A cleanup release with a rule attached to it.
The tool output limit was enforced in the tool runner, and these three tools were doing their own
formatting and not passing through it: directory_tree (a tree of a large repo),
read_multiple_files (several files at once, exactly the tool most likely to return something huge),
and glob (a pattern matching a lot of files). All three now go through the shared snipping
function.
The rule that comes out of this, and the reason I record it: a limit enforced in one place is not a limit. Each tool that formats its own output is a hole in the limit, and the holes are the tools with the biggest outputs. The fix is not to patch three tools; it is a shared function, and a convention that tool output goes through it.
Small fix in the same run: the CLI stopped printing an empty thinking block for reasoning models, which is the kind of line that is entirely about not showing the user a box that contains nothing.
Related, because it is the same class of bug in the same tool set: 1.5.5 (4 August) catches
search_content not respecting the limit either, and 1.5.6 (4 August) makes list in the
search_content skill use it. Four releases in four days, all tightening the same screw.