Skip to content

review: ground a cluster member on its shared anchor, not only the evidence's vocabulary #363

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jwbron merged 3 commits into from
Aug 21, 2026
Merged

review: ground a cluster member on its shared anchor, not only the evidence's vocabulary #363

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ad9753b
[agent/pra42-cluster-grounding] review: ground a cluster member on it…
jwbron Aug 20, 2026
1534d1d
review: record the grounding path per merged copy, pin the anchor pat…
jwbron Aug 20, 2026
899519e
[agent/pra42-cluster-grounding] review: pin a merge outcome on the ca…
jwbron Aug 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/review-cluster-grounding.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"review": minor
---

Run 32390393344 (webapp#41609) posted one finding twice: two sources filed it on the same line of moderation_helpers.go, the claim-clusterer correctly proposed the pair as one cluster, and the grounding tripwire vetoed the merge as "ungrounded" because the cluster's evidence spoke in the hunk's identifiers (`_configIncludesModeration`, `shouldModerateDuringMainCompletion`) while both claims spoke config-side (`pre_flight_moderation_check`, `config_files`), zero shared salient tokens. The evidence is model prose with free word choice, so that check was grading the clusterer's phrasing rather than the identity it asserted. Two changes: an exactly shared anchor (the member sits on the survivor's own line; paths already match structurally) now grounds a proposed member with no vocabulary needed, and salient tokens fold casing styles (`PreFlightModerationCheck` and `pre_flight_moderation_check` are one token) so the vocabulary path tests names, not spellings. Grounding a member against the survivor's own text was considered and rejected: run 30587343777's cap survivor names `staleAfter` in a while-here aside, and the distinct staleAfter finding would falsely ground against it (that counterexample stays pinned in the tests). The 41609 pair is replayed verbatim as a regression fixture and now merges to one comment. Each clusterer-absorbed copy in dispatch-result.json now records which path grounded it (`groundedBy: "anchor" | "evidence"`), so the planned audit of "ungrounded" rejections can tell the two apart, and the clusterer prompt no longer promises the unconditional mechanical discard the code stopped making.
Loading
Loading