fix: 推理/评测结果同步、数据集统计与算力节点管理增强

后端:
- 抽取 fetch_eval_result_content 复用函数，model_eval_detail 直接应用评测任务结果
- health 接口移除数据库依赖，返回静态指标
- 数据集: count_dataset_records JSON 感知计数; 文件统计改为从 dataset_files 聚合重算; 在线编辑记录 size/record_count/version_no; 上传同步批处理
- 算力节点: 调度支持 requested GPU 子集校验与容量计算; 新增 delete_compute_node(含活动任务保护)及 DELETE 接口; 连接池 connect_timeout
- 评测任务落库 basic_metrics/score/completed_time, failed/stopped 记录 error

评测引擎:
- _load_dataset 支持 JSON/JSONL 文件
- 新增 exact match 与文本相似度指标, 余弦相似度去掉 2 样本限制

前端:
- 算力节点列表「维护」改为「删除」(带确认弹窗), compute.ts 新增 deleteComputeNode
- 数据集上传超时调整为 120s; FineTuneTask 增加 compute_node_id; GpuInfo 状态增加 reserved

compute/engines/llama_factory/eval_runner.py

@@ -13,30 +13,42 @@ from __future__ import annotations
 
 import json
 import math
+import re
 import sys
 import time
+from difflib import SequenceMatcher
 from pathlib import Path
 from typing import Any
 
 
-def _load_jsonl(path: str) -> list[dict[str, Any]]:
-    """Load a JSONL dataset file.  Each line must be a JSON object.
+def _load_dataset(path: str) -> list[dict[str, Any]]:
+    """Load a JSON or JSONL dataset file.
 
     Supports common field names used across the platform:
     * ``instruction`` + ``input`` + ``output``  (Alpaca-style)
     * ``question`` + ``answer``
     * ``messages``  (ShareGPT-style – the last assistant message is treated as reference)
     """
+    file_path = Path(path)
+    text = file_path.read_text(encoding="utf-8", errors="replace").strip()
+    if not text:
+        return []
+    if file_path.suffix.lower() == ".json":
+        value = json.loads(text)
+        if isinstance(value, list):
+            return [item for item in value if isinstance(item, dict)]
+        return [value] if isinstance(value, dict) else []
+
     samples: list[dict[str, Any]] = []
-    with open(path, encoding="utf-8") as fh:
-        for line in fh:
-            line = line.strip()
-            if not line:
-                continue
-            try:
-                obj = json.loads(line)
-            except json.JSONDecodeError:
-                continue
+    for line in text.splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            obj = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if isinstance(obj, dict):
             samples.append(obj)
     return samples
 
@@ -115,8 +127,6 @@ def _compute_cosine(references: list[str], predictions: list[str]) -> dict[str,
         from sklearn.metrics.pairwise import cosine_similarity
     except ImportError:
         return {"enabled": False, "error": "scikit-learn not installed", "score": 0}
-    if len(predictions) < 2:
-        return {"enabled": True, "score": 0, "error": "need at least 2 samples for corpus cosine"}
     try:
         vectorizer = TfidfVectorizer()
         tfidf = vectorizer.fit_transform(references + predictions)
@@ -129,6 +139,32 @@ def _compute_cosine(references: list[str], predictions: list[str]) -> dict[str,
         return {"enabled": True, "score": 0, "error": "insufficient text for vectorization"}
 
 
+def _normalize_text(value: str) -> str:
+    return re.sub(r"\s+", " ", str(value or "").strip().lower())
+
+
+def _compute_exact_match(references: list[str], predictions: list[str]) -> dict[str, Any]:
+    total = len(predictions)
+    if not total:
+        return {"enabled": True, "score": 0, "matched": 0, "total": 0}
+    matched = sum(
+        1
+        for ref, pred in zip(references, predictions)
+        if _normalize_text(ref) == _normalize_text(pred)
+    )
+    return {"enabled": True, "score": round(matched / total * 100, 2), "matched": matched, "total": total}
+
+
+def _compute_text_similarity(references: list[str], predictions: list[str]) -> dict[str, Any]:
+    if not predictions:
+        return {"enabled": True, "score": 0}
+    scores = [
+        SequenceMatcher(None, _normalize_text(ref), _normalize_text(pred)).ratio()
+        for ref, pred in zip(references, predictions)
+    ]
+    return {"enabled": True, "score": round(sum(scores) / max(len(scores), 1) * 100, 2)}
+
+
 # ---------------------------------------------------------------------------
 # LLM Judge
 # ---------------------------------------------------------------------------
@@ -265,7 +301,7 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
 
     # ---- 1. Load dataset ----
     print(f"[eval] loading dataset: {dataset_path}")
-    raw_samples = _load_jsonl(dataset_path)
+    raw_samples = _load_dataset(dataset_path)
     print(f"[eval] loaded {len(raw_samples)} samples")
 
     # ---- 2. Load model ----
@@ -356,6 +392,8 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
     cosine_cfg = basic_cfg.get("cosine", {})
     if cosine_cfg.get("enabled"):
         metrics_result["cosine"] = _compute_cosine(references, predictions)
+    metrics_result["exact_match"] = _compute_exact_match(references, predictions)
+    metrics_result["text_similarity"] = _compute_text_similarity(references, predictions)
 
     # ---- 5. Summarise ----
     completed = len(samples)
@@ -375,9 +413,23 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
         overall_evaluation = f"评测完成：{completed} 样本，{passed_count} 通过，平均 {avg_score}/{max_score} 分"
     else:
         passed_count = 0
-        overall_score = 0
+        enabled_scores = [
+            float(item.get("score") or 0)
+            for item in metrics_result.values()
+            if isinstance(item, dict) and item.get("enabled", True) and item.get("score") is not None
+        ]
+        overall_score = round(sum(enabled_scores) / len(enabled_scores), output_precision) if enabled_scores else 0
         overall_score_max = 100
-        dimension_summary = []
+        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
+        ]
         overall_evaluation = f"评测完成：{completed} 样本（未配置 LLM 评委）"
 
     result = {