Repository navigation

feat(eval): dataset-level evaluators + classification schemas, samples, e2e - #1663

Merged

ajay-kesavan merged 34 commits into

mainfrom

feat/classification-evaluator-types

Jul 23, 2026

Merged

feat(eval): dataset-level evaluators + classification schemas, samples, e2e#1663
ajay-kesavan merged 34 commits into
mainfrom
feat/classification-evaluator-types

Commits on May 20, 2026
- feat(eval): add evaluator type schemas for classification evaluators
  
  ajay-kesavan
  and
  claude
  committed
  6b11767
- test(eval): add e2e tests + sample projects for classification evaluators
  
  ajay-kesavan
  and
  claude
  committed
  037b60c
- feat(eval): add dataset-level evaluator framework with precision/recall/f-score
  
  ajay-kesavan
  and
  claude
  committed
  5e574f1
- docs(eval): add runnable dataset evaluator demo + bump uv.lock for 2.10.69
  
  ajay-kesavan
  and
  claude
  committed
  d6b7ab5
Commits on Jun 19, 2026
Commits on Jun 24, 2026
- Merge remote-tracking branch 'origin/main' into feat/classification-evaluator-types
  ajay-kesavan
  committed
  2be26c9
Commits on Jul 7, 2026
- Merge remote-tracking branch 'origin/main' into feat/classification-evaluator-types
  ajay-kesavan
  committed
  b872c8f
Commits on Jul 8, 2026
- refactor(eval): move aggregators to ExactMatch, revert on Binary/Multiclass
  
  ajay-kesavan
  and
  claude
  committed
  dd910e4
- refactor(eval)!: trim PR to the ExactMatch aggregator contract only
  
  ajay-kesavan
  and
  claude
  committed
  383cbb7
- feat(eval): restore local dataset aggregation for `uipath eval`
  
  ajay-kesavan
  and
  claude
  committed
  2885c26
Commits on Jul 9, 2026
- feat(eval)!: single aggregation implementation — SDK owns the math
  
  ajay-kesavan
  and
  claude
  committed
  1ce1209
- fix(eval): review-round hardening for dataset aggregators
  
  ajay-kesavan
  and
  claude
  committed
  ea3672e
- fix(eval): round-2 review — validator gaps + test leanness
  
  ajay-kesavan
  and
  claude
  committed
  fa0d86c
Commits on Jul 21, 2026
Commits on Jul 22, 2026
- Merge remote-tracking branch 'origin/main' into feat/classification-evaluator-types
  ajay-kesavan
  committed
  c710a77
Commits on Jul 23, 2026
- chore(uipath): bump version to 2.13.15
  
  ajay-kesavan
  and
  claude
  committed
  0d76fe8
- fix(eval): count OOV predictions as recall misses; reject negated + aggregators
  
  ajay-kesavan
  and
  claude
  committed
  5b95d05
- Merge branch 'main' into feat/classification-evaluator-types
  ajay-kesavan
  authored
  d85dc44

Commits

Commits on May 20, 2026

Commits on Jun 19, 2026

Commits on Jun 24, 2026

Commits on Jul 7, 2026

Commits on Jul 8, 2026

Commits on Jul 9, 2026

Commits on Jul 21, 2026

Commits on Jul 22, 2026

Commits on Jul 23, 2026