SEO: real robots.txt + hreflang pairs + BlogPosting schema

robots.txt was absent at the origin, so Cloudflare served its Free-plan
Content Signals Policy placeholder — a file with no User-agent, no Sitemap
and no directives. Adds src/pages/robots.txt.ts (origin 200 → CF merges
instead of substituting) pointing at sitemap-index.xml, disallowing
/pagefind/, and expressing search=yes / ai-input=yes / ai-train=no in line
with the two-lane SEO+GEO strategy in docs/seo-reference.md. Citation
crawlers (Google-Extended, OAI-SearchBot, PerplexityBot, ClaudeBot) stay
allowed; only training-only harvesters blocked.

hreflang was never emitted despite full EN/ZH i18n: both language versions
sat in the sitemap with no cross-reference. BaseLayout gains altLocaleUrl
and emits en/zh/x-default per page; every post pair, category pair, and
landing page now cross-links.

Also adds BlogPosting JSON-LD (@id-linked to the site-wide Person node)
so Google has a rich-result-eligible node per article, and creates the
missing /zh/about/ page — the EN about page pointed its language switch at
a 404, and /about/ was the only unpaired page after hreflang landed.

src/layouts/BaseLayout.astro

@@ -15,6 +15,9 @@ interface Props {
   // When provided, the language switch links to it; otherwise it falls back to
   // the section landing page (/ for EN, /zh/ for ZH).
   switchHref?: string;
+  // Absolute URL of the other-language version of THIS page (built by each
+  // page) — drives hreflang so EN/ZH twins don't compete for the same query.
+  altLocaleUrl?: string;
   article?: {
     publishedTime: string;
     modifiedTime?: string;
@@ -30,12 +33,23 @@ const {
   ogImage = '/og-default.png',
   type = 'website',
   switchHref,
+  altLocaleUrl,
   article,
 } = Astro.props;
 
 const canonical = new URL(Astro.url.pathname, SITE.url).href;
 const ogImageUrl = new URL(ogImage, SITE.url).href;
 
+// hreflang: only emitted when the page has a known counterpart in the other
+// language. x-default points at the English version (English-first site).
+const hreflang = altLocaleUrl
+  ? [
+      { hreflang: 'en', href: lang === 'en' ? canonical : altLocaleUrl },
+      { hreflang: 'zh', href: lang === 'zh' ? canonical : altLocaleUrl },
+      { hreflang: 'x-default', href: lang === 'en' ? canonical : altLocaleUrl },
+    ]
+  : [];
+
 // Language switcher: opposite of current page lang.
 // If a per-page translation link is provided, use it; else fall back to the section landing.
 const isZh = lang === 'zh';
@@ -59,6 +73,11 @@ const nav = isZh
     <meta name="description" content={description} />
     <link rel="canonical" href={canonical} />
 
+    <!-- hreflang: this page + its other-language twin -->
+    {hreflang.map((alt) => (
+      <link rel="alternate" hreflang={alt.hreflang} href={alt.href} />
+    ))}
+
     <!-- Open Graph -->
     <meta property="og:type" content={type} />
     <meta property="og:site_name" content={SITE.name} />
@@ -69,6 +88,7 @@ const nav = isZh
     <meta property="og:image:width" content="1200" />
     <meta property="og:image:height" content="630" />
     <meta property="og:locale" content={SITE.locale} />
+    {lang === 'zh' && <meta property="og:locale:alternate" content="en_US" />}
 
     <!-- Twitter -->
     <meta name="twitter:card" content="summary_large_image" />
@@ -101,6 +121,7 @@ const nav = isZh
     <script type="application/ld+json" set:html={JSON.stringify({
       '@context': 'https://schema.org',
       '@type': 'Person',
+      '@id': `${SITE.url}/#person`,
       name: SITE.author,
       alternateName: SITE.handle,
       url: SITE.url,

src/pages/about.astro

@@ -4,7 +4,12 @@ import AuthorCard from '../components/AuthorCard.astro';
 import { SITE } from '../config';
 ---
 
-<BaseLayout title="About — Mr Hoelee" description={`About ${SITE.author} (${SITE.handle}).`}>
+<BaseLayout
+  title="About — Mr Hoelee"
+  description={`About ${SITE.author} (${SITE.handle}).`}
+  switchHref="/zh/about/"
+  altLocaleUrl={`${SITE.url}/zh/about/`}
+>
   <h1>About</h1>
   <p>
     I'm {SITE.author} ({SITE.handle}), a full-stack developer and DevOps engineer

src/pages/categories/[category].astro

@@ -1,5 +1,6 @@
 ---
 import BaseLayout from '../../layouts/BaseLayout.astro';
+import { SITE } from '../../config';
 import PostList from '../../components/PostList.astro';
 import CategoryArt from '../../components/CategoryArt.astro';
 import { getCollection } from 'astro:content';
@@ -28,6 +29,7 @@ const blurb = meta?.blurb.en;
   title={`${name} — Mr Hoelee`}
   description={blurb ?? `Posts in the ${category} category.`}
   switchHref={`/zh/categories/${category}/`}
+  altLocaleUrl={`${SITE.url}/zh/categories/${category}/`}
 >
   <h1>{name}</h1>
   {blurb && <p class="lede">{blurb}</p>}

src/pages/categories/index.astro

@@ -3,6 +3,7 @@ import BaseLayout from '../../layouts/BaseLayout.astro';
 import CategoryGrid from '../../components/CategoryGrid.astro';
 import { getCollection } from 'astro:content';
 import { isEn } from '../../lib/lang';
+import { SITE } from '../../config';
 
 const posts = await getCollection('posts', isEn);
 
@@ -17,6 +18,7 @@ for (const p of posts) {
   title="Categories — Mr Hoelee"
   description={`Browse ${posts.length} technical posts by category: case studies, DevOps, AI, engineering, tutorials and quick notes.`}
   switchHref="/zh/categories/"
+  altLocaleUrl={`${SITE.url}/zh/categories/`}
 >
   <div class="page-head">
     <h1>Categories</h1>

src/pages/index.astro

@@ -9,7 +9,7 @@ import { sortByUpdated } from '../lib/sort';
 const posts = sortByUpdated(await getCollection('posts', isEn));
 ---
 
-<BaseLayout title={SITE.title} description={SITE.description}>
+<BaseLayout title={SITE.title} description={SITE.description} altLocaleUrl={`${SITE.url}/zh/`}>
   <section>
     <h1>Hi, I'm {SITE.author}.</h1>
     <p>

src/pages/posts/[...slug].astro

@@ -3,6 +3,7 @@ import BaseLayout from '../../layouts/BaseLayout.astro';
 import AuthorCard from '../../components/AuthorCard.astro';
 import { getCollection, render } from 'astro:content';
 import { postLang } from '../../lib/lang';
+import { SITE } from '../../config';
 
 export async function getStaticPaths() {
   const posts = await getCollection('posts', ({ data }) => !data.draft);
@@ -45,6 +46,28 @@ const otherLangSlug = lang === 'en' ? `zh/${post.slug}` : post.slug.replace(/^zh
 const translation = post.data.translation
   ?? (all.some((p) => p.slug === otherLangSlug) ? otherLangSlug : undefined);
 const switchHref = translation ? `/posts/${translation}/` : undefined;
+const altLocaleUrl = translation ? new URL(`/posts/${translation}/`, SITE.url).href : undefined;
+
+// BlogPosting structured data — gives Google a rich-result-eligible node and
+// links the article to the site-wide Person node (E-E-A-T).
+const postUrl = new URL(`/posts/${post.slug}/`, SITE.url).href;
+const jsonLd = {
+  '@context': 'https://schema.org',
+  '@type': 'BlogPosting',
+  mainEntityOfPage: { '@type': 'WebPage', '@id': postUrl },
+  headline: post.data.title,
+  description: post.data.description,
+  image: new URL(post.data.ogImage ?? '/og-default.png', SITE.url).href,
+  inLanguage: lang === 'zh' ? 'zh' : 'en',
+  datePublished: post.data.pubDate.toISOString(),
+  dateModified: (post.data.updatedDate ?? post.data.pubDate).toISOString(),
+  author: { '@id': `${SITE.url}/#person` },
+  publisher: { '@id': `${SITE.url}/#person` },
+  isPartOf: { '@type': 'Blog', '@id': `${SITE.url}/#blog`, name: SITE.name, url: SITE.url },
+  articleSection: post.data.category,
+  keywords: post.data.tags.join(', '),
+  wordCount: words,
+};
 ---
 
 <BaseLayout
@@ -54,6 +77,7 @@ const switchHref = translation ? `/posts/${translation}/` : undefined;
   ogImage={post.data.ogImage ?? '/og-default.png'}
   type="article"
   switchHref={switchHref}
+  altLocaleUrl={altLocaleUrl}
   article={{
     publishedTime: post.data.pubDate.toISOString(),
     modifiedTime: post.data.updatedDate?.toISOString(),
@@ -61,6 +85,7 @@ const switchHref = translation ? `/posts/${translation}/` : undefined;
     category: post.data.category,
   }}
 >
+  <script type="application/ld+json" set:html={JSON.stringify(jsonLd)} />
   <article>
     <header class="article-head">
       <h1>{post.data.title}</h1>

src/pages/posts/index.astro

@@ -4,11 +4,17 @@ import PostList from '../../components/PostList.astro';
 import { getCollection } from 'astro:content';
 import { isEn } from '../../lib/lang';
 import { sortByUpdated } from '../../lib/sort';
+import { SITE } from '../../config';
 
 const posts = sortByUpdated(await getCollection('posts', isEn));
 ---
 
-<BaseLayout title="Posts — Mr Hoelee" description="All posts on Mr Hoelee's blog.">
+<BaseLayout
+  title="Posts — Mr Hoelee"
+  description="All posts on Mr Hoelee's blog."
+  switchHref="/zh/"
+  altLocaleUrl={`${SITE.url}/zh/`}
+>
   <h1>Posts</h1>
   {posts.length === 0 ? (
     <p><em>No posts yet.</em></p>

src/pages/robots.txt.ts

@@ -0,0 +1,54 @@
+import type { APIRoute } from 'astro';
+import { SITE } from '../config';
+
+/**
+ * robots.txt — served from the origin so Cloudflare merges its managed
+ * block instead of substituting the placeholder Content Signals Policy.
+ *
+ * Policy here: allow classic search (this blog is a name-search / GEO play)
+ * and allow the citation crawlers that power AI Overviews / ChatGPT Search /
+ * Perplexity, because being cited is the point of the two-lane strategy in
+ * docs/seo-reference.md. Block only the training-only harvesters that give
+ * no referral traffic back.
+ */
+export const GET: APIRoute = () => {
+  const body = `# robots.txt — blog.hoelee.com
+# Policy: index freely. Allow citation/answer engines, block training-only harvesters.
+
+User-agent: *
+Allow: /
+
+# Pagefind's search shards are build artifacts, not content.
+Disallow: /pagefind/
+
+# AI trainers that send no traffic back (blocked).
+User-agent: CCBot
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+User-agent: Amazonbot
+Disallow: /
+
+User-agent: Applebot-Extended
+Disallow: /
+
+# Deliberately ALLOWED (cite us, don't train on us — enforced by Cloudflare
+# Content-Signal below): Googlebot / Google-Extended (AI Overviews, Gemini),
+# OAI-SearchBot / GPTBot (ChatGPT Search), PerplexityBot, ClaudeBot, Bingbot.
+
+# Content signals: machine-readable preference statements (contentsignals.org).
+User-Agent: *
+Content-Signal: search=yes, ai-input=yes, ai-train=no
+
+Sitemap: ${SITE.url}/sitemap-index.xml
+`;
+
+  return new Response(body, {
+    headers: {
+      'Content-Type': 'text/plain; charset=utf-8',
+      'Cache-Control': 'public, max-age=3600',
+    },
+  });
+};

src/pages/zh/about.astro

@@ -0,0 +1,40 @@
+---
+import BaseLayout from '../../layouts/BaseLayout.astro';
+import AuthorCard from '../../components/AuthorCard.astro';
+import { SITE } from '../../config';
+---
+
+<BaseLayout
+  title="关于 — Mr Hoelee"
+  description={`关于 ${SITE.author}（${SITE.handle}）。`}
+  lang="zh"
+  switchHref="/about/"
+  altLocaleUrl={`${SITE.url}/about/`}
+>
+  <h1>关于</h1>
+  <p>
+    我是 {SITE.author}（{SITE.handle}），一名base在马来西亚的全栈开发者兼 DevOps
+    工程师。我做 Web 应用——PHP/CodeIgniter、Java/Spring、JavaScript/TypeScript/React——
+    并自托管一个约 140 个容器的 homelab（Docker、Traefik、nginx、Cloudflare tunnel）。
+    我运营 Hoelee Enterprise，一家面向马来西亚中小企业的网站设计开发公司
+    （邮箱托管只是副业，并非主业）。
+  </p>
+  <p>
+    这个博客就是我的动态作品集：我把自己构建的东西记录下来，从自托管 CI/CD、
+    Docker 编排，到 Web3 实验与 AI 自动化。无论你是招聘方、客户，还是同路的
+    开发者，这里的文章都是我能做什么最诚实的呈现。
+  </p>
+
+  <AuthorCard bio="base在马来西亚的全栈开发者兼 DevOps 工程师。接受远程／混合办公机会。" />
+
+  <h2>联系方式</h2>
+  <p>
+    <a href={`mailto:${SITE.email}`}>{SITE.email}</a>
+    <span class="sep">·</span>
+    <a href={SITE.linkedin} target="_blank" rel="noopener">LinkedIn</a>
+    <span class="sep">·</span>
+    <a href={SITE.gitea} target="_blank" rel="noopener">git.hoelee.com</a>
+    <span class="sep">·</span>
+    <a href={SITE.website} target="_blank" rel="noopener">www.hoelee.com</a>
+  </p>
+</BaseLayout>

src/pages/zh/categories/[category].astro

@@ -1,5 +1,6 @@
 ---
 import BaseLayout from '../../../layouts/BaseLayout.astro';
+import { SITE } from '../../../config';
 import PostList from '../../../components/PostList.astro';
 import CategoryArt from '../../../components/CategoryArt.astro';
 import { getCollection } from 'astro:content';
@@ -29,6 +30,7 @@ const blurb = meta?.blurb.zh;
   description={blurb ?? `「${category}」分类下的文章。`}
   lang="zh"
   switchHref={`/categories/${category}/`}
+  altLocaleUrl={`${SITE.url}/categories/${category}/`}
 >
   <h1>{name}</h1>
   {blurb && <p class="lede">{blurb}</p>}

src/pages/zh/categories/index.astro

@@ -3,6 +3,7 @@ import BaseLayout from '../../../layouts/BaseLayout.astro';
 import CategoryGrid from '../../../components/CategoryGrid.astro';
 import { getCollection } from 'astro:content';
 import { isZh } from '../../../lib/lang';
+import { SITE } from '../../../config';
 
 const posts = await getCollection('posts', isZh);
 
@@ -18,6 +19,7 @@ for (const p of posts) {
   description={`按分类浏览 ${posts.length} 篇中文技术文章：案例研究、DevOps、AI、工程开发、教程与随记。`}
   lang="zh"
   switchHref="/categories/"
+  altLocaleUrl={`${SITE.url}/categories/`}
 >
   <div class="page-head">
     <h1>分类</h1>

src/pages/zh/index.astro

@@ -13,6 +13,7 @@ const posts = sortByUpdated(await getCollection('posts', isZh));
   title={`${SITE.handle} — 技术博客`}
   description="Hoelee 的技术博客中文版：工程、DevOps、自托管、AI 自动化与 Web3 实验。"
   lang="zh"
+  altLocaleUrl={`${SITE.url}/`}
 >
   <section>
     <h1>你好，我是 {SITE.author}。</h1>