2.6 KiB
2.6 KiB
ADR-0018 — External audit and exploration mode
Status: Accepted Date: 2026-08-22 Accepted under: ARCH-000012
Decision
- Domovoy may operate in a test-only
Explorationprofile when an ordinary local conversation or cognitive-provider recovery request is received. Exploration permits contextual reasoning, allowlisted read-only diagnostics, hypothesis generation, alternatives and a reversible next-step proposal. - Exploration is not an authority grant. It does not grant access to raw secrets, executor credentials, a provider's unapproved data-egress path, or direct mutation of canonical or external state.
- Audit is an independently deployed, rebuildable projection of compact, redacted action/proposal events. It is not a canonical owner and never executes actions.
- An attributed external audit verdict is an Observation. A later Commit
contract may require a current
ALLOWObservation as an additional precondition for explicitly configured action classes.REVIEW_REQUIRED,STOP, missing or stale review do not authorize execution. - Loss of the audit deployment does not remove exploration or approved read-only diagnostics. A review-governed external action remains a pending proposal; it is neither executed nor silently converted to failure.
- Audit payloads exclude raw credentials, secrets and private content. They carry stable identifiers/references, classifications, hashes and redacted summaries only.
- Initial delivery is staged: first semantic local dialogue and provider recovery, then capability-use telemetry, then audit-only projection. No existing executor action is review-governed until a later task names its class and recovery behavior.
Consequences
- Local cognition remains useful during provider loss and can seek a recovery plan instead of returning canned availability text.
- Higher-level external scrutiny is possible without creating a competing executor or a second source of semantic truth.
- Commit/Executor, semantic ownership, append-only evidence and unknown outcome semantics remain invariants, so external review has attributable evidence to inspect.
- The first implementation task may change local semantic routing and capability telemetry only; audit projection and Commit gating need their own explicit contracts and failure/rebuild tests.
Revisit triggers
- The first external audit projection is deployed.
- A concrete external action class is proposed for review gating.
- Audit needs a data class beyond redacted references.
- The Exploration profile needs a new privilege or canonical owner.