Some tests are written to record a mistake, so that it can't come back.
Regression test
A test written after a bug, which fails on the old code and passes on the fix. A regression is when something that used to work stops working.
An agent has no memory of last month's bug, and may reintroduce it while tidying up. The test remembers. It only counts if you have seen it fail on the broken version.
Say it to your agent
“Before you fix this: write a test that reproduces it, run it, and paste the failure. Commit that. Then fix it, run it again, and paste the pass. I want both outputs in the pull request.”