feat: Implement CI workflow for content validation and build process; add validation script for blog content integrity

Author: mingcheng

.github/workflows/ci.yml

@@ -0,0 +1,45 @@
+name: CI
+
+on:
+  pull_request:
+    branches: [main, develop]
+  push:
+    branches: [main, develop]
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    name: Validate
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: latest
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          cache: pnpm
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Validate blog content
+        run: node scripts/validate-content.mjs
+
+      - name: TypeScript type check
+        run: pnpm typecheck
+
+      - name: Build website
+        env:
+          DOCUSAURUS_ON_BROKEN_LINKS: throw
+        run: pnpm build

.github/workflows/deploy.yml

@@ -39,6 +39,12 @@ jobs:
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
 
+      - name: Validate blog content
+        run: node scripts/validate-content.mjs
+
+      - name: TypeScript type check
+        run: pnpm typecheck
+
       - name: Build website
         run: pnpm build
 

docusaurus.config.ts

@@ -20,7 +20,8 @@ const config: Config = {
   organizationName: "inclusionAI",
   projectName: "inclusionai.github.io",
 
-  onBrokenLinks: "warn",
+  onBrokenLinks: "throw",
+  onBrokenMarkdownLinks: "throw",
 
   i18n: {
     defaultLocale: "en",

package.json

@@ -12,7 +12,8 @@
     "serve": "docusaurus serve",
     "write-translations": "docusaurus write-translations",
     "write-heading-ids": "docusaurus write-heading-ids",
-    "typecheck": "tsc"
+    "typecheck": "tsc",
+    "validate": "node scripts/validate-content.mjs"
   },
   "dependencies": {
     "@docusaurus/core": "3.9.2",

scripts/validate-content.mjs

@@ -0,0 +1,88 @@
+// ---------------------------------------------------------------------------
+// Blog content validation script
+// Checks every blog post for required frontmatter fields and data integrity.
+// Run: node scripts/validate-content.mjs
+// ---------------------------------------------------------------------------
+import fs from "node:fs";
+import path from "node:path";
+import matter from "gray-matter";
+
+const BLOG_DIR = path.join(process.cwd(), "blog");
+const REQUIRED_FIELDS = ["title", "date", "authors"];
+
+let errors = 0;
+let checked = 0;
+
+// --- Blog frontmatter validation ---
+const dirs = fs
+  .readdirSync(BLOG_DIR, { withFileTypes: true })
+  .filter((d) => d.isDirectory());
+
+for (const dir of dirs) {
+  const base = path.join(BLOG_DIR, dir.name);
+  const file = ["index.mdx", "index.md"]
+    .map((n) => path.join(base, n))
+    .find((f) => fs.existsSync(f));
+
+  if (!file) {
+    console.error(`ERROR  blog/${dir.name}/ — missing index.mdx or index.md`);
+    errors++;
+    continue;
+  }
+
+  checked++;
+  const raw = fs.readFileSync(file, "utf-8");
+  let fm;
+  try {
+    fm = matter(raw).data;
+  } catch (e) {
+    console.error(`ERROR  blog/${dir.name}/ — invalid frontmatter: ${e.message}`);
+    errors++;
+    continue;
+  }
+
+  for (const field of REQUIRED_FIELDS) {
+    if (fm.draft === true) continue; // skip draft posts
+    if (!fm[field]) {
+      console.error(`ERROR  blog/${dir.name}/ — missing required field "${field}"`);
+      errors++;
+    }
+  }
+
+  // Validate date is parseable
+  if (fm.date && isNaN(new Date(fm.date).getTime())) {
+    console.error(`ERROR  blog/${dir.name}/ — invalid date "${fm.date}"`);
+    errors++;
+  }
+
+  // Title should not be empty
+  if (fm.title && fm.title.trim().length === 0) {
+    console.error(`ERROR  blog/${dir.name}/ — title is empty`);
+    errors++;
+  }
+}
+
+// --- Data file import validation ---
+const DATA_DIR = path.join(process.cwd(), "src", "data");
+const dataFiles = fs
+  .readdirSync(DATA_DIR)
+  .filter((f) => f.endsWith(".ts"));
+
+for (const file of dataFiles) {
+  const filePath = path.join(DATA_DIR, file);
+  const content = fs.readFileSync(filePath, "utf-8");
+
+  // Check for empty export arrays (likely a mistake)
+  const emptyArrayMatch = content.match(/export const \w+:\s*\w+\[\]\s*=\s*\[\s*\]/);
+  if (emptyArrayMatch) {
+    console.error(`WARN   src/data/${file} — contains empty exported array`);
+  }
+}
+
+console.log(`\nValidated ${checked} blog posts, found ${errors} error(s).`);
+
+if (errors > 0) {
+  process.exit(1);
+}
+
+console.log("All content checks passed.");

src/pages/model.tsx

@@ -1,5 +1,5 @@
 import React, { useState, useMemo } from "react";
-import type { ReactNode } from "react";
+import type { ReactNode, Key } from "react";
 import Layout from "@theme/Layout";
 import Link from "@docusaurus/Link";
 import clsx from "clsx";
@@ -18,7 +18,7 @@ function categoryClass(cat: ModelCategory): string {
   return styles.catMultiModal;
 }
 
-function ModelCard({ item }: { item: ModelItem }) {
+function ModelCard({ item }: { key?: Key; item: ModelItem }) {
   return (
     <Link to={`/blog/${item.blogSlug}`} className={styles.card}>
       <div className={styles.cardHeader}>

src/pages/system.tsx

@@ -1,5 +1,5 @@
 import React, { useState, useMemo } from "react";
-import type { ReactNode } from "react";
+import type { ReactNode, Key } from "react";
 import Layout from "@theme/Layout";
 import Link from "@docusaurus/Link";
 import clsx from "clsx";
@@ -22,7 +22,7 @@ function categoryClass(cat: SystemCategory): string {
   return styles.catBenchmarks;
 }
 
-function SystemCard({ item }: { item: SystemItem }) {
+function SystemCard({ item }: { key?: Key; item: SystemItem }) {
   return (
     <Link to={`/blog/${item.blogSlug}`} className={styles.card}>
       <div className={styles.cardHeader}>