added support for robots.txt and llm.txt so bots and ai agents can fetch the subdomain

2026-08-22 10:25:03 +01:00
parent c25947e994
commit cad896b770
2 changed files with 103 additions and 2 deletions
@@ -71,6 +71,81 @@ app.use(express.json());
 app.use(express.urlencoded({ extended: false }));
 app.get('/', (req, res) => res.sendFile(path.join(__dirname, '..', 'client.html')));

+// robots.txt with Cloudflare's Content Signals Policy — explicitly allows
+// search indexing, AI input (RAG/grounding/real-time retrieval), and AI
+// training. Previously there was no route for this at all, so Express fell
+// through to its default 404 handler for every request to /robots.txt.
+app.get('/robots.txt', (req, res) => {
+  res.type('text/plain');
+  res.send(
+`# As a condition of accessing this website, you agree to abide by the following
+# content signals:
+
+# (a)  If a content-signal = yes, you may collect content for the corresponding
+#      use.
+# (b)  If a content-signal = no, you may not collect content for the
+#      corresponding use.
+# (c)  If the website operator does not include a content signal for a
+#      corresponding use, the website operator neither grants nor restricts
+#      permission via content signal with respect to the corresponding use.
+
+# The content signals and their meanings are:
+
+# search:   building a search index and providing search results (e.g., returning
+#           hyperlinks and short excerpts from your website's contents). Search does not
+#           include providing AI-generated search summaries.
+# ai-input: inputting content into one or more AI models (e.g., retrieval
+#           augmented generation, grounding, or other real-time taking of content for
+#           generative AI search answers).
+# ai-train: training or fine-tuning AI models.
+
+# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
+# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
+# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
+
+User-Agent: *
+Content-Signal: search=yes, ai-input=yes, ai-train=yes
+Allow: /
+`
+  );
+});
+
+// llms.txt — a concise, Markdown summary purpose-built for AI agents/LLMs to
+// understand and describe the site (distinct from robots.txt, which only
+// controls access/usage permissions, not comprehension).
+app.get('/llms.txt', (req, res) => {
+  res.type('text/plain');
+  res.send(
+`# UNLOZE Webclient
+
+> A free, browser-based streaming client for Counter-Strike Source (CSS).
+> No Steam account, no download, and no installation required — the game
+> runs server-side and streams to your browser via WebRTC.
+
+## What this is
+
+UNLOZE Webclient lets anyone play Counter-Strike Source directly in a web
+browser, streamed from a server-hosted instance of the game. This is aimed
+at players who don't own CSS on Steam or don't want to install it locally.
+
+Only one visitor controls the game at a time (via a queue system); others
+can watch the live stream while waiting their turn.
+
+## Available game modes
+
+- Zombie Escape — ze.unloze.com:27015
+- Zombie Escape 2 — ze.unloze.com:27035
+- Minigames — mg.unloze.com:27017
+- Zombie Riot — zr.unloze.com:27016
+
+## Related links
+
+- Main community site: https://unloze.com
+- Counter-Strike Source on Steam: https://store.steampowered.com/app/240/CounterStrike_Source/
+`
+  );
+});
+
 // ── Internal-request gate ─────────────────────────────────────────────────────
 // Used by /webclient-name (POST), /webclient-current-ip (GET), and
 // /webclient-force-restart (POST) — all internal-only endpoints intended for