Repository navigation

[Eval] Report failures and unknowns in results table - #59

Open

Birfy wants to merge 8 commits into

mainfrom

codex/eval-attempt-reporting

Open

[Eval] Report failures and unknowns in results table#59
Birfy wants to merge 8 commits into
mainfrom
codex/eval-attempt-reporting

Commits on Oct 9, 2026
- [Eval] Include failed attempts in results table
  Birfy
  committed
  4896e42
- [Eval] Preserve scored metrics with all-attempt totals
  Birfy
  committed
  33c247b
- [Eval] Format attempt reporting changes
  Birfy
  committed
  9418a39
- [Eval] Preserve precision for failure-inclusive cost
  Birfy
  committed
  8c8851f
- Merge latest main into evaluation reporting PR
  Birfy
  committed
  8df79c6
- Fix replay handling of unknown elapsed time
  Birfy
  committed
  a4a2458
- Preserve signed recorded durations
  Birfy
  committed
  91e1d54
Commits on Oct 13, 2026
- Merge remote-tracking branch 'origin/main' into codex/eval-attempt-reporting
  Birfy
  committed
  bc38ad3