Linux Kernel Summit discussions
 help / color / mirror / Atom feed
From: Roman Gushchin <roman.gushchin@linux.dev>
To: James Bottomley <James.Bottomley@hansenpartnership.com>
Cc: Guenter Roeck <linux@roeck-us.net>,
	Greg KH <gregkh@linuxfoundation.org>,
	sashiko-reviews@lists.linux.dev, Chris Mason <clm@fb.com>,
	linux-scsi@vger.kernel.org, ksummit@lists.linux.dev
Subject: Re: How to fix problems with the sashiko review model
Date: Wed, 22 Jul 2026 09:40:13 -0700	[thread overview]
Message-ID: <8CC99AC2-E8E6-4644-A504-454C1FFD30CC@linux.dev> (raw)
In-Reply-To: <8cb7a4a8a13bb003daa1d1413517e104955772d3.camel@HansenPartnership.com>

> On Jul 22, 2026, at 8:10 AM, James Bottomley <James.Bottomley@hansenpartnership.com> wrote:
> 
> On Wed, 2026-07-22 at 06:43 -0700, Guenter Roeck wrote:
> [...]
>> For Sashiko, fork and clone
>> https://github.com/sashiko-dev/sashiko.git,
>> submit your changes into the clone, and send a pull request. Or at
>> least that is how I do it.
>> 
>> In the Sashiko source, per-subsystem prompts are located in directory
>> third_party/prompts/kernel/subsystem.
> 
> OK, now I'm confused.  I thought
> 
> https://github.com/masoncl/review-prompts
> 
> was the source of truth for this, but that project seems to have been
> copied into sashiko rather than pulled in as a module.  If you want to
> improve the review prompts do you now have to submit to both (which is
> getting to be a bit wasteful)?

It’s a bit messy now, but Chris and me are working on something more sane.
As of now, Sashiko is using per-subsystem prompts from Chris’s repository
with some changes around more generic prompts. I periodically pull updates
from Chris’s repository. Also several folks sent prompts changes directly to
Sashiko repository, Idk if Chris is merging them back, probably not.

I also experiment with auto-generating prompts based on human feedback
to sashiko reviews, initial results are quite promising.

So as of now, I’d say send a pull request to Chris or me directly, we’ll figure out
a better model going forward.

The hard part is testing: it’s quite easy to confuse a LLM with an unlucky prompt change.
We need a stronger guidance and maybe LLM review for prompts too (sashiko for sashiko?!).
E.g. Sashiko implements a much smaller set of tools (intentionally) than a generic coding agent,
so if a prompt contains something like “run checkpatch.pl” or “search lore for …” it might be
very confusing to the LLM. When I’m pulling significant prompt updates from Chris’s repository,
I run the full benchmark to make sure we don’t get regressions.

Thanks!

  parent reply	other threads:[~2026-07-22 16:40 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20260722041257.1557-1-pengpeng@iscas.ac.cn>
     [not found] ` <20260722042744.5C1B01F000E9@smtp.kernel.org>
2026-07-22 11:58   ` How to fix problems with the sashiko review model James Bottomley
2026-07-22 12:11     ` Laurent Pinchart
2026-07-22 12:42       ` James Bottomley
2026-07-22 13:08     ` Greg KH
2026-07-22 13:10       ` Greg KH
2026-07-22 13:45         ` James Bottomley
2026-07-22 14:08           ` Theodore Tso
2026-07-22 15:29           ` Miguel Ojeda
2026-07-22 13:42       ` James Bottomley
2026-07-22 14:00         ` Johannes Berg
2026-07-22 14:17           ` James Bottomley
2026-07-22 14:25             ` Johannes Berg
2026-07-22 15:39               ` Steven Rostedt
2026-07-22 15:55                 ` James Bottomley
2026-07-22 16:36                   ` Johannes Berg
2026-07-22 15:09             ` Mauro Carvalho Chehab
2026-07-22 15:24               ` James Bottomley
2026-07-22 20:25                 ` Mauro Carvalho Chehab
2026-07-22 14:20           ` Mark Brown
2026-07-22 13:43       ` Guenter Roeck
2026-07-22 15:10         ` James Bottomley
2026-07-22 15:41           ` Miguel Ojeda
2026-07-22 15:54           ` Arnaldo Carvalho de Melo
2026-07-22 16:40           ` Roman Gushchin [this message]
2026-07-22 15:55     ` Roman Gushchin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=8CC99AC2-E8E6-4644-A504-454C1FFD30CC@linux.dev \
    --to=roman.gushchin@linux.dev \
    --cc=James.Bottomley@hansenpartnership.com \
    --cc=clm@fb.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=ksummit@lists.linux.dev \
    --cc=linux-scsi@vger.kernel.org \
    --cc=linux@roeck-us.net \
    --cc=sashiko-reviews@lists.linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox