Commit graph

2 commits

Author SHA1 Message Date
Shay
310aed9ff0
chore: Refactor CLI and Governance Anchors (#926)
* docs: consolidate governance anchors and clean up test registries

* refactor(cli): decompose cli into dedicated modules

* test: fix broken test baselines and formatting

* docs: add domain boundary READMEs for governance anchors

* test: update baseline for determination lane

* test: fix capability_pass expectation

* test: fix CORE_SHOWCASE_SKIP_BUDGET enforcement

* chore: cleanup CLI extraction and unreachable code
2026-07-03 12:34:56 -07:00
Shay
db5bc028f9 feat(adr-0034): EthicsCheck — structural surface parallel to SafetyCheck
Completes the predicate-surface layer for ethics packs, sibling to
ADR-0032's SafetyCheck.  Same registry-of-predicates shape; same
observational discipline; same honest reporting of runtime-checkable=False
for structural commitments that cannot be evaluated from per-turn evidence.

Five default predicates for the v1 commitments:

  acknowledge_uncertainty           — alignment < threshold ⇒ requires hedge
  defer_high_stakes_to_human_review — high_stakes ⇒ requires recommend_review
  disclose_limitations              — ungrounded ⇒ requires disclosure marker
  no_manipulation                   — structural; runtime_checkable=False
  respect_user_autonomy             — prescriptive ⇒ requires ≥2 options surfaced

`no_manipulation` is the ethics-side analogue of `no_hot_path_repair`
in SafetyCheck — an aggregate property enforced by realizer design and
review, not a per-turn metric.  Honest reporting rather than a silent
upheld pass.

ChatRuntime exposes `runtime.ethics_check`; turn loop does not
auto-invoke.  Refusal / re-articulation wiring is a future ADR.

Test coverage: 27 new tests; combined pack-layer surface suite
(identity + safety + ethics, loaders + checks) is now 108 tests, all
green.  Cognition (121), teaching (17), runtime (19), smoke (67)
unaffected.
2026-05-17 20:46:34 -07:00