feat: goal 模式新语义——prompt 即目标,无验收命令,不限轮次,模型宣告完成 (#67)

console 打勾 goal 模式时不再有专用 goal 文本、验收命令、轮次
三个输入(已移除,换成说明行),只发 goal_mode=1;server 侧
goal_mode=1 时 goal 存 prompt、验收命令空、轮次存 0,带验收
命令或与计划模式同用时 400,旧的带验收命令任务照原样可用。

host.py goal 循环:verify 为空时不跑验测,轮次提示里写明
标记约定;模型在完整跑完的回合末尾单独一行输出“目标已
达成”即达标(超时回合的部分文本含标记也不算);--max-rounds
0 为不限轮次,goal-resume 续跑按 0 处理(不用 or 兜底成 3)。
刹车只有取消与预算耗尽(后者记 interrupted、可续跑)。

迁移与 worker:tasks 加 goal_mode 列(server 迁移、worker 列
补齐、PG schema 三处同步);worker 按 goal_mode 或
verify_command 判定 goal 路径,重试与后续消息排空对新语义
同样只跑一次/不排空;Local/Docker goal_task 的 --verify 可选、
--max-rounds 0 原样传。

Co-authored-by: host <host@test.local>
This commit is contained in:
openqjandhost authored and GitHub committed 2026-10-27 03:54:48 +08:00
1 parent 4179fb1a0a
commit c86b450851
10 files changed
+519 -108

No files matched your search

+7 -10
View File
@@ -151,11 +151,7 @@
<option value="full">完全访问</option>
</select>
</div>
<div id="goalFields" style="display:none">
<input id="goal" type="text" placeholder="goal(缺省用 prompt)" style="width:100%; box-sizing:border-box; margin:6px 0;">
<input id="verifyCommand" type="text" placeholder="verify_command 验收命令(goal 模式必填项按服务端规则)" style="width:100%; box-sizing:border-box; margin:6px 0;">
<label>轮次 <input id="goalRounds" type="number" value="3" min="1" style="width:60px;"></label>
</div>
<div id="goalHint" style="display:none" class="muted">goal 模式:输入框内容即目标,不需要专用 prompt 与验收命令;不限轮次,模型确认达成后在回复末尾输出“目标已达成”即结束,未达成会一直运行,可用取消停止。</div>
<div class="bar">
<button id="createTask" class="primary">提交任务</button>
<span id="taskMsg" class="muted"></span>
@@ -316,7 +312,7 @@ async function loadTasks() {
var pr = t.pr_url ? "<a href='" + esc(t.pr_url) + "' target='_blank' rel='noopener'>#" + esc(t.pr_number) + "</a>" : "";
return "<tr data-id='" + esc(t.id) + "' class='" + (currentTask && currentTask.id === t.id ? "selected" : "") + "'>" +
"<td>" + esc(shortId(t.id)) + "</td>" +
"<td>" + (t.plan ? "[计划] " : "") + (t.forked_from ? "[分支] " : "") + esc(String(t.prompt || "").slice(0, 60)) + "</td>" +
"<td>" + (t.plan ? "[计划] " : "") + (t.forked_from ? "[分支] " : "") + ((t.goal_mode || t.verify_command) ? "[目标] " : "") + esc(String(t.prompt || "").slice(0, 60)) + "</td>" +
"<td class='st-" + esc(t.status) + "'>" + esc(t.status) + "</td>" +
"<td>" + esc(t.executor || "") + "</td>" +
"<td>" + esc(t.worktree_host || "") + "</td>" +
@@ -442,6 +438,7 @@ async function showDetail(taskId) {
" | 权限 " + esc(t.approval || "默认") +
(t.plan ? " | <b>计划模式(只读)</b>" : "") +
(t.forked_from ? " | 分支自 " + esc(shortId(t.forked_from)) : "") +
(t.goal_mode ? " | <b>goal 模式(不限轮次,模型宣告完成)</b>" : (t.verify_command ? " | goal 模式(旧语义,验收命令)" : "")) +
(t.pr_url ? " | <a href='" + esc(t.pr_url) + "' target='_blank' rel='noopener'>PR #" + esc(t.pr_number) + "</a>" : "") +
"<br>prompt:<br>" + esc(t.prompt || "");
var body = "";
@@ -519,7 +516,7 @@ $("#refreshProjects").onclick = loadProjects;
$("#refreshWorkers").onclick = loadWorkers;
$("#refreshTasks").onclick = loadTasks;
$("#projectSelect").onchange = loadTasks;
$("#goalMode").onchange = function () { $("#goalFields").style.display = this.checked ? "block" : "none"; };
$("#goalMode").onchange = function () { $("#goalHint").style.display = this.checked ? "block" : "none"; };
$("#createProject").onclick = async function () {
var name = $("#newProjectName").value.trim();
if (!name) { $("#projectMsg").textContent = "项目名必填"; return; }
@@ -556,9 +553,9 @@ $("#createTask").onclick = async function () {
body.plan = 1;
}
if ($("#goalMode").checked) {
body.goal = $("#goal").value.trim() || prompt;
body.verify_command = $("#verifyCommand").value.trim();
body.goal_max_rounds = parseInt($("#goalRounds").value, 10) || 3;
// 新 goal 语义:prompt 本身就是目标;不发专用 goal 文本、
// 验收命令与轮次(服务端 goal_mode=1 时一律不限轮次)。
body.goal_mode = 1;
}
try {
var t = await api("/tasks", "POST", body);