Add RAGAS evaluation web console (FastAPI + vanilla JS)

- webapp/: FastAPI backend with runs/scenarios/evaluations API routers;
  services for run_reader, report_builder, scenario_scanner, task_manager
  (lazy ragas import — server boots even without ragas); Pydantic models
- webapp/static/: single-page console (layout A: left-nav + main area);
  report detail with metric cards, Chart.js distribution histogram,
  grouping table, lowest-score sample review; trigger evaluation + log polling
- webmain.py: uvicorn entry point (alongside existing main.py CLI)
- start.bat: Windows one-click launcher with env checks and auto-browser open
- rag_eval/datasets/: implement missing loader + normalizer modules
  (load_dataset_records, normalize_records) required by evaluator
- scripts/seed_sample_run.py: generate realistic demo run artifacts
- .gitignore: exclude datasets/ data files but keep rag_eval/datasets/ source

Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>

webapp/api/runs.py

@@ -0,0 +1,32 @@
+"""Routes for listing evaluation runs and fetching a single run's report."""
+
+from __future__ import annotations
+
+from fastapi import APIRouter, HTTPException
+
+from webapp.models import RunDetail
+from webapp.services import report_builder, run_reader
+
+router = APIRouter(prefix="/api/runs", tags=["runs"])
+
+
+@router.get("")
+def get_runs() -> dict[str, list]:
+    """Return summaries for every discoverable evaluation run."""
+    summaries = run_reader.list_run_summaries()
+    return {"runs": [summary.model_dump() for summary in summaries]}
+
+
+@router.get("/{run_id}")
+def get_run_detail(run_id: str) -> RunDetail:
+    """Return the full summary and aggregated report for one run."""
+    run_dir = run_reader.find_run_dir(run_id)
+    if run_dir is None:
+        raise HTTPException(status_code=404, detail=f"未找到运行: {run_id}")
+
+    summary = run_reader.build_run_summary(run_dir)
+    if summary is None:
+        raise HTTPException(status_code=404, detail=f"运行元数据缺失: {run_id}")
+
+    report = report_builder.build_report(run_dir, summary.metrics)
+    return RunDetail(summary=summary, report=report)