Present completion research as web document

evaluation-site/Dockerfile

@@ -2,9 +2,13 @@ FROM nginx:1.29.5-alpine
 
 COPY --chmod=0644 nginx.conf /etc/nginx/conf.d/default.conf
 COPY --chmod=0644 index.html /usr/share/nginx/html/index.html
+COPY --chmod=0644 evaluation-v1.html /usr/share/nginx/html/evaluation-v1.html
 RUN install -d -m 0755 /usr/share/nginx/html/assets
 COPY --chmod=0644 assets/styles.css /usr/share/nginx/html/assets/styles.css
 COPY --chmod=0644 assets/app.js /usr/share/nginx/html/assets/app.js
+COPY --chmod=0644 assets/research.css /usr/share/nginx/html/assets/research.css
+COPY --chmod=0644 assets/evidence-data.js /usr/share/nginx/html/assets/evidence-data.js
+COPY --chmod=0644 assets/research.js /usr/share/nginx/html/assets/research.js
 
 EXPOSE 8080
 

evaluation-site/README.md

@@ -1,6 +1,30 @@
-# Agent Evaluation Site
+# Agent Completion Research Site
 
-中文交互式报告，用于展示 K1412 Agent Evaluation v1 的结论、任务契约、发布门禁和相关产物。
+中文研究文档，用网页呈现“Agent 如何证明完成、验证器怎样误判、失败后如何恢复”的
+全文审计结论。
+
+首页是当前研究结论，旧的 K1412 Agent Evaluation v1 说明页保留在：
+
+```text
+/evaluation-v1.html
+```
+
+网页是阅读层，事实源仍是：
+
+- `research/completion-verification/findings.md`
+- `research/completion-verification/evidence-ledger.md`
+
+## Build Evidence Data
+
+证据浏览器由 Markdown 账本确定性生成：
+
+```bash
+python3 evaluation-site/build_research_data.py
+python3 evaluation-site/build_research_data.py --check
+```
+
+`tools/check_project.py` 会检查生成数据的 SHA-256、40 篇全文池、37 篇审计记录和
+26 篇核心证据，防止网页与研究源漂移。
 
 ## Local Preview
 
@@ -8,7 +32,12 @@
 python3 -m http.server 4173 --directory evaluation-site
 ```
 
-打开 `http://127.0.0.1:4173/`。
+打开：
+
+```text
+research document: http://127.0.0.1:4173/
+archived v1 report: http://127.0.0.1:4173/evaluation-v1.html
+```
 
 ## Production
 
@@ -18,10 +47,5 @@ python3 -m http.server 4173 --directory evaluation-site
 - public URL: `https://agent-eval.k1412.top/`
 - deployment: k1412 Unraid Compose Manager
 - NAS host port: `12005`
-- immutable image: `docker.k1412.top/wuyang/agent-eval:20260727T084425Z-cd1eacb`
 
-网页是阅读入口，事实源仍是：
-
-- `research/evaluation/k1412-agent-evaluation-v1.md`
-- `data/evaluation/k1412-agent-eval-task-contracts-v1.json`
-- `tools/evaluation/score_agent_runs.py`
+生产部署必须使用不可变镜像，并在这里和项目状态文档中记录最终 tag。

evaluation-site/assets/research.js

@@ -0,0 +1,296 @@
+(() => {
+  "use strict";
+
+  const evidenceData = window.K1412_EVIDENCE;
+  const evidenceList = document.querySelector("#evidence-list");
+  const evidenceCount = document.querySelector("#evidence-count");
+  const emptyEvidence = document.querySelector("#empty-evidence");
+  const searchInput = document.querySelector("#evidence-search");
+  const expandButton = document.querySelector("#expand-evidence");
+  const depthButtons = [...document.querySelectorAll("[data-depth]")];
+  const themeButtons = [...document.querySelectorAll("[data-theme]")];
+
+  const depthLabels = {
+    core: "核心证据",
+    support: "旁证",
+    context: "历史背景",
+  };
+
+  const themeLabels = {
+    verification: "完成证明",
+    protocol: "协议审计",
+    recovery: "失败恢复",
+    reliability: "风险可靠性",
+    context: "历史背景",
+  };
+
+  const state = {
+    query: "",
+    depth: "all",
+    theme: "all",
+    expanded: false,
+  };
+
+  function normalize(value) {
+    return String(value || "")
+      .toLocaleLowerCase("zh-CN")
+      .replace(/\s+/g, " ")
+      .trim();
+  }
+
+  function searchableText(record) {
+    return normalize(
+      [
+        record.id,
+        record.title,
+        record.depth,
+        record.theme,
+        record.evidence,
+        record.supports,
+        record.boundary,
+      ].join(" ")
+    );
+  }
+
+  function filteredRecords() {
+    if (!evidenceData || !Array.isArray(evidenceData.records)) {
+      return [];
+    }
+
+    const terms = normalize(state.query).split(" ").filter(Boolean);
+    return evidenceData.records.filter((record) => {
+      if (state.depth !== "all" && record.depth !== state.depth) {
+        return false;
+      }
+      if (state.theme !== "all" && record.theme !== state.theme) {
+        return false;
+      }
+      const haystack = searchableText(record);
+      return terms.every((term) => haystack.includes(term));
+    });
+  }
+
+  function tag(label, className) {
+    const element = document.createElement("span");
+    element.className = `evidence-tag ${className || ""}`.trim();
+    element.textContent = label;
+    return element;
+  }
+
+  function detailColumn(title, text, className = "") {
+    const wrapper = document.createElement("div");
+    wrapper.className = className;
+
+    const heading = document.createElement("h4");
+    heading.textContent = title;
+    const paragraph = document.createElement("p");
+    paragraph.textContent = text || "本轮未将该论文用于直接论证。";
+
+    wrapper.append(heading, paragraph);
+    return wrapper;
+  }
+
+  function evidenceItem(record) {
+    const details = document.createElement("details");
+    details.className = "evidence-item";
+    details.dataset.depth = record.depth;
+    details.open = state.expanded;
+
+    const summary = document.createElement("summary");
+
+    const id = document.createElement("span");
+    id.className = "evidence-id";
+    id.textContent = record.id;
+
+    const heading = document.createElement("div");
+    heading.className = "evidence-heading";
+    const title = document.createElement("h3");
+    title.textContent = record.title;
+    const tags = document.createElement("div");
+    tags.className = "evidence-tags";
+    tags.append(
+      tag(depthLabels[record.depth] || record.depth, record.depth),
+      tag(themeLabels[record.theme] || record.theme)
+    );
+    heading.append(title, tags);
+
+    const openLabel = document.createElement("span");
+    openLabel.className = "evidence-open";
+    openLabel.textContent = details.open ? "收起" : "展开";
+
+    summary.append(id, heading, openLabel);
+    details.append(summary);
+
+    if (record.depth === "context") {
+      const detail = document.createElement("div");
+      detail.className = "evidence-detail context-detail";
+      detail.append(
+        detailColumn("本轮位置", record.boundary, "evidence-boundary")
+      );
+      details.append(detail);
+    } else {
+      const detail = document.createElement("div");
+      detail.className = "evidence-detail";
+      detail.append(
+        detailColumn("核过的直接证据", record.evidence),
+        detailColumn("可支持的判断", record.supports),
+        detailColumn("不能外推", record.boundary, "evidence-boundary")
+      );
+      details.append(detail);
+    }
+
+    const source = document.createElement("div");
+    source.className = "evidence-source";
+    const sourceLink = document.createElement("a");
+    sourceLink.href = record.url;
+    sourceLink.target = "_blank";
+    sourceLink.rel = "noreferrer";
+    sourceLink.textContent = "打开 arXiv 原文";
+    source.append(sourceLink);
+    details.append(source);
+
+    details.addEventListener("toggle", () => {
+      openLabel.textContent = details.open ? "收起" : "展开";
+    });
+
+    return details;
+  }
+
+  function updateFilterButtons(buttons, value, attribute) {
+    buttons.forEach((button) => {
+      const active = button.dataset[attribute] === value;
+      button.classList.toggle("is-active", active);
+      button.setAttribute("aria-pressed", String(active));
+    });
+  }
+
+  function renderEvidence() {
+    if (!evidenceData) {
+      evidenceCount.textContent = "证据数据未载入。";
+      emptyEvidence.hidden = false;
+      return;
+    }
+
+    const records = filteredRecords();
+    const fragment = document.createDocumentFragment();
+    records.forEach((record) => fragment.append(evidenceItem(record)));
+    evidenceList.replaceChildren(fragment);
+
+    const counts = evidenceData.counts;
+    evidenceCount.textContent =
+      `显示 ${records.length} / ${counts.pool} 篇` +
+      ` · 核心 ${counts.core} · 旁证 ${counts.support} · 背景 ${counts.context}`;
+    emptyEvidence.hidden = records.length !== 0;
+    expandButton.disabled = records.length === 0;
+    expandButton.textContent = state.expanded ? "收起当前结果" : "展开当前结果";
+  }
+
+  depthButtons.forEach((button) => {
+    button.addEventListener("click", () => {
+      state.depth = button.dataset.depth;
+      state.expanded = false;
+      updateFilterButtons(depthButtons, state.depth, "depth");
+      renderEvidence();
+    });
+  });
+
+  themeButtons.forEach((button) => {
+    button.addEventListener("click", () => {
+      state.theme = button.dataset.theme;
+      state.expanded = false;
+      updateFilterButtons(themeButtons, state.theme, "theme");
+      renderEvidence();
+    });
+  });
+
+  searchInput?.addEventListener("input", (event) => {
+    state.query = event.target.value;
+    state.expanded = false;
+    renderEvidence();
+  });
+
+  expandButton?.addEventListener("click", () => {
+    state.expanded = !state.expanded;
+    document.querySelectorAll(".evidence-item").forEach((item) => {
+      item.open = state.expanded;
+      const label = item.querySelector(".evidence-open");
+      if (label) {
+        label.textContent = state.expanded ? "收起" : "展开";
+      }
+    });
+    expandButton.textContent = state.expanded ? "收起当前结果" : "展开当前结果";
+  });
+
+  function updateReadingProgress() {
+    const documentHeight =
+      document.documentElement.scrollHeight - window.innerHeight;
+    const progress = documentHeight > 0 ? window.scrollY / documentHeight : 0;
+    const bar = document.querySelector("#reading-progress");
+    if (bar) {
+      bar.style.width = `${Math.min(1, Math.max(0, progress)) * 100}%`;
+    }
+  }
+
+  let progressFrame = 0;
+  window.addEventListener(
+    "scroll",
+    () => {
+      if (progressFrame) {
+        return;
+      }
+      progressFrame = window.requestAnimationFrame(() => {
+        updateReadingProgress();
+        progressFrame = 0;
+      });
+    },
+    { passive: true }
+  );
+  updateReadingProgress();
+
+  const navAliases = {
+    conclusions: "overview",
+    synthesis: "model",
+  };
+  const navLinks = [...document.querySelectorAll(".primary-nav a")];
+  const sections = [...document.querySelectorAll("[data-section]")];
+
+  const sectionObserver = new IntersectionObserver(
+    (entries) => {
+      const visible = entries
+        .filter((entry) => entry.isIntersecting)
+        .sort((a, b) => b.intersectionRatio - a.intersectionRatio)[0];
+      if (!visible) {
+        return;
+      }
+      const targetId = navAliases[visible.target.id] || visible.target.id;
+      navLinks.forEach((link) => {
+        const active = link.getAttribute("href") === `#${targetId}`;
+        link.classList.toggle("is-active", active);
+        if (active) {
+          const nav = link.closest(".primary-nav");
+          if (nav && nav.scrollWidth > nav.clientWidth) {
+            nav.scrollTo({
+              left: Math.max(0, link.offsetLeft - nav.clientWidth / 2),
+              behavior: "smooth",
+            });
+          }
+        }
+      });
+    },
+    {
+      rootMargin: "-18% 0px -62% 0px",
+      threshold: [0, 0.08, 0.2],
+    }
+  );
+  sections.forEach((section) => sectionObserver.observe(section));
+
+  renderEvidence();
+
+  if (window.location.hash) {
+    window.requestAnimationFrame(() => {
+      window.requestAnimationFrame(() => {
+        document.querySelector(window.location.hash)?.scrollIntoView();
+      });
+    });
+  }
+})();

evaluation-site/build_research_data.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+"""Build the browser evidence index from the committed Markdown ledger."""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import re
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+LEDGER = ROOT / "research" / "completion-verification" / "evidence-ledger.md"
+OUTPUT = ROOT / "evaluation-site" / "assets" / "evidence-data.js"
+
+SECTION_SLUGS = {
+    "完成证明与 evaluator 误差": "verification",
+    "测试、benchmark 和协议会不会错误认证": "protocol",
+    "故障发现、定位和恢复": "recovery",
+    "变更风险、协作和重复可靠性": "reliability",
+    "全文池与排除": "context",
+}
+
+
+def parse_link(value: str) -> tuple[str, str]:
+    match = re.fullmatch(r"\[([^\]]+)\]\((https?://[^)]+)\)", value.strip())
+    if not match:
+        raise ValueError(f"Invalid paper link: {value}")
+    return match.group(1), match.group(2)
+
+
+def parse_ledger(text: str) -> list[dict[str, str]]:
+    section = ""
+    records: list[dict[str, str]] = []
+
+    for raw_line in text.splitlines():
+        heading = re.match(r"^## \d+\.\s+(.+)$", raw_line)
+        if heading:
+            title = heading.group(1).strip()
+            section = SECTION_SLUGS.get(title, "")
+            continue
+
+        if not raw_line.startswith("| ["):
+            continue
+
+        columns = [column.strip() for column in raw_line.strip().strip("|").split("|")]
+        if len(columns) not in {3, 5}:
+            raise ValueError(f"Unexpected table row with {len(columns)} columns: {raw_line}")
+
+        title, url = parse_link(columns[0])
+        arxiv_match = re.search(r"(\d{4}\.\d{5})", url)
+        if not arxiv_match:
+            raise ValueError(f"Missing arXiv id: {url}")
+        arxiv_id = arxiv_match.group(1)
+        title = re.sub(rf",\s*{re.escape(arxiv_id)}$", "", title)
+
+        record = {
+            "id": arxiv_id,
+            "title": title,
+            "url": url,
+            "depth": columns[1],
+            "theme": section,
+        }
+
+        if len(columns) == 5:
+            record.update(
+                {
+                    "evidence": columns[2],
+                    "supports": columns[3],
+                    "boundary": columns[4],
+                }
+            )
+        else:
+            record.update(
+                {
+                    "evidence": "",
+                    "supports": "",
+                    "boundary": columns[2],
+                }
+            )
+
+        records.append(record)
+
+    return records
+
+
+def build_payload(text: str) -> dict[str, object]:
+    records = parse_ledger(text)
+    counts = {
+        "pool": len(records),
+        "audited": sum(record["depth"] in {"core", "support"} for record in records),
+        "core": sum(record["depth"] == "core" for record in records),
+        "support": sum(record["depth"] == "support" for record in records),
+        "context": sum(record["depth"] == "context" for record in records),
+    }
+    return {
+        "source": "research/completion-verification/evidence-ledger.md",
+        "source_sha256": hashlib.sha256(text.encode("utf-8")).hexdigest(),
+        "counts": counts,
+        "records": records,
+    }
+
+
+def render(payload: dict[str, object]) -> str:
+    body = json.dumps(payload, ensure_ascii=False, separators=(",", ":"))
+    return (
+        "/* Generated by evaluation-site/build_research_data.py. */\n"
+        f"window.K1412_EVIDENCE={body};\n"
+    )
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--check",
+        action="store_true",
+        help="Fail if the generated browser data is stale.",
+    )
+    args = parser.parse_args()
+
+    expected = render(build_payload(LEDGER.read_text(encoding="utf-8")))
+    if args.check:
+        if not OUTPUT.exists() or OUTPUT.read_text(encoding="utf-8") != expected:
+            print(f"stale: {OUTPUT.relative_to(ROOT)}")
+            return 1
+        print(f"ok: {OUTPUT.relative_to(ROOT)}")
+        return 0
+
+    OUTPUT.write_text(expected, encoding="utf-8")
+    print(f"wrote: {OUTPUT.relative_to(ROOT)}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

evaluation-site/evaluation-v1.html

@@ -0,0 +1,353 @@
+<!doctype html>
+<html lang="zh-CN">
+  <head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="theme-color" content="#f3f4ef">
+    <meta
+      name="description"
+      content="K1412 Agent 评估方案：用任务契约、独立判分和配对回归决定一次 Agent 改动是否应该上线。"
+    >
+    <title>K1412 Agent 评估</title>
+    <link
+      rel="icon"
+      href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32'%3E%3Crect width='32' height='32' fill='%23121713'/%3E%3Ctext x='16' y='22' text-anchor='middle' font-family='serif' font-size='18' fill='white'%3EK%3C/text%3E%3C/svg%3E"
+    >
+    <link rel="stylesheet" href="/assets/styles.css">
+    <script src="/assets/app.js" defer></script>
+  </head>
+  <body>
+    <a class="skip-link" href="#main">跳到正文</a>
+
+    <header class="topbar">
+      <a class="brand" href="#conclusion" aria-label="K1412 Agent 评估首页">
+        <span class="brand-mark" aria-hidden="true">K</span>
+        <span>
+          <strong>Agent 评估</strong>
+          <small>K1412 Research</small>
+        </span>
+      </a>
+
+      <nav class="topnav" aria-label="页面导航">
+        <a class="is-active" href="#conclusion">结论</a>
+        <a href="#decision">决策</a>
+        <a href="#layers">层次</a>
+        <a href="#tasks">任务</a>
+        <a href="#artifacts">产物</a>
+      </nav>
+
+      <a
+        class="source-link"
+        href="https://git.k1412.top/wuyang/agent"
+        target="_blank"
+        rel="noreferrer"
+      >源仓库</a>
+    </header>
+
+    <main id="main">
+      <section class="report-intro" id="conclusion" data-section>
+        <div class="section-number">01 / 结论</div>
+        <div class="intro-layout">
+          <div class="intro-copy">
+            <p class="eyebrow">K1412 Agent Evaluation v1 · 2026.07.27</p>
+            <h1>不评总分，只评一次改动是否该上线。</h1>
+            <p class="lead">
+              固定模型、任务、工作区和预算，只改变一个 Agent 行为假设。
+              用独立验证回答它改善了什么、破坏了什么，以及证据是否足以进入生产。
+            </p>
+          </div>
+
+          <aside class="evidence-boundary" aria-label="证据边界">
+            <p class="boundary-label">当前证据边界</p>
+            <p>
+              方案来自对 <code>zk-data-agent@e2e7a7b</code> 真实运行事件、
+              隔离工作区和完成门禁的检查。
+            </p>
+            <p class="boundary-warning">
+              尚未运行真实模型对比。最新论文只是摘要级线索。
+            </p>
+          </aside>
+        </div>
+
+        <dl class="headline-stats" aria-label="方案摘要">
+          <div>
+            <dt>任务契约</dt>
+            <dd>10</dd>
+            <small>跨产物、恢复、上下文、安全与委派</small>
+          </div>
+          <div>
+            <dt>评测层次</dt>
+            <dd>6</dd>
+            <small>从确定性单测到生产价值抽样</small>
+          </div>
+          <div>
+            <dt>当前可跑</dt>
+            <dd>2</dd>
+            <small>其余任务明确标注 runner 缺口</small>
+          </div>
+          <div>
+            <dt>真实对比</dt>
+            <dd>0</dd>
+            <small>不把设计契约伪装成实验结论</small>
+          </div>
+        </dl>
+
+        <div class="method-rail" aria-label="评估闭环">
+          <div><span>01</span><strong>问题</strong><small>一次只改变一个假设</small></div>
+          <div><span>02</span><strong>任务</strong><small>固定夹具、预算和模型</small></div>
+          <div><span>03</span><strong>运行</strong><small>配对、重复、随机顺序</small></div>
+          <div><span>04</span><strong>判分</strong><small>独立 Validator 与轨迹规则</small></div>
+          <div><span>05</span><strong>决定</strong><small>推广、继续或拒绝</small></div>
+        </div>
+      </section>
+
+      <section class="decision-section" id="decision" data-section>
+        <div class="section-heading">
+          <div>
+            <div class="section-number">02 / 发布决策</div>
+            <h2>先看回归，再谈平均提升</h2>
+          </div>
+          <p>
+            下面是方法演算，不是真实跑分。它使用与仓库评分器一致的配对逻辑和统计口径。
+          </p>
+        </div>
+
+        <div class="decision-workbench">
+          <form class="simulation-controls" id="simulation-form">
+            <fieldset>
+              <legend>配对运行结果</legend>
+
+              <label class="range-row" for="gains">
+                <span><strong>新增成功</strong><small>基线失败，候选成功</small></span>
+                <input id="gains" name="gains" type="range" min="0" max="20" value="6">
+                <output for="gains">6</output>
+              </label>
+
+              <label class="range-row" for="regressions">
+                <span><strong>回归失败</strong><small>基线成功，候选失败</small></span>
+                <input id="regressions" name="regressions" type="range" min="0" max="20" value="1">
+                <output for="regressions">1</output>
+              </label>
+
+              <label class="range-row" for="both-pass">
+                <span><strong>双方成功</strong><small>两种版本都通过</small></span>
+                <input id="both-pass" name="bothPass" type="range" min="0" max="30" value="18">
+                <output for="both-pass">18</output>
+              </label>
+
+              <label class="range-row" for="both-fail">
+                <span><strong>双方失败</strong><small>两种版本都未通过</small></span>
+                <input id="both-fail" name="bothFail" type="range" min="0" max="30" value="5">
+                <output for="both-fail">5</output>
+              </label>
+            </fieldset>
+
+            <fieldset class="gate-controls">
+              <legend>硬门禁与效率</legend>
+              <label>
+                <span>安全违规</span>
+                <input id="safety" name="safety" type="number" min="0" max="99" value="0">
+              </label>
+              <label>
+                <span>新增假完成</span>
+                <input id="false-completion" name="falseCompletion" type="number" min="0" max="99" value="0">
+              </label>
+              <label class="latency-control" for="latency">
+                <span>候选延迟变化</span>
+                <input id="latency" name="latency" type="range" min="-50" max="50" value="-12">
+                <output for="latency">-12%</output>
+              </label>
+            </fieldset>
+          </form>
+
+          <div class="decision-output" aria-live="polite">
+            <div class="decision-status">
+              <span class="status-dot" aria-hidden="true"></span>
+              <div>
+                <small>机械建议</small>
+                <h3 id="decision-label">发布候选</h3>
+              </div>
+              <span class="sample-count" id="sample-count">30 次配对</span>
+            </div>
+
+            <p class="decision-reason" id="decision-reason">
+              新增成功多于回归，且没有安全或假完成阻断项。进入轨迹复核，而不是直接发布。
+            </p>
+
+            <div class="outcome-matrix" aria-label="基线与候选结果矩阵">
+              <div class="matrix-corner">基线 \ 候选</div>
+              <div class="matrix-axis">失败</div>
+              <div class="matrix-axis">成功</div>
+              <div class="matrix-axis matrix-row-label">失败</div>
+              <div class="matrix-cell neutral"><span>双方失败</span><strong id="matrix-both-fail">5</strong></div>
+              <div class="matrix-cell positive"><span>新增成功</span><strong id="matrix-gain">6</strong></div>
+              <div class="matrix-axis matrix-row-label">成功</div>
+              <div class="matrix-cell negative"><span>回归失败</span><strong id="matrix-regression">1</strong></div>
+              <div class="matrix-cell stable"><span>双方成功</span><strong id="matrix-both-pass">18</strong></div>
+            </div>
+
+            <div class="rate-comparison">
+              <div>
+                <span>基线成功率</span>
+                <strong id="baseline-rate">63.3%</strong>
+                <small id="baseline-ci">95% CI 45.5%–78.1%</small>
+              </div>
+              <div>
+                <span>候选成功率</span>
+                <strong id="variant-rate">80.0%</strong>
+                <small id="variant-ci">95% CI 62.7%–90.5%</small>
+              </div>
+              <div>
+                <span>配对差异</span>
+                <strong id="net-gain">+5</strong>
+                <small id="mcnemar-p">McNemar p = 0.125</small>
+              </div>
+            </div>
+
+            <div class="blocker-line" id="blocker-line">
+              <strong>硬门禁通过</strong>
+              <span>安全违规 0 · 新增假完成 0</span>
+            </div>
+          </div>
+        </div>
+      </section>
+
+      <section class="layer-section" id="layers" data-section>
+        <div class="section-heading">
+          <div>
+            <div class="section-number">03 / 评测层次</div>
+            <h2>高层成功不能掩盖底层回归</h2>
+          </div>
+          <p>真实模型评测建立在单测、隔离和伪模型链路之上，不替代它们。</p>
+        </div>
+
+        <div class="layer-tabs" role="tablist" aria-label="评测层次">
+          <button class="is-active" role="tab" aria-selected="true" data-layer="0">L0 单元</button>
+          <button role="tab" aria-selected="false" data-layer="1">L1 Docker</button>
+          <button role="tab" aria-selected="false" data-layer="2">L2 E2E</button>
+          <button role="tab" aria-selected="false" data-layer="3">L3 行为</button>
+          <button role="tab" aria-selected="false" data-layer="4">L4 压力</button>
+          <button role="tab" aria-selected="false" data-layer="5">L5 生产</button>
+        </div>
+
+        <article class="layer-detail" id="layer-detail" tabindex="0">
+          <div class="layer-code" id="layer-code">L0</div>
+          <div>
+            <p class="layer-purpose" id="layer-purpose">单元与策略门禁</p>
+            <h3 id="layer-title">先证明规则本身没有坏</h3>
+            <p id="layer-description">
+              检查参数规范化、完成证据、权限和事件顺序。每次提交运行，不调用真实模型。
+            </p>
+          </div>
+          <dl>
+            <div><dt>模型</dt><dd id="layer-model">不调用</dd></div>
+            <div><dt>节奏</dt><dd id="layer-cadence">每次提交</dd></div>
+            <div><dt>失败动作</dt><dd id="layer-action">阻止进入高层评测</dd></div>
+          </dl>
+        </article>
+      </section>
+
+      <section class="task-section" id="tasks" data-section>
+        <div class="section-heading">
+          <div>
+            <div class="section-number">04 / 任务契约</div>
+            <h2>任务描述不是真值</h2>
+          </div>
+          <p>最终状态、命令结果和副作用 Validator 才决定任务是否真的完成。</p>
+        </div>
+
+        <div class="task-toolbar">
+          <label class="search-field" for="task-search">
+            <span class="visually-hidden">搜索任务</span>
+            <input id="task-search" type="search" placeholder="搜索任务、能力或场景">
+          </label>
+          <div class="segmented" role="group" aria-label="任务状态筛选">
+            <button class="is-active" data-filter="all">全部 <span>10</span></button>
+            <button data-filter="current">当前可跑 <span>2</span></button>
+            <button data-filter="needed">需补能力 <span>8</span></button>
+          </div>
+        </div>
+
+        <div class="task-list-header" aria-hidden="true">
+          <span>任务</span>
+          <span>能力家族</span>
+          <span>Runner 状态</span>
+          <span></span>
+        </div>
+        <div class="task-list" id="task-list"></div>
+        <p class="empty-state" id="task-empty" hidden>没有匹配的任务。</p>
+      </section>
+
+      <section class="artifact-section" id="artifacts" data-section>
+        <div class="section-heading">
+          <div>
+            <div class="section-number">05 / 相关产物</div>
+            <h2>结论、契约、工具与边界均可追溯</h2>
+          </div>
+          <p>网页是阅读入口，Git 仓库仍是事实源。</p>
+        </div>
+
+        <div class="artifact-list">
+          <a href="https://git.k1412.top/wuyang/agent/src/branch/main/research/evaluation/k1412-agent-evaluation-v1.md" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A1</span>
+            <span><strong>中文评估方案</strong><small>问题、任务、层次、判分、指标、协议和发布门禁</small></span>
+            <em>设计契约</em>
+          </a>
+          <a href="https://git.k1412.top/wuyang/agent/src/branch/main/data/evaluation/k1412-agent-eval-task-contracts-v1.json" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A2</span>
+            <span><strong>10 个任务契约</strong><small>机器可读的目标、完成条件、禁区、预算和 Runner 缺口</small></span>
+            <em>JSON</em>
+          </a>
+          <a href="https://git.k1412.top/wuyang/agent/src/branch/main/tools/evaluation/score_agent_runs.py" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A3</span>
+            <span><strong>运行结果评分器</strong><small>汇总成功、假完成、回归、区间、配对检验、延迟与 Token</small></span>
+            <em>Python</em>
+          </a>
+          <a href="https://git.k1412.top/wuyang/agent/src/branch/main/experiments/agent-evaluation/2026-07-27-k1412-agent-evaluation-design.md" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A4</span>
+            <span><strong>实验记录</strong><small>已经确认的事实、设计假设、验证结果和不可外推边界</small></span>
+            <em>记录</em>
+          </a>
+          <a href="https://git.k1412.top/wuyang/agent/src/branch/main/papers/corpus-summary-2026-07-27.md" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A5</span>
+            <span><strong>论文增量摘要</strong><small>249 个候选、157 个高相关、151 篇新增及评测研究信号</small></span>
+            <em>语料</em>
+          </a>
+          <a href="https://lab.k1412.top/" target="_blank" rel="noreferrer">
+            <span class="artifact-index">A6</span>
+            <span><strong>Agent 论文库</strong><small>1125 篇论文的搜索、主题探索和原始条目入口</small></span>
+            <em>在线</em>
+          </a>
+        </div>
+
+        <div class="command-line">
+          <code>python3 tools/evaluation/score_agent_runs.py results.jsonl --baseline v3 --variant v4 --format markdown</code>
+          <button id="copy-command" type="button">复制命令</button>
+        </div>
+      </section>
+
+      <section class="implementation-section" id="implementation">
+        <div class="section-number">06 / 下一步</div>
+        <div class="implementation-layout">
+          <div>
+            <p class="eyebrow">Implementation order</p>
+            <h2>先让两项任务真实可判，再扩大任务集。</h2>
+          </div>
+          <ol>
+            <li><span>01</span><p><strong>抽出 LiveEvalRunner</strong>从现有单次脚本提取可复用运行器。</p></li>
+            <li><span>02</span><p><strong>接入独立 Validator</strong>先覆盖脚本报告与数据分析两个任务。</p></li>
+            <li><span>03</span><p><strong>导出 Result JSONL</strong>固定模型、Prompt、工具、镜像、预算与版本。</p></li>
+            <li><span>04</span><p><strong>运行配对 Smoke</strong>确定性层全部通过后才调用真实模型。</p></li>
+            <li><span>05</span><p><strong>复核回归轨迹</strong>检查 gains、regressions、both-fail 与假完成。</p></li>
+          </ol>
+        </div>
+      </section>
+    </main>
+
+    <footer>
+      <span>K1412 Agent Evaluation</span>
+      <span>方案基线 <code>df475e8</code></span>
+      <span>数据更新 2026.07.27</span>
+    </footer>
+  </body>
+</html>

tools/check_project.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import ast
+import hashlib
 import json
 from collections import Counter
 from pathlib import Path
@@ -21,12 +22,19 @@ REQUIRED_FILES = (
     "data/summary.json",
     "research/memory/findings.md",
     "research/memory/evidence-ledger.md",
+    "research/completion-verification/findings.md",
+    "research/completion-verification/evidence-ledger.md",
     "research/evaluation/k1412-agent-evaluation-v1.md",
     "data/evaluation/k1412-agent-eval-task-contracts-v1.json",
     "tools/evaluation/score_agent_runs.py",
     "evaluation-site/index.html",
+    "evaluation-site/evaluation-v1.html",
     "evaluation-site/assets/styles.css",
     "evaluation-site/assets/app.js",
+    "evaluation-site/assets/research.css",
+    "evaluation-site/assets/research.js",
+    "evaluation-site/assets/evidence-data.js",
+    "evaluation-site/build_research_data.py",
     "evaluation-site/Dockerfile",
     "evaluation-site/nginx.conf",
     "web/app.py",
@@ -96,7 +104,10 @@ def check_research_data() -> dict[str, int]:
 
 
 def check_python_syntax() -> int:
-    paths = sorted((ROOT / "tools").rglob("*.py")) + [ROOT / "web" / "app.py"]
+    paths = sorted((ROOT / "tools").rglob("*.py")) + [
+        ROOT / "web" / "app.py",
+        ROOT / "evaluation-site" / "build_research_data.py",
+    ]
     for path in paths:
         ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
     return len(paths)
@@ -143,16 +154,52 @@ def check_evaluation_contract() -> int:
     return len(tasks)
 
 
-def check_evaluation_site() -> None:
+def check_evaluation_site() -> int:
     html = (ROOT / "evaluation-site/index.html").read_text(encoding="utf-8")
+    archived_html = (ROOT / "evaluation-site/evaluation-v1.html").read_text(encoding="utf-8")
     javascript = (ROOT / "evaluation-site/assets/app.js").read_text(encoding="utf-8")
+    research_javascript = (ROOT / "evaluation-site/assets/research.js").read_text(encoding="utf-8")
+    evidence_javascript = (ROOT / "evaluation-site/assets/evidence-data.js").read_text(
+        encoding="utf-8"
+    )
+    ledger = (ROOT / "research/completion-verification/evidence-ledger.md").read_text(
+        encoding="utf-8"
+    )
     dockerfile = (ROOT / "evaluation-site/Dockerfile").read_text(encoding="utf-8")
     nginx = (ROOT / "evaluation-site/nginx.conf").read_text(encoding="utf-8")
-    require("不是真实跑分" in html, "evaluation simulation must keep its evidence boundary visible")
-    require("尚未运行真实模型对比" in html, "evaluation report overstates current evidence")
+    require("Agent 到底凭什么说" in html, "completion research document is missing")
+    require("自有跑分" in html and ">0<" in html, "research page overstates benchmark evidence")
+    require("completion certificate" in html.lower(), "research synthesis boundary is missing")
+    require(
+        "不是真实跑分" in archived_html,
+        "archived evaluation simulation must keep its evidence boundary visible",
+    )
+    require(
+        "尚未运行真实模型对比" in archived_html,
+        "archived evaluation report overstates current evidence",
+    )
     require("const TASKS" in javascript, "evaluation task browser is missing")
+    require("K1412_EVIDENCE" in research_javascript, "research evidence browser is missing")
+
+    prefix = "window.K1412_EVIDENCE="
+    require(evidence_javascript.startswith("/* Generated") and prefix in evidence_javascript, "bad evidence data")
+    payload_text = evidence_javascript.split(prefix, 1)[1].strip()
+    require(payload_text.endswith(";"), "bad evidence data terminator")
+    payload = json.loads(payload_text[:-1])
+    counts = payload.get("counts") or {}
+    records = payload.get("records") or []
+    require(counts.get("pool") == len(records) == 40, "completion evidence pool count mismatch")
+    require(counts.get("audited") == 37, "completion audited count mismatch")
+    require(counts.get("core") == 26, "completion core count mismatch")
+    require(
+        payload.get("source_sha256") == hashlib.sha256(ledger.encode("utf-8")).hexdigest(),
+        "completion evidence browser data is stale",
+    )
+
     require("install -d -m 0755" in dockerfile, "static asset directory must remain traversable")
+    require("evaluation-v1.html" in dockerfile, "archived evaluation page is not packaged")
     require('location = /health' in nginx, "evaluation site health endpoint is missing")
+    return int(counts["audited"])
 
 
 def main() -> int:
@@ -163,7 +210,7 @@ def main() -> int:
     check_ollama_contract()
     check_experiment_state()
     evaluation_tasks = check_evaluation_contract()
-    check_evaluation_site()
+    completion_evidence = check_evaluation_site()
     print(
         json.dumps(
             {
@@ -171,6 +218,7 @@ def main() -> int:
                 "collections": collections,
                 "research": research,
                 "evaluation_tasks": evaluation_tasks,
+                "completion_evidence": completion_evidence,
                 "evaluation_site": True,
                 "python_files_checked": python_files,
             },