feat(advisor): add 0.85 advisory threshold triggering LLM suggestions

- Add advisory_threshold=0.85 field to MetricRule (higher-is-better metrics)
- diagnose() now emits severity='low' for scores in (warning_threshold, 0.85)
- noise_sensitivity (lower-is-better) keeps its existing two-tier thresholds
- writer.py: severity labels mapped to Chinese (严重/警告/待优化)
- llm_analyzer.py: prompt explains low/warning/critical tiers in Chinese
- Tests: 5 new cases for 'low' severity, updated log summary assertions

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

rag_eval/advisor/writer.py

@@ -8,12 +8,22 @@ from .rules import Diagnosis
 
 logger = logging.getLogger("rag_eval.advisor")
 
+# Chinese display labels for each severity tier.
+_SEVERITY_LABEL: dict[str, str] = {
+    "critical": "严重",
+    "warning": "警告",
+    "low": "待优化",
+}
+
 
 def _format_log_summary(diagnoses: list[Diagnosis], advice_path: Path) -> str:
     """Return a single-line log summary of triggered diagnoses."""
     if not diagnoses:
         return "[advisor] 所有指标正常，无需优化建议。"
-    parts = [f"{d.metric}({d.mean_score:.2f}, {d.severity})" for d in diagnoses]
+    parts = [
+        f"{d.metric}({d.mean_score:.2f},{_SEVERITY_LABEL.get(d.severity, d.severity)})"
+        for d in diagnoses
+    ]
     triggered = " ".join(parts)
     return f"[advisor] 触发诊断 {len(diagnoses)} 项: {triggered}  →  {advice_path}"
 
@@ -24,7 +34,8 @@ def _build_fallback_report(diagnoses: list[Diagnosis]) -> str:
         return ""
     lines = ["## 规则诊断（LLM 分析不可用）\n"]
     for d in diagnoses:
-        lines.append(f"### {d.metric}  [{d.severity}]  均值={d.mean_score:.4f}")
+        label = _SEVERITY_LABEL.get(d.severity, d.severity)
+        lines.append(f"### {d.metric}  [{label}]  均值={d.mean_score:.4f}")
         lines.append("\n**可能原因：**")
         for cause in d.root_causes:
             lines.append(f"- {cause}")