core/evals/gsm8k_math/train_sample
Shay 73f74588ae fix(evals): stabilize test harness post-CGA substrate migration
- Resolved `tmp_path_factory` exhaustion error in `conftest.py` isolation setup
- Fixed aggressive string-replacement artifacts (`is_eval_close(..., True and ...)`) in contemplation and relational reader test modules that swallowed boolean precedence
- Re-pinned Claude hybrid verification expected artifacts (scenarios 1-5) to correctly reflect their new geometry-derived trace hashes
- Updated construction affordance invariants and tests to reflect the targeted promotion of `proportional_change.decrease_to_fraction` from diagnostic-only to serving-allowed
2026-07-04 18:43:01 -07:00
..
v1 fix(evals): stabilize test harness post-CGA substrate migration 2026-07-04 18:43:01 -07:00
__init__.py feat(gsm8k): ADR-0126 P6 — train-sample runner + exit-criterion gate 2026-05-23 06:33:06 -07:00