refactor: update Judge to use Runner protocol and RunnerResult

- Judge now accepts Runner instead of ModelRunner
- evaluate() calls runner.run(output_type=...) instead of invoke_structured_model
- response.parsed replaces StructuredResponse.data; None guard added
- evaluate_messages() accepts RunnerResult instead of ModelResponse
- Tests updated to use RunnerResult and mock_runner.run

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

Author: jsonbailey

packages/sdk/server-ai/src/ldai/client.py

@@ -339,7 +339,7 @@ def _create_judge_instance(
             if not provider:
                 return None
 
-            return Judge(judge_config, provider, sample_rate=sample_rate)  # type: ignore[arg-type]
+            return Judge(judge_config, provider, sample_rate=sample_rate)
         except Exception as error:
             return None
 

packages/sdk/server-ai/tests/test_judge.py

@@ -333,7 +333,7 @@ async def test_evaluate_uses_instance_sample_rate_when_arg_omitted(
 
         assert isinstance(result, JudgeResult)
         assert result.sampled is False
-        mock_runner.invoke_structured_model.assert_not_called()
+        mock_runner.run.assert_not_called()
 
     @pytest.mark.asyncio
     async def test_evaluate_arg_overrides_instance_sample_rate(
@@ -346,7 +346,7 @@ async def test_evaluate_arg_overrides_instance_sample_rate(
 
         assert isinstance(result, JudgeResult)
         assert result.sampled is False
-        mock_runner.invoke_structured_model.assert_not_called()
+        mock_runner.run.assert_not_called()
 
 
 class TestJudgeEvaluateMessages: