1. Deny-only Critic veto
Measured: the Critic returned success: true with the reasoning 'having a netherite_pickaxe in their inventory means they have successfully mined gold, stone bricks, bricks and polished andesite', and separately returned success: true while its own evidence line read 'Live Inventory has 0/1 ...'. Both reached completed_tasks.json, which is why the completed count grows while the skill count does not.
mechanical_verdict() in voyager_verification is three-valued: True, False, or None. None means 'this deployment cannot judge this objective from the world', which is not the same as failed. VerifiedCreativeCritic now denies a model success only when mechanical_verdict returns a definite False -- an objective with a countable postcondition whose world state contradicts the claim. Every other verdict, including every objective this deployment cannot measure, still goes to the pinned upstream CriticAgent unchanged. The wrapper can deny a success; it can never cre…
Restore official Voyager decision agents and attest the runtime
naldo
5ddf32a
Remove the local curriculum/action/critic/skill overrides, the
deterministic action parser, the affordance catalog, and the build
blueprints, so Curriculum, Action, Critic and SkillManager are the
upstream implementations at the pinned commit.
The single declared adaptation is the curriculum parse-failure retry
feedback, applied through voyager_runtime_contract and recorded in
.upstream-expected/ for the AST attestation. Skill templates are
quarantined before the learning loop, and template skills can no longer
drive a build catalog.
