Repository navigation
Mission layer: journeys, baseline, assess and evaluate (M9.2, M9.3, M9.10) - #77
Merged
Merged
Conversation
…9.10) aloop mission journeys, baseline, assess and evaluate: user journeys with pinned runners and research-sourced refs, a baseline measured twice within tolerance and confirmed by a human, the state measured exactly as the baseline froze it, and a gap list that evaluate check recomputes. Hardened after an adversarial review (43 findings, each reproduced and now a test): gates decide from the committed, hash-chained ledger.jsonl, never from a status field; measurements, vetoes, retirements and the current version are records; runner scripts are pinned by sha256; NaN, unreported values and malformed files block instead of passing or crashing. Adds baseline restore. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018RxETAY6S1gcmdctBK8a8Z
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 02:47
adeelahmad
pushed a commit
that referenced
this pull request
Oct 20, 2026
…les branch Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012rsDo9GYzNx8tXucywZHnA
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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: the mission layer had only its core (
aloop mission init / check / approve / status). There were no user journeys and no baseline, and nothing measured the product or listed what was left to earn.After:
aloop mission journeys,baseline,assessandevaluaterun the evaluation half of ROADMAP §4.12. Journeys are user paths with GA4-valid step events, research-sourced refs and a pinned runner. A baseline is measured twice within tolerance, confirmed by a human, and replaced only with evidence; an autonomous mission applies a replacement after its veto window. The state is measured exactly as the baseline froze it. The gap list is a pure function of the state, the baseline and the goal, andevaluate checkrecomputes it.An adversarial review (4 lenses, 43 findings, each reproduced) shaped the design: gates decide from the committed, hash-chained
docs/agents/mission/ledger.jsonl, never from astatusfield, because status is outside the digest.How: four areas in
plugin/mission/plus_runner.py, built on the M9.0 contract._mission.pygains the ledger (record,records,newest,covered,ledger_problems; each row carries the hash of the row it follows). The review's findings, now tests:baseline.measuredrecord for the exact content, and the veto window starts at that record.baseline restorelets the human reinstate an archived version.Still open, recorded in ROADMAP:
Evidence
mission-core10,mission-journeys7,mission-baseline11 andmission-evaluate6 checks pass.make cipasses locally: lint, tests, eval-validate, test-hosts and conformance 78/78 (4m44s).Generated by Claude Code