Skip to content

skills(review-reviewers): name pull_request_review self-trigger variant - #707

Merged
max-sixty merged 1 commit into
mainfrom
hourly/review-27736348149
Jun 18, 2026
Merged

max-sixty merged 1 commit into
mainfrom
hourly/review-27736348149

Conversation

@tend-agent

Copy link
Copy Markdown
Collaborator

What

Name the pull_request_review self-trigger variant explicitly in the review-reviewers non-issues entry for tend-mention firing on the bot's own activity.

Why

The non-issues list already documents tend-mention self-triggering on the bot's own issue_comment events and silent-exiting, and states that sender/commenter-based filters are not the accepted shape (only label-based skips are). The same mechanism fires when the bot's own tend-review review mirrors back as a pull_request_review event — but the entry only named issue_comment, so the review-mirror variant wasn't covered by name.

review-reviewers has been tracking this variant as a carry observation with an explicit codification threshold (≥3 occurrences). This hour it recurred 4× in a single cycle (run 27736348149), well past threshold:

Run PR Bot review that mirrored back
27733853442 #703 APPROVED 03:02:10Z
27734197509 #704 APPROVED 03:12:07Z
27734337256 #704 APPROVED 03:16:09Z
27735172009 #705 COMMENTED→APPROVED 03:28–03:41Z

All four are the bot's own reviews (PRs authored by max-sixty) firing pull_request_review → tend-mention, which then silent-exits via the self-conversation guard. This is correct, accepted behavior — the change only documents the variant so future review-reviewers runs map it to the existing non-issue instead of re-analyzing it or proposing a (rejected) sender filter.

Scope

One-sentence addition to the existing entry. No behavioral change; the runtime self-trigger handling is unchanged and remains correct.

Evidence log (accumulated carry history): https://gist.github.com/530887e60f9483c8f094304bfe38ea57

The non-issues entry for tend-mention firing on the bot's own activity
only named issue_comment events. The same self-trigger fires when the
bot's own tend-review review mirrors back as pull_request_review; the
review-reviewers carry tracked this variant and it has now crossed the
codification threshold (4 occurrences in one cycle). Name it explicitly
so future runs map it to the existing non-issue rather than re-analyzing.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@tend-agent tend-agent added the claude-behavior Behavioral issues found by review-reviewers label Jun 18, 2026
@max-sixty
max-sixty merged commit 579b646 into main Jun 18, 2026
5 checks passed
@max-sixty
max-sixty deleted the hourly/review-27736348149 branch June 18, 2026 08:54
@max-sixty max-sixty mentioned this pull request Jun 23, 2026
max-sixty added a commit that referenced this pull request Jun 23, 2026
Bumps generator version to 0.1.7, syncs the lockfile, and adds the
`## 0.1.7` CHANGELOG section (published verbatim as the GitHub Release
notes on tag push).

Changes since 0.1.6: pin actions/checkout to v7 with review opting into
the fork-PR checkout guard (#725); bump claude-code to 2.1.185 (#719);
running-in-ci surfaces blocking scope rules instead of routing around
them (#717) and caps CI-poll loops to the Bash 10-min limit (#695);
nightly workflow-regen bases its worktree on an open PR rather than
branch-ref existence (#721); de-duplicate composite-action step bodies
under shared/steps/ with harness-named action paths (#712); correct the
codex effort list (#710); review-reviewers and worker-deploy doc fixes
(#707, #711).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

claude-behavior Behavioral issues found by review-reviewers

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants