Skip to content

Review: the reviewer can read and cite recorded decisions, and an open finding is not raised twice (#634) - #636

Merged
kirkmarple-clockgrove merged 2 commits into
mainfrom
fix/634
Nov 19, 2026
Merged

kirkmarple-clockgrove merged 2 commits into
mainfrom
fix/634

Conversation

@kirkmarple-clockgrove

Copy link
Copy Markdown
Contributor

Closes #634

What changes

  1. The reviewer can read every decision. Each reviewer call (the first pass and its rerun) goes through reviewerCall, which writes $PENDULUM_IN first: issue.md and decisions.md, the latter with every trusted decision, uncut, each heading carrying its key. The write uses only what the stage already holds, so it reads nothing from GitHub and does not touch the checkout while the required checks run beside the reviewer. The prompt's decisions section shows the same keys, and its cut note now says to read the file "before you judge". The worker's section and note are unchanged.
  2. A new judgment beside deferred: {"met": false, "decision": "<key>"}. reviewPost takes the stage's trusted decisions (authors with write access) and looks the key up in a Map of their keys. On an exact hit it adds no comment and the body line reads not met; assigned by <author>'s decision <link>. Any other key, and every caller that passes no decisions (a session's post-review, the bench replay), is a plain not met with its comment. met stays false. Decisions now carry url (GitHub's html_url). Documented in reviewerPrompt, the review skill's reference.md and docs/PLAN.md; bench/skills.json re-recorded.
  3. No second comment for an open finding. When an earlier review of Pendulum's exists and the answer judges an entry not met, the stage reads Pendulum's own open findings (unaddressedReviewComments, never a third party's or a writer's comment) and reviewPost adds no "not met" comment for an entry one of them already carries. The body line says its finding is already open. A failed read posts the comment as before; an outage ends the stage as on any read.

Trust

The key is only ever matched against the stage's own trusted decisions. Text in the reviewer's answer, the PR body, a reply or an untrusted comment cannot supply one: a key that is not in that list changes nothing. Whether the decision really assigns the entry elsewhere stays the reviewer's judgement, as the issue says.

Tests

Three regression tests, each failing on main:

  • handoff.test.mjs: a reviewer call starts with decisions.md holding every trusted decision under its key, those the prompt cuts included (real openHandoff, reviewerCall and the sandboxed write).
  • exit.test.mjs: a trusted key gets no comment and the body names the decision; an unknown key is a plain not met.
  • exit.test.mjs: an entry with an open finding gets no second comment.

One existing assert changed: foundation.test.mjs pins the review job's reviewPost(...) call as source text, so its pinned string gains the two new arguments.

🤖 Generated with Claude Code

https://claude.ai/code/session_017VqP6hg8ahWzteM9zqi8pU

…n finding is not raised twice (#634)

The reviewer's prompt points at $PENDULUM_IN/decisions.md for the decisions
it cuts for length, but the review stage first wrote that folder just before
the answer pass. Each reviewer call now starts with the issue and every
trusted decision written there, uncut, each under its key, and the cut note
tells the reviewer to read them before it judges.

An entry a maintainer's decision assigns outside the PR can be judged
{"met": false, "decision": "<key>"}. reviewPost keeps it only when the key
is exactly the key of one of the stage's trusted decisions (a map lookup):
it adds no comment, and the review body lists the entry as not met, assigned
by that decision, with its author and link. Any other key is a plain not met.

reviewPost adds no "not met" comment for an entry whose finding from an
earlier review of Pendulum's is still open on the PR.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017VqP6hg8ahWzteM9zqi8pU
…rst)

Review of #636: reviewsCover and coveredHead differ when a marked review has no commit_id; gating both on scope.first keeps them in step.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017VqP6hg8ahWzteM9zqi8pU
@kirkmarple-clockgrove
kirkmarple-clockgrove added this pull request to the merge queue Nov 19, 2026
Merged via the queue into main with commit 656f60c Nov 19, 2026
10 checks passed
@kirkmarple-clockgrove
kirkmarple-clockgrove deleted the fix/634 branch November 19, 2026 00:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Review: recorded decisions not readable by the reviewer, and an entry a decision assigns elsewhere can only be a finding, so it Blocks

1 participant