@docslurp/contrib-astro 0.0.0-stage → 0.3.0

package/DocSlurpSearch.astro

@@ -0,0 +1,15 @@
+---
+/**
+ * Browser key only: restrict it to this site's origin and the search scope.
+ * workspaceId takes a slug, UUID or "default" (the key organization's default
+ * workspace) and defaults to "default"; apiUrl defaults to https://docslurp.io.
+ */
+interface Props { clientKey: string; workspaceId?: string; apiUrl?: string; placeholder?: string; }
+const { clientKey, workspaceId = 'default', apiUrl = 'https://docslurp.io', placeholder = 'Search documents…' } = Astro.props;
+---
+<docslurp-search-box api-url={apiUrl} workspace-id={workspaceId} client-key={clientKey} placeholder={placeholder}></docslurp-search-box>
+<noscript><p>Enable JavaScript to search the document collection.</p></noscript>
+<script>
+  import { defineDocSlurpSearch } from '@docslurp/sdk/widget';
+  defineDocSlurpSearch();
+</script>

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025-2026 DocSlurp, Inc. and contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/LICENSES/Apache-2.0.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Support. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 DocSlurp, Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/NOTICE

@@ -0,0 +1,12 @@
+DocSlurp
+Copyright 2025-2026 DocSlurp, Inc. and contributors
+
+Earlier versions were distributed under the Apache License, Version 2.0.
+Existing license grants remain in effect for those versions. Retain applicable
+upstream copyright, patent, license and attribution notices when redistributing
+code from those versions. The accompanying Apache-2.0 text preserves the
+previous repository notice and supplies the future license for SSPL versions.
+
+Third-party components retain their own licenses. DocSlurp's license does not
+relicense dependencies, models, fonts, assets or separately licensed files.
+See THIRD_PARTY_NOTICES.md in the repository for the compatibility review.

package/README.md

@@ -1,3 +1,65 @@
-# Temporary Holding Version
+# @docslurp/contrib-astro
 
-This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
+[Package docs](https://docslurp.io/docs/packages/contrib-astro) · [GitHub](https://github.com/DocSlurp/docslurp-oss/tree/main/packages/contrib-astro) · [npm](https://www.npmjs.com/package/@docslurp/contrib-astro)
+
+Add cited DocSlurp search to an Astro site with one component. It renders a small framework-free widget, so it needs no React hydration.
+
+```astro
+---
+import DocSlurpSearch from "@docslurp/contrib-astro";
+---
+<!-- PUBLIC_DOCSLURP_CLIENT_KEY holds a browser key, safe to ship in page HTML. -->
+<DocSlurpSearch clientKey={import.meta.env.PUBLIC_DOCSLURP_CLIENT_KEY} />
+<!-- To search a named workspace: <DocSlurpSearch clientKey={...} workspaceId="product-manuals" /> -->
+```
+
+| Prop | Default | Notes |
+| --- | --- | --- |
+| `clientKey` | Required | A browser key: search-only and restricted to your allowed websites. Server keys are refused in the browser. |
+| `workspaceId` | `default` | A workspace slug (such as `product-manuals`), UUID or `default`, the key organization's default workspace. See [Workspaces](https://docslurp.io/docs/http#workspaces). |
+| `apiUrl` | `https://docslurp.io` | The service origin. |
+| `placeholder` | `Search documents…` | Search box placeholder. |
+
+Use a browser key for public content. The same component is also exported as `@docslurp/sdk/astro`. For setup steps, see the [Astro guide](https://docslurp.io/docs/search-integrations/astro).
+
+## Index your rendered Astro docs at build time
+
+`@docslurp/contrib-astro/build` is an optional build integration for sites that use the **Astro Node standalone adapter**. After the build, it:
+
+1. Renders the routes you list on a temporary local server.
+2. Keeps each page's `<main>` content, including headings and code, and drops scripts, styles, navigation, asides and search controls.
+3. Uploads the pages to DocSlurp, using each canonical page URL so a rebuild replaces the previous version instead of adding a duplicate. A content-based idempotency key makes retrying an identical submission safe.
+4. Waits up to ten minutes for the run to finish.
+
+Your server key is used only during the build. It never ends up in the generated files or public configuration.
+
+```js
+// astro.config.mjs (output: 'server' with the @astrojs/node standalone adapter)
+import docslurpDocsIndex from '@docslurp/contrib-astro/build';
+
+integrations: [docslurpDocsIndex({
+  routes: ['/docs', '/docs/getting-started'], // List every public page to index.
+  site: 'https://docs.example.com',           // Origin used for canonical page URLs.
+  apiUrl: 'https://docslurp.io',
+  apiKey: process.env.DOCSLURP_API_KEY,       // Server key with the ingest scope.
+  workspaceName: 'Product documentation',
+  // To add to an existing workspace instead: workspaceId: 'existing-workspace-slug',
+})]
+```
+
+Without `apiKey`, the build still writes `.docslurp/docs-index.json` and skips the upload. With a key, any indexing failure fails the build. A successful upload writes `docslurp-docs-search.json` to the client output with the workspace ID, so your search component can find it. Use `renderEnv` to pass environment variables that only the page renderer needs.
+
+Pages are indexed as text: the upload asks for `{ visionFallback: false, preserveImages: false, summarize: true }`, so rendered HTML skips page images and vision and gets per-page summaries. Pass `pipeline` with other pipeline overrides to change that.
+
+To index a site after it deploys (for example when the build has no API key), crawl the live pages instead:
+
+```bash
+DOCSLURP_API_KEY=... DOCSLURP_DOCS_WORKSPACE_ID=<workspace id> \
+  node node_modules/@docslurp/contrib-astro/index-docs.mjs --site https://docs.example.com --routes routes.json --output .docslurp/docs-index.json
+```
+
+`--routes` is a file or URL with a JSON array of paths. Only those paths on the site's own origin are fetched, and redirects are refused. Elements marked `data-search-exclude` (repeated boilerplate) are left out of the index.
+
+This integration does not render protected pages, discover dynamic routes, delete documents for removed pages, or support other Astro adapters, so list your public documentation routes explicitly. Keep public documentation in its own organization, and use keys from that organization for both indexing and search.
+
+For how DocSlurp indexes its own website, see [Dogfood docs search](https://github.com/DocSlurp/docslurp-oss/blob/main/docs/docs-search.md).

package/build.mjs

@@ -0,0 +1,27 @@
+import { spawn } from 'node:child_process';
+import { fileURLToPath } from 'node:url';
+
+/** Index rendered Astro Node standalone pages through DocSlurp's public API. */
+export default function docslurpDocsIndex({ routes, apiKey, apiUrl = 'https://docslurp.io', workspaceId, workspaceName = 'DocSlurp documentation', site = 'https://docslurp.io', renderEnv = {}, pipeline }) {
+  let root;
+  return {
+    name: '@docslurp/contrib-astro/docs-index',
+    hooks: {
+      'astro:config:done': ({ config }) => { root = config.root; },
+      'astro:build:done': async ({ dir, logger }) => {
+        const entry = new URL('../server/entry.mjs', dir);
+        const output = new URL('.docslurp/docs-index.json', root);
+        // Isolate server imports and startup state from Astro's build process.
+        await new Promise((resolve, reject) => {
+          const child = spawn(process.execPath, [fileURLToPath(new URL('./index-docs.mjs', import.meta.url)), '--entry', fileURLToPath(entry), '--output', fileURLToPath(output), '--public-config', fileURLToPath(new URL('docslurp-docs-search.json', dir))], {
+            cwd: fileURLToPath(root), stdio: 'inherit',
+            env: { ...process.env, ...renderEnv, ASTRO_NODE_AUTOSTART: 'disabled', DOCSLURP_API_KEY: apiKey ?? '', DOCSLURP_DOCS_INDEX_OPTIONS: JSON.stringify({ routes, apiUrl, workspaceId, workspaceName, site, ...(pipeline ? { pipeline } : {}) }) },
+          });
+          child.on('error', reject);
+          child.on('exit', code => code === 0 ? resolve() : reject(new Error(`DocSlurp docs indexing exited with ${code}`)));
+        });
+        logger.info(apiKey ? 'Docs submitted to DocSlurp; indexing completed.' : 'Docs corpus built. No DOCSLURP_API_KEY: remote indexing skipped.');
+      },
+    },
+  };
+}

package/index-docs.mjs

@@ -0,0 +1,148 @@
+import { createServer } from 'node:http';
+import { createHash } from 'node:crypto';
+import { mkdir, readFile, writeFile } from 'node:fs/promises';
+import { dirname } from 'node:path';
+import { pathToFileURL } from 'node:url';
+
+export function docFilename(path) { return `docslurp-docs-${Buffer.from(path).toString('base64url')}.html`; }
+/**
+ * Cloudflare Email Obfuscation rewrites addresses with a random key on every
+ * request, so a crawled page differed each time (forcing a re-index) and the
+ * index held "[email protected]". Decode them back to the address.
+ */
+export function decodeCloudflareEmails(html) {
+  const decode = (hex) => {
+    if (!/^(?:[0-9a-f]{2})+$/i.test(hex)) return null;
+    const key = parseInt(hex.slice(0, 2), 16);
+    let out = '';
+    for (let i = 2; i < hex.length; i += 2) out += String.fromCharCode(parseInt(hex.slice(i, i + 2), 16) ^ key);
+    return out.replace(/[<>&"]/g, (c) => ({ '<': '&lt;', '>': '&gt;', '&': '&amp;', '"': '&quot;' })[c]);
+  };
+  return html
+    .replace(/<a\b[^>]*\bdata-cfemail="([0-9a-f]+)"[^>]*>[\s\S]*?<\/a>/gi, (match, hex) => decode(hex) ?? match)
+    .replace(/<span\b[^>]*\bdata-cfemail="([0-9a-f]+)"[^>]*>[\s\S]*?<\/span>/gi, (match, hex) => decode(hex) ?? match)
+    .replace(/href="\/cdn-cgi\/l\/email-protection#([0-9a-f]+)"/gi, (match, hex) => { const email = decode(hex); return email ? `href="mailto:${email}"` : match; });
+}
+
+export function extractDoc(html) {
+  html = decodeCloudflareEmails(html);
+  const main = html.match(/<main\b[^>]*>([\s\S]*?)<\/main>/i)?.[1];
+  if (!main) throw new Error('Docs page has no main content');
+  // `data-search-exclude` marks boilerplate repeated across pages (step numbers, agent handoffs).
+  const content = main.replace(/<(script|style|nav|aside)\b[^>]*>[\s\S]*?<\/\1>/gi, '').replace(/<([a-z][a-z0-9-]*)\b[^>]*\bdata-search-exclude\b[^>]*>[\s\S]*?<\/\1>/gi, '').replace(/<docslurp-docs-search\b[^>]*>[\s\S]*?<\/docslurp-docs-search>/gi, '');
+  const title = html.match(/<title[^>]*>([\s\S]*?)<\/title>/i)?.[1] ?? 'Documentation';
+  return { title, html: `<!doctype html><html><head><meta charset="utf-8"><title>${title}</title></head><body><main>${content}</main></body></html>` };
+}
+
+const DOCS_ROUTE = /^\/docs(?:\/[a-z0-9-]+)*$/;
+
+/**
+ * Crawl a deployed site's docs routes (for indexing after a deploy, when the
+ * build had no API key). Only the given routes on the site's own origin are
+ * fetched; redirects are refused so a page can't pull in another host.
+ */
+export async function crawlDocs({ site, routes }, fetchImpl = fetch) {
+  const origin = new URL(site).origin;
+  const corpus = [];
+  for (const path of [...new Set(routes)].sort()) {
+    if (!DOCS_ROUTE.test(path)) throw new Error(`Invalid docs route: ${path}`);
+    const response = await fetchImpl(`${origin}${path}`, { redirect: 'manual', headers: { Accept: 'text/html' }, signal: AbortSignal.timeout(30_000) });
+    if (response.status !== 200) throw new Error(`Fetch ${path}: HTTP ${response.status}`);
+    corpus.push({ path, filename: docFilename(path), canonicalId: `${origin}${path}`, ...extractDoc(await response.text()) });
+  }
+  return corpus;
+}
+
+/**
+ * Rendered HTML docs need text, not page images or vision rescue: faster,
+ * cheaper, fewer moving parts. Per-page summaries help search and chat.
+ */
+export const DEFAULT_DOCS_PIPELINE = Object.freeze({ visionFallback: false, preserveImages: false, summarize: true });
+
+export async function indexDocs(corpus, { apiUrl, workspaceId, workspaceName, pipeline = DEFAULT_DOCS_PIPELINE }, apiKey, fetchImpl = fetch) {
+  const base = apiUrl.replace(/\/$/, '');
+  const request = async (path, init = {}) => {
+    const response = await fetchImpl(`${base}${path}`, { ...init, headers: { ...init.headers, Authorization: `Bearer ${apiKey}` }, signal: AbortSignal.timeout(60_000) });
+    if (!response.ok) throw new Error(`DocSlurp ${path}: HTTP ${response.status}`);
+    return response.json();
+  };
+  let target = workspaceId;
+  if (!target) {
+    const { workspaces } = await request('/v1/workspaces');
+    const matches = workspaces.filter(w => w.name === workspaceName);
+    if (matches.length > 1) throw new Error('Multiple docs workspaces: set DOCSLURP_DOCS_WORKSPACE_ID');
+    target = matches[0]?.id;
+  }
+  const form = new FormData();
+  const canonicalIds = [];
+  for (const doc of corpus) {
+    form.append('files', new Blob([doc.html], { type: 'text/html' }), doc.filename);
+    canonicalIds.push(doc.canonicalId);
+  }
+  form.set('canonicalIds', JSON.stringify(canonicalIds));
+  if (pipeline) form.set('pipeline', JSON.stringify(pipeline));
+  if (target) form.set('workspaceId', target);
+  else { form.set('newWorkspace', 'true'); form.set('workspaceName', workspaceName); }
+  const hash = createHash('sha256').update(JSON.stringify({ target: target ?? workspaceName, corpus, pipeline: pipeline ?? null })).digest('hex');
+  const result = await request('/v1/ingest/bulk', { method: 'POST', headers: { 'Idempotency-Key': `docs-${hash}` }, body: form });
+  const deadline = Date.now() + 10 * 60_000;
+  while (Date.now() < deadline) {
+    const { run } = await request(`/v1/runs/${encodeURIComponent(result.run.id)}/progress`);
+    if (run.status === 'completed') return { workspaceId: result.workspace.id, runId: run.id };
+    if (['failed', 'cancelled'].includes(run.status)) throw new Error(`Docs ingestion ${run.status}`);
+    await new Promise(resolve => setTimeout(resolve, 2000));
+  }
+  throw new Error('Docs indexing timed out after 10 minutes; inspect the run before retrying');
+}
+
+async function main() {
+  const args = process.argv.slice(2);
+  const value = name => args[args.indexOf(name) + 1];
+  const options = { apiUrl: process.env.DOCSLURP_URL ?? 'https://docslurp.io', workspaceId: process.env.DOCSLURP_DOCS_WORKSPACE_ID || process.env.PUBLIC_DOCSLURP_DOCS_WORKSPACE_ID || undefined, workspaceName: 'DocSlurp documentation', ...(process.env.DOCSLURP_DOCS_PIPELINE ? { pipeline: JSON.parse(process.env.DOCSLURP_DOCS_PIPELINE) } : {}), ...JSON.parse(process.env.DOCSLURP_DOCS_INDEX_OPTIONS ?? '{}') };
+  const output = value('--output');
+  let corpus;
+  if (args.includes('--entry')) {
+    const { handler } = await import(pathToFileURL(value('--entry')).href);
+    const server = createServer(handler);
+    await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
+    try {
+      corpus = [];
+      for (const path of [...new Set(options.routes)].sort()) {
+        if (!DOCS_ROUTE.test(path)) throw new Error(`Invalid docs route: ${path}`);
+        const response = await fetch(`http://127.0.0.1:${server.address().port}${path}`, { headers: { Host: new URL(options.site).host, 'X-Forwarded-Host': new URL(options.site).host, 'X-Forwarded-Proto': 'https' }, signal: AbortSignal.timeout(30_000) });
+        if (!response.ok) throw new Error(`Render ${path}: HTTP ${response.status}`);
+        corpus.push({ path, filename: docFilename(path), canonicalId: `${options.site}${path}`, ...extractDoc(await response.text()) });
+      }
+    } finally {
+      server.closeAllConnections();
+      await new Promise(resolve => server.close(resolve));
+    }
+    await mkdir(dirname(output), { recursive: true });
+    await writeFile(output, JSON.stringify(corpus, null, 2));
+    console.log(`[docs-index] Rendered ${corpus.length} pages`);
+  } else if (args.includes('--site')) {
+    // Deployed site: routes from --routes (URL or file with a JSON array), else the options.
+    const source = args.includes('--routes') ? value('--routes') : null;
+    const routes = source
+      ? JSON.parse(/^https?:/.test(source) ? await (await fetch(source, { signal: AbortSignal.timeout(30_000) })).text() : await readFile(source, 'utf8'))
+      : options.routes;
+    if (!Array.isArray(routes) || !routes.length) throw new Error('No docs routes to crawl');
+    corpus = await crawlDocs({ site: value('--site'), routes });
+    if (output) { await mkdir(dirname(output), { recursive: true }); await writeFile(output, JSON.stringify(corpus, null, 2)); }
+    console.log(`[docs-index] Crawled ${corpus.length} pages from ${new URL(value('--site')).origin}`);
+  } else corpus = JSON.parse(await readFile(output, 'utf8'));
+  if (!corpus.length) throw new Error('Empty docs corpus');
+  const key = process.env.DOCSLURP_API_KEY?.trim();
+  if (key) {
+    const indexed = await indexDocs(corpus, options, key);
+    console.log('[docs-index]', indexed);
+    if (args.includes('--public-config')) await writeFile(value('--public-config'), JSON.stringify({ workspaceId: indexed.workspaceId }));
+  }
+  else {
+    console.log('[docs-index] No API key; remote indexing skipped');
+    if (args.includes('--public-config')) await writeFile(value('--public-config'), JSON.stringify({ workspaceId: options.workspaceId ?? null }));
+  }
+}
+if (process.argv[1] && import.meta.url === pathToFileURL(process.argv[1]).href) {
+  main().then(() => process.exit(0)).catch(error => { console.error(error.message); process.exit(1); });
+}

package/package.json

@@ -1,6 +1,40 @@
 {
   "name": "@docslurp/contrib-astro",
-  "version": "0.0.0-stage",
-  "stub": true,
-  "description": "Temporary package placeholder for staged publishing"
+  "version": "0.3.0",
+  "description": "Astro search component for DocSlurp cited search, with a framework-free browser widget.",
+  "license": "MIT",
+  "homepage": "https://docslurp.io/docs/packages/contrib-astro",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/DocSlurp/docslurp-oss.git",
+    "directory": "packages/contrib-astro"
+  },
+  "bugs": {
+    "url": "https://github.com/DocSlurp/docslurp-oss/issues"
+  },
+  "type": "module",
+  "exports": {
+    ".": "./DocSlurpSearch.astro",
+    "./build": "./build.mjs"
+  },
+  "files": [
+    "DocSlurpSearch.astro",
+    "README.md",
+    "LICENSE",
+    "NOTICE",
+    "LICENSES",
+    "build.mjs",
+    "index-docs.mjs"
+  ],
+  "dependencies": {
+    "@docslurp/sdk": "^0.3.0"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "scripts": {
+    "build": "pnpm --filter @docslurp/sdk build",
+    "typecheck": "pnpm --filter @docslurp/sdk typecheck",
+    "test": "node --test index-docs.test.mjs"
+  }
 }