Commit graph

2 commits

Author SHA1 Message Date
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
Shay
145d797196 feat(field-wedge): geometric field reader — relational-metric lane wrong=0 (Phase W.1)
Measurement #1 of the field-reasoner falsifiable experiment: does the CL(4,1) field,
given an honest metric encoding, read forward-substitutable quantitative-relational
problems from TEXT with wrong==0? It does — 14/15 correct, 0 wrong, 1 refused
(precision ceiling), scored against an independent arithmetic oracle.

- generate/relational_field_reader.py: reads problem text into conformal points on
  the e1 number line; additive/part-whole relations are conformal TRANSLATOR versors
  (versor_apply(T_delta, embed[x]) == embed[x+delta], exact); the answer reads back
  by projective dehomogenization. Refusal-first: fences multiplicative/ratio (the
  sign/orientation-blind cases), the precision ceiling, non-forward-substitutable
  references, negatives. A per-step exactness self-check turns any f64 translator
  drift into a refusal (precision_drift) — it NEVER commits a wrong integer. Its
  parser is an independent reimplementation importing no generate.derivation/math_*.
- evals/relational_metric/: independent arithmetic oracle (computes gold from the
  STRUCTURE, shares no code with the reader), 15-case fixture, and a runner that
  enforces gold integrity + wrong==0.
- INV-25: relational_metric registered in INDEPENDENT_GOLD_LANES (oracle proven
  code-disjoint from the field reader and the algebra engine). The independently
  golded panel is now three domains: deductive, dimensional, relational-metric.

Green: smoke 87, 53 architectural invariants, 16 new tests; deductive + dimensional
lanes unperturbed (wrong=0).
2026-06-04 19:34:43 -07:00