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/static/js/runner.js

@@ -0,0 +1,133 @@
+// runner.js — 新建评估视图：列出场景、触发评估、轮询任务状态与日志。
+
+const Runner = {
+  selectedScenario: null,
+  pollTimer: null,
+
+  // 绑定运行按钮。
+  init() {
+    document.getElementById("run-btn").addEventListener("click", () => Runner.trigger());
+    document.getElementById("view-report-btn").addEventListener("click", () => {
+      if (Runner.lastRunId) {
+        App.currentRunId = Runner.lastRunId;
+        App.enableReportNav();
+        App.switchView("report");
+      }
+    });
+  },
+
+  // 加载并渲染可触发的场景列表。
+  async loadScenarios() {
+    const list = document.getElementById("scenario-list");
+    list.innerHTML = '<p class="muted">加载中…</p>';
+    try {
+      const data = await API.scenarios();
+      const scenarios = data.scenarios || [];
+      if (scenarios.length === 0) {
+        list.innerHTML = '<p class="muted">未在 scenarios/ 下找到场景文件。</p>';
+        return;
+      }
+      list.innerHTML = "";
+      scenarios.forEach((sc) => list.appendChild(Runner.renderScenarioItem(sc)));
+    } catch (err) {
+      list.innerHTML = `<p class="muted">加载失败：${App.escape(err.message)}</p>`;
+    }
+  },
+
+  // 构造单个场景条目。
+  renderScenarioItem(sc) {
+    const item = document.createElement("div");
+    const invalid = !!sc.error;
+    item.className = "scenario-item" + (invalid ? " invalid" : "");
+
+    const modeTag = sc.mode
+      ? `<span class="tag mode-${App.escape(sc.mode)}">${App.escape(sc.mode)}</span>`
+      : "";
+    const metricCount = (sc.metrics || []).length;
+
+    item.innerHTML = `
+      <div>
+        <div class="scenario-name">${App.escape(sc.scenario_name || sc.path)}</div>
+        <div class="scenario-path">${App.escape(sc.path)}</div>
+        ${sc.error ? `<div class="scenario-path" style="color:#dc2626">${App.escape(sc.error)}</div>` : ""}
+      </div>
+      <div class="scenario-tags">
+        ${modeTag}
+        <span class="tag">${metricCount} 指标</span>
+      </div>
+    `;
+
+    if (!invalid) {
+      item.addEventListener("click", () => {
+        document.querySelectorAll(".scenario-item").forEach((el) => el.classList.remove("selected"));
+        item.classList.add("selected");
+        Runner.selectedScenario = sc.path;
+        document.getElementById("selected-scenario").textContent = sc.path;
+        document.getElementById("run-btn").disabled = false;
+      });
+    }
+    return item;
+  },
+
+  // 触发评估并开始轮询。
+  async trigger() {
+    if (!Runner.selectedScenario) return;
+    const runBtn = document.getElementById("run-btn");
+    runBtn.disabled = true;
+
+    const panel = document.getElementById("task-panel");
+    const logBox = document.getElementById("task-log");
+    const statusBadge = document.getElementById("task-status");
+    const reportBtn = document.getElementById("view-report-btn");
+    panel.hidden = false;
+    reportBtn.hidden = true;
+    logBox.textContent = "";
+    Runner._setStatus(statusBadge, "queued");
+
+    try {
+      const resp = await API.triggerEvaluation(Runner.selectedScenario);
+      Runner.poll(resp.task_id);
+    } catch (err) {
+      Runner._setStatus(statusBadge, "failed");
+      logBox.textContent = `触发失败：${err.message}`;
+      runBtn.disabled = false;
+    }
+  },
+
+  // 周期性轮询任务状态，刷新日志与徽标。
+  poll(taskId) {
+    const logBox = document.getElementById("task-log");
+    const statusBadge = document.getElementById("task-status");
+    const reportBtn = document.getElementById("view-report-btn");
+    const runBtn = document.getElementById("run-btn");
+
+    if (Runner.pollTimer) clearInterval(Runner.pollTimer);
+    Runner.pollTimer = setInterval(async () => {
+      try {
+        const status = await API.taskStatus(taskId);
+        logBox.textContent = (status.logs || []).join("\n");
+        logBox.scrollTop = logBox.scrollHeight;
+        Runner._setStatus(statusBadge, status.status);
+
+        if (status.status === "completed" || status.status === "failed") {
+          clearInterval(Runner.pollTimer);
+          runBtn.disabled = false;
+          if (status.status === "completed" && status.run_id) {
+            Runner.lastRunId = status.run_id;
+            reportBtn.hidden = false;
+          }
+        }
+      } catch (err) {
+        clearInterval(Runner.pollTimer);
+        logBox.textContent += `\n轮询失败：${err.message}`;
+        runBtn.disabled = false;
+      }
+    }, 1200);
+  },
+
+  // 更新状态徽标的文本与配色类。
+  _setStatus(badge, status) {
+    badge.textContent = status;
+    badge.className = "badge " + status;
+  },
+};