Fix Unix socket HTTPS/HTTP issue in OpenGraph fetching

Co-authored-by: JasonLovesDoggo <66544866+JasonLovesDoggo@users.noreply.github.com>
Initial investigation into Unix socket HTTPS/HTTP issue
2026-04-14 20:48:44 +00:00 · 2025-08-24 03:36:36 +00:00 · 2025-08-24 03:30:41 +00:00 · 2025-08-24 03:17:57 +00:00 · 2025-08-23 23:14:37 -04:00 · 2025-08-24 03:12:08 +00:00
13 changed files with 1118 additions and 15 deletions
--- a/.github/actions/spelling/expect.txt
+++ b/.github/actions/spelling/expect.txt
@@ -1,5 +1,6 @@
 acs
 Aibrew
+alibaba
 alrest
 amazonbot
 anthro
--- a/data/bots/_deny-pathological.yaml
+++ b/data/bots/_deny-pathological.yaml
@@ -2,4 +2,5 @@
 - import: (data)/bots/headless-browsers.yaml
 - import: (data)/bots/us-ai-scraper.yaml
 - import: (data)/bots/custom-async-http-client.yaml
+- import: (data)/crawlers/alibaba-cloud.yaml
 - import: (data)/crawlers/huawei-cloud.yaml
--- a/data/crawlers/alibaba-cloud.yaml
+++ b/data/crawlers/alibaba-cloud.yaml
@@ -0,0 +1,881 @@
+- name: alibaba-cloud
+  action: DENY
+  # Updated 2025-08-20 from IP addresses for AS45102
+  remote_addresses:
+    - 103.81.186.0/23
+    - 110.76.21.0/24
+    - 110.76.23.0/24
+    - 116.251.64.0/18
+    - 139.95.0.0/23
+    - 139.95.10.0/23
+    - 139.95.12.0/23
+    - 139.95.14.0/23
+    - 139.95.16.0/23
+    - 139.95.18.0/23
+    - 139.95.2.0/23
+    - 139.95.4.0/23
+    - 139.95.6.0/23
+    - 139.95.64.0/24
+    - 139.95.8.0/23
+    - 14.1.112.0/22
+    - 14.1.115.0/24
+    - 140.205.1.0/24
+    - 140.205.122.0/24
+    - 147.139.0.0/17
+    - 147.139.0.0/18
+    - 147.139.128.0/17
+    - 147.139.128.0/18
+    - 147.139.155.0/24
+    - 147.139.192.0/18
+    - 147.139.64.0/18
+    - 149.129.0.0/20
+    - 149.129.0.0/21
+    - 149.129.16.0/23
+    - 149.129.192.0/18
+    - 149.129.192.0/19
+    - 149.129.224.0/19
+    - 149.129.32.0/19
+    - 149.129.64.0/18
+    - 149.129.64.0/19
+    - 149.129.8.0/21
+    - 149.129.96.0/19
+    - 156.227.20.0/24
+    - 156.236.12.0/24
+    - 156.236.17.0/24
+    - 156.240.76.0/23
+    - 156.245.1.0/24
+    - 161.117.0.0/16
+    - 161.117.0.0/17
+    - 161.117.126.0/24
+    - 161.117.127.0/24
+    - 161.117.128.0/17
+    - 161.117.128.0/24
+    - 161.117.129.0/24
+    - 161.117.138.0/24
+    - 161.117.143.0/24
+    - 170.33.104.0/24
+    - 170.33.105.0/24
+    - 170.33.106.0/24
+    - 170.33.107.0/24
+    - 170.33.136.0/24
+    - 170.33.137.0/24
+    - 170.33.138.0/24
+    - 170.33.20.0/24
+    - 170.33.21.0/24
+    - 170.33.22.0/24
+    - 170.33.23.0/24
+    - 170.33.24.0/24
+    - 170.33.29.0/24
+    - 170.33.30.0/24
+    - 170.33.31.0/24
+    - 170.33.32.0/24
+    - 170.33.33.0/24
+    - 170.33.34.0/24
+    - 170.33.35.0/24
+    - 170.33.64.0/24
+    - 170.33.65.0/24
+    - 170.33.66.0/24
+    - 170.33.68.0/24
+    - 170.33.69.0/24
+    - 170.33.72.0/24
+    - 170.33.73.0/24
+    - 170.33.76.0/24
+    - 170.33.77.0/24
+    - 170.33.78.0/24
+    - 170.33.79.0/24
+    - 170.33.80.0/24
+    - 170.33.81.0/24
+    - 170.33.82.0/24
+    - 170.33.83.0/24
+    - 170.33.84.0/24
+    - 170.33.85.0/24
+    - 170.33.86.0/24
+    - 170.33.88.0/24
+    - 170.33.90.0/24
+    - 170.33.92.0/24
+    - 170.33.93.0/24
+    - 185.78.106.0/23
+    - 198.11.128.0/18
+    - 198.11.137.0/24
+    - 198.11.184.0/21
+    - 202.144.199.0/24
+    - 203.107.64.0/24
+    - 203.107.65.0/24
+    - 203.107.66.0/24
+    - 203.107.67.0/24
+    - 203.107.68.0/24
+    - 205.204.102.0/23
+    - 205.204.111.0/24
+    - 205.204.117.0/24
+    - 205.204.125.0/24
+    - 205.204.96.0/19
+    - 223.5.5.0/24
+    - 223.6.6.0/24
+    - 2400:3200::/48
+    - 2400:3200:baba::/48
+    - 2400:b200:4100::/48
+    - 2400:b200:4101::/48
+    - 2400:b200:4102::/48
+    - 2400:b200:4103::/48
+    - 2401:8680:4100::/48
+    - 2401:b180:4100::/48
+    - 2404:2280:1000::/36
+    - 2404:2280:1000::/37
+    - 2404:2280:1800::/37
+    - 2404:2280:2000::/36
+    - 2404:2280:2000::/37
+    - 2404:2280:2800::/37
+    - 2404:2280:3000::/36
+    - 2404:2280:3000::/37
+    - 2404:2280:3800::/37
+    - 2404:2280:4000::/36
+    - 2404:2280:4000::/37
+    - 2404:2280:4800::/37
+    - 2408:4000:1000::/48
+    - 2408:4009:500::/48
+    - 240b:4000::/32
+    - 240b:4000::/33
+    - 240b:4000:8000::/33
+    - 240b:4000:fffe::/48
+    - 240b:4001::/32
+    - 240b:4001::/33
+    - 240b:4001:8000::/33
+    - 240b:4002::/32
+    - 240b:4002::/33
+    - 240b:4002:8000::/33
+    - 240b:4004::/32
+    - 240b:4004::/33
+    - 240b:4004:8000::/33
+    - 240b:4005::/32
+    - 240b:4005::/33
+    - 240b:4005:8000::/33
+    - 240b:4006::/48
+    - 240b:4006:1000::/44
+    - 240b:4006:1000::/45
+    - 240b:4006:1000::/47
+    - 240b:4006:1002::/47
+    - 240b:4006:1008::/45
+    - 240b:4006:1010::/44
+    - 240b:4006:1010::/45
+    - 240b:4006:1018::/45
+    - 240b:4006:1020::/44
+    - 240b:4006:1020::/45
+    - 240b:4006:1028::/45
+    - 240b:4007::/32
+    - 240b:4007::/33
+    - 240b:4007:8000::/33
+    - 240b:4009::/32
+    - 240b:4009::/33
+    - 240b:4009:8000::/33
+    - 240b:400b::/32
+    - 240b:400b::/33
+    - 240b:400b:8000::/33
+    - 240b:400c::/32
+    - 240b:400c::/33
+    - 240b:400c::/40
+    - 240b:400c::/41
+    - 240b:400c:100::/40
+    - 240b:400c:100::/41
+    - 240b:400c:180::/41
+    - 240b:400c:80::/41
+    - 240b:400c:8000::/33
+    - 240b:400c:f00::/48
+    - 240b:400c:f01::/48
+    - 240b:400c:ffff::/48
+    - 240b:400d::/32
+    - 240b:400d::/33
+    - 240b:400d:8000::/33
+    - 240b:400e::/32
+    - 240b:400e::/33
+    - 240b:400e:8000::/33
+    - 240b:400f::/32
+    - 240b:400f::/33
+    - 240b:400f:8000::/33
+    - 240b:4011::/32
+    - 240b:4011::/33
+    - 240b:4011:8000::/33
+    - 240b:4012::/48
+    - 240b:4013::/32
+    - 240b:4013::/33
+    - 240b:4013:8000::/33
+    - 240b:4014::/32
+    - 240b:4014::/33
+    - 240b:4014:8000::/33
+    - 43.100.0.0/15
+    - 43.100.0.0/16
+    - 43.101.0.0/16
+    - 43.102.0.0/20
+    - 43.102.112.0/20
+    - 43.102.16.0/20
+    - 43.102.32.0/20
+    - 43.102.48.0/20
+    - 43.102.64.0/20
+    - 43.102.80.0/20
+    - 43.102.96.0/20
+    - 43.103.0.0/17
+    - 43.103.0.0/18
+    - 43.103.64.0/18
+    - 43.104.0.0/15
+    - 43.104.0.0/16
+    - 43.105.0.0/16
+    - 43.108.0.0/17
+    - 43.108.0.0/18
+    - 43.108.64.0/18
+    - 43.91.0.0/16
+    - 43.91.0.0/17
+    - 43.91.128.0/17
+    - 43.96.10.0/24
+    - 43.96.100.0/24
+    - 43.96.101.0/24
+    - 43.96.102.0/24
+    - 43.96.104.0/24
+    - 43.96.11.0/24
+    - 43.96.20.0/24
+    - 43.96.21.0/24
+    - 43.96.23.0/24
+    - 43.96.24.0/24
+    - 43.96.25.0/24
+    - 43.96.3.0/24
+    - 43.96.32.0/24
+    - 43.96.33.0/24
+    - 43.96.34.0/24
+    - 43.96.35.0/24
+    - 43.96.4.0/24
+    - 43.96.40.0/24
+    - 43.96.5.0/24
+    - 43.96.52.0/24
+    - 43.96.6.0/24
+    - 43.96.66.0/24
+    - 43.96.67.0/24
+    - 43.96.68.0/24
+    - 43.96.69.0/24
+    - 43.96.7.0/24
+    - 43.96.70.0/24
+    - 43.96.71.0/24
+    - 43.96.72.0/24
+    - 43.96.73.0/24
+    - 43.96.74.0/24
+    - 43.96.75.0/24
+    - 43.96.8.0/24
+    - 43.96.80.0/24
+    - 43.96.81.0/24
+    - 43.96.84.0/24
+    - 43.96.85.0/24
+    - 43.96.86.0/24
+    - 43.96.88.0/24
+    - 43.96.9.0/24
+    - 43.96.96.0/24
+    - 43.98.0.0/16
+    - 43.98.0.0/17
+    - 43.98.128.0/17
+    - 43.99.0.0/16
+    - 43.99.0.0/17
+    - 43.99.128.0/17
+    - 45.199.179.0/24
+    - 47.235.0.0/22
+    - 47.235.0.0/23
+    - 47.235.1.0/24
+    - 47.235.10.0/23
+    - 47.235.10.0/24
+    - 47.235.11.0/24
+    - 47.235.12.0/23
+    - 47.235.12.0/24
+    - 47.235.13.0/24
+    - 47.235.16.0/23
+    - 47.235.16.0/24
+    - 47.235.18.0/23
+    - 47.235.18.0/24
+    - 47.235.19.0/24
+    - 47.235.2.0/23
+    - 47.235.20.0/24
+    - 47.235.21.0/24
+    - 47.235.22.0/24
+    - 47.235.23.0/24
+    - 47.235.24.0/22
+    - 47.235.24.0/23
+    - 47.235.26.0/23
+    - 47.235.28.0/23
+    - 47.235.28.0/24
+    - 47.235.29.0/24
+    - 47.235.30.0/24
+    - 47.235.31.0/24
+    - 47.235.4.0/24
+    - 47.235.5.0/24
+    - 47.235.6.0/23
+    - 47.235.6.0/24
+    - 47.235.7.0/24
+    - 47.235.8.0/24
+    - 47.235.9.0/24
+    - 47.236.0.0/15
+    - 47.236.0.0/16
+    - 47.237.0.0/16
+    - 47.237.32.0/20
+    - 47.237.34.0/24
+    - 47.238.0.0/15
+    - 47.238.0.0/16
+    - 47.239.0.0/16
+    - 47.240.0.0/16
+    - 47.240.0.0/17
+    - 47.240.128.0/17
+    - 47.241.0.0/16
+    - 47.241.0.0/17
+    - 47.241.128.0/17
+    - 47.242.0.0/15
+    - 47.242.0.0/16
+    - 47.243.0.0/16
+    - 47.244.0.0/16
+    - 47.244.0.0/17
+    - 47.244.128.0/17
+    - 47.244.73.0/24
+    - 47.245.0.0/18
+    - 47.245.0.0/19
+    - 47.245.128.0/17
+    - 47.245.128.0/18
+    - 47.245.192.0/18
+    - 47.245.32.0/19
+    - 47.245.64.0/18
+    - 47.245.64.0/19
+    - 47.245.96.0/19
+    - 47.246.100.0/22
+    - 47.246.104.0/21
+    - 47.246.104.0/22
+    - 47.246.108.0/22
+    - 47.246.120.0/24
+    - 47.246.122.0/24
+    - 47.246.123.0/24
+    - 47.246.124.0/24
+    - 47.246.125.0/24
+    - 47.246.128.0/22
+    - 47.246.128.0/23
+    - 47.246.130.0/23
+    - 47.246.132.0/22
+    - 47.246.132.0/23
+    - 47.246.134.0/23
+    - 47.246.136.0/21
+    - 47.246.136.0/22
+    - 47.246.140.0/22
+    - 47.246.144.0/23
+    - 47.246.144.0/24
+    - 47.246.145.0/24
+    - 47.246.146.0/23
+    - 47.246.146.0/24
+    - 47.246.147.0/24
+    - 47.246.150.0/23
+    - 47.246.150.0/24
+    - 47.246.151.0/24
+    - 47.246.152.0/23
+    - 47.246.152.0/24
+    - 47.246.153.0/24
+    - 47.246.154.0/24
+    - 47.246.155.0/24
+    - 47.246.156.0/22
+    - 47.246.156.0/23
+    - 47.246.158.0/23
+    - 47.246.160.0/20
+    - 47.246.160.0/21
+    - 47.246.168.0/21
+    - 47.246.176.0/20
+    - 47.246.176.0/21
+    - 47.246.184.0/21
+    - 47.246.192.0/22
+    - 47.246.192.0/23
+    - 47.246.194.0/23
+    - 47.246.196.0/22
+    - 47.246.196.0/23
+    - 47.246.198.0/23
+    - 47.246.32.0/22
+    - 47.246.66.0/24
+    - 47.246.67.0/24
+    - 47.246.68.0/23
+    - 47.246.68.0/24
+    - 47.246.69.0/24
+    - 47.246.72.0/21
+    - 47.246.72.0/22
+    - 47.246.76.0/22
+    - 47.246.80.0/24
+    - 47.246.82.0/23
+    - 47.246.82.0/24
+    - 47.246.83.0/24
+    - 47.246.84.0/22
+    - 47.246.84.0/23
+    - 47.246.86.0/23
+    - 47.246.88.0/22
+    - 47.246.88.0/23
+    - 47.246.90.0/23
+    - 47.246.92.0/23
+    - 47.246.92.0/24
+    - 47.246.93.0/24
+    - 47.246.96.0/21
+    - 47.246.96.0/22
+    - 47.250.0.0/17
+    - 47.250.0.0/18
+    - 47.250.128.0/17
+    - 47.250.128.0/18
+    - 47.250.192.0/18
+    - 47.250.64.0/18
+    - 47.250.99.0/24
+    - 47.251.0.0/16
+    - 47.251.0.0/17
+    - 47.251.128.0/17
+    - 47.251.224.0/22
+    - 47.252.0.0/17
+    - 47.252.0.0/18
+    - 47.252.128.0/17
+    - 47.252.128.0/18
+    - 47.252.192.0/18
+    - 47.252.64.0/18
+    - 47.252.67.0/24
+    - 47.253.0.0/16
+    - 47.253.0.0/17
+    - 47.253.128.0/17
+    - 47.254.0.0/17
+    - 47.254.0.0/18
+    - 47.254.113.0/24
+    - 47.254.128.0/18
+    - 47.254.128.0/19
+    - 47.254.160.0/19
+    - 47.254.192.0/18
+    - 47.254.192.0/19
+    - 47.254.224.0/19
+    - 47.254.64.0/18
+    - 47.52.0.0/16
+    - 47.52.0.0/17
+    - 47.52.128.0/17
+    - 47.56.0.0/15
+    - 47.56.0.0/16
+    - 47.57.0.0/16
+    - 47.74.0.0/18
+    - 47.74.0.0/19
+    - 47.74.0.0/21
+    - 47.74.128.0/17
+    - 47.74.128.0/18
+    - 47.74.192.0/18
+    - 47.74.32.0/19
+    - 47.74.64.0/18
+    - 47.74.64.0/19
+    - 47.74.96.0/19
+    - 47.75.0.0/16
+    - 47.75.0.0/17
+    - 47.75.128.0/17
+    - 47.76.0.0/16
+    - 47.76.0.0/17
+    - 47.76.128.0/17
+    - 47.77.0.0/22
+    - 47.77.0.0/23
+    - 47.77.104.0/21
+    - 47.77.12.0/22
+    - 47.77.128.0/17
+    - 47.77.128.0/18
+    - 47.77.128.0/21
+    - 47.77.136.0/21
+    - 47.77.144.0/21
+    - 47.77.152.0/21
+    - 47.77.16.0/21
+    - 47.77.16.0/22
+    - 47.77.192.0/18
+    - 47.77.2.0/23
+    - 47.77.20.0/22
+    - 47.77.24.0/22
+    - 47.77.24.0/23
+    - 47.77.26.0/23
+    - 47.77.32.0/19
+    - 47.77.32.0/20
+    - 47.77.4.0/22
+    - 47.77.4.0/23
+    - 47.77.48.0/20
+    - 47.77.6.0/23
+    - 47.77.64.0/19
+    - 47.77.64.0/20
+    - 47.77.8.0/21
+    - 47.77.8.0/22
+    - 47.77.80.0/20
+    - 47.77.96.0/20
+    - 47.77.96.0/21
+    - 47.78.0.0/17
+    - 47.78.128.0/17
+    - 47.79.0.0/20
+    - 47.79.0.0/21
+    - 47.79.104.0/21
+    - 47.79.112.0/20
+    - 47.79.128.0/19
+    - 47.79.128.0/20
+    - 47.79.144.0/20
+    - 47.79.16.0/20
+    - 47.79.16.0/21
+    - 47.79.192.0/18
+    - 47.79.192.0/19
+    - 47.79.224.0/19
+    - 47.79.24.0/21
+    - 47.79.32.0/20
+    - 47.79.32.0/21
+    - 47.79.40.0/21
+    - 47.79.48.0/20
+    - 47.79.48.0/21
+    - 47.79.52.0/23
+    - 47.79.54.0/23
+    - 47.79.56.0/21
+    - 47.79.56.0/23
+    - 47.79.58.0/23
+    - 47.79.60.0/23
+    - 47.79.62.0/23
+    - 47.79.64.0/20
+    - 47.79.64.0/21
+    - 47.79.72.0/21
+    - 47.79.8.0/21
+    - 47.79.80.0/20
+    - 47.79.80.0/21
+    - 47.79.83.0/24
+    - 47.79.88.0/21
+    - 47.79.96.0/19
+    - 47.79.96.0/20
+    - 47.80.0.0/18
+    - 47.80.0.0/19
+    - 47.80.128.0/17
+    - 47.80.128.0/18
+    - 47.80.192.0/18
+    - 47.80.32.0/19
+    - 47.80.64.0/18
+    - 47.80.64.0/19
+    - 47.80.96.0/19
+    - 47.81.0.0/18
+    - 47.81.0.0/19
+    - 47.81.128.0/17
+    - 47.81.128.0/18
+    - 47.81.192.0/18
+    - 47.81.32.0/19
+    - 47.81.64.0/18
+    - 47.81.64.0/19
+    - 47.81.96.0/19
+    - 47.82.0.0/18
+    - 47.82.0.0/19
+    - 47.82.10.0/23
+    - 47.82.12.0/23
+    - 47.82.128.0/17
+    - 47.82.128.0/18
+    - 47.82.14.0/23
+    - 47.82.192.0/18
+    - 47.82.32.0/19
+    - 47.82.32.0/21
+    - 47.82.40.0/21
+    - 47.82.48.0/21
+    - 47.82.56.0/21
+    - 47.82.64.0/18
+    - 47.82.64.0/19
+    - 47.82.8.0/23
+    - 47.82.96.0/19
+    - 47.83.0.0/16
+    - 47.83.0.0/17
+    - 47.83.128.0/17
+    - 47.83.32.0/21
+    - 47.83.40.0/21
+    - 47.83.48.0/21
+    - 47.83.56.0/21
+    - 47.84.0.0/16
+    - 47.84.0.0/17
+    - 47.84.128.0/17
+    - 47.84.144.0/21
+    - 47.84.152.0/21
+    - 47.84.160.0/21
+    - 47.84.168.0/21
+    - 47.85.0.0/16
+    - 47.85.0.0/17
+    - 47.85.112.0/22
+    - 47.85.112.0/23
+    - 47.85.114.0/23
+    - 47.85.128.0/17
+    - 47.86.0.0/16
+    - 47.86.0.0/17
+    - 47.86.128.0/17
+    - 47.87.0.0/18
+    - 47.87.0.0/19
+    - 47.87.128.0/18
+    - 47.87.128.0/19
+    - 47.87.160.0/19
+    - 47.87.192.0/22
+    - 47.87.192.0/23
+    - 47.87.194.0/23
+    - 47.87.196.0/22
+    - 47.87.196.0/23
+    - 47.87.198.0/23
+    - 47.87.200.0/22
+    - 47.87.200.0/23
+    - 47.87.202.0/23
+    - 47.87.204.0/22
+    - 47.87.204.0/23
+    - 47.87.206.0/23
+    - 47.87.208.0/22
+    - 47.87.208.0/23
+    - 47.87.210.0/23
+    - 47.87.212.0/22
+    - 47.87.212.0/23
+    - 47.87.214.0/23
+    - 47.87.216.0/22
+    - 47.87.216.0/23
+    - 47.87.218.0/23
+    - 47.87.220.0/22
+    - 47.87.220.0/23
+    - 47.87.222.0/23
+    - 47.87.224.0/22
+    - 47.87.224.0/23
+    - 47.87.226.0/23
+    - 47.87.228.0/22
+    - 47.87.228.0/23
+    - 47.87.230.0/23
+    - 47.87.232.0/22
+    - 47.87.232.0/23
+    - 47.87.234.0/23
+    - 47.87.236.0/22
+    - 47.87.236.0/23
+    - 47.87.238.0/23
+    - 47.87.240.0/22
+    - 47.87.240.0/23
+    - 47.87.242.0/23
+    - 47.87.32.0/19
+    - 47.87.64.0/18
+    - 47.87.64.0/19
+    - 47.87.96.0/19
+    - 47.88.0.0/17
+    - 47.88.0.0/18
+    - 47.88.109.0/24
+    - 47.88.128.0/17
+    - 47.88.128.0/18
+    - 47.88.135.0/24
+    - 47.88.192.0/18
+    - 47.88.41.0/24
+    - 47.88.42.0/24
+    - 47.88.43.0/24
+    - 47.88.64.0/18
+    - 47.89.0.0/18
+    - 47.89.0.0/19
+    - 47.89.100.0/24
+    - 47.89.101.0/24
+    - 47.89.102.0/24
+    - 47.89.103.0/24
+    - 47.89.104.0/21
+    - 47.89.104.0/22
+    - 47.89.108.0/22
+    - 47.89.122.0/24
+    - 47.89.123.0/24
+    - 47.89.124.0/23
+    - 47.89.124.0/24
+    - 47.89.125.0/24
+    - 47.89.128.0/18
+    - 47.89.128.0/19
+    - 47.89.160.0/19
+    - 47.89.192.0/18
+    - 47.89.192.0/19
+    - 47.89.221.0/24
+    - 47.89.224.0/19
+    - 47.89.32.0/19
+    - 47.89.72.0/22
+    - 47.89.72.0/23
+    - 47.89.74.0/23
+    - 47.89.76.0/22
+    - 47.89.76.0/23
+    - 47.89.78.0/23
+    - 47.89.80.0/23
+    - 47.89.82.0/23
+    - 47.89.84.0/24
+    - 47.89.88.0/22
+    - 47.89.88.0/23
+    - 47.89.90.0/23
+    - 47.89.92.0/22
+    - 47.89.92.0/23
+    - 47.89.94.0/23
+    - 47.89.96.0/24
+    - 47.89.97.0/24
+    - 47.89.98.0/23
+    - 47.89.99.0/24
+    - 47.90.0.0/17
+    - 47.90.0.0/18
+    - 47.90.128.0/17
+    - 47.90.128.0/18
+    - 47.90.172.0/24
+    - 47.90.173.0/24
+    - 47.90.174.0/24
+    - 47.90.175.0/24
+    - 47.90.192.0/18
+    - 47.90.64.0/18
+    - 47.91.0.0/19
+    - 47.91.0.0/20
+    - 47.91.112.0/20
+    - 47.91.128.0/17
+    - 47.91.128.0/18
+    - 47.91.16.0/20
+    - 47.91.192.0/18
+    - 47.91.32.0/19
+    - 47.91.32.0/20
+    - 47.91.48.0/20
+    - 47.91.64.0/19
+    - 47.91.64.0/20
+    - 47.91.80.0/20
+    - 47.91.96.0/19
+    - 47.91.96.0/20
+    - 5.181.224.0/23
+    - 59.82.136.0/23
+    - 8.208.0.0/16
+    - 8.208.0.0/17
+    - 8.208.0.0/18
+    - 8.208.0.0/19
+    - 8.208.128.0/17
+    - 8.208.141.0/24
+    - 8.208.32.0/19
+    - 8.209.0.0/19
+    - 8.209.0.0/20
+    - 8.209.128.0/18
+    - 8.209.128.0/19
+    - 8.209.16.0/20
+    - 8.209.160.0/19
+    - 8.209.192.0/18
+    - 8.209.192.0/19
+    - 8.209.224.0/19
+    - 8.209.36.0/23
+    - 8.209.36.0/24
+    - 8.209.37.0/24
+    - 8.209.38.0/23
+    - 8.209.38.0/24
+    - 8.209.39.0/24
+    - 8.209.40.0/22
+    - 8.209.40.0/23
+    - 8.209.42.0/23
+    - 8.209.44.0/22
+    - 8.209.44.0/23
+    - 8.209.46.0/23
+    - 8.209.48.0/20
+    - 8.209.48.0/21
+    - 8.209.56.0/21
+    - 8.209.64.0/18
+    - 8.209.64.0/19
+    - 8.209.96.0/19
+    - 8.210.0.0/16
+    - 8.210.0.0/17
+    - 8.210.128.0/17
+    - 8.210.240.0/24
+    - 8.211.0.0/17
+    - 8.211.0.0/18
+    - 8.211.104.0/21
+    - 8.211.128.0/18
+    - 8.211.128.0/19
+    - 8.211.160.0/19
+    - 8.211.192.0/18
+    - 8.211.192.0/19
+    - 8.211.224.0/19
+    - 8.211.226.0/24
+    - 8.211.64.0/18
+    - 8.211.80.0/21
+    - 8.211.88.0/21
+    - 8.211.96.0/21
+    - 8.212.0.0/17
+    - 8.212.0.0/18
+    - 8.212.128.0/18
+    - 8.212.128.0/19
+    - 8.212.160.0/19
+    - 8.212.192.0/18
+    - 8.212.192.0/19
+    - 8.212.224.0/19
+    - 8.212.64.0/18
+    - 8.213.0.0/17
+    - 8.213.0.0/18
+    - 8.213.128.0/19
+    - 8.213.128.0/20
+    - 8.213.144.0/20
+    - 8.213.160.0/21
+    - 8.213.160.0/22
+    - 8.213.164.0/22
+    - 8.213.176.0/20
+    - 8.213.176.0/21
+    - 8.213.184.0/21
+    - 8.213.192.0/18
+    - 8.213.192.0/19
+    - 8.213.224.0/19
+    - 8.213.251.0/24
+    - 8.213.252.0/24
+    - 8.213.253.0/24
+    - 8.213.64.0/18
+    - 8.214.0.0/16
+    - 8.214.0.0/17
+    - 8.214.128.0/17
+    - 8.215.0.0/16
+    - 8.215.0.0/17
+    - 8.215.128.0/17
+    - 8.215.160.0/24
+    - 8.215.162.0/23
+    - 8.215.168.0/24
+    - 8.215.169.0/24
+    - 8.216.0.0/17
+    - 8.216.0.0/18
+    - 8.216.128.0/17
+    - 8.216.128.0/18
+    - 8.216.148.0/24
+    - 8.216.192.0/18
+    - 8.216.64.0/18
+    - 8.216.69.0/24
+    - 8.216.74.0/24
+    - 8.217.0.0/16
+    - 8.217.0.0/17
+    - 8.217.128.0/17
+    - 8.218.0.0/16
+    - 8.218.0.0/17
+    - 8.218.128.0/17
+    - 8.219.0.0/16
+    - 8.219.0.0/17
+    - 8.219.128.0/17
+    - 8.219.40.0/21
+    - 8.220.116.0/24
+    - 8.220.128.0/18
+    - 8.220.128.0/19
+    - 8.220.147.0/24
+    - 8.220.160.0/19
+    - 8.220.192.0/18
+    - 8.220.192.0/19
+    - 8.220.224.0/19
+    - 8.220.229.0/24
+    - 8.220.64.0/18
+    - 8.220.64.0/19
+    - 8.220.96.0/19
+    - 8.221.0.0/17
+    - 8.221.0.0/18
+    - 8.221.0.0/21
+    - 8.221.128.0/17
+    - 8.221.128.0/18
+    - 8.221.184.0/22
+    - 8.221.188.0/22
+    - 8.221.192.0/18
+    - 8.221.192.0/21
+    - 8.221.200.0/21
+    - 8.221.208.0/21
+    - 8.221.216.0/21
+    - 8.221.48.0/21
+    - 8.221.56.0/21
+    - 8.221.64.0/18
+    - 8.221.8.0/21
+    - 8.222.0.0/20
+    - 8.222.0.0/21
+    - 8.222.112.0/20
+    - 8.222.128.0/17
+    - 8.222.128.0/18
+    - 8.222.16.0/20
+    - 8.222.16.0/21
+    - 8.222.192.0/18
+    - 8.222.24.0/21
+    - 8.222.32.0/20
+    - 8.222.32.0/21
+    - 8.222.40.0/21
+    - 8.222.48.0/20
+    - 8.222.48.0/21
+    - 8.222.56.0/21
+    - 8.222.64.0/20
+    - 8.222.64.0/21
+    - 8.222.72.0/21
+    - 8.222.8.0/21
+    - 8.222.80.0/20
+    - 8.222.80.0/21
+    - 8.222.88.0/21
+    - 8.222.96.0/19
+    - 8.222.96.0/20
+    - 8.223.0.0/17
+    - 8.223.0.0/18
+    - 8.223.128.0/17
+    - 8.223.128.0/18
+    - 8.223.192.0/18
+    - 8.223.64.0/18
--- a/docs/docs/CHANGELOG.md
+++ b/docs/docs/CHANGELOG.md
@@ -12,7 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]

 <!-- This changes the project to: -->
-
+- Added a missing link to the Caddy installation environment in the installation documentation.
 - Downstream consumers can change the default [log/slog#Logger](https://pkg.go.dev/log/slog#Logger) instance that Anubis uses by setting `opts.Logger` to your slog instance of choice ([#864](https://github.com/TecharoHQ/anubis/issues/864)).
 - The [Thoth client](https://anubis.techaro.lol/docs/admin/thoth) is now public in the repo instead of being an internal package.
 - [Custom-AsyncHttpClient](https://github.com/AsyncHttpClient/async-http-client)'s default User-Agent has an increased weight by default ([#852](https://github.com/TecharoHQ/anubis/issues/852)).
@@ -39,12 +39,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - The word "hack" has been removed from the translation strings for Anubis due to incidents involving people misunderstanding that word and sending particularly horrible things to the project lead over email.
 - Bump AI-robots.txt to version 1.39
 - Add a default block rule for Huawei Cloud.
+- Add a default block rule for Alibaba Cloud.
+- Add X-Request-URI support so that Subrequest Authentication has path support.

 ### Security-relevant changes

 #### Fix potential double-spend for challenges

-Anubis operates by issuing a challenge and having the client present a solution for that challenge. Challenges are identified by a unique UUID, which is tored in the database.
+Anubis operates by issuing a challenge and having the client present a solution for that challenge. Challenges are identified by a unique UUID, which is stored in the database.

 The problem is that a challenge could potentially be used twice by a dedicated attacker making a targeted attack against Anubis. Challenge records did not have a "spent" or "used" field. In total, a dedicated attacker could solve a challenge once and reuse that solution across multiple sessions in order to mint additional tokens.

--- a/docs/docs/admin/frameworks/wordpress.mdx
+++ b/docs/docs/admin/frameworks/wordpress.mdx
@@ -1,6 +1,6 @@
-# Wordpress
+# WordPress

-Wordpress is the most popular blog engine on the planet.
+WordPress is the most popular blog engine on the planet.

 ## Using a multi-site setup with Anubis

@@ -27,7 +27,7 @@ flowchart LR
    US --> |whatever you're doing| B
 ```

-Wordpress may not realize that the underlying connection is being done over HTTPS. This could lead to a redirect loop in the `/wp-admin/` routes. In order to fix this, add the following to your `wp-config.php` file:
+WordPress may not realize that the underlying connection is being done over HTTPS. This could lead to a redirect loop in the `/wp-admin/` routes. In order to fix this, add the following to your `wp-config.php` file:

 ```php
 if (isset($_SERVER['HTTP_X_FORWARDED_PROTO']) && $_SERVER['HTTP_X_FORWARDED_PROTO'] === 'https') {
@@ -36,4 +36,4 @@ if (isset($_SERVER['HTTP_X_FORWARDED_PROTO']) && $_SERVER['HTTP_X_FORWARDED_PROT
 }
 ```

-This will make Wordpress think that your connection is over HTTPS instead of plain HTTP.
+This will make WordPress think that your connection is over HTTPS instead of plain HTTP.
--- a/docs/docs/admin/installation.mdx
+++ b/docs/docs/admin/installation.mdx
@@ -178,6 +178,7 @@ Alternatively here is a key generated by your browser:
 To get Anubis filtering your traffic, you need to make sure it's added to your HTTP load balancer or platform configuration. See the [environments category](/docs/category/environments) for detailed information on individual environments.

 - [Apache](./environments/apache.mdx)
+- [Caddy](./environments/caddy.mdx)
 - [Docker compose](./environments/docker-compose.mdx)
 - [Kubernetes](./environments/kubernetes.mdx)
 - [Nginx](./environments/nginx.mdx)
--- a/internal/ogtags/ogtags.go
+++ b/internal/ogtags/ogtags.go
@@ -21,6 +21,24 @@ const (
 	querySeparatorLength  = 1 // Length of "?" for query strings
 )

+// unixRoundTripper wraps an http.Transport to handle Unix socket requests properly
+// by ensuring the URL scheme is set to "http" to avoid TLS issues.
+// Based on the UnixRoundTripper implementation in lib/http.go
+type unixRoundTripper struct {
+	Transport *http.Transport
+}
+
+// RoundTrip implements the http.RoundTripper interface
+func (t *unixRoundTripper) RoundTrip(req *http.Request) (*http.Response, error) {
+	req = req.Clone(req.Context())
+	if req.Host == "" {
+		req.Host = "localhost"
+	}
+	req.URL.Host = req.Host
+	req.URL.Scheme = "http" // Ensure HTTP scheme to avoid "server gave HTTP response to HTTPS client" error
+	return t.Transport.RoundTrip(req)
+}
+
 type OGTagCache struct {
 	cache     store.JSON[map[string]string]
 	targetURL *url.URL
@@ -69,11 +87,12 @@ func NewOGTagCache(target string, conf config.OpenGraph, backend store.Interface
 	// Configure custom transport for Unix sockets
 	if parsedTargetURL.Scheme == "unix" {
 		socketPath := parsedTargetURL.Path // For unix scheme, path is the socket path
-		client.Transport = &http.Transport{
+		transport := &http.Transport{
 			DialContext: func(_ context.Context, _, _ string) (net.Conn, error) {
 				return net.Dial("unix", socketPath)
 			},
 		}
+		client.Transport = &unixRoundTripper{Transport: transport}
 	}

 	return &OGTagCache{
--- a/internal/ogtags/ogtags_test.go
+++ b/internal/ogtags/ogtags_test.go
@@ -99,16 +99,16 @@ func TestNewOGTagCache_UnixSocket(t *testing.T) {
 	}

 	// Check if the client transport is configured for Unix sockets
-	transport, ok := cache.client.Transport.(*http.Transport)
+	roundTripper, ok := cache.client.Transport.(*unixRoundTripper)
 	if !ok {
-		t.Fatalf("expected client transport to be *http.Transport, got %T", cache.client.Transport)
+		t.Fatalf("expected client transport to be *unixRoundTripper, got %T", cache.client.Transport)
 	}
-	if transport.DialContext == nil {
+	if roundTripper.Transport.DialContext == nil {
 		t.Fatal("expected client transport DialContext to be non-nil for unix socket")
 	}

 	// Attempt a dummy dial to see if it uses the correct path (optional, more involved check)
-	dummyConn, err := transport.DialContext(context.Background(), "", "")
+	dummyConn, err := roundTripper.Transport.DialContext(context.Background(), "", "")
 	if err == nil {
 		dummyConn.Close()
 		t.Log("DialContext seems functional, but couldn't verify path without a listener")
--- a/internal/ogtags/test_unix_https_fix_test.go
+++ b/internal/ogtags/test_unix_https_fix_test.go
@@ -0,0 +1,98 @@
+package ogtags
+
+import (
+	"context"
+	"net"
+	"net/http"
+	"net/url"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+	
+	"github.com/TecharoHQ/anubis/lib/policy/config"
+	"github.com/TecharoHQ/anubis/lib/store/memory"
+)
+
+// TestUnixSocketHTTPSFix tests that the fix prevents "http: server gave HTTP response to HTTPS client" errors
+// when using Unix socket targets with HTTPS input URLs
+func TestUnixSocketHTTPSFix(t *testing.T) {
+	tempDir := t.TempDir()
+	socketPath := filepath.Join(tempDir, "test.sock")
+
+	// Create a simple HTTP server listening on the Unix socket
+	server := &http.Server{
+		Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			// Verify that the request comes in with HTTP (not HTTPS)
+			if r.URL.Scheme != "" && r.URL.Scheme != "http" {
+				t.Errorf("Unexpected scheme in request: %s (expected 'http' or empty)", r.URL.Scheme)
+			}
+			if r.TLS != nil {
+				t.Errorf("Request has TLS information when it shouldn't for Unix socket")
+			}
+			
+			w.Header().Set("Content-Type", "text/html")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`<html><head><meta property="og:title" content="Test Title"></head></html>`))
+		}),
+	}
+
+	// Listen on Unix socket
+	listener, err := net.Listen("unix", socketPath)
+	if err != nil {
+		t.Fatalf("Failed to create Unix socket listener: %v", err)
+	}
+	defer os.Remove(socketPath)
+	defer listener.Close()
+
+	// Start the server
+	go func() {
+		server.Serve(listener)
+	}()
+	defer server.Close()
+
+	// Wait a bit for server to start
+	time.Sleep(100 * time.Millisecond)
+
+	// Create OGTagCache with Unix socket target
+	target := "unix://" + socketPath
+	cache := NewOGTagCache(target, config.OpenGraph{
+		Enabled: true,
+		TimeToLive: time.Minute,
+	}, memory.New(t.Context()))
+
+	// Test cases that previously might have caused the "HTTP response to HTTPS client" error
+	testCases := []struct {
+		name string
+		url  string
+	}{
+		{"HTTPS URL", "https://example.com/test"},
+		{"HTTPS with port", "https://example.com:443/test"},
+		{"HTTPS with query", "https://example.com/test?param=value"},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			inputURL, _ := url.Parse(tc.url)
+			
+			// This should succeed without the "server gave HTTP response to HTTPS client" error
+			ogTags, err := cache.GetOGTags(context.Background(), inputURL, "example.com")
+			
+			if err != nil {
+				if strings.Contains(err.Error(), "server gave HTTP response to HTTPS client") {
+					t.Errorf("Fix did not work: still getting HTTPS/HTTP error: %v", err)
+				} else {
+					// Other errors are acceptable for this test
+					t.Logf("Got non-HTTPS error (acceptable): %v", err)
+				}
+			} else {
+				// Success case
+				if ogTags["og:title"] != "Test Title" {
+					t.Errorf("Expected og:title 'Test Title', got: %v", ogTags["og:title"])
+				}
+				t.Logf("Success: got expected og:title = %s", ogTags["og:title"])
+			}
+		})
+	}
+}
--- a/lib/policy/checker.go
+++ b/lib/policy/checker.go
@@ -102,6 +102,13 @@ func NewPathChecker(rexStr string) (checker.Impl, error) {
 }

 func (pc *PathChecker) Check(r *http.Request) (bool, error) {
+	originalUrl := r.Header.Get("X-Original-URI")
+	if originalUrl != "" {
+		if pc.regexp.MatchString(originalUrl) {
+			return true, nil
+		}
+	}
+
 	if pc.regexp.MatchString(r.URL.Path) {
 		return true, nil
 	}
--- a/lib/policy/checker_test.go
+++ b/lib/policy/checker_test.go
@@ -198,3 +198,96 @@ func TestHeaderExistsChecker(t *testing.T) {
 		})
 	}
 }
+
+func TestPathChecker_XOriginalURI(t *testing.T) {
+	tests := []struct {
+		name          string
+		regex         string
+		xOriginalURI  string
+		urlPath       string
+		headerKey     string
+		expectedMatch bool
+		expectError   bool
+	}{
+		{
+			name:          "X-Original-URI matches regex (with trailing space - current typo)",
+			regex:         "^/api/.*",
+			xOriginalURI:  "/api/users",
+			urlPath:       "/different/path",
+			headerKey:     "X-Original-URI",
+			expectedMatch: true,
+			expectError:   false,
+		},
+		{
+			name:          "X-Original-URI doesn't match, falls back to URL.Path",
+			regex:         "^/admin/.*",
+			xOriginalURI:  "/api/users",
+			urlPath:       "/admin/dashboard",
+			headerKey:     "X-Original-URI",
+			expectedMatch: true,
+			expectError:   false,
+		},
+		{
+			name:          "Neither X-Original-URI nor URL.Path match",
+			regex:         "^/admin/.*",
+			xOriginalURI:  "/api/users",
+			urlPath:       "/public/info",
+			headerKey:     "X-Original-URI ",
+			expectedMatch: false,
+			expectError:   false,
+		},
+		{
+			name:          "Empty X-Original-URI, URL.Path matches",
+			regex:         "^/static/.*",
+			xOriginalURI:  "",
+			urlPath:       "/static/css/style.css",
+			headerKey:     "X-Original-URI",
+			expectedMatch: true,
+			expectError:   false,
+		},
+		{
+			name:          "Complex regex matching X-Original-URI",
+			regex:         `^/api/v[0-9]+/(users|posts)/[0-9]+$`,
+			xOriginalURI:  "/api/v1/users/123",
+			urlPath:       "/different",
+			headerKey:     "X-Original-URI",
+			expectedMatch: true,
+			expectError:   false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Create the PathChecker
+			pc, err := NewPathChecker(tt.regex)
+			if err != nil {
+				if !tt.expectError {
+					t.Fatalf("NewPathChecker() unexpected error: %v", err)
+				}
+				return
+			}
+
+			if tt.expectError {
+				t.Fatal("NewPathChecker() expected error but got none")
+			}
+
+			req, err := http.NewRequest("GET", "http://example.com"+tt.urlPath, nil)
+			if err != nil {
+				t.Fatalf("Failed to create request: %v", err)
+			}
+
+			if tt.xOriginalURI != "" {
+				req.Header.Set(tt.headerKey, tt.xOriginalURI)
+			}
+
+			match, err := pc.Check(req)
+			if err != nil {
+				t.Fatalf("Check() unexpected error: %v", err)
+			}
+
+			if match != tt.expectedMatch {
+				t.Errorf("Check() = %v, want %v", match, tt.expectedMatch)
+			}
+		})
+	}
+}
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@techaro/anubis",
-  "version": "1.21.3",
+  "version": "1.22.0-pre1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@techaro/anubis",
-      "version": "1.21.3",
+      "version": "1.22.0-pre1",
      "license": "ISC",
      "dependencies": {
        "@aws-crypto/sha256-js": "^5.2.0"
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@techaro/anubis",
-  "version": "1.21.3",
+  "version": "1.22.0-pre1",
  "description": "",
  "main": "index.js",
  "scripts": {
@@ -30,4 +30,4 @@
  "dependencies": {
    "@aws-crypto/sha256-js": "^5.2.0"
  }
-}
+}
Author	SHA1	Message	Date
copilot-swe-agent[bot]	ac6101b6bf	Fix Unix socket HTTPS/HTTP issue in OpenGraph fetching Co-authored-by: JasonLovesDoggo <66544866+JasonLovesDoggo@users.noreply.github.com>	2025-08-24 03:36:36 +00:00
copilot-swe-agent[bot]	9a85f0b053	Initial investigation into Unix socket HTTPS/HTTP issue Co-authored-by: JasonLovesDoggo <66544866+JasonLovesDoggo@users.noreply.github.com>	2025-08-24 03:30:41 +00:00
copilot-swe-agent[bot]	bdb8d5c249	Initial plan	2025-08-24 03:17:57 +00:00
Skyler Mäntysaari	d1d631a18a	lib/checker: Implement X-Original-URI support (#1015 )	2025-08-23 23:14:37 -04:00
Timo Tijhof	f3cd6c9ca4	docs: fix "stored" typo in CHANGELOG.md (#1008 ) Co-authored-by: Jason Cameron <git@jasoncameron.dev>	2025-08-24 03:12:08 +00:00
Brad Parbs	23772fd3cb	s/Wordpress/WordPress in docs (#1020 ) Signed-off-by: Brad Parbs <brad@bradparbs.com>	2025-08-24 02:52:09 +00:00
Xe Iaso	a7a61690fc	chore: commit for v1.22.0-pre1 Signed-off-by: Xe Iaso <me@xeiaso.net>	2025-08-23 22:39:43 -04:00
Xe Iaso	f5afe8b6c8	chore: release v1.22.0-pre1 Signed-off-by: Xe Iaso <me@xeiaso.net>	2025-08-24 02:38:54 +00:00
Julian Krieger	61682e4987	Update installation.mdx to include a link to the Caddy docs (#993 ) * Update installation.mdx to include a link to the Caddy docs Signed-off-by: Julian Krieger <julian.krieger@hm.edu> * Update CHANGELOG.md to include documentation changes Signed-off-by: Julian Krieger <julian.krieger@hm.edu> --------- Signed-off-by: Julian Krieger <julian.krieger@hm.edu>	2025-08-20 23:02:49 +00:00
Xe Iaso	b0fa256e3e	fix(default-config): also block alibaba cloud (#1005 ) * fix(default-config): also block alibaba cloud Signed-off-by: Xe Iaso <me@xeiaso.net> * chore: spelling Signed-off-by: Xe Iaso <me@xeiaso.net> --------- Signed-off-by: Xe Iaso <me@xeiaso.net>	2025-08-20 23:01:49 +00:00