feat: 评测任务元数据增强与前端展示优化

后端:
- 新增评测指标标签生成(_build_eval_metric_label/_basic_metric_labels)
- eval 任务 payload 富化(_enrich_eval_payload): 解析模型名/数据集名/维度配置, 生成 metric_label
- 任务创建时解析 trained_models/模型名, metric 回退为 metric_label
- 运行时状态刷新增加 2s 节流, 避免频繁触发

前端:
- EvalTask 类型增加 dataset_id/metric_label
- 评测列表与详情展示 metric_label 指标标签, 模型名/指标超长 tooltip 省略
- 创建页改用 getComputeGpus 过滤空闲 GPU, 移除 getSystemInfo 依赖

backend/app/db/platform_store.py

@@ -104,6 +104,68 @@ def count_dataset_records(content: str) -> int:
     return len([line for line in text.splitlines() if line.strip()])
 
 
+_EVAL_METHOD_LABELS = {
+    "standard": "标准匹配",
+    "metric_standard": "综合评测",
+    "semantic": "语义相似度",
+    "sentiment": "情感分析",
+    "accuracy": "准确性评估",
+    "safety": "安全性评估",
+    "relevance": "相关性评估",
+    "fluency": "流畅性评估",
+    "factuality": "事实性评估",
+    "custom": "自定义评估",
+}
+
+
+def _eval_method_label(value: Any) -> str:
+    if isinstance(value, list):
+        return "、".join(_eval_method_label(item) for item in value if item)
+    text = str(value or "").strip()
+    return _EVAL_METHOD_LABELS.get(text, text)
+
+
+def _basic_metric_labels(config: dict[str, Any] | None) -> list[str]:
+    cfg = config or {}
+    labels: list[str] = []
+    bleu = cfg.get("bleu") or {}
+    if bleu.get("enabled"):
+        labels.append(f"BLEU-{int(bleu.get('ngram') or 4)}")
+    rouge = cfg.get("rouge") or {}
+    if rouge.get("enabled"):
+        methods = rouge.get("methods") or []
+        method_labels = {
+            "rouge1": "ROUGE-1",
+            "rouge2": "ROUGE-2",
+            "rougeL": "ROUGE-L",
+            "rouge_1": "ROUGE-1",
+            "rouge_2": "ROUGE-2",
+            "rouge_l": "ROUGE-L",
+        }
+        labels.extend(method_labels.get(str(item), str(item)) for item in methods)
+    cosine = cfg.get("cosine") or {}
+    if cosine.get("enabled"):
+        labels.append("Cosine")
+    return labels
+
+
+def _build_eval_metric_label(payload: dict[str, Any], dimension: dict[str, Any] | None = None) -> str:
+    parts: list[str] = []
+    dim = dimension or {}
+    dim_type = str(dim.get("type") or payload.get("dimension_type") or "").strip()
+    method_label = _eval_method_label(dim.get("eval_method") or payload.get("eval_method"))
+    if dim_type in {"classification", "metric"} and method_label:
+        parts.append(f"LLM：{method_label}")
+    elif dim_type == "text_similarity" and method_label:
+        parts.append(method_label)
+
+    parts.extend(_basic_metric_labels(payload.get("basic_metrics") or {}))
+    if not parts:
+        metric = str(payload.get("metric") or payload.get("eval_type") or "").strip()
+        return "自定义评测" if metric == "custom" else (metric or "-")
+    return " + ".join(parts)
+
+
 def version_number(value: Any, default: int = 0) -> int:
     try:
         number = int(value)
@@ -339,6 +401,7 @@ class PlatformStore:
         self.ensure_seed_data()
         # Track which compute nodes have an active inference model loaded
         self._inference_nodes: set[str] = set()
+        self._last_runtime_refresh = 0.0
 
     # ── inference node tracking ────────────────────────────────────
 
@@ -463,6 +526,10 @@ class PlatformStore:
     def refresh_runtime_state(self) -> None:
         if get_settings().compute_mode != "simulator":
             return
+        now_ts = time.monotonic()
+        if now_ts - self._last_runtime_refresh < 2:
+            return
+        self._last_runtime_refresh = now_ts
 
         with self.connect() as conn:
             rows = conn.execute(
@@ -2146,19 +2213,54 @@ class PlatformStore:
     def _json_payload_row(self, row: PgRow) -> dict[str, Any]:
         payload = json_loads(row["payload"], {})
         payload.update({"id": row["id"], "status": row.get("status"), "create_time": row["create_time"]})
+        if not payload.get("metric_label"):
+            payload["metric_label"] = _build_eval_metric_label(payload)
+        if not payload.get("metric") or payload.get("metric") == "custom":
+            payload["metric"] = payload["metric_label"]
         return payload
 
+    def _enrich_eval_payload(self, conn: PgConnection, payload: dict[str, Any]) -> dict[str, Any]:
+        data = dict(payload)
+        model_id = str(data.get("model_id") or "")
+        if model_id and not data.get("model_name"):
+            model = conn.execute("SELECT name FROM models WHERE id=?", (model_id,)).fetchone()
+            if not model:
+                model = conn.execute("SELECT name FROM trained_models WHERE id=? OR name=?", (model_id, model_id)).fetchone()
+            if model:
+                data["model_name"] = model["name"]
+
+        dataset_id = str(data.get("dataset_id") or "")
+        if dataset_id and not data.get("dataset"):
+            dataset = conn.execute("SELECT name FROM datasets WHERE id=?", (dataset_id,)).fetchone()
+            if dataset:
+                data["dataset"] = dataset["name"]
+
+        dimension = None
+        dimension_id = str(data.get("dimension_id") or "")
+        if dimension_id:
+            dimension_row = conn.execute("SELECT payload FROM eval_dimensions WHERE id=?", (dimension_id,)).fetchone()
+            if dimension_row:
+                dimension = json_loads(dimension_row["payload"], {})
+                data.setdefault("dimension_type", dimension.get("type"))
+                data.setdefault("eval_method", dimension.get("eval_method"))
+                data.setdefault("evaluator_model", dimension.get("eval_model"))
+
+        data["metric_label"] = _build_eval_metric_label(data, dimension)
+        if not data.get("metric") or data.get("metric") in {"custom", "自定义评测"}:
+            data["metric"] = data["metric_label"]
+        return data
+
     def eval_tasks(self) -> list[dict[str, Any]]:
         with self.connect() as conn:
             rows = conn.execute("SELECT * FROM eval_tasks ORDER BY create_time DESC").fetchall()
-            return [self._json_payload_row(row) for row in rows]
+            return [self._enrich_eval_payload(conn, self._json_payload_row(row)) for row in rows]
 
     def eval_task(self, task_id: str) -> dict[str, Any]:
         with self.connect() as conn:
             row = conn.execute("SELECT * FROM eval_tasks WHERE id=?", (task_id,)).fetchone()
             if not row:
                 raise KeyError(task_id)
-            payload = self._json_payload_row(row)
+            payload = self._enrich_eval_payload(conn, self._json_payload_row(row))
             payload.setdefault("sample_count", 0)
             payload.setdefault("completed_count", 0)
             payload.setdefault("passed_count", 0)
@@ -2184,12 +2286,29 @@ class PlatformStore:
             "metric": payload.get("metric") or "custom",
         }
         with self.connect() as conn:
-            model = conn.execute("SELECT name FROM models WHERE id=?", (str(payload.get("model_id")),)).fetchone()
+            model_id = str(payload.get("model_id") or "")
+            model = conn.execute("SELECT name FROM models WHERE id=?", (model_id,)).fetchone()
+            trained_model = conn.execute("SELECT name FROM trained_models WHERE id=? OR name=?", (model_id, model_id)).fetchone()
             dataset = conn.execute("SELECT name FROM datasets WHERE id=?", (str(payload.get("dataset_id")),)).fetchone()
+            dimension = None
+            dimension_id = str(payload.get("dimension_id") or "")
+            if dimension_id:
+                dimension_row = conn.execute("SELECT payload FROM eval_dimensions WHERE id=?", (dimension_id,)).fetchone()
+                if dimension_row:
+                    dimension = json_loads(dimension_row["payload"], {})
             if model:
                 data.setdefault("model_name", model["name"])
+            elif trained_model:
+                data.setdefault("model_name", trained_model["name"])
             if dataset:
                 data.setdefault("dataset", dataset["name"])
+            if dimension:
+                data.setdefault("dimension_type", dimension.get("type"))
+                data.setdefault("eval_method", dimension.get("eval_method"))
+                data.setdefault("evaluator_model", dimension.get("eval_model"))
+            data["metric_label"] = _build_eval_metric_label(data, dimension)
+            if data.get("metric") == "custom":
+                data["metric"] = data["metric_label"]
             conn.execute(
                 "INSERT INTO eval_tasks (id, name, payload, status, create_time) VALUES (?, ?, ?, ?, ?)",
                 (task_id, name, json_dumps(data), status, now),

frontend/src/types/index.ts

@@ -245,7 +245,9 @@ export interface EvalTask {
   model_name?: string
   model_id?: number | string
   dataset?: string
+  dataset_id?: number | string
   metric?: string
+  metric_label?: string
   score?: number
   status?: string
   create_time?: string

frontend/src/views/eval/EvalCreateView.vue

@@ -1,4 +1,4 @@
-<script setup lang="ts">
+<script setup lang="ts">
 import { onMounted, ref, watch } from 'vue'
 import { useRouter } from 'vue-router'
 import { ElMessage } from 'element-plus'
@@ -10,8 +10,7 @@ import StartEvalStep from './create/StartEvalStep.vue'
 import { createDimension, startEval } from '@/api/modules/eval'
 import { getTrainedModels, getModelList } from '@/api/modules/model'
 import { getDatasetList } from '@/api/modules/dataset'
-import { getSystemInfo } from '@/api/modules/system'
+import { getComputeGpus } from '@/api/modules/compute'
-import { getComputeNodes, type ComputeNode } from '@/api/modules/compute'
 import type { DatasetItem, Dimension, GpuInfo, ModelItem, TrainedModel } from '@/types'
 
 type StepExposed = { validate: () => Promise<boolean> }
@@ -83,9 +82,8 @@ async function loadData() {
   const results = await Promise.allSettled([
     getTrainedModels(),
     getDatasetList(),
-    getSystemInfo(),
     getModelList(),
-    getComputeNodes(),
+    getComputeGpus(),
   ])
 
   if (results[0].status === 'fulfilled') trainedModels.value = results[0].value?.models || []
@@ -93,18 +91,12 @@ async function loadData() {
     evalDatasets.value = (results[1].value || []).filter((dataset) => dataset.type === 'eval')
   }
   if (results[2].status === 'fulfilled') {
-    const allGpus: GpuInfo[] = results[2].value?.gpu || []
+    evalModels.value = (results[2].value || []).filter(
-    const nodes: ComputeNode[] = (results[4].status === 'fulfilled' ? results[4].value : []) || []
+      (model) => model.purpose === 'evaluation' || (model.model_source === 'api' && !!model.api_url),
-    const onlineIds = new Set(nodes.filter((n) => n.enabled && n.scheduler_status === 'online').map((n) => n.id))
-    // Only show idle GPUs from online compute nodes
-    gpus.value = allGpus.filter(
-      (g) => g.status === 'idle' && (!g.node_id || onlineIds.has(g.node_id)),
     )
   }
   if (results[3].status === 'fulfilled') {
-    evalModels.value = (results[3].value || []).filter(
+    gpus.value = ((results[3].value || []) as unknown as GpuInfo[]).filter((g) => g.status === 'idle')
-      (model) => model.purpose === 'evaluation' || (model.model_source === 'api' && !!model.api_url),
-    )
   }
 
   const failedCount = results.filter((result) => result.status === 'rejected').length

frontend/src/views/eval/EvalDetailView.vue

@@ -1,4 +1,4 @@
-<script setup lang="ts">
+<script setup lang="ts">
 import { computed, onMounted, onUnmounted, ref } from 'vue'
 import { useRoute } from 'vue-router'
 import PageCard from '@/components/PageCard.vue'
@@ -50,6 +50,8 @@ const passRate = computed(() => {
 })
 
 const overallScore = computed(() => formatScore(detail.value?.overall_score, detail.value?.overall_score_max))
+const displayModelName = computed(() => detail.value?.model_name || String(detail.value?.model_id || '-'))
+const displayMetric = computed(() => detail.value?.metric_label || detail.value?.metric || '-')
 
 function formatDateTime(value?: string) {
   if (!value) return '-'
@@ -121,9 +123,9 @@ onUnmounted(stopPolling)
           </div>
           <dl class="task-meta">
             <div><dt>任务 ID</dt><dd>{{ detail?.id || taskId }}</dd></div>
-            <div><dt>评测模型</dt><dd>{{ detail?.model_name || '-' }}</dd></div>
+            <div><dt>评测模型</dt><dd>{{ displayModelName }}</dd></div>
             <div><dt>测试集</dt><dd>{{ detail?.dataset || '-' }}</dd></div>
-            <div><dt>评测指标</dt><dd>{{ detail?.metric || '-' }}</dd></div>
+            <div><dt>评测指标</dt><dd>{{ displayMetric }}</dd></div>
           </dl>
         </div>
       </div>
@@ -141,7 +143,7 @@ onUnmounted(stopPolling)
         <div class="overview-item score-hero">
           <span>综合得分</span>
           <strong>{{ overallScore }}</strong>
-          <small>大模型综合评分</small>
+          <small>模型综合评分</small>
         </div>
         <div class="overview-item">
           <span>样本通过率</span>
@@ -164,7 +166,7 @@ onUnmounted(stopPolling)
         <div class="review-copy">
           <div class="section-heading">
             <div>
-              <h2 id="overall-review-title">大模型综合评价</h2>
+              <h2 id="overall-review-title">综合评价</h2>
               <p>基于全部已评测样本生成的总体结论</p>
             </div>
             <el-tag v-if="detail.evaluator_model" type="primary" size="small">
@@ -172,7 +174,7 @@ onUnmounted(stopPolling)
             </el-tag>
           </div>
           <p class="review-text">
-            {{ detail.overall_evaluation || (detail.status === 'running' ? '评测仍在进行，综合评价将在样本评分完成后生成。' : '暂无综合评价。') }}
+            {{ detail.overall_evaluation || (detail.status === 'running' ? '评测正在进行，综合评价将在样本完成后生成。' : '暂无综合评价。') }}
           </p>
 
           <div class="suggestion-block">
@@ -190,8 +192,8 @@ onUnmounted(stopPolling)
       <section v-if="detail.dimension_summary?.length" class="dimension-summary" aria-labelledby="dimension-title">
         <div class="section-heading compact-heading">
           <div>
-            <h2 id="dimension-title">维度表现</h2>
+            <h2 id="dimension-title">指标表现</h2>
-            <p>查看各评测维度的得分与样本通过率</p>
+            <p>查看各评测指标的得分与通过率</p>
           </div>
         </div>
         <div class="dimension-grid">
@@ -212,22 +214,10 @@ onUnmounted(stopPolling)
             <p>共 {{ filteredSamples.length }} 条结果，展开行可查看评分依据与子维度分数</p>
           </div>
           <div class="sample-filters" aria-label="样本筛选">
-            <el-input
+            <el-input v-model="keyword" clearable placeholder="搜索问题、回答或评价" aria-label="搜索样本" @input="resetPage">
-              v-model="keyword"
-              clearable
-              placeholder="搜索问题、回答或评价"
-              aria-label="搜索样本"
-              @input="resetPage"
-            >
               <template #prefix><i class="fa fa-search" aria-hidden="true" /></template>
             </el-input>
-            <el-select
+            <el-select v-model="judgementFilter" clearable placeholder="全部判定" aria-label="按判定筛选" @change="resetPage">
-              v-model="judgementFilter"
-              clearable
-              placeholder="全部判定"
-              aria-label="按判定筛选"
-              @change="resetPage"
-            >
               <el-option label="正确" value="正确" />
               <el-option label="部分正确" value="部分正确" />
               <el-option label="错误" value="错误" />
@@ -235,18 +225,12 @@ onUnmounted(stopPolling)
           </div>
         </div>
 
-        <el-table
+        <el-table v-if="filteredSamples.length" class="sample-results-table" :data="paginatedSamples" row-key="id" table-layout="fixed">
-          v-if="filteredSamples.length"
-          class="sample-results-table"
-          :data="paginatedSamples"
-          row-key="id"
-          table-layout="fixed"
-        >
           <el-table-column type="expand" width="48">
             <template #default="{ row }">
               <div class="sample-detail-grid">
                 <div class="evaluation-reason">
-                  <span>大模型评分依据</span>
+                  <span>评分依据</span>
                   <p>{{ row.evaluation_reason || '暂无评分依据。' }}</p>
                 </div>
                 <div v-if="row.error_type" class="error-type">
@@ -275,9 +259,7 @@ onUnmounted(stopPolling)
             <template #default="{ row }"><p class="cell-copy">{{ row.model_output || '等待生成' }}</p></template>
           </el-table-column>
           <el-table-column label="得分" width="90" align="center">
-            <template #default="{ row }">
+            <template #default="{ row }"><span class="sample-score">{{ formatScore(row.score, row.max_score) }}</span></template>
-              <span class="sample-score">{{ formatScore(row.score, row.max_score) }}</span>
-            </template>
           </el-table-column>
           <el-table-column label="判定" width="96" align="center">
             <template #default="{ row }">
@@ -294,21 +276,11 @@ onUnmounted(stopPolling)
           <p>{{ detail.status === 'running' ? '任务正在运行，结果生成后会显示在这里。' : '请调整筛选条件或稍后重试。' }}</p>
         </div>
 
-        <el-pagination
+        <el-pagination v-if="filteredSamples.length > pageSize" v-model:current-page="currentPage" v-model:page-size="pageSize" background layout="total, sizes, prev, pager, next" :page-sizes="[10, 20, 50]" :total="filteredSamples.length" aria-label="样本结果分页" />
-          v-if="filteredSamples.length > pageSize"
-          v-model:current-page="currentPage"
-          v-model:page-size="pageSize"
-          background
-          layout="total, sizes, prev, pager, next"
-          :page-sizes="[10, 20, 50]"
-          :total="filteredSamples.length"
-          aria-label="样本结果分页"
-        />
       </section>
     </template>
   </PageCard>
 </template>
-
 <style scoped lang="scss">
 .eval-detail-page {
   min-width: 0;
@@ -767,3 +739,6 @@ onUnmounted(stopPolling)
   }
 }
 </style>
+
+
+

frontend/src/views/eval/EvalView.vue

@@ -1,4 +1,4 @@
-<script setup lang="ts">
+<script setup lang="ts">
 import { ref, onMounted, onUnmounted } from 'vue'
 import { useRouter } from 'vue-router'
 import { ElMessage, ElMessageBox } from 'element-plus'
@@ -57,6 +57,14 @@ function handleViewDetail(row: any) {
   router.push({ name: 'model-eval-detail', params: { id: row.id } })
 }
 
+function displayModelName(row: Partial<EvalTask>) {
+  return row.model_name || String(row.model_id || '-')
+}
+
+function displayMetric(row: Partial<EvalTask>) {
+  return row.metric_label || row.metric || '-'
+}
+
 const { start: startPolling, stop: stopPolling } = usePolling(
   async () => {
     await loadEvalList({ silent: true })
@@ -102,9 +110,21 @@ onUnmounted(() => {
       </template>
             <template #columns>
               <el-table-column label="任务名称" prop="eval_task_name" align="center" />
-              <el-table-column label="评测模型" prop="model_name" align="center" />
+              <el-table-column label="评测模型" align="center" min-width="160">
+                <template #default="{ row }">
+                  <el-tooltip :content="displayModelName(row)" placement="top" :disabled="displayModelName(row).length < 18">
+                    <span class="cell-ellipsis">{{ displayModelName(row) }}</span>
+                  </el-tooltip>
+                </template>
+              </el-table-column>
               <el-table-column label="数据集" prop="dataset" align="center" />
-              <el-table-column label="指标" prop="metric" align="center" />
+              <el-table-column label="指标" align="center" min-width="220">
+                <template #default="{ row }">
+                  <el-tooltip :content="displayMetric(row)" placement="top" :disabled="displayMetric(row).length < 24">
+                    <span class="cell-ellipsis">{{ displayMetric(row) }}</span>
+                  </el-tooltip>
+                </template>
+              </el-table-column>
               <el-table-column label="评分" prop="score" width="100" align="center" />
               <el-table-column label="状态" width="100" align="center">
                 <template #default="{ row }">
@@ -159,7 +179,7 @@ onUnmounted(() => {
   min-height: 0;
 }
 
-/* 胶囊切换栏样式 */
+/* 胶囊切换栏 */
 .capsule-tabs {
   display: flex;
   background: #f1f5f9;
@@ -193,4 +213,13 @@ onUnmounted(() => {
   }
 }
 
+.cell-ellipsis {
+  display: inline-block;
+  max-width: 100%;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  vertical-align: middle;
+  white-space: nowrap;
+}
+
 </style>