core-labs/core
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions
core/docs
History
Shay a0372c951f feat(adr-0036): safety-only typed refusal policy 
Runtime-checkable SafetyVerdict violations now replace
ChatResponse.surface (and TurnEvent.surface on the main path) with a
deterministic typed refusal string.  Ethics violations remain
audit-only.

Why safety-only: safety is the universal floor (ADR-0029,
never-swappable, fail-closed).  Ethics is swappable per-deployment;
wiring ethics into refusal would let pack-swappers silently change
refusal behavior via JSON edit.  Wrong coupling.

Why typed refusal (not hedge injection / not re-articulation): typed
refusal is deterministic, audit-detectable by prefix, and preserves
replayability.  Hedge injection would blur surface-preferences-driven
hedging vs predicate-driven refusal.  Re-articulation retry yields the
same surface (planner is deterministic; no refusal-bias hint surface
exists).  Deferred to a future ADR.

Refusal contract:
- ChatResponse.surface = typed refusal string
- walk_surface + articulation_surface = unchanged (audit preserved)
- runtime._last_refusal_was_typed = True (next-turn evidence for
  no_silent_correction)
- Only runtime_checkable=True violations refuse
- Stub path symmetric

Files:
- chat/refusal.py (new) — pure refusal builder + audit helpers
- chat/runtime.py — invoke build_refusal_surface after safety_verdict
- tests/test_safety_refusal.py (new) — 20 tests
- docs/decisions/ADR-0036-safety-refusal-policy.md (new)

Verification:
- 20 new tests; combined pack-layer suite 116 green
- CLI suites unchanged: smoke 67, runtime 19, cognition 121
- core eval cognition: intent 100%, versor_closure 100% (baseline)
2026-05-17 21:10:52 -07:00
..
architecture
decisions feat(adr-0036): safety-only typed refusal policy 2026-05-17 21:10:52 -07:00
evals feat(adr-0024): Phase 6 — comparative demo, three head-to-head conditions 2026-05-17 16:02:37 -07:00
sessions feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
capability_roadmap.md docs: teaching-order doctrine + refresh formation/roadmap status 2026-05-17 18:48:44 -07:00
ethics_packs.md feat(adr-0034): EthicsCheck — structural surface parallel to SafetyCheck 2026-05-17 20:46:34 -07:00
eval_methodology.md feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 2026-05-15 22:36:53 -07:00
formation_pipeline_plan.md docs: teaching-order doctrine + refresh formation/roadmap status 2026-05-17 18:48:44 -07:00
frontier_baselines.md feat(evals): frontier structural-zero baselines for Phase 2 v1 lanes 2026-05-16 12:45:28 -07:00
identity_packs.md feat(surface): ADR-0031 — score-decomposition surface (per-axis hedges) 2026-05-17 20:16:22 -07:00
PROGRESS.md docs: ADR-0024 chain coverage across README, ADR index, contracts, papers 2026-05-17 16:28:54 -07:00
runtime_contracts.md docs: ADR-0024 chain coverage across README, ADR index, contracts, papers 2026-05-17 16:28:54 -07:00
RUST.md Activate and verify Rust backend 2026-05-13 22:23:48 -07:00
safety_packs.md feat(safety): ADR-0032 — SafetyCheck structural surface 2026-05-17 20:25:22 -07:00
teaching_order.md feat(identity-packs): ADR-0027 — swappable identity manifold via packs 2026-05-17 19:24:39 -07:00
truth_seeking_schema.md feat(epistemic): contradiction coherence checker — CONTESTED transitions wired, last Tier 4.5 row closes 2026-05-17 10:36:48 -07:00
Whitepaper.md docs: ADR-0024 chain coverage across README, ADR index, contracts, papers 2026-05-17 16:28:54 -07:00
Yellowpaper.md docs: ADR-0024 chain coverage across README, ADR index, contracts, papers 2026-05-17 16:28:54 -07:00