zq a62ec857f1 fix(reflect): support continuous reward scores in failure filtering ...

not r.get("hard") treats non-zero floats as success.
Add explicit float threshold check (< 1e-9).
Backward compatible with binary hard=0/1.

2026-05-29 19:04:42 +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

aggregate.py

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

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

reflect.py

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

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