Repository navigation
Mission loop review fixes (M9.8): restore, unmeasurable and vetoed proposals, block keys - #84
Merged
Merged
Conversation
…, block keys - An archived (once-confirmed) baseline version is never a replacement, so a human restore is not undone. - A proposed version that baseline measure would refuse asks for a new version, or a journey that supersedes a listed one that no longer runs as pinned; a raised bar after nothing to earn asks for a new version. - A vetoed content is named (by, when, why) and keyed on the content. - Every BLOCKED has its own key, so due tells the human each new block. - The ledger is folded by time; a committed hard ethics review fails closed; a state needs its state.assessed record; only the GOALS grant resets the failed-goal count; the fingerprint covers spend, reviews, intents, plans, the lock and grants. - Gaps M9.26 (sprint history) and M9.27 (eval trust); M9.24 adds the budget stop. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Aw6CiQcdpzdzZZXKf8WbUM
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…eck gets its id A derived goal's check waits on its ethics review, which is the Ethics Reviewer's step: area_checks marks those blocks foreign, so the planner's stop notes them instead of blocking. Gap rows renumbered to M9.30/M9.31. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0197nSutKR1QAAqgJhFZ8fPj
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
… waits for the human's typed line Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018RxETAY6S1gcmdctBK8a8Z
This was referenced Oct 20, 2026
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.
Requested by Adeel · project thread
Before: an adversarial review of
mission tick(#75) found 13 ways it could send the loop wrong:baseline restore, it kept asking for a new version that would undo the restore.baseline measurerefuses, until the repeat guard blocked.duestayed silent on the second.After: each of those, and the smaller ones below, is fixed and pinned by a test that failed on the old code.
How.
baseline.confirmedrecord covered is archived, never a replacement candidate. Only the human'sbaseline restorebrings it back, matchingbaseline.py.baseline measurechecks it (standing_problems, plus each listed journey'sjourneys.problems, which covers runner-file pins).DEFINE_JOURNEYS: a journey that supersedes it.BASELINE"can no longer be measured: propose a new version", under its own key.BASELINE"propose a new version" (it lists them), notDEFINE_JOURNEYSforever.bind), so re-proposing it is the same work.S<n>. A new block always reaches the human.ts(stable), as the core'srecords()reads them, so a union merge cannot make an older pick win.hardblocks, even when the run log is gone or holds only a clear review.state.assessedrecord (asassess.latestdoes).GOALS) resets that count./aloop:missionrows and the tick docstring are updated. The fresh-checkout claim is narrowed to what the ledger holds.New gap items (§4.12, one-line reasons):
mission.budget_exhausted, so a hit cap survives a fresh checkout.Evidence.
mission-tick.test.py: 27 checks (was 20). The 7 new sections each failed against the previoustick.py, and each now passes:EVALUATE, notBASELINE;dueexits 3 twice;mission-*.test.py,make pycheckandcheck-trackingpass locally.Generated by Claude Code