feat: add LLM role-assignment panel to 新建评估 view
This commit is contained in:
@@ -1,8 +1,9 @@
|
||||
// runner.js — 新建评估视图:列出场景、触发评估、轮询任务状态与日志。
|
||||
// runner.js — 新建评估视图:列出场景、LLM角色配置、触发评估、轮询任务状态与日志。
|
||||
|
||||
const Runner = {
|
||||
selectedScenario: null,
|
||||
pollTimer: null,
|
||||
lastRunId: null,
|
||||
|
||||
// 绑定运行按钮。
|
||||
init() {
|
||||
@@ -32,6 +33,27 @@ const Runner = {
|
||||
} catch (err) {
|
||||
list.innerHTML = `<p class="muted">加载失败:${App.escape(err.message)}</p>`;
|
||||
}
|
||||
// 同时加载 profiles 供角色选择
|
||||
Runner._populateProfileSelects();
|
||||
},
|
||||
|
||||
// 填充三个角色下拉框
|
||||
async _populateProfileSelects() {
|
||||
const cached = Profiles.getAll();
|
||||
const profiles = cached.length > 0
|
||||
? cached
|
||||
: (await API.profiles().catch(() => ({ profiles: [] }))).profiles;
|
||||
|
||||
["role-judge", "role-answer", "role-dataset"].forEach(id => {
|
||||
const sel = document.getElementById(id);
|
||||
sel.innerHTML = '<option value="">— 使用场景原始配置 —</option>';
|
||||
profiles.forEach(p => {
|
||||
const opt = document.createElement("option");
|
||||
opt.value = p.profile_id;
|
||||
opt.textContent = `${p.name} (${p.model})`;
|
||||
sel.appendChild(opt);
|
||||
});
|
||||
});
|
||||
},
|
||||
|
||||
// 构造单个场景条目。
|
||||
@@ -64,12 +86,14 @@ const Runner = {
|
||||
Runner.selectedScenario = sc.path;
|
||||
document.getElementById("selected-scenario").textContent = sc.path;
|
||||
document.getElementById("run-btn").disabled = false;
|
||||
// 显示 LLM 角色面板
|
||||
document.getElementById("llm-assignment-panel").hidden = false;
|
||||
});
|
||||
}
|
||||
return item;
|
||||
},
|
||||
|
||||
// 触发评估并开始轮询。
|
||||
// 触发评估:先 apply profiles(若选了),再触发任务。
|
||||
async trigger() {
|
||||
if (!Runner.selectedScenario) return;
|
||||
const runBtn = document.getElementById("run-btn");
|
||||
@@ -85,15 +109,41 @@ const Runner = {
|
||||
Runner._setStatus(statusBadge, "queued");
|
||||
|
||||
try {
|
||||
// Step 1: apply LLM profiles to YAML if any selected
|
||||
await Runner._applyProfilesIfNeeded(logBox);
|
||||
|
||||
// Step 2: trigger evaluation
|
||||
const resp = await API.triggerEvaluation(Runner.selectedScenario);
|
||||
Runner.poll(resp.task_id);
|
||||
} catch (err) {
|
||||
Runner._setStatus(statusBadge, "failed");
|
||||
logBox.textContent = `触发失败:${err.message}`;
|
||||
logBox.textContent = (logBox.textContent ? logBox.textContent + "\n" : "") + `触发失败:${err.message}`;
|
||||
runBtn.disabled = false;
|
||||
}
|
||||
},
|
||||
|
||||
// 如果用户选了 profile,就先 apply 写回 YAML
|
||||
async _applyProfilesIfNeeded(logBox) {
|
||||
const judgeId = document.getElementById("role-judge").value;
|
||||
const answerId = document.getElementById("role-answer").value;
|
||||
const datasetId = document.getElementById("role-dataset").value;
|
||||
|
||||
if (!judgeId && !answerId && !datasetId) return; // 全空,跳过
|
||||
|
||||
logBox.textContent = "正在将 LLM 配置写入场景文件…\n";
|
||||
const body = {
|
||||
scenario_path: Runner.selectedScenario,
|
||||
judge_profile_id: judgeId || null,
|
||||
answer_profile_id: answerId || null,
|
||||
dataset_profile_id: datasetId || null,
|
||||
};
|
||||
const result = await API.applyProfiles(body);
|
||||
const fields = (result.patched_fields || []).join(", ");
|
||||
logBox.textContent += fields
|
||||
? `✓ 已更新字段:${fields}\n`
|
||||
: "(未找到可更新的字段,继续运行)\n";
|
||||
},
|
||||
|
||||
// 周期性轮询任务状态,刷新日志与徽标。
|
||||
poll(taskId) {
|
||||
const logBox = document.getElementById("task-log");
|
||||
|
||||
Reference in New Issue
Block a user