feat(6251): the rule arms can be reviewed — menus_to_review re-runs prompt_rule, pre_tool_rule and write_path_rule

A rule arm logs its query, floor, budget and project, which is everything
semantic_search_rules takes, so a logged call is re-run to a depth past its
budget and judged like an auto_inject menu. within_budget is the arm's own
cut: inside the budget and, for the banded command and write arms, inside the
band of the top hit. "Opened after" reads rule pulls, and rules created
after the call are dropped as notes are.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/grimoire/mcp/tools/retrieval_review.py

@@ -42,7 +42,11 @@ async def menus_to_review(
 
     Args:
         source: the arm to review. Only arms whose search can be re-run
-            exactly are offered; today that is `auto_inject`.
+            exactly are offered: `auto_inject`, and the rule arms
+            `prompt_rule`, `pre_tool_rule` and `write_path_rule`. A rule
+            line's passage is the trigger the arm matched, and for the
+            command and write arms `within_budget` also needs the line to
+            sit inside the band of the top hit, as it did when shown.
         n: how many calls to sample, 1–20. Random among the calls you have not
             judged, so a review does not describe one afternoon.
         days: how far back to sample from.