diff --git a/instructions/upgrader-detectors.md b/instructions/upgrader-detectors.md index a33d6a8..df7be74 100644 --- a/instructions/upgrader-detectors.md +++ b/instructions/upgrader-detectors.md @@ -22,7 +22,7 @@ Fixes to try first: a significant event missed or badly bounded before a small n ## The checks -- **events**: before and after each fix, with `2>&1`; after, no `skipped` line. +- **events**: before and after each fix, with `2>&1`. - **range**: the range score, what you make rise, without losing a whole event. A hole has no measurement: it only counts its two bounds; for a hole, read the events check. Do not aim for 100 %. - **benchmark**: all lines of all stations, against the benchmark of the last committed state (the benchmark before, or that of your previous kept fix); before your output, the whole against the benchmark before. A regression (`/CLAUDE.md`): rework your change before committing it, or drop the fix. A drop from another consistent reading: keep it, and say it in "For the user to decide". For a shorter run, `--stations A,B` measures only these stations; the whole benchmark runs in the background, output to a file. To try a variant without touching the repository, copy the target in your working folder: the copy's scripts measure the copy, with the same arguments. diff --git a/instructions/validator-detectors.md b/instructions/validator-detectors.md index f2f275e..87b025e 100644 --- a/instructions/validator-detectors.md +++ b/instructions/validator-detectors.md @@ -15,7 +15,6 @@ The upgrader has just adapted the detectors to better find the events of a singl ## What you judge, for the detectors -- A `skipped` line in a benchmark means cancel. - Regressions: station by station and family by family, the range's station included, by the definition of `/CLAUDE.md`. A drop you do not count as a regression goes to "Reservations". - A range gain of nothing or almost, at the price of one more rule, means cancel (or remove for the fix in question); a rule removed is better than a rule added.