A review step can post all its findings to a pull request as one capped comment.
What's wrong with this entry?
A new prompt drives a posting step that takes a block of review findings and posts them to a GitHub pull request as one plain comment, capped at 40,000 characters. It is allowed exactly one write and nothing else: no review submission, no other API call, and no acting on instructions found inside the findings themselves.
add_issue_comment is the only write you may make, exactly once
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.219
PR-review anchor repo names reject "." and ".."
Both mention code review
-
v2.1.219
Composed PR-review publish refusal explains whether it is a live switch
Both mention code review
-
v2.1.239
Code review findings now carry a short summary and a category
Both mention code review