Add cognitive eval harness and calibration replay (#30)
* feat: add cognitive eval harness with CLI integration
20 eval cases across 8 categories (definition, comparison, cause,
procedure, recall, correction, verification, unknown). Metrics:
intent accuracy, term capture, surface groundedness, versor closure,
trace determinism. CLI: `core eval cognition [--json] [--report PATH]`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add operator calibration replay with deterministic grid search
Bounded parameter tuning via eval replay evidence. Grid search over
salience_top_k and inhibition_threshold with invariant regression
guard (versor closure must not regress). Frozen CalibrationParams,
before/after metrics, no pack or identity mutation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
366f7a08c4