eval: record baseline-aware soft-start observations - #109
Merged
Conversation
Issue #108 の登録済みprivate snapshotに対してdevelopmentを一度だけ実行し、8 hard gate全通過を確認したためholdoutを一度だけ開いた。両stageは支持、verifier pass、snapshot、source database、live configは不変だった。freeze artifact、code、docs、testsは変更せず、exclusive observed JSON 2件だけを記録する。支持範囲は固定local snapshot上のcutover候補に限定する。
lipluscodex
commented
Aug 21, 2026
lipluscodex
left a comment
Member
Author
There was a problem hiding this comment.
親セルフレビュー: PASS
- freeze merge commit
d73d115からの差分は、development / holdout observed JSON 2件だけです。protocol / fixture / schedule / gate / schema / audit / code / docs / testsは不変です。 - main上のmanifest first-addition commitでregistered outputs不在を維持した後、developmentとholdoutを各一度だけexclusive実行したphase provenanceを確認しました。
- 親側で両stage verifierを再実行し、development / holdoutとも
completed / 支持、8/8 hard gate passとして再計算一致しました。 - baseline-aware q3 boundary、confirmed-only boundary、soft-start schedule、learning latency / final quality、negative provisional bound、control safety、mutation locality / source isolationの全gateがpassです。
- development SHA
9aa5e60feb226eff4920f82eb6e995290aa75eef77a43ad83f0d1dcebaa1e53d、holdout SHAbdaa8e4ef14e2742b4df3ba6ad0559021f527b4b94d0f51175db666b2a3fc8deを確認しました。 - snapshot SHAは両stageの前後で登録値と一致し、source DB / live configは不変です。public resultにprivate path、node本文、credential-shaped value、replacement characterは検出されません。
- full 251 tests、eval smoke、GitHub CI、Optional MCP adapterはpass。残存blocking findingはありません。
次の処理: squash merge。支持範囲は固定local snapshot上のsoft-start cutover候補に限定し、live cutoverは実際のMCP code/runtime/configを確認する別段階で行います。
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #108
developmentを一度だけ実行し、全8 hard gate通過を確認したためholdoutを一度だけ開きました。両stageは
支持で、凍結verifier、privacy、source isolationを通過しています。freeze artifact、code、docs、testsは変更せず、exclusive observed JSON 2件だけを追加します。結果は固定local snapshot上のcutover候補に限定し、source database、live config、library defaultは変更しません。