fix: 模型评测异步加载等待与多节点路由修复

- eval_runner 等待异步模型加载完成（InferenceSession.wait_until_loaded），
  修复 "model load failed: unknown"
- 评测算力节点选择：优先页面选择的节点 / 模型所在节点（_select_eval_node），
  多节点时不再派发到不可达节点导致连接超时
- 前端评测 GPU 选择改为节点感知（节点:GPU 复合值），透传 compute_node_id，
  并检查 startEval 结果展示真实错误
- 大模型评价（judge）使用模型记录的真实 API 模型名（api_model），
  避免用平台内部名调用 LLM API 导致 HTTP 400
- 新增后端节点选择与 compute wait_until_loaded 单元测试

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

compute/engines/llama_factory/eval_runner.py

@@ -183,6 +183,9 @@ def _judge_sample(
     api_url = (config.get("api_url") or "").strip().rstrip("/")
     api_key = (config.get("api_key") or "").strip()
     eval_model = (config.get("eval_model") or "").strip()
+    # 优先使用模型记录里配置的真实 API 模型名（如 deepseek-chat），
+    # 否则回退到平台内部模型名
+    api_model = (config.get("api_model") or "").strip() or eval_model
     eval_prompt = (config.get("eval_prompt") or "").strip()
     score_min = float(config.get("score_min", 0))
     score_max = float(config.get("score_max", 5))
@@ -208,7 +211,7 @@ def _judge_sample(
         import urllib.error
 
         body = json.dumps({
-            "model": eval_model,
+            "model": api_model,
             "messages": [
                 {"role": "system", "content": system_msg},
                 {"role": "user", "content": user_msg},
@@ -308,13 +311,15 @@ def run_eval(config: dict[str, Any]) -> dict[str, Any]:
     print(f"[eval] loading model: {model_path}")
     from compute.engines.llama_factory.inference import InferenceSession
     session = InferenceSession()
-    load_result = session.load(
+    session.load(
         model_name_or_path=model_path,
         adapter_name_or_path=adapter_path,
         template=template,
         infer_backend=config.get("infer_backend", "huggingface"),
         infer_dtype=config.get("infer_dtype", "auto"),
     )
+    # load() 为异步加载（立即返回 loading），必须等待后台线程完成后再进行推理
+    load_result = session.wait_until_loaded(timeout=float(config.get("load_timeout", 1800)))
     if not load_result.get("loaded"):
         raise RuntimeError(f"model load failed: {load_result.get('error', 'unknown')}")
     print(f"[eval] model loaded OK")

compute/engines/llama_factory/inference.py

@@ -55,6 +55,31 @@ class InferenceSession:
                 "error": self._error,
             }
 
+    def wait_until_loaded(self, timeout: float | None = None) -> dict[str, Any]:
+        """Wait for an in-flight async load to finish and return its outcome.
+
+        供同步消费方（如 eval_runner 子进程）使用：``load()`` 立即返回 loading 后，
+        调用本方法等待后台加载线程完成，拿到最终的 loaded/error 结果。
+        若在 timeout 秒内仍未加载完成，返回 ``status == "loading"`` 并附上超时提示。
+        """
+        with self._state_lock:
+            thread = self._load_thread
+        if thread is not None and thread.is_alive():
+            thread.join(timeout=timeout)
+        with self._state_lock:
+            loaded = self._status == "ready"
+            status = self._status
+            error = self._error
+        if not loaded and status == "loading":
+            error = error or f"model load timed out after {timeout or 'N/A'}s"
+        return {
+            "loaded": loaded,
+            "status": status,
+            "model_name": self._model_name,
+            "adapter_path": self._adapter_path,
+            "error": error,
+        }
+
     def load(
         self,
         model_name_or_path,