fix(advisor): fix LLM API call, wire advice_markdown to webapp, update .env.example timeouts

- llm_analyzer.py: use llm.langchain_llm.ainvoke() (correct RAGAS 0.4.3 API)
- webapp/models.py: add advice_markdown field to ReportData
- webapp/services/run_reader.py: add read_advice_markdown() reading optimization_advice.md
- webapp/services/report_builder.py: pass advice_markdown into ReportData
- .env.example: OPENAI_TIMEOUT_SECONDS 30→180, RAGAS_METRIC_TIMEOUT_SECONDS 45→300

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

.env.example

@@ -5,15 +5,15 @@
 
 OPENAI_API_KEY=your-api-key
 OPENAI_BASE_URL=http://6.86.80.4:30080/v1
-OPENAI_TIMEOUT_SECONDS=30
+OPENAI_TIMEOUT_SECONDS=180
 
 # 默认评测模型（可在场景 YAML 或 Web 控制台 LLM 配置中覆盖）
 RAGAS_JUDGE_MODEL=deepseek-v4-flash
 RAGAS_EMBEDDING_MODEL=text-embedding-v3
 
-# 评估并发控制
+# 评估并发控制（启用 7 个指标时建议 RAGAS_METRIC_TIMEOUT_SECONDS=300）
 BATCH_SIZE=8
-RAGAS_METRIC_TIMEOUT_SECONDS=45
+RAGAS_METRIC_TIMEOUT_SECONDS=300
 
 
 # ===== 阿里云文档解析（dataset build 功能需要） =====

rag_eval/advisor/llm_analyzer.py

@@ -87,8 +87,9 @@ async def analyze(
     try:
         logger.info("[advisor] calling LLM for optimization analysis  scenario=%s", scenario_name)
         from langchain_core.messages import HumanMessage
-        result = await llm.agenerate(texts=[[HumanMessage(content=prompt)]])
+        # Use the underlying langchain chat model directly (RAGAS LangchainLLMWrapper wraps BaseChatModel)
-        text = result.generations[0][0].text.strip()
+        response = await llm.langchain_llm.ainvoke([HumanMessage(content=prompt)])
+        text = response.content.strip()
         logger.info("[advisor] LLM analysis complete  chars=%d", len(text))
         return text
     except Exception as exc:

webapp/models.py

@@ -73,6 +73,7 @@ class ReportData(BaseModel):
     groupings: dict[str, list[GroupStat]] = Field(default_factory=dict)
     lowest_samples: list[SampleScore] = Field(default_factory=list)
     summary_markdown: str = ""
+    advice_markdown: str = ""  # optimization_advice.md content (empty if not generated)
 
 
 class RunDetail(BaseModel):

webapp/services/report_builder.py

@@ -164,12 +164,14 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
     """Build the full aggregated report payload for one run directory."""
     frame = run_reader.read_scores_frame(run_dir)
     summary_markdown = run_reader.read_summary_markdown(run_dir)
+    advice_markdown = run_reader.read_advice_markdown(run_dir)
 
     if frame.empty or not metrics:
         return ReportData(
             metrics=metrics,
             metric_means={metric: None for metric in metrics},
             summary_markdown=summary_markdown,
+            advice_markdown=advice_markdown,
         )
 
     distributions = {
@@ -185,4 +187,5 @@ def build_report(run_dir: Path, metrics: list[str]) -> ReportData:
         groupings=_groupings(frame, metrics),
         lowest_samples=_lowest_samples(frame, metrics),
         summary_markdown=summary_markdown,
+        advice_markdown=advice_markdown,
     )

webapp/services/run_reader.py

@@ -220,3 +220,14 @@ def read_summary_markdown(run_dir: Path) -> str:
         return summary_path.read_text(encoding="utf-8")
     except OSError:
         return ""
+
+
+def read_advice_markdown(run_dir: Path) -> str:
+    """Return the optimization_advice.md for a run, or an empty string if not generated."""
+    advice_path = run_dir / "optimization_advice.md"
+    if not advice_path.is_file():
+        return ""
+    try:
+        return advice_path.read_text(encoding="utf-8")
+    except OSError:
+        return ""