dsh-livebench-panel 0.2.7 → 0.2.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/lib/index.js +6 -1
- package/package.json +1 -1
package/lib/index.js
CHANGED
|
@@ -691,7 +691,12 @@ function apply(ctx) {
|
|
|
691
691
|
? null
|
|
692
692
|
: reasoningEffort;
|
|
693
693
|
const hasEffortSuffix = effort !== null && effort !== "off";
|
|
694
|
-
|
|
694
|
+
// 每次评测使用带时间戳的独立 display-name：答案/判分文件各自独立，
|
|
695
|
+
// 成绩表里每次评测是独立一行，可对比模型的历史变化（不再覆盖旧数据）。
|
|
696
|
+
const _now = new Date();
|
|
697
|
+
const _pad = (n) => String(n).padStart(2, "0");
|
|
698
|
+
const runStamp = `r${_now.getFullYear()}${_pad(_now.getMonth() + 1)}${_pad(_now.getDate())}-${_pad(_now.getHours())}${_pad(_now.getMinutes())}${_pad(_now.getSeconds())}`;
|
|
699
|
+
const displayName = displayModelName(providerId || "direct", modelId) + (hasEffortSuffix ? "@" + effort : "") + "__" + runStamp;
|
|
695
700
|
let cliModel = modelId;
|
|
696
701
|
let writeError = null; // Anthropic-protocol proxies cannot go through --api-base (that path
|
|
697
702
|
// speaks OpenAI Chat Completions). Instead the generated model config
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-livebench-panel",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.8",
|
|
4
4
|
"description": "DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and read scores in place.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|