feat: 评测任务完成进度收尾与指标维度汇总展示

- platform_store: 评测任务完成时置进度 100% 并落地 completed_time
- eval_runner: 新增指标维度汇总，供雷达图等维度展示
- 前端: 评测详情/列表展示优化、模型管理增强

compute/engines/llama_factory/eval_runner.py

@@ -170,6 +170,30 @@ def _metric_record(score: float | None, sample_count: int, error: str = "", avai
     }
 
 
+def _metric_dimension_summary(metrics: dict[str, Any]) -> list[dict[str, Any]]:
+    labels = {
+        "bleu": "BLEU",
+        "rouge": "ROUGE-L",
+        "cosine": "Cosine 相似度",
+        "exact_match": "精确匹配",
+        "text_similarity": "文本相似度",
+    }
+    result: list[dict[str, Any]] = []
+    for name, item in metrics.items():
+        if not isinstance(item, dict) or item.get("score") is None:
+            continue
+        result.append({
+            "name": labels.get(name, name),
+            "score": float(item.get("score") or 0),
+            "max_score": float(item.get("max_score") or 100),
+            "pass_rate": float(item.get("score") or 0),
+            "sample_count": int(item.get("sample_count") or 0),
+            "available": item.get("available", True),
+            "error": item.get("error", ""),
+        })
+    return result
+
+
 def _rouge_tokens(text: str) -> str:
     text = str(text or "").strip().lower()
     tokens: list[str] = []
@@ -650,7 +674,10 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
             "score": overall_score,
             "max_score": 100,
             "pass_rate": round(passed_count / max(completed, 1) * 100, 1),
-        }]
+            "sample_count": completed,
+            "available": bool(scored),
+            "error": "部分样本未返回可解析评分" if len(scored) < completed else "",
+        }] + _metric_dimension_summary(metrics_result)
         overall_evaluation = f"评测完成：{completed} 样本，{passed_count} 通过，平均 {avg_score}/100 分"
     else:
         passed_count = 0
@@ -661,16 +688,7 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
         ]
         overall_score = round(sum(enabled_scores) / len(enabled_scores), output_precision) if enabled_scores else 0
         overall_score_max = 100
-        dimension_summary = [
-            {
-                "name": name,
-                "score": float(item.get("score") or 0),
-                "max_score": 100,
-                "pass_rate": float(item.get("score") or 0),
-            }
-            for name, item in metrics_result.items()
-            if isinstance(item, dict) and item.get("enabled", True) and item.get("score") is not None
-        ]
+        dimension_summary = _metric_dimension_summary(metrics_result)
         overall_evaluation = f"评测完成：{completed} 样本（未配置 LLM 评委）"
 
     result = {