docs: review-classifier truncation sentences in active voice

docs/swarm/review-classifier.md

@@ -235,8 +235,8 @@ The model answers each classification in JSON. The answer holds:
 
 - a **verdict**, one of _match_, _no match_ or _not applicable to this PR_
 - a **certainty** from 0 to 100, how sure the model is of that verdict
-- a **reason**; one over 500 characters is cut to 500, ending in `…`, and the
-  verdict and certainty are kept
+- a **reason**; the classifier truncates one over 500 characters to 499 plus
+  `…`, and keeps the verdict and certainty
 
 An answer:
 

swarm-review-classifier/README.md

@@ -18,8 +18,8 @@ forge and holds no forge credential.
 - One `claude --print` per classification, with no session, no tools
   (`--tools ""`), no MCP server, its own empty directory and
   `ANTHROPIC_API_KEY` in its environment only.
-- An answer is a JSON object with a verdict, a certainty and a reason; a
-  reason over 500 characters is cut to 500, ending in `…`. A failed run, a
+- An answer is a JSON object with a verdict, a certainty and a reason; the
+  classifier truncates a reason over 500 characters to 499 plus `…`. A failed run, a
   timeout or an answer that doesn't validate leaves that row without a verdict, and it doesn't count.
 - A run with no API key, or with no classification answered, fails as a
   whole: the caller sees an error, never a verdict.