Spec uncertainty engine + repoint ledger to @rafters#104
Merged
Conversation
…rtainty engine The CLAUDE.md rewrite (3c6e23b) updated some ledger imports but missed apps/web/src/api/auth.ts and the package.json declarations, leaving the workspace in a broken typecheck state -- the old package no longer resolves on the registry. Swap to @rafters/ledger across auth.ts, apps/web/package.json, and the root onlyBuiltDependencies list. Typecheck restored to green. Add docs/designs/uncertainty-engine.md -- design for the AI honesty layer. Generic input -> prediction -> outcome ledger, per-cohort Brier and reliability diagrams, five-state lifecycle (emitted, witnessed, calibrated, orphaned, retired). Phase 1 unblocks rafters by replacing the ezmode CORE_API ghost binding with a real platform endpoint. Issues #97-103 break out the Phase 1 work. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The institutional read
Other agents build models. Platform audits them. Every confidence number Rafters publishes is grounded in a published reliability record. Same ethic as publishing the revenue split.
The orphan state is load-bearing: silence is its own state, scored separately, surfaced as a metric. Treating silence as agreement poisons calibration upward; treating it as disagreement poisons it downward. Naming it removes the choice.
Phase 1 work breakdown
Issues #97-#103:
Test plan