Re: Patch pre-submission to Sashiko

["Vlastimil Babka (SUSE)" <vbabka@kernel.org>]

On 10/20/26 10:36, Jiri Kosina wrote:
> On Mon, 19 Oct 2026, Theodore Tso wrote:
> 
>> > When a submitter uses LLMs to generate a patch, it is reasonable for
>> > maintainers and reviewers to ask them to use shashiko to find problems
>> > before sending it to us. Asking for a shashkiko run before submitting
>> > patches could become part of the patch submitting process.
>> > 
>> > How about updating the submitting patches document to add a section on
>> > this with instructions on how to run it?
>> > 
>> > This shifts the responsibility to run shashiko to people using LLMs.
>> 
>> If people are using LLM's to generate a patch, it would be useful if
>> we can make it super easy for LLM's to call out to Sashiko as an
>> sub-agent.  
> 
> Yeah, but that pretty much brings us back to the potentially problematic 
> "free tokens for anybody developing out-of-tree / proprietary kernel code" 
> territory again.

I assumed Ted meant to call out to a local sashiko (as Roman explained,
using the LLM itself), not the hosted one?