import { defineConfig } from 'astro/config';
import mdx from '@astrojs/mdx';
import sitemap from '@astrojs/sitemap';

// Canonical origin. Drives canonical URLs, OG tags, and the sitemap.
const SITE = process.env.PUBLIC_SITE_URL ?? 'https://adr.smlcompany.ca';

export default defineConfig({
  site: SITE,

  // Static output is the point of this rebuild — see docs/04-seo-spec.md.
  // Do not switch to a server adapter without an AGENTS.md Change Log entry.
  output: 'static',

  // Directory-style URLs with a trailing slash, matched by the CloudFront
  // trailing-slash function. See docs/06-deployment.md.
  trailingSlash: 'always',
  build: { format: 'directory', inlineStylesheets: 'auto' },

  // Astro 7 changed this default from `true` to `'jsx'`. Measured, not assumed
  // (AGENTS.md entry (t)): in an .astro template, an inline pair split across
  // two lines renders as `<em>inline</em><strong>pair</strong>` under 'jsx' and
  // `<em>inline</em> <strong>pair</strong>` under `true`. The space is silently
  // deleted — no error, no warning; you find out by reading the page.
  //
  // MDX prose is NOT affected either way; the hazard is .astro markup only.
  // Held at the HTML-aware behaviour because hand-written templates on a
  // text-heavy site are exactly where a wrapped line meets an inline tag.
  // Revisit only with a measurement, not a preference. See R12.
  compressHTML: true,

  integrations: [
    mdx(),
    sitemap({
      // NOINDEX PAGES ARE EXCLUDED, and the list is now three shapes rather
      // than one. `/legal/*` is noindex by spec (docs/04). The two added at
      // build step 8 are the intake form's POST-redirect-GET landing pages:
      // both are transactional, neither has standalone value, and a search
      // result reading "your inquiry has been received" for someone who has not
      // sent one is worse than no result at all.
      //
      // ⚠️ `/insights/` IS DELIBERATELY NOT HERE even though it emits
      // `noindex` while no article is published. This filter cannot see
      // collection data — it runs from build config, with no access to
      // `getCollection` — so the exclusion could only be a guess at the
      // collection's state, and it would then be wrong in the direction that
      // matters the moment an article publishes. The page derives its own
      // `noindex` from the collection on every build, so the mismatch is
      // temporary, self-clearing, and reported accurately by Search Console as
      // excluded-by-noindex. Recorded rather than fixed with a frontmatter
      // parser in build config.
      //
      // The `/type-scale/` half of this condition is gone with the page it
      // named: the step-1 proof sheet was deleted at step 2, as its own comment
      // and InfinityMark's both said it would be. Recoverable from git if the
      // specimen is ever wanted again; it is not a route the site ships.
      filter: (page) =>
        !page.includes('/legal/') &&
        !page.includes('/contact/received/') &&
        !page.includes('/contact/could-not-send/') &&
        // `/bio/` is a condensed duplicate of `/about/` and `/fees/`, and it
        // exists to be rendered to a PDF (R16). Two URLs competing on the same
        // content is the thing `docs/04` is most concerned with, so it is
        // `noindex` and out of the sitemap.
        !page.includes('/bio/'),
      changefreq: 'monthly',
      // No `lastmod`. It was `new Date()`, which stamped every URL with the
      // build time — telling crawlers all 17 pages changed whenever one did.
      // Google discounts lastmod it judges unreliable, so that spent the signal
      // docs/04-seo-spec.md wants rather than sending it. Step 7 can reinstate
      // it per-entry from an article's `updatedDate` via `serialize`.
    }),
  ],

  // No `image` block: `astro/assets/services/sharp` is already Astro's default
  // service, so setting it was dead configuration. The conventions it used to
  // sit under — explicit width/height on every image, never base64-inline —
  // live in CLAUDE.md, which is where they are actually enforced (by review).

  // No `prefetch` block at all — removed 2026-08-26, see AGENTS.md entry (r).
  // Any prefetch setting ships Astro's prefetch script to every page, against
  // CLAUDE.md's "default to zero JS", for a marginal gain on a small static site
  // already served from CloudFront. Revisit only against real Lighthouse numbers.
});