Fix bot review false positives: drop fabricated 80-char rule, clarify enable/disable

The PR-review bot's prompt instructed it to flag lines over 80 characters,
but no such rule exists in the repo (markdownlint MD013 is disabled and
STYLE.md never mentions it). Remove that instruction from pr-review.yml.

Also clarify the STYLE.md word list so "turn on/off" applies to UI toggles
while "enable/disable" stays acceptable in general prose, matching STYLE.md's
own example. This stops the bot from flagging every "enable" as a violation.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/workflows/pr-review.yml

@@ -50,7 +50,6 @@ jobs:
 
         ### 3. Markdown Formatting
         - Poor markdown syntax (unclosed code blocks, broken lists, indentation issues, etc.)
-        - Line wrapping over 80 characters (except links, code blocks, tables)
 
         ### 4. AI-Generated Patterns (HIGH PRIORITY)
         Flag AI-isms from STYLE.md:

STYLE.md

@@ -464,6 +464,12 @@ _1. Optional. Enter a description for the job._
 | use                                   | utilize                |
 | help                                  | facilitate             |
 
+Use "turn on" and "turn off" for UI toggles, switches, and settings a user
+flips in the interface. In general prose, "enable" and "disable" are
+acceptable when describing a feature or capability becoming available — for
+example, "When you enable auto-log-out, your users are logged out." Don't
+treat every "enable" or "disable" as a violation.
+
 ### Version numbers
 
 - Use "earlier" not "lower": Docker Desktop 4.1 and earlier