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/tests/test_inference_session.py

@@ -125,3 +125,22 @@ def test_chat_stream_while_loading_yields_error(stub_llamafactory) -> None:
     session.load("/models/qwen")
     chunks = list(session.chat_stream([{"role": "user", "content": "hi"}]))
     assert any("still loading" in c for c in chunks)
+
+
+def test_wait_until_loaded_blocks_until_ready(stub_llamafactory) -> None:
+    session = InferenceSession()
+    result = session.load("/models/qwen")
+    assert result["status"] == "loading"
+    # 同步等待后台加载线程完成
+    outcome = session.wait_until_loaded(timeout=3.0)
+    assert outcome["loaded"] is True
+    assert outcome["status"] == "ready"
+
+
+def test_wait_until_loaded_reports_load_error(stub_failing_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/bad")
+    outcome = session.wait_until_loaded(timeout=3.0)
+    assert outcome["loaded"] is False
+    assert outcome["status"] == "error"
+    assert "boom" in outcome["error"]