muse-agent-example/docs/2026-07-20-正文智能体正式优化架构.html

103 lines
6.5 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!doctype html>
<html lang="zh-CN">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>正文智能体正式优化架构</title>
<style>
:root {
color-scheme: light;
--ink: #182128;
--muted: #596872;
--line: #c8d0d6;
--paper: #f5f7f8;
--blue: #dcecff;
--green: #ddf2e5;
--amber: #fff0c7;
--violet: #ebe3f8;
--red: #f8dddd;
--cyan: #def0f1;
}
* { box-sizing: border-box; }
body { margin: 0; background: var(--paper); color: var(--ink); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; letter-spacing: 0; }
main { width: min(1240px, calc(100% - 32px)); margin: 28px auto 48px; }
h1 { margin: 0 0 8px; font-size: 28px; }
.lead { margin: 0 0 26px; color: var(--muted); line-height: 1.6; }
section { margin-top: 30px; }
h2 { margin: 0 0 12px; font-size: 19px; }
.lane { display: grid; grid-template-columns: repeat(6, minmax(130px, 1fr)); gap: 12px; align-items: stretch; }
.node { min-height: 112px; padding: 14px; border: 1px solid var(--line); border-radius: 8px; background: white; position: relative; }
.node:not(:last-child)::after { content: "→"; position: absolute; right: -13px; top: 42px; z-index: 2; font-size: 18px; color: #53616c; }
.node strong { display: block; margin-bottom: 7px; font-size: 15px; }
.node span { color: var(--muted); font-size: 13px; line-height: 1.45; }
.outline { background: var(--blue); }
.cards { background: var(--green); }
.prose { background: var(--amber); }
.writer { background: var(--violet); }
.detector { background: var(--red); }
.decision { background: var(--cyan); }
.loops { display: grid; grid-template-columns: repeat(3, 1fr); gap: 14px; margin-top: 14px; }
.loop { padding: 14px 16px; border-left: 4px solid #687d8a; background: white; }
.loop b { display: block; margin-bottom: 6px; }
.loop p { margin: 0; color: var(--muted); font-size: 13px; line-height: 1.55; }
.eval { display: grid; grid-template-columns: 1fr 1fr 1fr 1.2fr 1fr; gap: 12px; }
.evidence, .orders { display: grid; grid-template-columns: 1fr 1fr; gap: 14px; }
.evidence article, .orders article { padding: 16px; border: 1px solid var(--line); border-radius: 8px; background: white; }
.evidence h3, .orders h3 { margin: 0 0 7px; font-size: 15px; }
.evidence p, .orders p { margin: 0; color: var(--muted); font-size: 13px; line-height: 1.55; }
@media (max-width: 980px) { .lane, .eval { grid-template-columns: 1fr 1fr; } .node::after { display: none; } .loops, .evidence, .orders { grid-template-columns: 1fr; } }
@media (max-width: 540px) { .lane, .eval { grid-template-columns: 1fr; } }
</style>
</head>
<body>
<main>
<h1>正文智能体正式优化架构</h1>
<p class="lead">卡负责定位,原文负责表现,正式设定负责事实,writer 只负责创作。生产链与离线评测链严格分离。</p>
<section>
<h2>两个方向不能混用</h2>
<div class="orders">
<article><h3>能力验证</h3><p>正文智能体 → 细纲智能体 → 大纲+设定智能体。自底向上隔离变量。</p></article>
<article><h3>正式生产</h3><p>大纲+设定 → 细纲 → 正文智能体。自顶向下提供创作输入。</p></article>
</div>
</section>
<section>
<h2>生产链</h2>
<div class="lane">
<div class="node outline"><strong>1. 已确认细纲</strong><span>硬事件、可调节拍、伏笔、钩子和新设定声明。</span></div>
<div class="node cards"><strong>2. 检索规划与卡索引</strong><span>按 asOf 重建当前态,带出历史来源指针。</span></div>
<div class="node prose"><strong>3. 连续四章 + 原文回读</strong><span>事实证据与表现证据分开装配,生成确定性 manifest。</span></div>
<div class="node writer"><strong>4. 无工具 Writer</strong><span>只接收 WriterContext;可按预算请求补证。</span></div>
<div class="node detector"><strong>5. Detector 硬门</strong><span>核细纲、事实、证据、时间线和输出合同,最多返修两轮。</span></div>
<div class="node decision"><strong>6. Shadow 与用户三决策</strong><span>原样接受先做 accept_preflight;修改后合并生成新版本 → detector → 返回 Shadow → accept_preflight;通过后 confirm。</span></div>
</div>
<div class="loops">
<div class="loop"><b>补证环</b><p>Writer 可返回结构化 evidenceRequests;最多 3 次,累计新增上下文不超过检索预算 30%。</p></div>
<div class="loop"><b>返修环</b><p>Detector 只阻断可验证硬错误;Writer 最多自动返修 2 轮,仍失败则交用户。</p></div>
<div class="loop"><b>创作自由边界</b><p>硬事件、结果和伏笔不可改;场景可拆并调序,可创造环境、动作、过渡和对白;新增 Canonical 事实必须申报。</p></div>
</div>
</section>
<section>
<h2>双证据模型</h2>
<div class="evidence">
<article><h3>Fact Evidence</h3><p>正式设定、Canonical 卡、状态台账、已确认正文和细纲声明的新事实,负责“写得对”。没有可靠事实来源的硬结论必须阻断。</p></article>
<article><h3>Prose Evidence</h3><p>历史原文场景,负责人物声音、动作习惯、能力表现、段落节奏和章末钩子,回答“怎么写得像”。</p></article>
</div>
</section>
<section>
<h2>离线评测链</h2>
<div class="eval">
<div class="node outline"><strong>A/B/C 三臂</strong><span>原文线、卡线、双线;A/B 只作诊断,不能被接受。</span></div>
<div class="node detector"><strong>统一 Detector</strong><span>授权、冻结、泄漏和候选结构门保持一致。</span></div>
<div class="node writer"><strong>双独立盲评</strong><span>臂名掩码,第二评委反序,评分步长 0.5。</span></div>
<div class="node prose"><strong>稳定性 / 第三评委</strong><span>同维差值超过 0.5 时最多增加一次第三评委。</span></div>
<div class="node decision"><strong>Gate A / Gate B</strong><span>Gate A:不足5章=insufficient;任一 schema/泄漏/系统/硬门失败=failed;其余 passed。Gate B:不足2书10章或不稳定&gt;20%=insufficient;硬错或文风/张力退化=failed;保真均值≥+0.25且60%样本正增益=passed;其余 no_gain。仅 passed 解锁细纲。</span></div>
</div>
</section>
</main>
</body>
</html>