Docs update

Author: Shashikant86

tests/rlm/test_phase3.py

@@ -370,9 +370,9 @@ def test_benchmark_cases_have_pure_rlm_env(self):
         for preset in ["oolong_style", "browsecomp_style", "token_efficiency"]:
             cases = get_benchmark_cases(preset)
             for case in cases:
-                assert (
-                    case.environment == "pure_rlm"
-                ), f"{preset}/{case.case_id} should use pure_rlm"
+                assert case.environment == "pure_rlm", (
+                    f"{preset}/{case.case_id} should use pure_rlm"
+                )
 
     def test_benchmark_cases_have_reasonable_timeouts(self):
         """Test that paper benchmarks have appropriate timeouts."""

tests/test_retry.py

@@ -83,9 +83,9 @@ def failing_operation():
         with pytest.raises(ValueError):
             controller.execute_sync_with_retry(failing_operation, "test_op")
 
-        assert (
-            attempt_count == max_attempts
-        ), f"Expected {max_attempts} attempts, got {attempt_count}"
+        assert attempt_count == max_attempts, (
+            f"Expected {max_attempts} attempts, got {attempt_count}"
+        )
 
     @pytest.mark.asyncio
     async def test_async_retry_respects_max_attempts(self):

tests/test_security_validator.py

@@ -209,6 +209,6 @@ class MockConfig:
         validator = SecurityValidator()
 
         # Check module code (where calculator_tool is defined)
-        assert not validator.has_eval(
-            program.module_code
-        ), f"Generated module code should not contain eval():\n{program.module_code}"
+        assert not validator.has_eval(program.module_code), (
+            f"Generated module code should not contain eval():\n{program.module_code}"
+        )