Repository navigation
Mission layer hardening: the records decide (second review of M9.0/M9.2/M9.3/M9.10) - #78
Merged
Merged
Conversation
….2/M9.3/M9.10) A second 4-lens adversarial review found 31 unique ways to weaken the evaluation or crash a gate; each is now a test. - Ledger: nothing decides from or records past a broken ledger (M.ledger_block, M.LedgerBroken); the lost-row cross-check is scoped to the branch that recorded the row; junk run-log lines are skipped; state.assessed, ethics.reviewed/blocked and goal.derived/met are rows. - Journeys: frozen, pinned and retired come from the confirmation and retirement records, never from files; runner.files must pin every project file the command runs (no links, inline code or outside scripts); a judged metric pins its rubric by sha256; a tighter operator is not a weakening; unknown flags exit 64. - Baseline: an edited, moved or malformed current version decides nothing; a veto binds content in any order and is decided from records; a version once confirmed comes back only by restore. - Evaluate: every input is the content its record covers (state, baseline, frozen journeys, the record-activated goal and its targets); evaluate check recomputes metrics and refuses a disagreeing state. - Core: UTF-8 in any locale (argv, files), a lone surrogate blocks, ethics gains a draft status, GA4 reserved names are one list. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018RxETAY6S1gcmdctBK8a8Z
adeelahmad
marked this pull request as ready for review
October 20, 2026 03:28
…r-plan-6re55w # Conflicts: # CHANGELOG.md # docs/ROADMAP.md
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
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
Master (#78) made state.assessed, goal.derived and goal.met ledger events and the Evaluator reads a goal's activity from the ledger. goal.py now records goal.derived and goal.met with M.record (subject: the goal file), reads its derived record from the ledger, refuses to decide past a broken ledger, and leaves the state.assessed check to evaluate's own problems(). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012rsDo9GYzNx8tXucywZHnA
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
#78 reads replacements from the journey.retired record's data, so the test's hand-made retirement records journey_id, replaced_by and its sha256. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012Ro7iYo3scQt6vAuAWdYpV
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…rgery paths PR #82 (M9.17) makes a mission grant need the human's own words: a prompt line the UserPromptSubmit hook captured. gate-mission-scope now denies the ways around that, for every agent and the supervisor: - a write (Write/Edit/patch or a Bash write) under <run data>/transcripts/, the captured prompts; - a Bash `transcripts prompt|record|snapshot|stop|stage-in`, the hooks' own commands; - where a mission is set, a host session started from a tool call (`claude -p`, `codex exec`, `opencode run`, or any prompt), since its prompt fires UserPromptSubmit too. A host's tools (`claude plugin validate`, `--version`, `opencode models`) stay allowed; no mission, no rule. Test: mission-scope-bash.test.py (220 rows; 13 of the 18 new ones fail on the previous gate), mission-roles.test.py (32 checks); make ci, conformance 78/78 and plugin validate --strict pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0197nSutKR1QAAqgJhFZ8fPj
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: after #77, a role that could edit artifact files, but not the ledger, could still weaken the evaluation or crash a gate. A second adversarial review (4 lenses) found 31 unique ways, each with a repro script. Some examples:
runner.filesmiss the script the command really runs.--replace-bysilently record a broader approval.mission init.After: the ledger records decide what a file cannot, and each finding is a test.
How:
_mission.py)M.ledger_blockat the top of every deciding command, andM.recordraisesM.LedgerBrokenrather than chain a row past a broken one.state.assessed,ethics.reviewed,ethics.blocked,goal.derivedandgoal.metare ledger rows.journeys) and the retirement records, never from files.runner.filesmust pin every project file the command runs. It refuses links, inline code (-c,-e) and scripts outside the project, andjourneys checkhashes the pinned files.query.rubric_sha256, and assess passes it tojudge.verdict.<=→<is tighter, not weaker.--k=vworks, and an unknown flag exits 64 in every area.baseline restore.evaluate checkrecomputesmetricsand refuses a state whose runs disagree.M.cli_text).ethicsgains adraftstatus.Known gap, recorded in ROADMAP with M9.9 and M9.17: on a checkout without the run log, removing the newest ledger rows is not detected.
Evidence
mission-core12,mission-journeys11,mission-baseline13 andmission-evaluate8. That is 15 new checks, each written RED first against the reproduced finding.make cipasses locally: fmt, lint, test, eval-validate, test-hosts and conformance (3m01s).Generated by Claude Code