style: fix ruff formatting violations in eval packages

Ruff format check was failing CI for uipath and uipath-eval packages.
Applied auto-format to 4 source files and 2 test files.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: rakesh-uipath

packages/uipath-eval/src/uipath_eval/_helpers/evaluators_helpers.py

@@ -21,6 +21,7 @@
     "!=": "ne",
 }
 
+
 def extract_tool_calls_names(spans: Sequence[ReadableSpan]) -> list[str]:
     """Extract the tool call names from execution spans IN ORDER.
 

packages/uipath-eval/src/uipath_eval/evaluators/base_legacy_evaluator.py

@@ -20,6 +20,7 @@
 
 __all__ = ["track_evaluation_metrics"]
 
+
 # Legacy evaluator config (non-generic version for simplicity)
 class LegacyEvaluatorConfig(BaseEvaluatorConfig[BaseEvaluationCriteria]):
     """Configuration for legacy evaluators."""

packages/uipath/src/uipath/eval/evaluators/__init__.py

@@ -48,7 +48,11 @@
 
 EVALUATORS: list[type[BaseEvaluator[Any, Any, Any]]] = [
     # Replace uipath_eval.ExactMatchEvaluator with local version (has attachment support)
-    *(e for e in _EVAL_EVALUATORS if e.get_evaluator_id() != ExactMatchEvaluator.get_evaluator_id()),
+    *(
+        e
+        for e in _EVAL_EVALUATORS
+        if e.get_evaluator_id() != ExactMatchEvaluator.get_evaluator_id()
+    ),
     ExactMatchEvaluator,
     LLMJudgeOutputEvaluator,
     LLMJudgeStrictJSONSimilarityOutputEvaluator,

packages/uipath/src/uipath/eval/evaluators/legacy_exact_match_evaluator.py

@@ -57,7 +57,9 @@ async def evaluate(
             EvaluationResult: Boolean (plain match) or NumericEvaluationResult (line-by-line)
         """
         if self.line_by_line_evaluation:
-            return await self._evaluate_line_by_line(agent_execution, evaluation_criteria)
+            return await self._evaluate_line_by_line(
+                agent_execution, evaluation_criteria
+            )
         return await self._evaluate_exact(agent_execution, evaluation_criteria)
 
     async def _evaluate_exact(

packages/uipath/tests/evaluators/test_evaluator_helpers.py

@@ -10,6 +10,7 @@
 from typing import Any
 
 import pytest
+from uipath_eval.models.models import ToolCall, ToolOutput
 
 from uipath.eval._helpers.evaluators_helpers import (
     extract_tool_calls,
@@ -20,7 +21,6 @@
     tool_calls_order_score,
     tool_calls_output_score,
 )
-from uipath_eval.models.models import ToolCall, ToolOutput
 
 
 class TestToolCallsOrderScore:

packages/uipath/tests/evaluators/test_evaluator_methods.py

@@ -16,6 +16,12 @@
 import pytest
 from opentelemetry.sdk.trace import ReadableSpan
 from pytest_mock.plugin import MockerFixture
+from uipath_eval.models.models import (
+    AgentExecution,
+    ToolCall,
+    ToolOutput,
+    UiPathEvaluationError,
+)
 
 from uipath.eval.evaluators.base_evaluator import BaseEvaluatorJustification
 from uipath.eval.evaluators.contains_evaluator import (
@@ -57,12 +63,6 @@
     ToolCallOutputEvaluatorJustification,
 )
 from uipath.eval.models import NumericEvaluationResult
-from uipath_eval.models.models import (
-    AgentExecution,
-    ToolCall,
-    ToolOutput,
-    UiPathEvaluationError,
-)
 
 
 @pytest.fixture