Just checked, the public instance check uses 24 month: https://github.com/VirtusLab/scala-steward-repos/blob/main/scripts/test-repos.scala#L32

Not sure where, but would be good to add a note about this feature.
Maybe a short above the value in default.scala-steward.conf ?

Will do. I'll also add it to https://github.com/scala-steward-org/scala-steward/blob/main/docs/repo-specific-configuration.md.

Just checked, the public instance check uses 24 month: https://github.com/VirtusLab/scala-steward-repos/blob/main/scripts/test-repos.scala#L32

Thanks for the pointer, I didn't know about this script! I'll take a look. Also pinging @tgodzik since he wrote that.

And 18 month of inactivity ? I think I would have choosen at most 12 month.

Dependabot: 90 days

I'm totally fine with decreasing the default.

Btw, calling a repo inactive instead of abandoned sounds also nicer and less dramatic. I'll update the code accordingly. It is probably also better to rename lastCommitMaxAge to something like inactivityThreshold which better communicates the intent of that config and does not leak the implementation.

Thanks for the pointer, I didn't know about this script! I'll take a look. Also pinging @tgodzik since he wrote that.

This is my manual approach to do the same, but I feel like yours is a much better. I just didn't have the time to delve into steward details before 😅 I did remove most things older that 2 years and added watch to all of them to be notified if someone started to work on it again.

Just checked, the public instance check uses 24 month: https://github.com/VirtusLab/scala-steward-repos/blob/main/scripts/test-repos.scala#L32

It was my best guess since I actually saw some repos that were for projects that were for sure used, just didn't need a lot of work recently, so nobody bothered. But I think if we do it automatically then it totally fine to make it shorter. I would probably try to make it so that we always get the last scala version update. Some smaller projects only need that and update 2.13.x rarely as the releases are less frequent now.

I wonder if we could also check if a repo is archived? Sometime it might be younger than a threshold but still no longer used.

And also would we be able to post an issue maybe if the steward failed? That would notify the maintainers that something is wrong. Though that might be a bigger change for another PR

I would probably try to make it so that we always get the last scala version update. Some smaller projects only need that and update 2.13.x rarely as the releases are less frequent now.

Makes sense. A threshold between 180 and 360 days should be sufficient for repos that only receive Scala 2.13 updates. Also, as instance operator you can always increase the default by running with a instance-wide repo config.

I wonder if we could also check if a repo is archived?

This exists since #2507 and it should be easy to grep for archived repos in the logs. Here is an example:

2025年01月23日 20:18:06,924 INFO ──────────── Steward fthomas/typelevel-webapp ────────────
2025年01月23日 20:18:06,925 INFO Check cache of fthomas/typelevel-webapp
2025年01月23日 20:18:10,184 ERROR Steward fthomas/typelevel-webapp failed
org.scalasteward.core.forge.github.GitHubException$RepositoryArchived: fthomas/typelevel-webapp
2025年01月23日 20:18:10,186 INFO ──────────── Total time: Steward fthomas/typelevel-webapp: 3s 261ms ────────────

For inactive repos, I should also add a dedicated exception to make grepping for them easier.

And also would we be able to post an issue maybe if the steward failed? That would notify the maintainers that something is wrong. Though that might be a bigger change for another PR

We have an issue for that: #2030. And for sure this is not as easy as this change. :-)