: Evaluation lifecycle (grounded generation → review → run → analyze) - #267

Merged

Apurva Banka (apurvabanka) merged 16 commits into

mainfrom

nbethapudi/evaluation-lifecycle

Sep 11, 2026

Commits on Sep 4, 2026

feat(evaluations): add grounded generation and quality exports

nehacopilot
and
Copilot
committed
50f7757
feat(evaluations): add review and promotion lifecycle

nehacopilot
and
Copilot
committed
b5ee5c6
feat(evaluations): run test sets and analyze results

nehacopilot
and
Copilot
committed
efee0c2
fix(evaluations): explain review-blocked test sets

nehacopilot
and
Copilot
committed
883fe5d
feat(evaluations): add maker and reviewer choice prompts

nehacopilot
and
Copilot
committed
d6bb693
fix(evaluations): make reviewer workflow feedback-only

nehacopilot
and
Copilot
committed
ba82bdd
feat(evaluations): refresh review sets automatically

nehacopilot
and
Copilot
committed
8f17612
fix(evaluations): preserve unmapped test case ids

nehacopilot
and
Copilot
committed
79f5bbb
fix(evaluations): address review and runtime gaps

nehacopilot
and
Copilot
committed
3666ea4
docs(evaluations): register run lifecycle

nehacopilot
and
Copilot
committed
aed5b53

Commits on Sep 7, 2026

fix(evaluations): use signed-in profile connections

nehacopilot
and
Copilot
committed
2e98915
chore(evaluations): add MinimalBot run POC

nehacopilot
and
Copilot
committed
17530b0
fix(evaluations): prefer latest matching profile

nehacopilot
and
Copilot
committed
b57793a
revert(evaluations): remove directly pushed MinimalBot POC

nehacopilot
and
Copilot
committed
12ec360

Commits on Sep 10, 2026

requested changes
apurvabanka_microsoft
committed
bfed56e

Commits on Sep 11, 2026

requested changes
apurvabanka_microsoft
committed
d5dea9f