Repository navigation
feat(harness): pin the review invocation in the adapter contract; protocol 6 (#85) - #228
Merged
Merged
Conversation
…tocol 6 (#85) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refs #85. This completes the v1 slice; see the note below.
The review Atom from #85's first slice (
5f490f1) built a read-only review invocation that was never pinned by the adapter contract. This PR finishes that, per the operator decision recorded in the issue on 2026-10-25:AdapterProtocolVersiongoes from"5"to"6", because the review invocation is a changed adapter invocation.adapterContractDigestnow also coversreview,review+extensionsandreview+modelfor codex, claude-code and cursor. The new"6"digest is pinned, and the historical pins 2–5 are unchanged.TestSliceBAnalysisInstructionNamesLineRangesnow accepts protocol 5 or later instead of exactly"5". This was an approved scope change.docs/atoms.mdstates that the review invocation is part of protocol 6, that saved bindings need a reviewedinit --rebind, and what is deferred.The v1 acceptance is already covered by existing tests on
main: per-adapter read-only flags, extensions refused,GH_TOKEN/GITHUB_TOKEN/CI tokens and plan credentials withheld from the provider, malformed output failing closed, bounded and escaped rendering, and high findings blocking delivery. Deferred (post-v1): the amendment loop, theissuefollow-up policy and learn integration. After this merges, the Lab gets a reviewed launcher-only rebind to protocol 6.Built by Forgecell Molecule
mol-85-764070c59dae6ade5ceb3bcd(plan revision 2). On the candidate tree every check passed, including the full-timeout 20mbaseline. Hand-delivered: the protected regression runs the base contract test, which has no"6"pin, so it fails by design. A clean-shellgo test -timeout 25m ./..., vet and gofmt all pass.🤖 Generated with Claude Code