Add semantic-drift signals and a deterministic drift-evaluator for confidence decay#89
Open
danielbdyer wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Description
StepExecutionReceiptto includesemanticConsistencysignals and populated them during runtime step execution inlib/runtime/scenario.ts.\lib/application/drift-evaluator.tswhich ingests run records and produces deterministic decay evaluations (total decay, floor, suppression counts, applied-signal rationale).\lib/application/confidence.tsso overlayscoreis reduced by the computed decay and decay lineage is recorded inArtifactConfidenceRecord.lineage.decay.\confidenceDecay) to tune per-artifact decayrates,minimumFloor, andsuppressionWindowRuns, and updated the default.tesseract/policy/trust-policy.yaml.\semantic-driftinbox kind, asemantic-drifthotspot kind, and scorecard fields (semanticDriftHotspotCount,runtimeFailureClasses) to surface actionable groupings and distinct failure classes.Testing
npm test -- tests/domain-validation-lanes.spec.ts tests/hotspots.spec.ts tests/vscode-integration.laws.spec.ts, all tests passed (24 passed).\npm run types/npm run build;npm run buildfailed due to pre-existing unrelated TypeScript issues inlib/application/replay-interpretation.tsandlib/infrastructure/mcp/dashboard-mcp-server.tsnot introduced by this change (noted during validation).Codex Task