Added manual live Ghost content smoke

.github/workflows/live-ghost-content-smoke.yml

@@ -0,0 +1,30 @@
+name: Live Ghost content smoke
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  smoke:
+    name: Observe live Ghost content
+    if: github.repository == 'TryGhost/algolia' && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6.0.10
+      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
+        with:
+          node-version-file: .nvmrc
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+      - name: Run live content smoke
+        env:
+          GHOST_URL: https://main.ghost.is
+          GHOST_API_VERSION: v6.0
+          MAIN_GHOST_CONTENT_API_KEY: ${{ secrets.MAIN_GHOST_CONTENT_API_KEY }}
+        run: pnpm --filter @tryghost/algolia-html-extractor smoke:live

packages/algolia-html-extractor/README.md

@@ -24,3 +24,19 @@ position, its heading rank, and the source tag. The returned values are read-onl
 The package handles HTML parsing itself and has no configuration options. Turning fragments into
 Algolia records, merging `pre` content, and sending records to Algolia are separate jobs handled by
 the downstream packages.
+
+## Maintainer smoke check
+
+Maintainers can run the `Live Ghost content smoke` workflow by hand to check published posts and
+pages from `main.ghost.is`. It runs only from this repository's `main` branch and writes a
+privacy-safe structural summary to the job. It does not save live content, write a baseline, run on
+pull requests, or publish the package.
+
+The workflow installs the workspace and then runs:
+
+```sh
+pnpm --filter @tryghost/algolia-html-extractor smoke:live
+```
+
+This command expects the workflow's URL, API version, Content API key, and job-summary environment.
+It is not a general-purpose extractor command.

packages/algolia-html-extractor/package.json

@@ -26,6 +26,7 @@
     "lint": "oxlint --quiet . && oxfmt --check .",
     "posttest": "pnpm typecheck && pnpm lint",
     "build": "tsc --project tsconfig.build.json",
+    "smoke:live": "node smoke/cli.mts",
     "prepack": "pnpm build"
   },
   "files": [

packages/algolia-html-extractor/smoke/cli.mts

@@ -0,0 +1,70 @@
+import {appendFile} from 'node:fs/promises';
+
+import {
+    SmokeError,
+    runLiveGhostContentSmoke,
+    type SmokeTransport,
+    type SmokeTransportRequest
+} from './live-ghost-content-smoke.mts';
+
+const REQUEST_TIMEOUT_MS = 30_000;
+
+const createRequestUrl = (request: SmokeTransportRequest): URL => {
+    const requestUrl = new URL(`/ghost/api/content/${request.contentType}/`, request.target);
+    requestUrl.searchParams.set('key', request.contentApiKey);
+    requestUrl.searchParams.set('fields', request.fields);
+    requestUrl.searchParams.set('formats', request.formats);
+    requestUrl.searchParams.set('limit', String(request.limit));
+    requestUrl.searchParams.set('page', String(request.page));
+    return requestUrl;
+};
+
+const transport: SmokeTransport = async request => {
+    const response = await fetch(createRequestUrl(request), {
+        method: 'GET',
+        headers: {'Accept-Version': request.apiVersion},
+        redirect: request.redirect,
+        signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS)
+    });
+
+    let body: unknown = null;
+    if (response.status >= 200 && response.status < 300) {
+        try {
+            body = await response.json();
+        } catch {
+            body = null;
+        }
+    }
+
+    return {
+        status: response.status,
+        redirected: response.redirected,
+        body
+    };
+};
+
+const summaryPath = process.env.GITHUB_STEP_SUMMARY;
+if (summaryPath === undefined || summaryPath === '') {
+    process.stderr.write('Live Ghost content smoke failed: operational-failure\n');
+    process.exitCode = 1;
+} else {
+    try {
+        const report = await runLiveGhostContentSmoke({
+            target: process.env.GHOST_URL ?? '',
+            apiVersion: process.env.GHOST_API_VERSION ?? '',
+            contentApiKey: process.env.MAIN_GHOST_CONTENT_API_KEY ?? '',
+            transport,
+            clock: () => new Date(),
+            summarySink: summary => appendFile(summaryPath, summary, 'utf8')
+        });
+
+        process.stdout.write(`Live Ghost content smoke: ${report.category}\n`);
+        if (report.category !== 'ok') {
+            process.exitCode = 1;
+        }
+    } catch (error) {
+        const category = error instanceof SmokeError ? error.category : 'operational-failure';
+        process.stderr.write(`Live Ghost content smoke failed: ${category}\n`);
+        process.exitCode = 1;
+    }
+}