feat(advisor): add optimization advisor module

- rag_eval/advisor/: new package with rules engine, LLM analyzer, writer
  - rules.py: 7-metric diagnostic rules (warning/critical thresholds, top-3 low samples)
  - llm_analyzer.py: Chinese optimization report via judge_model, graceful fallback
  - writer.py: writes optimization_advice.md + log summary
  - __init__.py: run_advisor() entry point (no-op when optimization_advisor=False)
- Scenario.optimization_advisor: new bool field (default False)
- ScenarioModel: same field added, loader.py透传
- RunArtifactPaths.advice_md: new path field
- factory.py: build_models() now public; build_metric_pipeline() accepts pre-built llm/embeddings
- runner.py: lifts llm, passes to pipeline and advisor; calls run_advisor() at end
- siemens online YAML: optimization_advisor: true enabled
- tests: 9 rules tests + 6 writer tests, all pass
- docs: advisor section added to engine-flow.md and architecture.md

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

tests/test_advisor_writer.py

@@ -0,0 +1,113 @@
+import shutil
+import unittest
+from pathlib import Path
+
+from rag_eval.advisor.rules import Diagnosis
+from rag_eval.advisor.writer import write_advice, _format_log_summary
+
+
+class TestWriteAdvice(unittest.TestCase):
+    def setUp(self):
+        self.tmp = Path("tests/.tmp/test_advisor_writer")
+        shutil.rmtree(self.tmp, ignore_errors=True)
+        self.tmp.mkdir(parents=True, exist_ok=True)
+        self.advice_path = self.tmp / "optimization_advice.md"
+
+    def tearDown(self):
+        shutil.rmtree(self.tmp, ignore_errors=True)
+
+    def _make_diagnosis(self, metric="faithfulness", severity="warning"):
+        return Diagnosis(
+            metric=metric,
+            mean_score=0.55,
+            threshold=0.7,
+            severity=severity,
+            root_causes=["原因1", "原因2"],
+            suggested_actions=["建议1", "建议2"],
+            low_samples=[
+                {"sample_id": "s1", "question": "问题1", "answer": "答案1",
+                 "ground_truth": "标准1", metric: 0.4},
+            ],
+        )
+
+    def test_write_creates_file(self):
+        diag = self._make_diagnosis()
+        write_advice(
+            diagnoses=[diag],
+            llm_markdown="## faithfulness\n\nLLM 建议内容",
+            advice_path=self.advice_path,
+            scenario_name="test-scenario",
+            run_id="2026-01-01T00-00-00",
+            judge_model="deepseek-v4-flash",
+        )
+        self.assertTrue(self.advice_path.exists())
+
+    def test_write_contains_scenario_name_and_run_id(self):
+        diag = self._make_diagnosis()
+        write_advice(
+            diagnoses=[diag],
+            llm_markdown="## faithfulness\n\nLLM 建议",
+            advice_path=self.advice_path,
+            scenario_name="siemens-test",
+            run_id="2026-01-01T00-00-00",
+            judge_model="deepseek-v4-flash",
+        )
+        content = self.advice_path.read_text(encoding="utf-8")
+        self.assertIn("siemens-test", content)
+        self.assertIn("2026-01-01T00-00-00", content)
+
+    def test_write_contains_llm_markdown(self):
+        diag = self._make_diagnosis()
+        write_advice(
+            diagnoses=[diag],
+            llm_markdown="## faithfulness\n\n具体建议文本",
+            advice_path=self.advice_path,
+            scenario_name="test",
+            run_id="rid",
+            judge_model="model",
+        )
+        content = self.advice_path.read_text(encoding="utf-8")
+        self.assertIn("具体建议文本", content)
+
+    def test_write_fallback_when_no_llm_markdown(self):
+        """When llm_markdown is empty, writer emits rule-only report."""
+        diag = self._make_diagnosis()
+        write_advice(
+            diagnoses=[diag],
+            llm_markdown="",
+            advice_path=self.advice_path,
+            scenario_name="test",
+            run_id="rid",
+            judge_model="model",
+        )
+        content = self.advice_path.read_text(encoding="utf-8")
+        self.assertIn("faithfulness", content)
+        self.assertIn("原因1", content)
+
+    def test_log_summary_format(self):
+        diags = [
+            self._make_diagnosis("faithfulness", "critical"),
+            self._make_diagnosis("context_recall", "warning"),
+        ]
+        summary = _format_log_summary(diags, self.advice_path)
+        self.assertIn("faithfulness", summary)
+        self.assertIn("critical", summary)
+        self.assertIn("context_recall", summary)
+        self.assertIn("warning", summary)
+
+    def test_write_empty_diagnoses_still_creates_file(self):
+        write_advice(
+            diagnoses=[],
+            llm_markdown="",
+            advice_path=self.advice_path,
+            scenario_name="test",
+            run_id="rid",
+            judge_model="model",
+        )
+        self.assertTrue(self.advice_path.exists())
+        content = self.advice_path.read_text(encoding="utf-8")
+        self.assertIn("未发现明显指标异常", content)
+
+
+if __name__ == "__main__":
+    unittest.main()