rereads half the repo sometimes



