test: isolate CLI output capture with monkeypatch/redirect to fix stdout corruption in full suite runs (Issue #178)

- Replace raw patch("sys.stdout") and contextlib.redirect_stderr with pytest MonkeyPatch or contextlib redirect scoped to main calls in CLI tests (create_*, prs, python_cli, manage_labels, merge_pr, review_pr).
- Add regression tests in test_review_proofs.py for stdout/stderr remaining usable.
- Ensures normal pytest summary output without junitxml workaround; improves review validation reporting per #173.
- No behavior change to production code or gates.

Refs #178

tests/test_review_pr.py

@@ -79,15 +79,19 @@ class TestAPIPayload(unittest.TestCase):
         self.assertEqual(mock_api.call_count, 0)
 
     def test_merge_flag_message_points_to_gated_workflow(self):
+        from _pytest.monkeypatch import MonkeyPatch
         import io
-        import contextlib
         with patch("review_pr.get_auth_header", return_value=FAKE_CREDS), \
                 patch("review_pr.api_request") as mock_api:
             buf = io.StringIO()
-            with contextlib.redirect_stderr(buf):
+            monkeypatch = MonkeyPatch()
+            monkeypatch.setattr(sys, "stderr", buf)
+            try:
                 rc = review_pr.main([
                     "--pr-number", "81", "--event", "APPROVE", "--merge",
                 ])
+            finally:
+                monkeypatch.undo()
         self.assertEqual(rc, 2)
         self.assertEqual(mock_api.call_count, 0)
         msg = buf.getvalue().lower()