Update environment.py

environment.py

@@ -498,7 +498,7 @@ class CodeReviewEnv:
                 lint_results=self._lint_results,
                 doc_results=self._doc_results,
                 proposed_fix=None,
-                original_code=self._current_code
+                original_code=original_buggy
             )
             
             self._comments.append(f"Author: {response}")
@@ -513,6 +513,7 @@ class CodeReviewEnv:
                 base_reward = -0.05
                 self._done = True
             else:
+                original_buggy = self._current_code
                 self._current_code = action.fix_code
 
                 runner = TestRunner(self._current_bug_id)