From 7f6bbdc82c67fd3e00d9893bcedb6a03490d3c28 Mon Sep 17 00:00:00 2001
From: Erich Blume <blume.erich@gmail.com>
Date: Thu, 16 Apr 2026 15:39:48 -0700
Subject: [PATCH] Add robots.txt to forge.eblu.me blocking crawlers from
 /mirrors/

Facebook has been scraping forge mirror repos at ~3-4 req/s, slowing
down the Forgejo instance. Serve robots.txt directly from nginx to
disallow /mirrors/ while leaving eblume/* accessible to crawlers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 fly/nginx.conf | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fly/nginx.conf b/fly/nginx.conf
index 75cd102..995042e 100644
--- a/fly/nginx.conf
+++ b/fly/nginx.conf
@@ -155,6 +155,12 @@ http {
             internal;
         }
 
+        # Serve robots.txt directly — block crawlers from mirror repos
+        location = /robots.txt {
+            default_type text/plain;
+            return 200 "User-agent: *\nDisallow: /mirrors/\n";
+        }
+
         # Block swagger API docs — use forge.ops.eblu.me from tailnet
         location /swagger {
             return 403 "API documentation is only available at forge.ops.eblu.me (tailnet).\n";