3 commits

Author	SHA1	Message	Date
Shay	9bbdcc96aa	feat(W-008): L10 Shape B hybrid engine-state persistence (#271) ... * ci: re-trigger full-pytest * docs: ADR-0146 — L10 Shape B hybrid engine-state persistence * feat(W-008): Shape B engine-state persistence spike (ADR-0146) * fix(W-008): eval isolation + env-var path + empty-manifest guard - evals/run_cognition_eval.py: all ChatRuntime() calls pass no_load_state=True so parallel eval workers never touch engine_state/ checkpoints - engine_state/__init__.py: honour CORE_ENGINE_STATE_DIR env var (ADR-0146 spec) - engine_state/__init__.py: load_manifest() skips empty file instead of crashing (defensive against partial writes in concurrent contexts) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-25 11:45:54 -07:00
Shay	0eaba474ed	parallel eval runner (#46)	2026-05-19 23:51:59 -07:00
Shay	366f7a08c4	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>	2026-05-15 07:41:36 -07:00