Update environment.py

environment.py

@@ -247,39 +247,39 @@ class CodeReviewEnv:
         if self._last_action_type in ("write_comment", "ask_question", "propose_fix"):
             author_response = self._test_results or ""
         else:
-        author_response = ""
+            author_response = ""
 
         return EnhancedObservation(
-        code_snippet=self._current_code,
-        last_tool_output=self._test_results or "",
-        author_response=author_response,          # ← fixed
+            code_snippet=self._current_code,
+            last_tool_output=self._test_results or "",
+            author_response=author_response,          # ← fixed
 
-        current_test_score=self._current_test_score,
-        current_lint_score=self._current_lint_score,
-        negotiation_score=self._author.get_negotiation_score(),
+             current_test_score=self._current_test_score,
+            current_lint_score=self._current_lint_score,
+            negotiation_score=self._author.get_negotiation_score(),
 
-        previous_test_score=self._previous_test_score,
-        previous_lint_score=self._previous_lint_score,
+            previous_test_score=self._previous_test_score,
+            previous_lint_score=self._previous_lint_score,
 
-        author_confidence=self._author._confidence,
-        author_threshold=self._author.thresholds.get(self._author.personality, 0.5),
+            author_confidence=self._author._confidence,
+            author_threshold=self._author.thresholds.get(self._author.personality, 0.5),
 
-        step=self._step_count,
-        max_steps=self.max_steps,
-        progress_ratio=self._step_count / self.max_steps,
+            step=self._step_count,
+            max_steps=self.max_steps,
+            progress_ratio=self._step_count / self.max_steps,
 
-        tests_run=self._tests_run,
-        linter_run=self._linter_run,
-        docs_queried=self._docs_queried,
+            tests_run=self._tests_run,
+            linter_run=self._linter_run,
+            docs_queried=self._docs_queried,
 
-        last_action_type=self._last_action_type,
-        action_history=self._action_history[-5:],
+            last_action_type=self._last_action_type,
+            action_history=self._action_history[-5:],
 
-        done=self._done,
+            done=self._done,
 
-        bug_description=self._bug_description,
-        comments_count=len(self._comments),
-        )
+            bug_description=self._bug_description,
+            comments_count=len(self._comments),
+            )
     # ===================================================================
     def _compute_dense_reward(
         self,