Yif Yang d190bf37c1 Merge pull request #25 from lvbaocheng/feature/gate-soft-metric ...

Add configurable gate metric (hard / soft / mixed) for skill validation

Default is `hard`, preserving exact pre-PR behavior — verified by 22 unit
assertions on the gate module plus an end-to-end 8-step trainer-trajectory
test that produces a bit-for-bit identical accept/reject sequence between
the pre-PR and post-PR code paths under `gate_metric: hard`. Paper-
reproduction results are unaffected.

`soft` and `mixed` are opt-in via `evaluation.gate_metric` in the config
and address small-selection-set runs where discrete hard accuracy is too
coarse to distinguish candidate skills.

2026-05-30 08:01:39 +00:00

..

datasets

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

engine

Merge pull request #25 from lvbaocheng/feature/gate-soft-metric

2026-05-30 08:01:39 +00:00

envs

Make rollout completion tokens configurable

2026-05-28 09:45:47 +00:00

evaluation

Add configurable gate metric (hard / soft / mixed) for skill validation

2026-05-30 14:45:27 +08:00

gradient

fix(reflect): support continuous reward scores in failure filtering

2026-05-29 19:04:42 +08:00

model

fix(claude): use --effort instead of deprecated --thinking flag

2026-05-30 11:24:13 +08:00

optimizer

cleanup: remove unused benchmarks, deep_probe, meta_reflect

2026-05-24 19:36:48 +00:00

prompts

cleanup: remove unused benchmarks, deep_probe, meta_reflect

2026-05-24 19:36:48 +00:00

scheduler

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

utils

fix(scoring): use float() instead of int() for continuous reward scores

2026-05-30 07:47:41 +08:00

__init__.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00

config.py

Add configurable gate metric (hard / soft / mixed) for skill validation

2026-05-30 14:45:27 +08:00

types.py

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00