Pre-release: v1.18.0-pre1

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

.github/workflows/docker.yml

@@ -74,7 +74,7 @@ jobs:
           SLOG_LEVEL: debug
       
       - name: Generate artifact attestation
-        uses: actions/attest-build-provenance@c074443f1aee8d4aeeae555aebba3282517141b2 # v2.2.3
+        uses: actions/attest-build-provenance@db473fddc028af60658334401dc6fa3ffd8669fd # v2.3.0
         with:
           subject-name: ghcr.io/techarohq/anubis
           subject-digest: ${{ steps.build.outputs.digest }}

.github/workflows/docs-deploy.yml

@@ -38,7 +38,7 @@ jobs:
 
       - name: Build and push
         id: build
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ./docs
           cache-to: type=gha
@@ -49,14 +49,14 @@ jobs:
           push: true
 
       - name: Apply k8s manifests to aeacus
-        uses: actions-hub/kubectl@9270913c29699788b51bc04becd0ebdf048ffb49 # v1.32.3
+        uses: actions-hub/kubectl@e81783053d902f50d752d21a6d99cf9689a652e1 # v1.33.0
         env:
           KUBE_CONFIG: ${{ secrets.AEACUS_KUBECONFIG }}
         with:
           args: apply -k docs/manifest
 
       - name: Apply k8s manifests to aeacus
-        uses: actions-hub/kubectl@9270913c29699788b51bc04becd0ebdf048ffb49 # v1.32.3
+        uses: actions-hub/kubectl@e81783053d902f50d752d21a6d99cf9689a652e1 # v1.33.0
         env:
           KUBE_CONFIG: ${{ secrets.AEACUS_KUBECONFIG }}
         with:

.github/workflows/docs-test.yml

@@ -28,7 +28,7 @@ jobs:
 
       - name: Build and push
         id: build
-        uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
         with:
           context: ./docs
           cache-to: type=gha

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

@@ -64,7 +64,7 @@ jobs:
 
     - name: Build Packages
       run: |
-        wget https://github.com/TecharoHQ/yeet/releases/download/v0.2.1/yeet_0.2.1_amd64.deb -O var/yeet.deb
+        wget https://github.com/TecharoHQ/yeet/releases/download/v0.2.2/yeet_0.2.2_amd64.deb -O var/yeet.deb
         sudo apt -y install -f ./var/yeet.deb
         rm ./var/yeet.deb
         yeet

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

@@ -66,7 +66,7 @@ jobs:
 
     - name: Build Packages
       run: |
-        wget https://github.com/TecharoHQ/yeet/releases/download/v0.2.1/yeet_0.2.1_amd64.deb -O var/yeet.deb
+        wget https://github.com/TecharoHQ/yeet/releases/download/v0.2.2/yeet_0.2.2_amd64.deb -O var/yeet.deb
         sudo apt -y install -f ./var/yeet.deb
         rm ./var/yeet.deb
         yeet

.github/workflows/zizmor.yml

@@ -21,7 +21,7 @@ jobs:
           persist-credentials: false
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5.4.2
+        uses: astral-sh/setup-uv@6b9c6063abd6010835644d4c2e1bef4cf5cd0fca # v6.0.1
 
       - name: Run zizmor 🌈
         run: uvx zizmor --format sarif . > results.sarif 
@@ -29,7 +29,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} 
 
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@45775bd8235c68ba998cffa5171334d58593da47 # v3.28.15
+        uses: github/codeql-action/upload-sarif@60168efe1c415ce0f5521ea06d5c2062adbeed1b # v3.28.17
         with:
           sarif_file: results.sarif
           category: zizmor

.github/zizmor.yml

@@ -0,0 +1,5 @@
+rules:
+  unpinned-uses:
+    config:
+      policies:
+        Homebrew/actions/*: any

.vscode/settings.json

@@ -0,0 +1,15 @@
+{
+  "github.copilot.enable": {
+    "*": false,
+    "plaintext": false,
+    "markdown": false,
+    "mdx": false,
+    "json": false,
+    "scminput": false,
+    "yaml": false,
+    "go": false,
+    "zig": false,
+    "javascript": false,
+    "properties": false
+  }
+}

README.md

@@ -15,6 +15,7 @@
 Anubis is brought to you by sponsors and donors like:
 
 [![Distrust](./docs/static/img/sponsors/distrust-logo.webp)](https://distrust.co)
+[![Terminal Trove](./docs/static/img/sponsors/terminal-trove.webp)](https://terminaltrove.com/?utm_campaign=github&utm_medium=referral&utm_content=anubis&utm_source=abgh)
 
 ## Overview
 

VERSION

@@ -1 +1 @@
-1.17.0
+1.18.0-pre1

anubis.go

@@ -1,6 +1,8 @@
 // Package anubis contains the version number of Anubis.
 package anubis
 
+import "time"
+
 // Version is the current version of Anubis.
 //
 // This variable is set at build time using the -X linker flag. If not set,
@@ -11,6 +13,9 @@ var Version = "devel"
 // access.
 const CookieName = "within.website-x-cmd-anubis-auth"
 
+// CookieDefaultExpirationTime is the amount of time before the cookie/JWT expires.
+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 = ""
 

cmd/anubis/main.go

@@ -43,6 +43,7 @@ var (
 	bindNetwork              = flag.String("bind-network", "tcp", "network family to bind HTTP to, e.g. unix, tcp")
 	challengeDifficulty      = flag.Int("difficulty", anubis.DefaultDifficulty, "difficulty of the challenge")
 	cookieDomain             = flag.String("cookie-domain", "", "if set, the top-level domain that the Anubis cookie will be valid for")
+	cookieExpiration         = flag.Duration("cookie-expiration-time", anubis.CookieDefaultExpirationTime, "The amount of time the authorization cookie is valid for")
 	cookiePartitioned        = flag.Bool("cookie-partitioned", false, "if true, sets the partitioned flag on Anubis cookies, enabling CHIPS support")
 	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")
@@ -59,6 +60,7 @@ var (
 	debugBenchmarkJS         = flag.Bool("debug-benchmark-js", false, "respond to every request with a challenge for benchmarking hashrate")
 	ogPassthrough            = flag.Bool("og-passthrough", false, "enable Open Graph tag passthrough")
 	ogTimeToLive             = flag.Duration("og-expiry-time", 24*time.Hour, "Open Graph tag cache expiration time")
+	ogCacheConsiderHost      = flag.Bool("og-cache-consider-host", false, "enable or disable the use of the host in the Open Graph tag cache")
 	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")
 )
@@ -205,16 +207,15 @@ func main() {
 		log.Fatalf("can't parse policy file: %v", err)
 	}
 
-	fmt.Println("Rule error IDs:")
+	ruleErrorIDs := make(map[string]string)
 	for _, rule := range policy.Bots {
 		if rule.Action != config.RuleDeny {
 			continue
 		}
 
 		hash := rule.Hash()
-		fmt.Printf("* %s: %s\n", rule.Name, hash)
+		ruleErrorIDs[rule.Name] = hash
 	}
-	fmt.Println()
 
 	// replace the bot policy rules with a single rule that always benchmarks
 	if *debugBenchmarkJS {
@@ -272,18 +273,20 @@ func main() {
 	}
 
 	s, err := libanubis.New(libanubis.Options{
-		BasePrefix:        *basePrefix,
-		Next:              rp,
-		Policy:            policy,
-		ServeRobotsTXT:    *robotsTxt,
-		PrivateKey:        priv,
-		CookieDomain:      *cookieDomain,
-		CookiePartitioned: *cookiePartitioned,
-		OGPassthrough:     *ogPassthrough,
-		OGTimeToLive:      *ogTimeToLive,
-		RedirectDomains:   redirectDomainsList,
-		Target:            *target,
-		WebmasterEmail:    *webmasterEmail,
+		BasePrefix:           *basePrefix,
+		Next:                 rp,
+		Policy:               policy,
+		ServeRobotsTXT:       *robotsTxt,
+		PrivateKey:           priv,
+		CookieDomain:         *cookieDomain,
+		CookieExpiration:     *cookieExpiration,
+		CookiePartitioned:    *cookiePartitioned,
+		OGPassthrough:        *ogPassthrough,
+		OGTimeToLive:         *ogTimeToLive,
+		RedirectDomains:      redirectDomainsList,
+		Target:               *target,
+		WebmasterEmail:       *webmasterEmail,
+		OGCacheConsidersHost: *ogCacheConsiderHost,
 	})
 	if err != nil {
 		log.Fatalf("can't construct libanubis.Server: %v", err)
@@ -320,6 +323,8 @@ func main() {
 		"og-passthrough", *ogPassthrough,
 		"og-expiry-time", *ogTimeToLive,
 		"base-prefix", *basePrefix,
+		"cookie-expiration-time", *cookieExpiration,
+		"rule-error-ids", ruleErrorIDs,
 	)
 
 	go func() {

data/apps/allow-api-routes.yaml

@@ -0,0 +1,6 @@
+- name: allow-api-routes
+  action: ALLOW
+  expression:
+    all:
+    - '!(method == "HEAD" || method == "GET")'
+    - path.startsWith("/api/")

data/botPolicies.json

@@ -1,40 +1,16 @@
 {
   "bots": [
+    {
+      "import": "(data)/bots/_deny-pathological.yaml"
+    },
     {
       "import": "(data)/bots/ai-robots-txt.yaml"
     },
     {
-      "import": "(data)/bots/cloudflare-workers.yaml"
+      "import": "(data)/crawlers/_allow-good.yaml"
     },
     {
-      "import": "(data)/bots/headless-browsers.yaml"
-    },
-    {
-      "import": "(data)/bots/us-ai-scraper.yaml"
-    },
-    {
-      "import": "(data)/crawlers/googlebot.yaml"
-    },
-    {
-      "import": "(data)/crawlers/bingbot.yaml"
-    },
-    {
-      "import": "(data)/crawlers/duckduckbot.yaml"
-    },
-    {
-      "import": "(data)/crawlers/qwantbot.yaml"
-    },
-    {
-      "import": "(data)/crawlers/internet-archive.yaml"
-    },
-    {
-      "import": "(data)/crawlers/kagibot.yaml"
-    },
-    {
-      "import": "(data)/crawlers/marginalia.yaml"
-    },
-    {
-      "import": "(data)/crawlers/mojeekbot.yaml"
+      "import": "(data)/bots/aggressive-brazilian-scrapers.yaml"
     },
     {
       "import": "(data)/common/keep-internet-working.yaml"
@@ -45,5 +21,9 @@
       "action": "CHALLENGE"
     }
   ],
-  "dnsbl": false
+  "dnsbl": false,
+  "status_codes": {
+    "CHALLENGE": 200,
+    "DENY": 200
+  }
 }

data/botPolicies.yaml

@@ -12,21 +12,24 @@
 
 bots:
 # Pathological bots to deny
-- # This correlates to data/bots/ai-robots-txt.yaml in the source tree
-  import: (data)/bots/ai-robots-txt.yaml
-- import: (data)/bots/cloudflare-workers.yaml 
-- import: (data)/bots/headless-browsers.yaml
-- import: (data)/bots/us-ai-scraper.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
 
-# Search engines to allow
-- import: (data)/crawlers/googlebot.yaml
-- import: (data)/crawlers/bingbot.yaml
-- import: (data)/crawlers/duckduckbot.yaml
-- import: (data)/crawlers/qwantbot.yaml
-- import: (data)/crawlers/internet-archive.yaml
-- import: (data)/crawlers/kagibot.yaml
-- import: (data)/crawlers/marginalia.yaml
-- import: (data)/crawlers/mojeekbot.yaml
+# Enforce https://github.com/ai-robots-txt/ai.robots.txt
+- import: (data)/bots/ai-robots-txt.yaml
+
+# Search engine crawlers to allow, defaults to:
+#   - Google (so they don't try to bypass Anubis)
+#   - Bing
+#   - DuckDuckGo
+#   - Qwant
+#   - The Internet Archive
+#   - Kagi
+#   - Marginalia
+#   - Mojeek
+- import: (data)/crawlers/_allow-good.yaml
 
 # Allow common "keeping the internet working" routes (well-known, favicon, robots.txt)
 - import: (data)/common/keep-internet-working.yaml
@@ -48,3 +51,11 @@ bots:
   action: CHALLENGE
 
 dnsbl: false
+
+# By default, send HTTP 200 back to clients that either get issued a challenge
+# or a denial. This seems weird, but this is load-bearing due to the fact that
+# the most aggressive scraper bots seem to really, really, want an HTTP 200 and
+# will stop sending requests once they get it.
+status_codes:
+  CHALLENGE: 200
+  DENY: 200 

data/bots/_deny-pathological.yaml

@@ -0,0 +1,3 @@
+- import: (data)/bots/cloudflare-workers.yaml
+- import: (data)/bots/headless-browsers.yaml
+- import: (data)/bots/us-ai-scraper.yaml

data/bots/aggressive-brazilian-scrapers.yaml

@@ -0,0 +1,28 @@
+- name: deny-aggressive-brazilian-scrapers
+  action: DENY
+  expression:
+    any:
+    # Internet Explorer should be out of support
+    - userAgent.contains("MSIE")
+    # Trident is the Internet Explorer browser engine
+    - userAgent.contains("Trident")
+    # Opera is a fork of chrome now
+    - userAgent.contains("Presto")
+    # Windows CE is discontinued
+    - userAgent.contains("Windows CE")
+    # Windows 95 is discontinued
+    - userAgent.contains("Windows 95")
+    # Windows 98 is discontinued
+    - userAgent.contains("Windows 98")
+    # Windows 9.x is discontinued
+    - userAgent.contains("Win 9x")
+    # Amazon does not have an Alexa Toolbar.
+    - userAgent.contains("Alexa Toolbar")
+- name: challenge-aggressive-brazilian-scrapers
+  action: CHALLENGE
+  expression:
+    any:
+    # This is not released, even Windows 11 calls itself Windows 10
+    - userAgent.contains("Windows NT 11.0")
+    # iPods are not in common use
+    - userAgent.contains("iPod")

data/bots/ai-robots-txt.yaml

@@ -1,4 +1,4 @@
 - name: "ai-robots-txt"
   user_agent_regex: >-
-    AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo Bot|Meta-ExternalAgent|Meta-ExternalFetcher|OAI-SearchBot|omgili|omgilibot|PanguBot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot
-  action: DENY
+    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity-User|PerplexityBot|PetalBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot
+  action: DENY

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

@@ -0,0 +1,9 @@
+# phrik in the Arch Linux IRC channels
+- name: archlinux-phrik
+  action: ALLOW
+  expression:
+    all:
+    - remoteAddress == "159.69.213.214"
+    - 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

@@ -0,0 +1,9 @@
+# chat in the gentoo IRC channels
+- name: gentoo-chat
+  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"

data/clients/git.yaml

@@ -0,0 +1,14 @@
+- name: allow-git-clients
+  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"

data/clients/go-get.yaml

@@ -0,0 +1,7 @@
+- name: go-get
+  action: ALLOW
+  expression:
+    all:
+    - userAgent.startsWith("Go-http-client/")
+    - '"go-get" in query'
+    - query["go-get"] == "1"

data/common/allow-api-like.yaml

@@ -0,0 +1,6 @@
+- name: allow-api-routes
+  action: ALLOW
+  expression:
+    all:
+    - '!(method == "HEAD" || method == "GET")'
+    - path.startsWith("/api/")

data/common/json-api.yaml

@@ -0,0 +1,7 @@
+- name: allow-api-requests
+  action: ALLOW
+  expression:
+    all:
+      - '"Accept" in headers'
+      - 'headers["Accept"] == "application/json"'
+      - 'path.startsWith("/api/")'

data/common/keep-internet-working.yaml

@@ -7,4 +7,7 @@
   action: ALLOW
 - name: robots-txt
   path_regex: ^/robots.txt$
+  action: ALLOW
+- name: sitemap
+  path_regex: ^/sitemap.xml$
   action: ALLOW

data/common/rfc-violations.yaml

@@ -0,0 +1,3 @@
+- name: no-user-agent-string
+  action: DENY
+  expression: userAgent == ""

data/crawlers/_allow-good.yaml

@@ -0,0 +1,8 @@
+- import: (data)/crawlers/googlebot.yaml
+- import: (data)/crawlers/bingbot.yaml
+- import: (data)/crawlers/duckduckbot.yaml
+- import: (data)/crawlers/qwantbot.yaml
+- import: (data)/crawlers/internet-archive.yaml
+- import: (data)/crawlers/kagibot.yaml
+- import: (data)/crawlers/marginalia.yaml
+- import: (data)/crawlers/mojeekbot.yaml

data/embed.go

@@ -3,6 +3,6 @@ package data
 import "embed"
 
 var (
-	//go:embed botPolicies.yaml botPolicies.json apps bots common crawlers
+	//go:embed botPolicies.yaml botPolicies.json all:apps all:bots all:clients all:common all:crawlers
 	BotPolicies embed.FS
 )

docs/docs/CHANGELOG.md

@@ -11,6 +11,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+- Use CSS variables to deduplicate styles
+- Fixed native packages not containing the stdlib and botPolicies.yaml
+- Change import syntax to allow multi-level imports
+- Changed the startup logging to use JSON formatting as all the other logs do.
+- Added the ability to do [expression matching with CEL](./admin/configuration/expressions.mdx)
+- Add a warning for clients that don't store cookies
+- Disable Open Graph passthrough by default ([#435](https://github.com/TecharoHQ/anubis/issues/435))
+- Clarify the license of the mascot images ([#442](https://github.com/TecharoHQ/anubis/issues/442))
+
+## v1.17.1: Asahi sas Brutus: Echo 1
+
+- Added customization of authorization cookie expiration time with `--cookie-expiration-time` flag or envvar
+- Updated the `OG_PASSTHROUGH` to be true by default, thereby allowing Open Graph tags to be passed through by default
+- Added the ability to [customize Anubis' HTTP status codes](./admin/configuration/custom-status-codes.mdx) ([#355](https://github.com/TecharoHQ/anubis/issues/355))
+
 ## v1.17.0: Asahi sas Brutus
 
 - Ensure regexes can't end in newlines ([#372](https://github.com/TecharoHQ/anubis/issues/372))
@@ -23,7 +38,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added support to allow to restrict the allowed redirect domains
 - Whitelisted [DuckDuckBot](https://duckduckgo.com/duckduckgo-help-pages/results/duckduckbot/) in botPolicies
 - Improvements to build scripts to make them less independent of the build host
-- Improved the OpenGraph error logging
+- Improved the Open Graph error logging
 - Added `Opera` to the `generic-browser` bot policy rule
 - Added FreeBSD rc.d script so can be run as a FreeBSD daemon
 - Allow requests from the Internet Archive
@@ -41,6 +56,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed mojeekbot user agent regex
 - Added support for running anubis behind a base path (e.g. `/myapp`)
 - Reduce Anubis' paranoia with user cookies ([#365](https://github.com/TecharoHQ/anubis/pull/365))
+- Added support for Open Graph passthrough while using unix sockets
+- The Open Graph subsystem now passes the HTTP `HOST` header through to the origin
+- Updated the `OG_PASSTHROUGH` to be true by default, thereby allowing Open Graph tags to be passed through by default
 
 ## v1.16.0
 
@@ -54,7 +72,7 @@ The following features are the "big ticket" items:
 - A prebaked tarball has been added, allowing distros to build Anubis like they could in v1.15.x
 - The placeholder Anubis mascot has been replaced with a design by [CELPHASE](https://bsky.app/profile/celphase.bsky.social)
 - Verification page now shows hash rate and a progress bar for completion probability
-- Added support for [OpenGraph tags](https://ogp.me/) when rendering the challenge page. This allows for social previews to be generated when sharing the challenge page on social media platforms ([#195](https://github.com/TecharoHQ/anubis/pull/195))
+- Added support for [Open Graph tags](https://ogp.me/) when rendering the challenge page. This allows for social previews to be generated when sharing the challenge page on social media platforms ([#195](https://github.com/TecharoHQ/anubis/pull/195))
 - Added support for passing the ed25519 signing key in a file with `-ed25519-private-key-hex-file` or `ED25519_PRIVATE_KEY_HEX_FILE`
 
 The other small fixes have been made:

docs/docs/admin/configuration/custom-status-codes.mdx

@@ -0,0 +1,19 @@
+# Custom status codes for Anubis errors
+
+Out of the box, Anubis will reply with `HTTP 200` for challenge and denial pages. This is intended to make AI scrapers have a hard time with your website because when they are faced with a non-200 response, they will hammer the page over and over until they get a 200 response. This behavior may not be desirable, as such Anubis lets you customize what HTTP status codes are returned when Anubis throws challenge and denial pages.
+
+This is configured in the `status_codes` block of your [bot policy file](../policies.mdx):
+
+```yaml
+status_codes:
+  CHALLENGE: 200
+  DENY: 200
+```
+
+To match CloudFlare's behavior, use a configuration like this:
+
+```yaml
+status_codes:
+  CHALLENGE: 403
+  DENY: 403
+```

docs/docs/admin/configuration/expressions.mdx

@@ -0,0 +1,150 @@
+# Expression-based rule matching
+
+Most of the Anubis matchers let you match individual parts of a request and only those parts in isolation. In order to defend a service in depth, you often need the ability to match against multiple aspects of a request. Anubis implements [Common Expression Language (CEL)](https://cel.dev) to let administrators define these more advanced rules. This allows you to tailor your approach for the individual services you are protecting.
+
+As an example, here is a rule that lets you allow JSON API requests through Anubis:
+
+```yaml
+- name: allow-api-requests
+  action: ALLOW
+  expression:
+    all:
+      - '"Accept" in headers'
+      - 'headers["Accept"] == "application/json"'
+      - 'path.startsWith("/api/")'
+```
+
+This is an advanced feature and as such it is easy to get yourself in trouble with it. Use this with care.
+
+## Common Expression Language (CEL)
+
+CEL is an expression language made by Google as a part of their access control lists system. As programs grow more complicated and users have the need to express more complicated security requirements, they often want the ability to just run a small bit of code to check things for themselves. CEL expressions are built for this. They are implicitly sandboxed so that they cannot affect the system they are running in and also designed to evaluate as fast as humanly possible.
+
+Imagine a CEL expression as the contents of an `if` statement in JavaScript or the `WHERE` clause in SQL. Consider this example expression:
+
+```python
+userAgent == ""
+```
+
+This is roughly equivalent to the following in JavaScript:
+
+```js
+if (userAgent == "") {
+  // Do something
+}
+```
+
+Using these expressions, you can define more elaborate rules as facts and circumstances demand. For more information about the syntax and grammar of CEL, take a look at [the language specification](https://github.com/google/cel-spec/blob/master/doc/langdef.md).
+
+## How Anubis uses CEL
+
+Anubis uses CEL to let administrators create complicated filter rules. Anubis has several modes of using CEL:
+
+- Validating requests against single expressions
+- Validating multiple expressions and ensuring at least one of them are true (`any`)
+- Validating multiple expressions and ensuring all of them are true (`all`)
+
+The common pattern is that every Anubis expression returns `true`, `false`, or raises an error.
+
+### Single expressions
+
+A single expression that returns either `true` or `false`. If the expression returns `true`, then the action specified in the rule will be taken. If it returns `false`, Anubis will move on to the next rule.
+
+For example, consider this rule:
+
+```yaml
+- name: no-user-agent-string
+  action: DENY
+  expression: userAgent == ""
+```
+
+For this rule, if a request comes in without a [`User-Agent` string](https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers/User-Agent) set, Anubis will deny the request and return an error page.
+
+### `any` blocks
+
+An `any` block that contains a list of expressions. If any expression in the list returns `true`, then the action specified in the rule will be taken. If all expressions in that list return `false`, Anubis will move on to the next rule.
+
+For example, consider this rule:
+
+```yaml
+- name: known-banned-user
+  action: DENY
+  expression:
+    any:
+      - remoteAddress == "8.8.8.8"
+      - remoteAddress == "1.1.1.1"
+```
+
+For this rule, if a request comes in from `8.8.8.8` or `1.1.1.1`, Anubis will deny the request and return an error page.
+
+#### `all` blocks
+
+An `all` block that contains a list of expressions. If all expressions in the list return `true`, then the action specified in the rule will be taken. If any of the expressions in the list returns `false`, Anubis will move on to the next rule.
+
+For example, consider this rule:
+
+```yaml
+- name: go-get
+  action: ALLOW
+  expression:
+    all:
+      - userAgent.startsWith("Go-http-client/")
+      - '"go-get" in query'
+      - query["go-get"] == "1"
+```
+
+For this rule, if a request comes in matching [the signature of the `go get` command](https://pkg.go.dev/cmd/go#hdr-Remote_import_paths), Anubis will allow it through to the target.
+
+## Variables exposed to Anubis expressions
+
+Anubis exposes the following variables to expressions:
+
+| Name            | Type                  | Explanation                                                                                                                               | Example                                                      |
+| :-------------- | :-------------------- | :---------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------- |
+| `headers`       | `map[string, string]` | The [headers](https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers) of the request being processed.                        | `{"User-Agent": "Mozilla/5.0 Gecko/20100101 Firefox/137.0"}` |
+| `host`          | `string`              | The [HTTP hostname](https://web.dev/articles/url-parts#host) the request is targeted to.                                                  | `anubis.techaro.lol`                                         |
+| `method`        | `string`              | The [HTTP method](https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Methods) in the request being processed.                    | `GET`, `POST`, `DELETE`, etc.                                |
+| `path`          | `string`              | The [path](https://web.dev/articles/url-parts#pathname) of the request being processed.                                                   | `/`, `/api/memes/create`                                     |
+| `query`         | `map[string, string]` | The [query parameters](https://web.dev/articles/url-parts#query) of the request being processed.                                          | `?foo=bar` -> `{"foo": "bar"}`                               |
+| `remoteAddress` | `string`              | The IP address of the client.                                                                                                             | `1.1.1.1`                                                    |
+| `userAgent`     | `string`              | The [`User-Agent`](https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers/User-Agent) string in the request being processed. | `Mozilla/5.0 Gecko/20100101 Firefox/137.0`                   |
+
+Of note: in many languages when you look up a key in a map and there is nothing there, the language will return some "falsy" value like `undefined` in JavaScript, `None` in Python, or the zero value of the type in Go. In CEL, if you try to look up a value that does not exist, execution of the expression will fail and Anubis will return an error.
+
+In order to avoid this, make sure the header or query parameter you are testing is present in the request with an `all` block like this:
+
+```yaml
+- name: challenge-wiki-history-page
+  action: CHALLENGE
+  all:
+    - 'path == "/index.php"'
+    - '"title" in query'
+    - '"action" in query'
+    - 'query["action"] == "history"
+```
+
+This rule throws a challenge if and only if all of the following conditions are true:
+
+- The URL path is `/index.php`
+- The URL query string contains a `title` value
+- The URL query string contains an `action` value
+- The URL query string's `action` value is `"history"`
+
+So given an HTTP request like this:
+
+```text
+GET /index.php?title=Index&action=history HTTP/1.1
+User-Agent: Mozilla/5.0 Gecko/20100101 Firefox/137.0
+Host: wiki.int.techaro.lol
+X-Real-Ip: 8.8.8.8
+```
+
+Anubis would return a challenge because all of those conditions are true.
+
+## Functions exposed to Anubis expressions
+
+There are currently no functions from the Anubis runtime exposed to expressions. This will change in the future.
+
+## Life advice
+
+Expressions are very powerful. This is a benefit and a burden. If you are not careful with your expression targeting, you will be liable to get yourself into trouble. If you are at all in doubt, throw a `CHALLENGE` over a `DENY`. Legitimate users can easily work around a `CHALLENGE` result with a [proof of work challenge](../../design/why-proof-of-work.mdx). Bots are less likely to be able to do this.

docs/docs/admin/configuration/import.mdx

@@ -79,6 +79,45 @@ config.BotOrImport: rule definition is invalid, you must set either bot rules or
 
 Paths can either be prefixed with `(data)` to import from the [the data folder in the Anubis source tree](https://github.com/TecharoHQ/anubis/tree/main/data) or anywhere on the filesystem. If you don't have access to the Anubis source tree, check /usr/share/docs/anubis/data or in the tarball you extracted Anubis from.
 
+## Importing from imports
+
+You can also import from an imported file in case you want to import an entire folder of rules at once.
+
+<Tabs>
+<TabItem value="json" label="JSON">
+
+```json
+{
+  "bots": [
+    {
+      "import": "(data)/bots/_deny-pathological.yaml"
+    }
+  ]
+}
+```
+
+</TabItem>
+<TabItem value="yaml" label="YAML" default>
+
+```yaml
+bots:
+  - import: (data)/bots/_deny-pathological.yaml
+```
+
+</TabItem>
+</Tabs>
+
+This lets you import an entire ruleset at once:
+
+```yaml
+# (data)/bots/_deny-pathological.yaml
+- import: (data)/bots/cloudflare-workers.yaml
+- import: (data)/bots/headless-browsers.yaml
+- import: (data)/bots/us-ai-scraper.yaml
+```
+
+Use this with care, you can easily get yourself into a state where Anubis recursively imports things for eternity if you are not careful. The best way to use this is to make a "root import" named `_everything.yaml` or `_allow-good.yaml` so they sort to the top. Name your meta-imports after the main verb they are enforcing so that you can glance at the configuration file and understand what it's doing.
+
 ## Writing snippets
 
 Snippets can be written in either JSON or YAML, with a preference for YAML. When writing a snippet, write the bot rules you want directly at the top level of the file in a list.

docs/docs/admin/configuration/open-graph.mdx

@@ -5,14 +5,15 @@ title: Open Graph Configuration
 
 # Open Graph Configuration
 
-This page provides detailed information on how to configure [OpenGraph tag](https://ogp.me/) passthrough in Anubis. This enables social previews of resources protected by Anubis without having to exempt each scraper individually.
+This page provides detailed information on how to configure [Open Graph tag](https://ogp.me/) passthrough in Anubis. This enables social previews of resources protected by Anubis without having to exempt each scraper individually.
 
 ## Configuration Options
 
-| Name             | Description                                               | Type     | Default | Example                 |
-|------------------|-----------------------------------------------------------|----------|---------|-------------------------|
-| `OG_PASSTHROUGH` | Enables or disables the Open Graph tag passthrough system | Boolean  | `false` | `OG_PASSTHROUGH=true`   |
-| `OG_EXPIRY_TIME` | Configurable cache expiration time for Open Graph tags    | Duration | `24h`   | `OG_EXPIRY_TIME=1h`     |
+| Name                     | Description                                               | Type     | Default | Example                       |
+| ------------------------ | --------------------------------------------------------- | -------- | ------- | ----------------------------- |
+| `OG_PASSTHROUGH`         | Enables or disables the Open Graph tag passthrough system | Boolean  | `true`  | `OG_PASSTHROUGH=true`         |
+| `OG_EXPIRY_TIME`         | Configurable cache expiration time for Open Graph tags    | Duration | `24h`   | `OG_EXPIRY_TIME=1h`           |
+| `OG_CACHE_CONSIDER_HOST` | Enables or disables the use of the host in the cache key  | Boolean  | `false` | `OG_CACHE_CONSIDER_HOST=true` |
 
 ## Usage
 
@@ -21,6 +22,7 @@ To configure Open Graph tags, you can set the following environment variables, e
 ```sh
 export OG_PASSTHROUGH=true
 export OG_EXPIRY_TIME=1h
+export OG_CACHE_CONSIDER_HOST=false
 ```
 
 ## Implementation Details
@@ -33,6 +35,8 @@ When `OG_PASSTHROUGH` is enabled, Anubis will:
 
 The cache expiration time is controlled by `OG_EXPIRY_TIME`.
 
+When `OG_CACHE_CONSIDER_HOST` is enabled, Anubis will include the host in the cache key for Open Graph tags. This ensures that tags are cached separately for different hosts.
+
 ## Example
 
 Here is an example of how to configure Open Graph tags in your Anubis setup:
@@ -40,8 +44,19 @@ Here is an example of how to configure Open Graph tags in your Anubis setup:
 ```sh
 export OG_PASSTHROUGH=true
 export OG_EXPIRY_TIME=1h
+export OG_CACHE_CONSIDER_HOST=false
 ```
 
-With these settings, Anubis will cache Open Graph tags for 1 hour and pass them through to the challenge page.
+With these settings, Anubis will cache Open Graph tags for 1 hour and pass them through to the challenge page, not considering the host in the cache key.
+
+## When to Enable `OG_CACHE_CONSIDER_HOST`
+
+In most cases, you would want to keep `OG_CACHE_CONSIDER_HOST` set to `false` to avoid unnecessary cache fragmentation. However, there are some scenarios where enabling this option can be beneficial:
+
+1. **Multi-Tenant Applications**: If you are running a multi-tenant application where different tenants are hosted on different subdomains, enabling `OG_CACHE_CONSIDER_HOST` ensures that the Open Graph tags are cached separately for each tenant. This prevents one tenant's Open Graph tags from being served to another tenant's users.
+
+2. **Different Content for Different Hosts**: If your application serves different content based on the host, enabling `OG_CACHE_CONSIDER_HOST` ensures that the correct Open Graph tags are cached and served for each host. This is useful for applications that have different branding or content for different domains or subdomains.
+
+3. **Security and Privacy Concerns**: In some cases, you may want to ensure that Open Graph tags are not shared between different hosts for security or privacy reasons. Enabling `OG_CACHE_CONSIDER_HOST` ensures that the tags are cached separately for each host, preventing any potential leakage of information between hosts.
 
 For more information, refer to the [installation guide](../installation).

docs/docs/admin/environments/apache.mdx

@@ -119,7 +119,7 @@ Make sure to add a separate configuration file for the listener on port 3001:
 ```text
 # /etc/httpd/conf.d/listener-3001.conf
 
-Listen 3001
+Listen 127.0.0.1:3001
 ```
 
 This can be repeated for multiple sites. Anubis does not care about the HTTP `Host` header and will happily cope with multiple websites via the same instance.

docs/docs/admin/environments/caddy.mdx

@@ -0,0 +1,71 @@
+# Caddy
+
+To use Anubis with Caddy, stick Anubis between Caddy and your backend. For example, consider this application setup:
+
+```mermaid
+---
+title: Caddy with Anubis in the middle
+---
+
+flowchart LR
+    T(User Traffic)
+    TCP(TCP 80/443)
+    An(Anubis)
+    B(Backend)
+    Blocked
+
+    T --> TCP
+    TCP --> |Traffic filtering| An
+    An --> |Happy traffic| B
+    An --> |Malicious traffic| Blocked
+```
+
+Instead of your traffic going directly to your backend, it takes a detour through Anubis. Anubis filters out the "bad" traffic and passes the "good" traffic to the backend.
+
+To set up Anubis with Docker compose and Caddy, start with a `docker-compose` configuration like this:
+
+```yaml
+services:
+  caddy:
+    image: caddy:2
+    ports:
+      - 80:80
+      - 443:443
+      - 443:443/udp
+    volumes:
+      - ./conf:/etc/caddy
+      - caddy_config:/config
+      - caddy_data:/data
+
+  anubis:
+    image: ghcr.io/techarohq/anubis:latest
+    pull_policy: always
+    environment:
+      BIND: ":3000"
+      TARGET: http://httpdebug:3000
+
+  httpdebug:
+    image: ghcr.io/xe/x/httpdebug
+    pull_policy: always
+
+volumes:
+  caddy_data:
+  caddy_config:
+```
+
+And then put the following in `conf/Caddyfile`:
+
+```Caddyfile
+# conf/Caddyfile
+
+yourdomain.example.com {
+  tls your@email.address
+
+  reverse_proxy http://anubis:3000 {
+		header_up X-Real-Ip {remote_host}
+		header_up X-Http-Version {http.request.proto}
+	}
+}
+```
+
+If you want to protect multiple services with Anubis, you will need to either start multiple instances of Anubis (Anubis requires less than 32 MB of ram on average) or set up a two-tier routing setup where TLS termination is done with one instance of Caddy and the actual routing to services is done with another instance of Caddy. See the [nginx](./nginx.mdx) or [Apache](./apache.mdx) documentation to get ideas on how you would do this.

docs/docs/admin/environments/nginx.mdx

@@ -147,7 +147,7 @@ upstream anubis {
 
   # Try anubis first over a UNIX socket
   server unix:/run/anubis/nginx.sock;
-  #server http://127.0.0.1:8923;
+  #server 127.0.0.1:8923;
 
   # Optional: fall back to serving the websites directly. This allows your
   # websites to be resilient against Anubis failing, at the risk of exposing

docs/docs/admin/environments/traefik.mdx

@@ -1,6 +1,6 @@
 ---
 id: traefik
-title: Integrate Anubis with Traefik in a Docker Compose Environment
+title: Traefik
 ---
 
 
@@ -174,7 +174,7 @@ services:
     networks:
       - traefik
     labels:
-      - traefik.enable=true # Eneabling Traefik
+      - traefik.enable=true # Enabling Traefik
       - traefik.docker.network=traefik # Telling Traefik which network to use
       - traefik.http.routers.target2.rule=Host(`another.com`) # Only Matching Requests for example.com
       - traefik.http.routers.target2.entrypoints=websecure # Listening on the exclusive Anubis Network

docs/docs/admin/installation.mdx

@@ -54,7 +54,8 @@ Anubis uses these environment variables for configuration:
 | `BASE_PREFIX`                  | unset                   | If set, adds a global prefix to all Anubis endpoints. For example, setting this to `/myapp` would make Anubis accessible at `/myapp/` instead of `/`. This is useful when running Anubis behind a reverse proxy that routes based on path prefixes.                                                                  |
 | `BIND`                         | `:8923`                 | The network address that Anubis listens on. For `unix`, set this to a path: `/run/anubis/instance.sock`                                                                                                                                                                                                              |
 | `BIND_NETWORK`                 | `tcp`                   | The address family that Anubis listens on. Accepts `tcp`, `unix` and anything Go's [`net.Listen`](https://pkg.go.dev/net#Listen) supports.                                                                                                                                                                           |
-| `COOKIE_DOMAIN`                | unset                   | The domain the Anubis challenge pass cookie should be set to. This should be set to the domain you bought from your registrar (EG: `techaro.lol` if your webapp is running on `anubis.techaro.lol`). See [here](https://stackoverflow.com/a/1063760) for more information.                                           |
+| `COOKIE_DOMAIN`                | unset                   | The domain the Anubis challenge pass cookie should be set to. This should be set to the domain you bought from your registrar (EG: `techaro.lol` if your webapp is running on `anubis.techaro.lol`). See this [stackoverflow explanation of cookies](https://stackoverflow.com/a/1063760) for more information.      |
+| `COOKIE_EXPIRATION_TIME`       | `168h`                  | The amount of time the authorization cookie is valid for.                                                                                                                                                                                                                                                            |
 | `COOKIE_PARTITIONED`           | `false`                 | If set to `true`, enables the [partitioned (CHIPS) flag](https://developers.google.com/privacy-sandbox/cookies/chips), meaning that Anubis inside an iframe has a different set of cookies than the domain hosting the iframe.                                                                                       |
 | `DIFFICULTY`                   | `4`                     | The difficulty of the challenge, or the number of leading zeroes that must be in successful responses.                                                                                                                                                                                                               |
 | `ED25519_PRIVATE_KEY_HEX`      | unset                   | The hex-encoded ed25519 private key used to sign Anubis responses. If this is not set, Anubis will generate one for you. This should be exactly 64 characters long. See below for details.                                                                                                                           |
@@ -63,6 +64,7 @@ Anubis uses these environment variables for configuration:
 | `METRICS_BIND_NETWORK`         | `tcp`                   | The address family that the Anubis metrics server listens on. See `BIND_NETWORK` for more information.                                                                                                                                                                                                               |
 | `OG_EXPIRY_TIME`               | `24h`                   | The expiration time for the Open Graph tag cache.                                                                                                                                                                                                                                                                    |
 | `OG_PASSTHROUGH`               | `false`                 | If set to `true`, Anubis will enable Open Graph tag passthrough.                                                                                                                                                                                                                                                     |
+| `OG_CACHE_CONSIDER_HOST`       | `false`                 | If set to `true`, Anubis will consider the host in the Open Graph tag cache key.                                                                                                                                                                                                                                     |
 | `POLICY_FNAME`                 | unset                   | The file containing [bot policy configuration](./policies.mdx). See the bot policy documentation for more details. If unset, the default bot policy configuration is used.                                                                                                                                           |
 | `REDIRECT_DOMAINS`             | unset                   | If set, restrict the domains that Anubis can redirect to when passing a challenge.<br/><br/>If this is unset, Anubis may redirect to any domain which could cause security issues in the unlikely case that an attacker passes a challenge for your browser and then tricks you into clicking a link to your domain. |
 | `SERVE_ROBOTS_TXT`             | `false`                 | If set `true`, Anubis will serve a default `robots.txt` file that disallows all known AI scrapers by name and then additionally disallows every scraper. This is useful if facts and circumstances make it difficult to change the underlying service to serve such a `robots.txt` file.                             |

docs/docs/design/how-anubis-works.mdx

@@ -37,7 +37,7 @@ flowchart TD
     ValidateChallenge -- If anything is wrong --> Fail
 ```
 
-### Challenge presentation
+## Challenge presentation
 
 Anubis decides to present a challenge using this logic:
 
@@ -89,7 +89,7 @@ work valid?"}
     PresentChallenge -- Back again for another cycle --> Request
 ```
 
-### Proof of passing challenges
+## Proof of passing challenges
 
 When a client passes a challenge, Anubis sets an HTTP cookie named `"within.website-x-cmd-anubis-auth"` containing a signed [JWT](https://jwt.io/) (JSON Web Token). This JWT contains the following claims:
 
@@ -102,7 +102,7 @@ When a client passes a challenge, Anubis sets an HTTP cookie named `"within.webs
 
 This ensures that the token has enough metadata to prove that the token is valid (due to the token's signature), but also so that the server can independently prove the token is valid. This cookie is allowed to be set without triggering an EU cookie banner notification; but depending on facts and circumstances, you may wish to disclose this to your users.
 
-### Challenge format
+## Challenge format
 
 Challenges are formed by taking some user request metadata and using that to generate a SHA-256 checksum. The following request headers are used:
 
@@ -115,6 +115,6 @@ Challenges are formed by taking some user request metadata and using that to gen
 
 This forms a fingerprint of the requestor using metadata that any requestor already is sending. It also uses time as an input, which is known to both the server and requestor due to the nature of linear timelines. Depending on facts and circumstances, you may wish to disclose this to your users.
 
-### JWT signing
+## JWT signing
 
 Anubis uses an ed25519 keypair to sign the JWTs issued when challenges are passed. Anubis will generate a new ed25519 keypair every time it starts. At this time, there is no way to share this keypair between instance of Anubis, but that will be addressed in future versions.

docs/docs/index.mdx

@@ -20,6 +20,7 @@ title: Anubis
 Anubis is brought to you by sponsors and donors like:
 
 [![Distrust](/img/sponsors/distrust-logo.webp)](https://distrust.co)
+[![Terminal Trove](/img/sponsors/terminal-trove.webp)](https://terminaltrove.com/?utm_campaign=github&utm_medium=referral&utm_content=anubis&utm_source=abgh)
 
 ## Overview
 

docs/docs/user/frequently-asked-questions.mdx

@@ -0,0 +1,20 @@
+# Frequently Asked Questions
+
+## Why can't you just put details about the proof of work challenge into the challenge page so I don't need to run JavaScript?
+
+A common question is something along the lines of "why can't you give me a shell script to run the challenge on my laptop so that I don't have to enable JavaScript". Malware has been known to show an interstitial that [asks the user to paste something into their run box on Windows](https://www.malwarebytes.com/blog/news/2025/03/fake-captcha-websites-hijack-your-clipboard-to-install-information-stealers), which will then make that machine a zombie in a botnet.
+
+It would be in very bad taste to associate a security product such as Anubis with behavior similar to what malware uses. This would destroy user trust in the product and potentially result in reputational damage for the contributors. When at all possible, we want to avoid this happening.
+
+Technically inclined users are easily able to understand how the proof of work check works by either reading the JavaScript on the page or [reading the source code of the JavaScript program](https://github.com/TecharoHQ/anubis/tree/main/web/js). Please note that the format of the challenges and the algorithms used to solve them are liable to change without notice and are not considered part of the public API of Anubis. When such a change occurs, this will break your workarounds.
+
+If [sufficient funding is raised](https://github.com/TecharoHQ/anubis/discussions/278), a browser extension that packages the proof of work checks and looks for Anubis challenge pages to solve them will be created.
+
+## Why does Anubis use [Web Workers](https://developer.mozilla.org/en-US/docs/Web/API/Web_Workers_API/Using_web_workers) to do its proof of work challenge?
+
+Anubis uses [Web Workers](https://developer.mozilla.org/en-US/docs/Web/API/Web_Workers_API/Using_web_workers) to do its proof of work challenge for two main reasons:
+
+1. The proof of work operation is a lot of serially blocking calls. If you do serially blocking calls in JavaScript, some browsers will hang and not respond to user input. This is bad user experience. Using a Web Worker allows the browser to do this computation in the background so your browser will not hang.
+2. Web Workers allow you to do multithreaded execution of JavaScript code. This lets Anubis run its checks in parallel across all your system cores so that the challenge can complete as fast as possible. In the last decade, most CPU advancements have come from making cores and code extremely parallel. Using Web Workers lets Anubis take advantage of your hardware as much as possible so that the challenge finishes as fast as possible.
+
+If you use a browser extension such as [JShelter](https://jshelter.org/), you will need to [modify your JShelter configuration](./known-broken-extensions.md#jshelter) to allow Anubis' proof of work computation to complete.

docs/docs/user/known-broken-extensions.md

@@ -3,17 +3,47 @@ title: List of known browser extensions that can break Anubis
 ---
 
 This page contains a list of all of the browser extensions that are known to break Anubis' functionality and their associated GitHub issues, along with instructions on how to work around the issue.
+
 ## [JShelter](https://jshelter.org/)
 
-| Extension    | JShelter                                      |
-| :----------- | :-------------------------------------------- |
-| Website      | [jshelter.org](https://jshelter.org/)         |
-| GitHub issue | https://github.com/TecharoHQ/anubis/issues/25 |
+| Extension    | JShelter                                                                                                                                           |
+| :----------- | :------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Website      | [jshelter.org](https://jshelter.org/)                                                                                                              |
+| GitHub issue | https://github.com/TecharoHQ/anubis/issues/25                                                                                                      |
+| Be aware of  | [What are Web Workers, and what are the threats that I face?](https://jshelter.org/faq/#what-are-web-workers-and-what-are-the-threats-that-i-face) |
 
-Workaround steps:
+### Workaround steps (recommended):
+
+1. Click on the JShelter badge icon (typically in the toolbar next to your navigation bar; if you cannot locate the icon, see [this question](https://jshelter.org/faq/#can-i-see-a-jshelter-badge-icon-next-to-my-navigation-bar-i-want-to-interact-with-the-extension-easily-and-avoid-going-through-settings)).
+2. Expand JavaScript Shield settings by clicking on the `Modify` button.
+3. Click on the `Detail tweaks of JS shield for this site` button.
+4. Click and drag the `WebWorker` slider to the left until `Remove` is replaced by the `Unprotected`.
+5. Refresh the page, for example, by clicking on the `Refresh page` button at the top of the JShelter pop up window.
+6. You might want to restore the Worker settings once you go through the challenge.
+
+### Workaround steps (alternative if you do not want to dig in JShelter's pop up):
+
+1. Click on the JShelter badge icon (typically in the toolbar next to your navigation bar; if you cannot locate the icon, see [this question](https://jshelter.org/faq/#can-i-see-a-jshelter-badge-icon-next-to-my-navigation-bar-i-want-to-interact-with-the-extension-easily-and-avoid-going-through-settings)).
+2. Expand JavaScript Shield settings by clicking on the `Modify` button.
+3. Choose "Turn JavaScript Shield off"
+4. Refresh the page, for example, by clicking on the `Refresh page` button at the top of the JShelter pop up window.
+
+:::note
+
+Taking these actions will remove all protections of JavaScript Shield for all pages at the visited web site. You might want review and amend your JavaScript shield settings once you go through the challenge based on your operational security model.
+
+:::
+
+### Workaround steps (alternative if you do not like JShelter's pop up):
 
 1. Open JShelter extension settings
 2. Click on JS Shield details
 3. Enter in the domain for a website protected by Anubis
 4. Choose "Turn JavaScript Shield off"
 5. Hit "Add to list"
+
+:::note
+
+Taking these actions will remove all protections of JavaScript Shield for all pages at the visited web site. You might want review and amend your JavaScript shield settings once you go through the challenge based on your operational security model.
+
+:::

docs/docs/user/known-instances.md

@@ -29,8 +29,27 @@ This page contains a non-exhaustive list with all websites using Anubis.
 - https://wiki.archlinux.org/
 - https://git.devuan.org/
 - https://hydra.nixos.org/
-- https://hydra.nixos.org/
 - https://codeberg.org/
+- https://www.cfaarchive.org/
+- <details>
+  <summary>FreeCAD</summary>
+  - https://forum.freecad.org/
+  - https://wiki.freecad.org/
+  </details>
+- <details>
+  <summary>ScummVM</summary>
+  - https://forums.scummvm.org/
+  - https://wiki.scummvm.org/
+  </details>
+- <details>
+  <summary>Sourceware</summary>
+  - https://sourceware.org/cgit
+  - https://sourceware.org/glibc/wiki
+  - https://builder.sourceware.org/testruns/
+  - https://patchwork.sourceware.org/
+  - https://gcc.gnu.org/bugzilla/
+  - https://gcc.gnu.org/cgit
+  </details>
 - <details>
   <summary>The United Nations</summary>
   - https://policytoolbox.iiep.unesco.org/

go.mod

@@ -6,22 +6,25 @@ require (
 	github.com/a-h/templ v0.3.857
 	github.com/facebookgo/flagenv v0.0.0-20160425205200-fcd59fca7456
 	github.com/golang-jwt/jwt/v5 v5.2.2
+	github.com/google/cel-go v0.25.0
 	github.com/playwright-community/playwright-go v0.5101.0
 	github.com/prometheus/client_golang v1.22.0
 	github.com/sebest/xff v0.0.0-20210106013422-671bd2870b3a
 	github.com/yl2chen/cidranger v1.0.2
 	golang.org/x/net v0.39.0
+	k8s.io/apimachinery v0.32.3
 )
 
 require (
+	cel.dev/expr v0.23.1 // indirect
 	github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c // indirect
 	github.com/a-h/parse v0.0.0-20250122154542-74294addb73e // indirect
 	github.com/andybalholm/brotli v1.1.0 // indirect
+	github.com/antlr4-go/antlr/v4 v4.13.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cenkalti/backoff/v4 v4.3.0 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/cli/browser v1.3.0 // indirect
-	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/deckarep/golang-set/v2 v2.6.0 // indirect
 	github.com/facebookgo/ensure v0.0.0-20160127193407-b4ab57deab51 // indirect
 	github.com/facebookgo/stack v0.0.0-20160209184415-751773369052 // indirect
@@ -30,22 +33,26 @@ require (
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/go-jose/go-jose/v3 v3.0.4 // indirect
 	github.com/go-stack/stack v1.8.1 // indirect
+	github.com/kr/text v0.2.0 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/natefinch/atomic v1.0.1 // indirect
-	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.1 // indirect
 	github.com/prometheus/common v0.62.0 // indirect
 	github.com/prometheus/procfs v0.15.1 // indirect
+	github.com/stoewer/go-strcase v1.2.0 // indirect
+	golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa // indirect
 	golang.org/x/exp/typeparams v0.0.0-20231108232855-2478ac86f678 // indirect
 	golang.org/x/mod v0.24.0 // indirect
 	golang.org/x/sync v0.13.0 // indirect
 	golang.org/x/sys v0.32.0 // indirect
+	golang.org/x/text v0.24.0 // indirect
 	golang.org/x/tools v0.32.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 // indirect
 	google.golang.org/protobuf v1.36.5 // indirect
 	honnef.co/go/tools v0.6.1 // indirect
-	k8s.io/apimachinery v0.32.3 // indirect
 	sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
 	sigs.k8s.io/yaml v1.4.0 // indirect
 )

go.sum

@@ -1,3 +1,5 @@
+cel.dev/expr v0.23.1 h1:K4KOtPCJQjVggkARsjG9RWXP6O4R73aHeJMa/dmCQQg=
+cel.dev/expr v0.23.1/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
 github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c h1:pxW6RcqyfI9/kWtOwnv/G+AzdKuy2ZrqINhenH4HyNs=
 github.com/BurntSushi/toml v1.4.1-0.20240526193622-a339e1f7089c/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
 github.com/a-h/parse v0.0.0-20250122154542-74294addb73e h1:HjVbSQHy+dnlS6C3XajZ69NYAb5jbGNfHanvm1+iYlo=
@@ -6,6 +8,8 @@ github.com/a-h/templ v0.3.857 h1:6EqcJuGZW4OL+2iZ3MD+NnIcG7nGkaQeF2Zq5kf9ZGg=
 github.com/a-h/templ v0.3.857/go.mod h1:qhrhAkRFubE7khxLZHsBFHfX+gWwVNKbzKeF9GlPV4M=
 github.com/andybalholm/brotli v1.1.0 h1:eLKJA0d02Lf0mVpIDgYnqXcUn0GqVmEFny3VuID1U3M=
 github.com/andybalholm/brotli v1.1.0/go.mod h1:sms7XGricyQI9K10gOSf56VKKWS4oLer58Q+mhRPtnY=
+github.com/antlr4-go/antlr/v4 v4.13.0 h1:lxCg3LAv+EUK6t1i0y1V6/SLeUi0eKEKdhQAlS8TVTI=
+github.com/antlr4-go/antlr/v4 v4.13.0/go.mod h1:pfChB/xh/Unjila75QW7+VU4TSnWnnk9UTnmpPaOR2g=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
@@ -14,6 +18,7 @@ github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UF
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/cli/browser v1.3.0 h1:LejqCrpWr+1pRqmEPDGnTZOjsMe7sehifLynZJuqJpo=
 github.com/cli/browser v1.3.0/go.mod h1:HH8s+fOAxjhQoBUAsKuPCbqUuxZDhQ2/aD+SzsEfBTk=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -37,11 +42,17 @@ github.com/go-stack/stack v1.8.1 h1:ntEHSVwIt7PNXNpgPmVfMrNhLtgjlmnZha2kOpuRiDw=
 github.com/go-stack/stack v1.8.1/go.mod h1:dcoOX6HbPZSZptuspn9bctJ+N/CnF5gGygcUP3XYfe4=
 github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
 github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
+github.com/google/cel-go v0.25.0 h1:jsFw9Fhn+3y2kBbltZR4VEz5xKkcIFRPDnuEzAGv5GY=
+github.com/google/cel-go v0.25.0/go.mod h1:hjEb6r5SuOSlhCHmFoLzu8HGCERvIsDAbxDAyNU/MmI=
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
 github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
 github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
 github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
@@ -68,10 +79,15 @@ github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ
 github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I=
 github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
 github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
+github.com/rogpeppe/go-internal v1.11.0 h1:cWPaGQEPrBb5/AsnsZesgZZ9yb1OQ+GOISoDNXVBh4M=
+github.com/rogpeppe/go-internal v1.11.0/go.mod h1:ddIwULY96R17DhadqLgMfk9H9tvdUzkipdSkR5nkCZA=
 github.com/sebest/xff v0.0.0-20210106013422-671bd2870b3a h1:iLcLb5Fwwz7g/DLK89F+uQBDeAhHhwdzB5fSlVdhGcM=
 github.com/sebest/xff v0.0.0-20210106013422-671bd2870b3a/go.mod h1:wozgYq9WEBQBaIJe4YZ0qTSFAMxmcwBhQH0fO0R34Z0=
+github.com/stoewer/go-strcase v1.2.0 h1:Z2iHWqGXH00XYgqDmNgQbIBxf3wrNq0F3feEy0ainaU=
+github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
+github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
@@ -81,6 +97,8 @@ github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5t
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
+golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa h1:FRnLl4eNAQl8hwxVVC17teOw8kdjVDVAiFMtgUdTSRQ=
+golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa/go.mod h1:zk2irFbV9DP96SEBUUAy67IdHUaZuSnrz1n472HUCLE=
 golang.org/x/exp/typeparams v0.0.0-20231108232855-2478ac86f678 h1:1P7xPZEwZMoBoz0Yze5Nx2/4pxj6nw9ZqHWXqP0iRgQ=
 golang.org/x/exp/typeparams v0.0.0-20231108232855-2478ac86f678/go.mod h1:AbB0pIl9nAr9wVwH+Z2ZpaocVmF5I4GyWCDIsVjR0bk=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
@@ -97,8 +115,6 @@ golang.org/x/net v0.39.0/go.mod h1:X7NRbYVEA+ewNkCNyJ513WmMdQ3BineSwVtN2zD/d+E=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw=
-golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sync v0.13.0 h1:AauUjRAJ9OSnvULf/ARrrVywoJDy0YS2AwQ98I37610=
 golang.org/x/sync v0.13.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -124,18 +140,24 @@ golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.24.0 h1:dd5Bzh4yt5KYA8f9CJHCP4FB4D51c2c6JvN37xJJkJ0=
+golang.org/x/text v0.24.0/go.mod h1:L8rBsPeo2pSS+xqN0d5u2ikmjtmoJbDBT1b7nHvFCdU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
-golang.org/x/tools v0.31.0 h1:0EedkvKDbh+qistFTd0Bcwe/YLh4vHwWEkiI0toFIBU=
-golang.org/x/tools v0.31.0/go.mod h1:naFTU+Cev749tSJRXJlna0T3WxKvb1kWEx15xA4SdmQ=
 golang.org/x/tools v0.32.0 h1:Q7N1vhpkQv7ybVzLFtTjvQya2ewbwNDZzUgfXGqtMWU=
 golang.org/x/tools v0.32.0/go.mod h1:ZxrU41P/wAbZD8EDa6dDCa6XfpkhJ7HFMjHJXfBDu8s=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 h1:YcyjlL1PRr2Q17/I0dPk2JmYS5CDXfcdb2Z3YRioEbw=
+google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:OCdP9MfskevB/rbYvHTsXTtKC+3bHWajPdoKgjcYkfo=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 h1:2035KHhUv+EpyB+hWgJnaWKJOdX1E95w2S8Rr4uWKTs=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
 google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
 google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

internal/ogtags/cache.go

@@ -8,18 +8,21 @@ import (
 )
 
 // GetOGTags is the main function that retrieves Open Graph tags for a URL
-func (c *OGTagCache) GetOGTags(url *url.URL) (map[string]string, error) {
+func (c *OGTagCache) GetOGTags(url *url.URL, originalHost string) (map[string]string, error) {
 	if url == nil {
 		return nil, errors.New("nil URL provided, cannot fetch OG tags")
 	}
-	urlStr := c.getTarget(url)
+
+	target := c.getTarget(url)
+	cacheKey := c.generateCacheKey(target, originalHost)
+
 	// Check cache first
-	if cachedTags := c.checkCache(urlStr); cachedTags != nil {
+	if cachedTags := c.checkCache(cacheKey); cachedTags != nil {
 		return cachedTags, nil
 	}
 
-	// Fetch HTML content
-	doc, err := c.fetchHTMLDocument(urlStr)
+	// Fetch HTML content, passing the original host
+	doc, err := c.fetchHTMLDocumentWithCache(target, originalHost, cacheKey)
 	if errors.Is(err, syscall.ECONNREFUSED) {
 		slog.Debug("Connection refused, returning empty tags")
 		return nil, nil
@@ -35,17 +38,28 @@ func (c *OGTagCache) GetOGTags(url *url.URL) (map[string]string, error) {
 	ogTags := c.extractOGTags(doc)
 
 	// Store in cache
-	c.cache.Set(urlStr, ogTags, c.ogTimeToLive)
+	c.cache.Set(cacheKey, ogTags, c.ogTimeToLive)
 
 	return ogTags, nil
 }
 
+func (c *OGTagCache) generateCacheKey(target string, originalHost string) string {
+	var cacheKey string
+
+	if c.ogCacheConsiderHost {
+		cacheKey = target + "|" + originalHost
+	} else {
+		cacheKey = target
+	}
+	return cacheKey
+}
+
 // checkCache checks if we have the tags cached and returns them if so
-func (c *OGTagCache) checkCache(urlStr string) map[string]string {
-	if cachedTags, ok := c.cache.Get(urlStr); ok {
+func (c *OGTagCache) checkCache(cacheKey string) map[string]string {
+	if cachedTags, ok := c.cache.Get(cacheKey); ok {
 		slog.Debug("cache hit", "tags", cachedTags)
 		return cachedTags
 	}
-	slog.Debug("cache miss", "url", urlStr)
+	slog.Debug("cache miss", "url", cacheKey)
 	return nil
 }

internal/ogtags/cache_test.go

@@ -4,12 +4,13 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"net/url"
+	"reflect"
 	"testing"
 	"time"
 )
 
 func TestCheckCache(t *testing.T) {
-	cache := NewOGTagCache("http://example.com", true, time.Minute)
+	cache := NewOGTagCache("http://example.com", true, time.Minute, false)
 
 	// Set up test data
 	urlStr := "http://example.com/page"
@@ -17,18 +18,19 @@ func TestCheckCache(t *testing.T) {
 		"og:title":       "Test Title",
 		"og:description": "Test Description",
 	}
+	cacheKey := cache.generateCacheKey(urlStr, "example.com")
 
 	// Test cache miss
-	tags := cache.checkCache(urlStr)
+	tags := cache.checkCache(cacheKey)
 	if tags != nil {
 		t.Errorf("expected nil tags on cache miss, got %v", tags)
 	}
 
 	// Manually add to cache
-	cache.cache.Set(urlStr, expectedTags, time.Minute)
+	cache.cache.Set(cacheKey, expectedTags, time.Minute)
 
 	// Test cache hit
-	tags = cache.checkCache(urlStr)
+	tags = cache.checkCache(cacheKey)
 	if tags == nil {
 		t.Fatal("expected non-nil tags on cache hit, got nil")
 	}
@@ -67,7 +69,7 @@ func TestGetOGTags(t *testing.T) {
 	defer ts.Close()
 
 	// Create an instance of OGTagCache with a short TTL for testing
-	cache := NewOGTagCache(ts.URL, true, 1*time.Minute)
+	cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
 
 	// Parse the test server URL
 	parsedURL, err := url.Parse(ts.URL)
@@ -76,7 +78,8 @@ func TestGetOGTags(t *testing.T) {
 	}
 
 	// Test fetching OG tags from the test server
-	ogTags, err := cache.GetOGTags(parsedURL)
+	// Pass the host from the parsed test server URL
+	ogTags, err := cache.GetOGTags(parsedURL, parsedURL.Host)
 	if err != nil {
 		t.Fatalf("failed to get OG tags: %v", err)
 	}
@@ -95,13 +98,15 @@ func TestGetOGTags(t *testing.T) {
 	}
 
 	// Test fetching OG tags from the cache
-	ogTags, err = cache.GetOGTags(parsedURL)
+	// Pass the host from the parsed test server URL
+	ogTags, err = cache.GetOGTags(parsedURL, parsedURL.Host)
 	if err != nil {
 		t.Fatalf("failed to get OG tags from cache: %v", err)
 	}
 
 	// Test fetching OG tags from the cache (3rd time)
-	newOgTags, err := cache.GetOGTags(parsedURL)
+	// Pass the host from the parsed test server URL
+	newOgTags, err := cache.GetOGTags(parsedURL, parsedURL.Host)
 	if err != nil {
 		t.Fatalf("failed to get OG tags from cache: %v", err)
 	}
@@ -120,3 +125,116 @@ func TestGetOGTags(t *testing.T) {
 
 	}
 }
+
+// TestGetOGTagsWithHostConsideration tests the behavior of the cache with and without host consideration and for multiple hosts in a theoretical setup.
+func TestGetOGTagsWithHostConsideration(t *testing.T) {
+	var loadCount int // Counter to track how many times the test route is loaded
+
+	// Create a test server
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		loadCount++ // Increment counter on each request to the server
+		w.Header().Set("Content-Type", "text/html")
+		w.Write([]byte(`
+			<!DOCTYPE html>
+			<html>
+			<head>
+				<meta property="og:title" content="Test Title" />
+				<meta property="og:description" content="Test Description" />
+			</head>
+			<body><p>Content</p></body>
+			</html>
+		`))
+	}))
+	defer ts.Close()
+
+	parsedURL, err := url.Parse(ts.URL)
+	if err != nil {
+		t.Fatalf("failed to parse test server URL: %v", err)
+	}
+
+	expectedTags := map[string]string{
+		"og:title":       "Test Title",
+		"og:description": "Test Description",
+	}
+
+	testCases := []struct {
+		name                string
+		ogCacheConsiderHost bool
+		requests            []struct {
+			host              string
+			expectedLoadCount int // Expected load count *after* this request
+		}
+	}{
+		{
+			name:                "Host Not Considered - Same Host",
+			ogCacheConsiderHost: false,
+			requests: []struct {
+				host              string
+				expectedLoadCount int
+			}{
+				{"host1", 1}, // First request, miss
+				{"host1", 1}, // Second request, same host, hit (host ignored)
+			},
+		},
+		{
+			name:                "Host Not Considered - Different Host",
+			ogCacheConsiderHost: false,
+			requests: []struct {
+				host              string
+				expectedLoadCount int
+			}{
+				{"host1", 1}, // First request, miss
+				{"host2", 1}, // Second request, different host, hit (host ignored)
+			},
+		},
+		{
+			name:                "Host Considered - Same Host",
+			ogCacheConsiderHost: true,
+			requests: []struct {
+				host              string
+				expectedLoadCount int
+			}{
+				{"host1", 1}, // First request, miss
+				{"host1", 1}, // Second request, same host, hit
+			},
+		},
+		{
+			name:                "Host Considered - Different Host",
+			ogCacheConsiderHost: true,
+			requests: []struct {
+				host              string
+				expectedLoadCount int
+			}{
+				{"host1", 1}, // First request, miss
+				{"host2", 2}, // Second request, different host, miss
+				{"host2", 2}, // Third request, same as second, hit
+				{"host1", 2}, // Fourth request, same as first, hit
+			},
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			loadCount = 0 // Reset load count for each test case
+			cache := NewOGTagCache(ts.URL, true, 1*time.Minute, tc.ogCacheConsiderHost)
+
+			for i, req := range tc.requests {
+				ogTags, err := cache.GetOGTags(parsedURL, req.host)
+				if err != nil {
+					t.Errorf("Request %d (host: %s): unexpected error: %v", i+1, req.host, err)
+					continue // Skip further checks for this request if error occurred
+				}
+
+				// Verify tags are correct (should always be the same in this setup)
+				if !reflect.DeepEqual(ogTags, expectedTags) {
+					t.Errorf("Request %d (host: %s): expected tags %v, got %v", i+1, req.host, expectedTags, ogTags)
+				}
+
+				// Verify the load count to check cache hit/miss behavior
+				if loadCount != req.expectedLoadCount {
+					t.Errorf("Request %d (host: %s): expected load count %d, got %d (cache hit/miss mismatch)", i+1, req.host, req.expectedLoadCount, loadCount)
+				}
+			}
+		})
+	}
+}

internal/ogtags/fetch.go

@@ -1,6 +1,7 @@
 package ogtags
 
 import (
+	"context"
 	"errors"
 	"fmt"
 	"golang.org/x/net/html"
@@ -16,17 +17,35 @@ var (
 	emptyMap     = map[string]string{}             // used to indicate an empty result in the cache. Can't use nil as it would be a cache miss.
 )
 
-func (c *OGTagCache) fetchHTMLDocument(urlStr string) (*html.Node, error) {
-	resp, err := c.client.Get(urlStr)
+// fetchHTMLDocumentWithCache fetches the HTML document from the given URL string,
+// preserving the original host header.
+func (c *OGTagCache) fetchHTMLDocumentWithCache(urlStr string, originalHost string, cacheKey string) (*html.Node, error) {
+	req, err := http.NewRequestWithContext(context.Background(), "GET", urlStr, nil)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create http request: %w", err)
+	}
+
+	// Set the Host header to the original host
+	if originalHost != "" {
+		req.Host = originalHost
+	}
+
+	// Add proxy headers
+	req.Header.Set("X-Forwarded-Proto", "https")
+	req.Header.Set("User-Agent", "Anubis-OGTag-Fetcher/1.0") // For tracking purposes
+
+	// Send the request
+	resp, err := c.client.Do(req)
 	if err != nil {
 		var netErr net.Error
 		if errors.As(err, &netErr) && netErr.Timeout() {
 			slog.Debug("og: request timed out", "url", urlStr)
-			c.cache.Set(urlStr, emptyMap, c.ogTimeToLive/2) // Cache empty result for half the TTL to not spam the server
+			c.cache.Set(cacheKey, emptyMap, c.ogTimeToLive/2) // Cache empty result for half the TTL to not spam the server
 		}
 		return nil, fmt.Errorf("http get failed: %w", err)
 	}
-	// this defer will call MaxBytesReader's Close, which closes the original body.
+
+	// Ensure the response body is closed
 	defer func(Body io.ReadCloser) {
 		err := Body.Close()
 		if err != nil {
@@ -36,19 +55,17 @@ func (c *OGTagCache) fetchHTMLDocument(urlStr string) (*html.Node, error) {
 
 	if resp.StatusCode != http.StatusOK {
 		slog.Debug("og: received non-OK status code", "url", urlStr, "status", resp.StatusCode)
-		c.cache.Set(urlStr, emptyMap, c.ogTimeToLive) // Cache empty result for non-successful status codes
+		c.cache.Set(cacheKey, emptyMap, c.ogTimeToLive) // Cache empty result for non-successful status codes
 		return nil, fmt.Errorf("%w: page not found", ErrOgHandled)
 	}
 
 	// Check content type
 	ct := resp.Header.Get("Content-Type")
 	if ct == "" {
-		// assume non html body
 		return nil, fmt.Errorf("missing Content-Type header")
 	} else {
 		mediaType, _, err := mime.ParseMediaType(ct)
 		if err != nil {
-			// Malformed Content-Type header
 			slog.Debug("og: malformed Content-Type header", "url", urlStr, "contentType", ct)
 			return nil, fmt.Errorf("%w malformed Content-Type header: %w", ErrOgHandled, err)
 		}
@@ -59,17 +76,16 @@ func (c *OGTagCache) fetchHTMLDocument(urlStr string) (*html.Node, error) {
 		}
 	}
 
-	resp.Body = http.MaxBytesReader(nil, resp.Body, c.maxContentLength)
+	resp.Body = http.MaxBytesReader(nil, resp.Body, maxContentLength)
 
 	doc, err := html.Parse(resp.Body)
 	if err != nil {
 		// Check if the error is specifically because the limit was exceeded
 		var maxBytesErr *http.MaxBytesError
 		if errors.As(err, &maxBytesErr) {
-			slog.Debug("og: content exceeded max length", "url", urlStr, "limit", c.maxContentLength)
-			return nil, fmt.Errorf("content too large: exceeded %d bytes", c.maxContentLength)
+			slog.Debug("og: content exceeded max length", "url", urlStr, "limit", maxContentLength)
+			return nil, fmt.Errorf("content too large: exceeded %d bytes", maxContentLength)
 		}
-		// parsing error (e.g., malformed HTML)
 		return nil, fmt.Errorf("failed to parse HTML: %w", err)
 	}
 

internal/ogtags/fetch_test.go

@@ -2,6 +2,7 @@ package ogtags
 
 import (
 	"fmt"
+	"golang.org/x/net/html"
 	"io"
 	"net/http"
 	"net/http/httptest"
@@ -78,8 +79,8 @@ func TestFetchHTMLDocument(t *testing.T) {
 			}))
 			defer ts.Close()
 
-			cache := NewOGTagCache("", true, time.Minute)
-			doc, err := cache.fetchHTMLDocument(ts.URL)
+			cache := NewOGTagCache("", true, time.Minute, false)
+			doc, err := cache.fetchHTMLDocument(ts.URL, "anything")
 
 			if tt.expectError {
 				if err == nil {
@@ -105,9 +106,9 @@ func TestFetchHTMLDocumentInvalidURL(t *testing.T) {
 		t.Skip("test requires theoretical network egress")
 	}
 
-	cache := NewOGTagCache("", true, time.Minute)
+	cache := NewOGTagCache("", true, time.Minute, false)
 
-	doc, err := cache.fetchHTMLDocument("http://invalid.url.that.doesnt.exist.example")
+	doc, err := cache.fetchHTMLDocument("http://invalid.url.that.doesnt.exist.example", "anything")
 
 	if err == nil {
 		t.Error("expected error for invalid URL, got nil")
@@ -117,3 +118,9 @@ func TestFetchHTMLDocumentInvalidURL(t *testing.T) {
 		t.Error("expected nil document for invalid URL, got non-nil")
 	}
 }
+
+// fetchHTMLDocument allows you to call fetchHTMLDocumentWithCache without a duplicate generateCacheKey call
+func (c *OGTagCache) fetchHTMLDocument(urlStr string, originalHost string) (*html.Node, error) {
+	cacheKey := c.generateCacheKey(urlStr, originalHost)
+	return c.fetchHTMLDocumentWithCache(urlStr, originalHost, cacheKey)
+}

internal/ogtags/integration_test.go

@@ -93,7 +93,7 @@ func TestIntegrationGetOGTags(t *testing.T) {
 			expectError:  false,
 		},
 		{
-			name:         "Non-existent page",
+			name:         "Nonexistent page",
 			path:         "/not-found",
 			query:        "",
 			expectedTags: nil,
@@ -104,7 +104,7 @@ func TestIntegrationGetOGTags(t *testing.T) {
 	for _, tc := range testCases {
 		t.Run(tc.name, func(t *testing.T) {
 			// Create cache instance
-			cache := NewOGTagCache(ts.URL, true, 1*time.Minute)
+			cache := NewOGTagCache(ts.URL, true, 1*time.Minute, false)
 
 			// Create URL for test
 			testURL, _ := url.Parse(ts.URL)
@@ -112,7 +112,8 @@ func TestIntegrationGetOGTags(t *testing.T) {
 			testURL.RawQuery = tc.query
 
 			// Get OG tags
-			ogTags, err := cache.GetOGTags(testURL)
+			// Pass the host from the test URL
+			ogTags, err := cache.GetOGTags(testURL, testURL.Host)
 
 			// Check error expectation
 			if tc.expectError {
@@ -139,7 +140,8 @@ func TestIntegrationGetOGTags(t *testing.T) {
 			}
 
 			// Test cache retrieval
-			cachedOGTags, err := cache.GetOGTags(testURL)
+			// Pass the host from the test URL
+			cachedOGTags, err := cache.GetOGTags(testURL, testURL.Host)
 			if err != nil {
 				t.Fatalf("failed to get OG tags from cache: %v", err)
 			}

internal/ogtags/ogtags.go

@@ -1,51 +1,111 @@
 package ogtags
 
 import (
+	"context"
+	"log/slog"
+	"net"
 	"net/http"
 	"net/url"
+	"strings"
 	"time"
 
 	"github.com/TecharoHQ/anubis/decaymap"
 )
 
+const (
+	maxContentLength = 16 << 20        // 16 MiB in bytes, if there is a reasonable reason that you need more than this...Why?
+	httpTimeout      = 5 * time.Second /*todo: make this configurable?*/
+)
+
 type OGTagCache struct {
-	cache            *decaymap.Impl[string, map[string]string]
-	target           string
-	ogPassthrough    bool
-	ogTimeToLive     time.Duration
-	approvedTags     []string
-	approvedPrefixes []string
-	client           *http.Client
-	maxContentLength int64
+	cache               *decaymap.Impl[string, map[string]string]
+	targetURL           *url.URL
+	ogCacheConsiderHost bool
+	ogPassthrough       bool
+	ogTimeToLive        time.Duration
+	approvedTags        []string
+	approvedPrefixes    []string
+	client              *http.Client
 }
 
-func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration) *OGTagCache {
+func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration, ogTagsConsiderHost bool) *OGTagCache {
 	// Predefined approved tags and prefixes
 	// In the future, these could come from configuration
 	defaultApprovedTags := []string{"description", "keywords", "author"}
 	defaultApprovedPrefixes := []string{"og:", "twitter:", "fediverse:"}
-	client := &http.Client{
-		Timeout: 5 * time.Second, /*make this configurable?*/
+
+	var parsedTargetURL *url.URL
+	var err error
+
+	if target == "" {
+		// Default to localhost if target is empty
+		parsedTargetURL, _ = url.Parse("http://localhost")
+	} else {
+		parsedTargetURL, err = url.Parse(target)
+		if err != nil {
+			slog.Debug("og: failed to parse target URL, treating as non-unix", "target", target, "error", err)
+			// If parsing fails, treat it as a non-unix target for backward compatibility or default behavior
+			// For now, assume it's not a scheme issue but maybe an invalid char, etc.
+			// A simple string target might be intended if it's not a full URL.
+			parsedTargetURL = &url.URL{Scheme: "http", Host: target} // Assume http if scheme missing and host-like
+			if !strings.Contains(target, "://") && !strings.HasPrefix(target, "unix:") {
+				// If it looks like just a host/host:port (and not unix), prepend http:// (todo: is this bad...? Trace path to see if i can yell at user to do it right)
+				parsedTargetURL, _ = url.Parse("http://" + target) // fetch cares about scheme but anubis doesn't
+			}
+		}
 	}
 
-	const maxContentLength = 16 << 20 // 16 MiB in bytes
+	client := &http.Client{
+		Timeout: httpTimeout,
+	}
+
+	// Configure custom transport for Unix sockets
+	if parsedTargetURL.Scheme == "unix" {
+		socketPath := parsedTargetURL.Path // For unix scheme, path is the socket path
+		client.Transport = &http.Transport{
+			DialContext: func(_ context.Context, _, _ string) (net.Conn, error) {
+				return net.Dial("unix", socketPath)
+			},
+		}
+	}
 
 	return &OGTagCache{
-		cache:            decaymap.New[string, map[string]string](),
-		target:           target,
-		ogPassthrough:    ogPassthrough,
-		ogTimeToLive:     ogTimeToLive,
-		approvedTags:     defaultApprovedTags,
-		approvedPrefixes: defaultApprovedPrefixes,
-		client:           client,
-		maxContentLength: maxContentLength,
+		cache:               decaymap.New[string, map[string]string](),
+		targetURL:           parsedTargetURL, // Store the parsed URL
+		ogPassthrough:       ogPassthrough,
+		ogTimeToLive:        ogTimeToLive,
+		ogCacheConsiderHost: ogTagsConsiderHost, // todo: refactor to be a separate struct
+		approvedTags:        defaultApprovedTags,
+		approvedPrefixes:    defaultApprovedPrefixes,
+		client:              client,
 	}
 }
 
+// getTarget constructs the target URL string for fetching OG tags.
+// For Unix sockets, it creates a "fake" HTTP URL that the custom dialer understands.
 func (c *OGTagCache) getTarget(u *url.URL) string {
-	return c.target + u.Path
+	if c.targetURL.Scheme == "unix" {
+		// The custom dialer ignores the host, but we need a valid http URL structure.
+		// Use "unix" as a placeholder host. Path and Query from original request are appended.
+		fakeURL := &url.URL{
+			Scheme:   "http", // Scheme must be http/https for client.Get
+			Host:     "unix", // Arbitrary host, ignored by custom dialer
+			Path:     u.Path,
+			RawQuery: u.RawQuery,
+		}
+		return fakeURL.String()
+	}
+
+	// For regular http/https targets
+	target := *c.targetURL // Make a copy
+	target.Path = u.Path
+	target.RawQuery = u.RawQuery
+	return target.String()
+
 }
 
 func (c *OGTagCache) Cleanup() {
-	c.cache.Cleanup()
+	if c.cache != nil {
+		c.cache.Cleanup()
+	}
 }

internal/ogtags/ogtags_test.go

@@ -1,7 +1,16 @@
 package ogtags
 
 import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"net/http"
 	"net/url"
+	"os"
+	"path/filepath"
+	"reflect"
+	"strings"
 	"testing"
 	"time"
 )
@@ -29,14 +38,23 @@ func TestNewOGTagCache(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			cache := NewOGTagCache(tt.target, tt.ogPassthrough, tt.ogTimeToLive)
+			cache := NewOGTagCache(tt.target, tt.ogPassthrough, tt.ogTimeToLive, false)
 
 			if cache == nil {
 				t.Fatal("expected non-nil cache, got nil")
 			}
 
-			if cache.target != tt.target {
-				t.Errorf("expected target %s, got %s", tt.target, cache.target)
+			// Check the parsed targetURL, handling the default case for empty target
+			expectedURLStr := tt.target
+			if tt.target == "" {
+				// Default behavior when target is empty is now http://localhost
+				expectedURLStr = "http://localhost"
+			} else if !strings.Contains(tt.target, "://") && !strings.HasPrefix(tt.target, "unix:") {
+				// Handle case where target is just host or host:port (and not unix)
+				expectedURLStr = "http://" + tt.target
+			}
+			if cache.targetURL.String() != expectedURLStr {
+				t.Errorf("expected targetURL %s, got %s", expectedURLStr, cache.targetURL.String())
 			}
 
 			if cache.ogPassthrough != tt.ogPassthrough {
@@ -50,6 +68,45 @@ func TestNewOGTagCache(t *testing.T) {
 	}
 }
 
+// TestNewOGTagCache_UnixSocket specifically tests unix socket initialization
+func TestNewOGTagCache_UnixSocket(t *testing.T) {
+	tempDir := t.TempDir()
+	socketPath := filepath.Join(tempDir, "test.sock")
+	target := "unix://" + socketPath
+
+	cache := NewOGTagCache(target, true, 5*time.Minute, false)
+
+	if cache == nil {
+		t.Fatal("expected non-nil cache, got nil")
+	}
+
+	if cache.targetURL.Scheme != "unix" {
+		t.Errorf("expected targetURL scheme 'unix', got '%s'", cache.targetURL.Scheme)
+	}
+	if cache.targetURL.Path != socketPath {
+		t.Errorf("expected targetURL path '%s', got '%s'", socketPath, cache.targetURL.Path)
+	}
+
+	// Check if the client transport is configured for Unix sockets
+	transport, ok := cache.client.Transport.(*http.Transport)
+	if !ok {
+		t.Fatalf("expected client transport to be *http.Transport, got %T", cache.client.Transport)
+	}
+	if transport.DialContext == nil {
+		t.Fatal("expected client transport DialContext to be non-nil for unix socket")
+	}
+
+	// Attempt a dummy dial to see if it uses the correct path (optional, more involved check)
+	dummyConn, err := transport.DialContext(context.Background(), "", "")
+	if err == nil {
+		dummyConn.Close()
+		t.Log("DialContext seems functional, but couldn't verify path without a listener")
+	} else if !strings.Contains(err.Error(), "connect: connection refused") && !strings.Contains(err.Error(), "connect: no such file or directory") {
+		// We expect connection refused or not found if nothing is listening
+		t.Errorf("DialContext failed with unexpected error: %v", err)
+	}
+}
+
 func TestGetTarget(t *testing.T) {
 	tests := []struct {
 		name     string
@@ -66,24 +123,39 @@ func TestGetTarget(t *testing.T) {
 			expected: "http://example.com",
 		},
 		{
-			name:     "With complex path",
-			target:   "http://example.com",
-			path:     "/pag(#*((#@)ΓΓΓΓe/Γ",
-			query:    "id=123",
-			expected: "http://example.com/pag(#*((#@)ΓΓΓΓe/Γ",
+			name:   "With complex path",
+			target: "http://example.com",
+			path:   "/pag(#*((#@)ΓΓΓΓe/Γ",
+			query:  "id=123",
+			// Expect URL encoding and query parameter
+			expected: "http://example.com/pag%28%23%2A%28%28%23@%29%CE%93%CE%93%CE%93%CE%93e/%CE%93?id=123",
 		},
 		{
 			name:     "With query and path",
 			target:   "http://example.com",
 			path:     "/page",
 			query:    "id=123",
-			expected: "http://example.com/page",
+			expected: "http://example.com/page?id=123",
+		},
+		{
+			name:     "Unix socket target",
+			target:   "unix:/tmp/anubis.sock",
+			path:     "/some/path",
+			query:    "key=value&flag=true",
+			expected: "http://unix/some/path?key=value&flag=true", // Scheme becomes http, host is 'unix'
+		},
+		{
+			name:     "Unix socket target with ///",
+			target:   "unix:///var/run/anubis.sock",
+			path:     "/",
+			query:    "",
+			expected: "http://unix/",
 		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			cache := NewOGTagCache(tt.target, false, time.Minute)
+			cache := NewOGTagCache(tt.target, false, time.Minute, false)
 
 			u := &url.URL{
 				Path:     tt.path,
@@ -98,3 +170,86 @@ func TestGetTarget(t *testing.T) {
 		})
 	}
 }
+
+// TestIntegrationGetOGTags_UnixSocket tests fetching OG tags via a Unix socket.
+func TestIntegrationGetOGTags_UnixSocket(t *testing.T) {
+	tempDir := t.TempDir()
+
+	socketPath := filepath.Join(tempDir, "anubis-test.sock")
+
+	// Ensure the socket does not exist initially
+	_ = os.Remove(socketPath)
+
+	// Create a simple HTTP server listening on the Unix socket
+	listener, err := net.Listen("unix", socketPath)
+	if err != nil {
+		t.Fatalf("Failed to listen on unix socket %s: %v", socketPath, err)
+	}
+	defer func(listener net.Listener, socketPath string) {
+		if listener != nil {
+			if err := listener.Close(); err != nil && !errors.Is(err, net.ErrClosed) {
+				t.Logf("Error closing listener: %v", err)
+			}
+		}
+
+		if _, err := os.Stat(socketPath); err == nil {
+			if err := os.Remove(socketPath); err != nil {
+				t.Logf("Error removing socket file %s: %v", socketPath, err)
+			}
+		}
+	}(listener, socketPath)
+
+	server := &http.Server{
+		Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.Header().Set("Content-Type", "text/html")
+			fmt.Fprintln(w, `<!DOCTYPE html><html><head><meta property="og:title" content="Unix Socket Test" /></head><body>Test</body></html>`)
+		}),
+	}
+	go func() {
+		if err := server.Serve(listener); err != nil && !errors.Is(err, http.ErrServerClosed) {
+			t.Logf("Unix socket server error: %v", err)
+		}
+	}()
+	defer func(server *http.Server, ctx context.Context) {
+		err := server.Shutdown(ctx)
+		if err != nil {
+			t.Logf("Error shutting down server: %v", err)
+		}
+	}(server, context.Background()) // Ensure server is shut down
+
+	// Wait a moment for the server to start
+	time.Sleep(100 * time.Millisecond)
+
+	// Create cache instance pointing to the Unix socket
+	targetURL := "unix://" + socketPath
+	cache := NewOGTagCache(targetURL, true, 1*time.Minute, false)
+
+	// Create a dummy URL for the request (path and query matter)
+	testReqURL, _ := url.Parse("/some/page?query=1")
+
+	// Get OG tags
+	// Pass an empty string for host, as it's irrelevant for unix sockets
+	ogTags, err := cache.GetOGTags(testReqURL, "")
+
+	if err != nil {
+		t.Fatalf("GetOGTags failed for unix socket: %v", err)
+	}
+
+	expectedTags := map[string]string{
+		"og:title": "Unix Socket Test",
+	}
+
+	if !reflect.DeepEqual(ogTags, expectedTags) {
+		t.Errorf("Expected OG tags %v, got %v", expectedTags, ogTags)
+	}
+
+	// Test cache retrieval (should hit cache)
+	// Pass an empty string for host
+	cachedTags, err := cache.GetOGTags(testReqURL, "")
+	if err != nil {
+		t.Fatalf("GetOGTags (cache hit) failed for unix socket: %v", err)
+	}
+	if !reflect.DeepEqual(cachedTags, expectedTags) {
+		t.Errorf("Expected cached OG tags %v, got %v", expectedTags, cachedTags)
+	}
+}

internal/ogtags/parse_test.go

@@ -12,7 +12,7 @@ import (
 // TestExtractOGTags updated with correct expectations based on filtering logic
 func TestExtractOGTags(t *testing.T) {
 	// Use a cache instance that reflects the default approved lists
-	testCache := NewOGTagCache("", false, time.Minute)
+	testCache := NewOGTagCache("", false, time.Minute, false)
 	// Manually set approved tags/prefixes based on the user request for clarity
 	testCache.approvedTags = []string{"description"}
 	testCache.approvedPrefixes = []string{"og:"}
@@ -189,7 +189,7 @@ func TestIsOGMetaTag(t *testing.T) {
 
 func TestExtractMetaTagInfo(t *testing.T) {
 	// Use a cache instance that reflects the default approved lists
-	testCache := NewOGTagCache("", false, time.Minute)
+	testCache := NewOGTagCache("", false, time.Minute, false)
 	testCache.approvedTags = []string{"description"}
 	testCache.approvedPrefixes = []string{"og:"}
 

lib/anubis.go

@@ -170,7 +170,7 @@ func (s *Server) checkRules(w http.ResponseWriter, r *http.Request, cr policy.Ch
 		hash := rule.Hash()
 
 		lg.Debug("rule hash", "hash", hash)
-		s.respondWithStatus(w, r, fmt.Sprintf("Access Denied: error code %s", hash), http.StatusOK)
+		s.respondWithStatus(w, r, fmt.Sprintf("Access Denied: error code %s", hash), s.policy.StatusCodes.Deny)
 		return true
 	case config.RuleChallenge:
 		lg.Debug("challenge requested")
@@ -202,7 +202,7 @@ func (s *Server) handleDNSBL(w http.ResponseWriter, r *http.Request, ip string,
 
 		if resp != dnsbl.AllGood {
 			lg.Info("DNSBL hit", "status", resp.String())
-			s.respondWithStatus(w, r, fmt.Sprintf("DroneBL reported an entry: %s, see https://dronebl.org/lookup?ip=%s", resp.String(), ip), http.StatusOK)
+			s.respondWithStatus(w, r, fmt.Sprintf("DroneBL reported an entry: %s, see https://dronebl.org/lookup?ip=%s", resp.String(), ip), s.policy.StatusCodes.Deny)
 			return true
 		}
 	}
@@ -348,7 +348,7 @@ func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {
 		"response":  response,
 		"iat":       time.Now().Unix(),
 		"nbf":       time.Now().Add(-1 * time.Minute).Unix(),
-		"exp":       time.Now().Add(24 * 7 * time.Hour).Unix(),
+		"exp":       time.Now().Add(s.opts.CookieExpiration).Unix(),
 	})
 	tokenString, err := token.SignedString(s.priv)
 	if err != nil {
@@ -361,7 +361,7 @@ func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {
 	http.SetCookie(w, &http.Cookie{
 		Name:        anubis.CookieName,
 		Value:       tokenString,
-		Expires:     time.Now().Add(24 * 7 * time.Hour),
+		Expires:     time.Now().Add(s.opts.CookieExpiration),
 		SameSite:    http.SameSiteLaxMode,
 		Domain:      s.opts.CookieDomain,
 		Partitioned: s.opts.CookiePartitioned,

lib/anubis_test.go

@@ -8,11 +8,13 @@ import (
 	"os"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/TecharoHQ/anubis"
 	"github.com/TecharoHQ/anubis/data"
 	"github.com/TecharoHQ/anubis/internal"
 	"github.com/TecharoHQ/anubis/lib/policy"
+	"github.com/TecharoHQ/anubis/lib/policy/config"
 )
 
 func loadPolicies(t *testing.T, fname string) *policy.ParsedConfig {
@@ -83,7 +85,7 @@ func TestCVE2025_24369(t *testing.T) {
 		Next:   http.NewServeMux(),
 		Policy: pol,
 
-		CookieDomain:      "local.cetacean.club",
+		CookieDomain:      ".local.cetacean.club",
 		CookiePartitioned: true,
 		CookieName:        t.Name(),
 	})
@@ -126,17 +128,18 @@ func TestCVE2025_24369(t *testing.T) {
 	}
 }
 
-func TestCookieSettings(t *testing.T) {
+func TestCookieCustomExpiration(t *testing.T) {
 	pol := loadPolicies(t, "")
 	pol.DefaultDifficulty = 0
+	ckieExpiration := 10 * time.Minute
 
 	srv := spawnAnubis(t, Options{
 		Next:   http.NewServeMux(),
 		Policy: pol,
 
-		CookieDomain:      "local.cetacean.club",
-		CookiePartitioned: true,
-		CookieName:        t.Name(),
+		CookieDomain:     "local.cetacean.club",
+		CookieName:       t.Name(),
+		CookieExpiration: ckieExpiration,
 	})
 
 	ts := httptest.NewServer(internal.RemoteXRealIP(true, "tcp", srv))
@@ -180,7 +183,99 @@ func TestCookieSettings(t *testing.T) {
 	q.Set("elapsedTime", fmt.Sprint(elapsedTime))
 	req.URL.RawQuery = q.Encode()
 
+	requestReceiveLowerBound := time.Now()
 	resp, err = cli.Do(req)
+	requestReceiveUpperBound := time.Now()
+	if err != nil {
+		t.Fatalf("can't do challenge passing")
+	}
+
+	if resp.StatusCode != http.StatusFound {
+		resp.Write(os.Stderr)
+		t.Errorf("wanted %d, got: %d", http.StatusFound, resp.StatusCode)
+	}
+
+	var ckie *http.Cookie
+	for _, cookie := range resp.Cookies() {
+		t.Logf("%#v", cookie)
+		if cookie.Name == anubis.CookieName {
+			ckie = cookie
+			break
+		}
+	}
+	if ckie == nil {
+		t.Errorf("Cookie %q not found", anubis.CookieName)
+		return
+	}
+
+	expirationLowerBound := requestReceiveLowerBound.Add(ckieExpiration)
+	expirationUpperBound := requestReceiveUpperBound.Add(ckieExpiration)
+	// Since the cookie expiration precision is only to the second due to the Unix() call, we can
+	// lower the level of expected precision.
+	if ckie.Expires.Unix() < expirationLowerBound.Unix() || ckie.Expires.Unix() > expirationUpperBound.Unix() {
+		t.Errorf("cookie expiration is not within the expected range. expected between: %v and %v. got: %v", expirationLowerBound, expirationUpperBound, ckie.Expires)
+		return
+	}
+}
+
+func TestCookieSettings(t *testing.T) {
+	pol := loadPolicies(t, "")
+	pol.DefaultDifficulty = 0
+
+	srv := spawnAnubis(t, Options{
+		Next:   http.NewServeMux(),
+		Policy: pol,
+
+		CookieDomain:      "local.cetacean.club",
+		CookiePartitioned: true,
+		CookieName:        t.Name(),
+		CookieExpiration:  anubis.CookieDefaultExpirationTime,
+	})
+
+	ts := httptest.NewServer(internal.RemoteXRealIP(true, "tcp", srv))
+	defer ts.Close()
+
+	cli := &http.Client{
+		CheckRedirect: func(req *http.Request, via []*http.Request) error {
+			return http.ErrUseLastResponse
+		},
+	}
+
+	resp, err := cli.Post(ts.URL+"/.within.website/x/cmd/anubis/api/make-challenge", "", nil)
+	if err != nil {
+		t.Fatalf("can't request challenge: %v", err)
+	}
+	defer resp.Body.Close()
+
+	var chall = struct {
+		Challenge string `json:"challenge"`
+	}{}
+	if err := json.NewDecoder(resp.Body).Decode(&chall); err != nil {
+		t.Fatalf("can't read challenge response body: %v", err)
+	}
+
+	nonce := 0
+	elapsedTime := 420
+	redir := "/"
+	calculated := ""
+	calcString := fmt.Sprintf("%s%d", chall.Challenge, nonce)
+	calculated = internal.SHA256sum(calcString)
+
+	req, err := http.NewRequest(http.MethodGet, ts.URL+"/.within.website/x/cmd/anubis/api/pass-challenge", nil)
+	if err != nil {
+		t.Fatalf("can't make request: %v", err)
+	}
+
+	q := req.URL.Query()
+	q.Set("response", calculated)
+	q.Set("nonce", fmt.Sprint(nonce))
+	q.Set("redir", redir)
+	q.Set("elapsedTime", fmt.Sprint(elapsedTime))
+	req.URL.RawQuery = q.Encode()
+
+	requestReceiveLowerBound := time.Now()
+	resp, err = cli.Do(req)
+	requestReceiveUpperBound := time.Now()
 	if err != nil {
 		t.Fatalf("can't do challenge passing")
 	}
@@ -207,6 +302,15 @@ func TestCookieSettings(t *testing.T) {
 		t.Errorf("cookie domain is wrong, wanted local.cetacean.club, got: %s", ckie.Domain)
 	}
 
+	expirationLowerBound := requestReceiveLowerBound.Add(anubis.CookieDefaultExpirationTime)
+	expirationUpperBound := requestReceiveUpperBound.Add(anubis.CookieDefaultExpirationTime)
+	// Since the cookie expiration precision is only to the second due to the Unix() call, we can
+	// lower the level of expected precision.
+	if ckie.Expires.Unix() < expirationLowerBound.Unix() || ckie.Expires.Unix() > expirationUpperBound.Unix() {
+		t.Errorf("cookie expiration is not within the expected range. expected between: %v and %v. got: %v", expirationLowerBound, expirationUpperBound, ckie.Expires)
+		return
+	}
+
 	if ckie.Partitioned != srv.opts.CookiePartitioned {
 		t.Errorf("wanted partitioned flag %v, got: %v", srv.opts.CookiePartitioned, ckie.Partitioned)
 	}
@@ -393,3 +497,87 @@ func TestBasePrefix(t *testing.T) {
 		})
 	}
 }
+
+func TestCustomStatusCodes(t *testing.T) {
+	h := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		t.Log(r.UserAgent())
+		w.WriteHeader(http.StatusOK)
+		fmt.Fprintln(w, "OK")
+	})
+
+	statusMap := map[string]int{
+		"ALLOW":     200,
+		"CHALLENGE": 401,
+		"DENY":      403,
+	}
+
+	pol := loadPolicies(t, "./testdata/aggressive_403.yaml")
+	pol.DefaultDifficulty = 4
+
+	srv := spawnAnubis(t, Options{
+		Next:   h,
+		Policy: pol,
+	})
+
+	ts := httptest.NewServer(internal.RemoteXRealIP(true, "tcp", srv))
+	defer ts.Close()
+
+	for userAgent, statusCode := range statusMap {
+		t.Run(userAgent, func(t *testing.T) {
+			req, err := http.NewRequestWithContext(t.Context(), http.MethodGet, ts.URL, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			req.Header.Set("User-Agent", userAgent)
+
+			resp, err := ts.Client().Do(req)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			if resp.StatusCode != statusCode {
+				t.Errorf("wanted status code %d but got: %d", statusCode, resp.StatusCode)
+			}
+		})
+	}
+}
+
+func TestCloudflareWorkersRule(t *testing.T) {
+	for _, variant := range []string{"cel", "header"} {
+		t.Run(variant, func(t *testing.T) {
+			pol := loadPolicies(t, "./testdata/cloudflare-workers-"+variant+".yaml")
+
+			h := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				fmt.Fprintln(w, "OK")
+			})
+
+			s, err := New(Options{
+				Next:           h,
+				Policy:         pol,
+				ServeRobotsTXT: true,
+			})
+			if err != nil {
+				t.Fatalf("can't construct libanubis.Server: %v", err)
+			}
+
+			t.Run("no-cf-worker-header", func(t *testing.T) {
+				req, err := http.NewRequest(http.MethodGet, "/", nil)
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				req.Header.Add("X-Real-Ip", "127.0.0.1")
+
+				cr, _, err := s.check(req)
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				if cr.Rule != config.RuleAllow {
+					t.Errorf("rule is wrong, wanted %s, got: %s", config.RuleAllow, cr.Rule)
+				}
+			})
+		})
+	}
+}

lib/config.go

@@ -29,13 +29,15 @@ type Options struct {
 	ServeRobotsTXT  bool
 	PrivateKey      ed25519.PrivateKey
 
+	CookieExpiration  time.Duration
 	CookieDomain      string
 	CookieName        string
 	CookiePartitioned bool
 
-	OGPassthrough bool
-	OGTimeToLive  time.Duration
-	Target        string
+	OGPassthrough        bool
+	OGTimeToLive         time.Duration
+	OGCacheConsidersHost bool
+	Target               string
 
 	WebmasterEmail string
 	BasePrefix     string
@@ -89,7 +91,7 @@ func New(opts Options) (*Server, error) {
 		policy:     opts.Policy,
 		opts:       opts,
 		DNSBLCache: decaymap.New[string, dnsbl.DroneBLResponse](),
-		OGTags:     ogtags.NewOGTagCache(opts.Target, opts.OGPassthrough, opts.OGTimeToLive),
+		OGTags:     ogtags.NewOGTagCache(opts.Target, opts.OGPassthrough, opts.OGTimeToLive, opts.OGCacheConsidersHost),
 	}
 
 	mux := http.NewServeMux()

lib/http.go

@@ -54,7 +54,7 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
 	var ogTags map[string]string = nil
 	if s.opts.OGPassthrough {
 		var err error
-		ogTags, err = s.OGTags.GetOGTags(r.URL)
+		ogTags, err = s.OGTags.GetOGTags(r.URL, r.Host)
 		if err != nil {
 			lg.Error("failed to get OG tags", "err", err)
 		}
@@ -67,7 +67,10 @@ func (s *Server) RenderIndex(w http.ResponseWriter, r *http.Request, rule *polic
 		return
 	}
 
-	handler := internal.NoStoreCache(templ.Handler(component))
+	handler := internal.NoStoreCache(templ.Handler(
+		component,
+		templ.WithStatus(s.opts.Policy.StatusCodes.Challenge),
+	))
 	handler.ServeHTTP(w, r)
 }
 

lib/policy/celchecker.go

@@ -0,0 +1,108 @@
+package policy
+
+import (
+	"fmt"
+	"net/http"
+
+	"github.com/TecharoHQ/anubis/internal"
+	"github.com/TecharoHQ/anubis/lib/policy/config"
+	"github.com/TecharoHQ/anubis/lib/policy/expressions"
+	"github.com/google/cel-go/cel"
+	"github.com/google/cel-go/common/types"
+)
+
+type CELChecker struct {
+	src     string
+	program cel.Program
+}
+
+func NewCELChecker(cfg *config.ExpressionOrList) (*CELChecker, error) {
+	env, err := expressions.NewEnvironment()
+	if err != nil {
+		return nil, err
+	}
+
+	var src string
+	var ast *cel.Ast
+
+	if cfg.Expression != "" {
+		src = cfg.Expression
+		var iss *cel.Issues
+		intermediate, iss := env.Compile(src)
+		if iss != nil {
+			return nil, iss.Err()
+		}
+
+		ast, iss = env.Check(intermediate)
+		if iss != nil {
+			return nil, iss.Err()
+		}
+	}
+
+	if len(cfg.All) != 0 {
+		ast, err = expressions.Join(env, expressions.JoinAnd, cfg.All...)
+	}
+
+	if len(cfg.Any) != 0 {
+		ast, err = expressions.Join(env, expressions.JoinOr, cfg.Any...)
+	}
+
+	if err != nil {
+		return nil, err
+	}
+
+	program, err := expressions.Compile(env, ast)
+	if err != nil {
+		return nil, fmt.Errorf("can't compile CEL program: %w", err)
+	}
+
+	return &CELChecker{
+		src:     src,
+		program: program,
+	}, nil
+}
+
+func (cc *CELChecker) Hash() string {
+	return internal.SHA256sum(cc.src)
+}
+
+func (cc *CELChecker) Check(r *http.Request) (bool, error) {
+	result, _, err := cc.program.ContextEval(r.Context(), &CELRequest{r})
+
+	if err != nil {
+		return false, err
+	}
+
+	if val, ok := result.(types.Bool); ok {
+		return bool(val), nil
+	}
+
+	return false, nil
+}
+
+type CELRequest struct {
+	*http.Request
+}
+
+func (cr *CELRequest) Parent() cel.Activation { return nil }
+
+func (cr *CELRequest) ResolveName(name string) (any, bool) {
+	switch name {
+	case "remoteAddress":
+		return cr.Header.Get("X-Real-Ip"), true
+	case "host":
+		return cr.Host, true
+	case "method":
+		return cr.Method, true
+	case "userAgent":
+		return cr.UserAgent(), true
+	case "path":
+		return cr.URL.Path, true
+	case "query":
+		return expressions.URLValues{Values: cr.URL.Query()}, true
+	case "headers":
+		return expressions.HTTPHeaders{Header: cr.Header}, true
+	default:
+		return nil, false
+	}
+}

lib/policy/config/config.go

@@ -6,6 +6,7 @@ import (
 	"io"
 	"io/fs"
 	"net"
+	"net/http"
 	"os"
 	"regexp"
 	"strings"
@@ -28,6 +29,7 @@ var (
 	ErrInvalidImportStatement            = errors.New("config.ImportStatement: invalid source file")
 	ErrCantSetBotAndImportValuesAtOnce   = errors.New("config.BotOrImport: can't set bot rules and import values at the same time")
 	ErrMustSetBotOrImportRules           = errors.New("config.BotOrImport: rule definition is invalid, you must set either bot rules or an import statement, not both")
+	ErrStatusCodeNotValid                = errors.New("config.StatusCode: status code not valid, must be between 100 and 599")
 )
 
 type Rule string
@@ -53,9 +55,11 @@ type BotConfig struct {
 	UserAgentRegex *string           `json:"user_agent_regex"`
 	PathRegex      *string           `json:"path_regex"`
 	HeadersRegex   map[string]string `json:"headers_regex"`
-	Action         Rule              `json:"action"`
 	RemoteAddr     []string          `json:"remote_addresses"`
-	Challenge      *ChallengeRules   `json:"challenge,omitempty"`
+	Expression     *ExpressionOrList `json:"expression"`
+
+	Action    Rule            `json:"action"`
+	Challenge *ChallengeRules `json:"challenge,omitempty"`
 }
 
 func (b BotConfig) Zero() bool {
@@ -83,7 +87,12 @@ func (b BotConfig) Valid() error {
 		errs = append(errs, ErrBotMustHaveName)
 	}
 
-	if b.UserAgentRegex == nil && b.PathRegex == nil && len(b.RemoteAddr) == 0 && len(b.HeadersRegex) == 0 {
+	allFieldsEmpty := b.UserAgentRegex == nil &&
+		b.PathRegex == nil &&
+		len(b.RemoteAddr) == 0 &&
+		len(b.HeadersRegex) == 0
+
+	if allFieldsEmpty && b.Expression == nil {
 		errs = append(errs, ErrBotMustHaveUserAgentOrPath)
 	}
 
@@ -135,6 +144,12 @@ func (b BotConfig) Valid() error {
 		}
 	}
 
+	if b.Expression != nil {
+		if err := b.Expression.Valid(); err != nil {
+			errs = append(errs, err)
+		}
+	}
+
 	switch b.Action {
 	case RuleAllow, RuleBenchmark, RuleChallenge, RuleDeny:
 		// okay
@@ -214,18 +229,27 @@ func (is *ImportStatement) load() error {
 	}
 	defer fin.Close()
 
+	var imported []BotOrImport
 	var result []BotConfig
 
-	if err := yaml.NewYAMLToJSONDecoder(fin).Decode(&result); err != nil {
+	if err := yaml.NewYAMLToJSONDecoder(fin).Decode(&imported); err != nil {
 		return fmt.Errorf("can't parse %s: %w", is.Import, err)
 	}
 
 	var errs []error
 
-	for _, b := range result {
+	for _, b := range imported {
 		if err := b.Valid(); err != nil {
 			errs = append(errs, err)
 		}
+
+		if b.ImportStatement != nil {
+			result = append(result, b.ImportStatement.Bots...)
+		}
+
+		if b.BotConfig != nil {
+			result = append(result, *b.BotConfig)
+		}
 	}
 
 	if len(errs) != 0 {
@@ -262,9 +286,33 @@ func (boi *BotOrImport) Valid() error {
 	return ErrMustSetBotOrImportRules
 }
 
+type StatusCodes struct {
+	Challenge int `json:"CHALLENGE"`
+	Deny      int `json:"DENY"`
+}
+
+func (sc StatusCodes) Valid() error {
+	var errs []error
+
+	if sc.Challenge == 0 || (sc.Challenge < 100 && sc.Challenge >= 599) {
+		errs = append(errs, fmt.Errorf("%w: challenge is %d", ErrStatusCodeNotValid, sc.Challenge))
+	}
+
+	if sc.Deny == 0 || (sc.Deny < 100 && sc.Deny >= 599) {
+		errs = append(errs, fmt.Errorf("%w: deny is %d", ErrStatusCodeNotValid, sc.Deny))
+	}
+
+	if len(errs) != 0 {
+		return fmt.Errorf("status codes not valid:\n%w", errors.Join(errs...))
+	}
+
+	return nil
+}
+
 type fileConfig struct {
-	Bots  []BotOrImport `json:"bots"`
-	DNSBL bool          `json:"dnsbl"`
+	Bots        []BotOrImport `json:"bots"`
+	DNSBL       bool          `json:"dnsbl"`
+	StatusCodes StatusCodes   `json:"status_codes"`
 }
 
 func (c fileConfig) Valid() error {
@@ -280,6 +328,10 @@ func (c fileConfig) Valid() error {
 		}
 	}
 
+	if err := c.StatusCodes.Valid(); err != nil {
+		errs = append(errs, err)
+	}
+
 	if len(errs) != 0 {
 		return fmt.Errorf("config is not valid:\n%w", errors.Join(errs...))
 	}
@@ -289,6 +341,10 @@ func (c fileConfig) Valid() error {
 
 func Load(fin io.Reader, fname string) (*Config, error) {
 	var c fileConfig
+	c.StatusCodes = StatusCodes{
+		Challenge: http.StatusOK,
+		Deny:      http.StatusOK,
+	}
 	if err := yaml.NewYAMLToJSONDecoder(fin).Decode(&c); err != nil {
 		return nil, fmt.Errorf("can't parse policy config YAML %s: %w", fname, err)
 	}
@@ -298,7 +354,8 @@ func Load(fin io.Reader, fname string) (*Config, error) {
 	}
 
 	result := &Config{
-		DNSBL: c.DNSBL,
+		DNSBL:       c.DNSBL,
+		StatusCodes: c.StatusCodes,
 	}
 
 	var validationErrs []error
@@ -331,8 +388,9 @@ func Load(fin io.Reader, fname string) (*Config, error) {
 }
 
 type Config struct {
-	Bots  []BotConfig
-	DNSBL bool
+	Bots        []BotConfig
+	DNSBL       bool
+	StatusCodes StatusCodes
 }
 
 func (c Config) Valid() error {

lib/policy/config/expressionorlist.go

@@ -0,0 +1,62 @@
+package config
+
+import (
+	"encoding/json"
+	"errors"
+	"slices"
+)
+
+var (
+	ErrExpressionOrListMustBeStringOrObject = errors.New("config: this must be a string or an object")
+	ErrExpressionEmpty                      = errors.New("config: this expression is empty")
+	ErrExpressionCantHaveBoth               = errors.New("config: expression block can't contain multiple expression types")
+)
+
+type ExpressionOrList struct {
+	Expression string   `json:"-"`
+	All        []string `json:"all"`
+	Any        []string `json:"any"`
+}
+
+func (eol ExpressionOrList) Equal(rhs *ExpressionOrList) bool {
+	if eol.Expression != rhs.Expression {
+		return false
+	}
+
+	if !slices.Equal(eol.All, rhs.All) {
+		return false
+	}
+
+	if !slices.Equal(eol.Any, rhs.Any) {
+		return false
+	}
+
+	return true
+}
+
+func (eol *ExpressionOrList) UnmarshalJSON(data []byte) error {
+	switch string(data[0]) {
+	case `"`: // string
+		return json.Unmarshal(data, &eol.Expression)
+	case "{": // object
+		type RawExpressionOrList ExpressionOrList
+		var val RawExpressionOrList
+		if err := json.Unmarshal(data, &val); err != nil {
+			return err
+		}
+		eol.All = val.All
+		eol.Any = val.Any
+
+		return nil
+	}
+
+	return ErrExpressionOrListMustBeStringOrObject
+}
+
+func (eol *ExpressionOrList) Valid() error {
+	if len(eol.All) != 0 && len(eol.Any) != 0 {
+		return ErrExpressionCantHaveBoth
+	}
+
+	return nil
+}

lib/policy/config/expressionorlist_test.go

@@ -0,0 +1,73 @@
+package config
+
+import (
+	"encoding/json"
+	"errors"
+	"testing"
+)
+
+func TestExpressionOrListUnmarshal(t *testing.T) {
+	for _, tt := range []struct {
+		name     string
+		inp      string
+		err      error
+		validErr error
+		result   *ExpressionOrList
+	}{
+		{
+			name: "simple",
+			inp:  `"\"User-Agent\" in headers"`,
+			result: &ExpressionOrList{
+				Expression: `"User-Agent" in headers`,
+			},
+		},
+		{
+			name: "object-and",
+			inp: `{
+			"all": ["\"User-Agent\" in headers"]
+			}`,
+			result: &ExpressionOrList{
+				All: []string{
+					`"User-Agent" in headers`,
+				},
+			},
+		},
+		{
+			name: "object-or",
+			inp: `{
+			"any": ["\"User-Agent\" in headers"]
+			}`,
+			result: &ExpressionOrList{
+				Any: []string{
+					`"User-Agent" in headers`,
+				},
+			},
+		},
+		{
+			name: "both-or-and",
+			inp: `{
+			"all": ["\"User-Agent\" in headers"],
+			"any": ["\"User-Agent\" in headers"]
+			}`,
+			validErr: ErrExpressionCantHaveBoth,
+		},
+	} {
+		t.Run(tt.name, func(t *testing.T) {
+			var eol ExpressionOrList
+
+			if err := json.Unmarshal([]byte(tt.inp), &eol); !errors.Is(err, tt.err) {
+				t.Errorf("wanted unmarshal error: %v but got: %v", tt.err, err)
+			}
+
+			if tt.result != nil && !eol.Equal(tt.result) {
+				t.Logf("wanted: %#v", tt.result)
+				t.Logf("got:    %#v", &eol)
+				t.Fatal("parsed expression is not what was expected")
+			}
+
+			if err := eol.Valid(); !errors.Is(err, tt.validErr) {
+				t.Errorf("wanted validation error: %v but got: %v", tt.err, err)
+			}
+		})
+	}
+}

lib/policy/config/testdata/bad/multiple_expression_types.json

@@ -0,0 +1,17 @@
+{
+  "bots": [
+    {
+      "name": "multiple-expression-types",
+      "action": "ALLOW",
+      "expression": {
+        "all": [
+          "userAgent.startsWith(\"git/\") || userAgent.contains(\"libgit\")",
+          "\"Git-Protocol\" in headers && headers[\"Git-Protocol\"] == \"version=2\"\n"
+        ],
+        "any": [
+          "userAgent.startsWith(\"evilbot/\")"
+        ]
+      }
+    }
+  ]
+}

lib/policy/config/testdata/bad/multiple_expression_types.yaml

@@ -0,0 +1,10 @@
+bots:
+- name: multiple-expression-types
+  action: ALLOW
+  expression:
+    all:
+    - userAgent.startsWith("git/") || userAgent.contains("libgit")
+    - >
+      "Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"
+    any:
+    - userAgent.startsWith("evilbot/")

lib/policy/config/testdata/bad/status-codes-0.json

@@ -0,0 +1,13 @@
+{
+  "bots": [
+    {
+      "name": "everything",
+      "user_agent_regex": ".*",
+      "action": "DENY"
+    }
+  ],
+  "status_codes": {
+    "CHALLENGE": 0,
+    "DENY": 0
+  }
+}

lib/policy/config/testdata/bad/status-codes-0.yaml

@@ -0,0 +1,8 @@
+bots:
+- name: everything
+  user_agent_regex: .*
+  action: DENY
+
+status_codes:
+  CHALLENGE: 0
+  DENY: 0

lib/policy/config/testdata/good/git_client.json

@@ -0,0 +1,14 @@
+{
+  "bots": [
+    {
+      "name": "allow-git-clients",
+      "action": "ALLOW",
+      "expression": {
+        "all": [
+          "userAgent.startsWith(\"git/\") || userAgent.contains(\"libgit\")",
+          "\"Git-Protocol\" in headers && headers[\"Git-Protocol\"] == \"version=2\""
+        ]
+      }
+    }
+  ]
+}

lib/policy/config/testdata/good/git_client.yaml

@@ -0,0 +1,8 @@
+bots:
+- name: allow-git-clients
+  action: ALLOW
+  expression:
+    all:
+    - userAgent.startsWith("git/") || userAgent.contains("libgit")
+    - >
+      "Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"

lib/policy/config/testdata/good/status-codes-paranoid.json

@@ -0,0 +1,13 @@
+{
+  "bots": [
+    {
+      "name": "everything",
+      "user_agent_regex": ".*",
+      "action": "DENY"
+    }
+  ],
+  "status_codes": {
+    "CHALLENGE": 200,
+    "DENY": 200
+  }
+}

lib/policy/config/testdata/good/status-codes-paranoid.yaml

@@ -0,0 +1,8 @@
+bots:
+- name: everything
+  user_agent_regex: .*
+  action: DENY
+
+status_codes:
+  CHALLENGE: 200
+  DENY: 200

lib/policy/config/testdata/good/status-codes-rfc.json

@@ -0,0 +1,13 @@
+{
+  "bots": [
+    {
+      "name": "everything",
+      "user_agent_regex": ".*",
+      "action": "DENY"
+    }
+  ],
+  "status_codes": {
+    "CHALLENGE": 403,
+    "DENY": 403
+  }
+}

lib/policy/config/testdata/good/status-codes-rfc.yaml

@@ -0,0 +1,8 @@
+bots:
+- name: everything
+  user_agent_regex: .*
+  action: DENY
+
+status_codes:
+  CHALLENGE: 403
+  DENY: 403

lib/policy/expressions/README.md

@@ -0,0 +1,3 @@
+# Expressions support
+
+The expressions support is based on ideas from [go-away](https://git.gammaspectra.live/git/go-away) but with different opinions about how things should be done.

lib/policy/expressions/environment.go

@@ -0,0 +1,45 @@
+package expressions
+
+import (
+	"github.com/google/cel-go/cel"
+	"github.com/google/cel-go/ext"
+)
+
+// NewEnvironment creates a new CEL environment, this is the set of
+// variables and functions that are passed into the CEL scope so that
+// Anubis can fail loudly and early when something is invalid instead
+// of blowing up at runtime.
+func NewEnvironment() (*cel.Env, error) {
+	return cel.NewEnv(
+		ext.Strings(
+			ext.StringsLocale("en_US"),
+			ext.StringsValidateFormatCalls(true),
+		),
+
+		// default all timestamps to UTC
+		cel.DefaultUTCTimeZone(true),
+
+		// Variables exposed to CEL programs:
+		cel.Variable("remoteAddress", cel.StringType),
+		cel.Variable("host", cel.StringType),
+		cel.Variable("method", cel.StringType),
+		cel.Variable("userAgent", cel.StringType),
+		cel.Variable("path", cel.StringType),
+		cel.Variable("query", cel.MapType(cel.StringType, cel.StringType)),
+		cel.Variable("headers", cel.MapType(cel.StringType, cel.StringType)),
+
+		// Functions exposed to CEL programs:
+	)
+}
+
+// Compile takes CEL environment and syntax tree then emits an optimized
+// Program for execution.
+func Compile(env *cel.Env, ast *cel.Ast) (cel.Program, error) {
+	return env.Program(
+		ast,
+		cel.EvalOptions(
+			// optimize regular expressions right now instead of on the fly
+			cel.OptOptimize,
+		),
+	)
+}

lib/policy/expressions/http_headers.go

@@ -0,0 +1,75 @@
+package expressions
+
+import (
+	"net/http"
+	"reflect"
+	"strings"
+
+	"github.com/google/cel-go/common/types"
+	"github.com/google/cel-go/common/types/ref"
+	"github.com/google/cel-go/common/types/traits"
+)
+
+// HTTPHeaders is a type wrapper to expose HTTP headers into CEL programs.
+type HTTPHeaders struct {
+	http.Header
+}
+
+func (h HTTPHeaders) ConvertToNative(typeDesc reflect.Type) (any, error) {
+	return nil, ErrNotImplemented
+}
+
+func (h HTTPHeaders) ConvertToType(typeVal ref.Type) ref.Val {
+	switch typeVal {
+	case types.MapType:
+		return h
+	case types.TypeType:
+		return types.MapType
+	}
+
+	return types.NewErr("can't convert from %q to %q", types.MapType, typeVal)
+}
+
+func (h HTTPHeaders) Equal(other ref.Val) ref.Val {
+	return types.Bool(false) // We don't want to compare header maps
+}
+
+func (h HTTPHeaders) Type() ref.Type {
+	return types.MapType
+}
+
+func (h HTTPHeaders) Value() any { return h }
+
+func (h HTTPHeaders) Find(key ref.Val) (ref.Val, bool) {
+	k, ok := key.(types.String)
+	if !ok {
+		return nil, false
+	}
+
+	if _, ok := h.Header[string(k)]; !ok {
+		return nil, false
+	}
+
+	return types.String(strings.Join(h.Header.Values(string(k)), ",")), true
+}
+
+func (h HTTPHeaders) Contains(key ref.Val) ref.Val {
+	_, ok := h.Find(key)
+	return types.Bool(ok)
+}
+
+func (h HTTPHeaders) Get(key ref.Val) ref.Val {
+	result, ok := h.Find(key)
+	if !ok {
+		return types.ValOrErr(result, "no such key: %v", key)
+	}
+	return result
+}
+
+func (h HTTPHeaders) Iterator() traits.Iterator { panic("TODO(Xe): implement me") }
+
+func (h HTTPHeaders) IsZeroValue() bool {
+	return len(h.Header) == 0
+}
+
+func (h HTTPHeaders) Size() ref.Val { return types.Int(len(h.Header)) }

lib/policy/expressions/http_headers_test.go

@@ -0,0 +1,52 @@
+package expressions
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/google/cel-go/common/types"
+)
+
+func TestHTTPHeaders(t *testing.T) {
+	headers := HTTPHeaders{
+		Header: http.Header{
+			"Content-Type": {"application/json"},
+			"Cf-Worker":    {"true"},
+			"User-Agent":   {"Go-http-client/2"},
+		},
+	}
+
+	t.Run("contains-existing-header", func(t *testing.T) {
+		resp := headers.Contains(types.String("User-Agent"))
+		if !bool(resp.(types.Bool)) {
+			t.Fatal("headers does not contain User-Agent")
+		}
+	})
+
+	t.Run("not-contains-missing-header", func(t *testing.T) {
+		resp := headers.Contains(types.String("Xxx-Random-Header"))
+		if bool(resp.(types.Bool)) {
+			t.Fatal("headers does not contain User-Agent")
+		}
+	})
+
+	t.Run("get-existing-header", func(t *testing.T) {
+		val := headers.Get(types.String("User-Agent"))
+		switch val.(type) {
+		case types.String:
+			// ok
+		default:
+			t.Fatalf("result was wrong type %T", val)
+		}
+	})
+
+	t.Run("not-get-missing-header", func(t *testing.T) {
+		val := headers.Get(types.String("Xxx-Random-Header"))
+		switch val.(type) {
+		case *types.Err:
+			// ok
+		default:
+			t.Fatalf("result was wrong type %T", val)
+		}
+	})
+}

lib/policy/expressions/join.go

@@ -0,0 +1,104 @@
+package expressions
+
+import (
+	"errors"
+	"fmt"
+	"strings"
+
+	"github.com/google/cel-go/cel"
+)
+
+// JoinOperator is a type wrapper for and/or operators.
+//
+// This is a separate type so that validation can be done at the type level.
+type JoinOperator string
+
+// Possible values for JoinOperator
+const (
+	JoinAnd JoinOperator = "&&"
+	JoinOr  JoinOperator = "||"
+)
+
+// Valid ensures that JoinOperator is semantically valid.
+func (jo JoinOperator) Valid() error {
+	switch jo {
+	case JoinAnd, JoinOr:
+		return nil
+	default:
+		return ErrWrongJoinOperator
+	}
+}
+
+var (
+	ErrWrongJoinOperator = errors.New("expressions: invalid join operator")
+	ErrNoExpressions     = errors.New("expressions: cannot join zero expressions")
+	ErrCantCompile       = errors.New("expressions: can't compile one expression")
+)
+
+// JoinClauses joins a list of compiled clauses into one big if statement.
+//
+// Imagine the following two clauses:
+//
+//	ball.color == "red"
+//	ball.shape == "round"
+//
+// JoinClauses would emit one "joined" clause such as:
+//
+//	( ball.color == "red" ) && ( ball.shape == "round" )
+func JoinClauses(env *cel.Env, operator JoinOperator, clauses ...*cel.Ast) (*cel.Ast, error) {
+	if err := operator.Valid(); err != nil {
+		return nil, fmt.Errorf("%w: wanted && or ||, got: %q", err, operator)
+	}
+
+	switch len(clauses) {
+	case 0:
+		return nil, ErrNoExpressions
+	case 1:
+		return clauses[0], nil
+	}
+
+	var exprs []string
+	var errs []error
+
+	for _, clause := range clauses {
+		clauseStr, err := cel.AstToString(clause)
+		if err != nil {
+			errs = append(errs, err)
+			continue
+		}
+
+		exprs = append(exprs, "( "+clauseStr+" )")
+	}
+
+	if len(errs) != 0 {
+		return nil, fmt.Errorf("errors while decompiling statements: %w", errors.Join(errs...))
+	}
+
+	statement := strings.Join(exprs, " "+string(operator)+" ")
+	result, iss := env.Compile(statement)
+	if iss != nil {
+		return nil, iss.Err()
+	}
+
+	return result, nil
+}
+
+func Join(env *cel.Env, operator JoinOperator, clauses ...string) (*cel.Ast, error) {
+	var statements []*cel.Ast
+	var errs []error
+
+	for _, clause := range clauses {
+		stmt, iss := env.Compile(clause)
+		if iss != nil && iss.Err() != nil {
+			errs = append(errs, fmt.Errorf("%w: %q gave: %w", ErrCantCompile, clause, iss.Err()))
+			continue
+		}
+		statements = append(statements, stmt)
+	}
+
+	if len(errs) != 0 {
+		return nil, fmt.Errorf("errors while joining clauses: %w", errors.Join(errs...))
+	}
+
+	return JoinClauses(env, operator, statements...)
+}

lib/policy/expressions/join_test.go

@@ -0,0 +1,90 @@
+package expressions
+
+import (
+	"errors"
+	"testing"
+
+	"github.com/google/cel-go/cel"
+)
+
+func TestJoin(t *testing.T) {
+	env, err := NewEnvironment()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for _, tt := range []struct {
+		name      string
+		clauses   []string
+		op        JoinOperator
+		err       error
+		resultStr string
+	}{
+		{
+			name:    "no-clauses",
+			clauses: []string{},
+			op:      JoinAnd,
+			err:     ErrNoExpressions,
+		},
+		{
+			name:      "one-clause-identity",
+			clauses:   []string{`remoteAddress == "8.8.8.8"`},
+			op:        JoinAnd,
+			err:       nil,
+			resultStr: `remoteAddress == "8.8.8.8"`,
+		},
+		{
+			name: "multi-clause-and",
+			clauses: []string{
+				`remoteAddress == "8.8.8.8"`,
+				`host == "anubis.techaro.lol"`,
+			},
+			op:        JoinAnd,
+			err:       nil,
+			resultStr: `remoteAddress == "8.8.8.8" && host == "anubis.techaro.lol"`,
+		},
+		{
+			name: "multi-clause-or",
+			clauses: []string{
+				`remoteAddress == "8.8.8.8"`,
+				`host == "anubis.techaro.lol"`,
+			},
+			op:        JoinOr,
+			err:       nil,
+			resultStr: `remoteAddress == "8.8.8.8" || host == "anubis.techaro.lol"`,
+		},
+		{
+			name: "git-user-agent",
+			clauses: []string{
+				`userAgent.startsWith("git/") || userAgent.contains("libgit")`,
+				`"Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"`,
+			},
+			op:  JoinAnd,
+			err: nil,
+			resultStr: `(userAgent.startsWith("git/") || userAgent.contains("libgit")) && "Git-Protocol" in headers &&
+headers["Git-Protocol"] == "version=2"`,
+		},
+	} {
+		t.Run(tt.name, func(t *testing.T) {
+			result, err := Join(env, tt.op, tt.clauses...)
+			if !errors.Is(err, tt.err) {
+				t.Errorf("wanted error %v but got: %v", tt.err, err)
+			}
+
+			if tt.err != nil {
+				return
+			}
+
+			program, err := cel.AstToString(result)
+			if err != nil {
+				t.Fatalf("can't decompile program: %v", err)
+			}
+
+			if tt.resultStr != program {
+				t.Logf("wanted: %s", tt.resultStr)
+				t.Logf("got: %s", program)
+				t.Error("program did not compile as expected")
+			}
+		})
+	}
+}

lib/policy/expressions/url_values.go

@@ -0,0 +1,78 @@
+package expressions
+
+import (
+	"errors"
+	"net/url"
+	"reflect"
+	"strings"
+
+	"github.com/google/cel-go/common/types"
+	"github.com/google/cel-go/common/types/ref"
+	"github.com/google/cel-go/common/types/traits"
+)
+
+var ErrNotImplemented = errors.New("expressions: not implemented")
+
+// URLValues is a type wrapper to expose url.Values into CEL programs.
+type URLValues struct {
+	url.Values
+}
+
+func (u URLValues) ConvertToNative(typeDesc reflect.Type) (any, error) {
+	return nil, ErrNotImplemented
+}
+
+func (u URLValues) ConvertToType(typeVal ref.Type) ref.Val {
+	switch typeVal {
+	case types.MapType:
+		return u
+	case types.TypeType:
+		return types.MapType
+	}
+
+	return types.NewErr("can't convert from %q to %q", types.MapType, typeVal)
+}
+
+func (u URLValues) Equal(other ref.Val) ref.Val {
+	return types.Bool(false) // We don't want to compare header maps
+}
+
+func (u URLValues) Type() ref.Type {
+	return types.MapType
+}
+
+func (u URLValues) Value() any { return u }
+
+func (u URLValues) Find(key ref.Val) (ref.Val, bool) {
+	k, ok := key.(types.String)
+	if !ok {
+		return nil, false
+	}
+
+	if _, ok := u.Values[string(k)]; !ok {
+		return nil, false
+	}
+
+	return types.String(strings.Join(u.Values[string(k)], ",")), true
+}
+
+func (u URLValues) Contains(key ref.Val) ref.Val {
+	_, ok := u.Find(key)
+	return types.Bool(ok)
+}
+
+func (u URLValues) Get(key ref.Val) ref.Val {
+	result, ok := u.Find(key)
+	if !ok {
+		return types.ValOrErr(result, "no such key: %v", key)
+	}
+	return result
+}
+
+func (u URLValues) Iterator() traits.Iterator { panic("TODO(Xe): implement me") }
+
+func (u URLValues) IsZeroValue() bool {
+	return len(u.Values) == 0
+}
+
+func (u URLValues) Size() ref.Val { return types.Int(len(u.Values)) }

lib/policy/expressions/url_values_test.go

@@ -0,0 +1,50 @@
+package expressions
+
+import (
+	"net/url"
+	"testing"
+
+	"github.com/google/cel-go/common/types"
+)
+
+func TestURLValues(t *testing.T) {
+	headers := URLValues{
+		Values: url.Values{
+			"format": {"json"},
+		},
+	}
+
+	t.Run("contains-existing-key", func(t *testing.T) {
+		resp := headers.Contains(types.String("format"))
+		if !bool(resp.(types.Bool)) {
+			t.Fatal("headers does not contain User-Agent")
+		}
+	})
+
+	t.Run("not-contains-missing-key", func(t *testing.T) {
+		resp := headers.Contains(types.String("not-there"))
+		if bool(resp.(types.Bool)) {
+			t.Fatal("headers does not contain User-Agent")
+		}
+	})
+
+	t.Run("get-existing-key", func(t *testing.T) {
+		val := headers.Get(types.String("format"))
+		switch val.(type) {
+		case types.String:
+			// ok
+		default:
+			t.Fatalf("result was wrong type %T", val)
+		}
+	})
+
+	t.Run("not-get-missing-key", func(t *testing.T) {
+		val := headers.Get(types.String("not-there"))
+		switch val.(type) {
+		case *types.Err:
+			// ok
+		default:
+			t.Fatalf("result was wrong type %T", val)
+		}
+	})
+}

lib/policy/policy.go

@@ -24,11 +24,13 @@ type ParsedConfig struct {
 	Bots              []Bot
 	DNSBL             bool
 	DefaultDifficulty int
+	StatusCodes       config.StatusCodes
 }
 
 func NewParsedConfig(orig *config.Config) *ParsedConfig {
 	return &ParsedConfig{
-		orig: orig,
+		orig:        orig,
+		StatusCodes: orig.StatusCodes,
 	}
 }
 
@@ -92,6 +94,15 @@ func ParseConfig(fin io.Reader, fname string, defaultDifficulty int) (*ParsedCon
 			}
 		}
 
+		if b.Expression != nil {
+			c, err := NewCELChecker(b.Expression)
+			if err != nil {
+				validationErrs = append(validationErrs, fmt.Errorf("while processing rule %s expressions: %w", b.Name, err))
+			} else {
+				cl = append(cl, c)
+			}
+		}
+
 		if b.Challenge == nil {
 			parsedBot.Challenge = &config.ChallengeRules{
 				Difficulty: defaultDifficulty,

lib/testdata/aggressive_403.yaml

@@ -0,0 +1,12 @@
+bots:
+- name: deny
+  user_agent_regex: DENY
+  action: DENY
+
+- name: challenge
+  user_agent_regex: CHALLENGE
+  action: CHALLENGE
+
+status_codes:
+  CHALLENGE: 401
+  DENY: 403

lib/testdata/cloudflare-workers-cel.yaml

@@ -0,0 +1,4 @@
+bots:
+- name: cloudflare-workers
+  expression: '"Cf-Worker" in headers'
+  action: DENY

lib/testdata/cloudflare-workers-header.yaml

@@ -0,0 +1,5 @@
+bots:
+- name: cloudflare-workers
+  headers_regex:
+    CF-Worker: .*
+  action: DENY

package-lock.json

@@ -1,17 +1,17 @@
 {
   "name": "@techaro/anubis",
-  "version": "1.0.0-see-VERSION-file",
+  "version": "1.18.0-pre1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@techaro/anubis",
-      "version": "1.0.0-see-VERSION-file",
+      "version": "1.17.0",
       "license": "ISC",
       "devDependencies": {
         "cssnano": "^7.0.6",
         "cssnano-preset-advanced": "^7.0.6",
-        "esbuild": "^0.25.2",
+        "esbuild": "^0.25.3",
         "postcss-cli": "^11.0.1",
         "postcss-import": "^16.1.0",
         "postcss-import-url": "^7.2.0",
@@ -19,9 +19,9 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.25.2.tgz",
-      "integrity": "sha512-wCIboOL2yXZym2cgm6mlA742s9QeJ8DjGVaL39dLN4rRwrOgOyYSnOaFPhKZGLb2ngj4EyfAFjsNJwPXZvseag==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.25.3.tgz",
+      "integrity": "sha512-W8bFfPA8DowP8l//sxjJLSLkD8iEjMc7cBVyP+u4cEv9sM7mdUCkgsj+t0n/BWPFtv7WWCN5Yzj0N6FJNUUqBQ==",
       "cpu": [
         "ppc64"
       ],
@@ -36,9 +36,9 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.25.2.tgz",
-      "integrity": "sha512-NQhH7jFstVY5x8CKbcfa166GoV0EFkaPkCKBQkdPJFvo5u+nGXLEH/ooniLb3QI8Fk58YAx7nsPLozUWfCBOJA==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.25.3.tgz",
+      "integrity": "sha512-PuwVXbnP87Tcff5I9ngV0lmiSu40xw1At6i3GsU77U7cjDDB4s0X2cyFuBiDa1SBk9DnvWwnGvVaGBqoFWPb7A==",
       "cpu": [
         "arm"
       ],
@@ -53,9 +53,9 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.25.2.tgz",
-      "integrity": "sha512-5ZAX5xOmTligeBaeNEPnPaeEuah53Id2tX4c2CVP3JaROTH+j4fnfHCkr1PjXMd78hMst+TlkfKcW/DlTq0i4w==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.25.3.tgz",
+      "integrity": "sha512-XelR6MzjlZuBM4f5z2IQHK6LkK34Cvv6Rj2EntER3lwCBFdg6h2lKbtRjpTTsdEjD/WSe1q8UyPBXP1x3i/wYQ==",
       "cpu": [
         "arm64"
       ],
@@ -70,9 +70,9 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.25.2.tgz",
-      "integrity": "sha512-Ffcx+nnma8Sge4jzddPHCZVRvIfQ0kMsUsCMcJRHkGJ1cDmhe4SsrYIjLUKn1xpHZybmOqCWwB0zQvsjdEHtkg==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.25.3.tgz",
+      "integrity": "sha512-ogtTpYHT/g1GWS/zKM0cc/tIebFjm1F9Aw1boQ2Y0eUQ+J89d0jFY//s9ei9jVIlkYi8AfOjiixcLJSGNSOAdQ==",
       "cpu": [
         "x64"
       ],
@@ -87,9 +87,9 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.25.2.tgz",
-      "integrity": "sha512-MpM6LUVTXAzOvN4KbjzU/q5smzryuoNjlriAIx+06RpecwCkL9JpenNzpKd2YMzLJFOdPqBpuub6eVRP5IgiSA==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.25.3.tgz",
+      "integrity": "sha512-eESK5yfPNTqpAmDfFWNsOhmIOaQA59tAcF/EfYvo5/QWQCzXn5iUSOnqt3ra3UdzBv073ykTtmeLJZGt3HhA+w==",
       "cpu": [
         "arm64"
       ],
@@ -104,9 +104,9 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.25.2.tgz",
-      "integrity": "sha512-5eRPrTX7wFyuWe8FqEFPG2cU0+butQQVNcT4sVipqjLYQjjh8a8+vUTfgBKM88ObB85ahsnTwF7PSIt6PG+QkA==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.25.3.tgz",
+      "integrity": "sha512-Kd8glo7sIZtwOLcPbW0yLpKmBNWMANZhrC1r6K++uDR2zyzb6AeOYtI6udbtabmQpFaxJ8uduXMAo1gs5ozz8A==",
       "cpu": [
         "x64"
       ],
@@ -121,9 +121,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.25.2.tgz",
-      "integrity": "sha512-mLwm4vXKiQ2UTSX4+ImyiPdiHjiZhIaE9QvC7sw0tZ6HoNMjYAqQpGyui5VRIi5sGd+uWq940gdCbY3VLvsO1w==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.25.3.tgz",
+      "integrity": "sha512-EJiyS70BYybOBpJth3M0KLOus0n+RRMKTYzhYhFeMwp7e/RaajXvP+BWlmEXNk6uk+KAu46j/kaQzr6au+JcIw==",
       "cpu": [
         "arm64"
       ],
@@ -138,9 +138,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.25.2.tgz",
-      "integrity": "sha512-6qyyn6TjayJSwGpm8J9QYYGQcRgc90nmfdUb0O7pp1s4lTY+9D0H9O02v5JqGApUyiHOtkz6+1hZNvNtEhbwRQ==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.25.3.tgz",
+      "integrity": "sha512-Q+wSjaLpGxYf7zC0kL0nDlhsfuFkoN+EXrx2KSB33RhinWzejOd6AvgmP5JbkgXKmjhmpfgKZq24pneodYqE8Q==",
       "cpu": [
         "x64"
       ],
@@ -155,9 +155,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.25.2.tgz",
-      "integrity": "sha512-UHBRgJcmjJv5oeQF8EpTRZs/1knq6loLxTsjc3nxO9eXAPDLcWW55flrMVc97qFPbmZP31ta1AZVUKQzKTzb0g==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.25.3.tgz",
+      "integrity": "sha512-dUOVmAUzuHy2ZOKIHIKHCm58HKzFqd+puLaS424h6I85GlSDRZIA5ycBixb3mFgM0Jdh+ZOSB6KptX30DD8YOQ==",
       "cpu": [
         "arm"
       ],
@@ -172,9 +172,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.25.2.tgz",
-      "integrity": "sha512-gq/sjLsOyMT19I8obBISvhoYiZIAaGF8JpeXu1u8yPv8BE5HlWYobmlsfijFIZ9hIVGYkbdFhEqC0NvM4kNO0g==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.25.3.tgz",
+      "integrity": "sha512-xCUgnNYhRD5bb1C1nqrDV1PfkwgbswTTBRbAd8aH5PhYzikdf/ddtsYyMXFfGSsb/6t6QaPSzxtbfAZr9uox4A==",
       "cpu": [
         "arm64"
       ],
@@ -189,9 +189,9 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.25.2.tgz",
-      "integrity": "sha512-bBYCv9obgW2cBP+2ZWfjYTU+f5cxRoGGQ5SeDbYdFCAZpYWrfjjfYwvUpP8MlKbP0nwZ5gyOU/0aUzZ5HWPuvQ==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.25.3.tgz",
+      "integrity": "sha512-yplPOpczHOO4jTYKmuYuANI3WhvIPSVANGcNUeMlxH4twz/TeXuzEP41tGKNGWJjuMhotpGabeFYGAOU2ummBw==",
       "cpu": [
         "ia32"
       ],
@@ -206,9 +206,9 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.25.2.tgz",
-      "integrity": "sha512-SHNGiKtvnU2dBlM5D8CXRFdd+6etgZ9dXfaPCeJtz+37PIUlixvlIhI23L5khKXs3DIzAn9V8v+qb1TRKrgT5w==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.25.3.tgz",
+      "integrity": "sha512-P4BLP5/fjyihmXCELRGrLd793q/lBtKMQl8ARGpDxgzgIKJDRJ/u4r1A/HgpBpKpKZelGct2PGI4T+axcedf6g==",
       "cpu": [
         "loong64"
       ],
@@ -223,9 +223,9 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.25.2.tgz",
-      "integrity": "sha512-hDDRlzE6rPeoj+5fsADqdUZl1OzqDYow4TB4Y/3PlKBD0ph1e6uPHzIQcv2Z65u2K0kpeByIyAjCmjn1hJgG0Q==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.25.3.tgz",
+      "integrity": "sha512-eRAOV2ODpu6P5divMEMa26RRqb2yUoYsuQQOuFUexUoQndm4MdpXXDBbUoKIc0iPa4aCO7gIhtnYomkn2x+bag==",
       "cpu": [
         "mips64el"
       ],
@@ -240,9 +240,9 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.25.2.tgz",
-      "integrity": "sha512-tsHu2RRSWzipmUi9UBDEzc0nLc4HtpZEI5Ba+Omms5456x5WaNuiG3u7xh5AO6sipnJ9r4cRWQB2tUjPyIkc6g==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.25.3.tgz",
+      "integrity": "sha512-ZC4jV2p7VbzTlnl8nZKLcBkfzIf4Yad1SJM4ZMKYnJqZFD4rTI+pBG65u8ev4jk3/MPwY9DvGn50wi3uhdaghg==",
       "cpu": [
         "ppc64"
       ],
@@ -257,9 +257,9 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.25.2.tgz",
-      "integrity": "sha512-k4LtpgV7NJQOml/10uPU0s4SAXGnowi5qBSjaLWMojNCUICNu7TshqHLAEbkBdAszL5TabfvQ48kK84hyFzjnw==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.25.3.tgz",
+      "integrity": "sha512-LDDODcFzNtECTrUUbVCs6j9/bDVqy7DDRsuIXJg6so+mFksgwG7ZVnTruYi5V+z3eE5y+BJZw7VvUadkbfg7QA==",
       "cpu": [
         "riscv64"
       ],
@@ -274,9 +274,9 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.25.2.tgz",
-      "integrity": "sha512-GRa4IshOdvKY7M/rDpRR3gkiTNp34M0eLTaC1a08gNrh4u488aPhuZOCpkF6+2wl3zAN7L7XIpOFBhnaE3/Q8Q==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.25.3.tgz",
+      "integrity": "sha512-s+w/NOY2k0yC2p9SLen+ymflgcpRkvwwa02fqmAwhBRI3SC12uiS10edHHXlVWwfAagYSY5UpmT/zISXPMW3tQ==",
       "cpu": [
         "s390x"
       ],
@@ -291,9 +291,9 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.25.2.tgz",
-      "integrity": "sha512-QInHERlqpTTZ4FRB0fROQWXcYRD64lAoiegezDunLpalZMjcUcld3YzZmVJ2H/Cp0wJRZ8Xtjtj0cEHhYc/uUg==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.25.3.tgz",
+      "integrity": "sha512-nQHDz4pXjSDC6UfOE1Fw9Q8d6GCAd9KdvMZpfVGWSJztYCarRgSDfOVBY5xwhQXseiyxapkiSJi/5/ja8mRFFA==",
       "cpu": [
         "x64"
       ],
@@ -308,9 +308,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.25.2.tgz",
-      "integrity": "sha512-talAIBoY5M8vHc6EeI2WW9d/CkiO9MQJ0IOWX8hrLhxGbro/vBXJvaQXefW2cP0z0nQVTdQ/eNyGFV1GSKrxfw==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.25.3.tgz",
+      "integrity": "sha512-1QaLtOWq0mzK6tzzp0jRN3eccmN3hezey7mhLnzC6oNlJoUJz4nym5ZD7mDnS/LZQgkrhEbEiTn515lPeLpgWA==",
       "cpu": [
         "arm64"
       ],
@@ -325,9 +325,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.25.2.tgz",
-      "integrity": "sha512-voZT9Z+tpOxrvfKFyfDYPc4DO4rk06qamv1a/fkuzHpiVBMOhpjK+vBmWM8J1eiB3OLSMFYNaOaBNLXGChf5tg==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.25.3.tgz",
+      "integrity": "sha512-i5Hm68HXHdgv8wkrt+10Bc50zM0/eonPb/a/OFVfB6Qvpiirco5gBA5bz7S2SHuU+Y4LWn/zehzNX14Sp4r27g==",
       "cpu": [
         "x64"
       ],
@@ -342,9 +342,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.25.2.tgz",
-      "integrity": "sha512-dcXYOC6NXOqcykeDlwId9kB6OkPUxOEqU+rkrYVqJbK2hagWOMrsTGsMr8+rW02M+d5Op5NNlgMmjzecaRf7Tg==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.25.3.tgz",
+      "integrity": "sha512-zGAVApJEYTbOC6H/3QBr2mq3upG/LBEXr85/pTtKiv2IXcgKV0RT0QA/hSXZqSvLEpXeIxah7LczB4lkiYhTAQ==",
       "cpu": [
         "arm64"
       ],
@@ -359,9 +359,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.25.2.tgz",
-      "integrity": "sha512-t/TkWwahkH0Tsgoq1Ju7QfgGhArkGLkF1uYz8nQS/PPFlXbP5YgRpqQR3ARRiC2iXoLTWFxc6DJMSK10dVXluw==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.25.3.tgz",
+      "integrity": "sha512-fpqctI45NnCIDKBH5AXQBsD0NDPbEFczK98hk/aa6HJxbl+UtLkJV2+Bvy5hLSLk3LHmqt0NTkKNso1A9y1a4w==",
       "cpu": [
         "x64"
       ],
@@ -376,9 +376,9 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.25.2.tgz",
-      "integrity": "sha512-cfZH1co2+imVdWCjd+D1gf9NjkchVhhdpgb1q5y6Hcv9TP6Zi9ZG/beI3ig8TvwT9lH9dlxLq5MQBBgwuj4xvA==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.25.3.tgz",
+      "integrity": "sha512-ROJhm7d8bk9dMCUZjkS8fgzsPAZEjtRJqCAmVgB0gMrvG7hfmPmz9k1rwO4jSiblFjYmNvbECL9uhaPzONMfgA==",
       "cpu": [
         "x64"
       ],
@@ -393,9 +393,9 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.25.2.tgz",
-      "integrity": "sha512-7Loyjh+D/Nx/sOTzV8vfbB3GJuHdOQyrOryFdZvPHLf42Tk9ivBU5Aedi7iyX+x6rbn2Mh68T4qq1SDqJBQO5Q==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.25.3.tgz",
+      "integrity": "sha512-YWcow8peiHpNBiIXHwaswPnAXLsLVygFwCB3A7Bh5jRkIBFWHGmNQ48AlX4xDvQNoMZlPYzjVOQDYEzWCqufMQ==",
       "cpu": [
         "arm64"
       ],
@@ -410,9 +410,9 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.25.2.tgz",
-      "integrity": "sha512-WRJgsz9un0nqZJ4MfhabxaD9Ft8KioqU3JMinOTvobbX6MOSUigSBlogP8QB3uxpJDsFS6yN+3FDBdqE5lg9kg==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.25.3.tgz",
+      "integrity": "sha512-qspTZOIGoXVS4DpNqUYUs9UxVb04khS1Degaw/MnfMe7goQ3lTfQ13Vw4qY/Nj0979BGvMRpAYbs/BAxEvU8ew==",
       "cpu": [
         "ia32"
       ],
@@ -427,9 +427,9 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.25.2.tgz",
-      "integrity": "sha512-kM3HKb16VIXZyIeVrM1ygYmZBKybX8N4p754bw390wGO3Tf2j4L2/WYL+4suWujpgf6GBYs3jv7TyUivdd05JA==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.25.3.tgz",
+      "integrity": "sha512-ICgUR+kPimx0vvRzf+N/7L7tVSQeE3BYY+NhHRHXS1kBuPO7z2+7ea2HbhDyZdTephgvNvKrlDDKUexuCVBVvg==",
       "cpu": [
         "x64"
       ],
@@ -1044,9 +1044,9 @@
       }
     },
     "node_modules/esbuild": {
-      "version": "0.25.2",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.25.2.tgz",
-      "integrity": "sha512-16854zccKPnC+toMywC+uKNeYSv+/eXkevRAfwRD/G9Cleq66m8XFIrigkbvauLLlCfDL45Q2cWegSg53gGBnQ==",
+      "version": "0.25.3",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.25.3.tgz",
+      "integrity": "sha512-qKA6Pvai73+M2FtftpNKRxJ78GIjmFXFxd/1DVBqGo/qNhLSfv+G12n9pNoWdytJC8U00TrViOwpjT0zgqQS8Q==",
       "dev": true,
       "hasInstallScript": true,
       "license": "MIT",
@@ -1057,31 +1057,31 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.25.2",
-        "@esbuild/android-arm": "0.25.2",
-        "@esbuild/android-arm64": "0.25.2",
-        "@esbuild/android-x64": "0.25.2",
-        "@esbuild/darwin-arm64": "0.25.2",
-        "@esbuild/darwin-x64": "0.25.2",
-        "@esbuild/freebsd-arm64": "0.25.2",
-        "@esbuild/freebsd-x64": "0.25.2",
-        "@esbuild/linux-arm": "0.25.2",
-        "@esbuild/linux-arm64": "0.25.2",
-        "@esbuild/linux-ia32": "0.25.2",
-        "@esbuild/linux-loong64": "0.25.2",
-        "@esbuild/linux-mips64el": "0.25.2",
-        "@esbuild/linux-ppc64": "0.25.2",
-        "@esbuild/linux-riscv64": "0.25.2",
-        "@esbuild/linux-s390x": "0.25.2",
-        "@esbuild/linux-x64": "0.25.2",
-        "@esbuild/netbsd-arm64": "0.25.2",
-        "@esbuild/netbsd-x64": "0.25.2",
-        "@esbuild/openbsd-arm64": "0.25.2",
-        "@esbuild/openbsd-x64": "0.25.2",
-        "@esbuild/sunos-x64": "0.25.2",
-        "@esbuild/win32-arm64": "0.25.2",
-        "@esbuild/win32-ia32": "0.25.2",
-        "@esbuild/win32-x64": "0.25.2"
+        "@esbuild/aix-ppc64": "0.25.3",
+        "@esbuild/android-arm": "0.25.3",
+        "@esbuild/android-arm64": "0.25.3",
+        "@esbuild/android-x64": "0.25.3",
+        "@esbuild/darwin-arm64": "0.25.3",
+        "@esbuild/darwin-x64": "0.25.3",
+        "@esbuild/freebsd-arm64": "0.25.3",
+        "@esbuild/freebsd-x64": "0.25.3",
+        "@esbuild/linux-arm": "0.25.3",
+        "@esbuild/linux-arm64": "0.25.3",
+        "@esbuild/linux-ia32": "0.25.3",
+        "@esbuild/linux-loong64": "0.25.3",
+        "@esbuild/linux-mips64el": "0.25.3",
+        "@esbuild/linux-ppc64": "0.25.3",
+        "@esbuild/linux-riscv64": "0.25.3",
+        "@esbuild/linux-s390x": "0.25.3",
+        "@esbuild/linux-x64": "0.25.3",
+        "@esbuild/netbsd-arm64": "0.25.3",
+        "@esbuild/netbsd-x64": "0.25.3",
+        "@esbuild/openbsd-arm64": "0.25.3",
+        "@esbuild/openbsd-x64": "0.25.3",
+        "@esbuild/sunos-x64": "0.25.3",
+        "@esbuild/win32-arm64": "0.25.3",
+        "@esbuild/win32-ia32": "0.25.3",
+        "@esbuild/win32-x64": "0.25.3"
       }
     },
     "node_modules/escalade": {
@@ -2691,4 +2691,4 @@
       }
     }
   }
-}
+}

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@techaro/anubis",
-  "version": "1.17.0",
+  "version": "1.18.0-pre1",
   "description": "",
   "main": "index.js",
   "scripts": {
@@ -17,7 +17,7 @@
   "devDependencies": {
     "cssnano": "^7.0.6",
     "cssnano-preset-advanced": "^7.0.6",
-    "esbuild": "^0.25.2",
+    "esbuild": "^0.25.3",
     "postcss-cli": "^11.0.1",
     "postcss-import": "^16.1.0",
     "postcss-import-url": "^7.2.0",

test/anubis_configs/aggressive_403.yaml

@@ -0,0 +1,12 @@
+bots:
+- name: deny
+  user_agent_regex: DENY
+  action: DENY
+
+- name: challenge
+  user_agent_regex: CHALLENGE
+  action: CHALLENGE
+
+status_codes:
+  CHALLENGE: 401
+  DENY: 403

test/caddy/Caddyfile

@@ -0,0 +1,16 @@
+:80 {
+	reverse_proxy http://anubis:3000 {
+		header_up X-Real-Ip {remote_host}
+		header_up X-Http-Version {http.request.proto}
+	}
+}
+
+:443 {
+	tls /etc/techaro/pki/caddy.local.cetacean.club/cert.pem /etc/techaro/pki/caddy.local.cetacean.club/key.pem
+
+	reverse_proxy http://anubis:3000 {
+		header_up X-Real-Ip {remote_host}
+		header_up X-Http-Version {http.request.proto}
+		header_up X-Tls-Version {http.request.tls.version}
+	}
+}

test/caddy/Dockerfile

@@ -0,0 +1,9 @@
+# FROM caddy:2.10.0-builder AS builder
+
+# RUN xcaddy build \
+#   --with github.com/lolPants/caddy-requestid
+
+FROM caddy:2.10.0 AS run
+
+# COPY --from=builder /usr/bin/caddy /usr/bin/caddy
+COPY Caddyfile /etc/caddy/Caddyfile

test/caddy/docker-compose.yaml

@@ -0,0 +1,22 @@
+services:
+  caddy:
+    image: xxxtest/caddy
+    build: .
+    ports:
+      - 8080:80
+      - 8443:443
+    volumes:
+      - "../pki/caddy.local.cetacean.club:/etc/techaro/pki/caddy.local.cetacean.club/"
+
+  anubis:
+    image: ghcr.io/techarohq/anubis:main
+    environment:
+      BIND: ":3000"
+      TARGET: http://httpdebug:3000
+      POLICY_FNAME: /etc/techaro/anubis/less_paranoid.yaml
+    volumes:
+      - ../anubis_configs:/etc/techaro/anubis
+
+  httpdebug:
+    image: ghcr.io/xe/x/httpdebug
+    pull_policy: always

test/caddy/start.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+# If the transient local TLS certificate doesn't exist, mint a new one
+if [ ! -f ../pki/caddy.local.cetacean.club/cert.pem ]; then
+  # Subshell to contain the directory change
+  (
+    cd ../pki \
+    && mkdir -p caddy.local.cetacean.club \
+    && \
+    # Try using https://github.com/FiloSottile/mkcert for better DevEx,
+    # but fall back to using https://github.com/jsha/minica in case
+    # you don't have that installed.
+    (
+      mkcert \
+        --cert-file ./caddy.local.cetacean.club/cert.pem \
+        --key-file ./caddy.local.cetacean.club/key.pem caddy.local.cetacean.club \
+      || go tool minica -domains caddy.local.cetacean.club
+    )
+  )
+fi
+
+docker compose up --build

test/unix-socket-xff/start.sh

@@ -37,6 +37,7 @@ go run ../cmd/unixhttpd &
 go tool anubis \
   --bind=./anubis.sock \
   --bind-network=unix \
+  --policy-fname=../anubis_configs/aggressive_403.yaml \
   --target=unix://$(pwd)/unixhttpd.sock &
 
 # A simple TLS terminator that forwards to Anubis, which will forward to

test/unix-socket-xff/test.mjs

@@ -0,0 +1,30 @@
+async function testWithUserAgent(userAgent) {
+  const statusCode =
+    await fetch("https://relayd.local.cetacean.club:3004/reqmeta", {
+      headers: {
+        "User-Agent": userAgent,
+      }
+    })
+      .then(resp => resp.status);
+  return statusCode;
+}
+
+const codes = {
+  allow: await testWithUserAgent("ALLOW"),
+  challenge: await testWithUserAgent("CHALLENGE"),
+  deny: await testWithUserAgent("DENY")
+}
+
+const expected = {
+  allow: 200,
+  challenge: 401,
+  deny: 403,
+};
+
+console.log("ALLOW:    ", codes.allow);
+console.log("CHALLENGE:", codes.challenge);
+console.log("DENY:     ", codes.deny);
+
+if (JSON.stringify(codes) !== JSON.stringify(expected)) {
+  throw new Error(`wanted ${JSON.stringify(expected)}, got: ${JSON.stringify(codes)}`);
+}

web/build.sh

@@ -33,7 +33,7 @@ for the JavaScript code in this page.
 */'
 
 esbuild js/main.mjs --sourcemap --bundle --minify --outfile=static/js/main.mjs "--banner:js=${LICENSE}"
-gzip -f -k static/js/main.mjs
+gzip -f -k -n static/js/main.mjs
 zstd -f -k --ultra -22 static/js/main.mjs
 brotli -fZk static/js/main.mjs
 

web/js/main.mjs

@@ -28,6 +28,11 @@ const dependencies = [
     msg: "Your browser doesn't support web workers (Anubis uses this to avoid freezing your browser). Do you have a plugin like JShelter installed?",
     value: window.Worker,
   },
+  {
+    name: "Cookies",
+    msg: "Your browser doesn't store cookies. Anubis uses cookies to determine which clients have passed challenges by storing a signed token in a cookie. Please enable storing cookies for this domain. The names of the cookies Anubis stores may vary without notice. Cookie names and values are not part of the public API.",
+    value: navigator.cookieEnabled,
+  },
 ];
 
 function showContinueBar(hash, nonce, t0, t1) {
@@ -131,6 +136,7 @@ function showContinueBar(hash, nonce, t0, t1) {
         statusMsg: msg,
         imageSrc: imageURL("reject", anubisVersion, basePrefix),
       });
+      return;
     }
   }
 

web/static/img/ATTRIBUTIONS.txt

@@ -0,0 +1,3 @@
+These mascot images were made by CELPHASE (https://bsky.app/profile/celphase.bsky.social).
+
+These images are available under the terms of the MIT license that this repository uses.

web/static/robots.txt

@@ -1,9 +1,11 @@
 User-agent: AI2Bot
 User-agent: Ai2Bot-Dolma
+User-agent: aiHitBot
 User-agent: Amazonbot
 User-agent: anthropic-ai
 User-agent: Applebot
 User-agent: Applebot-Extended
+User-agent: Brightbot 1.0
 User-agent: Bytespider
 User-agent: CCBot
 User-agent: ChatGPT-User
@@ -11,9 +13,13 @@ User-agent: Claude-Web
 User-agent: ClaudeBot
 User-agent: cohere-ai
 User-agent: cohere-training-data-crawler
+User-agent: Cotoyogi
+User-agent: Crawlspace
 User-agent: Diffbot
 User-agent: DuckAssistBot
 User-agent: FacebookBot
+User-agent: Factset_spyderbot
+User-agent: FirecrawlAgent
 User-agent: FriendlyCrawler
 User-agent: Google-Extended
 User-agent: GoogleOther
@@ -24,19 +30,27 @@ User-agent: iaskspider/2.0
 User-agent: ICC-Crawler
 User-agent: ImagesiftBot
 User-agent: img2dataset
+User-agent: imgproxy
 User-agent: ISSCyberRiskCrawler
 User-agent: Kangaroo Bot
+User-agent: meta-externalagent
 User-agent: Meta-ExternalAgent
+User-agent: meta-externalfetcher
 User-agent: Meta-ExternalFetcher
+User-agent: NovaAct
 User-agent: OAI-SearchBot
 User-agent: omgili
 User-agent: omgilibot
+User-agent: Operator
 User-agent: PanguBot
+User-agent: Perplexity-User
 User-agent: PerplexityBot
 User-agent: PetalBot
 User-agent: Scrapy
-User-agent: SemrushBot
+User-agent: SemrushBot-OCOB
+User-agent: SemrushBot-SWA
 User-agent: Sidetrade indexer bot
+User-agent: TikTokSpider
 User-agent: Timpibot
 User-agent: VelenPublicWebCrawler
 User-agent: Webzio-Extended
@@ -44,4 +58,4 @@ User-agent: YouBot
 Disallow: /
 
 User-agent: *
-Disallow: /
+Disallow: /

xess/xess.css

@@ -3,25 +3,28 @@
   --body-preformatted-font: Iosevka Curly Iaso, monospace;
   --body-title-font: Podkova, serif;
 
-  --dark-background: #1d2021;
-  --dark-text: #f9f5d7;
-  --dark-text-selection: #d3869b;
-  --dark-preformatted-background: #3c3836;
-  --dark-link-foreground: #b16286;
-  --dark-link-background: #282828;
-  --dark-blockquote-border-left: 1px solid #bdae93;
-
-  --light-background: #f9f5d7;
-  --light-text: #1d2021;
-  --light-text-selection: #d3869b;
-  --light-preformatted-background: #ebdbb2;
-  --light-link-foreground: #b16286;
-  --light-link-background: #fbf1c7;
-  --light-blockquote-border-left: 1px solid #655c54;
+  --background: #1d2021;
+  --text: #f9f5d7;
+  --text-selection: #d3869b;
+  --preformatted-background: #3c3836;
+  --link-foreground: #b16286;
+  --link-background: #282828;
+  --blockquote-border-left: 1px solid #bdae93;
 
   --progress-bar-outline: #b16286 solid 4px;
   --progress-bar-fill: #b16286;
 }
+@media (prefers-color-scheme: light) {
+  :root {
+    --background: #f9f5d7;
+    --text: #1d2021;
+    --text-selection: #d3869b;
+    --preformatted-background: #ebdbb2;
+    --link-foreground: #b16286;
+    --link-background: #fbf1c7;
+    --blockquote-border-left: 1px solid #655c54;
+  }
+}
 
 @font-face {
   font-family: "Geist";
@@ -54,12 +57,12 @@ main {
 }
 
 ::selection {
-  background: var(--dark-text-selection);
+  background: var(--text-selection);
 }
 
 body {
-  background: var(--dark-background);
-  color: var(--dark-text);
+  background: var(--background);
+  color: var(--text);
 }
 
 body,
@@ -113,7 +116,7 @@ html {
 }
 
 pre {
-  background-color: var(--dark-preformatted-background);
+  background-color: var(--preformatted-background);
   padding: 1em;
   border: 0;
   font-family: var(--body-preformatted-font);
@@ -122,8 +125,8 @@ pre {
 a,
 a:active,
 a:visited {
-  color: var(--dark-link-foreground);
-  background-color: var(--dark-link-background);
+  color: var(--link-foreground);
+  background-color: var(--link-background);
 }
 
 h1,
@@ -136,7 +139,7 @@ h5 {
 }
 
 blockquote {
-  border-left: var(--dark-blockquote-border-left);
+  border-left: var(--blockquote-border-left);
   margin: 0.5em 10px;
   padding: 0.5em 10px;
 }
@@ -144,41 +147,3 @@ blockquote {
 footer {
   text-align: center;
 }
-
-@media (prefers-color-scheme: light) {
-  ::selection {
-    background: var(--light-text-selection);
-  }
-
-  body {
-    background: var(--light-background);
-    color: var(--light-text);
-  }
-
-  pre {
-    background-color: var(--light-preformatted-background);
-    padding: 1em;
-    border: 0;
-  }
-
-  a,
-  a:active,
-  a:visited {
-    color: var(--light-link-foreground);
-    background-color: var(--light-link-background);
-  }
-
-  h1,
-  h2,
-  h3,
-  h4,
-  h5 {
-    margin-bottom: 0.1rem;
-  }
-
-  blockquote {
-    border-left: var(--light-blockquote-border-left);
-    margin: 0.5em 10px;
-    padding: 0.5em 10px;
-  }
-}

yeetfile.js

@@ -11,17 +11,25 @@ $`npm run assets`;
         documentation: {
             "./README.md": "README.md",
             "./LICENSE": "LICENSE",
-            "./docs/docs/CHANGELOG.md": "CHANGELOG.md",
-            "./docs/docs/admin/policies.mdx": "policies.md",
-            "./docs/docs/admin/native-install.mdx": "native-install.mdx",
             "./data/botPolicies.json": "botPolicies.json",
+            "./data/botPolicies.yaml": "botPolicies.yaml",
         },
 
-        build: ({ bin, etc, systemd, out }) => {
+        build: ({ bin, etc, systemd, doc }) => {
             $`go build -o ${bin}/anubis -ldflags '-s -w -extldflags "-static" -X "github.com/TecharoHQ/anubis.Version=${git.tag()}"' ./cmd/anubis`;
 
             file.install("./run/anubis@.service", `${systemd}/anubis@.service`);
             file.install("./run/default.env", `${etc}/default.env`);
+
+            $`mkdir -p ${doc}/docs`
+            $`cp -a docs/docs ${doc}`;
+            $`find ${doc} -name _category_.json -delete`;
+            $`mkdir -p ${doc}/data`;
+            $`cp -a data/apps ${doc}/data/apps`;
+            $`cp -a data/bots ${doc}/data/bots`;
+            $`cp -a data/clients ${doc}/data/clients`;
+            $`cp -a data/common ${doc}/data/common`;
+            $`cp -a data/crawlers ${doc}/data/crawlers`;
         },
     }));
 });
@@ -29,7 +37,7 @@ $`npm run assets`;
 // NOTE(Xe): Fixes #217. This is a "half baked" tarball that includes the harder
 // parts for deterministic distros already done. Distributions like NixOS, Gentoo
 // and *BSD ports have a difficult time fitting the square peg of their dependency
-// model into the bazarr of round holes that various modern languages use. Needless
+// model into the bazaar of round holes that various modern languages use. Needless
 // to say, this makes adoption easier.
 tarball.build({
     name: "anubis-src-vendor",