chore: go mod tidy

Signed-off-by: Xe Iaso <me@xeiaso.net>

.devcontainer/devcontainer.json

@@ -5,9 +5,10 @@
   "dockerComposeFile": ["./docker-compose.yaml"],
   "service": "workspace",
   "workspaceFolder": "/workspace/anubis",
-  "postStartCommand": "npm ci && go mod download",
+  "postStartCommand": "bash ./.devcontainer/poststart.sh",
   "features": {
-    "ghcr.io/xe/devcontainer-features/ko:1.1.0": {}
+    "ghcr.io/xe/devcontainer-features/ko:1.1.0": {},
+    "ghcr.io/devcontainers/features/github-cli:1": {}
   },
   "initializeCommand": "mkdir -p ${localEnv:HOME}${localEnv:USERPROFILE}/.local/share/atuin",
   "customizations": {
@@ -18,8 +19,14 @@
         "golang.go",
         "unifiedjs.vscode-mdx",
         "a-h.templ",
-        "redhat.vscode-yaml"
-      ]
+        "redhat.vscode-yaml",
+        "streetsidesoftware.code-spell-checker"
+      ],
+      "settings": {
+        "chat.instructionsFilesLocations": {
+          ".github/copilot-instructions.md": true
+        }
+      }
     }
   }
 }

.devcontainer/poststart.sh

@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+
+pwd
+
+npm ci &
+go mod download &
+go install ./utils/cmd/... &
+
+wait

.github/FUNDING.yml

@@ -1,2 +1,3 @@
 patreon: cadey
-github: xe
+github: xe
+liberapay: Xe

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,60 @@
+name: Bug report
+description: Create a report to help us improve
+
+body:
+  - type: textarea
+    id: description-of-bug
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: I can reliably get an error when...
+    validations:
+      required: true
+
+  - type: textarea
+    id: steps-to-reproduce
+    attributes:
+      label: Steps to reproduce
+      description: |
+        Steps to reproduce the behavior.
+      placeholder: |
+        1. Go to the following url...
+        2. Click on...
+        3. You get the following error: ...
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected behavior
+      description: |
+        A clear and concise description of what you expected to happen.
+        Ideally also describe *why* you expect it to happen.
+      placeholder: Instead of displaying an error, it would...
+    validations:
+      required: true
+
+  - type: input
+    id: version-os
+    attributes:
+      label: Your operating system and its version.
+      description: Unsure? Visit https://whatsmyos.com/
+      placeholder: Android 13
+    validations:
+      required: true
+
+  - type: input
+    id: version-browser
+    attributes:
+      label: Your browser and its version.
+      description: Unsure? Visit https://www.whatsmybrowser.org/
+      placeholder: Firefox 142
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional context
+      description: Add any other context about the problem here.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Security
+    url: https://techaro.lol/contact
+    about: Do not file security reports here. Email security@techaro.lol.

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -0,0 +1,39 @@
+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature request] "
+
+body:
+  - type: textarea
+    id: description-of-bug
+    attributes:
+      label: Is your feature request related to a problem? Please describe.
+      description: A clear and concise description of what the problem is that made you submit this report.
+      placeholder: I am always frustrated, when...
+    validations:
+      required: true
+
+  - type: textarea
+    id: description-of-solution
+    attributes:
+      label: Solution you would like.
+      description: A clear and concise description of what you want to happen.
+      placeholder: Instead of behaving like this, there should be...
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Describe alternatives you have considered.
+      description: A clear and concise description of any alternative solutions or features you have considered.
+      placeholder: Another workaround that would work, is...
+    validations:
+      required: false
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional context
+      description: Add any other context (such as mock-ups, proof of concepts or screenshots) about the feature request here.
+    validations:
+      required: false

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,11 +1,12 @@
 <!--
 delete me and describe your change here, give enough context for a maintainer to understand what and why
 
-See https://anubis.techaro.lol/docs/developer/code-quality for more information
+See https://github.com/TecharoHQ/anubis/blob/main/CONTRIBUTING.md for more information
 -->
 
 Checklist:
 
 - [ ] Added a description of the changes to the `[Unreleased]` section of docs/docs/CHANGELOG.md
-- [ ] Added test cases to [the relevant parts of the codebase](https://anubis.techaro.lol/docs/developer/code-quality)
+- [ ] Added test cases to [the relevant parts of the codebase](https://github.com/TecharoHQ/anubis/blob/main/CONTRIBUTING.md)
 - [ ] Ran integration tests `npm run test:integration` (unsupported on Windows, please use WSL)
+- [ ] All of my commits have [verified signatures](https://anubis.techaro.lol/docs/developer/signed-commits)

.github/actions/spelling/README.md

@@ -1,17 +1,17 @@
 # check-spelling/check-spelling configuration
 
-File | Purpose | Format | Info
--|-|-|-
-[dictionary.txt](dictionary.txt) | Replacement dictionary (creating this file will override the default dictionary) | one word per line | [dictionary](https://github.com/check-spelling/check-spelling/wiki/Configuration#dictionary)
-[allow.txt](allow.txt) | Add words to the dictionary | one word per line (only letters and `'`s allowed) | [allow](https://github.com/check-spelling/check-spelling/wiki/Configuration#allow)
-[reject.txt](reject.txt) | Remove words from the dictionary (after allow) | grep pattern matching whole dictionary words | [reject](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-reject)
-[excludes.txt](excludes.txt) | Files to ignore entirely | perl regular expression | [excludes](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-excludes)
-[only.txt](only.txt) | Only check matching files (applied after excludes) | perl regular expression | [only](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-only)
-[patterns.txt](patterns.txt) | Patterns to ignore from checked lines | perl regular expression (order matters, first match wins) | [patterns](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-patterns)
-[candidate.patterns](candidate.patterns) | Patterns that might be worth adding to [patterns.txt](patterns.txt) | perl regular expression with optional comment block introductions (all matches will be suggested) | [candidates](https://github.com/check-spelling/check-spelling/wiki/Feature:-Suggest-patterns)
-[line_forbidden.patterns](line_forbidden.patterns) | Patterns to flag in checked lines | perl regular expression (order matters, first match wins) | [patterns](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-patterns)
-[expect.txt](expect.txt) | Expected words that aren't in the dictionary | one word per line (sorted, alphabetically) | [expect](https://github.com/check-spelling/check-spelling/wiki/Configuration#expect)
-[advice.md](advice.md) | Supplement for GitHub comment when unrecognized words are found | GitHub Markdown | [advice](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-advice)
+| File                                               | Purpose                                                                          | Format                                                                                            | Info                                                                                                 |
+| -------------------------------------------------- | -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
+| [dictionary.txt](dictionary.txt)                   | Replacement dictionary (creating this file will override the default dictionary) | one word per line                                                                                 | [dictionary](https://github.com/check-spelling/check-spelling/wiki/Configuration#dictionary)         |
+| [allow.txt](allow.txt)                             | Add words to the dictionary                                                      | one word per line (only letters and `'`s allowed)                                                 | [allow](https://github.com/check-spelling/check-spelling/wiki/Configuration#allow)                   |
+| [reject.txt](reject.txt)                           | Remove words from the dictionary (after allow)                                   | grep pattern matching whole dictionary words                                                      | [reject](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-reject)     |
+| [excludes.txt](excludes.txt)                       | Files to ignore entirely                                                         | perl regular expression                                                                           | [excludes](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-excludes) |
+| [only.txt](only.txt)                               | Only check matching files (applied after excludes)                               | perl regular expression                                                                           | [only](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-only)         |
+| [patterns.txt](patterns.txt)                       | Patterns to ignore from checked lines                                            | perl regular expression (order matters, first match wins)                                         | [patterns](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-patterns) |
+| [candidate.patterns](candidate.patterns)           | Patterns that might be worth adding to [patterns.txt](patterns.txt)              | perl regular expression with optional comment block introductions (all matches will be suggested) | [candidates](https://github.com/check-spelling/check-spelling/wiki/Feature:-Suggest-patterns)        |
+| [line_forbidden.patterns](line_forbidden.patterns) | Patterns to flag in checked lines                                                | perl regular expression (order matters, first match wins)                                         | [patterns](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-patterns) |
+| [expect.txt](expect.txt)                           | Expected words that aren't in the dictionary                                     | one word per line (sorted, alphabetically)                                                        | [expect](https://github.com/check-spelling/check-spelling/wiki/Configuration#expect)                 |
+| [advice.md](advice.md)                             | Supplement for GitHub comment when unrecognized words are found                  | GitHub Markdown                                                                                   | [advice](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-advice)     |
 
 Note: you can replace any of these files with a directory by the same name (minus the suffix)
 and then include multiple files inside that directory (with that suffix) to merge multiple files together.

.github/actions/spelling/advice.md

@@ -2,30 +2,27 @@
 <details><summary>If the flagged items are :exploding_head: false positives</summary>
 
 If items relate to a ...
-* binary file (or some other file you wouldn't want to check at all).
+
+- binary file (or some other file you wouldn't want to check at all).
 
   Please add a file path to the `excludes.txt` file matching the containing file.
 
-  File paths are Perl 5 Regular Expressions - you can [test](
-https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your files.
+  File paths are Perl 5 Regular Expressions - you can [test](https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your files.
 
-  `^` refers to the file's path from the root of the repository, so `^README\.md$` would exclude [README.md](
-../tree/HEAD/README.md) (on whichever branch you're using).
+  `^` refers to the file's path from the root of the repository, so `^README\.md$` would exclude [README.md](../tree/HEAD/README.md) (on whichever branch you're using).
 
-* well-formed pattern.
+- well-formed pattern.
 
-  If you can write a [pattern](
-https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns
-) that would match it,
+  If you can write a [pattern](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns) that would match it,
   try adding it to the `patterns.txt` file.
 
-  Patterns are Perl 5 Regular Expressions - you can [test](
-https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your lines.
+  Patterns are Perl 5 Regular Expressions - you can [test](https://www.regexplanet.com/advanced/perl/) yours before committing to verify it will match your lines.
 
   Note that patterns can't match multiline strings.
 
 </details>
 
 <!-- adoption information-->
+
 :steam_locomotive: If you're seeing this message and your PR is from a branch that doesn't have check-spelling,
 please merge to your PR's base branch to get the version configured for your repository.

.github/actions/spelling/allow.txt

@@ -3,3 +3,34 @@ https
 ssh
 ubuntu
 workarounds
+rjack
+msgbox
+xeact
+ABee
+tencent
+maintnotifications
+azurediamond
+cooldown
+verifyfcrdns
+Spintax
+spintax
+clampip
+pseudoprofound
+reimagining
+iocaine
+admins
+fout
+iplist
+NArg
+blocklists
+rififi
+prolocation
+Prolocation
+Necron
+Stargate
+FFXIV
+uvensys
+de
+resourced
+envoyproxy
+unipromos

.github/actions/spelling/excludes.txt

@@ -87,8 +87,14 @@
 ^docs/docs/user/known-instances.md$
 ^docs/manifest/.*$
 ^docs/static/\.nojekyll$
+^internal/glob/glob_test.go$
+^internal/honeypot/naive/affirmations\.txt$
+^internal/honeypot/naive/spintext\.txt$
+^internal/honeypot/naive/titles\.txt$
+^lib/config/testdata/bad/unparseable\.json$
+^lib/localization/.*_test.go$
+^lib/localization/locales/.*\.json$
 ^lib/policy/config/testdata/bad/unparseable\.json$
+^test/.*$
 ignore$
 robots.txt
-^lib/localization/locales/.*\.json$
-^lib/localization/.*_test.go$

.github/actions/spelling/expect.txt

@@ -1,14 +1,21 @@
 acs
-aeacus
+Actorified
+actorifiedstore
+actorify
+agentic
 Aibrew
+alibaba
 alrest
 amazonbot
+anexia
 anthro
 anubis
 anubistest
-apk
+apnic
+APNICRANDNETAU
 Applebot
 archlinux
+arpa
 asnc
 asnchecker
 asns
@@ -19,18 +26,21 @@ badregexes
 bbolt
 bdba
 berr
+bezier
 bingbot
 Bitcoin
 bitrate
-blogging
 Bluesky
 blueskybot
 boi
+Bokm
 botnet
 botstopper
 BPort
 Brightbot
 broked
+buildah
+byteslice
 Bytespider
 cachebuster
 cachediptoasn
@@ -53,23 +63,27 @@ checkresult
 chibi
 cidranger
 ckie
-ckies
+CLAUDE
 cloudflare
+cloudsolutions
 Codespaces
 confd
-connnection
 containerbuild
+containerregistry
 coreutils
 Cotoyogi
-CRDs
 Cromite
 crt
 Cscript
 daemonizing
+databento
+dayjob
+dco
 DDOS
 Debian
 debrpm
 decaymap
+devcontainers
 Diffbot
 discordapp
 discordbot
@@ -77,11 +91,13 @@ distros
 dnf
 dnsbl
 dnserr
+DNSTTL
 domainhere
 dracula
 dronebl
 droneblresponse
 dropin
+dsilence
 duckduckbot
 eerror
 ellenjoe
@@ -97,14 +113,21 @@ externalfetcher
 extldflags
 facebookgo
 Factset
+fahedouch
 fastcgi
+FCr
+fcrdns
 fediverse
 ffprobe
+FFXIV
+fhdr
+financials
 finfos
 Firecrawl
 flagenv
 Fordola
 forgejo
+forwardauth
 fsys
 fullchain
 gaissmai
@@ -112,53 +135,71 @@ Galvus
 geoip
 geoipchecker
 gha
+GHSA
+Ghz
 gipc
 gitea
+GLM
 godotenv
+goimports
 goland
 gomod
 goodbot
 googlebot
+gopsutil
 govulncheck
 goyaml
 GPG
 GPT
 gptbot
+Graphene
 grpcprom
 grw
+gzw
 Hashcash
 hashrate
+hdr
 headermap
 healthcheck
+healthz
 hec
+helpdesk
+Hetzner
 hmc
+homelab
 hostable
+HSTS
 htmlc
 htmx
 httpdebug
-Huawei
+huawei
 hypertext
 iaskspider
+iaso
 iat
 ifm
 Imagesift
 imgproxy
 impressum
+inbox
+ingressed
 inp
+internets
 IPTo
 iptoasn
+isp
 iss
 isset
 ivh
 Jenomis
 JGit
+jhjj
 joho
 journalctl
 jshelter
 JWTs
 kagi
 kagibot
-keikaku
 Keyfunc
 keypair
 KHTML
@@ -168,17 +209,18 @@ lcj
 ldflags
 letsencrypt
 Lexentale
+lfc
 lgbt
 licend
 licstart
 lightpanda
-LIMSA
+limsa
 Linting
-linuxbrew
+listor
 LLU
 loadbalancer
 lol
-LOMINSA
+lominsa
 maintainership
 malware
 mcr
@@ -186,32 +228,46 @@ memes
 metarefresh
 metrix
 mimi
-minica
+Minfilia
 mistralai
+mnt
 Mojeek
 mojeekbot
 mozilla
+myclient
+mymaster
+mypass
+myuser
 nbf
+Necron
+nepeat
 netsurf
 nginx
 nicksnyder
+nikandfor
 nobots
 NONINFRINGEMENT
 nosleep
+nullglob
+oci
 OCOB
-ogtags
+ogtag
+oklch
 omgili
 omgilibot
 openai
+opendns
 opengraph
 openrc
 oswald
 pag
+pagegen
 palemoon
 Pangu
 parseable
 passthrough
 Patreon
+perplexitybot
 pgrep
 phrik
 pidfile
@@ -220,12 +276,15 @@ pipefail
 pki
 podkova
 podman
+Postgre
+poststart
 prebaked
 privkey
 promauto
 promhttp
 proofofwork
 publicsuffix
+purejs
 pwcmd
 pwuser
 qualys
@@ -234,43 +293,52 @@ qwantbot
 rac
 rawler
 rcvar
-rdb
 redhat
 redir
 redirectscheme
 refactors
-relayd
+remoteip
 reputational
-reqmeta
+Rhul
 risc
 ruleset
 runlevels
 RUnlock
 runtimedir
+runtimedirectory
+Ryzen
 sas
 sasl
+screenshots
 searchbot
 searx
 sebest
 secretplans
-selfsigned
 Semrush
 Seo
 setsebool
 shellcheck
+shirou
+shoneypot
+shopt
 Sidetrade
 simprint
 sitemap
 sls
 sni
+snipster
 Spambot
+spammer
 sparkline
 spyderbot
+srcip
 srv
 stackoverflow
+Stargate
 startprecmd
 stoppostcmd
 storetest
+strcmp
 subgrid
 subr
 subrequest
@@ -278,10 +346,12 @@ SVCNAME
 tagline
 tarballs
 tarrif
+taviso
 tbn
 tbr
 techaro
 techarohq
+telegrambot
 templ
 templruntime
 testarea
@@ -290,15 +360,17 @@ thoth
 thothmock
 Tik
 Timpibot
+TLog
 traefik
+trunc
+txn
 uberspace
 Unbreak
 unbreakdocker
 unifiedjs
-unixhttpd
 unmarshal
 unparseable
-uuidgen
+updown
 uvx
 UXP
 valkey
@@ -306,22 +378,27 @@ Varis
 Velen
 vendored
 vhosts
-videotest
-waitloop
+vkbot
+VKE
+vnd
+VPS
+Vultr
+WAIFU
 weblate
 webmaster
 webpage
 websecure
 websites
 Webzio
+whois
 wildbase
 withthothmock
+wolfbeast
 wordpress
-Workaround
+workaround
 workdir
 wpbot
-xcaddy
-Xeact
+XCircle
 xeiaso
 xeserv
 xesite
@@ -330,14 +407,18 @@ xff
 XForwarded
 XNG
 XOB
+XOriginal
 XReal
+Y'shtola
 yae
 YAMLTo
+Yda
 yeet
 yeetfile
 yourdomain
-yoursite
+yyz
 Zenos
 zizmor
 zombocom
 zos
+zst

.github/actions/spelling/patterns.txt

@@ -132,3 +132,7 @@ go install(?:\s+[a-z]+\.[-@\w/.]+)+
 # hit-count: 1 file-count: 1
 # microsoft
 \b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*
+
+# hit-count: 1 file-count: 1
+# data url
+\bdata:[-a-zA-Z=;:/0-9+]*,\S*

.github/dependabot.yml

@@ -8,6 +8,8 @@ updates:
       github-actions:
         patterns:
           - "*"
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: gomod
     directory: /
@@ -17,6 +19,8 @@ updates:
       gomod:
         patterns:
           - "*"
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: npm
     directory: /
@@ -26,3 +30,5 @@ updates:
       npm:
         patterns:
           - "*"
+    cooldown:
+      default-days: 7

.github/workflows/asset-verification.yml

@@ -0,0 +1,72 @@
+name: Asset Build Verification
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+permissions:
+  contents: read
+
+jobs:
+  asset_verification:
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: build essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
+
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "1.25.7"
+
+      - name: install node deps
+        run: |
+          npm ci
+
+      - name: Check for uncommitted changes before asset build
+        id: check-changes-before
+        run: |
+          if [[ -n $(git status --porcelain) ]]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Fail if there are uncommitted changes before build
+        if: steps.check-changes-before.outputs.has_changes == 'true'
+        run: |
+          echo "There are uncommitted changes before running npm run assets"
+          git status
+          exit 1
+
+      - name: Run asset build
+        run: |
+          npm run assets
+
+      - name: Check for uncommitted changes after asset build
+        id: check-changes-after
+        run: |
+          if [[ -n $(git status --porcelain) ]]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Fail if assets generated changes
+        if: steps.check-changes-after.outputs.has_changes == 'true'
+        run: |
+          echo "npm run assets generated uncommitted changes. This indicates the repository has outdated generated files."
+          echo "Please run 'npm run assets' locally and commit the changes."
+          git status
+          git diff
+          exit 1

.github/workflows/dco-check.yaml

@@ -0,0 +1,9 @@
+name: DCO Check
+
+on: [pull_request]
+
+jobs:
+  dco_check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: tisonkun/actions-dco@f1024cd563550b5632e754df11b7d30b73be54a5 # v1.1

.github/workflows/docker-pr.yml

@@ -2,7 +2,7 @@ name: Docker image builds (pull requests)
 
 on:
   pull_request:
-    branches: [ "main" ]
+    branches: ["main"]
 
 env:
   DOCKER_METADATA_SET_OUTPUT_ENV: "true"
@@ -15,39 +15,29 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-tags: true
           fetch-depth: 0
           persist-credentials: false
 
-      - name: Set up Homebrew
-        uses: Homebrew/actions/setup-homebrew@main
-
-      - name: Setup Homebrew cellar cache
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-        with:
-          path: |
-            /home/linuxbrew/.linuxbrew/Cellar
-            /home/linuxbrew/.linuxbrew/bin
-            /home/linuxbrew/.linuxbrew/etc
-            /home/linuxbrew/.linuxbrew/include
-            /home/linuxbrew/.linuxbrew/lib
-            /home/linuxbrew/.linuxbrew/opt
-            /home/linuxbrew/.linuxbrew/sbin
-            /home/linuxbrew/.linuxbrew/share
-            /home/linuxbrew/.linuxbrew/var
-          key: ${{ runner.os }}-go-homebrew-cellar-${{ hashFiles('go.sum') }}
-          restore-keys: |
-            ${{ runner.os }}-go-homebrew-cellar-
-
-      - name: Install Brew dependencies
+      - name: build essential
         run: |
-          brew bundle
+          sudo apt-get update
+          sudo apt-get install -y build-essential
+
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
+
+      - uses: ko-build/setup-ko@d006021bd0c28d1ce33a07e7943d48b079944c8d # v0.9
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
           images: ghcr.io/${{ github.repository }}
 

.github/workflows/docker.yml

@@ -21,42 +21,32 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-tags: true
           fetch-depth: 0
           persist-credentials: false
 
+      - name: build essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
+
       - name: Set lowercase image name
         run: |
           echo "IMAGE=ghcr.io/${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
 
-      - name: Set up Homebrew
-        uses: Homebrew/actions/setup-homebrew@main
-
-      - name: Setup Homebrew cellar cache
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
-          path: |
-            /home/linuxbrew/.linuxbrew/Cellar
-            /home/linuxbrew/.linuxbrew/bin
-            /home/linuxbrew/.linuxbrew/etc
-            /home/linuxbrew/.linuxbrew/include
-            /home/linuxbrew/.linuxbrew/lib
-            /home/linuxbrew/.linuxbrew/opt
-            /home/linuxbrew/.linuxbrew/sbin
-            /home/linuxbrew/.linuxbrew/share
-            /home/linuxbrew/.linuxbrew/var
-          key: ${{ runner.os }}-go-homebrew-cellar-${{ hashFiles('go.sum') }}
-          restore-keys: |
-            ${{ runner.os }}-go-homebrew-cellar-
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
 
-      - name: Install Brew dependencies
-        run: |
-          brew bundle
+      - uses: ko-build/setup-ko@d006021bd0c28d1ce33a07e7943d48b079944c8d # v0.9
 
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
@@ -64,7 +54,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
           images: ${{ env.IMAGE }}
 
@@ -78,7 +68,7 @@ jobs:
           SLOG_LEVEL: debug
 
       - name: Generate artifact attestation
-        uses: actions/attest-build-provenance@e8998f949152b193b063cb0ec769d69d929409be # v2.4.0
+        uses: actions/attest-build-provenance@a2bbfa25375fe432b6a289bc6b6cd05ecd0c4c32 # v4.1.0
         with:
           subject-name: ${{ env.IMAGE }}
           subject-digest: ${{ steps.build.outputs.digest }}

.github/workflows/docs-deploy.yml

@@ -17,15 +17,15 @@ jobs:
     runs-on: ubuntu-24.04
 
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
         with:
           registry: ghcr.io
           username: techarohq
@@ -33,13 +33,16 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
           images: ghcr.io/techarohq/anubis/docs
+          tags: |
+            type=sha,enable=true,priority=100,prefix=,suffix=,format=long
+            main
 
       - name: Build and push
         id: build
-        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
         with:
           context: ./docs
           cache-to: type=gha
@@ -49,15 +52,15 @@ jobs:
           platforms: linux/amd64
           push: true
 
-      - name: Apply k8s manifests to aeacus
-        uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
+      - name: Apply k8s manifests to limsa lominsa
+        uses: actions-hub/kubectl@5ada4e2c02eacc03978c2437e95c8b0f979a9619 # v1.35.2
         env:
           KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
         with:
           args: apply -k docs/manifest
 
-      - name: Apply k8s manifests to aeacus
-        uses: actions-hub/kubectl@d50394b7d704525f93faefce1e65a6329ff67271 # v1.33.2
+      - name: Apply k8s manifests to limsa lominsa
+        uses: actions-hub/kubectl@5ada4e2c02eacc03978c2437e95c8b0f979a9619 # v1.35.2
         env:
           KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
         with:

.github/workflows/docs-test.yml

@@ -2,7 +2,7 @@ name: Docs test build
 
 on:
   pull_request:
-    branches: [ "main" ]
+    branches: ["main"]
 
 permissions:
   contents: read
@@ -13,22 +13,25 @@ jobs:
     runs-on: ubuntu-24.04
 
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v6.0.0
         with:
-          images: ghcr.io/${{ github.repository }}/docs
+          images: ghcr.io/techarohq/anubis/docs
+          tags: |
+            type=sha,enable=true,priority=100,prefix=,suffix=,format=long
+            main
 
       - name: Build and push
         id: build
-        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
         with:
           context: ./docs
           cache-to: type=gha

.github/workflows/go-mod-tidy-check.yml

@@ -0,0 +1,76 @@
+name: Go Mod Tidy Check
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+permissions:
+  contents: read
+
+jobs:
+  go_mod_tidy_check:
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
+
+      - name: Check go.mod and go.sum in main directory
+        run: |
+          # Store original file state
+          cp go.mod go.mod.orig
+          cp go.sum go.sum.orig
+
+          # Run go mod tidy
+          go mod tidy
+
+          # Check if files changed
+          if ! diff -q go.mod.orig go.mod > /dev/null 2>&1; then
+            echo "ERROR: go.mod in main directory has changed after running 'go mod tidy'"
+            echo "Please run 'go mod tidy' locally and commit the changes"
+            diff go.mod.orig go.mod
+            exit 1
+          fi
+
+          if ! diff -q go.sum.orig go.sum > /dev/null 2>&1; then
+            echo "ERROR: go.sum in main directory has changed after running 'go mod tidy'"
+            echo "Please run 'go mod tidy' locally and commit the changes"
+            diff go.sum.orig go.sum
+            exit 1
+          fi
+
+          echo "SUCCESS: go.mod and go.sum in main directory are tidy"
+
+      - name: Check go.mod and go.sum in test directory
+        run: |
+          cd test
+
+          # Store original file state
+          cp go.mod go.mod.orig
+          cp go.sum go.sum.orig
+
+          # Run go mod tidy
+          go mod tidy
+
+          # Check if files changed
+          if ! diff -q go.mod.orig go.mod > /dev/null 2>&1; then
+            echo "ERROR: go.mod in test directory has changed after running 'go mod tidy'"
+            echo "Please run 'go mod tidy' locally and commit the changes"
+            diff go.mod.orig go.mod
+            exit 1
+          fi
+
+          if ! diff -q go.sum.orig go.sum > /dev/null 2>&1; then
+            echo "ERROR: go.sum in test directory has changed after running 'go mod tidy'"
+            echo "Please run 'go mod tidy' locally and commit the changes"
+            diff go.sum.orig go.sum
+            exit 1
+          fi
+
+          echo "SUCCESS: go.mod and go.sum in test directory are tidy"

.github/workflows/go.yml

@@ -2,9 +2,9 @@ name: Go
 
 on:
   push:
-    branches: [ "main" ]
+    branches: ["main"]
   pull_request:
-    branches: [ "main" ]
+    branches: ["main"]
 
 permissions:
   contents: read
@@ -15,77 +15,50 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-      with:
-        persist-credentials: false
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
-    - name: build essential
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y build-essential
+      - name: build essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
 
-    - name: Set up Homebrew
-      uses: Homebrew/actions/setup-homebrew@main
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
 
-    - name: Setup Homebrew cellar cache
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          /home/linuxbrew/.linuxbrew/Cellar
-          /home/linuxbrew/.linuxbrew/bin
-          /home/linuxbrew/.linuxbrew/etc
-          /home/linuxbrew/.linuxbrew/include
-          /home/linuxbrew/.linuxbrew/lib
-          /home/linuxbrew/.linuxbrew/opt
-          /home/linuxbrew/.linuxbrew/sbin
-          /home/linuxbrew/.linuxbrew/share
-          /home/linuxbrew/.linuxbrew/var
-        key: ${{ runner.os }}-go-homebrew-cellar-${{ hashFiles('go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-go-homebrew-cellar-
+      - name: Cache playwright binaries
+        uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+        id: playwright-cache
+        with:
+          path: |
+            ~/.cache/ms-playwright
+          key: ${{ runner.os }}-playwright-${{ hashFiles('**/go.sum') }}
 
-    - name: Install Brew dependencies
-      run: |
-        brew bundle
+      - name: install node deps
+        run: |
+          npm ci
 
-    - name: Setup Golang caches
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          ~/.cache/go-build
-          ~/go/pkg/mod
-        key: ${{ runner.os }}-golang-${{ hashFiles('**/go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-golang-
+      - name: install playwright browsers
+        run: |
+          npx --no-install playwright@1.52.0 install --with-deps
+          npx --no-install playwright@1.52.0 run-server --port 9001 &
 
-    - name: Cache playwright binaries
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      id: playwright-cache
-      with:
-        path: |
-          ~/.cache/ms-playwright
-        key: ${{ runner.os }}-playwright-${{ hashFiles('**/go.sum') }}
+      - name: Build
+        run: npm run build
 
-    - name: install node deps
-      run: |
-        npm ci
+      - name: Test
+        run: npm run test
 
-    - name: install playwright browsers
-      run: |
-        npx --no-install playwright@1.52.0 install --with-deps
-        npx --no-install playwright@1.52.0 run-server --port 9001 &
+      - name: Lint with staticcheck
+        uses: dominikh/staticcheck-action@9716614d4101e79b4340dd97b10e54d68234e431 # v1.4.1
+        with:
+          version: "latest"
 
-    - name: Build
-      run: npm run build
-
-    - name: Test
-      run: npm run test
-
-    - name: Lint with staticcheck
-      uses: dominikh/staticcheck-action@fe1dd0c3658873b46f8c9bb3291096a617310ca6 # v1.3.1
-      with:
-        version: "latest"
-
-    - name: Govulncheck
-      run: |
-        go tool govulncheck ./...
+      - name: Govulncheck
+        run: |
+          go tool govulncheck ./... ||:

.github/workflows/lint-pr-title.yaml

@@ -0,0 +1,19 @@
+name: "Lint PR"
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - edited
+      - synchronize
+
+jobs:
+  lint_pr_title:
+    name: Validate PR title
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    steps:
+      - uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/package-builds-stable.yml

@@ -1,8 +1,9 @@
 name: Package builds (stable)
 
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+  # release:
+  #   types: [published]
 
 permissions:
   contents: write
@@ -13,67 +14,40 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-      with:
-        persist-credentials: false
-        fetch-tags: true
-        fetch-depth: 0
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+          fetch-tags: true
+          fetch-depth: 0
 
-    - name: build essential
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y build-essential
+      - name: build essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
 
-    - name: Set up Homebrew
-      uses: Homebrew/actions/setup-homebrew@main
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
 
-    - name: Setup Homebrew cellar cache
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          /home/linuxbrew/.linuxbrew/Cellar
-          /home/linuxbrew/.linuxbrew/bin
-          /home/linuxbrew/.linuxbrew/etc
-          /home/linuxbrew/.linuxbrew/include
-          /home/linuxbrew/.linuxbrew/lib
-          /home/linuxbrew/.linuxbrew/opt
-          /home/linuxbrew/.linuxbrew/sbin
-          /home/linuxbrew/.linuxbrew/share
-          /home/linuxbrew/.linuxbrew/var
-        key: ${{ runner.os }}-go-homebrew-cellar-${{ hashFiles('go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-go-homebrew-cellar-
+      - name: install node deps
+        run: |
+          npm ci
 
-    - name: Install Brew dependencies
-      run: |
-        brew bundle
+      - name: Build Packages
+        run: |
+          go tool yeet
 
-    - name: Setup Golang caches
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          ~/.cache/go-build
-          ~/go/pkg/mod
-        key: ${{ runner.os }}-golang-${{ hashFiles('**/go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-golang-
-
-    - name: install node deps
-      run: |
-        npm ci
-
-    - name: Build Packages
-      run: |
-        go tool yeet
-
-    - name: Upload released artifacts
-      env:
-        GITHUB_TOKEN: ${{ github.TOKEN }}
-        RELEASE_VERSION: ${{github.event.release.tag_name}}
-      shell: bash
-      run: |
-        RELEASE="${RELEASE_VERSION}"
-        cd var
-        for file in *; do
-          gh release upload $RELEASE $file
-        done
+      - name: Upload released artifacts
+        env:
+          GITHUB_TOKEN: ${{ github.TOKEN }}
+          RELEASE_VERSION: ${{github.event.release.tag_name}}
+        shell: bash
+        run: |
+          RELEASE="${RELEASE_VERSION}"
+          cd var
+          for file in *; do
+            gh release upload $RELEASE $file
+          done

.github/workflows/package-builds-unstable.yml

@@ -2,9 +2,9 @@ name: Package builds (unstable)
 
 on:
   push:
-    branches: [ "main" ]
+    branches: ["main"]
   pull_request:
-    branches: [ "main" ]
+    branches: ["main"]
 
 permissions:
   contents: read
@@ -15,60 +15,33 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-      with:
-        persist-credentials: false
-        fetch-tags: true
-        fetch-depth: 0
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+          fetch-tags: true
+          fetch-depth: 0
 
-    - name: build essential
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y build-essential
+      - name: build essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
 
-    - name: Set up Homebrew
-      uses: Homebrew/actions/setup-homebrew@main
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
 
-    - name: Setup Homebrew cellar cache
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          /home/linuxbrew/.linuxbrew/Cellar
-          /home/linuxbrew/.linuxbrew/bin
-          /home/linuxbrew/.linuxbrew/etc
-          /home/linuxbrew/.linuxbrew/include
-          /home/linuxbrew/.linuxbrew/lib
-          /home/linuxbrew/.linuxbrew/opt
-          /home/linuxbrew/.linuxbrew/sbin
-          /home/linuxbrew/.linuxbrew/share
-          /home/linuxbrew/.linuxbrew/var
-        key: ${{ runner.os }}-go-homebrew-cellar-${{ hashFiles('go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-go-homebrew-cellar-
+      - name: install node deps
+        run: |
+          npm ci
 
-    - name: Install Brew dependencies
-      run: |
-        brew bundle
+      - name: Build Packages
+        run: |
+          go tool yeet
 
-    - name: Setup Golang caches
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-      with:
-        path: |
-          ~/.cache/go-build
-          ~/go/pkg/mod
-        key: ${{ runner.os }}-golang-${{ hashFiles('**/go.sum') }}
-        restore-keys: |
-          ${{ runner.os }}-golang-
-
-    - name: install node deps
-      run: |
-        npm ci
-
-    - name: Build Packages
-      run: |
-        go tool yeet
-
-    - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
-      with:
-        name: packages
-        path: var/*
+      - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: packages
+          path: var/*

.github/workflows/smoke-tests.yml

@@ -0,0 +1,64 @@
+name: Smoke tests
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    branches: ["main"]
+
+permissions:
+  contents: read
+
+jobs:
+  smoke-test:
+    strategy:
+      matrix:
+        test:
+          - default-config-macro
+          - docker-registry
+          - double_slash
+          - forced-language
+          - git-clone
+          - git-push
+          - healthcheck
+          - i18n
+          - log-file
+          - nginx
+          - palemoon/amd64
+          #- palemoon/i386
+          - robots_txt
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: "24.11.0"
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
+
+      - uses: ko-build/setup-ko@d006021bd0c28d1ce33a07e7943d48b079944c8d # v0.9
+
+      - name: Install utils
+        run: |
+          go install ./utils/cmd/...
+
+      - name: Run test
+        run: |
+          cd test/${{ matrix.test }}
+          backoff-retry --try-count 10 ./test.sh
+
+      - name: Sanitize artifact name
+        if: always()
+        run: echo "ARTIFACT_NAME=${{ matrix.test }}" | sed 's|/|-|g' >> $GITHUB_ENV
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
+        if: always()
+        with:
+          name: ${{ env.ARTIFACT_NAME }}
+          path: test/${{ matrix.test }}/var

.github/workflows/spelling.yml

@@ -59,16 +59,16 @@ name: Check Spelling
 on:
   push:
     branches:
-      - '**'
+      - "**"
     tags-ignore:
-      - '**'
+      - "**"
   pull_request:
     branches:
-      - '**'
+      - "**"
     types:
-      - 'opened'
-      - 'reopened'
-      - 'synchronize'
+      - "opened"
+      - "reopened"
+      - "synchronize"
 
 jobs:
   spelling:

.github/workflows/ssh-ci-runner-cron.yml

@@ -18,19 +18,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-tags: true
           fetch-depth: 0
           persist-credentials: false
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
       - name: Build and push
         run: |
           cd ./test/ssh-ci

.github/workflows/ssh-ci.yml

@@ -12,26 +12,35 @@ permissions:
 jobs:
   ssh:
     if: github.repository == 'TecharoHQ/anubis'
-    runs-on: ubuntu-24.04
+    #runs-on: alrest-techarohq
+    runs-on: ubuntu-latest
     strategy:
       matrix:
         host:
-          - ubuntu@riscv64.techaro.lol
-          - ci@ppc64le.techaro.lol
+          - riscv64
+          - ppc64le
+          #- aarch64-4k
+          #- aarch64-16k
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-tags: true
           fetch-depth: 0
           persist-credentials: false
+
       - name: Install CI target SSH key
-        uses: shimataro/ssh-key-action@d4fffb50872869abe2d9a9098a6d9c5aa7d16be4 # v2.7.0
+        uses: shimataro/ssh-key-action@6b84f2e793b32fa0b03a379cadadec75cc539391 # v2.8.0
         with:
           key: ${{ secrets.CI_SSH_KEY }}
           name: id_rsa
           known_hosts: ${{ secrets.CI_SSH_KNOWN_HOSTS }}
+
+      - uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version: "stable"
+
       - name: Run CI
-        run: bash test/ssh-ci/rigging.sh ${{ matrix.host }}
+        run: go run ./utils/cmd/backoff-retry bash test/ssh-ci/rigging.sh ${{ matrix.host }}
         env:
           GITHUB_RUN_ID: ${{ github.run_id }}

.github/workflows/zizmor.yml

@@ -1,12 +1,12 @@
 name: zizmor
 
 on:
-    push:
-      paths:
-        - '.github/workflows/*.ya?ml'
-    pull_request:
-      paths:
-        - '.github/workflows/*.ya?ml'
+  push:
+    paths:
+      - ".github/workflows/*.ya?ml"
+  pull_request:
+    paths:
+      - ".github/workflows/*.ya?ml"
 
 jobs:
   zizmor:
@@ -16,20 +16,20 @@ jobs:
       security-events: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@bd01e18f51369d5a26f1651c3cb451d3417e3bba # v6.3.1
+        uses: astral-sh/setup-uv@eac588ad8def6316056a12d4907a9d4d84ff7a3b # v7.3.0
 
       - name: Run zizmor 🌈
-        run: uvx zizmor --format sarif . > results.sarif 
+        run: uvx zizmor --format sarif . > results.sarif
         env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} 
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@39edc492dbe16b1465b0cafca41432d857bdb31a # v3.29.1
+        uses: github/codeql-action/upload-sarif@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
         with:
           sarif_file: results.sarif
           category: zizmor

.husky/commit-msg

@@ -0,0 +1,8 @@
+npx --no-install commitlint --edit "$1"
+
+# Check if commit message contains Signed-off-by line
+if ! grep -q "^Signed-off-by:" "$1"; then
+	echo "Commit message must contain a 'Signed-off-by:' line."
+	echo "Please use 'git commit --signoff' or add a Signed-off-by line to your commit message."
+	exit 1
+fi

.husky/pre-commit

@@ -0,0 +1,2 @@
+npm run lint
+npm run test

.ko.yaml

@@ -1,13 +1,13 @@
 defaultBaseImage: cgr.dev/chainguard/static
 defaultPlatforms:
-- linux/arm64
-- linux/amd64
-- linux/arm/v7
+  - linux/arm64
+  - linux/amd64
+  - linux/arm/v7
 
 builds:
-- id: anubis
-  main: ./cmd/anubis
-  ldflags:
-  - -s -w
-  - -extldflags "-static"
-  - -X github.com/TecharoHQ/anubis.Version={{.Env.VERSION}}
+  - id: anubis
+    main: ./cmd/anubis
+    ldflags:
+      - -s -w
+      - -extldflags "-static"
+      - -X github.com/TecharoHQ/anubis.Version={{.Env.VERSION}}

.prettierignore

@@ -0,0 +1,4 @@
+lib/config/testdata/bad/*
+*.inc
+AGENTS.md
+CLAUDE.md

.vscode/extensions.json

@@ -5,6 +5,7 @@
     "golang.go",
     "unifiedjs.vscode-mdx",
     "a-h.templ",
-    "redhat.vscode-yaml"
+    "redhat.vscode-yaml",
+    "streetsidesoftware.code-spell-checker"
   ]
-}
+}

.vscode/launch.json

@@ -24,4 +24,4 @@
       "type": "node-terminal"
     }
   ]
-}
+}

AGENTS.md

@@ -0,0 +1,75 @@
+# Agent instructions
+
+Primary agent documentation is in `CONTRIBUTING.md`. You MUST read this file before proceeding.
+
+## Useful Commands
+
+```shell
+npm ci           # install node dependencies
+npm run assets   # build JS/CSS (required before any Go build/test)
+npm run build    # assets + go build -> ./var/anubis
+npm run dev      # assets + run locally with --use-remote-address
+```
+
+## Testing
+
+```shell
+npm run test
+```
+
+## Linting
+
+```shell
+go vet ./...
+go tool staticcheck ./...
+go tool govulncheck ./...
+```
+
+## Commit Messages
+
+Commit messages follow the [**Conventional Commits**](https://www.conventionalcommits.org/en/v1.0.0/) format:
+
+```text
+<type>[optional scope]: <description>
+
+[optional body]
+
+[optional footer(s)]
+```
+
+**Types**: `feat`, `fix`, `docs`, `style`, `refactor`, `perf`, `test`, `build`, `ci`, `chore`, `revert`
+
+- Add `!` after type/scope for breaking changes or include `BREAKING CHANGE:` in the footer.
+- Keep descriptions concise, imperative, lowercase, and without a trailing period.
+- Reference issues/PRs in the footer when applicable.
+- **ALL git commits MUST be made with `--signoff`.** This is mandatory.
+
+### Attribution Requirements
+
+AI agents must disclose what tool and model they are using in the "Assisted-by" commit footer:
+
+```text
+Assisted-by: [Model Name] via [Tool Name]
+```
+
+Example:
+
+```text
+Assisted-by: GLM 4.6 via Claude Code
+```
+
+## PR Checklist
+
+- Add description of changes to `[Unreleased]` in `docs/docs/CHANGELOG.md`.
+- Add test cases for bug fixes and behavior changes.
+- Run integration tests: `npm run test:integration`.
+- All commits must have verified (signed) signatures.
+
+## Key Conventions
+
+- **Security-first**: This is security software. Code reviews are strict. Always add tests for bug fixes. Consider adversarial inputs.
+- **Configuration**: YAML-based policy files. Config structs validate via `Valid() error` methods returning sentinel errors.
+- **Store interface**: `lib/store.Interface` abstracts key-value storage.
+- **Environment variables**: Parsed from flags via `flagenv`. Use `.env` files locally (loaded by `godotenv/autoload`). Never commit `.env` files.
+- **Assets must be built first**: JS/CSS assets are embedded into the Go binary. Always run `npm run assets` before `go test` or `go build`.
+- **CEL expressions**: Policy rules support CEL (Common Expression Language) expressions for advanced matching. See `lib/policy/expressions/`.

CLAUDE.md

@@ -0,0 +1,2 @@
+@AGENTS.md
+@CONTRIBUTING.md

CONTRIBUTING.md

@@ -0,0 +1,144 @@
+# Contributing to Anubis
+
+Anubis is a Web AI Firewall Utility (WAIFU) written in Go. It uses sha256 proof-of-work challenges to protect upstream HTTP resources from scraper bots. This is security software -- correctness matters.
+
+## Build & Run
+
+Prerequisites: Go 1.24+, Node.js (any supported version), esbuild, gzip, zstd, brotli. Install all with `brew bundle` if you are using Homebrew.
+
+```shell
+npm ci           # install node dependencies
+npm run assets   # build JS/CSS (required before any Go build/test)
+npm run build    # assets + go build -> ./var/anubis
+npm run dev      # assets + run locally with --use-remote-address
+```
+
+## Testing
+
+```shell
+# Run all unit tests (assets must be built first)
+npm run test              # or: make test
+
+# Run a single test by name
+go test -run TestClampIP ./internal/
+
+# Run a single test file's package
+go test ./lib/config/
+
+# Run tests with verbose output
+go test -v -run TestBotValid ./lib/config/
+```
+
+### Smoke tests
+
+The `tests` folder contains "smoke tests" that are intended to set up Anubis in production-adjacent settings and testing it against real infrastructure tools. A smoke test is a folder with `test.sh` that sets up infrastructure, validates the behaviour, and then tears it down. Smoke tests are run in GitHub actions with `.github/workflows/smoke-tests.yaml`.
+
+## Linting
+
+```shell
+go vet ./...
+go tool staticcheck ./...
+go tool govulncheck ./...
+```
+
+## Code Generation
+
+The project uses `go generate` for templ templates and stringer. Always run `npm run generate` (or `make assets`) before building or testing. Generated files include:
+
+- `web/*.templ` -> templ-generated Go code
+- `web/static/` -> bundled/minified JS and CSS (with .gz, .zst, .br variants)
+
+## Project Layout
+
+Important folders:
+
+- `cmd/anubis`: Main entrypoint for the project. This is the program that runs on servers.
+- `lib/*`: The core library for Anubis and all of its features. This is internal code that is made public for ease of downstream consumption. No API stability is guaranteed. Use at your own risk.
+- `internal/*`: Actual internal code that is private to the implementation of Anubis. If you need to use a package in this, please copy it out and manually vendor it in your own project.
+- `test/*` Smoke tests (see dedicated section for details).
+- `web`: Frontend HTML templates.
+- `xess`: Frontend CSS framework and build logic.
+
+## Code Style
+
+### Go
+
+This project follows the idioms of the Go standard library. Generally follow the patterns that upstream Go uses, including:
+
+- Prefer packages from the standard library unless there is no other option.
+- Use package import aliases only when package names collide.
+- Use `goimports` to format code. Run with `npm run format`.
+- Use sentinel errors as package-level variables prefixed with `Err` (such as `ErrBotMustHaveName`). Wrap with `fmt.Errorf("package: small message giving context: %w", err)`.
+- Use `log/slog` for structured logging. Pass loggers as arguments to functions. Use `lg.With` to preload with context. Prefer using `slog.Debug` unless you absolutely need to report messages to users, some users have magical thinking about log verbosity.
+- Name PublicFunctionsAndTypes in PascalCase. Name privateFunctionsAndTypes in camelCase.
+- Acronyms stay uppercase (`URL`, `HTTP`, `IP`, `DNS`, etc.)
+- Enumerations should use strong types with validation logic for parsing remote input.
+- Be conservative in what you send but liberal in what you accept.
+- Anything reading configuration values should use both `json` and `yaml` struct tags. Use pointer values for optional configuration values.
+- Use [table-driven tests](https://go.dev/wiki/TableDrivenTests) when writing test code.
+- Use [`t.Helper()`](https://pkg.go.dev/testing#T.Helper) in helper code (setup/teardown scaffolding).
+- Use [`t.Cleanup()`](https://pkg.go.dev/testing#T.Cleanup) to tear down per-test or per-suite scaffolding.
+- Use [`errors.Is`](https://pkg.go.dev/errors#Is) for validating function results against sentinel errors.
+- Prefer same-package tests over black-box tests (`_test` packages).
+
+### JavaScript / TypeScript
+
+- Source lives in `web/js/`. Built with esbuild, bundled and minified.
+- Uses Preact (not React).
+- No linter config. Keep functions small. Use `const` by default.
+
+### Templ Templates
+
+Anubis uses [Templ](https://templ.guide) for generating HTML on the server.
+
+- `.templ` files in `web/` generate Go code. Run `go generate ./...` (or `npm run assets`) after modifying them.
+- Templates receive typed Go parameters. Keep logic in Go, not templates.
+
+## Commit Messages
+
+Commit messages follow the [**Conventional Commits**](https://www.conventionalcommits.org/en/v1.0.0/) format:
+
+```text
+<type>[optional scope]: <description>
+
+[optional body]
+
+[optional footer(s)]
+```
+
+**Types**: `feat`, `fix`, `docs`, `style`, `refactor`, `perf`, `test`, `build`, `ci`, `chore`, `revert`
+
+- Add `!` after type/scope for breaking changes or include `BREAKING CHANGE:` in the footer.
+- Keep descriptions concise, imperative, lowercase, and without a trailing period.
+- Reference issues/PRs in the footer when applicable.
+- **ALL git commits MUST be made with `--signoff`.** This is mandatory.
+
+### Attribution Requirements
+
+AI agents must disclose what tool and model they are using in the "Assisted-by" commit footer:
+
+```text
+Assisted-by: [Model Name] via [Tool Name]
+```
+
+Example:
+
+```text
+Assisted-by: GLM 4.6 via Claude Code
+```
+
+## PR Checklist
+
+- Add description of changes to `[Unreleased]` in `docs/docs/CHANGELOG.md`.
+- Add test cases for bug fixes and behavior changes.
+- Run integration tests: `npm run test:integration`.
+- All commits must have verified (signed) signatures.
+
+## Key Conventions
+
+- **Security-first**: This is security software. Code reviews are strict. Always add tests for bug fixes. Consider adversarial inputs.
+- **Configuration**: YAML-based policy files. Config structs validate via `Valid() error` methods returning sentinel errors.
+- **Store interface**: `lib/store.Interface` abstracts key-value storage.
+- **Environment variables**: Parsed from flags via `flagenv`. Use `.env` files locally (loaded by `godotenv/autoload`). Never commit `.env` files.
+- **Assets must be built first**: JS/CSS assets are embedded into the Go binary. Always run `npm run assets` before `go test` or `go build`.
+- **CEL expressions**: Policy rules support CEL (Common Expression Language) expressions for advanced matching. See `lib/policy/expressions/`.

Makefile

@@ -24,8 +24,7 @@ build: assets
 lint: assets
 	$(GO) vet ./...
 	$(GO) tool staticcheck ./...
-	$(GO) tool govulncheck ./...
-
+	
 prebaked-build:
 	$(GO) build -o ./var/anubis -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/anubis
 	$(GO) build -o ./var/robots2policy -ldflags "-X 'github.com/TecharoHQ/anubis.Version=$(VERSION)'" ./cmd/robots2policy

README.md

@@ -20,12 +20,27 @@ Anubis is brought to you by sponsors and donors like:
 <a href="https://www.raptorcs.com/content/base/products.html">
   <img src="./docs/static/img/sponsors/raptor-computing-logo.webp" alt="Raptor Computing Systems" height=64 />
 </a>
+<a href="https://databento.com/?utm_source=anubis&utm_medium=sponsor&utm_campaign=anubis">
+  <img src="./docs/static/img/sponsors/databento-logo.webp" alt="Databento" height="64" />
+</a>
 
 ### Gold Tier
 
+<a href="https://www.unipromos.com/?utm_campaign=github&utm_medium=referral&utm_content=anubis">
+  <img src="./docs/static/img/sponsors/unipromos.webp" alt="Unipromos" height="64" />
+</a>
+<a href="https://uvensys.de/?utm_campaign=github&utm_medium=referral&utm_content=anubis">
+  <img src="./docs/static/img/sponsors/uvensys.webp" alt="Uvensys" height="64">
+</a>
 <a href="https://distrust.co?utm_campaign=github&utm_medium=referral&utm_content=anubis">
   <img src="./docs/static/img/sponsors/distrust-logo.webp" alt="Distrust" height="64">
 </a>
+<a href="https://about.gitea.com?utm_campaign=github&utm_medium=referral&utm_content=anubis">
+  <img src="./docs/static/img/sponsors/gitea-logo.webp" alt="Gitea" height="64">
+</a>
+<a href="https://prolocation.net?utm_campaign=github&utm_medium=referral&utm_content=anubis">
+  <img src="./docs/static/img/sponsors/prolocation-logo.svg" alt="Prolocation" height="64">
+</a>
 <a href="https://terminaltrove.com/?utm_campaign=github&utm_medium=referral&utm_content=anubis&utm_source=abgh">
   <img src="./docs/static/img/sponsors/terminal-trove.webp" alt="Terminal Trove" height="64">
 </a>
@@ -41,6 +56,23 @@ Anubis is brought to you by sponsors and donors like:
 <a href="https://wildbase.xyz/">
   <img src="./docs/static/img/sponsors/wildbase-logo.webp" alt="Wildbase" height="64">
 </a>
+<a href="https://emma.pet">
+  <img
+    src="./docs/static/img/sponsors/nepeat-logo.webp"
+    alt="Cat eyes over the word Emma in a serif font"
+    height="64"
+  />
+</a>
+<a href="https://fabulous.systems/">
+  <img
+    src="./docs/static/img/sponsors/fabulous-systems.webp"
+    alt="Cat eyes over the word Emma in a serif font"
+    height="64"
+  />
+</a>
+<a href="https://www.anexia.com/">
+  <img src="./docs/static/img/sponsors/anexia-cloudsolutions-logo.webp" alt="ANEXIA Cloud Solutions" height="64">
+</a>
 
 ## Overview
 
@@ -52,7 +84,7 @@ Anubis is a bit of a nuclear response. This will result in your website being bl
 
 In most cases, you should not need this and can probably get by using Cloudflare to protect a given origin. However, for circumstances where you can't or won't use Cloudflare, Anubis is there for you.
 
-If you want to try this out, connect to [anubis.techaro.lol](https://anubis.techaro.lol).
+If you want to try this out, visit the Anubis documentation site at [anubis.techaro.lol](https://anubis.techaro.lol).
 
 ## Support
 

SECURITY.md

@@ -0,0 +1,13 @@
+# Security Policy
+
+Techaro follows the [Semver 2.0 scheme](https://semver.org/).
+
+## Supported Versions
+
+Techaro strives to support the two most recent minor versions of Anubis. Patches to those versions will be published as patch releases.
+
+## Reporting a Vulnerability
+
+Email security@techaro.lol with details on the vulnerability and reproduction steps. You will get a response as soon as possible.
+
+Please take care to send your email as a mixed plaintext and HTML message. Messages with GPG signatures or that are plaintext only may be blocked by the spam filter.

VERSION

@@ -1 +1 @@
-1.20.0
+1.25.0

anubis.go

@@ -11,7 +11,7 @@ var Version = "devel"
 
 // CookieName is the name of the cookie that Anubis uses in order to validate
 // access.
-var CookieName = "techaro.lol-anubis-auth"
+var CookieName = "techaro.lol-anubis"
 
 // TestCookieName is the name of the cookie that Anubis uses in order to check
 // if cookies are enabled on the client's browser.
@@ -23,6 +23,9 @@ const CookieDefaultExpirationTime = 7 * 24 * time.Hour
 // BasePrefix is a global prefix for all Anubis endpoints. Can be emptied to remove the prefix entirely.
 var BasePrefix = ""
 
+// PublicUrl is the externally accessible URL for this Anubis instance.
+var PublicUrl = ""
+
 // StaticPath is the location where all static Anubis assets are located.
 const StaticPath = "/.within.website/x/cmd/anubis/"
 
@@ -36,3 +39,6 @@ const DefaultDifficulty = 4
 // ForcedLanguage is the language being used instead of the one of the request's Accept-Language header
 // if being set.
 var ForcedLanguage = ""
+
+// UseSimplifiedExplanation can be set to true for using the simplified explanation
+var UseSimplifiedExplanation = false

cmd/anubis/main.go

@@ -30,14 +30,15 @@ import (
 	"github.com/TecharoHQ/anubis"
 	"github.com/TecharoHQ/anubis/data"
 	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/internal/thoth"
 	libanubis "github.com/TecharoHQ/anubis/lib"
+	"github.com/TecharoHQ/anubis/lib/config"
 	botPolicy "github.com/TecharoHQ/anubis/lib/policy"
-	"github.com/TecharoHQ/anubis/lib/policy/config"
+	"github.com/TecharoHQ/anubis/lib/thoth"
 	"github.com/TecharoHQ/anubis/web"
 	"github.com/facebookgo/flagenv"
 	_ "github.com/joho/godotenv/autoload"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
+	healthv1 "google.golang.org/grpc/health/grpc_health_v1"
 )
 
 var (
@@ -48,11 +49,14 @@ var (
 	cookieDomain             = flag.String("cookie-domain", "", "if set, the top-level domain that the Anubis cookie will be valid for")
 	cookieDynamicDomain      = flag.Bool("cookie-dynamic-domain", false, "if set, automatically set the cookie Domain value based on the request domain")
 	cookieExpiration         = flag.Duration("cookie-expiration-time", anubis.CookieDefaultExpirationTime, "The amount of time the authorization cookie is valid for")
-	cookiePrefix             = flag.String("cookie-prefix", "techaro.lol-anubis", "prefix for browser cookies created by Anubis")
+	cookiePrefix             = flag.String("cookie-prefix", anubis.CookieName, "prefix for browser cookies created by Anubis")
 	cookiePartitioned        = flag.Bool("cookie-partitioned", false, "if true, sets the partitioned flag on Anubis cookies, enabling CHIPS support")
+	difficultyInJWT          = flag.Bool("difficulty-in-jwt", false, "if true, adds a difficulty field in the JWT claims")
+	useSimplifiedExplanation = flag.Bool("use-simplified-explanation", false, "if true, replaces the text when clicking \"Why am I seeing this?\" with a more simplified text for a non-tech-savvy audience.")
 	forcedLanguage           = flag.String("forced-language", "", "if set, this language is being used instead of the one from the request's Accept-Language header")
 	hs512Secret              = flag.String("hs512-secret", "", "secret used to sign JWTs, uses ed25519 if not set")
 	cookieSecure             = flag.Bool("cookie-secure", true, "if true, sets the secure flag on Anubis cookies")
+	cookieSameSite           = flag.String("cookie-same-site", "None", "sets the same site option on Anubis cookies, will auto-downgrade None to Lax if cookie-secure is false. Valid values are None, Lax, Strict, and Default.")
 	ed25519PrivateKeyHex     = flag.String("ed25519-private-key-hex", "", "private key used to sign JWTs, if not set a random one will be assigned")
 	ed25519PrivateKeyHexFile = flag.String("ed25519-private-key-hex-file", "", "file name containing value for ed25519-private-key-hex")
 	metricsBind              = flag.String("metrics-bind", ":9090", "network address to bind metrics to")
@@ -64,9 +68,10 @@ var (
 	slogLevel                = flag.String("slog-level", "INFO", "logging level (see https://pkg.go.dev/log/slog#hdr-Levels)")
 	stripBasePrefix          = flag.Bool("strip-base-prefix", false, "if true, strips the base prefix from requests forwarded to the target server")
 	target                   = flag.String("target", "http://localhost:3923", "target to reverse proxy to, set to an empty string to disable proxying when only using auth request")
-	targetSNI                = flag.String("target-sni", "", "if set, the value of the TLS handshake hostname when forwarding requests to the target")
+	targetSNI                = flag.String("target-sni", "", "if set, TLS handshake hostname when forwarding requests to the target, if set to auto, use Host header")
 	targetHost               = flag.String("target-host", "", "if set, the value of the Host header when forwarding requests to the target")
 	targetInsecureSkipVerify = flag.Bool("target-insecure-skip-verify", false, "if true, skips TLS validation for the backend")
+	targetDisableKeepAlive   = flag.Bool("target-disable-keepalive", false, "if true, disables HTTP keep-alive for the backend")
 	healthcheck              = flag.Bool("healthcheck", false, "run a health check against Anubis")
 	useRemoteAddress         = flag.Bool("use-remote-address", false, "read the client's IP address from the network request, useful for debugging and running Anubis on bare metal")
 	debugBenchmarkJS         = flag.Bool("debug-benchmark-js", false, "respond to every request with a challenge for benchmarking hashrate")
@@ -76,11 +81,14 @@ var (
 	extractResources         = flag.String("extract-resources", "", "if set, extract the static resources to the specified folder")
 	webmasterEmail           = flag.String("webmaster-email", "", "if set, displays webmaster's email on the reject page for appeals")
 	versionFlag              = flag.Bool("version", false, "print Anubis version")
+	publicUrl                = flag.String("public-url", "", "the externally accessible URL for this Anubis instance, used for constructing redirect URLs (e.g., for forwardAuth).")
 	xffStripPrivate          = flag.Bool("xff-strip-private", true, "if set, strip private addresses from X-Forwarded-For")
+	customRealIPHeader       = flag.String("custom-real-ip-header", "", "if set, read remote IP from header of this name (in case your environment doesn't set X-Real-IP header)")
 
-	thothInsecure = flag.Bool("thoth-insecure", false, "if set, connect to Thoth over plain HTTP/2, don't enable this unless support told you to")
-	thothURL      = flag.String("thoth-url", "", "if set, URL for Thoth, the IP reputation database for Anubis")
-	thothToken    = flag.String("thoth-token", "", "if set, API token for Thoth, the IP reputation database for Anubis")
+	thothInsecure        = flag.Bool("thoth-insecure", false, "if set, connect to Thoth over plain HTTP/2, don't enable this unless support told you to")
+	thothURL             = flag.String("thoth-url", "", "if set, URL for Thoth, the IP reputation database for Anubis")
+	thothToken           = flag.String("thoth-token", "", "if set, API token for Thoth, the IP reputation database for Anubis")
+	jwtRestrictionHeader = flag.String("jwt-restriction-header", "X-Real-IP", "If set, the JWT is only valid if the current value of this header matched the value when the JWT was created")
 )
 
 func keyFromHex(value string) (ed25519.PrivateKey, error) {
@@ -97,7 +105,7 @@ func keyFromHex(value string) (ed25519.PrivateKey, error) {
 }
 
 func doHealthCheck() error {
-	resp, err := http.Get("http://localhost" + *metricsBind + anubis.BasePrefix + "/metrics")
+	resp, err := http.Get("http://localhost" + *metricsBind + "/healthz")
 	if err != nil {
 		return fmt.Errorf("failed to fetch metrics: %w", err)
 	}
@@ -137,6 +145,22 @@ func parseBindNetFromAddr(address string) (string, string) {
 	return "", address
 }
 
+func parseSameSite(s string) http.SameSite {
+	switch strings.ToLower(s) {
+	case "none":
+		return http.SameSiteNoneMode
+	case "lax":
+		return http.SameSiteLaxMode
+	case "strict":
+		return http.SameSiteStrictMode
+	case "default":
+		return http.SameSiteDefaultMode
+	default:
+		log.Fatalf("invalid cookie same-site mode: %s, valid values are None, Lax, Strict, and Default", s)
+	}
+	return http.SameSiteDefaultMode
+}
+
 func setupListener(network string, address string) (net.Listener, string) {
 	formattedAddress := ""
 
@@ -184,7 +208,7 @@ func setupListener(network string, address string) (net.Listener, string) {
 	return listener, formattedAddress
 }
 
-func makeReverseProxy(target string, targetSNI string, targetHost string, insecureSkipVerify bool) (http.Handler, error) {
+func makeReverseProxy(target string, targetSNI string, targetHost string, insecureSkipVerify bool, targetDisableKeepAlive bool) (http.Handler, error) {
 	targetUri, err := url.Parse(target)
 	if err != nil {
 		return nil, fmt.Errorf("failed to parse target URL: %w", err)
@@ -192,6 +216,10 @@ func makeReverseProxy(target string, targetSNI string, targetHost string, insecu
 
 	transport := http.DefaultTransport.(*http.Transport).Clone()
 
+	if targetDisableKeepAlive {
+		transport.DisableKeepAlives = true
+	}
+
 	// https://github.com/oauth2-proxy/oauth2-proxy/blob/4e2100a2879ef06aea1411790327019c1a09217c/pkg/upstream/http.go#L124
 	if targetUri.Scheme == "unix" {
 		// clean path up so we don't use the socket path in proxied requests
@@ -208,23 +236,28 @@ func makeReverseProxy(target string, targetSNI string, targetHost string, insecu
 
 	if insecureSkipVerify || targetSNI != "" {
 		transport.TLSClientConfig = &tls.Config{}
-		if insecureSkipVerify {
-			slog.Warn("TARGET_INSECURE_SKIP_VERIFY is set to true, TLS certificate validation will not be performed", "target", target)
-			transport.TLSClientConfig.InsecureSkipVerify = true
-		}
-		if targetSNI != "" {
-			transport.TLSClientConfig.ServerName = targetSNI
-		}
+	}
+	if insecureSkipVerify {
+		slog.Warn("TARGET_INSECURE_SKIP_VERIFY is set to true, TLS certificate validation will not be performed", "target", target)
+		transport.TLSClientConfig.InsecureSkipVerify = true
+	}
+	if targetSNI != "" && targetSNI != "auto" {
+		transport.TLSClientConfig.ServerName = targetSNI
 	}
 
 	rp := httputil.NewSingleHostReverseProxy(targetUri)
 	rp.Transport = transport
 
-	if targetHost != "" {
+	if targetHost != "" || targetSNI == "auto" {
 		originalDirector := rp.Director
 		rp.Director = func(req *http.Request) {
 			originalDirector(req)
-			req.Host = targetHost
+			if targetHost != "" {
+				req.Host = targetHost
+			}
+			if targetSNI == "auto" {
+				transport.TLSClientConfig.ServerName = req.Host
+			}
 		}
 	}
 
@@ -240,7 +273,18 @@ func main() {
 		return
 	}
 
-	internal.InitSlog(*slogLevel)
+	internal.SetHealth("anubis", healthv1.HealthCheckResponse_NOT_SERVING)
+
+	lg := internal.InitSlog(*slogLevel, os.Stderr)
+	lg.Info("starting up Anubis")
+
+	if *healthcheck {
+		log.Println("running healthcheck")
+		if err := doHealthCheck(); err != nil {
+			log.Fatal(err)
+		}
+		return
+	}
 
 	if *extractResources != "" {
 		if err := extractEmbedFS(data.BotPolicies, ".", *extractResources); err != nil {
@@ -253,11 +297,22 @@ func main() {
 		return
 	}
 
+	// install signal handler
+	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
+	defer stop()
+
+	wg := new(sync.WaitGroup)
+
+	if *metricsBind != "" {
+		wg.Add(1)
+		go metricsServer(ctx, *lg.With("subsystem", "metrics"), wg.Done)
+	}
+
 	var rp http.Handler
 	// when using anubis via Systemd and environment variables, then it is not possible to set targe to an empty string but only to space
 	if strings.TrimSpace(*target) != "" {
 		var err error
-		rp, err = makeReverseProxy(*target, *targetSNI, *targetHost, *targetInsecureSkipVerify)
+		rp, err = makeReverseProxy(*target, *targetSNI, *targetHost, *targetInsecureSkipVerify, *targetDisableKeepAlive)
 		if err != nil {
 			log.Fatalf("can't make reverse proxy: %v", err)
 		}
@@ -267,16 +322,14 @@ func main() {
 		log.Fatalf("you can't set COOKIE_DOMAIN and COOKIE_DYNAMIC_DOMAIN at the same time")
 	}
 
-	ctx := context.Background()
-
 	// Thoth configuration
 	switch {
 	case *thothURL != "" && *thothToken == "":
-		slog.Warn("THOTH_URL is set but no THOTH_TOKEN is set")
+		lg.Warn("THOTH_URL is set but no THOTH_TOKEN is set")
 	case *thothURL == "" && *thothToken != "":
-		slog.Warn("THOTH_TOKEN is set but no THOTH_URL is set")
+		lg.Warn("THOTH_TOKEN is set but no THOTH_URL is set")
 	case *thothURL != "" && *thothToken != "":
-		slog.Debug("connecting to Thoth")
+		lg.Debug("connecting to Thoth")
 		thothClient, err := thoth.New(ctx, *thothURL, *thothToken, *thothInsecure)
 		if err != nil {
 			log.Fatalf("can't dial thoth at %s: %v", *thothURL, err)
@@ -285,10 +338,24 @@ func main() {
 		ctx = thoth.With(ctx, thothClient)
 	}
 
-	policy, err := libanubis.LoadPoliciesOrDefault(ctx, *policyFname, *challengeDifficulty)
+	lg.Info("loading policy file", "fname", *policyFname)
+	policy, err := libanubis.LoadPoliciesOrDefault(ctx, *policyFname, *challengeDifficulty, *slogLevel)
 	if err != nil {
 		log.Fatalf("can't parse policy file: %v", err)
 	}
+	lg = policy.Logger
+	lg.Debug("swapped to new logger")
+	slog.SetDefault(lg)
+
+	// Warn if persistent storage is used without a configured signing key
+	if policy.Store.IsPersistent() {
+		if *hs512Secret == "" && *ed25519PrivateKeyHex == "" && *ed25519PrivateKeyHexFile == "" {
+			lg.Warn("[misconfiguration] persistent storage backend is configured, but no private key is set. " +
+				"Challenges will be invalidated when Anubis restarts. " +
+				"Set HS512_SECRET, ED25519_PRIVATE_KEY_HEX, or ED25519_PRIVATE_KEY_HEX_FILE to ensure challenges survive service restarts. " +
+				"See: https://anubis.techaro.lol/docs/admin/installation#key-generation")
+		}
+	}
 
 	ruleErrorIDs := make(map[string]string)
 	for _, rule := range policy.Bots {
@@ -346,13 +413,13 @@ func main() {
 			log.Fatalf("failed to generate ed25519 key: %v", err)
 		}
 
-		slog.Warn("generating random key, Anubis will have strange behavior when multiple instances are behind the same load balancer target, for more information: see https://anubis.techaro.lol/docs/admin/installation#key-generation")
+		lg.Warn("generating random key, Anubis will have strange behavior when multiple instances are behind the same load balancer target, for more information: see https://anubis.techaro.lol/docs/admin/installation#key-generation")
 	}
 
 	var redirectDomainsList []string
 	if *redirectDomains != "" {
-		domains := strings.Split(*redirectDomains, ",")
-		for _, domain := range domains {
+		domains := strings.SplitSeq(*redirectDomains, ",")
+		for domain := range domains {
 			_, err = url.Parse(domain)
 			if err != nil {
 				log.Fatalf("cannot parse redirect-domain %q: %s", domain, err.Error())
@@ -360,12 +427,13 @@ func main() {
 			redirectDomainsList = append(redirectDomainsList, strings.TrimSpace(domain))
 		}
 	} else {
-		slog.Warn("REDIRECT_DOMAINS is not set, Anubis will only redirect to the same domain a request is coming from, see https://anubis.techaro.lol/docs/admin/configuration/redirect-domains")
+		lg.Warn("REDIRECT_DOMAINS is not set, Anubis will only redirect to the same domain a request is coming from, see https://anubis.techaro.lol/docs/admin/configuration/redirect-domains")
 	}
 
 	anubis.CookieName = *cookiePrefix + "-auth"
 	anubis.TestCookieName = *cookiePrefix + "-cookie-verification"
 	anubis.ForcedLanguage = *forcedLanguage
+	anubis.UseSimplifiedExplanation = *useSimplifiedExplanation
 
 	// If OpenGraph configuration values are not set in the config file, use the
 	// values from flags / envvars.
@@ -377,46 +445,46 @@ func main() {
 	}
 
 	s, err := libanubis.New(libanubis.Options{
-		BasePrefix:          *basePrefix,
-		StripBasePrefix:     *stripBasePrefix,
-		Next:                rp,
-		Policy:              policy,
-		ServeRobotsTXT:      *robotsTxt,
-		ED25519PrivateKey:   ed25519Priv,
-		HS512Secret:         []byte(*hs512Secret),
-		CookieDomain:        *cookieDomain,
-		CookieDynamicDomain: *cookieDynamicDomain,
-		CookieExpiration:    *cookieExpiration,
-		CookiePartitioned:   *cookiePartitioned,
-		RedirectDomains:     redirectDomainsList,
-		Target:              *target,
-		WebmasterEmail:      *webmasterEmail,
-		OpenGraph:           policy.OpenGraph,
-		CookieSecure:        *cookieSecure,
+		BasePrefix:               *basePrefix,
+		StripBasePrefix:          *stripBasePrefix,
+		Next:                     rp,
+		Policy:                   policy,
+		TargetHost:               *targetHost,
+		TargetSNI:                *targetSNI,
+		TargetInsecureSkipVerify: *targetInsecureSkipVerify,
+		ServeRobotsTXT:           *robotsTxt,
+		ED25519PrivateKey:        ed25519Priv,
+		HS512Secret:              []byte(*hs512Secret),
+		CookieDomain:             *cookieDomain,
+		CookieDynamicDomain:      *cookieDynamicDomain,
+		CookieExpiration:         *cookieExpiration,
+		CookiePartitioned:        *cookiePartitioned,
+		RedirectDomains:          redirectDomainsList,
+		Target:                   *target,
+		WebmasterEmail:           *webmasterEmail,
+		OpenGraph:                policy.OpenGraph,
+		CookieSecure:             *cookieSecure,
+		CookieSameSite:           parseSameSite(*cookieSameSite),
+		PublicUrl:                *publicUrl,
+		JWTRestrictionHeader:     *jwtRestrictionHeader,
+		Logger:                   policy.Logger.With("subsystem", "anubis"),
+		DifficultyInJWT:          *difficultyInJWT,
 	})
 	if err != nil {
 		log.Fatalf("can't construct libanubis.Server: %v", err)
 	}
 
-	wg := new(sync.WaitGroup)
-	// install signal handler
-	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
-	defer stop()
-
-	if *metricsBind != "" {
-		wg.Add(1)
-		go metricsServer(ctx, wg.Done)
-	}
-
 	var h http.Handler
 	h = s
+	h = internal.CustomRealIPHeader(*customRealIPHeader, h)
 	h = internal.RemoteXRealIP(*useRemoteAddress, *bindNetwork, h)
 	h = internal.XForwardedForToXRealIP(h)
 	h = internal.XForwardedForUpdate(*xffStripPrivate, h)
+	h = internal.JA4H(h)
 
 	srv := http.Server{Handler: h, ErrorLog: internal.GetFilteredHTTPLogger()}
 	listener, listenerUrl := setupListener(*bindNetwork, *bind)
-	slog.Info(
+	lg.Info(
 		"listening",
 		"url", listenerUrl,
 		"difficulty", *challengeDifficulty,
@@ -430,6 +498,7 @@ func main() {
 		"base-prefix", *basePrefix,
 		"cookie-expiration-time", *cookieExpiration,
 		"rule-error-ids", ruleErrorIDs,
+		"public-url", *publicUrl,
 	)
 
 	go func() {
@@ -441,29 +510,41 @@ func main() {
 		}
 	}()
 
+	internal.SetHealth("anubis", healthv1.HealthCheckResponse_SERVING)
+
 	if err := srv.Serve(listener); !errors.Is(err, http.ErrServerClosed) {
 		log.Fatal(err)
 	}
 	wg.Wait()
 }
 
-func metricsServer(ctx context.Context, done func()) {
+func metricsServer(ctx context.Context, lg slog.Logger, done func()) {
 	defer done()
 
 	mux := http.NewServeMux()
-	mux.Handle(anubis.BasePrefix+"/metrics", promhttp.Handler())
+	mux.Handle("/metrics", promhttp.Handler())
+	mux.HandleFunc("/healthz", func(w http.ResponseWriter, r *http.Request) {
+		st, ok := internal.GetHealth("anubis")
+		if !ok {
+			slog.Error("health service anubis does not exist, file a bug")
+		}
+
+		switch st {
+		case healthv1.HealthCheckResponse_NOT_SERVING:
+			http.Error(w, "NOT OK", http.StatusInternalServerError)
+			return
+		case healthv1.HealthCheckResponse_SERVING:
+			fmt.Fprintln(w, "OK")
+			return
+		default:
+			http.Error(w, "UNKNOWN", http.StatusFailedDependency)
+			return
+		}
+	})
 
 	srv := http.Server{Handler: mux, ErrorLog: internal.GetFilteredHTTPLogger()}
 	listener, metricsUrl := setupListener(*metricsBindNetwork, *metricsBind)
-	slog.Debug("listening for metrics", "url", metricsUrl)
-
-	if *healthcheck {
-		log.Println("running healthcheck")
-		if err := doHealthCheck(); err != nil {
-			log.Fatal(err)
-		}
-		return
-	}
+	lg.Debug("listening for metrics", "url", metricsUrl)
 
 	go func() {
 		<-ctx.Done()

cmd/containerbuild/main.go

@@ -28,7 +28,7 @@ func main() {
 	flagenv.Parse()
 	flag.Parse()
 
-	internal.InitSlog(*slogLevel)
+	slog.SetDefault(internal.InitSlog(*slogLevel, os.Stderr))
 
 	koDockerRepo := strings.TrimSuffix(*dockerRepo, "/"+filepath.Base(*dockerRepo))
 
@@ -46,6 +46,11 @@ func main() {
 		)
 	}
 
+	if strings.Contains(*dockerTags, ",") {
+		newTags := strings.Join(strings.Split(*dockerTags, ","), "\n")
+		dockerTags = &newTags
+	}
+
 	setOutput("docker_image", strings.SplitN(*dockerTags, "\n", 2)[0])
 
 	version, err := run("git describe --tags --always --dirty")
@@ -154,5 +159,8 @@ func run(command string) (string, error) {
 }
 
 func setOutput(key, val string) {
-	fmt.Printf("::set-output name=%s::%s\n", key, val)
+    github_output := os.Getenv("GITHUB_OUTPUT")
+    f, _ := os.OpenFile(github_output, os.O_WRONLY|os.O_APPEND|os.O_CREATE, 0644)
+    fmt.Fprintf(f, "%s=%s\n", key, val)
+    f.Close()
 }

cmd/robots2policy/main.go

@@ -10,9 +10,10 @@ import (
 	"net/http"
 	"os"
 	"regexp"
+	"slices"
 	"strings"
 
-	"github.com/TecharoHQ/anubis/lib/policy/config"
+	"github.com/TecharoHQ/anubis/lib/config"
 
 	"sigs.k8s.io/yaml"
 )
@@ -29,7 +30,7 @@ var (
 )
 
 type RobotsRule struct {
-	UserAgent   string
+	UserAgents  []string
 	Disallows   []string
 	Allows      []string
 	CrawlDelay  int
@@ -130,10 +131,26 @@ func main() {
 	}
 }
 
+func createRuleFromAccumulated(userAgents, disallows, allows []string, crawlDelay int) RobotsRule {
+	rule := RobotsRule{
+		UserAgents: make([]string, len(userAgents)),
+		Disallows:  make([]string, len(disallows)),
+		Allows:     make([]string, len(allows)),
+		CrawlDelay: crawlDelay,
+	}
+	copy(rule.UserAgents, userAgents)
+	copy(rule.Disallows, disallows)
+	copy(rule.Allows, allows)
+	return rule
+}
+
 func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
 	scanner := bufio.NewScanner(input)
 	var rules []RobotsRule
-	var currentRule *RobotsRule
+	var currentUserAgents []string
+	var currentDisallows []string
+	var currentAllows []string
+	var currentCrawlDelay int
 
 	for scanner.Scan() {
 		line := strings.TrimSpace(scanner.Text())
@@ -154,47 +171,48 @@ func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
 
 		switch directive {
 		case "user-agent":
-			// Start a new rule section
-			if currentRule != nil {
-				rules = append(rules, *currentRule)
-			}
-			currentRule = &RobotsRule{
-				UserAgent: value,
-				Disallows: make([]string, 0),
-				Allows:    make([]string, 0),
+			// If we have accumulated rules with directives and encounter a new user-agent,
+			// flush the current rules
+			if len(currentUserAgents) > 0 && (len(currentDisallows) > 0 || len(currentAllows) > 0 || currentCrawlDelay > 0) {
+				rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
+				rules = append(rules, rule)
+				// Reset for next group
+				currentUserAgents = nil
+				currentDisallows = nil
+				currentAllows = nil
+				currentCrawlDelay = 0
 			}
+			currentUserAgents = append(currentUserAgents, value)
 
 		case "disallow":
-			if currentRule != nil && value != "" {
-				currentRule.Disallows = append(currentRule.Disallows, value)
+			if len(currentUserAgents) > 0 && value != "" {
+				currentDisallows = append(currentDisallows, value)
 			}
 
 		case "allow":
-			if currentRule != nil && value != "" {
-				currentRule.Allows = append(currentRule.Allows, value)
+			if len(currentUserAgents) > 0 && value != "" {
+				currentAllows = append(currentAllows, value)
 			}
 
 		case "crawl-delay":
-			if currentRule != nil {
+			if len(currentUserAgents) > 0 {
 				if delay, err := parseIntSafe(value); err == nil {
-					currentRule.CrawlDelay = delay
+					currentCrawlDelay = delay
 				}
 			}
 		}
 	}
 
-	// Don't forget the last rule
-	if currentRule != nil {
-		rules = append(rules, *currentRule)
+	// Don't forget the last group of rules
+	if len(currentUserAgents) > 0 {
+		rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
+		rules = append(rules, rule)
 	}
 
 	// Mark blacklisted user agents (those with "Disallow: /")
 	for i := range rules {
-		for _, disallow := range rules[i].Disallows {
-			if disallow == "/" {
-				rules[i].IsBlacklist = true
-				break
-			}
+		if slices.Contains(rules[i].Disallows, "/") {
+			rules[i].IsBlacklist = true
 		}
 	}
 
@@ -211,10 +229,11 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 	var anubisRules []AnubisRule
 	ruleCounter := 0
 
+	// Process each robots rule individually
 	for _, robotsRule := range robotsRules {
-		userAgent := robotsRule.UserAgent
+		userAgents := robotsRule.UserAgents
 
-		// Handle crawl delay as weight adjustment (do this first before any continues)
+		// Handle crawl delay
 		if robotsRule.CrawlDelay > 0 && *crawlDelay > 0 {
 			ruleCounter++
 			rule := AnubisRule{
@@ -223,20 +242,32 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 				Weight: &config.Weight{Adjust: *crawlDelay},
 			}
 
-			if userAgent == "*" {
+			if len(userAgents) == 1 && userAgents[0] == "*" {
 				rule.Expression = &config.ExpressionOrList{
 					All: []string{"true"}, // Always applies
 				}
-			} else {
+			} else if len(userAgents) == 1 {
 				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgents[0])},
+				}
+			} else {
+				// Multiple user agents - use any block
+				var expressions []string
+				for _, ua := range userAgents {
+					if ua == "*" {
+						expressions = append(expressions, "true")
+					} else {
+						expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
+					}
+				}
+				rule.Expression = &config.ExpressionOrList{
+					Any: expressions,
 				}
 			}
-
 			anubisRules = append(anubisRules, rule)
 		}
 
-		// Handle blacklisted user agents (complete deny/challenge)
+		// Handle blacklisted user agents
 		if robotsRule.IsBlacklist {
 			ruleCounter++
 			rule := AnubisRule{
@@ -244,21 +275,36 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 				Action: *userAgentDeny,
 			}
 
-			if userAgent == "*" {
-				// This would block everything - convert to a weight adjustment instead
-				rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
-				rule.Action = "WEIGH"
-				rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
-				rule.Expression = &config.ExpressionOrList{
-					All: []string{"true"}, // Always applies
+			if len(userAgents) == 1 {
+				userAgent := userAgents[0]
+				if userAgent == "*" {
+					// This would block everything - convert to a weight adjustment instead
+					rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
+					rule.Action = "WEIGH"
+					rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
+					rule.Expression = &config.ExpressionOrList{
+						All: []string{"true"}, // Always applies
+					}
+				} else {
+					rule.Expression = &config.ExpressionOrList{
+						All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					}
 				}
 			} else {
+				// Multiple user agents - use any block
+				var expressions []string
+				for _, ua := range userAgents {
+					if ua == "*" {
+						expressions = append(expressions, "true")
+					} else {
+						expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
+					}
+				}
 				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					Any: expressions,
 				}
 			}
 			anubisRules = append(anubisRules, rule)
-			continue
 		}
 
 		// Handle specific disallow rules
@@ -276,9 +322,33 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 			// Build CEL expression
 			var conditions []string
 
-			// Add user agent condition if not wildcard
-			if userAgent != "*" {
-				conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgent))
+			// Add user agent conditions
+			if len(userAgents) == 1 && userAgents[0] == "*" {
+				// Wildcard user agent - no user agent condition needed
+			} else if len(userAgents) == 1 {
+				conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgents[0]))
+			} else {
+				// For multiple user agents, we need to use a more complex expression
+				// This is a limitation - we can't easily combine any for user agents with all for path
+				// So we'll create separate rules for each user agent
+				for _, ua := range userAgents {
+					if ua == "*" {
+						continue // Skip wildcard as it's handled separately
+					}
+					ruleCounter++
+					subRule := AnubisRule{
+						Name:   fmt.Sprintf("%s-disallow-%d", *policyName, ruleCounter),
+						Action: *baseAction,
+						Expression: &config.ExpressionOrList{
+							All: []string{
+								fmt.Sprintf("userAgent.contains(%q)", ua),
+								buildPathCondition(disallow),
+							},
+						},
+					}
+					anubisRules = append(anubisRules, subRule)
+				}
+				continue
 			}
 
 			// Add path condition
@@ -291,7 +361,6 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 
 			anubisRules = append(anubisRules, rule)
 		}
-
 	}
 
 	return anubisRules

cmd/robots2policy/robots2policy_test.go

@@ -22,9 +22,9 @@ type TestCase struct {
 type TestOptions struct {
 	format           string
 	action           string
-	crawlDelayWeight int
 	policyName       string
 	deniedAction     string
+	crawlDelayWeight int
 }
 
 func TestDataFileConversion(t *testing.T) {
@@ -78,6 +78,12 @@ func TestDataFileConversion(t *testing.T) {
 			expectedFile: "complex.yaml",
 			options:      TestOptions{format: "yaml", crawlDelayWeight: 5},
 		},
+		{
+			name:         "consecutive_user_agents",
+			robotsFile:   "consecutive.robots.txt",
+			expectedFile: "consecutive.yaml",
+			options:      TestOptions{format: "yaml", crawlDelayWeight: 3},
+		},
 	}
 
 	for _, tc := range testCases {
@@ -152,8 +158,8 @@ func TestDataFileConversion(t *testing.T) {
 			}
 
 			if strings.ToLower(*outputFormat) == "yaml" {
-				var actualData []interface{}
-				var expectedData []interface{}
+				var actualData []any
+				var expectedData []any
 
 				err = yaml.Unmarshal(actualOutput, &actualData)
 				if err != nil {
@@ -172,8 +178,8 @@ func TestDataFileConversion(t *testing.T) {
 					t.Errorf("Output mismatch for %s\nExpected:\n%s\n\nActual:\n%s", tc.name, expectedStr, actualStr)
 				}
 			} else {
-				var actualData []interface{}
-				var expectedData []interface{}
+				var actualData []any
+				var expectedData []any
 
 				err = json.Unmarshal(actualOutput, &actualData)
 				if err != nil {
@@ -413,6 +419,6 @@ Disallow: /`
 
 // compareData performs a deep comparison of two data structures,
 // ignoring differences that are semantically equivalent in YAML/JSON
-func compareData(actual, expected interface{}) bool {
+func compareData(actual, expected any) bool {
 	return reflect.DeepEqual(actual, expected)
 }

cmd/robots2policy/testdata/blacklist.yaml

@@ -25,6 +25,6 @@
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("Googlebot")
-        - path.startsWith("/search")
-  name: robots-txt-policy-disallow-7
+      - userAgent.contains("Googlebot")
+      - path.startsWith("/search")
+  name: robots-txt-policy-disallow-7

cmd/robots2policy/testdata/complex.yaml

@@ -20,8 +20,8 @@
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("Googlebot")
-        - path.startsWith("/search/")
+      - userAgent.contains("Googlebot")
+      - path.startsWith("/search/")
   name: robots-txt-policy-disallow-6
 - action: WEIGH
   expression: userAgent.contains("Bingbot")
@@ -31,14 +31,14 @@
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("Bingbot")
-        - path.startsWith("/search/")
+      - userAgent.contains("Bingbot")
+      - path.startsWith("/search/")
   name: robots-txt-policy-disallow-8
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("Bingbot")
-        - path.startsWith("/admin/")
+      - userAgent.contains("Bingbot")
+      - path.startsWith("/admin/")
   name: robots-txt-policy-disallow-9
 - action: DENY
   expression: userAgent.contains("BadBot")
@@ -54,18 +54,18 @@
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/.*/admin")
+      - userAgent.contains("TestBot")
+      - path.matches("^/.*/admin")
   name: robots-txt-policy-disallow-13
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/temp.*\\.html")
+      - userAgent.contains("TestBot")
+      - path.matches("^/temp.*\\.html")
   name: robots-txt-policy-disallow-14
 - action: CHALLENGE
   expression:
     all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/file.\\.log")
+      - userAgent.contains("TestBot")
+      - path.matches("^/file.\\.log")
   name: robots-txt-policy-disallow-15

cmd/robots2policy/testdata/consecutive.robots.txt

@@ -0,0 +1,25 @@
+# Test consecutive user agents that should be grouped into any: blocks
+User-agent: *
+Disallow: /admin
+Crawl-delay: 10
+
+# Multiple consecutive user agents - should be grouped
+User-agent: BadBot
+User-agent: SpamBot
+User-agent: EvilBot
+Disallow: /
+
+# Single user agent - should be separate
+User-agent: GoodBot
+Disallow: /private
+
+# Multiple consecutive user agents with crawl delay
+User-agent: SlowBot1
+User-agent: SlowBot2
+Crawl-delay: 5
+
+# Multiple consecutive user agents with specific path
+User-agent: SearchBot1
+User-agent: SearchBot2
+User-agent: SearchBot3
+Disallow: /search 

cmd/robots2policy/testdata/consecutive.yaml

@@ -0,0 +1,47 @@
+- action: WEIGH
+  expression: "true"
+  name: robots-txt-policy-crawl-delay-1
+  weight:
+    adjust: 3
+- action: CHALLENGE
+  expression: path.startsWith("/admin")
+  name: robots-txt-policy-disallow-2
+- action: DENY
+  expression:
+    any:
+      - userAgent.contains("BadBot")
+      - userAgent.contains("SpamBot")
+      - userAgent.contains("EvilBot")
+  name: robots-txt-policy-blacklist-3
+- action: CHALLENGE
+  expression:
+    all:
+      - userAgent.contains("GoodBot")
+      - path.startsWith("/private")
+  name: robots-txt-policy-disallow-4
+- action: WEIGH
+  expression:
+    any:
+      - userAgent.contains("SlowBot1")
+      - userAgent.contains("SlowBot2")
+  name: robots-txt-policy-crawl-delay-5
+  weight:
+    adjust: 3
+- action: CHALLENGE
+  expression:
+    all:
+      - userAgent.contains("SearchBot1")
+      - path.startsWith("/search")
+  name: robots-txt-policy-disallow-7
+- action: CHALLENGE
+  expression:
+    all:
+      - userAgent.contains("SearchBot2")
+      - path.startsWith("/search")
+  name: robots-txt-policy-disallow-8
+- action: CHALLENGE
+  expression:
+    all:
+      - userAgent.contains("SearchBot3")
+      - path.startsWith("/search")
+  name: robots-txt-policy-disallow-9

cmd/robots2policy/testdata/empty.yaml

@@ -1 +1 @@
-[]
+[]

cmd/robots2policy/testdata/simple.json

@@ -1,12 +1,12 @@
 [
   {
-    "action": "CHALLENGE",
     "expression": "path.startsWith(\"/admin/\")",
-    "name": "robots-txt-policy-disallow-1"
+    "name": "robots-txt-policy-disallow-1",
+    "action": "CHALLENGE"
   },
   {
-    "action": "CHALLENGE",
     "expression": "path.startsWith(\"/private\")",
-    "name": "robots-txt-policy-disallow-2"
+    "name": "robots-txt-policy-disallow-2",
+    "action": "CHALLENGE"
   }
-]
+]

data/apps/allow-api-routes.yaml

@@ -2,5 +2,5 @@
   action: ALLOW
   expression:
     all:
-    - '!(method == "HEAD" || method == "GET")'
-    - path.startsWith("/api/")
+      - '!(method == "HEAD" || method == "GET")'
+      - path.startsWith("/api/")

data/apps/gitea-rss-feeds.yaml

@@ -4,4 +4,4 @@
   path_regex: ^/[.A-Za-z0-9_-]{1,256}?[./A-Za-z0-9_-]*\.atom$
 - name: gitea-feed-rss
   action: ALLOW
-  path_regex: ^/[.A-Za-z0-9_-]{1,256}?[./A-Za-z0-9_-]*\.rss$
+  path_regex: ^/[.A-Za-z0-9_-]{1,256}?[./A-Za-z0-9_-]*\.rss$

data/apps/qualys-ssl-labs.yml

@@ -3,5 +3,6 @@
 - name: qualys-ssl-labs
   action: ALLOW
   remote_addresses:
-  - 64.41.200.0/24
-  - 2600:C02:1020:4202::/64
+    - 69.67.183.0/24
+    - 2600:C02:1020:4202::/64
+    - 2602:fdaa:c6:2::/64

data/apps/searx-checker.yml

@@ -5,5 +5,5 @@
 - name: searx-checker
   action: ALLOW
   remote_addresses:
-  - 167.235.158.251/32
-  - 2a01:4f8:1c1c:8fc2::1/128
+    - 167.235.158.251/32
+    - 2a01:4f8:1c1c:8fc2::1/128

data/botPolicies.json

@@ -1,29 +0,0 @@
-{
-  "bots": [
-    {
-      "import": "(data)/bots/_deny-pathological.yaml"
-    },
-    {
-      "import": "(data)/meta/ai-block-aggressive.yaml"
-    },
-    {
-      "import": "(data)/crawlers/_allow-good.yaml"
-    },
-    {
-      "import": "(data)/bots/aggressive-brazilian-scrapers.yaml"
-    },
-    {
-      "import": "(data)/common/keep-internet-working.yaml"
-    },
-    {
-      "name": "generic-browser",
-      "user_agent_regex": "Mozilla|Opera",
-      "action": "CHALLENGE"
-    }
-  ],
-  "dnsbl": false,
-  "status_codes": {
-    "CHALLENGE": 200,
-    "DENY": 200
-  }
-}

data/botPolicies.yaml

@@ -11,9 +11,12 @@
 ## /usr/share/docs/anubis/data or in the tarball you extracted Anubis from.
 
 bots:
+  # You can import the entire default config with this macro:
+  # - import: (data)/meta/default-config.yaml
+
   # Pathological bots to deny
-  - # This correlates to data/bots/deny-pathological.yaml in the source tree
-    # https://github.com/TecharoHQ/anubis/blob/main/data/bots/deny-pathological.yaml
+  - # This correlates to data/bots/_deny-pathological.yaml in the source tree
+    # https://github.com/TecharoHQ/anubis/blob/main/data/bots/_deny-pathological.yaml
     import: (data)/bots/_deny-pathological.yaml
   - import: (data)/bots/aggressive-brazilian-scrapers.yaml
 
@@ -47,8 +50,7 @@ bots:
   #   user_agent_regex: (?i:bot|crawler)
   #   action: CHALLENGE
   #   challenge:
-  #     difficulty: 16  # impossible
-  #     report_as: 4    # lie to the operator
+  #     difficulty: 16 # impossible
   #     algorithm: slow # intentionally waste CPU cycles and time
 
   # Requires a subscription to Thoth to use, see
@@ -74,6 +76,25 @@ bots:
     weight:
       adjust: 10
 
+  # ## System load based checks.
+  # # If the system is under high load, add weight.
+  # - name: high-load-average
+  #   action: WEIGH
+  #   expression: load_1m >= 10.0 # make sure to end the load comparison in a .0
+  #   weight:
+  #     adjust: 20
+
+  ## If your backend service is running on the same operating system as Anubis,
+  ## you can uncomment this rule to make the challenge easier when the system is
+  ## under low load.
+  ##
+  ## If it is not, remove weight.
+  # - name: low-load-average
+  #   action: WEIGH
+  #   expression: load_15m <= 4.0 # make sure to end the load comparison in a .0
+  #   weight:
+  #     adjust: -10
+
   # Generic catchall rule
   - name: generic-browser
     user_agent_regex: >-
@@ -183,7 +204,6 @@ thresholds:
       # https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
       algorithm: metarefresh
       difficulty: 1
-      report_as: 1
   # For clients that are browser-like but have either gained points from custom rules or
   # report as a standard browser.
   - name: moderate-suspicion
@@ -196,13 +216,21 @@ thresholds:
       # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
       algorithm: fast
       difficulty: 2 # two leading zeros, very fast for most clients
-      report_as: 2
-  # For clients that are browser like and have gained many points from custom rules
-  - name: extreme-suspicion
-    expression: weight >= 20
+  - name: mild-proof-of-work
+    expression:
+      all:
+        - weight >= 20
+        - weight < 30
     action: CHALLENGE
     challenge:
       # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
       algorithm: fast
       difficulty: 4
-      report_as: 4
+  # For clients that are browser like and have gained many points from custom rules
+  - name: extreme-suspicion
+    expression: weight >= 30
+    action: CHALLENGE
+    challenge:
+      # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
+      algorithm: fast
+      difficulty: 6

data/bots/_deny-pathological.yaml

@@ -1,3 +1,6 @@
 - import: (data)/bots/cloudflare-workers.yaml
 - import: (data)/bots/headless-browsers.yaml
-- import: (data)/bots/us-ai-scraper.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

data/bots/ai-robots-txt.yaml

@@ -4,5 +4,5 @@
 # CCBot is allowed because if Common Crawl is allowed, then scrapers don't need to scrape to get the data.
 - name: "ai-robots-txt"
   user_agent_regex: >-
-    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|bedrockbot|Brightbot 1.0|Bytespider|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|MyCentralAIScraperBot|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|Poseidon Research Crawler|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot|SemrushBot-BA|SemrushBot-CT|SemrushBot-OCOB|SemrushBot-SI|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YandexAdditional|YandexAdditionalBot|YouBot
+    AddSearchBot|AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|Andibot|anthropic-ai|Applebot|Applebot-Extended|Awario|bedrockbot|bigsur.ai|Brightbot 1.0|Bytespider|CCBot|ChatGPT Agent|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|CloudVertexBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Datenbank Crawler|Devin|Diffbot|DuckAssistBot|Echobot Bot|EchoboxBot|FacebookBot|facebookexternalhit|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Gemini-Deep-Research|Google-CloudVertexBot|Google-Extended|GoogleAgent-Mariner|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|LinerBot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User|MistralAI-User/1.0|MyCentralAIScraperBot|netEstate Imprint Crawler|NovaAct|OAI-SearchBot|omgili|omgilibot|OpenAI|Operator|PanguBot|Panscient|panscient.com|Perplexity-User|PerplexityBot|PetalBot|PhindBot|Poseidon Research Crawler|QualifiedBot|QuillBot|quillbot.com|SBIntuitionsBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|Thinkbot|TikTokSpider|Timpibot|VelenPublicWebCrawler|WARDBot|Webzio-Extended|wpbot|YaK|YandexAdditional|YandexAdditionalBot|YouBot
   action: DENY

data/bots/custom-async-http-client.yaml

@@ -0,0 +1,5 @@
+- name: "custom-async-http-client"
+  user_agent_regex: "Custom-AsyncHttpClient"
+  action: WEIGH
+  weight:
+    adjust: 10

data/bots/headless-browsers.yaml

@@ -6,4 +6,4 @@
   action: DENY
 - name: headless-chromium
   user_agent_regex: HeadlessChromium
-  action: DENY
+  action: DENY

data/bots/irc-bots/archlinux-phrik.yaml

@@ -3,7 +3,7 @@
   action: ALLOW
   expression:
     all:
-    - remoteAddress == "159.69.213.214" || remoteAddress == "2a01:4f8:c2c:7bf4::1"
-    - userAgent == "Mozilla/5.0 (compatible; utils.web Limnoria module)"
-    - '"X-Http-Version" in headers'
-    - headers["X-Http-Version"] == "HTTP/1.1"
+      - remoteAddress == "159.69.213.214" || remoteAddress == "2a01:4f8:c2c:7bf4::1"
+      - userAgent == "Mozilla/5.0 (compatible; utils.web Limnoria module)"
+      - '"X-Http-Version" in headers'
+      - headers["X-Http-Version"] == "HTTP/1.1"

data/bots/irc-bots/gentoo-chat.yaml

@@ -3,7 +3,7 @@
   action: ALLOW
   expression:
     all:
-    - remoteAddress == "45.76.166.57"
-    - userAgent == "Mozilla/5.0 (Linux x86_64; rv:76.0) Gecko/20100101 Firefox/76.0"
-    - '"X-Http-Version" in headers'
-    - headers["X-Http-Version"] == "HTTP/1.1"
+      - remoteAddress == "45.76.166.57"
+      - userAgent == "Mozilla/5.0 (Linux x86_64; rv:76.0) Gecko/20100101 Firefox/76.0"
+      - '"X-Http-Version" in headers'
+      - headers["X-Http-Version"] == "HTTP/1.1"

data/bots/us-ai-scraper.yaml

@@ -1,3 +1,3 @@
 - name: us-artificial-intelligence-scraper
   user_agent_regex: \+https\://github\.com/US-Artificial-Intelligence/scraper
-  action: DENY
+  action: DENY

data/clients/ai.yaml

@@ -4,5 +4,5 @@
 #  - Claude-User: No published IP allowlist
 - name: "ai-clients"
   user_agent_regex: >-
-    ChatGPT-User|Claude-User|MistralAI-User
+    ChatGPT-User|Claude-User|MistralAI-User|Perplexity-User
   action: DENY

data/clients/docker-client.yaml

@@ -0,0 +1,60 @@
+- name: allow-docker-client
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("docker/")
+      - userAgent.contains("git-commit/")
+      - '"Accept" in headers'
+      - headers["Accept"].contains("vnd.docker.distribution")
+      - '"Baggage" in headers'
+      - headers["Baggage"].contains("trigger")
+
+- name: allow-crane-client
+  action: ALLOW
+  expression:
+    all:
+      - userAgent.contains("crane/")
+      - userAgent.contains("go-containerregistry/")
+
+- name: allow-docker-distribution-api-client
+  action: ALLOW
+  expression:
+    all:
+      - '"Docker-Distribution-Api-Version" in headers'
+      - '!(userAgent.contains("Mozilla"))'
+
+- name: allow-go-containerregistry-client
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("go-containerregistry/")
+
+- name: allow-buildah
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("Buildah/")
+
+- name: allow-podman
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("containers/")
+
+- name: allow-containerd
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("containerd/")
+
+- name: allow-renovate
+  action: ALLOW
+  expression:
+    all:
+      - path.startsWith("/v2/")
+      - userAgent.contains("Renovate/")

data/clients/git.yaml

@@ -2,13 +2,19 @@
   action: ALLOW
   expression:
     all:
-    - >
-      (  
-        userAgent.startsWith("git/") ||
-        userAgent.contains("libgit") ||
-        userAgent.startsWith("go-git") ||
-        userAgent.startsWith("JGit/") ||
-        userAgent.startsWith("JGit-")
-      )
-    - '"Git-Protocol" in headers'
-    - headers["Git-Protocol"] == "version=2"
+      - >
+        (  
+          userAgent.startsWith("git/") ||
+          userAgent.contains("libgit") ||
+          userAgent.startsWith("go-git") ||
+          userAgent.startsWith("JGit/") ||
+          userAgent.startsWith("JGit-")
+        )
+      - '"Accept" in headers'
+      - headers["Accept"] == "*/*"
+      - '"Cache-Control" in headers'
+      - headers["Cache-Control"] == "no-cache"
+      - '"Pragma" in headers'
+      - headers["Pragma"] == "no-cache"
+      - '"Accept-Encoding" in headers'
+      - headers["Accept-Encoding"].contains("gzip")

data/clients/go-get.yaml

@@ -2,6 +2,6 @@
   action: ALLOW
   expression:
     all:
-    - userAgent.startsWith("Go-http-client/")
-    - '"go-get" in query'
-    - query["go-get"] == "1"
+      - userAgent.startsWith("Go-http-client/")
+      - '"go-get" in query'
+      - query["go-get"] == "1"

data/clients/mistral-mistralai-user.yaml

@@ -4,7 +4,4 @@
   user_agent_regex: MistralAI-User/.+; \+https\://docs\.mistral\.ai/robots
   action: ALLOW
   # https://mistral.ai/mistralai-user-ips.json
-  remote_addresses: [
-    "20.240.160.161/32",
-    "20.240.160.1/32",
-  ]
+  remote_addresses: ["20.240.160.161/32", "20.240.160.1/32"]

data/clients/openai-chatgpt-user.yaml

@@ -5,89 +5,90 @@
   action: ALLOW
   # https://openai.com/chatgpt-user.json
   # curl 'https://openai.com/chatgpt-user.json' | jq '.prefixes.[].ipv4Prefix' | sed 's/$/,/'
-  remote_addresses: [
-    "13.65.138.112/28",
-    "23.98.179.16/28",
-    "13.65.138.96/28",
-    "172.183.222.128/28",
-    "20.102.212.144/28",
-    "40.116.73.208/28",
-    "172.183.143.224/28",
-    "52.190.190.16/28",
-    "13.83.237.176/28",
-    "51.8.155.64/28",
-    "74.249.86.176/28",
-    "51.8.155.48/28",
-    "20.55.229.144/28",
-    "135.237.131.208/28",
-    "135.237.133.48/28",
-    "51.8.155.112/28",
-    "135.237.133.112/28",
-    "52.159.249.96/28",
-    "52.190.137.16/28",
-    "52.255.111.112/28",
-    "40.84.181.32/28",
-    "172.178.141.112/28",
-    "52.190.142.64/28",
-    "172.178.140.144/28",
-    "52.190.137.144/28",
-    "172.178.141.128/28",
-    "57.154.187.32/28",
-    "4.196.118.112/28",
-    "20.193.50.32/28",
-    "20.215.188.192/28",
-    "20.215.214.16/28",
-    "4.197.22.112/28",
-    "4.197.115.112/28",
-    "172.213.21.16/28",
-    "172.213.11.144/28",
-    "172.213.12.112/28",
-    "172.213.21.144/28",
-    "20.90.7.144/28",
-    "57.154.175.0/28",
-    "57.154.174.112/28",
-    "52.236.94.144/28",
-    "137.135.191.176/28",
-    "23.98.186.192/28",
-    "23.98.186.96/28",
-    "23.98.186.176/28",
-    "23.98.186.64/28",
-    "68.221.67.192/28",
-    "68.221.67.160/28",
-    "13.83.167.128/28",
-    "20.228.106.176/28",
-    "52.159.227.32/28",
-    "68.220.57.64/28",
-    "172.213.21.112/28",
-    "68.221.67.224/28",
-    "68.221.75.16/28",
-    "20.97.189.96/28",
-    "52.252.113.240/28",
-    "52.230.163.32/28",
-    "172.212.159.64/28",
-    "52.255.111.80/28",
-    "52.255.111.0/28",
-    "4.151.241.240/28",
-    "52.255.111.32/28",
-    "52.255.111.48/28",
-    "52.255.111.16/28",
-    "52.230.164.176/28",
-    "52.176.139.176/28",
-    "52.173.234.16/28",
-    "4.151.71.176/28",
-    "4.151.119.48/28",
-    "52.255.109.112/28",
-    "52.255.109.80/28",
-    "20.161.75.208/28",
-    "68.154.28.96/28",
-    "52.255.109.128/28",
-    "52.225.75.208/28",
-    "52.190.139.48/28",
-    "68.221.67.240/28",
-    "52.156.77.144/28",
-    "52.148.129.32/28",
-    "40.84.221.208/28",
-    "104.210.139.224/28",
-    "40.84.221.224/28",
-    "104.210.139.192/28",
-  ]
+  remote_addresses:
+    [
+      "13.65.138.112/28",
+      "23.98.179.16/28",
+      "13.65.138.96/28",
+      "172.183.222.128/28",
+      "20.102.212.144/28",
+      "40.116.73.208/28",
+      "172.183.143.224/28",
+      "52.190.190.16/28",
+      "13.83.237.176/28",
+      "51.8.155.64/28",
+      "74.249.86.176/28",
+      "51.8.155.48/28",
+      "20.55.229.144/28",
+      "135.237.131.208/28",
+      "135.237.133.48/28",
+      "51.8.155.112/28",
+      "135.237.133.112/28",
+      "52.159.249.96/28",
+      "52.190.137.16/28",
+      "52.255.111.112/28",
+      "40.84.181.32/28",
+      "172.178.141.112/28",
+      "52.190.142.64/28",
+      "172.178.140.144/28",
+      "52.190.137.144/28",
+      "172.178.141.128/28",
+      "57.154.187.32/28",
+      "4.196.118.112/28",
+      "20.193.50.32/28",
+      "20.215.188.192/28",
+      "20.215.214.16/28",
+      "4.197.22.112/28",
+      "4.197.115.112/28",
+      "172.213.21.16/28",
+      "172.213.11.144/28",
+      "172.213.12.112/28",
+      "172.213.21.144/28",
+      "20.90.7.144/28",
+      "57.154.175.0/28",
+      "57.154.174.112/28",
+      "52.236.94.144/28",
+      "137.135.191.176/28",
+      "23.98.186.192/28",
+      "23.98.186.96/28",
+      "23.98.186.176/28",
+      "23.98.186.64/28",
+      "68.221.67.192/28",
+      "68.221.67.160/28",
+      "13.83.167.128/28",
+      "20.228.106.176/28",
+      "52.159.227.32/28",
+      "68.220.57.64/28",
+      "172.213.21.112/28",
+      "68.221.67.224/28",
+      "68.221.75.16/28",
+      "20.97.189.96/28",
+      "52.252.113.240/28",
+      "52.230.163.32/28",
+      "172.212.159.64/28",
+      "52.255.111.80/28",
+      "52.255.111.0/28",
+      "4.151.241.240/28",
+      "52.255.111.32/28",
+      "52.255.111.48/28",
+      "52.255.111.16/28",
+      "52.230.164.176/28",
+      "52.176.139.176/28",
+      "52.173.234.16/28",
+      "4.151.71.176/28",
+      "4.151.119.48/28",
+      "52.255.109.112/28",
+      "52.255.109.80/28",
+      "20.161.75.208/28",
+      "68.154.28.96/28",
+      "52.255.109.128/28",
+      "52.225.75.208/28",
+      "52.190.139.48/28",
+      "68.221.67.240/28",
+      "52.156.77.144/28",
+      "52.148.129.32/28",
+      "40.84.221.208/28",
+      "104.210.139.224/28",
+      "40.84.221.224/28",
+      "104.210.139.192/28",
+    ]

data/clients/perplexity-user.yaml

@@ -0,0 +1,8 @@
+# Acts on behalf of user requests
+# https://docs.perplexity.ai/guides/bots
+- name: perplexity-user
+  user_agent_regex: Perplexity-User/.+; \+https\://perplexity\.ai/perplexity-user
+  action: ALLOW
+  # https://www.perplexity.com/perplexity-user.json
+  remote_addresses:
+    ["44.208.221.197/32", "34.193.163.52/32", "18.97.21.0/30", "18.97.43.80/29"]

data/clients/telegram-preview.yaml

@@ -0,0 +1,6 @@
+- name: telegrambot
+  action: ALLOW
+  expression:
+    all:
+      - userAgent.matches("TelegramBot")
+      - verifyFCrDNS(remoteAddress, "ptr\\.telegram\\.org$")

data/clients/vk-preview.yaml

@@ -0,0 +1,6 @@
+- name: vkbot
+  action: ALLOW
+  expression:
+    all:
+      - userAgent.matches("vkShare[^+]+\\+http\\://vk\\.com/dev/Share")
+      - verifyFCrDNS(remoteAddress, "^snipster\\d+\\.go\\.mail\\.ru$")

data/common/acts-like-browser.yaml

@@ -0,0 +1,55 @@
+# Assert behaviour that only genuine browsers display. This ensures that modern Chrome
+# or Firefox versions will get through without a challenge.
+#
+# These rules have been known to be bypassed by some of the worst automated scrapers.
+# Use at your own risk.
+
+- name: realistic-browser-catchall
+  expression:
+    all:
+      - '"User-Agent" in headers'
+      - '( userAgent.contains("Firefox") ) || ( userAgent.contains("Chrome") ) || ( userAgent.contains("Safari") )'
+      - '"Accept" in headers'
+      - '"Sec-Fetch-Dest" in headers'
+      - '"Sec-Fetch-Mode" in headers'
+      - '"Sec-Fetch-Site" in headers'
+      - '"Accept-Encoding" in headers'
+      - '( headers["Accept-Encoding"].contains("zstd") || headers["Accept-Encoding"].contains("br") )'
+      - '"Accept-Language" in headers'
+  action: WEIGH
+  weight:
+    adjust: -10
+
+# The Upgrade-Insecure-Requests header is typically sent by browsers, but not always
+- name: upgrade-insecure-requests
+  expression: '"Upgrade-Insecure-Requests" in headers'
+  action: WEIGH
+  weight:
+    adjust: -2
+
+# Chrome should behave like Chrome
+- name: chrome-is-proper
+  expression:
+    all:
+      - userAgent.contains("Chrome")
+      - '"Sec-Ch-Ua" in headers'
+      - 'headers["Sec-Ch-Ua"].contains("Chromium")'
+      - '"Sec-Ch-Ua-Mobile" in headers'
+      - '"Sec-Ch-Ua-Platform" in headers'
+  action: WEIGH
+  weight:
+    adjust: -5
+
+- name: should-have-accept
+  expression: '!("Accept" in headers)'
+  action: WEIGH
+  weight:
+    adjust: 5
+
+# Generic catchall rule
+- name: generic-browser
+  user_agent_regex: >-
+    Mozilla|Opera
+  action: WEIGH
+  weight:
+    adjust: 10

data/common/allow-api-like.yaml

@@ -2,5 +2,5 @@
   action: ALLOW
   expression:
     all:
-    - '!(method == "HEAD" || method == "GET")'
-    - path.startsWith("/api/")
+      - '!(method == "HEAD" || method == "GET")'
+      - path.startsWith("/api/")

data/common/json-api.yaml

@@ -4,4 +4,4 @@
     all:
       - '"Accept" in headers'
       - 'headers["Accept"] == "application/json"'
-      - 'path.startsWith("/api/")'
+      - 'path.startsWith("/api/")'

data/common/keep-internet-working.yaml

@@ -1,13 +1,13 @@
 # Common "keeping the internet working" routes
 - name: well-known
-  path_regex: ^/.well-known/.*$
+  path_regex: ^/\.well-known/.*$
   action: ALLOW
 - name: favicon
-  path_regex: ^/favicon.ico$
+  path_regex: ^/favicon\.(?:ico|png|gif|jpg|jpeg|svg)$
   action: ALLOW
 - name: robots-txt
-  path_regex: ^/robots.txt$
+  path_regex: ^/robots\.txt$
   action: ALLOW
 - name: sitemap
-  path_regex: ^/sitemap.xml$
-  action: ALLOW
+  path_regex: ^/sitemap\.xml$
+  action: ALLOW

data/common/rfc-violations.yaml

@@ -1,3 +1,3 @@
 - name: no-user-agent-string
   action: DENY
-  expression: userAgent == ""
+  expression: userAgent == ""

data/crawlers/_allow-good.yaml

@@ -8,3 +8,5 @@
 - import: (data)/crawlers/marginalia.yaml
 - import: (data)/crawlers/mojeekbot.yaml
 - import: (data)/crawlers/commoncrawl.yaml
+- import: (data)/crawlers/wikimedia-citoid.yaml
+- import: (data)/crawlers/yandexbot.yaml

data/crawlers/ai-search.yaml

@@ -4,5 +4,5 @@
 #  - Claude-SearchBot: No published IP allowlist
 - name: "ai-crawlers-search"
   user_agent_regex: >-
-    OAI-SearchBot|Claude-SearchBot
+    OAI-SearchBot|Claude-SearchBot|PerplexityBot
   action: DENY

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

data/crawlers/applebot.yaml

@@ -4,17 +4,18 @@
   user_agent_regex: Applebot
   action: ALLOW
   # https://search.developer.apple.com/applebot.json
-  remote_addresses: [
-    "17.241.208.160/27",
-    "17.241.193.160/27",
-    "17.241.200.160/27",
-    "17.22.237.0/24",
-    "17.22.245.0/24",
-    "17.22.253.0/24",
-    "17.241.75.0/24",
-    "17.241.219.0/24",
-    "17.241.227.0/24",
-    "17.246.15.0/24",
-    "17.246.19.0/24",
-    "17.246.23.0/24",
-  ]
+  remote_addresses:
+    [
+      "17.241.208.160/27",
+      "17.241.193.160/27",
+      "17.241.200.160/27",
+      "17.22.237.0/24",
+      "17.22.245.0/24",
+      "17.22.253.0/24",
+      "17.241.75.0/24",
+      "17.241.219.0/24",
+      "17.241.227.0/24",
+      "17.246.15.0/24",
+      "17.246.19.0/24",
+      "17.246.23.0/24",
+    ]

data/crawlers/bingbot.yaml

@@ -2,33 +2,34 @@
   user_agent_regex: \+http\://www\.bing\.com/bingbot\.htm
   action: ALLOW
   # https://www.bing.com/toolbox/bingbot.json
-  remote_addresses: [
-    "157.55.39.0/24",
-    "207.46.13.0/24",
-    "40.77.167.0/24",
-    "13.66.139.0/24",
-    "13.66.144.0/24",
-    "52.167.144.0/24",
-    "13.67.10.16/28",
-    "13.69.66.240/28",
-    "13.71.172.224/28",
-    "139.217.52.0/28",
-    "191.233.204.224/28",
-    "20.36.108.32/28",
-    "20.43.120.16/28",
-    "40.79.131.208/28",
-    "40.79.186.176/28",
-    "52.231.148.0/28",
-    "20.79.107.240/28",
-    "51.105.67.0/28",
-    "20.125.163.80/28",
-    "40.77.188.0/22",
-    "65.55.210.0/24",
-    "199.30.24.0/23",
-    "40.77.202.0/24",
-    "40.77.139.0/25",
-    "20.74.197.0/28",
-    "20.15.133.160/27",
-    "40.77.177.0/24",
-    "40.77.178.0/23"
-  ]
+  remote_addresses:
+    [
+      "157.55.39.0/24",
+      "207.46.13.0/24",
+      "40.77.167.0/24",
+      "13.66.139.0/24",
+      "13.66.144.0/24",
+      "52.167.144.0/24",
+      "13.67.10.16/28",
+      "13.69.66.240/28",
+      "13.71.172.224/28",
+      "139.217.52.0/28",
+      "191.233.204.224/28",
+      "20.36.108.32/28",
+      "20.43.120.16/28",
+      "40.79.131.208/28",
+      "40.79.186.176/28",
+      "52.231.148.0/28",
+      "20.79.107.240/28",
+      "51.105.67.0/28",
+      "20.125.163.80/28",
+      "40.77.188.0/22",
+      "65.55.210.0/24",
+      "199.30.24.0/23",
+      "40.77.202.0/24",
+      "40.77.139.0/25",
+      "20.74.197.0/28",
+      "20.15.133.160/27",
+      "40.77.177.0/24",
+      "40.77.178.0/23",
+    ]

data/crawlers/duckduckbot.yaml

@@ -2,274 +2,275 @@
   user_agent_regex: DuckDuckBot/1\.1; \(\+http\://duckduckgo\.com/duckduckbot\.html\)
   action: ALLOW
   # https://duckduckgo.com/duckduckgo-help-pages/results/duckduckbot
-  remote_addresses: [
-    "57.152.72.128/32",
-    "51.8.253.152/32",
-    "40.80.242.63/32",
-    "20.12.141.99/32",
-    "20.49.136.28/32",
-    "51.116.131.221/32",
-    "51.107.40.209/32",
-    "20.40.133.240/32",
-    "20.50.168.91/32",
-    "51.120.48.122/32",
-    "20.193.45.113/32",
-    "40.76.173.151/32",
-    "40.76.163.7/32",
-    "20.185.79.47/32",
-    "52.142.26.175/32",
-    "20.185.79.15/32",
-    "52.142.24.149/32",
-    "40.76.162.208/32",
-    "40.76.163.23/32",
-    "40.76.162.191/32",
-    "40.76.162.247/32",
-    "40.88.21.235/32",
-    "20.191.45.212/32",
-    "52.146.59.12/32",
-    "52.146.59.156/32",
-    "52.146.59.154/32",
-    "52.146.58.236/32",
-    "20.62.224.44/32",
-    "51.104.180.53/32",
-    "51.104.180.47/32",
-    "51.104.180.26/32",
-    "51.104.146.225/32",
-    "51.104.146.235/32",
-    "20.73.202.147/32",
-    "20.73.132.240/32",
-    "20.71.12.143/32",
-    "20.56.197.58/32",
-    "20.56.197.63/32",
-    "20.43.150.93/32",
-    "20.43.150.85/32",
-    "20.44.222.1/32",
-    "40.89.243.175/32",
-    "13.89.106.77/32",
-    "52.143.242.6/32",
-    "52.143.241.111/32",
-    "52.154.60.82/32",
-    "20.197.209.11/32",
-    "20.197.209.27/32",
-    "20.226.133.105/32",
-    "191.234.216.4/32",
-    "191.234.216.178/32",
-    "20.53.92.211/32",
-    "20.53.91.2/32",
-    "20.207.99.197/32",
-    "20.207.97.190/32",
-    "40.81.250.205/32",
-    "40.64.106.11/32",
-    "40.64.105.247/32",
-    "20.72.242.93/32",
-    "20.99.255.235/32",
-    "20.113.3.121/32",
-    "52.224.16.221/32",
-    "52.224.21.53/32",
-    "52.224.20.204/32",
-    "52.224.21.19/32",
-    "52.224.20.249/32",
-    "52.224.20.203/32",
-    "52.224.20.190/32",
-    "52.224.16.229/32",
-    "52.224.21.20/32",
-    "52.146.63.80/32",
-    "52.224.20.227/32",
-    "52.224.20.193/32",
-    "52.190.37.160/32",
-    "52.224.21.23/32",
-    "52.224.20.223/32",
-    "52.224.20.181/32",
-    "52.224.21.49/32",
-    "52.224.21.55/32",
-    "52.224.21.61/32",
-    "52.224.19.152/32",
-    "52.224.20.186/32",
-    "52.224.21.27/32",
-    "52.224.21.51/32",
-    "52.224.20.174/32",
-    "52.224.21.4/32",
-    "51.104.164.109/32",
-    "51.104.167.71/32",
-    "51.104.160.177/32",
-    "51.104.162.149/32",
-    "51.104.167.95/32",
-    "51.104.167.54/32",
-    "51.104.166.111/32",
-    "51.104.167.88/32",
-    "51.104.161.32/32",
-    "51.104.163.250/32",
-    "51.104.164.189/32",
-    "51.104.167.19/32",
-    "51.104.160.167/32",
-    "51.104.167.110/32",
-    "20.191.44.119/32",
-    "51.104.167.104/32",
-    "20.191.44.234/32",
-    "51.104.164.215/32",
-    "51.104.167.52/32",
-    "20.191.44.22/32",
-    "51.104.167.87/32",
-    "51.104.167.96/32",
-    "20.191.44.16/32",
-    "51.104.167.61/32",
-    "51.104.164.147/32",
-    "20.50.48.159/32",
-    "40.114.182.172/32",
-    "20.50.50.130/32",
-    "20.50.50.163/32",
-    "20.50.50.46/32",
-    "40.114.182.153/32",
-    "20.50.50.118/32",
-    "20.50.49.55/32",
-    "20.50.49.25/32",
-    "40.114.183.251/32",
-    "20.50.50.123/32",
-    "20.50.49.237/32",
-    "20.50.48.192/32",
-    "20.50.50.134/32",
-    "51.138.90.233/32",
-    "40.114.183.196/32",
-    "20.50.50.146/32",
-    "40.114.183.88/32",
-    "20.50.50.145/32",
-    "20.50.50.121/32",
-    "20.50.49.40/32",
-    "51.138.90.206/32",
-    "40.114.182.45/32",
-    "51.138.90.161/32",
-    "20.50.49.0/32",
-    "40.119.232.215/32",
-    "104.43.55.167/32",
-    "40.119.232.251/32",
-    "40.119.232.50/32",
-    "40.119.232.146/32",
-    "40.119.232.218/32",
-    "104.43.54.127/32",
-    "104.43.55.117/32",
-    "104.43.55.116/32",
-    "104.43.55.166/32",
-    "52.154.169.50/32",
-    "52.154.171.70/32",
-    "52.154.170.229/32",
-    "52.154.170.113/32",
-    "52.154.171.44/32",
-    "52.154.172.2/32",
-    "52.143.244.81/32",
-    "52.154.171.87/32",
-    "52.154.171.250/32",
-    "52.154.170.28/32",
-    "52.154.170.122/32",
-    "52.143.243.117/32",
-    "52.143.247.235/32",
-    "52.154.171.235/32",
-    "52.154.171.196/32",
-    "52.154.171.0/32",
-    "52.154.170.243/32",
-    "52.154.170.26/32",
-    "52.154.169.200/32",
-    "52.154.170.96/32",
-    "52.154.170.88/32",
-    "52.154.171.150/32",
-    "52.154.171.205/32",
-    "52.154.170.117/32",
-    "52.154.170.209/32",
-    "191.235.202.48/32",
-    "191.233.3.202/32",
-    "191.235.201.214/32",
-    "191.233.3.197/32",
-    "191.235.202.38/32",
-    "20.53.78.144/32",
-    "20.193.24.10/32",
-    "20.53.78.236/32",
-    "20.53.78.138/32",
-    "20.53.78.123/32",
-    "20.53.78.106/32",
-    "20.193.27.215/32",
-    "20.193.25.197/32",
-    "20.193.12.126/32",
-    "20.193.24.251/32",
-    "20.204.242.101/32",
-    "20.207.72.113/32",
-    "20.204.242.19/32",
-    "20.219.45.67/32",
-    "20.207.72.11/32",
-    "20.219.45.190/32",
-    "20.204.243.55/32",
-    "20.204.241.148/32",
-    "20.207.72.110/32",
-    "20.204.240.172/32",
-    "20.207.72.21/32",
-    "20.204.246.81/32",
-    "20.207.107.181/32",
-    "20.204.246.254/32",
-    "20.219.43.246/32",
-    "52.149.25.43/32",
-    "52.149.61.51/32",
-    "52.149.58.139/32",
-    "52.149.60.38/32",
-    "52.148.165.38/32",
-    "52.143.95.162/32",
-    "52.149.56.151/32",
-    "52.149.30.45/32",
-    "52.149.58.173/32",
-    "52.143.95.204/32",
-    "52.149.28.83/32",
-    "52.149.58.69/32",
-    "52.148.161.87/32",
-    "52.149.58.27/32",
-    "52.149.28.18/32",
-    "20.79.226.26/32",
-    "20.79.239.66/32",
-    "20.79.238.198/32",
-    "20.113.14.159/32",
-    "20.75.144.152/32",
-    "20.43.172.120/32",
-    "20.53.134.160/32",
-    "20.201.15.208/32",
-    "20.93.28.24/32",
-    "20.61.34.40/32",
-    "52.242.224.168/32",
-    "20.80.129.80/32",
-    "20.195.108.47/32",
-    "4.195.133.120/32",
-    "4.228.76.163/32",
-    "4.182.131.108/32",
-    "4.209.224.56/32",
-    "108.141.83.74/32",
-    "4.213.46.14/32",
-    "172.169.17.165/32",
-    "51.8.71.117/32",
-    "20.3.1.178/32",
-    "52.149.56.151/32",
-    "52.149.30.45/32",
-    "52.149.58.173/32",
-    "52.143.95.204/32",
-    "52.149.28.83/32",
-    "52.149.58.69/32",
-    "52.148.161.87/32",
-    "52.149.58.27/32",
-    "52.149.28.18/32",
-    "20.79.226.26/32",
-    "20.79.239.66/32",
-    "20.79.238.198/32",
-    "20.113.14.159/32",
-    "20.75.144.152/32",
-    "20.43.172.120/32",
-    "20.53.134.160/32",
-    "20.201.15.208/32",
-    "20.93.28.24/32",
-    "20.61.34.40/32",
-    "52.242.224.168/32",
-    "20.80.129.80/32",
-    "20.195.108.47/32",
-    "4.195.133.120/32",
-    "4.228.76.163/32",
-    "4.182.131.108/32",
-    "4.209.224.56/32",
-    "108.141.83.74/32",
-    "4.213.46.14/32",
-    "172.169.17.165/32",
-    "51.8.71.117/32",
-    "20.3.1.178/32"
-  ]
+  remote_addresses:
+    [
+      "57.152.72.128/32",
+      "51.8.253.152/32",
+      "40.80.242.63/32",
+      "20.12.141.99/32",
+      "20.49.136.28/32",
+      "51.116.131.221/32",
+      "51.107.40.209/32",
+      "20.40.133.240/32",
+      "20.50.168.91/32",
+      "51.120.48.122/32",
+      "20.193.45.113/32",
+      "40.76.173.151/32",
+      "40.76.163.7/32",
+      "20.185.79.47/32",
+      "52.142.26.175/32",
+      "20.185.79.15/32",
+      "52.142.24.149/32",
+      "40.76.162.208/32",
+      "40.76.163.23/32",
+      "40.76.162.191/32",
+      "40.76.162.247/32",
+      "40.88.21.235/32",
+      "20.191.45.212/32",
+      "52.146.59.12/32",
+      "52.146.59.156/32",
+      "52.146.59.154/32",
+      "52.146.58.236/32",
+      "20.62.224.44/32",
+      "51.104.180.53/32",
+      "51.104.180.47/32",
+      "51.104.180.26/32",
+      "51.104.146.225/32",
+      "51.104.146.235/32",
+      "20.73.202.147/32",
+      "20.73.132.240/32",
+      "20.71.12.143/32",
+      "20.56.197.58/32",
+      "20.56.197.63/32",
+      "20.43.150.93/32",
+      "20.43.150.85/32",
+      "20.44.222.1/32",
+      "40.89.243.175/32",
+      "13.89.106.77/32",
+      "52.143.242.6/32",
+      "52.143.241.111/32",
+      "52.154.60.82/32",
+      "20.197.209.11/32",
+      "20.197.209.27/32",
+      "20.226.133.105/32",
+      "191.234.216.4/32",
+      "191.234.216.178/32",
+      "20.53.92.211/32",
+      "20.53.91.2/32",
+      "20.207.99.197/32",
+      "20.207.97.190/32",
+      "40.81.250.205/32",
+      "40.64.106.11/32",
+      "40.64.105.247/32",
+      "20.72.242.93/32",
+      "20.99.255.235/32",
+      "20.113.3.121/32",
+      "52.224.16.221/32",
+      "52.224.21.53/32",
+      "52.224.20.204/32",
+      "52.224.21.19/32",
+      "52.224.20.249/32",
+      "52.224.20.203/32",
+      "52.224.20.190/32",
+      "52.224.16.229/32",
+      "52.224.21.20/32",
+      "52.146.63.80/32",
+      "52.224.20.227/32",
+      "52.224.20.193/32",
+      "52.190.37.160/32",
+      "52.224.21.23/32",
+      "52.224.20.223/32",
+      "52.224.20.181/32",
+      "52.224.21.49/32",
+      "52.224.21.55/32",
+      "52.224.21.61/32",
+      "52.224.19.152/32",
+      "52.224.20.186/32",
+      "52.224.21.27/32",
+      "52.224.21.51/32",
+      "52.224.20.174/32",
+      "52.224.21.4/32",
+      "51.104.164.109/32",
+      "51.104.167.71/32",
+      "51.104.160.177/32",
+      "51.104.162.149/32",
+      "51.104.167.95/32",
+      "51.104.167.54/32",
+      "51.104.166.111/32",
+      "51.104.167.88/32",
+      "51.104.161.32/32",
+      "51.104.163.250/32",
+      "51.104.164.189/32",
+      "51.104.167.19/32",
+      "51.104.160.167/32",
+      "51.104.167.110/32",
+      "20.191.44.119/32",
+      "51.104.167.104/32",
+      "20.191.44.234/32",
+      "51.104.164.215/32",
+      "51.104.167.52/32",
+      "20.191.44.22/32",
+      "51.104.167.87/32",
+      "51.104.167.96/32",
+      "20.191.44.16/32",
+      "51.104.167.61/32",
+      "51.104.164.147/32",
+      "20.50.48.159/32",
+      "40.114.182.172/32",
+      "20.50.50.130/32",
+      "20.50.50.163/32",
+      "20.50.50.46/32",
+      "40.114.182.153/32",
+      "20.50.50.118/32",
+      "20.50.49.55/32",
+      "20.50.49.25/32",
+      "40.114.183.251/32",
+      "20.50.50.123/32",
+      "20.50.49.237/32",
+      "20.50.48.192/32",
+      "20.50.50.134/32",
+      "51.138.90.233/32",
+      "40.114.183.196/32",
+      "20.50.50.146/32",
+      "40.114.183.88/32",
+      "20.50.50.145/32",
+      "20.50.50.121/32",
+      "20.50.49.40/32",
+      "51.138.90.206/32",
+      "40.114.182.45/32",
+      "51.138.90.161/32",
+      "20.50.49.0/32",
+      "40.119.232.215/32",
+      "104.43.55.167/32",
+      "40.119.232.251/32",
+      "40.119.232.50/32",
+      "40.119.232.146/32",
+      "40.119.232.218/32",
+      "104.43.54.127/32",
+      "104.43.55.117/32",
+      "104.43.55.116/32",
+      "104.43.55.166/32",
+      "52.154.169.50/32",
+      "52.154.171.70/32",
+      "52.154.170.229/32",
+      "52.154.170.113/32",
+      "52.154.171.44/32",
+      "52.154.172.2/32",
+      "52.143.244.81/32",
+      "52.154.171.87/32",
+      "52.154.171.250/32",
+      "52.154.170.28/32",
+      "52.154.170.122/32",
+      "52.143.243.117/32",
+      "52.143.247.235/32",
+      "52.154.171.235/32",
+      "52.154.171.196/32",
+      "52.154.171.0/32",
+      "52.154.170.243/32",
+      "52.154.170.26/32",
+      "52.154.169.200/32",
+      "52.154.170.96/32",
+      "52.154.170.88/32",
+      "52.154.171.150/32",
+      "52.154.171.205/32",
+      "52.154.170.117/32",
+      "52.154.170.209/32",
+      "191.235.202.48/32",
+      "191.233.3.202/32",
+      "191.235.201.214/32",
+      "191.233.3.197/32",
+      "191.235.202.38/32",
+      "20.53.78.144/32",
+      "20.193.24.10/32",
+      "20.53.78.236/32",
+      "20.53.78.138/32",
+      "20.53.78.123/32",
+      "20.53.78.106/32",
+      "20.193.27.215/32",
+      "20.193.25.197/32",
+      "20.193.12.126/32",
+      "20.193.24.251/32",
+      "20.204.242.101/32",
+      "20.207.72.113/32",
+      "20.204.242.19/32",
+      "20.219.45.67/32",
+      "20.207.72.11/32",
+      "20.219.45.190/32",
+      "20.204.243.55/32",
+      "20.204.241.148/32",
+      "20.207.72.110/32",
+      "20.204.240.172/32",
+      "20.207.72.21/32",
+      "20.204.246.81/32",
+      "20.207.107.181/32",
+      "20.204.246.254/32",
+      "20.219.43.246/32",
+      "52.149.25.43/32",
+      "52.149.61.51/32",
+      "52.149.58.139/32",
+      "52.149.60.38/32",
+      "52.148.165.38/32",
+      "52.143.95.162/32",
+      "52.149.56.151/32",
+      "52.149.30.45/32",
+      "52.149.58.173/32",
+      "52.143.95.204/32",
+      "52.149.28.83/32",
+      "52.149.58.69/32",
+      "52.148.161.87/32",
+      "52.149.58.27/32",
+      "52.149.28.18/32",
+      "20.79.226.26/32",
+      "20.79.239.66/32",
+      "20.79.238.198/32",
+      "20.113.14.159/32",
+      "20.75.144.152/32",
+      "20.43.172.120/32",
+      "20.53.134.160/32",
+      "20.201.15.208/32",
+      "20.93.28.24/32",
+      "20.61.34.40/32",
+      "52.242.224.168/32",
+      "20.80.129.80/32",
+      "20.195.108.47/32",
+      "4.195.133.120/32",
+      "4.228.76.163/32",
+      "4.182.131.108/32",
+      "4.209.224.56/32",
+      "108.141.83.74/32",
+      "4.213.46.14/32",
+      "172.169.17.165/32",
+      "51.8.71.117/32",
+      "20.3.1.178/32",
+      "52.149.56.151/32",
+      "52.149.30.45/32",
+      "52.149.58.173/32",
+      "52.143.95.204/32",
+      "52.149.28.83/32",
+      "52.149.58.69/32",
+      "52.148.161.87/32",
+      "52.149.58.27/32",
+      "52.149.28.18/32",
+      "20.79.226.26/32",
+      "20.79.239.66/32",
+      "20.79.238.198/32",
+      "20.113.14.159/32",
+      "20.75.144.152/32",
+      "20.43.172.120/32",
+      "20.53.134.160/32",
+      "20.201.15.208/32",
+      "20.93.28.24/32",
+      "20.61.34.40/32",
+      "52.242.224.168/32",
+      "20.80.129.80/32",
+      "20.195.108.47/32",
+      "4.195.133.120/32",
+      "4.228.76.163/32",
+      "4.182.131.108/32",
+      "4.209.224.56/32",
+      "108.141.83.74/32",
+      "4.213.46.14/32",
+      "172.169.17.165/32",
+      "51.8.71.117/32",
+      "20.3.1.178/32",
+    ]

data/crawlers/googlebot.yaml

@@ -2,262 +2,263 @@
   user_agent_regex: \+http\://www\.google\.com/bot\.html
   action: ALLOW
   # https://developers.google.com/static/search/apis/ipranges/googlebot.json
-  remote_addresses: [
-    "2001:4860:4801:10::/64",
-    "2001:4860:4801:11::/64",
-    "2001:4860:4801:12::/64",
-    "2001:4860:4801:13::/64",
-    "2001:4860:4801:14::/64",
-    "2001:4860:4801:15::/64",
-    "2001:4860:4801:16::/64",
-    "2001:4860:4801:17::/64",
-    "2001:4860:4801:18::/64",
-    "2001:4860:4801:19::/64",
-    "2001:4860:4801:1a::/64",
-    "2001:4860:4801:1b::/64",
-    "2001:4860:4801:1c::/64",
-    "2001:4860:4801:1d::/64",
-    "2001:4860:4801:1e::/64",
-    "2001:4860:4801:1f::/64",
-    "2001:4860:4801:20::/64",
-    "2001:4860:4801:21::/64",
-    "2001:4860:4801:22::/64",
-    "2001:4860:4801:23::/64",
-    "2001:4860:4801:24::/64",
-    "2001:4860:4801:25::/64",
-    "2001:4860:4801:26::/64",
-    "2001:4860:4801:27::/64",
-    "2001:4860:4801:28::/64",
-    "2001:4860:4801:29::/64",
-    "2001:4860:4801:2::/64",
-    "2001:4860:4801:2a::/64",
-    "2001:4860:4801:2b::/64",
-    "2001:4860:4801:2c::/64",
-    "2001:4860:4801:2d::/64",
-    "2001:4860:4801:2e::/64",
-    "2001:4860:4801:2f::/64",
-    "2001:4860:4801:31::/64",
-    "2001:4860:4801:32::/64",
-    "2001:4860:4801:33::/64",
-    "2001:4860:4801:34::/64",
-    "2001:4860:4801:35::/64",
-    "2001:4860:4801:36::/64",
-    "2001:4860:4801:37::/64",
-    "2001:4860:4801:38::/64",
-    "2001:4860:4801:39::/64",
-    "2001:4860:4801:3a::/64",
-    "2001:4860:4801:3b::/64",
-    "2001:4860:4801:3c::/64",
-    "2001:4860:4801:3d::/64",
-    "2001:4860:4801:3e::/64",
-    "2001:4860:4801:40::/64",
-    "2001:4860:4801:41::/64",
-    "2001:4860:4801:42::/64",
-    "2001:4860:4801:43::/64",
-    "2001:4860:4801:44::/64",
-    "2001:4860:4801:45::/64",
-    "2001:4860:4801:46::/64",
-    "2001:4860:4801:47::/64",
-    "2001:4860:4801:48::/64",
-    "2001:4860:4801:49::/64",
-    "2001:4860:4801:4a::/64",
-    "2001:4860:4801:4b::/64",
-    "2001:4860:4801:4c::/64",
-    "2001:4860:4801:50::/64",
-    "2001:4860:4801:51::/64",
-    "2001:4860:4801:52::/64",
-    "2001:4860:4801:53::/64",
-    "2001:4860:4801:54::/64",
-    "2001:4860:4801:55::/64",
-    "2001:4860:4801:56::/64",
-    "2001:4860:4801:60::/64",
-    "2001:4860:4801:61::/64",
-    "2001:4860:4801:62::/64",
-    "2001:4860:4801:63::/64",
-    "2001:4860:4801:64::/64",
-    "2001:4860:4801:65::/64",
-    "2001:4860:4801:66::/64",
-    "2001:4860:4801:67::/64",
-    "2001:4860:4801:68::/64",
-    "2001:4860:4801:69::/64",
-    "2001:4860:4801:6a::/64",
-    "2001:4860:4801:6b::/64",
-    "2001:4860:4801:6c::/64",
-    "2001:4860:4801:6d::/64",
-    "2001:4860:4801:6e::/64",
-    "2001:4860:4801:6f::/64",
-    "2001:4860:4801:70::/64",
-    "2001:4860:4801:71::/64",
-    "2001:4860:4801:72::/64",
-    "2001:4860:4801:73::/64",
-    "2001:4860:4801:74::/64",
-    "2001:4860:4801:75::/64",
-    "2001:4860:4801:76::/64",
-    "2001:4860:4801:77::/64",
-    "2001:4860:4801:78::/64",
-    "2001:4860:4801:79::/64",
-    "2001:4860:4801:80::/64",
-    "2001:4860:4801:81::/64",
-    "2001:4860:4801:82::/64",
-    "2001:4860:4801:83::/64",
-    "2001:4860:4801:84::/64",
-    "2001:4860:4801:85::/64",
-    "2001:4860:4801:86::/64",
-    "2001:4860:4801:87::/64",
-    "2001:4860:4801:88::/64",
-    "2001:4860:4801:90::/64",
-    "2001:4860:4801:91::/64",
-    "2001:4860:4801:92::/64",
-    "2001:4860:4801:93::/64",
-    "2001:4860:4801:94::/64",
-    "2001:4860:4801:95::/64",
-    "2001:4860:4801:96::/64",
-    "2001:4860:4801:a0::/64",
-    "2001:4860:4801:a1::/64",
-    "2001:4860:4801:a2::/64",
-    "2001:4860:4801:a3::/64",
-    "2001:4860:4801:a4::/64",
-    "2001:4860:4801:a5::/64",
-    "2001:4860:4801:c::/64",
-    "2001:4860:4801:f::/64",
-    "192.178.5.0/27",
-    "192.178.6.0/27",
-    "192.178.6.128/27",
-    "192.178.6.160/27",
-    "192.178.6.192/27",
-    "192.178.6.32/27",
-    "192.178.6.64/27",
-    "192.178.6.96/27",
-    "34.100.182.96/28",
-    "34.101.50.144/28",
-    "34.118.254.0/28",
-    "34.118.66.0/28",
-    "34.126.178.96/28",
-    "34.146.150.144/28",
-    "34.147.110.144/28",
-    "34.151.74.144/28",
-    "34.152.50.64/28",
-    "34.154.114.144/28",
-    "34.155.98.32/28",
-    "34.165.18.176/28",
-    "34.175.160.64/28",
-    "34.176.130.16/28",
-    "34.22.85.0/27",
-    "34.64.82.64/28",
-    "34.65.242.112/28",
-    "34.80.50.80/28",
-    "34.88.194.0/28",
-    "34.89.10.80/28",
-    "34.89.198.80/28",
-    "34.96.162.48/28",
-    "35.247.243.240/28",
-    "66.249.64.0/27",
-    "66.249.64.128/27",
-    "66.249.64.160/27",
-    "66.249.64.224/27",
-    "66.249.64.32/27",
-    "66.249.64.64/27",
-    "66.249.64.96/27",
-    "66.249.65.0/27",
-    "66.249.65.128/27",
-    "66.249.65.160/27",
-    "66.249.65.192/27",
-    "66.249.65.224/27",
-    "66.249.65.32/27",
-    "66.249.65.64/27",
-    "66.249.65.96/27",
-    "66.249.66.0/27",
-    "66.249.66.128/27",
-    "66.249.66.160/27",
-    "66.249.66.192/27",
-    "66.249.66.224/27",
-    "66.249.66.32/27",
-    "66.249.66.64/27",
-    "66.249.66.96/27",
-    "66.249.68.0/27",
-    "66.249.68.128/27",
-    "66.249.68.32/27",
-    "66.249.68.64/27",
-    "66.249.68.96/27",
-    "66.249.69.0/27",
-    "66.249.69.128/27",
-    "66.249.69.160/27",
-    "66.249.69.192/27",
-    "66.249.69.224/27",
-    "66.249.69.32/27",
-    "66.249.69.64/27",
-    "66.249.69.96/27",
-    "66.249.70.0/27",
-    "66.249.70.128/27",
-    "66.249.70.160/27",
-    "66.249.70.192/27",
-    "66.249.70.224/27",
-    "66.249.70.32/27",
-    "66.249.70.64/27",
-    "66.249.70.96/27",
-    "66.249.71.0/27",
-    "66.249.71.128/27",
-    "66.249.71.160/27",
-    "66.249.71.192/27",
-    "66.249.71.224/27",
-    "66.249.71.32/27",
-    "66.249.71.64/27",
-    "66.249.71.96/27",
-    "66.249.72.0/27",
-    "66.249.72.128/27",
-    "66.249.72.160/27",
-    "66.249.72.192/27",
-    "66.249.72.224/27",
-    "66.249.72.32/27",
-    "66.249.72.64/27",
-    "66.249.72.96/27",
-    "66.249.73.0/27",
-    "66.249.73.128/27",
-    "66.249.73.160/27",
-    "66.249.73.192/27",
-    "66.249.73.224/27",
-    "66.249.73.32/27",
-    "66.249.73.64/27",
-    "66.249.73.96/27",
-    "66.249.74.0/27",
-    "66.249.74.128/27",
-    "66.249.74.160/27",
-    "66.249.74.192/27",
-    "66.249.74.32/27",
-    "66.249.74.64/27",
-    "66.249.74.96/27",
-    "66.249.75.0/27",
-    "66.249.75.128/27",
-    "66.249.75.160/27",
-    "66.249.75.192/27",
-    "66.249.75.224/27",
-    "66.249.75.32/27",
-    "66.249.75.64/27",
-    "66.249.75.96/27",
-    "66.249.76.0/27",
-    "66.249.76.128/27",
-    "66.249.76.160/27",
-    "66.249.76.192/27",
-    "66.249.76.224/27",
-    "66.249.76.32/27",
-    "66.249.76.64/27",
-    "66.249.76.96/27",
-    "66.249.77.0/27",
-    "66.249.77.128/27",
-    "66.249.77.160/27",
-    "66.249.77.192/27",
-    "66.249.77.224/27",
-    "66.249.77.32/27",
-    "66.249.77.64/27",
-    "66.249.77.96/27",
-    "66.249.78.0/27",
-    "66.249.78.32/27",
-    "66.249.79.0/27",
-    "66.249.79.128/27",
-    "66.249.79.160/27",
-    "66.249.79.192/27",
-    "66.249.79.224/27",
-    "66.249.79.32/27",
-    "66.249.79.64/27",
-    "66.249.79.96/27"
-  ]
+  remote_addresses:
+    [
+      "2001:4860:4801:10::/64",
+      "2001:4860:4801:11::/64",
+      "2001:4860:4801:12::/64",
+      "2001:4860:4801:13::/64",
+      "2001:4860:4801:14::/64",
+      "2001:4860:4801:15::/64",
+      "2001:4860:4801:16::/64",
+      "2001:4860:4801:17::/64",
+      "2001:4860:4801:18::/64",
+      "2001:4860:4801:19::/64",
+      "2001:4860:4801:1a::/64",
+      "2001:4860:4801:1b::/64",
+      "2001:4860:4801:1c::/64",
+      "2001:4860:4801:1d::/64",
+      "2001:4860:4801:1e::/64",
+      "2001:4860:4801:1f::/64",
+      "2001:4860:4801:20::/64",
+      "2001:4860:4801:21::/64",
+      "2001:4860:4801:22::/64",
+      "2001:4860:4801:23::/64",
+      "2001:4860:4801:24::/64",
+      "2001:4860:4801:25::/64",
+      "2001:4860:4801:26::/64",
+      "2001:4860:4801:27::/64",
+      "2001:4860:4801:28::/64",
+      "2001:4860:4801:29::/64",
+      "2001:4860:4801:2::/64",
+      "2001:4860:4801:2a::/64",
+      "2001:4860:4801:2b::/64",
+      "2001:4860:4801:2c::/64",
+      "2001:4860:4801:2d::/64",
+      "2001:4860:4801:2e::/64",
+      "2001:4860:4801:2f::/64",
+      "2001:4860:4801:31::/64",
+      "2001:4860:4801:32::/64",
+      "2001:4860:4801:33::/64",
+      "2001:4860:4801:34::/64",
+      "2001:4860:4801:35::/64",
+      "2001:4860:4801:36::/64",
+      "2001:4860:4801:37::/64",
+      "2001:4860:4801:38::/64",
+      "2001:4860:4801:39::/64",
+      "2001:4860:4801:3a::/64",
+      "2001:4860:4801:3b::/64",
+      "2001:4860:4801:3c::/64",
+      "2001:4860:4801:3d::/64",
+      "2001:4860:4801:3e::/64",
+      "2001:4860:4801:40::/64",
+      "2001:4860:4801:41::/64",
+      "2001:4860:4801:42::/64",
+      "2001:4860:4801:43::/64",
+      "2001:4860:4801:44::/64",
+      "2001:4860:4801:45::/64",
+      "2001:4860:4801:46::/64",
+      "2001:4860:4801:47::/64",
+      "2001:4860:4801:48::/64",
+      "2001:4860:4801:49::/64",
+      "2001:4860:4801:4a::/64",
+      "2001:4860:4801:4b::/64",
+      "2001:4860:4801:4c::/64",
+      "2001:4860:4801:50::/64",
+      "2001:4860:4801:51::/64",
+      "2001:4860:4801:52::/64",
+      "2001:4860:4801:53::/64",
+      "2001:4860:4801:54::/64",
+      "2001:4860:4801:55::/64",
+      "2001:4860:4801:56::/64",
+      "2001:4860:4801:60::/64",
+      "2001:4860:4801:61::/64",
+      "2001:4860:4801:62::/64",
+      "2001:4860:4801:63::/64",
+      "2001:4860:4801:64::/64",
+      "2001:4860:4801:65::/64",
+      "2001:4860:4801:66::/64",
+      "2001:4860:4801:67::/64",
+      "2001:4860:4801:68::/64",
+      "2001:4860:4801:69::/64",
+      "2001:4860:4801:6a::/64",
+      "2001:4860:4801:6b::/64",
+      "2001:4860:4801:6c::/64",
+      "2001:4860:4801:6d::/64",
+      "2001:4860:4801:6e::/64",
+      "2001:4860:4801:6f::/64",
+      "2001:4860:4801:70::/64",
+      "2001:4860:4801:71::/64",
+      "2001:4860:4801:72::/64",
+      "2001:4860:4801:73::/64",
+      "2001:4860:4801:74::/64",
+      "2001:4860:4801:75::/64",
+      "2001:4860:4801:76::/64",
+      "2001:4860:4801:77::/64",
+      "2001:4860:4801:78::/64",
+      "2001:4860:4801:79::/64",
+      "2001:4860:4801:80::/64",
+      "2001:4860:4801:81::/64",
+      "2001:4860:4801:82::/64",
+      "2001:4860:4801:83::/64",
+      "2001:4860:4801:84::/64",
+      "2001:4860:4801:85::/64",
+      "2001:4860:4801:86::/64",
+      "2001:4860:4801:87::/64",
+      "2001:4860:4801:88::/64",
+      "2001:4860:4801:90::/64",
+      "2001:4860:4801:91::/64",
+      "2001:4860:4801:92::/64",
+      "2001:4860:4801:93::/64",
+      "2001:4860:4801:94::/64",
+      "2001:4860:4801:95::/64",
+      "2001:4860:4801:96::/64",
+      "2001:4860:4801:a0::/64",
+      "2001:4860:4801:a1::/64",
+      "2001:4860:4801:a2::/64",
+      "2001:4860:4801:a3::/64",
+      "2001:4860:4801:a4::/64",
+      "2001:4860:4801:a5::/64",
+      "2001:4860:4801:c::/64",
+      "2001:4860:4801:f::/64",
+      "192.178.5.0/27",
+      "192.178.6.0/27",
+      "192.178.6.128/27",
+      "192.178.6.160/27",
+      "192.178.6.192/27",
+      "192.178.6.32/27",
+      "192.178.6.64/27",
+      "192.178.6.96/27",
+      "34.100.182.96/28",
+      "34.101.50.144/28",
+      "34.118.254.0/28",
+      "34.118.66.0/28",
+      "34.126.178.96/28",
+      "34.146.150.144/28",
+      "34.147.110.144/28",
+      "34.151.74.144/28",
+      "34.152.50.64/28",
+      "34.154.114.144/28",
+      "34.155.98.32/28",
+      "34.165.18.176/28",
+      "34.175.160.64/28",
+      "34.176.130.16/28",
+      "34.22.85.0/27",
+      "34.64.82.64/28",
+      "34.65.242.112/28",
+      "34.80.50.80/28",
+      "34.88.194.0/28",
+      "34.89.10.80/28",
+      "34.89.198.80/28",
+      "34.96.162.48/28",
+      "35.247.243.240/28",
+      "66.249.64.0/27",
+      "66.249.64.128/27",
+      "66.249.64.160/27",
+      "66.249.64.224/27",
+      "66.249.64.32/27",
+      "66.249.64.64/27",
+      "66.249.64.96/27",
+      "66.249.65.0/27",
+      "66.249.65.128/27",
+      "66.249.65.160/27",
+      "66.249.65.192/27",
+      "66.249.65.224/27",
+      "66.249.65.32/27",
+      "66.249.65.64/27",
+      "66.249.65.96/27",
+      "66.249.66.0/27",
+      "66.249.66.128/27",
+      "66.249.66.160/27",
+      "66.249.66.192/27",
+      "66.249.66.224/27",
+      "66.249.66.32/27",
+      "66.249.66.64/27",
+      "66.249.66.96/27",
+      "66.249.68.0/27",
+      "66.249.68.128/27",
+      "66.249.68.32/27",
+      "66.249.68.64/27",
+      "66.249.68.96/27",
+      "66.249.69.0/27",
+      "66.249.69.128/27",
+      "66.249.69.160/27",
+      "66.249.69.192/27",
+      "66.249.69.224/27",
+      "66.249.69.32/27",
+      "66.249.69.64/27",
+      "66.249.69.96/27",
+      "66.249.70.0/27",
+      "66.249.70.128/27",
+      "66.249.70.160/27",
+      "66.249.70.192/27",
+      "66.249.70.224/27",
+      "66.249.70.32/27",
+      "66.249.70.64/27",
+      "66.249.70.96/27",
+      "66.249.71.0/27",
+      "66.249.71.128/27",
+      "66.249.71.160/27",
+      "66.249.71.192/27",
+      "66.249.71.224/27",
+      "66.249.71.32/27",
+      "66.249.71.64/27",
+      "66.249.71.96/27",
+      "66.249.72.0/27",
+      "66.249.72.128/27",
+      "66.249.72.160/27",
+      "66.249.72.192/27",
+      "66.249.72.224/27",
+      "66.249.72.32/27",
+      "66.249.72.64/27",
+      "66.249.72.96/27",
+      "66.249.73.0/27",
+      "66.249.73.128/27",
+      "66.249.73.160/27",
+      "66.249.73.192/27",
+      "66.249.73.224/27",
+      "66.249.73.32/27",
+      "66.249.73.64/27",
+      "66.249.73.96/27",
+      "66.249.74.0/27",
+      "66.249.74.128/27",
+      "66.249.74.160/27",
+      "66.249.74.192/27",
+      "66.249.74.32/27",
+      "66.249.74.64/27",
+      "66.249.74.96/27",
+      "66.249.75.0/27",
+      "66.249.75.128/27",
+      "66.249.75.160/27",
+      "66.249.75.192/27",
+      "66.249.75.224/27",
+      "66.249.75.32/27",
+      "66.249.75.64/27",
+      "66.249.75.96/27",
+      "66.249.76.0/27",
+      "66.249.76.128/27",
+      "66.249.76.160/27",
+      "66.249.76.192/27",
+      "66.249.76.224/27",
+      "66.249.76.32/27",
+      "66.249.76.64/27",
+      "66.249.76.96/27",
+      "66.249.77.0/27",
+      "66.249.77.128/27",
+      "66.249.77.160/27",
+      "66.249.77.192/27",
+      "66.249.77.224/27",
+      "66.249.77.32/27",
+      "66.249.77.64/27",
+      "66.249.77.96/27",
+      "66.249.78.0/27",
+      "66.249.78.32/27",
+      "66.249.79.0/27",
+      "66.249.79.128/27",
+      "66.249.79.160/27",
+      "66.249.79.192/27",
+      "66.249.79.224/27",
+      "66.249.79.32/27",
+      "66.249.79.64/27",
+      "66.249.79.96/27",
+    ]

data/crawlers/huawei-cloud.yaml

@@ -0,0 +1,617 @@
+- name: huawei-cloud
+  action: DENY
+  # Updated 2025-08-20 from IP addresses for AS136907
+  remote_addresses:
+    - 1.178.32.0/20
+    - 1.178.48.0/20
+    - 101.44.0.0/20
+    - 101.44.144.0/20
+    - 101.44.16.0/20
+    - 101.44.160.0/20
+    - 101.44.173.0/24
+    - 101.44.176.0/20
+    - 101.44.192.0/20
+    - 101.44.208.0/22
+    - 101.44.212.0/22
+    - 101.44.216.0/22
+    - 101.44.220.0/22
+    - 101.44.224.0/22
+    - 101.44.228.0/22
+    - 101.44.232.0/22
+    - 101.44.236.0/22
+    - 101.44.240.0/22
+    - 101.44.244.0/22
+    - 101.44.248.0/22
+    - 101.44.252.0/24
+    - 101.44.253.0/24
+    - 101.44.254.0/24
+    - 101.44.255.0/24
+    - 101.44.32.0/20
+    - 101.44.48.0/20
+    - 101.44.64.0/20
+    - 101.44.80.0/20
+    - 101.44.96.0/20
+    - 101.46.0.0/20
+    - 101.46.128.0/21
+    - 101.46.136.0/21
+    - 101.46.144.0/21
+    - 101.46.152.0/21
+    - 101.46.160.0/21
+    - 101.46.168.0/21
+    - 101.46.176.0/21
+    - 101.46.184.0/21
+    - 101.46.192.0/21
+    - 101.46.200.0/21
+    - 101.46.208.0/21
+    - 101.46.216.0/21
+    - 101.46.224.0/22
+    - 101.46.232.0/22
+    - 101.46.236.0/22
+    - 101.46.240.0/22
+    - 101.46.244.0/22
+    - 101.46.248.0/22
+    - 101.46.252.0/24
+    - 101.46.253.0/24
+    - 101.46.254.0/24
+    - 101.46.255.0/24
+    - 101.46.32.0/20
+    - 101.46.48.0/20
+    - 101.46.64.0/20
+    - 101.46.80.0/20
+    - 103.198.203.0/24
+    - 103.215.0.0/24
+    - 103.215.1.0/24
+    - 103.215.3.0/24
+    - 103.240.156.0/22
+    - 103.240.157.0/24
+    - 103.255.60.0/22
+    - 103.255.60.0/24
+    - 103.255.61.0/24
+    - 103.255.62.0/24
+    - 103.255.63.0/24
+    - 103.40.100.0/23
+    - 103.84.110.0/24
+    - 110.238.100.0/22
+    - 110.238.104.0/21
+    - 110.238.112.0/21
+    - 110.238.120.0/22
+    - 110.238.124.0/22
+    - 110.238.64.0/21
+    - 110.238.72.0/21
+    - 110.238.80.0/20
+    - 110.238.96.0/24
+    - 110.238.98.0/24
+    - 110.238.99.0/24
+    - 110.239.127.0/24
+    - 110.239.184.0/22
+    - 110.239.188.0/23
+    - 110.239.190.0/23
+    - 110.239.64.0/19
+    - 110.239.96.0/19
+    - 110.41.208.0/24
+    - 110.41.209.0/24
+    - 110.41.210.0/24
+    - 111.119.192.0/20
+    - 111.119.208.0/20
+    - 111.119.224.0/20
+    - 111.119.240.0/20
+    - 111.91.0.0/20
+    - 111.91.112.0/20
+    - 111.91.16.0/20
+    - 111.91.32.0/20
+    - 111.91.48.0/20
+    - 111.91.64.0/20
+    - 111.91.80.0/20
+    - 111.91.96.0/20
+    - 114.119.128.0/19
+    - 114.119.160.0/21
+    - 114.119.168.0/24
+    - 114.119.169.0/24
+    - 114.119.170.0/24
+    - 114.119.171.0/24
+    - 114.119.172.0/22
+    - 114.119.176.0/20
+    - 115.30.32.0/20
+    - 115.30.48.0/20
+    - 119.12.160.0/20
+    - 119.13.112.0/20
+    - 119.13.160.0/24
+    - 119.13.161.0/24
+    - 119.13.162.0/23
+    - 119.13.163.0/24
+    - 119.13.164.0/22
+    - 119.13.168.0/21
+    - 119.13.168.0/24
+    - 119.13.169.0/24
+    - 119.13.170.0/24
+    - 119.13.172.0/24
+    - 119.13.173.0/24
+    - 119.13.32.0/22
+    - 119.13.36.0/22
+    - 119.13.64.0/24
+    - 119.13.65.0/24
+    - 119.13.66.0/23
+    - 119.13.68.0/22
+    - 119.13.72.0/22
+    - 119.13.76.0/22
+    - 119.13.80.0/21
+    - 119.13.88.0/22
+    - 119.13.92.0/22
+    - 119.13.96.0/20
+    - 119.8.0.0/21
+    - 119.8.128.0/24
+    - 119.8.129.0/24
+    - 119.8.130.0/23
+    - 119.8.132.0/22
+    - 119.8.136.0/21
+    - 119.8.144.0/20
+    - 119.8.160.0/19
+    - 119.8.18.0/24
+    - 119.8.192.0/20
+    - 119.8.192.0/21
+    - 119.8.200.0/21
+    - 119.8.208.0/20
+    - 119.8.21.0/24
+    - 119.8.22.0/24
+    - 119.8.224.0/24
+    - 119.8.227.0/24
+    - 119.8.228.0/22
+    - 119.8.23.0/24
+    - 119.8.232.0/21
+    - 119.8.24.0/21
+    - 119.8.240.0/23
+    - 119.8.242.0/23
+    - 119.8.244.0/24
+    - 119.8.245.0/24
+    - 119.8.246.0/24
+    - 119.8.247.0/24
+    - 119.8.248.0/24
+    - 119.8.249.0/24
+    - 119.8.250.0/24
+    - 119.8.253.0/24
+    - 119.8.254.0/23
+    - 119.8.32.0/19
+    - 119.8.4.0/24
+    - 119.8.64.0/22
+    - 119.8.68.0/24
+    - 119.8.69.0/24
+    - 119.8.70.0/24
+    - 119.8.71.0/24
+    - 119.8.72.0/21
+    - 119.8.8.0/21
+    - 119.8.80.0/20
+    - 119.8.96.0/19
+    - 121.91.152.0/21
+    - 121.91.168.0/21
+    - 121.91.200.0/21
+    - 121.91.200.0/24
+    - 121.91.201.0/24
+    - 121.91.204.0/24
+    - 121.91.205.0/24
+    - 122.8.128.0/20
+    - 122.8.144.0/20
+    - 122.8.160.0/20
+    - 122.8.176.0/21
+    - 122.8.184.0/22
+    - 122.8.188.0/22
+    - 124.243.128.0/18
+    - 124.243.156.0/24
+    - 124.243.157.0/24
+    - 124.243.158.0/24
+    - 124.243.159.0/24
+    - 124.71.248.0/24
+    - 124.71.249.0/24
+    - 124.71.250.0/24
+    - 124.71.252.0/24
+    - 124.71.253.0/24
+    - 124.81.0.0/20
+    - 124.81.112.0/20
+    - 124.81.128.0/20
+    - 124.81.144.0/20
+    - 124.81.16.0/20
+    - 124.81.160.0/20
+    - 124.81.176.0/20
+    - 124.81.192.0/20
+    - 124.81.208.0/20
+    - 124.81.224.0/20
+    - 124.81.240.0/20
+    - 124.81.32.0/20
+    - 124.81.48.0/20
+    - 124.81.64.0/20
+    - 124.81.80.0/20
+    - 124.81.96.0/20
+    - 139.9.98.0/24
+    - 139.9.99.0/24
+    - 14.137.132.0/22
+    - 14.137.136.0/22
+    - 14.137.140.0/22
+    - 14.137.152.0/24
+    - 14.137.153.0/24
+    - 14.137.154.0/24
+    - 14.137.155.0/24
+    - 14.137.156.0/24
+    - 14.137.157.0/24
+    - 14.137.161.0/24
+    - 14.137.163.0/24
+    - 14.137.169.0/24
+    - 14.137.170.0/23
+    - 14.137.172.0/22
+    - 146.174.128.0/20
+    - 146.174.144.0/20
+    - 146.174.160.0/20
+    - 146.174.176.0/20
+    - 148.145.160.0/20
+    - 148.145.192.0/20
+    - 148.145.208.0/20
+    - 148.145.224.0/23
+    - 148.145.234.0/23
+    - 148.145.236.0/23
+    - 148.145.238.0/23
+    - 149.232.128.0/20
+    - 149.232.144.0/20
+    - 150.40.128.0/20
+    - 150.40.144.0/20
+    - 150.40.160.0/20
+    - 150.40.176.0/20
+    - 150.40.182.0/24
+    - 150.40.192.0/20
+    - 150.40.208.0/20
+    - 150.40.224.0/20
+    - 150.40.240.0/20
+    - 154.220.192.0/19
+    - 154.81.16.0/20
+    - 154.83.0.0/23
+    - 154.86.32.0/20
+    - 154.86.48.0/20
+    - 154.93.100.0/23
+    - 154.93.104.0/23
+    - 156.227.22.0/23
+    - 156.230.32.0/21
+    - 156.230.40.0/21
+    - 156.230.64.0/18
+    - 156.232.16.0/20
+    - 156.240.128.0/18
+    - 156.249.32.0/20
+    - 156.253.16.0/20
+    - 157.254.211.0/24
+    - 157.254.212.0/24
+    - 159.138.0.0/20
+    - 159.138.112.0/21
+    - 159.138.114.0/24
+    - 159.138.120.0/22
+    - 159.138.124.0/24
+    - 159.138.125.0/24
+    - 159.138.126.0/23
+    - 159.138.128.0/20
+    - 159.138.144.0/20
+    - 159.138.152.0/21
+    - 159.138.16.0/22
+    - 159.138.160.0/20
+    - 159.138.176.0/23
+    - 159.138.178.0/24
+    - 159.138.179.0/24
+    - 159.138.180.0/24
+    - 159.138.181.0/24
+    - 159.138.182.0/23
+    - 159.138.188.0/23
+    - 159.138.190.0/23
+    - 159.138.192.0/20
+    - 159.138.20.0/22
+    - 159.138.208.0/21
+    - 159.138.216.0/22
+    - 159.138.220.0/23
+    - 159.138.224.0/20
+    - 159.138.24.0/21
+    - 159.138.240.0/20
+    - 159.138.32.0/20
+    - 159.138.48.0/20
+    - 159.138.64.0/21
+    - 159.138.67.0/24
+    - 159.138.76.0/24
+    - 159.138.77.0/24
+    - 159.138.78.0/24
+    - 159.138.79.0/24
+    - 159.138.80.0/20
+    - 159.138.96.0/20
+    - 166.108.192.0/20
+    - 166.108.208.0/20
+    - 166.108.224.0/20
+    - 166.108.240.0/20
+    - 176.52.128.0/20
+    - 176.52.144.0/20
+    - 180.87.192.0/20
+    - 180.87.208.0/20
+    - 180.87.224.0/20
+    - 180.87.240.0/20
+    - 182.160.0.0/20
+    - 182.160.16.0/24
+    - 182.160.17.0/24
+    - 182.160.18.0/23
+    - 182.160.20.0/22
+    - 182.160.20.0/24
+    - 182.160.24.0/21
+    - 182.160.36.0/22
+    - 182.160.49.0/24
+    - 182.160.52.0/22
+    - 182.160.56.0/21
+    - 182.160.56.0/24
+    - 182.160.57.0/24
+    - 182.160.58.0/24
+    - 182.160.59.0/24
+    - 182.160.60.0/24
+    - 182.160.61.0/24
+    - 182.160.62.0/24
+    - 183.87.112.0/20
+    - 183.87.128.0/20
+    - 183.87.144.0/20
+    - 183.87.32.0/20
+    - 183.87.48.0/20
+    - 183.87.64.0/20
+    - 183.87.80.0/20
+    - 183.87.96.0/20
+    - 188.119.192.0/20
+    - 188.119.208.0/20
+    - 188.119.224.0/20
+    - 188.119.240.0/20
+    - 188.239.0.0/20
+    - 188.239.16.0/20
+    - 188.239.32.0/20
+    - 188.239.48.0/20
+    - 189.1.192.0/20
+    - 189.1.208.0/20
+    - 189.1.224.0/20
+    - 189.1.240.0/20
+    - 189.28.112.0/20
+    - 189.28.96.0/20
+    - 190.92.192.0/19
+    - 190.92.224.0/19
+    - 190.92.248.0/24
+    - 190.92.252.0/24
+    - 190.92.253.0/24
+    - 190.92.254.0/24
+    - 201.77.32.0/20
+    - 202.170.88.0/21
+    - 202.76.128.0/20
+    - 202.76.144.0/20
+    - 202.76.160.0/20
+    - 202.76.176.0/20
+    - 203.123.80.0/20
+    - 203.167.20.0/23
+    - 203.167.22.0/24
+    - 212.34.192.0/20
+    - 212.34.208.0/20
+    - 213.250.128.0/20
+    - 213.250.144.0/20
+    - 213.250.160.0/20
+    - 213.250.176.0/21
+    - 213.250.184.0/21
+    - 219.83.0.0/20
+    - 219.83.112.0/22
+    - 219.83.116.0/23
+    - 219.83.118.0/23
+    - 219.83.121.0/24
+    - 219.83.122.0/24
+    - 219.83.123.0/24
+    - 219.83.124.0/24
+    - 219.83.16.0/20
+    - 219.83.32.0/20
+    - 219.83.76.0/23
+    - 2404:a140:43::/48
+    - 2405:f080::/39
+    - 2405:f080:1::/48
+    - 2405:f080:1000::/39
+    - 2405:f080:1200::/39
+    - 2405:f080:1400::/48
+    - 2405:f080:1401::/48
+    - 2405:f080:1402::/48
+    - 2405:f080:1403::/48
+    - 2405:f080:1500::/40
+    - 2405:f080:1600::/48
+    - 2405:f080:1602::/48
+    - 2405:f080:1603::/48
+    - 2405:f080:1800::/39
+    - 2405:f080:1800::/44
+    - 2405:f080:1810::/48
+    - 2405:f080:1811::/48
+    - 2405:f080:1812::/48
+    - 2405:f080:1813::/48
+    - 2405:f080:1814::/48
+    - 2405:f080:1815::/48
+    - 2405:f080:1900::/40
+    - 2405:f080:1e02::/47
+    - 2405:f080:1e04::/47
+    - 2405:f080:1e06::/47
+    - 2405:f080:1e1e::/47
+    - 2405:f080:1e20::/47
+    - 2405:f080:200::/48
+    - 2405:f080:2000::/39
+    - 2405:f080:201::/48
+    - 2405:f080:202::/48
+    - 2405:f080:2040::/48
+    - 2405:f080:2200::/39
+    - 2405:f080:2280::/48
+    - 2405:f080:2281::/48
+    - 2405:f080:2282::/48
+    - 2405:f080:2283::/48
+    - 2405:f080:2284::/48
+    - 2405:f080:2285::/48
+    - 2405:f080:2286::/48
+    - 2405:f080:2287::/48
+    - 2405:f080:2288::/48
+    - 2405:f080:2289::/48
+    - 2405:f080:228a::/48
+    - 2405:f080:228b::/48
+    - 2405:f080:228c::/48
+    - 2405:f080:228d::/48
+    - 2405:f080:228e::/48
+    - 2405:f080:228f::/48
+    - 2405:f080:2400::/39
+    - 2405:f080:2600::/39
+    - 2405:f080:2800::/48
+    - 2405:f080:2a00::/48
+    - 2405:f080:2e00::/47
+    - 2405:f080:3000::/38
+    - 2405:f080:3000::/40
+    - 2405:f080:3100::/40
+    - 2405:f080:3200::/48
+    - 2405:f080:3201::/48
+    - 2405:f080:3202::/48
+    - 2405:f080:3203::/48
+    - 2405:f080:3204::/48
+    - 2405:f080:3205::/48
+    - 2405:f080:3400::/38
+    - 2405:f080:3400::/40
+    - 2405:f080:3500::/40
+    - 2405:f080:3600::/48
+    - 2405:f080:3601::/48
+    - 2405:f080:3602::/48
+    - 2405:f080:3603::/48
+    - 2405:f080:3604::/48
+    - 2405:f080:3605::/48
+    - 2405:f080:400::/39
+    - 2405:f080:4000::/40
+    - 2405:f080:4100::/48
+    - 2405:f080:4102::/48
+    - 2405:f080:4103::/48
+    - 2405:f080:4104::/48
+    - 2405:f080:4200::/40
+    - 2405:f080:4300::/40
+    - 2405:f080:600::/48
+    - 2405:f080:800::/40
+    - 2405:f080:810::/44
+    - 2405:f080:a00::/39
+    - 2405:f080:a11::/48
+    - 2405:f080:e02::/48
+    - 2405:f080:e03::/48
+    - 2405:f080:e04::/47
+    - 2405:f080:e05::/48
+    - 2405:f080:e06::/48
+    - 2405:f080:e07::/48
+    - 2405:f080:e0e::/47
+    - 2405:f080:e10::/47
+    - 2405:f080:edff::/48
+    - 27.106.0.0/20
+    - 27.106.112.0/20
+    - 27.106.16.0/20
+    - 27.106.32.0/20
+    - 27.106.48.0/20
+    - 27.106.64.0/20
+    - 27.106.80.0/20
+    - 27.106.96.0/20
+    - 27.255.0.0/23
+    - 27.255.10.0/23
+    - 27.255.12.0/23
+    - 27.255.14.0/23
+    - 27.255.16.0/23
+    - 27.255.18.0/23
+    - 27.255.2.0/23
+    - 27.255.20.0/23
+    - 27.255.22.0/23
+    - 27.255.26.0/23
+    - 27.255.28.0/23
+    - 27.255.30.0/23
+    - 27.255.32.0/23
+    - 27.255.34.0/23
+    - 27.255.36.0/23
+    - 27.255.38.0/23
+    - 27.255.4.0/23
+    - 27.255.40.0/23
+    - 27.255.42.0/23
+    - 27.255.44.0/23
+    - 27.255.46.0/23
+    - 27.255.48.0/23
+    - 27.255.50.0/23
+    - 27.255.52.0/23
+    - 27.255.54.0/23
+    - 27.255.58.0/23
+    - 27.255.6.0/23
+    - 27.255.60.0/23
+    - 27.255.62.0/23
+    - 27.255.8.0/23
+    - 42.201.128.0/20
+    - 42.201.144.0/20
+    - 42.201.160.0/20
+    - 42.201.176.0/20
+    - 42.201.192.0/20
+    - 42.201.208.0/20
+    - 42.201.224.0/20
+    - 42.201.240.0/20
+    - 43.225.140.0/22
+    - 43.255.104.0/22
+    - 45.194.104.0/21
+    - 45.199.144.0/22
+    - 45.202.128.0/19
+    - 45.202.160.0/20
+    - 45.202.176.0/21
+    - 45.202.184.0/21
+    - 45.203.40.0/21
+    - 46.250.160.0/20
+    - 46.250.176.0/20
+    - 49.0.192.0/21
+    - 49.0.200.0/21
+    - 49.0.224.0/22
+    - 49.0.228.0/22
+    - 49.0.232.0/21
+    - 49.0.240.0/20
+    - 62.245.0.0/20
+    - 62.245.16.0/20
+    - 80.238.128.0/22
+    - 80.238.132.0/22
+    - 80.238.136.0/22
+    - 80.238.140.0/22
+    - 80.238.144.0/22
+    - 80.238.148.0/22
+    - 80.238.152.0/22
+    - 80.238.156.0/22
+    - 80.238.164.0/22
+    - 80.238.164.0/24
+    - 80.238.165.0/24
+    - 80.238.168.0/22
+    - 80.238.168.0/24
+    - 80.238.169.0/24
+    - 80.238.170.0/24
+    - 80.238.171.0/24
+    - 80.238.172.0/22
+    - 80.238.176.0/22
+    - 80.238.180.0/24
+    - 80.238.181.0/24
+    - 80.238.183.0/24
+    - 80.238.184.0/24
+    - 80.238.185.0/24
+    - 80.238.186.0/24
+    - 80.238.190.0/24
+    - 80.238.192.0/20
+    - 80.238.208.0/20
+    - 80.238.224.0/20
+    - 80.238.240.0/20
+    - 83.101.0.0/21
+    - 83.101.104.0/21
+    - 83.101.16.0/21
+    - 83.101.24.0/21
+    - 83.101.32.0/21
+    - 83.101.48.0/21
+    - 83.101.56.0/23
+    - 83.101.58.0/23
+    - 83.101.64.0/21
+    - 83.101.72.0/21
+    - 83.101.8.0/23
+    - 83.101.80.0/21
+    - 83.101.88.0/24
+    - 83.101.89.0/24
+    - 83.101.96.0/21
+    - 87.119.12.0/24
+    - 89.150.192.0/20
+    - 89.150.208.0/20
+    - 94.244.128.0/20
+    - 94.244.144.0/20
+    - 94.244.160.0/20
+    - 94.244.176.0/20
+    - 94.45.160.0/19
+    - 94.45.160.0/24
+    - 94.45.161.0/24
+    - 94.45.163.0/24
+    - 94.74.112.0/21
+    - 94.74.120.0/21
+    - 94.74.64.0/20
+    - 94.74.80.0/20
+    - 94.74.96.0/20

data/crawlers/internet-archive.yaml

@@ -1,8 +1,4 @@
 - name: internet-archive
   action: ALLOW
   # https://ipinfo.io/AS7941
-  remote_addresses: [
-    "207.241.224.0/20",
-    "208.70.24.0/21",
-    "2620:0:9c0::/48"
-  ]
+  remote_addresses: ["207.241.224.0/20", "208.70.24.0/21", "2620:0:9c0::/48"]

data/crawlers/kagibot.yaml

@@ -2,9 +2,10 @@
   user_agent_regex: \+https\://kagi\.com/bot
   action: ALLOW
   # https://kagi.com/bot
-  remote_addresses: [
-    "216.18.205.234/32",
-    "35.212.27.76/32",
-    "104.254.65.50/32",
-    "209.151.156.194/32"
-  ]
+  remote_addresses:
+    [
+      "216.18.205.234/32",
+      "35.212.27.76/32",
+      "104.254.65.50/32",
+      "209.151.156.194/32",
+    ]

data/crawlers/marginalia.yaml

@@ -2,10 +2,11 @@
   user_agent_regex: search\.marginalia\.nu
   action: ALLOW
   # Received directly over email
-  remote_addresses: [
-    "193.183.0.162/31",
-    "193.183.0.164/30",
-    "193.183.0.168/30",
-    "193.183.0.172/31",
-    "193.183.0.174/32"
-  ]
+  remote_addresses:
+    [
+      "193.183.0.162/31",
+      "193.183.0.164/30",
+      "193.183.0.168/30",
+      "193.183.0.172/31",
+      "193.183.0.174/32",
+    ]

data/crawlers/mojeekbot.yaml

@@ -2,4 +2,4 @@
   user_agent_regex: \+https\://www\.mojeek\.com/bot\.html
   action: ALLOW
   # https://www.mojeek.com/bot.html
-  remote_addresses: [ "5.102.173.71/32" ]
+  remote_addresses: ["5.102.173.71/32"]

data/crawlers/openai-gptbot.yaml

@@ -4,13 +4,14 @@
   user_agent_regex: GPTBot/1\.1; \+https\://openai\.com/gptbot
   action: ALLOW
   # https://openai.com/gptbot.json
-  remote_addresses: [
-    "52.230.152.0/24",
-    "20.171.206.0/24",
-    "20.171.207.0/24",
-    "4.227.36.0/25",
-    "20.125.66.80/28",
-    "172.182.204.0/24",
-    "172.182.214.0/24",
-    "172.182.215.0/24",
-  ]
+  remote_addresses:
+    [
+      "52.230.152.0/24",
+      "20.171.206.0/24",
+      "20.171.207.0/24",
+      "4.227.36.0/25",
+      "20.125.66.80/28",
+      "172.182.204.0/24",
+      "172.182.214.0/24",
+      "172.182.215.0/24",
+    ]

data/crawlers/openai-searchbot.yaml

@@ -4,10 +4,11 @@
   user_agent_regex: OAI-SearchBot/1\.0; \+https\://openai\.com/searchbot
   action: ALLOW
   # https://openai.com/searchbot.json
-  remote_addresses: [
-    "20.42.10.176/28",
-    "172.203.190.128/28",
-    "104.210.140.128/28",
-    "51.8.102.0/24",
-    "135.234.64.0/24"
-  ]
+  remote_addresses:
+    [
+      "20.42.10.176/28",
+      "172.203.190.128/28",
+      "104.210.140.128/28",
+      "51.8.102.0/24",
+      "135.234.64.0/24",
+    ]

data/crawlers/perplexitybot.yaml

@@ -0,0 +1,17 @@
+# Indexing for search, does not collect training data
+# https://docs.perplexity.ai/guides/bots
+- name: perplexitybot
+  user_agent_regex: PerplexityBot/.+; \+https\://perplexity\.ai/perplexitybot
+  action: ALLOW
+  # https://www.perplexity.com/perplexitybot.json
+  remote_addresses:
+    [
+      "107.20.236.150/32",
+      "3.224.62.45/32",
+      "18.210.92.235/32",
+      "3.222.232.239/32",
+      "3.211.124.183/32",
+      "3.231.139.107/32",
+      "18.97.1.228/30",
+      "18.97.9.96/29",
+    ]

data/crawlers/qwantbot.yaml

@@ -2,4 +2,4 @@
   user_agent_regex: \+https\://help\.qwant\.com/bot/
   action: ALLOW
   # https://help.qwant.com/wp-content/uploads/sites/2/2025/01/qwantbot.json
-  remote_addresses: [ "91.242.162.0/24" ]
+  remote_addresses: ["91.242.162.0/24"]

data/crawlers/tencent-cloud.yaml

@@ -0,0 +1,165 @@
+# Tencent Cloud crawler IP ranges
+- name: tencent-cloud
+  action: DENY
+  remote_addresses:
+    - 101.32.0.0/17
+    - 101.32.176.0/20
+    - 101.32.192.0/18
+    - 101.33.116.0/22
+    - 101.33.120.0/21
+    - 101.33.16.0/20
+    - 101.33.2.0/23
+    - 101.33.32.0/19
+    - 101.33.4.0/22
+    - 101.33.64.0/19
+    - 101.33.8.0/21
+    - 101.33.96.0/20
+    - 119.28.28.0/24
+    - 119.29.29.0/24
+    - 124.156.0.0/16
+    - 129.226.0.0/18
+    - 129.226.128.0/18
+    - 129.226.224.0/19
+    - 129.226.96.0/19
+    - 150.109.0.0/18
+    - 150.109.128.0/20
+    - 150.109.160.0/19
+    - 150.109.192.0/18
+    - 150.109.64.0/20
+    - 150.109.80.0/21
+    - 150.109.88.0/22
+    - 150.109.96.0/19
+    - 162.14.60.0/22
+    - 162.62.0.0/18
+    - 162.62.128.0/20
+    - 162.62.144.0/21
+    - 162.62.152.0/22
+    - 162.62.172.0/22
+    - 162.62.176.0/20
+    - 162.62.192.0/19
+    - 162.62.255.0/24
+    - 162.62.80.0/20
+    - 162.62.96.0/19
+    - 170.106.0.0/16
+    - 43.128.0.0/14
+    - 43.132.0.0/22
+    - 43.132.12.0/22
+    - 43.132.128.0/17
+    - 43.132.16.0/22
+    - 43.132.28.0/22
+    - 43.132.32.0/22
+    - 43.132.40.0/22
+    - 43.132.52.0/22
+    - 43.132.60.0/24
+    - 43.132.64.0/22
+    - 43.132.69.0/24
+    - 43.132.70.0/23
+    - 43.132.72.0/21
+    - 43.132.80.0/21
+    - 43.132.88.0/22
+    - 43.132.92.0/23
+    - 43.132.96.0/19
+    - 43.133.0.0/16
+    - 43.134.0.0/16
+    - 43.135.0.0/17
+    - 43.135.128.0/18
+    - 43.135.192.0/19
+    - 43.152.0.0/21
+    - 43.152.11.0/24
+    - 43.152.12.0/22
+    - 43.152.128.0/22
+    - 43.152.133.0/24
+    - 43.152.134.0/23
+    - 43.152.136.0/21
+    - 43.152.144.0/20
+    - 43.152.160.0/22
+    - 43.152.16.0/21
+    - 43.152.164.0/23
+    - 43.152.166.0/24
+    - 43.152.168.0/21
+    - 43.152.178.0/23
+    - 43.152.180.0/22
+    - 43.152.184.0/21
+    - 43.152.192.0/18
+    - 43.152.24.0/22
+    - 43.152.31.0/24
+    - 43.152.32.0/23
+    - 43.152.35.0/24
+    - 43.152.36.0/22
+    - 43.152.40.0/21
+    - 43.152.48.0/20
+    - 43.152.74.0/23
+    - 43.152.76.0/22
+    - 43.152.80.0/22
+    - 43.152.8.0/23
+    - 43.152.92.0/23
+    - 43.153.0.0/16
+    - 43.154.0.0/15
+    - 43.156.0.0/15
+    - 43.158.0.0/16
+    - 43.159.0.0/20
+    - 43.159.128.0/17
+    - 43.159.64.0/23
+    - 43.159.70.0/23
+    - 43.159.72.0/21
+    - 43.159.81.0/24
+    - 43.159.82.0/23
+    - 43.159.85.0/24
+    - 43.159.86.0/23
+    - 43.159.88.0/21
+    - 43.159.96.0/19
+    - 43.160.0.0/15
+    - 43.162.0.0/16
+    - 43.163.0.0/17
+    - 43.163.128.0/18
+    - 43.163.192.255/32
+    - 43.163.193.0/24
+    - 43.163.194.0/23
+    - 43.163.196.0/22
+    - 43.163.200.0/21
+    - 43.163.208.0/20
+    - 43.163.224.0/19
+    - 43.164.0.0/18
+    - 43.164.128.0/17
+    - 43.165.0.0/16
+    - 43.166.128.0/18
+    - 43.166.224.0/19
+    - 43.168.0.0/20
+    - 43.168.16.0/21
+    - 43.168.24.0/22
+    - 43.168.255.0/24
+    - 43.168.32.0/19
+    - 43.168.64.0/20
+    - 43.168.80.0/22
+    - 43.169.0.0/16
+    - 43.170.0.0/16
+    - 43.174.0.0/18
+    - 43.174.128.0/17
+    - 43.174.64.0/22
+    - 43.174.68.0/23
+    - 43.174.71.0/24
+    - 43.174.74.0/23
+    - 43.174.76.0/22
+    - 43.174.80.0/20
+    - 43.174.96.0/19
+    - 43.175.0.0/20
+    - 43.175.113.0/24
+    - 43.175.114.0/23
+    - 43.175.116.0/22
+    - 43.175.120.0/21
+    - 43.175.128.0/18
+    - 43.175.16.0/22
+    - 43.175.192.0/20
+    - 43.175.20.0/23
+    - 43.175.208.0/21
+    - 43.175.216.0/22
+    - 43.175.220.0/23
+    - 43.175.22.0/24
+    - 43.175.222.0/24
+    - 43.175.224.0/20
+    - 43.175.25.0/24
+    - 43.175.26.0/23
+    - 43.175.28.0/22
+    - 43.175.32.0/19
+    - 43.175.64.0/19
+    - 43.175.96.0/20

data/crawlers/wikimedia-citoid.yaml

@@ -0,0 +1,18 @@
+# Wikimedia Foundation citation services
+# https://www.mediawiki.org/wiki/Citoid
+
+- name: wikimedia-citoid
+  user_agent_regex: "Citoid/WMF"
+  action: ALLOW
+  remote_addresses: [
+    "208.80.152.0/22",
+    "2620:0:860::/46",
+  ]
+
+- name: wikimedia-zotero-translation-server
+  user_agent_regex: "ZoteroTranslationServer/WMF"
+  action: ALLOW
+  remote_addresses: [
+    "208.80.152.0/22",
+    "2620:0:860::/46",
+  ]

data/crawlers/yandexbot.yaml

@@ -0,0 +1,6 @@
+- name: yandexbot
+  action: ALLOW
+  expression:
+    all:
+      - userAgent.matches("\\+http\\://yandex\\.com/bots")
+      - verifyFCrDNS(remoteAddress, "^.*\\.yandex\\.(ru|com|net)$")