Repository navigation

Eval: judge each case on the outcome a user would see - #5167

Merged

chubes4 merged 8 commits into

trunkfrom

eval/judge-outcomes

Oct 21, 2026

Merged

Eval: judge each case on the outcome a user would see#5167
chubes4 merged 8 commits into
trunkfrom
eval/judge-outcomes

Commits on Oct 16, 2026
- Eval: judge each case on the outcome a user would see, against an isolated site registry
  chubes4
  committed
  50175bd
Commits on Oct 17, 2026
- Eval: give each case its own sites folder, so concurrent cases never delete each other's sites
  chubes4
  committed
  8914641
Commits on Oct 20, 2026
- Merge trunk: usage, stop reason and transcript now come from #5193
  chubes4
  committed
  fe778b7
Commits on Oct 21, 2026