Ariadne opens a pull request when it can: the repository is mapped, the file
is in the write allowlist, and the change is one anchored snippet the
validator can check. When any of that fails the incident escalates with a
diagnosis and nothing else - even though the model that wrote the diagnosis
frequently knows exactly what the fix is. That knowledge was discarded at the
moment it was most useful, because the cases where no patch is possible are
exactly the cases a maintainer has to do by hand.
A diagnosis may now carry up to three code suggestions: the file, what is
wrong there, and the code to change it to. Rendered into the issue under a
heading that says the change was not applied, because a code block in an issue
reads like something that already happened unless it is told otherwise.
Deliberately not a patch, and the difference is the safety story. A patch must
survive the validator because Ariadne acts on it. A suggestion is read by a
person who is already going to edit that file, so being wrong costs them a
moment's thought rather than a bad commit - which is why suggestions may
describe changes too large or too diffuse for the patcher to have attempted,
and why nothing here is anchored, applied or pushed.
Bounded at three. A diagnosis that suggests a dozen changes has stopped
diagnosing and started rewriting, and an issue that long buries the reason a
person was called in the first place.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
