On Fri, Oct 16, 2026 at 02:17:25PM -0400, Julia Lawall wrote:
On Fri, 16 Oct 2026, Sasha Levin wrote:
On Fri, Oct 16, 2026 at 02:00:15PM -0400, Julia Lawall wrote:
>
>
> On Fri, 16 Oct 2026, Sasha Levin wrote:
>
> > A bug fixed in one place often exists elsewhere, in copied code, sibling
> > drivers, or other users of the same interface, and reviewers routinely
> > ask whether that was checked. Left alone, agents tend to audit the whole
> > tree by reading it. Add a skill that states the defect as a rule,
> > searches for it through shared interfaces, copied code, the introducing
> > series and earlier fixes, and verifies each candidate before reporting
> > it.
> >
> > When Coccinelle is available, the skill searches with a semantic patch:
> > it looks for an existing one under scripts/coccinelle/, checks that the
> > rule marks the fixed site in the code before the fix, runs it over the
> > whole tree with coccicheck, and checks which code spatch could not
> > parse. These steps live in references/coccinelle.md, which the agent
> > reads only when it uses Coccinelle.
>
> Could I get some feedback from this? I would be interested to know about
> code that it can't parse. Maybe AI could write a semantic patch and try
> it?
Right, this is exactly what the skill currently says:
+2. Otherwise, write a semantic patch outside the repository. Match only what
+ the defect needs, not names or statements specific to the fixed site. Mark
[...]
I'd expect the agent to have information in the transcript about this, or are
you looking for something different?
I just want to know how to find it, or ideally if it could be reported to
me (or to the Coccinelle mailing list).
I can add an instruction to the prompt that any issues discovered and fixed
this way should also include the semantic patch?
--
Thanks,
Sasha
