João Moura 9de80df7f3 fix(cli): print whatever areas the evaluation graded (#7701) ...

`crewai eval` printed a fixed tuple of area names. The areas belong to the
evaluation, not to the client, so a fixed list does two wrong things the
moment the evaluator's vocabulary moves ahead of an installed CLI: it drops
every area it has not heard of, and it invents "not measured" for ones that no
longer exist. A user would see one real grade and three phantom blanks, with
no sign that anything had been dropped.

It now prints the areas it was sent, in the order they arrived. The verdict is
still validated exactly as before — a grade is an int in 1..5 or null — so a
malformed payload is still a protocol error rather than something printed.

This lands before the evaluator's own change so that an installed CLI keeps
working through the rollout rather than after it.

2026-09-21 23:23:21 -07:00

..

cli

fix(cli): print whatever areas the evaluation graded (#7701)

2026-09-21 23:23:21 -07:00

crewai

feat(tracing): record the last traced run for crewai eval instead of printing it (#7648)

2026-09-21 17:28:25 +00:00

crewai-core

feat(cli): improve platform integration setup UX (#7453)

2026-09-17 11:35:32 -07:00

crewai-files

feat: bump versions to 1.15.22 (#7520)

2026-09-16 22:04:49 +00:00

crewai-tools

fix(tools): keep selenium driver reusable (#7663)

2026-09-21 10:58:22 +00:00

devtools

feat: bump versions to 1.15.22 (#7520)

2026-09-16 22:04:49 +00:00