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>

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 ""