21c22b2201
Resolves all 5 TBDs and closes all 8 acceptance gates for ADR-0022. TBD-1 (intent oracle): regex seed + field ratification — generate/intent_ratifier.py. RATIFIED / DEMOTED / PASSTHROUGH outcomes; DEMOTED routes through honest refusal. TBD-2 (region intersection algebra): generate/admissibility.py. Token-set composition via sorted set intersection; blade composition via outer product with zero-blade as neutral element; rotor composition via sandwich conjugation routed through algebra.backend.versor_apply (Rust parity preserved by construction). Empty intersections preserved — no silent relaxation. Wiring: propose() and generate() accept an AdmissibilityRegion (default None preserves legacy behavior); pipeline ratifies intent at step 1b.i before graph construction. Eval lane: evals/forward_semantic_control/ — both legs run against CognitiveTurnPipeline (constrained) vs bare ChatRuntime.chat() (unconstrained baseline). Dev (3 cases) and public/v1 (1 case) both report overall_pass=true, causality_gap=1.0, coincidence_rate=0.0. Chain-endpoint probe surfaces 'delta' only under forward semantic control. Bench cost (30 turns): -2.8% wall-clock (within +5% budget the ADR set for the ratification gate on every turn). 138x cheaper than Sonnet 4.5; main was 142x. Tests: 33 new (25 admissibility + 8 ratifier). Full suite 912/913 pass — the single failure is pre-existing pack-size drift on main, unrelated. |
||
|---|---|---|
| .. | ||
| architecture | ||
| decisions | ||
| sessions | ||
| capability_roadmap.md | ||
| eval_methodology.md | ||
| formation_pipeline_plan.md | ||
| frontier_baselines.md | ||
| PROGRESS.md | ||
| runtime_contracts.md | ||
| RUST.md | ||
| truth_seeking_schema.md | ||
| Whitepaper.md | ||
| Yellowpaper.md | ||