fix(Dockerfile): add HEALTHCHECK

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

.air.toml

@@ -9,4 +9,4 @@ exclude_dir = ["var", "vendor", "docs", "node_modules"]
 
 [logger]
 time = true
-# to change flags at runtime, prepend with -- e.g. $ air -- --target http://localhost:3000 --difficulty 20 --use-remote-address
+# to change flags at runtime, prepend with -- e.g. $ air -- --target http://localhost:3000 --difficulty 20 --use-remote-address

.dockerignore

@@ -0,0 +1,25 @@
+.env
+*.deb
+*.rpm
+
+# Additional package locks
+pnpm-lock.yaml
+yarn.lock
+
+# Go binaries and test artifacts
+main
+*.test
+
+node_modules
+
+# MacOS
+.DS_store
+
+# Intellij
+.idea
+
+# how does this get here
+doc/VERSION
+
+web/static/js/*
+!web/static/js/.gitignore

.gitattributes

@@ -1 +1 @@
-**/*_templ.go linguist-generated=true
+web/index_templ.go linguist-generated

.github/actions/spelling/allow.txt

@@ -2,4 +2,4 @@ github
 https
 ssh
 ubuntu
-workarounds
+workarounds

.github/actions/spelling/excludes.txt

@@ -83,7 +83,6 @@
 ^\Q.github/FUNDING.yml\E$
 ^\Q.github/workflows/spelling.yml\E$
 ^data/crawlers/
-^docs/manifest/.*$
 ^docs/static/\.nojekyll$
 ignore$
 robots.txt

.github/actions/spelling/expect.txt

@@ -6,13 +6,8 @@ amazonbot
 anthro
 anubis
 anubistest
-apk
 Applebot
 archlinux
-asnc
-asnchecker
-asns
-aspirational
 badregexes
 bdba
 berr
@@ -28,7 +23,6 @@ Brightbot
 broked
 Bytespider
 cachebuster
-cachediptoasn
 Caddyfile
 caninetools
 Cardyb
@@ -36,7 +30,6 @@ celchecker
 CELPHASE
 cerr
 certresolver
-cespare
 CGNAT
 cgr
 chainguard
@@ -55,7 +48,6 @@ coreutils
 Cotoyogi
 CRDs
 crt
-Cscript
 daemonizing
 DDOS
 Debian
@@ -94,24 +86,17 @@ Fordola
 forgejo
 fsys
 fullchain
-gaissmai
 Galvus
-geoip
-geoipchecker
 gha
-gipc
 gitea
-godotenv
 goland
 gomod
 goodbot
 googlebot
 govulncheck
-goyaml
 GPG
 GPT
 gptbot
-grpcprom
 grw
 Hashcash
 hashrate
@@ -121,10 +106,8 @@ hebis
 hec
 hmc
 hostable
-htmlc
 htmx
 httpdebug
-Huawei
 hypertext
 iaskspider
 iat
@@ -132,14 +115,11 @@ ifm
 Imagesift
 imgproxy
 inp
-IPTo
-iptoasn
 iss
 isset
 ivh
 Jenomis
 JGit
-joho
 journalctl
 jshelter
 JWTs
@@ -187,6 +167,7 @@ OCOB
 ogtags
 omgili
 omgilibot
+onionservice
 openai
 openrc
 pag
@@ -214,7 +195,6 @@ qualys
 qwant
 qwantbot
 rac
-rawler
 rcvar
 redir
 redirectscheme
@@ -234,7 +214,6 @@ sebest
 secretplans
 selfsigned
 Semrush
-Seo
 setsebool
 shellcheck
 Sidetrade
@@ -255,22 +234,18 @@ subrequest
 SVCNAME
 tagline
 tarballs
-tarrif
 techaro
 techarohq
 templ
 templruntime
 testarea
-thoth
-thothmock
 Tik
 Timpibot
+torproject
 traefik
 uberspace
 unixhttpd
 unmarshal
-unparseable
-uuidgen
 uvx
 UXP
 Varis
@@ -286,7 +261,6 @@ websecure
 websites
 Webzio
 wildbase
-withthothmock
 wordpress
 Workaround
 workdir

.github/actions/spelling/patterns.txt

@@ -131,4 +131,4 @@ go install(?:\s+[a-z]+\.[-@\w/.]+)+
 
 # hit-count: 1 file-count: 1
 # microsoft
-\b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*
+\b(?:https?://|)(?:(?:(?:blogs|download\.visualstudio|docs|msdn2?|research)\.|)microsoft|blogs\.msdn)\.co(?:m|\.\w\w)/[-_a-zA-Z0-9()=./%]*

.github/workflows/docker.yml

@@ -3,8 +3,8 @@ name: Docker image builds
 on:
   workflow_dispatch:
   push:
-    branches: ["main"]
-    tags: ["v*"]
+    branches: [ "main" ]
+    tags: [ "v*" ]
 
 env:
   DOCKER_METADATA_SET_OUTPUT_ENV: "true"
@@ -55,7 +55,7 @@ jobs:
         run: |
           brew bundle
 
-      - name: Log into registry
+      - name: Log into registry 
         uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
         with:
           registry: ghcr.io
@@ -77,8 +77,9 @@ jobs:
           DOCKER_REPO: ${{ env.IMAGE }}
           SLOG_LEVEL: debug
 
+      
       - name: Generate artifact attestation
-        uses: actions/attest-build-provenance@e8998f949152b193b063cb0ec769d69d929409be # v2.4.0
+        uses: actions/attest-build-provenance@db473fddc028af60658334401dc6fa3ffd8669fd # v2.3.0
         with:
           subject-name: ${{ env.IMAGE }}
           subject-digest: ${{ steps.build.outputs.digest }}

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

@@ -1,37 +0,0 @@
-name: Regenerate ssh ci runner image
-
-on:
-  # pull_request:
-  #   branches: ["main"]
-  schedule:
-    - cron: "0 0 1,8,15,22 * *"
-  workflow_dispatch:
-
-permissions:
-  pull-requests: write
-  contents: write
-  packages: write
-
-jobs:
-  ssh-ci-rebuild:
-    if: github.repository == 'TecharoHQ/anubis'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-        with:
-          fetch-tags: true
-          fetch-depth: 0
-          persist-credentials: false
-      - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
-      - name: Build and push
-        run: |
-          cd ./test/ssh-ci
-          docker buildx bake --push

.github/workflows/ssh-ci.yml

@@ -1,37 +0,0 @@
-name: SSH CI
-
-on:
-  push:
-    branches: ["main"]
-  # pull_request:
-  #   branches: ["main"]
-
-permissions:
-  contents: read
-
-jobs:
-  ssh:
-    if: github.repository == 'TecharoHQ/anubis'
-    runs-on: ubuntu-24.04
-    strategy:
-      matrix:
-        host:
-          - ubuntu@riscv64.techaro.lol
-          - ci@ppc64le.techaro.lol
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
-        with:
-          fetch-tags: true
-          fetch-depth: 0
-          persist-credentials: false
-      - name: Install CI target SSH key
-        uses: shimataro/ssh-key-action@d4fffb50872869abe2d9a9098a6d9c5aa7d16be4 # v2.7.0
-        with:
-          key: ${{ secrets.CI_SSH_KEY }}
-          name: id_rsa
-          known_hosts: ${{ secrets.CI_SSH_KNOWN_HOSTS }}
-      - name: Run CI
-        run: bash test/ssh-ci/rigging.sh ${{ matrix.host }}
-        env:
-          GITHUB_RUN_ID: ${{ github.run_id }}

.github/workflows/zizmor.yml

@@ -29,7 +29,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} 
 
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@ce28f5bb42b7a9f2c824e633a3f6ee835bab6858 # v3.29.0
+        uses: github/codeql-action/upload-sarif@fca7ace96b7d713c7035871441bd52efbe39e27e # v3.28.19
         with:
           sarif_file: results.sarif
           category: zizmor

.vscode/settings.json

@@ -11,24 +11,5 @@
     "zig": false,
     "javascript": false,
     "properties": false
-  },
-  "[markdown]": {
-    "editor.wordWrap": "wordWrapColumn",
-    "editor.wordWrapColumn": 80,
-    "editor.wordBasedSuggestions": "off"
-  },
-  "[mdx]": {
-    "editor.wordWrap": "wordWrapColumn",
-    "editor.wordWrapColumn": 80,
-    "editor.wordBasedSuggestions": "off"
-  },
-  "[nunjucks]": {
-    "editor.wordWrap": "wordWrapColumn",
-    "editor.wordWrapColumn": 80,
-    "editor.wordBasedSuggestions": "off"
-  },
-  "cSpell.enabledFileTypes": {
-    "mdx": true,
-    "md": true
   }
 }

Dockerfile

@@ -0,0 +1,30 @@
+ARG ALPINE_VERSION=edge
+FROM --platform=${BUILDPLATFORM} alpine:${ALPINE_VERSION} AS build
+
+ARG TARGETOS
+ARG TARGETARCH
+ARG COMPONENT=anubis
+ARG VERSION=devel-docker
+
+RUN apk -U add go nodejs git build-base git npm bash zstd brotli gzip
+
+WORKDIR /app
+
+COPY go.mod go.sum ./
+RUN go mod download
+
+COPY . .
+RUN --mount=type=cache,target=/root/.cache npm ci && npm run assets
+RUN --mount=type=cache,target=/root/.cache GOOS=${TARGETOS} GOARCH=${TARGETARCH} CGO_ENABLED=0 GOARM=7 go build -gcflags "all=-N -l" -o /app/bin/${COMPONENT} -ldflags "-s -w -extldflags -static -X github.com/TecharoHQ/anubis.Version=${VERSION}" ./cmd/${COMPONENT}
+
+FROM alpine:${ALPINE_VERSION} AS run
+WORKDIR /app
+
+RUN apk -U add ca-certificates mailcap
+
+COPY --from=build /app/bin/anubis /app/bin/anubis
+
+CMD ["/app/bin/anubis"]
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 CMD [ "/app/bin/anubis", "--healthcheck" ]
+
+LABEL org.opencontainers.image.source="https://github.com/TecharoHQ/anubis"

cmd/anubis/main.go

@@ -30,13 +30,11 @@ import (
 	"github.com/TecharoHQ/anubis"
 	"github.com/TecharoHQ/anubis/data"
 	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/internal/thoth"
 	libanubis "github.com/TecharoHQ/anubis/lib"
 	botPolicy "github.com/TecharoHQ/anubis/lib/policy"
 	"github.com/TecharoHQ/anubis/lib/policy/config"
 	"github.com/TecharoHQ/anubis/web"
 	"github.com/facebookgo/flagenv"
-	_ "github.com/joho/godotenv/autoload"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 )
 
@@ -57,7 +55,6 @@ var (
 	policyFname              = flag.String("policy-fname", "", "full path to anubis policy document (defaults to a sensible built-in policy)")
 	redirectDomains          = flag.String("redirect-domains", "", "list of domains separated by commas which anubis is allowed to redirect to. Leaving this unset allows any domain.")
 	slogLevel                = flag.String("slog-level", "INFO", "logging level (see https://pkg.go.dev/log/slog#hdr-Levels)")
-	stripBasePrefix          = flag.Bool("strip-base-prefix", false, "if true, strips the base prefix from requests forwarded to the target server")
 	target                   = flag.String("target", "http://localhost:3923", "target to reverse proxy to, set to an empty string to disable proxying when only using auth request")
 	targetSNI                = flag.String("target-sni", "", "if set, the value of the TLS handshake hostname when forwarding requests to the target")
 	targetHost               = flag.String("target-host", "", "if set, the value of the Host header when forwarding requests to the target")
@@ -72,10 +69,6 @@ var (
 	webmasterEmail           = flag.String("webmaster-email", "", "if set, displays webmaster's email on the reject page for appeals")
 	versionFlag              = flag.Bool("version", false, "print Anubis version")
 	xffStripPrivate          = flag.Bool("xff-strip-private", true, "if set, strip private addresses from X-Forwarded-For")
-
-	thothInsecure = flag.Bool("thoth-insecure", false, "if set, connect to Thoth over plain HTTP/2, don't enable this unless support told you to")
-	thothURL      = flag.String("thoth-url", "", "if set, URL for Thoth, the IP reputation database for Anubis")
-	thothToken    = flag.String("thoth-token", "", "if set, API token for Thoth, the IP reputation database for Anubis")
 )
 
 func keyFromHex(value string) (ed25519.PrivateKey, error) {
@@ -239,25 +232,7 @@ func main() {
 		}
 	}
 
-	ctx := context.Background()
-
-	// Thoth configuration
-	switch {
-	case *thothURL != "" && *thothToken == "":
-		slog.Warn("THOTH_URL is set but no THOTH_TOKEN is set")
-	case *thothURL == "" && *thothToken != "":
-		slog.Warn("THOTH_TOKEN is set but no THOTH_URL is set")
-	case *thothURL != "" && *thothToken != "":
-		slog.Debug("connecting to Thoth")
-		thothClient, err := thoth.New(ctx, *thothURL, *thothToken, *thothInsecure)
-		if err != nil {
-			log.Fatalf("can't dial thoth at %s: %v", *thothURL, err)
-		}
-
-		ctx = thoth.With(ctx, thothClient)
-	}
-
-	policy, err := libanubis.LoadPoliciesOrDefault(ctx, *policyFname, *challengeDifficulty)
+	policy, err := libanubis.LoadPoliciesOrDefault(*policyFname, *challengeDifficulty)
 	if err != nil {
 		log.Fatalf("can't parse policy file: %v", err)
 	}
@@ -285,10 +260,6 @@ func main() {
 	} else if strings.HasSuffix(*basePrefix, "/") {
 		log.Fatalf("[misconfiguration] base-prefix must not end with a slash")
 	}
-	if *stripBasePrefix && *basePrefix == "" {
-		log.Fatalf("[misconfiguration] strip-base-prefix is set to true, but base-prefix is not set, " +
-			"this may result in unexpected behavior")
-	}
 
 	var priv ed25519.PrivateKey
 	if *ed25519PrivateKeyHex != "" && *ed25519PrivateKeyHexFile != "" {
@@ -333,7 +304,6 @@ func main() {
 
 	s, err := libanubis.New(libanubis.Options{
 		BasePrefix:           *basePrefix,
-		StripBasePrefix:      *stripBasePrefix,
 		Next:                 rp,
 		Policy:               policy,
 		ServeRobotsTXT:       *robotsTxt,

cmd/robots2policy/batch/batch_process.go

@@ -1,78 +0,0 @@
-/*
-Batch process robots.txt files from archives like https://github.com/nrjones8/robots-dot-txt-archive-bot/tree/master/data/cleaned
-into Anubis CEL policies. Usage: go run batch_process.go <directory with robots.txt files>
-*/
-package main
-
-import (
-	"fmt"
-	"io/fs"
-	"log"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-)
-
-func main() {
-	if len(os.Args) < 2 {
-		fmt.Println("Usage: go run batch_process.go <cleaned_directory>")
-		fmt.Println("Example: go run batch_process.go ./cleaned")
-		os.Exit(1)
-	}
-
-	cleanedDir := os.Args[1]
-	outputDir := "generated_policies"
-
-	// Create output directory
-	if err := os.MkdirAll(outputDir, 0755); err != nil {
-		log.Fatalf("Failed to create output directory: %v", err)
-	}
-
-	count := 0
-	err := filepath.WalkDir(cleanedDir, func(path string, d fs.DirEntry, err error) error {
-		if err != nil {
-			return err
-		}
-
-		// Skip directories
-		if d.IsDir() {
-			return nil
-		}
-
-		// Generate policy name from file path
-		relPath, _ := filepath.Rel(cleanedDir, path)
-		policyName := strings.ReplaceAll(relPath, "/", "-")
-		policyName = strings.TrimSuffix(policyName, "-robots.txt")
-		policyName = strings.ReplaceAll(policyName, ".", "-")
-
-		outputFile := filepath.Join(outputDir, policyName+".yaml")
-
-		cmd := exec.Command("go", "run", "main.go",
-			"-input", path,
-			"-output", outputFile,
-			"-name", policyName,
-			"-format", "yaml")
-
-		if err := cmd.Run(); err != nil {
-			fmt.Printf("Warning: Failed to process %s: %v\n", path, err)
-			return nil // Continue processing other files
-		}
-
-		count++
-		if count%100 == 0 {
-			fmt.Printf("Processed %d files...\n", count)
-		} else if count%10 == 0 {
-			fmt.Print(".")
-		}
-
-		return nil
-	})
-
-	if err != nil {
-		log.Fatalf("Error walking directory: %v", err)
-	}
-
-	fmt.Printf("Successfully processed %d robots.txt files\n", count)
-	fmt.Printf("Generated policies saved to: %s/\n", outputDir)
-}

cmd/robots2policy/main.go

@@ -1,313 +0,0 @@
-package main
-
-import (
-	"bufio"
-	"encoding/json"
-	"flag"
-	"fmt"
-	"io"
-	"log"
-	"net/http"
-	"os"
-	"regexp"
-	"strings"
-
-	"github.com/TecharoHQ/anubis/lib/policy/config"
-
-	"sigs.k8s.io/yaml"
-)
-
-var (
-	inputFile     = flag.String("input", "", "path to robots.txt file (use - for stdin)")
-	outputFile    = flag.String("output", "", "output file path (use - for stdout, defaults to stdout)")
-	outputFormat  = flag.String("format", "yaml", "output format: yaml or json")
-	baseAction    = flag.String("action", "CHALLENGE", "default action for disallowed paths: ALLOW, DENY, CHALLENGE, WEIGH")
-	crawlDelay    = flag.Int("crawl-delay-weight", 0, "if > 0, add weight adjustment for crawl-delay (difficulty adjustment)")
-	policyName    = flag.String("name", "robots-txt-policy", "name for the generated policy")
-	userAgentDeny = flag.String("deny-user-agents", "DENY", "action for specifically blocked user agents: DENY, CHALLENGE")
-	helpFlag      = flag.Bool("help", false, "show help")
-)
-
-type RobotsRule struct {
-	UserAgent   string
-	Disallows   []string
-	Allows      []string
-	CrawlDelay  int
-	IsBlacklist bool // true if this is a specifically denied user agent
-}
-
-type AnubisRule struct {
-	Expression *config.ExpressionOrList `yaml:"expression,omitempty" json:"expression,omitempty"`
-	Challenge  *config.ChallengeRules   `yaml:"challenge,omitempty" json:"challenge,omitempty"`
-	Weight     *config.Weight           `yaml:"weight,omitempty" json:"weight,omitempty"`
-	Name       string                   `yaml:"name" json:"name"`
-	Action     string                   `yaml:"action" json:"action"`
-}
-
-func init() {
-	flag.Usage = func() {
-		fmt.Fprintf(os.Stderr, "Usage of %s:\n", os.Args[0])
-		fmt.Fprintf(os.Stderr, "%s [options] -input <robots.txt>\n\n", os.Args[0])
-		flag.PrintDefaults()
-		fmt.Fprintln(os.Stderr, "\nExamples:")
-		fmt.Fprintln(os.Stderr, "  # Convert local robots.txt file")
-		fmt.Fprintln(os.Stderr, "  robots2policy -input robots.txt -output policy.yaml")
-		fmt.Fprintln(os.Stderr, "")
-		fmt.Fprintln(os.Stderr, "  # Convert from URL")
-		fmt.Fprintln(os.Stderr, "  robots2policy -input https://example.com/robots.txt -format json")
-		fmt.Fprintln(os.Stderr, "")
-		fmt.Fprintln(os.Stderr, "  # Read from stdin, write to stdout")
-		fmt.Fprintln(os.Stderr, "  curl https://example.com/robots.txt | robots2policy -input -")
-		os.Exit(2)
-	}
-}
-
-func main() {
-	flag.Parse()
-
-	if len(flag.Args()) > 0 || *helpFlag || *inputFile == "" {
-		flag.Usage()
-	}
-
-	// Read robots.txt
-	var input io.Reader
-	if *inputFile == "-" {
-		input = os.Stdin
-	} else if strings.HasPrefix(*inputFile, "http://") || strings.HasPrefix(*inputFile, "https://") {
-		resp, err := http.Get(*inputFile)
-		if err != nil {
-			log.Fatalf("failed to fetch robots.txt from URL: %v", err)
-		}
-		defer resp.Body.Close()
-		input = resp.Body
-	} else {
-		file, err := os.Open(*inputFile)
-		if err != nil {
-			log.Fatalf("failed to open input file: %v", err)
-		}
-		defer file.Close()
-		input = file
-	}
-
-	// Parse robots.txt
-	rules, err := parseRobotsTxt(input)
-	if err != nil {
-		log.Fatalf("failed to parse robots.txt: %v", err)
-	}
-
-	// Convert to Anubis rules
-	anubisRules := convertToAnubisRules(rules)
-
-	// Check if any rules were generated
-	if len(anubisRules) == 0 {
-		log.Fatal("no valid rules generated from robots.txt - file may be empty or contain no disallow directives")
-	}
-
-	// Generate output
-	var output []byte
-	switch strings.ToLower(*outputFormat) {
-	case "yaml":
-		output, err = yaml.Marshal(anubisRules)
-	case "json":
-		output, err = json.MarshalIndent(anubisRules, "", "  ")
-	default:
-		log.Fatalf("unsupported output format: %s (use yaml or json)", *outputFormat)
-	}
-
-	if err != nil {
-		log.Fatalf("failed to marshal output: %v", err)
-	}
-
-	// Write output
-	if *outputFile == "" || *outputFile == "-" {
-		fmt.Print(string(output))
-	} else {
-		err = os.WriteFile(*outputFile, output, 0644)
-		if err != nil {
-			log.Fatalf("failed to write output file: %v", err)
-		}
-		fmt.Printf("Generated Anubis policy written to %s\n", *outputFile)
-	}
-}
-
-func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
-	scanner := bufio.NewScanner(input)
-	var rules []RobotsRule
-	var currentRule *RobotsRule
-
-	for scanner.Scan() {
-		line := strings.TrimSpace(scanner.Text())
-
-		// Skip empty lines and comments
-		if line == "" || strings.HasPrefix(line, "#") {
-			continue
-		}
-
-		// Split on first colon
-		parts := strings.SplitN(line, ":", 2)
-		if len(parts) != 2 {
-			continue
-		}
-
-		directive := strings.TrimSpace(strings.ToLower(parts[0]))
-		value := strings.TrimSpace(parts[1])
-
-		switch directive {
-		case "user-agent":
-			// Start a new rule section
-			if currentRule != nil {
-				rules = append(rules, *currentRule)
-			}
-			currentRule = &RobotsRule{
-				UserAgent: value,
-				Disallows: make([]string, 0),
-				Allows:    make([]string, 0),
-			}
-
-		case "disallow":
-			if currentRule != nil && value != "" {
-				currentRule.Disallows = append(currentRule.Disallows, value)
-			}
-
-		case "allow":
-			if currentRule != nil && value != "" {
-				currentRule.Allows = append(currentRule.Allows, value)
-			}
-
-		case "crawl-delay":
-			if currentRule != nil {
-				if delay, err := parseIntSafe(value); err == nil {
-					currentRule.CrawlDelay = delay
-				}
-			}
-		}
-	}
-
-	// Don't forget the last rule
-	if currentRule != nil {
-		rules = append(rules, *currentRule)
-	}
-
-	// Mark blacklisted user agents (those with "Disallow: /")
-	for i := range rules {
-		for _, disallow := range rules[i].Disallows {
-			if disallow == "/" {
-				rules[i].IsBlacklist = true
-				break
-			}
-		}
-	}
-
-	return rules, scanner.Err()
-}
-
-func parseIntSafe(s string) (int, error) {
-	var result int
-	_, err := fmt.Sscanf(s, "%d", &result)
-	return result, err
-}
-
-func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
-	var anubisRules []AnubisRule
-	ruleCounter := 0
-
-	for _, robotsRule := range robotsRules {
-		userAgent := robotsRule.UserAgent
-
-		// Handle crawl delay as weight adjustment (do this first before any continues)
-		if robotsRule.CrawlDelay > 0 && *crawlDelay > 0 {
-			ruleCounter++
-			rule := AnubisRule{
-				Name:   fmt.Sprintf("%s-crawl-delay-%d", *policyName, ruleCounter),
-				Action: "WEIGH",
-				Weight: &config.Weight{Adjust: *crawlDelay},
-			}
-
-			if userAgent == "*" {
-				rule.Expression = &config.ExpressionOrList{
-					All: []string{"true"}, // Always applies
-				}
-			} else {
-				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
-				}
-			}
-
-			anubisRules = append(anubisRules, rule)
-		}
-
-		// Handle blacklisted user agents (complete deny/challenge)
-		if robotsRule.IsBlacklist {
-			ruleCounter++
-			rule := AnubisRule{
-				Name:   fmt.Sprintf("%s-blacklist-%d", *policyName, ruleCounter),
-				Action: *userAgentDeny,
-			}
-
-			if userAgent == "*" {
-				// This would block everything - convert to a weight adjustment instead
-				rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
-				rule.Action = "WEIGH"
-				rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
-				rule.Expression = &config.ExpressionOrList{
-					All: []string{"true"}, // Always applies
-				}
-			} else {
-				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
-				}
-			}
-			anubisRules = append(anubisRules, rule)
-			continue
-		}
-
-		// Handle specific disallow rules
-		for _, disallow := range robotsRule.Disallows {
-			if disallow == "/" {
-				continue // Already handled as blacklist above
-			}
-
-			ruleCounter++
-			rule := AnubisRule{
-				Name:   fmt.Sprintf("%s-disallow-%d", *policyName, ruleCounter),
-				Action: *baseAction,
-			}
-
-			// Build CEL expression
-			var conditions []string
-
-			// Add user agent condition if not wildcard
-			if userAgent != "*" {
-				conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgent))
-			}
-
-			// Add path condition
-			pathCondition := buildPathCondition(disallow)
-			conditions = append(conditions, pathCondition)
-
-			rule.Expression = &config.ExpressionOrList{
-				All: conditions,
-			}
-
-			anubisRules = append(anubisRules, rule)
-		}
-
-	}
-
-	return anubisRules
-}
-
-func buildPathCondition(robotsPath string) string {
-	// Handle wildcards in robots.txt paths
-	if strings.Contains(robotsPath, "*") || strings.Contains(robotsPath, "?") {
-		// Convert robots.txt wildcards to regex
-		regex := regexp.QuoteMeta(robotsPath)
-		regex = strings.ReplaceAll(regex, `\*`, `.*`) // * becomes .*
-		regex = strings.ReplaceAll(regex, `\?`, `.`)  // ? becomes .
-		regex = "^" + regex
-		return fmt.Sprintf("path.matches(%q)", regex)
-	}
-
-	// Simple prefix match for most cases
-	return fmt.Sprintf("path.startsWith(%q)", robotsPath)
-}

cmd/robots2policy/robots2policy_test.go

@@ -1,418 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-	"reflect"
-	"strings"
-	"testing"
-
-	"gopkg.in/yaml.v3"
-)
-
-type TestCase struct {
-	name         string
-	robotsFile   string
-	expectedFile string
-	options      TestOptions
-}
-
-type TestOptions struct {
-	format           string
-	action           string
-	crawlDelayWeight int
-	policyName       string
-	deniedAction     string
-}
-
-func TestDataFileConversion(t *testing.T) {
-
-	testCases := []TestCase{
-		{
-			name:         "simple_default",
-			robotsFile:   "simple.robots.txt",
-			expectedFile: "simple.yaml",
-			options:      TestOptions{format: "yaml"},
-		},
-		{
-			name:         "simple_json",
-			robotsFile:   "simple.robots.txt",
-			expectedFile: "simple.json",
-			options:      TestOptions{format: "json"},
-		},
-		{
-			name:         "simple_deny_action",
-			robotsFile:   "simple.robots.txt",
-			expectedFile: "deny-action.yaml",
-			options:      TestOptions{format: "yaml", action: "DENY"},
-		},
-		{
-			name:         "simple_custom_name",
-			robotsFile:   "simple.robots.txt",
-			expectedFile: "custom-name.yaml",
-			options:      TestOptions{format: "yaml", policyName: "my-custom-policy"},
-		},
-		{
-			name:         "blacklist_with_crawl_delay",
-			robotsFile:   "blacklist.robots.txt",
-			expectedFile: "blacklist.yaml",
-			options:      TestOptions{format: "yaml", crawlDelayWeight: 3},
-		},
-		{
-			name:         "wildcards",
-			robotsFile:   "wildcards.robots.txt",
-			expectedFile: "wildcards.yaml",
-			options:      TestOptions{format: "yaml"},
-		},
-		{
-			name:         "empty_file",
-			robotsFile:   "empty.robots.txt",
-			expectedFile: "empty.yaml",
-			options:      TestOptions{format: "yaml"},
-		},
-		{
-			name:         "complex_scenario",
-			robotsFile:   "complex.robots.txt",
-			expectedFile: "complex.yaml",
-			options:      TestOptions{format: "yaml", crawlDelayWeight: 5},
-		},
-	}
-
-	for _, tc := range testCases {
-		t.Run(tc.name, func(t *testing.T) {
-			robotsPath := filepath.Join("testdata", tc.robotsFile)
-			expectedPath := filepath.Join("testdata", tc.expectedFile)
-
-			// Read robots.txt input
-			robotsFile, err := os.Open(robotsPath)
-			if err != nil {
-				t.Fatalf("Failed to open robots file %s: %v", robotsPath, err)
-			}
-			defer robotsFile.Close()
-
-			// Parse robots.txt
-			rules, err := parseRobotsTxt(robotsFile)
-			if err != nil {
-				t.Fatalf("Failed to parse robots.txt: %v", err)
-			}
-
-			// Set test options
-			oldFormat := *outputFormat
-			oldAction := *baseAction
-			oldCrawlDelay := *crawlDelay
-			oldPolicyName := *policyName
-			oldDeniedAction := *userAgentDeny
-
-			if tc.options.format != "" {
-				*outputFormat = tc.options.format
-			}
-			if tc.options.action != "" {
-				*baseAction = tc.options.action
-			}
-			if tc.options.crawlDelayWeight > 0 {
-				*crawlDelay = tc.options.crawlDelayWeight
-			}
-			if tc.options.policyName != "" {
-				*policyName = tc.options.policyName
-			}
-			if tc.options.deniedAction != "" {
-				*userAgentDeny = tc.options.deniedAction
-			}
-
-			// Restore options after test
-			defer func() {
-				*outputFormat = oldFormat
-				*baseAction = oldAction
-				*crawlDelay = oldCrawlDelay
-				*policyName = oldPolicyName
-				*userAgentDeny = oldDeniedAction
-			}()
-
-			// Convert to Anubis rules
-			anubisRules := convertToAnubisRules(rules)
-
-			// Generate output
-			var actualOutput []byte
-			switch strings.ToLower(*outputFormat) {
-			case "yaml":
-				actualOutput, err = yaml.Marshal(anubisRules)
-			case "json":
-				actualOutput, err = json.MarshalIndent(anubisRules, "", "  ")
-			}
-			if err != nil {
-				t.Fatalf("Failed to marshal output: %v", err)
-			}
-
-			// Read expected output
-			expectedOutput, err := os.ReadFile(expectedPath)
-			if err != nil {
-				t.Fatalf("Failed to read expected file %s: %v", expectedPath, err)
-			}
-
-			if strings.ToLower(*outputFormat) == "yaml" {
-				var actualData []interface{}
-				var expectedData []interface{}
-
-				err = yaml.Unmarshal(actualOutput, &actualData)
-				if err != nil {
-					t.Fatalf("Failed to unmarshal actual output: %v", err)
-				}
-
-				err = yaml.Unmarshal(expectedOutput, &expectedData)
-				if err != nil {
-					t.Fatalf("Failed to unmarshal expected output: %v", err)
-				}
-
-				// Compare data structures
-				if !compareData(actualData, expectedData) {
-					actualStr := strings.TrimSpace(string(actualOutput))
-					expectedStr := strings.TrimSpace(string(expectedOutput))
-					t.Errorf("Output mismatch for %s\nExpected:\n%s\n\nActual:\n%s", tc.name, expectedStr, actualStr)
-				}
-			} else {
-				var actualData []interface{}
-				var expectedData []interface{}
-
-				err = json.Unmarshal(actualOutput, &actualData)
-				if err != nil {
-					t.Fatalf("Failed to unmarshal actual JSON output: %v", err)
-				}
-
-				err = json.Unmarshal(expectedOutput, &expectedData)
-				if err != nil {
-					t.Fatalf("Failed to unmarshal expected JSON output: %v", err)
-				}
-
-				// Compare data structures
-				if !compareData(actualData, expectedData) {
-					actualStr := strings.TrimSpace(string(actualOutput))
-					expectedStr := strings.TrimSpace(string(expectedOutput))
-					t.Errorf("Output mismatch for %s\nExpected:\n%s\n\nActual:\n%s", tc.name, expectedStr, actualStr)
-				}
-			}
-		})
-	}
-}
-
-func TestCaseInsensitiveParsing(t *testing.T) {
-	robotsTxt := `User-Agent: *
-Disallow: /admin
-Crawl-Delay: 10
-
-User-agent: TestBot
-disallow: /test
-crawl-delay: 5
-
-USER-AGENT: UpperBot
-DISALLOW: /upper
-CRAWL-DELAY: 20`
-
-	reader := strings.NewReader(robotsTxt)
-	rules, err := parseRobotsTxt(reader)
-	if err != nil {
-		t.Fatalf("Failed to parse case-insensitive robots.txt: %v", err)
-	}
-
-	expectedRules := 3
-	if len(rules) != expectedRules {
-		t.Errorf("Expected %d rules, got %d", expectedRules, len(rules))
-	}
-
-	// Check that all crawl delays were parsed
-	for i, rule := range rules {
-		expectedDelays := []int{10, 5, 20}
-		if rule.CrawlDelay != expectedDelays[i] {
-			t.Errorf("Rule %d: expected crawl delay %d, got %d", i, expectedDelays[i], rule.CrawlDelay)
-		}
-	}
-}
-
-func TestVariousOutputFormats(t *testing.T) {
-	robotsTxt := `User-agent: *
-Disallow: /admin`
-
-	reader := strings.NewReader(robotsTxt)
-	rules, err := parseRobotsTxt(reader)
-	if err != nil {
-		t.Fatalf("Failed to parse robots.txt: %v", err)
-	}
-
-	oldPolicyName := *policyName
-	*policyName = "test-policy"
-	defer func() { *policyName = oldPolicyName }()
-
-	anubisRules := convertToAnubisRules(rules)
-
-	// Test YAML output
-	yamlOutput, err := yaml.Marshal(anubisRules)
-	if err != nil {
-		t.Fatalf("Failed to marshal YAML: %v", err)
-	}
-
-	if !strings.Contains(string(yamlOutput), "name: test-policy-disallow-1") {
-		t.Errorf("YAML output doesn't contain expected rule name")
-	}
-
-	// Test JSON output
-	jsonOutput, err := json.MarshalIndent(anubisRules, "", "  ")
-	if err != nil {
-		t.Fatalf("Failed to marshal JSON: %v", err)
-	}
-
-	if !strings.Contains(string(jsonOutput), `"name": "test-policy-disallow-1"`) {
-		t.Errorf("JSON output doesn't contain expected rule name")
-	}
-}
-
-func TestDifferentActions(t *testing.T) {
-	robotsTxt := `User-agent: *
-Disallow: /admin`
-
-	testActions := []string{"ALLOW", "DENY", "CHALLENGE", "WEIGH"}
-
-	for _, action := range testActions {
-		t.Run("action_"+action, func(t *testing.T) {
-			reader := strings.NewReader(robotsTxt)
-			rules, err := parseRobotsTxt(reader)
-			if err != nil {
-				t.Fatalf("Failed to parse robots.txt: %v", err)
-			}
-
-			oldAction := *baseAction
-			*baseAction = action
-			defer func() { *baseAction = oldAction }()
-
-			anubisRules := convertToAnubisRules(rules)
-
-			if len(anubisRules) != 1 {
-				t.Fatalf("Expected 1 rule, got %d", len(anubisRules))
-			}
-
-			if anubisRules[0].Action != action {
-				t.Errorf("Expected action %s, got %s", action, anubisRules[0].Action)
-			}
-		})
-	}
-}
-
-func TestPolicyNaming(t *testing.T) {
-	robotsTxt := `User-agent: *
-Disallow: /admin
-Disallow: /private
-
-User-agent: BadBot
-Disallow: /`
-
-	testNames := []string{"custom-policy", "my-rules", "site-protection"}
-
-	for _, name := range testNames {
-		t.Run("name_"+name, func(t *testing.T) {
-			reader := strings.NewReader(robotsTxt)
-			rules, err := parseRobotsTxt(reader)
-			if err != nil {
-				t.Fatalf("Failed to parse robots.txt: %v", err)
-			}
-
-			oldName := *policyName
-			*policyName = name
-			defer func() { *policyName = oldName }()
-
-			anubisRules := convertToAnubisRules(rules)
-
-			// Check that all rule names use the custom prefix
-			for _, rule := range anubisRules {
-				if !strings.HasPrefix(rule.Name, name+"-") {
-					t.Errorf("Rule name %s doesn't start with expected prefix %s-", rule.Name, name)
-				}
-			}
-		})
-	}
-}
-
-func TestCrawlDelayWeights(t *testing.T) {
-	robotsTxt := `User-agent: *
-Disallow: /admin
-Crawl-delay: 10
-
-User-agent: SlowBot
-Disallow: /slow
-Crawl-delay: 60`
-
-	testWeights := []int{1, 5, 10, 25}
-
-	for _, weight := range testWeights {
-		t.Run(fmt.Sprintf("weight_%d", weight), func(t *testing.T) {
-			reader := strings.NewReader(robotsTxt)
-			rules, err := parseRobotsTxt(reader)
-			if err != nil {
-				t.Fatalf("Failed to parse robots.txt: %v", err)
-			}
-
-			oldWeight := *crawlDelay
-			*crawlDelay = weight
-			defer func() { *crawlDelay = oldWeight }()
-
-			anubisRules := convertToAnubisRules(rules)
-
-			// Count weight rules and verify they have correct weight
-			weightRules := 0
-			for _, rule := range anubisRules {
-				if rule.Action == "WEIGH" && rule.Weight != nil {
-					weightRules++
-					if rule.Weight.Adjust != weight {
-						t.Errorf("Expected weight %d, got %d", weight, rule.Weight.Adjust)
-					}
-				}
-			}
-
-			expectedWeightRules := 2 // One for *, one for SlowBot
-			if weightRules != expectedWeightRules {
-				t.Errorf("Expected %d weight rules, got %d", expectedWeightRules, weightRules)
-			}
-		})
-	}
-}
-
-func TestBlacklistActions(t *testing.T) {
-	robotsTxt := `User-agent: BadBot
-Disallow: /
-
-User-agent: SpamBot
-Disallow: /`
-
-	testActions := []string{"DENY", "CHALLENGE"}
-
-	for _, action := range testActions {
-		t.Run("blacklist_"+action, func(t *testing.T) {
-			reader := strings.NewReader(robotsTxt)
-			rules, err := parseRobotsTxt(reader)
-			if err != nil {
-				t.Fatalf("Failed to parse robots.txt: %v", err)
-			}
-
-			oldAction := *userAgentDeny
-			*userAgentDeny = action
-			defer func() { *userAgentDeny = oldAction }()
-
-			anubisRules := convertToAnubisRules(rules)
-
-			// All rules should be blacklist rules with the specified action
-			for _, rule := range anubisRules {
-				if !strings.Contains(rule.Name, "blacklist") {
-					t.Errorf("Expected blacklist rule, got %s", rule.Name)
-				}
-				if rule.Action != action {
-					t.Errorf("Expected action %s, got %s", action, rule.Action)
-				}
-			}
-		})
-	}
-}
-
-// compareData performs a deep comparison of two data structures,
-// ignoring differences that are semantically equivalent in YAML/JSON
-func compareData(actual, expected interface{}) bool {
-	return reflect.DeepEqual(actual, expected)
-}

cmd/robots2policy/testdata/blacklist.robots.txt

@@ -1,15 +0,0 @@
-# Test with blacklisted user agents
-User-agent: *
-Disallow: /admin
-Crawl-delay: 10
-
-User-agent: BadBot
-Disallow: /
-
-User-agent: SpamBot
-Disallow: /
-Crawl-delay: 60
-
-User-agent: Googlebot
-Disallow: /search
-Crawl-delay: 5

cmd/robots2policy/testdata/blacklist.yaml

@@ -1,30 +0,0 @@
-- action: WEIGH
-  expression: "true"
-  name: robots-txt-policy-crawl-delay-1
-  weight:
-    adjust: 3
-- action: CHALLENGE
-  expression: path.startsWith("/admin")
-  name: robots-txt-policy-disallow-2
-- action: DENY
-  expression: userAgent.contains("BadBot")
-  name: robots-txt-policy-blacklist-3
-- action: WEIGH
-  expression: userAgent.contains("SpamBot")
-  name: robots-txt-policy-crawl-delay-4
-  weight:
-    adjust: 3
-- action: DENY
-  expression: userAgent.contains("SpamBot")
-  name: robots-txt-policy-blacklist-5
-- action: WEIGH
-  expression: userAgent.contains("Googlebot")
-  name: robots-txt-policy-crawl-delay-6
-  weight:
-    adjust: 3
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("Googlebot")
-        - path.startsWith("/search")
-  name: robots-txt-policy-disallow-7

cmd/robots2policy/testdata/complex.robots.txt

@@ -1,30 +0,0 @@
-# Complex real-world example
-User-agent: *
-Disallow: /admin/
-Disallow: /private/
-Disallow: /api/internal/
-Allow: /api/public/
-Crawl-delay: 5
-
-User-agent: Googlebot
-Disallow: /search/
-Allow: /api/
-Crawl-delay: 2
-
-User-agent: Bingbot
-Disallow: /search/
-Disallow: /admin/
-Crawl-delay: 10
-
-User-agent: BadBot
-Disallow: /
-
-User-agent: SeoBot
-Disallow: /
-Crawl-delay: 300
-
-# Test with various patterns
-User-agent: TestBot
-Disallow: /*/admin
-Disallow: /temp*.html
-Disallow: /file?.log

cmd/robots2policy/testdata/complex.yaml

@@ -1,71 +0,0 @@
-- action: WEIGH
-  expression: "true"
-  name: robots-txt-policy-crawl-delay-1
-  weight:
-    adjust: 5
-- action: CHALLENGE
-  expression: path.startsWith("/admin/")
-  name: robots-txt-policy-disallow-2
-- action: CHALLENGE
-  expression: path.startsWith("/private/")
-  name: robots-txt-policy-disallow-3
-- action: CHALLENGE
-  expression: path.startsWith("/api/internal/")
-  name: robots-txt-policy-disallow-4
-- action: WEIGH
-  expression: userAgent.contains("Googlebot")
-  name: robots-txt-policy-crawl-delay-5
-  weight:
-    adjust: 5
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("Googlebot")
-        - path.startsWith("/search/")
-  name: robots-txt-policy-disallow-6
-- action: WEIGH
-  expression: userAgent.contains("Bingbot")
-  name: robots-txt-policy-crawl-delay-7
-  weight:
-    adjust: 5
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("Bingbot")
-        - path.startsWith("/search/")
-  name: robots-txt-policy-disallow-8
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("Bingbot")
-        - path.startsWith("/admin/")
-  name: robots-txt-policy-disallow-9
-- action: DENY
-  expression: userAgent.contains("BadBot")
-  name: robots-txt-policy-blacklist-10
-- action: WEIGH
-  expression: userAgent.contains("SeoBot")
-  name: robots-txt-policy-crawl-delay-11
-  weight:
-    adjust: 5
-- action: DENY
-  expression: userAgent.contains("SeoBot")
-  name: robots-txt-policy-blacklist-12
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/.*/admin")
-  name: robots-txt-policy-disallow-13
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/temp.*\\.html")
-  name: robots-txt-policy-disallow-14
-- action: CHALLENGE
-  expression:
-    all:
-        - userAgent.contains("TestBot")
-        - path.matches("^/file.\\.log")
-  name: robots-txt-policy-disallow-15

cmd/robots2policy/testdata/custom-name.yaml

@@ -1,6 +0,0 @@
-- action: CHALLENGE
-  expression: path.startsWith("/admin/")
-  name: my-custom-policy-disallow-1
-- action: CHALLENGE
-  expression: path.startsWith("/private")
-  name: my-custom-policy-disallow-2

cmd/robots2policy/testdata/deny-action.yaml

@@ -1,6 +0,0 @@
-- action: DENY
-  expression: path.startsWith("/admin/")
-  name: robots-txt-policy-disallow-1
-- action: DENY
-  expression: path.startsWith("/private")
-  name: robots-txt-policy-disallow-2

cmd/robots2policy/testdata/empty.robots.txt

@@ -1,2 +0,0 @@
-# Empty robots.txt (comments only)
-# No actual rules

cmd/robots2policy/testdata/empty.yaml

@@ -1 +0,0 @@
-[]

cmd/robots2policy/testdata/simple.json

@@ -1,12 +0,0 @@
-[
-  {
-    "action": "CHALLENGE",
-    "expression": "path.startsWith(\"/admin/\")",
-    "name": "robots-txt-policy-disallow-1"
-  },
-  {
-    "action": "CHALLENGE",
-    "expression": "path.startsWith(\"/private\")",
-    "name": "robots-txt-policy-disallow-2"
-  }
-]

cmd/robots2policy/testdata/simple.robots.txt

@@ -1,5 +0,0 @@
-# Simple robots.txt test
-User-agent: *
-Disallow: /admin/
-Disallow: /private
-Allow: /public

cmd/robots2policy/testdata/simple.yaml

@@ -1,6 +0,0 @@
-- action: CHALLENGE
-  expression: path.startsWith("/admin/")
-  name: robots-txt-policy-disallow-1
-- action: CHALLENGE
-  expression: path.startsWith("/private")
-  name: robots-txt-policy-disallow-2

cmd/robots2policy/testdata/wildcards.robots.txt

@@ -1,6 +0,0 @@
-# Test wildcard patterns
-User-agent: *
-Disallow: /search*
-Disallow: /*/private
-Disallow: /file?.txt
-Disallow: /admin/*?action=delete

cmd/robots2policy/testdata/wildcards.yaml

@@ -1,12 +0,0 @@
-- action: CHALLENGE
-  expression: path.matches("^/search.*")
-  name: robots-txt-policy-disallow-1
-- action: CHALLENGE
-  expression: path.matches("^/.*/private")
-  name: robots-txt-policy-disallow-2
-- action: CHALLENGE
-  expression: path.matches("^/file.\\.txt")
-  name: robots-txt-policy-disallow-3
-- action: CHALLENGE
-  expression: path.matches("^/admin/.*.action=delete")
-  name: robots-txt-policy-disallow-4

data/botPolicies.yaml

@@ -51,29 +51,6 @@ bots:
   #     report_as: 4    # lie to the operator
   #     algorithm: slow # intentionally waste CPU cycles and time
 
-  # Requires a subscription to Thoth to use, see
-  # https://anubis.techaro.lol/docs/admin/thoth#geoip-based-filtering
-  - name: countries-with-aggressive-scrapers
-    action: WEIGH
-    geoip:
-      counties:
-        - BR
-        - CN
-    weight:
-      adjust: 10
-
-  # Requires a subscription to Thoth to use, see
-  # https://anubis.techaro.lol/docs/admin/thoth#asn-based-filtering
-  - name: aggressive-asns-without-functional-abuse-contact
-    action: WEIGH
-    asns:
-      match:
-        - 13335 # Cloudflare
-        - 136907 # Huawei Cloud
-        - 45102 # Alibaba Cloud
-    weight:
-      adjust: 10
-
   # Generic catchall rule
   - name: generic-browser
     user_agent_regex: >-

docker-bake.hcl

@@ -1,12 +1,13 @@
 variable "ALPINE_VERSION" { default = "3.22" }
+variable "GITHUB_SHA" { default = "devel" }
 
 group "default" {
   targets = [
-    "ci-runner",
+    "anubis",
   ]
 }
 
-target "ci-runner" {
+target "anubis" {
   args = {
     ALPINE_VERSION = "3.22"
   }
@@ -21,6 +22,6 @@ target "ci-runner" {
   ]
   pull = true
   tags = [
-    "ghcr.io/techarohq/anubis/ci-runner:latest"
+    "ghcr.io/techarohq/anubis:${GITHUB_SHA}"
   ]
 }

docs/blog/2025-06-16-welcome/index.mdx

@@ -1,14 +0,0 @@
----
-slug: welcome
-title: Welcome to the Anubis blog!
-authors: [xe]
-tags: [intro]
----
-
-Hello, world!
-
-At Techaro, we've been working on making Anubis even better, and in the process we want to share what we've done, how it works, and signal boost cool things the community has done. As things happen, we'll blog about them so that you can learn from our struggles.
-
-More details to come soon!
-
-{/* truncate */}

docs/blog/authors.yml

@@ -1,9 +0,0 @@
-xe:
-  name: Xe Iaso
-  title: CEO @ Techaro
-  url: https://github.com/Xe
-  image_url: https://github.com/Xe.png
-  email: xe@techaro.lol
-  page: true
-  socials:
-    github: Xe

docs/blog/tags.yml

@@ -1 +0,0 @@
-

docs/docs/CHANGELOG.md

@@ -11,8 +11,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-- Replace cidranger with bart for IP range checking, improving IP matching performance by 3-20x with zero heap 
-  allocations
 - Remove the unused `/test-error` endpoint and update the testing endpoint `/make-challenge` to only be enabled in
   development
 - Add `--xff-strip-private` flag/envvar to toggle skipping X-Forwarded-For private addresses or not
@@ -22,11 +20,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Implement a no-JS challenge method: [`metarefresh`](./admin/configuration/challenges/metarefresh.mdx) ([#95](https://github.com/TecharoHQ/anubis/issues/95))
 - Bump AI-robots.txt to version 1.34
 - Make progress bar styling more compatible (UXP, etc)
-- Optimized the OGTags subsystem with reduced allocations and runtime per request by up to 66%
-- Add `--strip-base-prefix` flag/envvar to strip the base prefix from request paths when forwarding to target servers
-- Add `robots2policy` CLI utility to convert robots.txt files to Anubis challenge policies using CEL expressions ([#409](https://github.com/TecharoHQ/anubis/issues/409))
-- Implement GeoIP and ASN based checks via [Thoth](https://anubis.techaro.lol/docs/admin/thoth) ([#206](https://github.com/TecharoHQ/anubis/issues/206))
-- Replace internal SHA256 hashing with xxhash for 4-6x performance improvement in policy evaluation and cache operations
 
 ## v1.19.1: Jenomis cen Lexentale - Echo 1
 
@@ -162,6 +155,7 @@ Other changes:
 - Moved all CSS inline to the Xess package, changed colors to be CSS variables
 - Set or append to `X-Forwarded-For` header unless the remote connects over a loopback address [#328](https://github.com/TecharoHQ/anubis/issues/328)
 - 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

docs/docs/admin/installation.mdx

@@ -4,6 +4,8 @@ title: Setting up Anubis
 
 import RandomKey from "@site/src/components/RandomKey";
 
+import Tabs from "@theme/Tabs";
+import TabItem from "@theme/TabItem";
 
 Anubis is meant to sit between your reverse proxy (such as Nginx or Caddy) and your target service. One instance of Anubis must be used per service you are protecting.
 
@@ -30,7 +32,7 @@ TLS terminator)
 Anubis is shipped in the Docker repo [`ghcr.io/techarohq/anubis`](https://github.com/TecharoHQ/anubis/pkgs/container/anubis). The following tags exist for your convenience:
 
 | Tag                 | Meaning                                                                                                                            |
-|:--------------------|:-----------------------------------------------------------------------------------------------------------------------------------|
+| :------------------ | :--------------------------------------------------------------------------------------------------------------------------------- |
 | `latest`            | The latest [tagged release](https://github.com/TecharoHQ/anubis/releases), if you are in doubt, start here.                        |
 | `v<version number>` | The Anubis image for [any given tagged release](https://github.com/TecharoHQ/anubis/tags)                                          |
 | `main`              | The current build on the `main` branch. Only use this if you need the latest and greatest features as they are merged into `main`. |
@@ -48,7 +50,7 @@ For more detailed information on installing Anubis with native packages, please
 Anubis uses these environment variables for configuration:
 
 | Environment Variable           | Default value           | Explanation                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-|:-------------------------------|:------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| :----------------------------- | :---------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `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.                                                                                                                                                                                                                                                                                                                                                              |
@@ -67,7 +69,6 @@ Anubis uses these environment variables for configuration:
 | `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.<br/><br/>Note that if you are hosting Anubis on a non-standard port (`https://example:com:8443`, `http://www.example.net:8080`, etc.), you must also include the port number here. |
 | `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.                                                                                                                                                                                                                |
 | `SOCKET_MODE`                  | `0770`                  | _Only used when at least one of the `*_BIND_NETWORK` variables are set to `unix`._ The socket mode (permissions) for Unix domain sockets.                                                                                                                                                                                                                                                                                                                                                               |
-| `STRIP_BASE_PREFIX`            | `false`                 | If set to `true`, strips the base prefix from request paths when forwarding to the target server. This is useful when your target service expects to receive requests without the base prefix. For example, with `BASE_PREFIX=/foo` and `STRIP_BASE_PREFIX=true`, a request to `/foo/bar` would be forwarded to the target as `/bar`.                                                                                                                                                                   |
 | `TARGET`                       | `http://localhost:3923` | The URL of the service that Anubis should forward valid requests to. Supports Unix domain sockets, set this to a URI like so: `unix:///path/to/socket.sock`.                                                                                                                                                                                                                                                                                                                                            |
 | `USE_REMOTE_ADDRESS`           | unset                   | If set to `true`, Anubis will take the client's IP from the network socket. For production deployments, it is expected that a reverse proxy is used in front of Anubis, which pass the IP using headers, instead.                                                                                                                                                                                                                                                                                       |
 | `WEBMASTER_EMAIL`              | unset                   | If set, shows a contact email address when rendering error pages. This email address will be how users can get in contact with administrators.                                                                                                                                                                                                                                                                                                                                                          |
@@ -128,21 +129,6 @@ With corresponding Anubis configuration:
 BASE_PREFIX=/myapp
 ```
 
-#### Stripping Base Prefix
-
-If your target service doesn't expect to receive the base prefix in request paths, you can use the `STRIP_BASE_PREFIX` option:
-
-```
-BASE_PREFIX=/myapp
-STRIP_BASE_PREFIX=true
-```
-
-With this configuration:
-- A request to `/myapp/api/users` would be forwarded to your target service as `/api/users`
-- A request to `/myapp/` would be forwarded as `/`
-
-This is particularly useful when working with applications that weren't designed to handle path prefixes. However, note that if your target application generates absolute redirects or links (like `/login` instead of `./login`), these may break the subpath routing since they won't include the base prefix.
-
 ### Key generation
 
 To generate an ed25519 private key, you can use this command:

docs/docs/admin/robots2policy.mdx

@@ -1,84 +0,0 @@
----
-title: robots2policy CLI Tool
-sidebar_position: 50
----
-
-The `robots2policy` tool converts robots.txt files into Anubis challenge policies. It reads robots.txt rules and generates equivalent CEL expressions for path matching and user-agent filtering.
-
-## Installation
-
-Install directly with Go:
-
-```bash
-go install github.com/TecharoHQ/anubis/cmd/robots2policy@latest
-```
-## Usage
-
-Basic conversion from URL:
-
-```bash
-robots2policy -input https://www.example.com/robots.txt
-```
-
-Convert local file to YAML:
-
-```bash
-robots2policy -input robots.txt -output policy.yaml
-```
-
-Convert with custom settings:
-
-```bash
-robots2policy -input robots.txt -action DENY -format json
-```
-
-## Options
-
-| Flag                  | Description                                                        | Default             |
-|-----------------------|--------------------------------------------------------------------|---------------------|
-| `-input`              | robots.txt file path or URL (use `-` for stdin)                    | *required*          |
-| `-output`             | Output file (use `-` for stdout)                                   | stdout              |
-| `-format`             | Output format: `yaml` or `json`                                    | `yaml`              |
-| `-action`             | Action for disallowed paths: `ALLOW`, `DENY`, `CHALLENGE`, `WEIGH` | `CHALLENGE`         |
-| `-name`               | Policy name prefix                                                 | `robots-txt-policy` |
-| `-crawl-delay-weight` | Weight adjustment for crawl-delay rules                            | `3`                 |
-| `-deny-user-agents`   | Action for blacklisted user agents                                 | `DENY`              |
-
-## Example
-
-Input robots.txt:
-```txt
-User-agent: *
-Disallow: /admin/
-Disallow: /private
-
-User-agent: BadBot
-Disallow: /
-```
-
-Generated policy:
-```yaml
-- name: robots-txt-policy-disallow-1
-  action: CHALLENGE
-  expression:
-    single: path.startsWith("/admin/")
-- name: robots-txt-policy-disallow-2
-  action: CHALLENGE
-  expression:
-    single: path.startsWith("/private")
-- name: robots-txt-policy-blacklist-3
-  action: DENY
-  expression:
-    single: userAgent.contains("BadBot")
-```
-
-## Using the Generated Policy
-
-Save the output and import it in your main policy file:
-
-```yaml
-import:
-  - path: "./robots-policy.yaml"
-```
-
-The tool handles wildcard patterns, user-agent specific rules, and blacklisted bots automatically.

docs/docs/admin/thoth.mdx

@@ -1,81 +0,0 @@
-# Thoth-based advanced checks
-
-Status: Beta
-
-Anubis instances are normally isolated. Each Anubis instance has its own configuration and exists in roughly its own world without any long term memory between requests. As threats, workarounds, and AI scraper toolchains evolve, administrators will need a way to get more up to date information faster than Anubis' release cycle.
-
-Thus, Thoth is being created. Thoth is the reputation database for Anubis. Thoth feeds information to Anubis so that it can make better decisions about which traffic is innocuous and which traffic is suspicious.
-
-:::note
-
-Thoth is hosted by [Techaro](https://techaro.lol). Thoth is a paid service. Thoth is opt-in and requires manual intervention (including payment) to use. The code that powers Thoth is currently closed source.
-
-To get access to Thoth, please subscribe [on GitHub Sponsors](https://github.com/sponsors/Xe) and [email Xe](mailto:xe@techaro.lol). This will be self-service soon.
-
-:::
-
-## Implementation
-
-Thoth is a web service that listens over [gRPC](https://grpc.io/). Thoth's API is documented in protocol buffer definitions in the GitHub repo [TecharoHQ/thoth-proto](https://github.com/TecharoHQ/thoth-proto).
-
-Thoth is designed to be _informative_, not _authoritative_. Thoth cannot and will not arbitrarily block requests, origins, or other traffic. Thoth is there to inform Anubis and influence the weight of requests so that upstream resources can be protected. Additionally, Anubis aggressively caches data from Thoth such that over time Anubis will not need to request data very often. This makes the fast path for repeat visitors even faster and reduces the amount of data that Thoth is exposed to.
-
-## Thoth features
-
-Thoth is currently in active development. Currently, Thoth provides the following features to Anubis:
-
-- BGP Autonomous System (ASN) based filtering
-- GeoIP location based filtering
-
-### ASN-based filtering
-
-When companies link their backbone infrastructure to the Internet, they do so via a [BGP Autonomous System](<https://en.wikipedia.org/wiki/Autonomous_system_(Internet)>), denoted by a number (the Autonomous System Number or ASN). Every IP address on the Internet is owned by an ASN with a 1:1 lookup that does not change very frequently.
-
-Anubis uses Thoth to match IP addresses to BGP Autonomous Systems so that you can either issue arbitrary challenges to individual internet service providers (such as Cloudflare or Huawei Cloud) or, at the administrator's explicit instruction, block them altogether. For example, here's how you add 10 weight points to requests from Cloudflare, Huawei Cloud, and Alibaba Cloud:
-
-```yaml
-- name: aggressive-asns-without-functional-abuse-contact
-  action: WEIGH
-  asns:
-    match:
-      - 13335 # Cloudflare
-      - 136907 # Huawei Cloud
-      - 45102 # Alibaba Cloud
-  weight:
-    adjust: 10
-```
-
-You can look up details for [AS13335](https://bgp.tools/as/13335) or any of these other top offenders on [bgp.tools](https://bgp.tools).
-
-### GeoIP-based filtering
-
-In extreme cases, an administrator may have to take action against an entire country. This is not an ideal circumstance, but sometimes reality forces their hands and the administrators just want to sleep at night.
-
-Anubis uses Thoth to look up the geographic location registered to an IP address. This lookup is not the best and will get better with time, but you ship what you can so you can make it better for next time.
-
-For example, to add 10 weight points to requests from Brazil and China:
-
-```yaml
-- name: countries-with-aggressive-scrapers
-  action: WEIGH
-  geoip:
-    counties:
-      - BR
-      - CN
-  weight:
-    adjust: 10
-```
-
-Use this with care.
-
-## Work-in-progress features
-
-This section is a bit aspirational and is where Thoth will end up rather than things you can use today.
-
-In general, a lot of Thoth features are focused on taking the same Anubis you know and love and making it better, smarter, and less paranoid. These include:
-
-- Private rulesets for advanced patterns, current known exploits, and other recognition tactics that need to be kept cloak and dagger for operational security reasons
-- Private challenge implementations via WebAssembly, including advanced browser detection logic
-- Reputation querying so that Thoth can arbitrarily influence the weight of requests based on the net aggregate pass rate so that the most common browsers can get through with no challenge issued at all
-- APIs for trusted administrators to report abusive request fingerprints so that Anubis can react to threats as they evolve
-- A way for Anubis to periodically report the pass rate per ASN and other fingerprints so that methodology can be improved

docs/docs/user/known-instances.md

@@ -41,23 +41,13 @@ This page contains a non-exhaustive list with all websites using Anubis.
 - https://minihoot.site
 - https://catgirl.click/
 - https://wiki.dolphin-emu.org/
-- https://squirreljme.cc/
-- https://gitlab.postmarketos.org/
-- https://wiki.koha-community.org/
 - <details>
   <summary>FreeCAD</summary>
   - https://forum.freecad.org/
   - https://wiki.freecad.org/
   </details>
-- <details>
-  <summary>ReactOS</summary>
-  - https://reactos.org/forum
-  - https://reactos.org/wiki
-  - https://git.reactos.org
-  </details>
 - <details>
   <summary>ScummVM</summary>
-  - https://bugs.scummvm.org/
   - https://forums.scummvm.org/
   - https://wiki.scummvm.org/
   </details>

docs/docusaurus.config.ts

@@ -47,21 +47,21 @@ const config: Config = {
           editUrl:
             'https://github.com/TecharoHQ/anubis/tree/main/docs/',
         },
-        blog: {
-          showReadingTime: true,
-          feedOptions: {
-            type: ['rss', 'atom', "json"],
-            xslt: true,
-          },
-          // Please change this to your repo.
-          // Remove this to remove the "edit this page" links.
-          editUrl:
-            'https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/',
-          // Useful options to enforce blogging best practices
-          onInlineTags: 'warn',
-          onInlineAuthors: 'warn',
-          onUntruncatedBlogPosts: 'warn',
-        },
+        // blog: {
+        //   showReadingTime: true,
+        //   feedOptions: {
+        //     type: ['rss', 'atom', "json"],
+        //     xslt: true,
+        //   },
+        //   // Please change this to your repo.
+        //   // Remove this to remove the "edit this page" links.
+        //   editUrl:
+        //     'https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/',
+        //   // Useful options to enforce blogging best practices
+        //   onInlineTags: 'warn',
+        //   onInlineAuthors: 'warn',
+        //   onUntruncatedBlogPosts: 'warn',
+        // },
         theme: {
           customCss: './src/css/custom.css',
         },
@@ -86,14 +86,9 @@ const config: Config = {
           type: 'docSidebar',
           sidebarId: 'tutorialSidebar',
           position: 'left',
-          label: 'Docs',
-        },
-        { to: '/blog', label: 'Blog', position: 'left' },
-        {
-          href: 'https://github.com/sponsors/Xe',
-          label: "Sponsorship",
-          position: 'left'
+          label: 'Tutorial',
         },
+        // { to: '/blog', label: 'Blog', position: 'left' },
         {
           href: 'https://github.com/TecharoHQ/anubis',
           label: 'GitHub',
@@ -133,10 +128,6 @@ const config: Config = {
         {
           title: 'More',
           items: [
-            {
-              label: 'Blog',
-              to: '/blog',
-            },
             {
               label: 'GitHub',
               href: 'https://github.com/TecharoHQ/anubis',

docs/manifest/1password.yaml

@@ -1,6 +0,0 @@
-apiVersion: onepassword.com/v1
-kind: OnePasswordItem
-metadata:
-  name: anubis-docs-thoth
-spec:
-  itemPath: "vaults/lc5zo4zjz3if3mkeuhufjmgmui/items/pwguumqcmtxvqbeb7y4gj7l36i"

docs/manifest/cfg/anubis/botPolicies.yaml

@@ -51,13 +51,6 @@ bots:
   #     report_as: 4    # lie to the operator
   #     algorithm: slow # intentionally waste CPU cycles and time
 
-  - name: rss-feed-blog
-    action: ALLOW
-    expression:
-      any:
-        - path.startsWith("/blog/atom.")
-        - path.startsWith("/blog/rss.")
-
   # Generic catchall rule
   - name: generic-browser
     user_agent_regex: >-

docs/manifest/deployment.yaml

@@ -38,8 +38,6 @@ spec:
               value: "4"
             - name: "METRICS_BIND"
               value: ":9090"
-            - name: "OG_PASSTHROUGH"
-              value: "true"
             - name: "POLICY_FNAME"
               value: "/xe/cfg/anubis/botPolicies.yaml"
             - name: "SERVE_ROBOTS_TXT"
@@ -68,6 +66,3 @@ spec:
                 - ALL
             seccompProfile:
               type: RuntimeDefault
-          envFrom:
-            - secretRef:
-                name: anubis-docs-thoth

docs/manifest/kustomization.yaml

@@ -1,9 +1,7 @@
 resources:
-  - 1password.yaml
   - deployment.yaml
   - ingress.yaml
   - onionservice.yaml
-  - poddisruptionbudget.yaml
   - service.yaml
 
 configMapGenerator:

docs/manifest/poddisruptionbudget.yaml

@@ -1,9 +0,0 @@
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: anubis-docs
-spec:
-  minAvailable: 1
-  selector:
-    matchLabels:
-      app: anubis-docs

go.mod

@@ -3,29 +3,20 @@ module github.com/TecharoHQ/anubis
 go 1.24.2
 
 require (
-	github.com/TecharoHQ/thoth-proto v0.4.0
 	github.com/a-h/templ v0.3.898
-	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/facebookgo/flagenv v0.0.0-20160425205200-fcd59fca7456
-	github.com/gaissmai/bart v0.20.4
 	github.com/golang-jwt/jwt/v5 v5.2.2
 	github.com/google/cel-go v0.25.0
-	github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1
-	github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0
-	github.com/joho/godotenv v1.5.1
 	github.com/playwright-community/playwright-go v0.5200.0
 	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 v0.41.0
-	google.golang.org/grpc v1.72.2
-	gopkg.in/yaml.v3 v3.0.1
 	k8s.io/apimachinery v0.33.1
-	sigs.k8s.io/yaml v1.4.0
 )
 
 require (
 	al.essio.dev/pkg/shellescape v1.6.0 // indirect
-	buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 // indirect
 	cel.dev/expr v0.23.1 // indirect
 	dario.cat/mergo v1.0.2 // indirect
 	github.com/AlekSi/pointer v1.2.0 // indirect
@@ -44,9 +35,10 @@ require (
 	github.com/blakesmith/ar v0.0.0-20190502131153-809d4375e1fb // indirect
 	github.com/cavaliergopher/cpio 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/cli/go-gh v0.1.0 // indirect
-	github.com/cloudflare/circl v1.6.1 // indirect
+	github.com/cloudflare/circl v1.6.0 // indirect
 	github.com/cyphar/filepath-securejoin v0.4.1 // indirect
 	github.com/deckarep/golang-set/v2 v2.8.0 // indirect
 	github.com/dlclark/regexp2 v1.11.4 // indirect
@@ -92,7 +84,7 @@ require (
 	github.com/shopspring/decimal v1.4.0 // indirect
 	github.com/skeema/knownhosts v1.3.1 // indirect
 	github.com/spf13/cast v1.7.1 // indirect
-	github.com/stoewer/go-strcase v1.3.0 // indirect
+	github.com/stoewer/go-strcase v1.2.0 // indirect
 	github.com/ulikunitz/xz v0.5.12 // indirect
 	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	gitlab.com/digitalxero/go-conventional-commit v1.0.7 // indirect
@@ -108,13 +100,15 @@ require (
 	golang.org/x/tools v0.33.0 // indirect
 	golang.org/x/vuln v1.1.4 // indirect
 	golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20250218202821-56aae31c358a // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20250218202821-56aae31c358a // indirect
-	google.golang.org/protobuf v1.36.6 // 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
 	gopkg.in/warnings.v0 v0.1.2 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 	honnef.co/go/tools v0.6.1 // indirect
 	mvdan.cc/sh/v3 v3.11.0 // indirect
 	sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
+	sigs.k8s.io/yaml v1.4.0 // indirect
 )
 
 tool (

go.sum

@@ -1,7 +1,5 @@
 al.essio.dev/pkg/shellescape v1.6.0 h1:NxFcEqzFSEVCGN2yq7Huv/9hyCEGVa/TncnOOBBeXHA=
 al.essio.dev/pkg/shellescape v1.6.0/go.mod h1:6sIqp7X2P6mThCQ7twERpZTuigpr6KbZWtls1U8I890=
-buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 h1:YhMSc48s25kr7kv31Z8vf7sPUIq5YJva9z1mn/hAt0M=
-buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1/go.mod h1:avRlCjnFzl98VPaeCtJ24RrV/wwHFzB8sWXhj26+n/U=
 cel.dev/expr v0.23.1 h1:K4KOtPCJQjVggkARsjG9RWXP6O4R73aHeJMa/dmCQQg=
 cel.dev/expr v0.23.1/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
 dario.cat/mergo v1.0.2 h1:85+piFYR1tMbRrLcDwR18y4UKJ3aH1Tbzi24VRW1TK8=
@@ -30,8 +28,6 @@ github.com/ProtonMail/gopenpgp/v2 v2.7.1 h1:Awsg7MPc2gD3I7IFac2qE3Gdls0lZW8SzrFZ
 github.com/ProtonMail/gopenpgp/v2 v2.7.1/go.mod h1:/BU5gfAVwqyd8EfC3Eu7zmuhwYQpKs+cGD8M//iiaxs=
 github.com/Songmu/gitconfig v0.2.0 h1:pX2++u4KUq+K2k/ZCzGXLtkD3ceCqIdi0tDyb+IbSyo=
 github.com/Songmu/gitconfig v0.2.0/go.mod h1:cB5bYJer+pl7W8g6RHFwL/0X6aJROVrYuHlvc7PT+hE=
-github.com/TecharoHQ/thoth-proto v0.4.0 h1:UbkvfgCku0Dm1R6O4ug3HOsJNnE6F3wB8x+Dpw2lzFI=
-github.com/TecharoHQ/thoth-proto v0.4.0/go.mod h1:IcGnZt3iYUZQVEa0Lwk5l4ix0hCeXlWUV1TJMZvbWx0=
 github.com/TecharoHQ/yeet v0.6.0 h1:RCBAjr7wIlllsgy0tpvWpLX7jsZgu2tiuBY3RrprcR0=
 github.com/TecharoHQ/yeet v0.6.0/go.mod h1:bj2V4Fg8qKQXoiuPZa3HuawrE8g+LsOQv/9q2WyGSsA=
 github.com/a-h/parse v0.0.0-20250122154542-74294addb73e h1:HjVbSQHy+dnlS6C3XajZ69NYAb5jbGNfHanvm1+iYlo=
@@ -67,8 +63,8 @@ github.com/cli/go-gh v0.1.0 h1:kMqFmC3ECBrV2UKzlOHjNOTTchExVc5tjNHtCqk/zYk=
 github.com/cli/go-gh v0.1.0/go.mod h1:eTGWl99EMZ+3Iau5C6dHyGAJRRia65MtdBtuhWc+84o=
 github.com/cli/safeexec v1.0.0/go.mod h1:Z/D4tTN8Vs5gXYHDCbaM1S/anmEDnJb1iW0+EJ5zx3Q=
 github.com/cli/shurcooL-graphql v0.0.1/go.mod h1:U7gCSuMZP/Qy7kbqkk5PrqXEeDgtfG5K+W+u8weorps=
-github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
-github.com/cloudflare/circl v1.6.1/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
+github.com/cloudflare/circl v1.6.0 h1:cr5JKic4HI+LkINy2lg3W2jF8sHCVTBncJr5gIIq7qk=
+github.com/cloudflare/circl v1.6.0/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
 github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=
 github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=
 github.com/cyphar/filepath-securejoin v0.4.1 h1:JyxxyPEaktOD+GAnqIqTf9A8tHyAG22rowi7HkoSU1s=
@@ -103,8 +99,6 @@ github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHk
 github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/fsnotify/fsnotify v1.8.0 h1:dAwr6QBTBZIkG8roQaJjGof0pp0EeF+tNV7YBP3F/8M=
 github.com/fsnotify/fsnotify v1.8.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
-github.com/gaissmai/bart v0.20.4 h1:Ik47r1fy3jRVU+1eYzKSW3ho2UgBVTVnUS8O993584U=
-github.com/gaissmai/bart v0.20.4/go.mod h1:cEed+ge8dalcbpi8wtS9x9m2hn/fNJH5suhdGQOHnYk=
 github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
 github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
 github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
@@ -117,10 +111,6 @@ github.com/go-git/go-git/v5 v5.14.0 h1:/MD3lCrGjCen5WfEAzKg00MJJffKhC8gzS80ycmCi
 github.com/go-git/go-git/v5 v5.14.0/go.mod h1:Z5Xhoia5PcWA3NF8vRLURn9E5FRhSl7dGj9ItW3Wk5k=
 github.com/go-jose/go-jose/v3 v3.0.4 h1:Wp5HA7bLQcKnf6YYao/4kpRpVMp/yf6+pJKV8WFSaNY=
 github.com/go-jose/go-jose/v3 v3.0.4/go.mod h1:5b+7YgP7ZICgJDBdfjZaIt+H/9L9T/YQrVfLAMboGkQ=
-github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
-github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
-github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
-github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.13.0 h1:HyWk6mgj5qFqCT5fjGBuRArbVDfE4hi8+e8ceBS/t7Q=
 github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
@@ -144,8 +134,6 @@ github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeD
 github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
 github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 h1:f+oWsMOmNPc8JmEHVZIycC7hBoQxHH9pNKQORJNozsQ=
 github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8/go.mod h1:wcDNUvekVysuuOpQKo3191zZyTpiI6se1N1ULghS0sw=
-github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
-github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
 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-cmdtest v0.4.1-0.20220921163831-55ab3332a786 h1:rcv+Ippz6RAtvaGgKxc+8FQIpxHgsF+HBzPyYL2cyVU=
@@ -171,18 +159,12 @@ github.com/goreleaser/fileglob v1.3.0 h1:/X6J7U8lbDpQtBvGcwwPS6OpzkNVlVEsFUVRx9+
 github.com/goreleaser/fileglob v1.3.0/go.mod h1:Jx6BoXv3mbYkEzwm9THo7xbr5egkAraxkGorbJb4RxU=
 github.com/goreleaser/nfpm/v2 v2.42.1 h1:xu2pLRgQuz2ab+YZFoeIzwU/M5jjjCKDGwv1lRbVGvk=
 github.com/goreleaser/nfpm/v2 v2.42.1/go.mod h1:dY53KWYKebkOocxgkmpM7SRX0Nv5hU+jEu2kIaM4/LI=
-github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1 h1:qnpSQwGEnkcRpTqNOIR6bJbR0gAorgP9CSALpRcKoAA=
-github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1/go.mod h1:lXGCsh6c22WGtjr+qGHj1otzZpV/1kwTMAqkwZsnWRU=
-github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0 h1:pRhl55Yx1eC7BZ1N+BBWwnKaMyD8uC+34TLdndZMAKk=
-github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0/go.mod h1:XKMd7iuf/RGPSMJ/U4HP0zS2Z9Fh8Ps9a+6X26m/tmI=
 github.com/h2non/parth v0.0.0-20190131123155-b4df798d6542/go.mod h1:Ow0tF8D4Kplbc8s8sSb3V2oUCygFHVp8gC3Dn6U4MNI=
 github.com/henvic/httpretty v0.0.6/go.mod h1:X38wLjWXHkXT7r2+uK8LjCMne9rsuNaBLJ+5cU2/Pmo=
 github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI=
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
-github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
-github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
 github.com/kevinburke/ssh_config v1.2.0 h1:x584FjTGwHzMwvHx18PXxbBVzfnxogHaAReU4gf13a4=
@@ -266,17 +248,13 @@ github.com/smartystreets/goconvey v1.8.1 h1:qGjIddxOk4grTu9JPOU31tVfq3cNdBlNa5sS
 github.com/smartystreets/goconvey v1.8.1/go.mod h1:+/u4qLyY6x1jReYOp7GOM2FSt8aP9CzCZL03bI28W60=
 github.com/spf13/cast v1.7.1 h1:cuNEagBQEHWN1FnbGEjCXL2szYEXqfJPbP2HNUaca9Y=
 github.com/spf13/cast v1.7.1/go.mod h1:ancEpBxwJDODSW/UG4rDrAqiKolqNNh2DX3mk86cAdo=
-github.com/stoewer/go-strcase v1.3.0 h1:g0eASXYtp+yvN9fK8sH94oCIk0fau9uV1/ZdJ0AVEzs=
-github.com/stoewer/go-strcase v1.3.0/go.mod h1:fAH5hQ5pehh+j3nZfvwdk2RgEgQjAoM8wodgtPmh1xo=
+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/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
-github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 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 v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
-github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/thlib/go-timezone-local v0.0.0-20210907160436-ef149e42d28e/go.mod h1:/Tnicc6m/lsJE0irFMA0LfIwTBo4QP7A8IfyIv4zZKI=
@@ -286,21 +264,11 @@ github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM
 github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 h1:nIPpBwaJSVYIxUFsDv3M8ofmx9yWTog9BfvIu0q41lo=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8/go.mod h1:HUYIGzjTL3rfEspMxjDjgmT5uz5wzYJKVo23qUhYTos=
+github.com/yl2chen/cidranger v1.0.2 h1:lbOWZVCG1tCRX4u24kuM1Tb4nHqWkDxwLdoS+SevawU=
+github.com/yl2chen/cidranger v1.0.2/go.mod h1:9U1yz7WPYDwf0vpNWFaeRh0bjwz5RVgRy/9UEQfHl0g=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 gitlab.com/digitalxero/go-conventional-commit v1.0.7 h1:8/dO6WWG+98PMhlZowt/YjuiKhqhGlOCwlIV8SqqGh8=
 gitlab.com/digitalxero/go-conventional-commit v1.0.7/go.mod h1:05Xc2BFsSyC5tKhK0y+P3bs0AwUtNuTp+mTpbCU/DZ0=
-go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
-go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
-go.opentelemetry.io/otel v1.34.0 h1:zRLXxLCgL1WyKsPVrgbSdMN4c0FMkDAskSTQP+0hdUY=
-go.opentelemetry.io/otel v1.34.0/go.mod h1:OWFPOQ+h4G8xpyjgqo4SxJYdDQ/qmRH+wivy7zzx9oI=
-go.opentelemetry.io/otel/metric v1.34.0 h1:+eTR3U0MyfWjRDhmFMxe2SsW64QrZ84AOhvqS7Y+PoQ=
-go.opentelemetry.io/otel/metric v1.34.0/go.mod h1:CEDrp0fy2D0MvkXE+dPV7cMi8tWZwX3dmaIhwPOaqHE=
-go.opentelemetry.io/otel/sdk v1.34.0 h1:95zS4k/2GOy069d321O8jWgYsW3MzVV+KuSPKp7Wr1A=
-go.opentelemetry.io/otel/sdk v1.34.0/go.mod h1:0e/pNiaMAqaykJGKbi+tSjWfNNHMTxoC9qANsCzbyxU=
-go.opentelemetry.io/otel/sdk/metric v1.34.0 h1:5CeK9ujjbFVL5c1PhLuStg1wxA7vQv7ce1EK0Gyvahk=
-go.opentelemetry.io/otel/sdk/metric v1.34.0/go.mod h1:jQ/r8Ze28zRKoNRdkjCZxfs6YvBTG1+YIqyFVFYec5w=
-go.opentelemetry.io/otel/trace v1.34.0 h1:+ouXS2V8Rd4hp4580a8q23bg0azF2nI8cqLYnC8mh/k=
-go.opentelemetry.io/otel/trace v1.34.0/go.mod h1:Svm7lSjQD7kG7KJ/MUHPVXSDGz2OX4h0M2jHBhmSfRE=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
@@ -385,14 +353,12 @@ golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20220609144429-65e65417b02f/go.mod h1:K8+ghG5WaK9qNqU5K3HdILfMLy1f3aNYFI/wnl100a8=
 golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9 h1:LLhsEBxRTBLuKlQxFBYUOU8xyFgXv6cOTp2HASDlsDk=
 golang.org/x/xerrors v0.0.0-20240716161551-93cc26a95ae9/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90=
-google.golang.org/genproto/googleapis/api v0.0.0-20250218202821-56aae31c358a h1:nwKuGPlUAt+aR+pcrkfFRrTU1BVrSmYyYMxYbUIVHr0=
-google.golang.org/genproto/googleapis/api v0.0.0-20250218202821-56aae31c358a/go.mod h1:3kWAYMk1I75K4vykHtKt2ycnOgpA6974V7bREqbsenU=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20250218202821-56aae31c358a h1:51aaUVRocpvUOSQKM6Q7VuoaktNIaMCLuhZB6DKksq4=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20250218202821-56aae31c358a/go.mod h1:uRxBH1mhmO8PGhU89cMcHaXKZqO+OfakD8QQO0oYwlQ=
-google.golang.org/grpc v1.72.2 h1:TdbGzwb82ty4OusHWepvFWGLgIbNo1/SUynEN0ssqv8=
-google.golang.org/grpc v1.72.2/go.mod h1:wH5Aktxcg25y1I3w7H69nHfXdOG3UiadoBtjh3izSDM=
-google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
-google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
+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 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

internal/hash.go

@@ -3,23 +3,10 @@ package internal
 import (
 	"crypto/sha256"
 	"encoding/hex"
-	"strconv"
-
-	"github.com/cespare/xxhash/v2"
 )
 
-// SHA256sum computes a cryptographic hash. Still used for proof-of-work challenges
-// where we need the security properties of a cryptographic hash function.
 func SHA256sum(text string) string {
 	hash := sha256.New()
 	hash.Write([]byte(text))
 	return hex.EncodeToString(hash.Sum(nil))
 }
-
-// FastHash is a high-performance non-cryptographic hash function suitable for
-// internal caching, policy rule identification, and other performance-critical
-// use cases where cryptographic security is not required.
-func FastHash(text string) string {
-	h := xxhash.Sum64String(text)
-	return strconv.FormatUint(h, 16)
-}

internal/hash_bench_test.go

@@ -1,261 +0,0 @@
-package internal
-
-import (
-	"fmt"
-	"strings"
-	"testing"
-)
-
-// XXHash64sum is a test alias for FastHash to benchmark against SHA256
-func XXHash64sum(text string) string {
-	return FastHash(text)
-}
-
-// Test data that matches real usage patterns in the codebase
-var (
-	// Typical policy checker inputs
-	policyInputs = []string{
-		"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
-		"User-Agent: bot/1.0",
-		"User-Agent: GoogleBot/2.1",
-		"/robots.txt",
-		"/api/.*",
-		"10.0.0.0/8",
-		"192.168.1.0/24",
-		"172.16.0.0/12",
-	}
-
-	// Challenge data from challengeFor function
-	challengeInputs = []string{
-		"Accept-Language=en-US,X-Real-IP=192.168.1.100,User-Agent=Mozilla/5.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=abc123,Difficulty=5",
-		"Accept-Language=fr-FR,X-Real-IP=10.0.0.50,User-Agent=Chrome/91.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=def456,Difficulty=3",
-		"Accept-Language=es-ES,X-Real-IP=172.16.1.1,User-Agent=Safari/14.0,WeekTime=2025-06-16T00:00:00Z,Fingerprint=ghi789,Difficulty=7",
-	}
-
-	// Bot rule patterns
-	botRuleInputs = []string{
-		"GoogleBot::path:/robots.txt",
-		"BingBot::useragent:Mozilla/5.0 (compatible; bingbot/2.0)",
-		"FacebookBot::headers:Accept-Language,User-Agent",
-		"TwitterBot::cidr:192.168.1.0/24",
-	}
-
-	// CEL expressions from policy rules
-	celInputs = []string{
-		`request.headers["User-Agent"].contains("bot")`,
-		`request.path.startsWith("/api/") && request.method == "POST"`,
-		`request.remoteAddress in ["192.168.1.0/24", "10.0.0.0/8"]`,
-		`request.userAgent.matches(".*[Bb]ot.*") || request.userAgent.matches(".*[Cc]rawler.*")`,
-	}
-
-	// Thoth ASN checker inputs
-	asnInputs = []string{
-		"ASNChecker\nAS 15169\nAS 8075\nAS 32934",
-		"ASNChecker\nAS 13335\nAS 16509\nAS 14061",
-		"ASNChecker\nAS 36351\nAS 20940\nAS 8100",
-	}
-)
-
-func BenchmarkSHA256_PolicyInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := policyInputs[i%len(policyInputs)]
-		_ = SHA256sum(input)
-	}
-}
-
-func BenchmarkXXHash_PolicyInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := policyInputs[i%len(policyInputs)]
-		_ = XXHash64sum(input)
-	}
-}
-
-func BenchmarkSHA256_ChallengeInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := challengeInputs[i%len(challengeInputs)]
-		_ = SHA256sum(input)
-	}
-}
-
-func BenchmarkXXHash_ChallengeInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := challengeInputs[i%len(challengeInputs)]
-		_ = XXHash64sum(input)
-	}
-}
-
-func BenchmarkSHA256_BotRuleInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := botRuleInputs[i%len(botRuleInputs)]
-		_ = SHA256sum(input)
-	}
-}
-
-func BenchmarkXXHash_BotRuleInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := botRuleInputs[i%len(botRuleInputs)]
-		_ = XXHash64sum(input)
-	}
-}
-
-func BenchmarkSHA256_CELInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := celInputs[i%len(celInputs)]
-		_ = SHA256sum(input)
-	}
-}
-
-func BenchmarkXXHash_CELInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := celInputs[i%len(celInputs)]
-		_ = XXHash64sum(input)
-	}
-}
-
-func BenchmarkSHA256_ASNInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := asnInputs[i%len(asnInputs)]
-		_ = SHA256sum(input)
-	}
-}
-
-func BenchmarkXXHash_ASNInputs(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		input := asnInputs[i%len(asnInputs)]
-		_ = XXHash64sum(input)
-	}
-}
-
-// Benchmark the policy list hashing used in checker.go
-func BenchmarkSHA256_PolicyList(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		var sb strings.Builder
-		for _, input := range policyInputs {
-			fmt.Fprintln(&sb, SHA256sum(input))
-		}
-		_ = SHA256sum(sb.String())
-	}
-}
-
-func BenchmarkXXHash_PolicyList(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		var sb strings.Builder
-		for _, input := range policyInputs {
-			fmt.Fprintln(&sb, XXHash64sum(input))
-		}
-		_ = XXHash64sum(sb.String())
-	}
-}
-
-// Tests that xxhash doesn't have collisions in realistic scenarios
-func TestHashCollisions(t *testing.T) {
-	allInputs := append(append(append(append(policyInputs, challengeInputs...), botRuleInputs...), celInputs...), asnInputs...)
-
-	// Start with realistic inputs from actual usage
-	xxhashHashes := make(map[string]string)
-	for _, input := range allInputs {
-		hash := XXHash64sum(input)
-		if existing, exists := xxhashHashes[hash]; exists {
-			t.Errorf("XXHash collision detected: %q and %q both hash to %s", input, existing, hash)
-		}
-		xxhashHashes[hash] = input
-	}
-
-	t.Logf("Basic test: %d realistic inputs, no collisions", len(allInputs))
-
-	// Test similar strings that might cause hash collisions
-	prefixes := []string{"User-Agent: ", "X-Real-IP: ", "Accept-Language: ", "Host: "}
-	suffixes := []string{"bot", "crawler", "spider", "scraper", "Mozilla", "Chrome", "Safari", "Firefox"}
-	variations := []string{"", "/1.0", "/2.0", " (compatible)", " (Windows)", " (Linux)", " (Mac)"}
-
-	stressCount := 0
-	for _, prefix := range prefixes {
-		for _, suffix := range suffixes {
-			for _, variation := range variations {
-				for i := 0; i < 100; i++ {
-					input := fmt.Sprintf("%s%s%s-%d", prefix, suffix, variation, i)
-					hash := XXHash64sum(input)
-					if existing, exists := xxhashHashes[hash]; exists {
-						t.Errorf("XXHash collision in stress test: %q and %q both hash to %s", input, existing, hash)
-					}
-					xxhashHashes[hash] = input
-					stressCount++
-				}
-			}
-		}
-	}
-	t.Logf("Stress test 1: %d similar string variations, no collisions", stressCount)
-
-	// Test sequential patterns that might be problematic
-	patterns := []string{
-		"192.168.1.%d",
-		"10.0.0.%d",
-		"172.16.%d.1",
-		"challenge-%d",
-		"bot-rule-%d",
-		"policy-%016x",
-		"session-%016x",
-	}
-
-	seqCount := 0
-	for _, pattern := range patterns {
-		for i := 0; i < 10000; i++ {
-			input := fmt.Sprintf(pattern, i)
-			hash := XXHash64sum(input)
-			if existing, exists := xxhashHashes[hash]; exists {
-				t.Errorf("XXHash collision in sequential test: %q and %q both hash to %s", input, existing, hash)
-			}
-			xxhashHashes[hash] = input
-			seqCount++
-		}
-	}
-	t.Logf("Stress test 2: %d sequential patterns, no collisions", seqCount)
-
-	totalInputs := len(allInputs) + stressCount + seqCount
-	t.Logf("TOTAL: Tested %d inputs across realistic scenarios - NO COLLISIONS", totalInputs)
-}
-
-// Verify xxhash output works as cache keys
-func TestXXHashFormat(t *testing.T) {
-	testCases := []string{
-		"short",
-		"",
-		"very long string with lots of content that might be used in policy checking and other internal hashing scenarios",
-		"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
-	}
-
-	for _, input := range testCases {
-		hash := XXHash64sum(input)
-
-		// Check it's valid hex
-		if len(hash) == 0 {
-			t.Errorf("Empty hash for input %q", input)
-		}
-
-		// xxhash is 64-bit so max 16 hex chars
-		if len(hash) > 16 {
-			t.Errorf("Hash too long for input %q: %s (length %d)", input, hash, len(hash))
-		}
-
-		// Make sure it's all hex characters
-		for _, char := range hash {
-			if !((char >= '0' && char <= '9') || (char >= 'a' && char <= 'f')) {
-				t.Errorf("Non-hex character %c in hash %s for input %q", char, hash, input)
-			}
-		}
-
-		t.Logf("Input: %q -> Hash: %s", input, hash)
-	}
-}

internal/ogtags/mem_test.go

@@ -1,149 +0,0 @@
-package ogtags
-
-import (
-	"net/url"
-	"runtime"
-	"strings"
-	"testing"
-
-	"golang.org/x/net/html"
-)
-
-func BenchmarkGetTarget(b *testing.B) {
-	tests := []struct {
-		name   string
-		target string
-		paths  []string
-	}{
-		{
-			name:   "HTTP",
-			target: "http://example.com",
-			paths:  []string{"/", "/path", "/path/to/resource", "/path?query=1&foo=bar"},
-		},
-		{
-			name:   "Unix",
-			target: "unix:///var/run/app.sock",
-			paths:  []string{"/", "/api/endpoint", "/api/endpoint?param=value"},
-		},
-	}
-
-	for _, tt := range tests {
-		b.Run(tt.name, func(b *testing.B) {
-			cache := NewOGTagCache(tt.target, false, 0, false)
-			urls := make([]*url.URL, len(tt.paths))
-			for i, path := range tt.paths {
-				u, _ := url.Parse(path)
-				urls[i] = u
-			}
-
-			b.ResetTimer()
-			b.ReportAllocs()
-
-			for i := 0; i < b.N; i++ {
-				_ = cache.getTarget(urls[i%len(urls)])
-			}
-		})
-	}
-}
-
-func BenchmarkExtractOGTags(b *testing.B) {
-	htmlSamples := []string{
-		`<html><head>
-			<meta property="og:title" content="Test Title">
-			<meta property="og:description" content="Test Description">
-			<meta name="keywords" content="test,keywords">
-		</head><body></body></html>`,
-		`<html><head>
-			<meta property="og:title" content="Page Title">
-			<meta property="og:type" content="website">
-			<meta property="og:url" content="https://example.com">
-			<meta property="og:image" content="https://example.com/image.jpg">
-			<meta property="twitter:card" content="summary_large_image">
-			<meta property="twitter:title" content="Twitter Title">
-			<meta name="description" content="Page description">
-			<meta name="author" content="John Doe">
-		</head><body><div><p>Content</p></div></body></html>`,
-	}
-
-	cache := NewOGTagCache("http://example.com", false, 0, false)
-	docs := make([]*html.Node, len(htmlSamples))
-
-	for i, sample := range htmlSamples {
-		doc, _ := html.Parse(strings.NewReader(sample))
-		docs[i] = doc
-	}
-
-	b.ResetTimer()
-	b.ReportAllocs()
-
-	for i := 0; i < b.N; i++ {
-		_ = cache.extractOGTags(docs[i%len(docs)])
-	}
-}
-
-// Memory usage test
-func TestMemoryUsage(t *testing.T) {
-	cache := NewOGTagCache("http://example.com", false, 0, false)
-
-	// Force GC and wait for it to complete
-	runtime.GC()
-
-	var m1 runtime.MemStats
-	runtime.ReadMemStats(&m1)
-
-	// Run getTarget many times
-	u, _ := url.Parse("/path/to/resource?query=1&foo=bar&baz=qux")
-	for i := 0; i < 10000; i++ {
-		_ = cache.getTarget(u)
-	}
-
-	// Force GC after operations
-	runtime.GC()
-
-	var m2 runtime.MemStats
-	runtime.ReadMemStats(&m2)
-
-	allocatedBytes := int64(m2.TotalAlloc) - int64(m1.TotalAlloc)
-	allocatedKB := float64(allocatedBytes) / 1024.0
-	allocatedPerOp := float64(allocatedBytes) / 10000.0
-
-	t.Logf("Memory allocated for 10k getTarget calls:")
-	t.Logf("  Total: %.2f KB (%.2f MB)", allocatedKB, allocatedKB/1024.0)
-	t.Logf("  Per operation: %.2f bytes", allocatedPerOp)
-
-	// Test extractOGTags memory usage
-	htmlDoc := `<html><head>
-		<meta property="og:title" content="Test Title">
-		<meta property="og:description" content="Test Description">
-		<meta property="og:image" content="https://example.com/image.jpg">
-		<meta property="twitter:card" content="summary">
-		<meta name="keywords" content="test,keywords,example">
-		<meta name="author" content="Test Author">
-		<meta property="unknown:tag" content="Should be ignored">
-	</head><body></body></html>`
-
-	doc, _ := html.Parse(strings.NewReader(htmlDoc))
-
-	runtime.GC()
-	runtime.ReadMemStats(&m1)
-
-	for i := 0; i < 1000; i++ {
-		_ = cache.extractOGTags(doc)
-	}
-
-	runtime.GC()
-	runtime.ReadMemStats(&m2)
-
-	allocatedBytes = int64(m2.TotalAlloc) - int64(m1.TotalAlloc)
-	allocatedKB = float64(allocatedBytes) / 1024.0
-	allocatedPerOp = float64(allocatedBytes) / 1000.0
-
-	t.Logf("Memory allocated for 1k extractOGTags calls:")
-	t.Logf("  Total: %.2f KB (%.2f MB)", allocatedKB, allocatedKB/1024.0)
-	t.Logf("  Per operation: %.2f bytes", allocatedPerOp)
-
-	// Sanity checks
-	if allocatedPerOp > 10000 {
-		t.Errorf("extractOGTags allocating too much memory per operation: %.2f bytes", allocatedPerOp)
-	}
-}

internal/ogtags/ogtags.go

@@ -13,20 +13,14 @@ import (
 )
 
 const (
-	maxContentLength = 8 << 20         // 8 MiB is enough for anyone
+	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?*/
-
-	schemeSeparatorLength = 3 // Length of "://"
-	querySeparatorLength  = 1 // Length of "?" for query strings
 )
 
 type OGTagCache struct {
-	cache     *decaymap.Impl[string, map[string]string]
-	targetURL *url.URL
-	client    *http.Client
-
-	// Pre-built strings for optimization
-	unixPrefix          string // "http://unix"
+	cache               *decaymap.Impl[string, map[string]string]
+	targetURL           *url.URL
+	client              *http.Client
 	approvedTags        []string
 	approvedPrefixes    []string
 	ogTimeToLive        time.Duration
@@ -36,6 +30,7 @@ type OGTagCache struct {
 
 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:"}
 
@@ -76,50 +71,37 @@ func NewOGTagCache(target string, ogPassthrough bool, ogTimeToLive time.Duration
 
 	return &OGTagCache{
 		cache:               decaymap.New[string, map[string]string](),
-		targetURL:           parsedTargetURL,
+		targetURL:           parsedTargetURL, // Store the parsed URL
 		ogPassthrough:       ogPassthrough,
 		ogTimeToLive:        ogTimeToLive,
-		ogCacheConsiderHost: ogTagsConsiderHost,
+		ogCacheConsiderHost: ogTagsConsiderHost, // todo: refactor to be a separate struct
 		approvedTags:        defaultApprovedTags,
 		approvedPrefixes:    defaultApprovedPrefixes,
 		client:              client,
-		unixPrefix:          "http://unix",
 	}
 }
 
 // getTarget constructs the target URL string for fetching OG tags.
-// Optimized to minimize allocations by building strings directly.
+// For Unix sockets, it creates a "fake" HTTP URL that the custom dialer understands.
 func (c *OGTagCache) getTarget(u *url.URL) string {
-	var escapedPath = u.EscapedPath() // will cause an allocation if path contains special characters
 	if c.targetURL.Scheme == "unix" {
-		// Build URL string directly without creating intermediate URL object
-		var sb strings.Builder
-		sb.Grow(len(c.unixPrefix) + len(escapedPath) + len(u.RawQuery) + querySeparatorLength) // Pre-allocate
-		sb.WriteString(c.unixPrefix)
-		sb.WriteString(escapedPath)
-		if u.RawQuery != "" {
-			sb.WriteByte('?')
-			sb.WriteString(u.RawQuery)
+		// 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 sb.String()
+		return fakeURL.String()
 	}
 
-	// For regular http/https targets, build URL string directly
-	var sb strings.Builder
-	// Pre-calculate size: scheme + "://" + host + path + "?" + query
-	estimatedSize := len(c.targetURL.Scheme) + schemeSeparatorLength + len(c.targetURL.Host) + len(escapedPath) + len(u.RawQuery) + querySeparatorLength
-	sb.Grow(estimatedSize)
+	// For regular http/https targets
+	target := *c.targetURL // Make a copy
+	target.Path = u.Path
+	target.RawQuery = u.RawQuery
+	return target.String()
 
-	sb.WriteString(c.targetURL.Scheme)
-	sb.WriteString("://")
-	sb.WriteString(c.targetURL.Host)
-	sb.WriteString(escapedPath)
-	if u.RawQuery != "" {
-		sb.WriteByte('?')
-		sb.WriteString(u.RawQuery)
-	}
-
-	return sb.String()
 }
 
 func (c *OGTagCache) Cleanup() {

internal/ogtags/ogtags_fuzz_test.go

@@ -1,309 +0,0 @@
-package ogtags
-
-import (
-	"net/url"
-	"strings"
-	"testing"
-	"unicode/utf8"
-
-	"golang.org/x/net/html"
-)
-
-// FuzzGetTarget tests getTarget with various inputs
-func FuzzGetTarget(f *testing.F) {
-	// Seed corpus with interesting test cases
-	testCases := []struct {
-		target string
-		path   string
-		query  string
-	}{
-		{"http://example.com", "/", ""},
-		{"http://example.com", "/path", "q=1"},
-		{"unix:///tmp/socket", "/api", "key=value"},
-		{"https://example.com:8080", "/path/to/resource", "a=1&b=2"},
-		{"http://example.com", "/path with spaces", "q=hello world"},
-		{"http://example.com", "/path/❤️/emoji", "emoji=🎉"},
-		{"http://example.com", "/path/../../../etc/passwd", ""},
-		{"http://example.com", "/path%2F%2E%2E%2F", "q=%3Cscript%3E"},
-		{"unix:///var/run/app.sock", "/../../etc/passwd", ""},
-		{"http://[::1]:8080", "/ipv6", "test=1"},
-		{"http://example.com", strings.Repeat("/very/long/path", 100), strings.Repeat("param=value&", 100)},
-		{"http://example.com", "/path%20with%20encoded", "q=%20encoded%20"},
-		{"http://example.com", "/пример/кириллица", "q=тест"},
-		{"http://example.com", "/中文/路径", "查询=值"},
-		{"", "/path", "q=1"}, // Empty target
-	}
-
-	for _, tc := range testCases {
-		f.Add(tc.target, tc.path, tc.query)
-	}
-
-	f.Fuzz(func(t *testing.T, target, path, query string) {
-		// Skip invalid UTF-8 to focus on realistic inputs
-		if !utf8.ValidString(target) || !utf8.ValidString(path) || !utf8.ValidString(query) {
-			t.Skip()
-		}
-
-		// Create cache - should not panic
-		cache := NewOGTagCache(target, false, 0, false)
-
-		// Create URL
-		u := &url.URL{
-			Path:     path,
-			RawQuery: query,
-		}
-
-		// Call getTarget - should not panic
-		result := cache.getTarget(u)
-
-		// Basic validation
-		if result == "" {
-			t.Errorf("getTarget returned empty string for target=%q, path=%q, query=%q", target, path, query)
-		}
-
-		// Verify result is a valid URL (for non-empty targets)
-		if target != "" {
-			parsedResult, err := url.Parse(result)
-			if err != nil {
-				t.Errorf("getTarget produced invalid URL %q: %v", result, err)
-			} else {
-				// For unix sockets, verify the scheme is http
-				if strings.HasPrefix(target, "unix:") && parsedResult.Scheme != "http" {
-					t.Errorf("Unix socket URL should have http scheme, got %q", parsedResult.Scheme)
-				}
-			}
-		}
-
-		// Ensure no memory corruption by calling multiple times
-		for i := 0; i < 3; i++ {
-			result2 := cache.getTarget(u)
-			if result != result2 {
-				t.Errorf("getTarget not deterministic: %q != %q", result, result2)
-			}
-		}
-	})
-}
-
-// FuzzExtractOGTags tests extractOGTags with various HTML inputs
-func FuzzExtractOGTags(f *testing.F) {
-	// Seed corpus with interesting HTML cases
-	htmlCases := []string{
-		`<html><head><meta property="og:title" content="Test"></head></html>`,
-		`<meta property="og:title" content="No HTML tags">`,
-		`<html><head>` + strings.Repeat(`<meta property="og:title" content="Many tags">`, 1000) + `</head></html>`,
-		`<html><head><meta property="og:title" content="<script>alert('xss')</script>"></head></html>`,
-		`<html><head><meta property="og:title" content="Line1&#10;Line2"></head></html>`,
-		`<html><head><meta property="og:emoji" content="❤️🎉🎊"></head></html>`,
-		`<html><head><meta property="og:title" content="` + strings.Repeat("A", 10000) + `"></head></html>`,
-		`<html><head><meta property="og:title" content='Single quotes'></head></html>`,
-		`<html><head><meta property=og:title content=no-quotes></head></html>`,
-		`<html><head><meta name="keywords" content="test,keywords"></head></html>`,
-		`<html><head><meta property="unknown:tag" content="Should be ignored"></head></html>`,
-		`<html><head><meta property="` + strings.Repeat("og:", 100) + `title" content="Nested prefixes"></head></html>`,
-		`<html>` + strings.Repeat(`<div>`, 1000) + `<meta property="og:title" content="Deep nesting">` + strings.Repeat(`</div>`, 1000) + `</html>`,
-		`<!DOCTYPE html><html xmlns="http://www.w3.org/1999/xhtml"><head><meta property="og:title" content="With doctype"/></head></html>`,
-		`<html><head><meta property="" content="Empty property"></head></html>`,
-		`<html><head><meta content="Content only"></head></html>`,
-		`<html><head><meta property="og:title"></head></html>`, // No content
-		``, // Empty HTML
-		`<html><head><meta property="og:title" content="Кириллица"></head></html>`,
-		`<html><head><meta property="og:title" content="中文内容"></head></html>`,
-		`<html><head><!--<meta property="og:title" content="Commented out">--></head></html>`,
-		`<html><head><META PROPERTY="OG:TITLE" CONTENT="UPPERCASE"></head></html>`,
-	}
-
-	for _, htmlc := range htmlCases {
-		f.Add(htmlc)
-	}
-
-	f.Fuzz(func(t *testing.T, htmlContent string) {
-		// Skip invalid UTF-8
-		if !utf8.ValidString(htmlContent) {
-			t.Skip()
-		}
-
-		// Parse HTML - may fail on invalid input
-		doc, err := html.Parse(strings.NewReader(htmlContent))
-		if err != nil {
-			// This is expected for malformed HTML
-			return
-		}
-
-		cache := NewOGTagCache("http://example.com", false, 0, false)
-
-		// Should not panic
-		tags := cache.extractOGTags(doc)
-
-		// Validate results
-		for property, content := range tags {
-			// Ensure property is approved
-			approved := false
-			for _, prefix := range cache.approvedPrefixes {
-				if strings.HasPrefix(property, prefix) {
-					approved = true
-					break
-				}
-			}
-			if !approved {
-				for _, tag := range cache.approvedTags {
-					if property == tag {
-						approved = true
-						break
-					}
-				}
-			}
-			if !approved {
-				t.Errorf("Unapproved property %q was extracted", property)
-			}
-
-			// Ensure content is valid string
-			if !utf8.ValidString(content) {
-				t.Errorf("Invalid UTF-8 in content for property %q", property)
-			}
-		}
-
-		// Test determinism
-		tags2 := cache.extractOGTags(doc)
-		if len(tags) != len(tags2) {
-			t.Errorf("extractOGTags not deterministic: different lengths %d != %d", len(tags), len(tags2))
-		}
-		for k, v := range tags {
-			if tags2[k] != v {
-				t.Errorf("extractOGTags not deterministic: %q=%q != %q=%q", k, v, k, tags2[k])
-			}
-		}
-	})
-}
-
-// FuzzGetTargetRoundTrip tests that getTarget produces valid URLs that can be parsed back
-func FuzzGetTargetRoundTrip(f *testing.F) {
-	f.Add("http://example.com", "/path/to/resource", "key=value&foo=bar")
-	f.Add("unix:///tmp/socket", "/api/endpoint", "param=test")
-
-	f.Fuzz(func(t *testing.T, target, path, query string) {
-		if !utf8.ValidString(target) || !utf8.ValidString(path) || !utf8.ValidString(query) {
-			t.Skip()
-		}
-
-		cache := NewOGTagCache(target, false, 0, false)
-		u := &url.URL{Path: path, RawQuery: query}
-
-		result := cache.getTarget(u)
-		if result == "" {
-			return
-		}
-
-		// Parse the result back
-		parsed, err := url.Parse(result)
-		if err != nil {
-			t.Errorf("getTarget produced unparseable URL: %v", err)
-			return
-		}
-
-		// For non-unix targets, verify path preservation (accounting for encoding)
-		if !strings.HasPrefix(target, "unix:") && target != "" {
-			// The paths should match after normalization
-			expectedPath := u.EscapedPath()
-			if parsed.EscapedPath() != expectedPath {
-				t.Errorf("Path not preserved: want %q, got %q", expectedPath, parsed.EscapedPath())
-			}
-
-			// Query should be preserved exactly
-			if parsed.RawQuery != query {
-				t.Errorf("Query not preserved: want %q, got %q", query, parsed.RawQuery)
-			}
-		}
-	})
-}
-
-// FuzzExtractMetaTagInfo tests the extractMetaTagInfo function directly
-func FuzzExtractMetaTagInfo(f *testing.F) {
-	// Seed with various attribute combinations
-	f.Add("og:title", "Test Title", "property")
-	f.Add("keywords", "test,keywords", "name")
-	f.Add("og:description", "A description with \"quotes\"", "property")
-	f.Add("twitter:card", "summary", "property")
-	f.Add("unknown:tag", "Should be filtered", "property")
-	f.Add("", "Content without property", "property")
-	f.Add("og:title", "", "property") // Property without content
-
-	f.Fuzz(func(t *testing.T, propertyValue, contentValue, propertyKey string) {
-		if !utf8.ValidString(propertyValue) || !utf8.ValidString(contentValue) || !utf8.ValidString(propertyKey) {
-			t.Skip()
-		}
-
-		// Create a meta node
-		node := &html.Node{
-			Type: html.ElementNode,
-			Data: "meta",
-			Attr: []html.Attribute{
-				{Key: propertyKey, Val: propertyValue},
-				{Key: "content", Val: contentValue},
-			},
-		}
-
-		cache := NewOGTagCache("http://example.com", false, 0, false)
-
-		// Should not panic
-		property, content := cache.extractMetaTagInfo(node)
-
-		// If property is returned, it must be approved
-		if property != "" {
-			approved := false
-			for _, prefix := range cache.approvedPrefixes {
-				if strings.HasPrefix(property, prefix) {
-					approved = true
-					break
-				}
-			}
-			if !approved {
-				for _, tag := range cache.approvedTags {
-					if property == tag {
-						approved = true
-						break
-					}
-				}
-			}
-			if !approved {
-				t.Errorf("extractMetaTagInfo returned unapproved property: %q", property)
-			}
-		}
-
-		// Content should match input if property is approved
-		if property != "" && content != contentValue {
-			t.Errorf("Content mismatch: want %q, got %q", contentValue, content)
-		}
-	})
-}
-
-// Benchmark comparison for the fuzzed scenarios
-func BenchmarkFuzzedGetTarget(b *testing.B) {
-	// Test with various challenging inputs found during fuzzing
-	inputs := []struct {
-		name   string
-		target string
-		path   string
-		query  string
-	}{
-		{"Simple", "http://example.com", "/api", "k=v"},
-		{"LongPath", "http://example.com", strings.Repeat("/segment", 50), ""},
-		{"LongQuery", "http://example.com", "/", strings.Repeat("param=value&", 50)},
-		{"Unicode", "http://example.com", "/путь/路径/path", "q=значение"},
-		{"Encoded", "http://example.com", "/path%20with%20spaces", "q=%3Cscript%3E"},
-		{"Unix", "unix:///tmp/socket.sock", "/api/v1/resource", "id=123&format=json"},
-	}
-
-	for _, input := range inputs {
-		b.Run(input.name, func(b *testing.B) {
-			cache := NewOGTagCache(input.target, false, 0, false)
-			u := &url.URL{Path: input.path, RawQuery: input.query}
-
-			b.ResetTimer()
-			b.ReportAllocs()
-
-			for i := 0; i < b.N; i++ {
-				_ = cache.getTarget(u)
-			}
-		})
-	}
-}

internal/ogtags/parse.go

@@ -12,12 +12,15 @@ func (c *OGTagCache) extractOGTags(doc *html.Node) map[string]string {
 
 	var traverseNodes func(*html.Node)
 	traverseNodes = func(n *html.Node) {
+		// isOGMetaTag only checks if it's a <meta> tag.
+		// The actual filtering happens in extractMetaTagInfo now.
 		if isOGMetaTag(n) {
 			property, content := c.extractMetaTagInfo(n)
 			if property != "" {
 				ogTags[property] = content
 			}
 		}
+
 		for child := n.FirstChild; child != nil; child = child.NextSibling {
 			traverseNodes(child)
 		}
@@ -36,40 +39,43 @@ func isOGMetaTag(n *html.Node) bool {
 }
 
 // extractMetaTagInfo extracts property and content from a meta tag
+// *and* checks if the property is approved.
+// Returns empty property string if the tag is not approved.
 func (c *OGTagCache) extractMetaTagInfo(n *html.Node) (property, content string) {
-	var propertyKey string
+	var rawProperty string // Store the property found before approval check
 
-	// Single pass through attributes, using range to avoid bounds checking
 	for _, attr := range n.Attr {
-		switch attr.Key {
-		case "property", "name":
-			propertyKey = attr.Val
-		case "content":
+		if attr.Key == "property" || attr.Key == "name" {
+			rawProperty = attr.Val
+		}
+		if attr.Key == "content" {
 			content = attr.Val
 		}
-		// Early exit if we have both
-		if propertyKey != "" && content != "" {
+	}
+
+	// Check if the rawProperty is approved
+	isApproved := false
+	for _, prefix := range c.approvedPrefixes {
+		if strings.HasPrefix(rawProperty, prefix) {
+			isApproved = true
 			break
 		}
 	}
-
-	if propertyKey == "" {
-		return "", content
-	}
-
-	// Check prefixes first (more common case)
-	for _, prefix := range c.approvedPrefixes {
-		if strings.HasPrefix(propertyKey, prefix) {
-			return propertyKey, content
+	// Check exact approved tags if not already approved by prefix
+	if !isApproved {
+		for _, tag := range c.approvedTags {
+			if rawProperty == tag {
+				isApproved = true
+				break
+			}
 		}
 	}
 
-	// Check exact matches
-	for _, tag := range c.approvedTags {
-		if propertyKey == tag {
-			return propertyKey, content
-		}
+	// Only return the property if it's approved
+	if isApproved {
+		property = rawProperty
 	}
 
-	return "", content
+	// Content is returned regardless, but property will be "" if not approved
+	return property, content
 }

internal/test/playwright_test.go

@@ -595,7 +595,7 @@ func spawnAnubisWithOptions(t *testing.T, basePrefix string) string {
 		fmt.Fprintf(w, "<html><body><span id=anubis-test>%d</span></body></html>", time.Now().Unix())
 	})
 
-	policy, err := libanubis.LoadPoliciesOrDefault(t.Context(), "", anubis.DefaultDifficulty)
+	policy, err := libanubis.LoadPoliciesOrDefault("", anubis.DefaultDifficulty)
 	if err != nil {
 		t.Fatal(err)
 	}

internal/thoth/asnchecker.go

@@ -1,69 +0,0 @@
-package thoth
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"log/slog"
-	"net/http"
-	"strings"
-	"time"
-
-	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-)
-
-func (c *Client) ASNCheckerFor(asns []uint32) checker.Impl {
-	asnMap := map[uint32]struct{}{}
-	var sb strings.Builder
-	fmt.Fprintln(&sb, "ASNChecker")
-	for _, asn := range asns {
-		asnMap[asn] = struct{}{}
-		fmt.Fprintln(&sb, "AS", asn)
-	}
-
-	return &ASNChecker{
-		iptoasn: c.IPToASN,
-		asns:    asnMap,
-		hash:    internal.FastHash(sb.String()),
-	}
-}
-
-type ASNChecker struct {
-	iptoasn iptoasnv1.IpToASNServiceClient
-	asns    map[uint32]struct{}
-	hash    string
-}
-
-func (asnc *ASNChecker) Check(r *http.Request) (bool, error) {
-	ctx, cancel := context.WithTimeout(r.Context(), 500*time.Millisecond)
-	defer cancel()
-
-	ipInfo, err := asnc.iptoasn.Lookup(ctx, &iptoasnv1.LookupRequest{
-		IpAddress: r.Header.Get("X-Real-Ip"),
-	})
-	if err != nil {
-		switch {
-		case errors.Is(err, context.DeadlineExceeded):
-			slog.Debug("error contacting thoth", "err", err, "actionable", false)
-			return false, nil
-		default:
-			slog.Error("error contacting thoth, please contact support", "err", err, "actionable", true)
-			return false, nil
-		}
-	}
-
-	// If IP is not publicly announced, return false
-	if !ipInfo.GetAnnounced() {
-		return false, nil
-	}
-
-	_, ok := asnc.asns[uint32(ipInfo.GetAsNumber())]
-
-	return ok, nil
-}
-
-func (asnc *ASNChecker) Hash() string {
-	return asnc.hash
-}

internal/thoth/asnchecker_test.go

@@ -1,81 +0,0 @@
-package thoth_test
-
-import (
-	"fmt"
-	"net/http/httptest"
-	"testing"
-
-	"github.com/TecharoHQ/anubis/internal/thoth"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-)
-
-var _ checker.Impl = &thoth.ASNChecker{}
-
-func TestASNChecker(t *testing.T) {
-	cli := loadSecrets(t)
-
-	asnc := cli.ASNCheckerFor([]uint32{13335})
-
-	for _, cs := range []struct {
-		ipAddress string
-		wantMatch bool
-		wantError bool
-	}{
-		{
-			ipAddress: "1.1.1.1",
-			wantMatch: true,
-			wantError: false,
-		},
-		{
-			ipAddress: "2.2.2.2",
-			wantMatch: false,
-			wantError: false,
-		},
-		{
-			ipAddress: "taco",
-			wantMatch: false,
-			wantError: false,
-		},
-		{
-			ipAddress: "127.0.0.1",
-			wantMatch: false,
-			wantError: false,
-		},
-	} {
-		t.Run(fmt.Sprintf("%v", cs), func(t *testing.T) {
-			req := httptest.NewRequest("GET", "/", nil)
-			req.Header.Set("X-Real-Ip", cs.ipAddress)
-
-			match, err := asnc.Check(req)
-
-			if match != cs.wantMatch {
-				t.Errorf("Wanted match: %v, got: %v", cs.wantMatch, match)
-			}
-
-			switch {
-			case err != nil && !cs.wantError:
-				t.Errorf("Did not want error but got: %v", err)
-			case err == nil && cs.wantError:
-				t.Error("Wanted error but got none")
-			}
-		})
-	}
-}
-
-func BenchmarkWithCache(b *testing.B) {
-	cli := loadSecrets(b)
-	req := &iptoasnv1.LookupRequest{IpAddress: "1.1.1.1"}
-
-	_, err := cli.IPToASN.Lookup(b.Context(), req)
-	if err != nil {
-		b.Error(err)
-	}
-
-	for b.Loop() {
-		_, err := cli.IPToASN.Lookup(b.Context(), req)
-		if err != nil {
-			b.Error(err)
-		}
-	}
-}

internal/thoth/auth.go

@@ -1,39 +0,0 @@
-package thoth
-
-import (
-	"context"
-
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/metadata"
-)
-
-func authUnaryClientInterceptor(token string) grpc.UnaryClientInterceptor {
-	return func(
-		ctx context.Context,
-		method string,
-		req interface{},
-		reply interface{},
-		cc *grpc.ClientConn,
-		invoker grpc.UnaryInvoker,
-		opts ...grpc.CallOption,
-	) error {
-		md := metadata.Pairs("authorization", "Bearer "+token)
-		ctx = metadata.NewOutgoingContext(ctx, md)
-		return invoker(ctx, method, req, reply, cc, opts...)
-	}
-}
-
-func authStreamClientInterceptor(token string) grpc.StreamClientInterceptor {
-	return func(
-		ctx context.Context,
-		desc *grpc.StreamDesc,
-		cc *grpc.ClientConn,
-		method string,
-		streamer grpc.Streamer,
-		opts ...grpc.CallOption,
-	) (grpc.ClientStream, error) {
-		md := metadata.Pairs("authorization", "Bearer "+token)
-		ctx = metadata.NewOutgoingContext(ctx, md)
-		return streamer(ctx, desc, cc, method, opts...)
-	}
-}

internal/thoth/cachediptoasn.go

@@ -1,84 +0,0 @@
-package thoth
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"log/slog"
-	"net/netip"
-
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-	"github.com/gaissmai/bart"
-	"google.golang.org/grpc"
-)
-
-type IPToASNWithCache struct {
-	next  iptoasnv1.IpToASNServiceClient
-	table *bart.Table[*iptoasnv1.LookupResponse]
-}
-
-func NewIpToASNWithCache(next iptoasnv1.IpToASNServiceClient) *IPToASNWithCache {
-	result := &IPToASNWithCache{
-		next:  next,
-		table: &bart.Table[*iptoasnv1.LookupResponse]{},
-	}
-
-	for _, pfx := range []netip.Prefix{
-		netip.MustParsePrefix("10.0.0.0/8"),         // RFC 1918
-		netip.MustParsePrefix("172.16.0.0/12"),      // RFC 1918
-		netip.MustParsePrefix("192.168.0.0/16"),     // RFC 1918
-		netip.MustParsePrefix("127.0.0.0/8"),        // Loopback
-		netip.MustParsePrefix("169.254.0.0/16"),     // Link-local
-		netip.MustParsePrefix("100.64.0.0/10"),      // CGNAT
-		netip.MustParsePrefix("192.0.0.0/24"),       // Protocol assignments
-		netip.MustParsePrefix("192.0.2.0/24"),       // TEST-NET-1
-		netip.MustParsePrefix("198.18.0.0/15"),      // Benchmarking
-		netip.MustParsePrefix("198.51.100.0/24"),    // TEST-NET-2
-		netip.MustParsePrefix("203.0.113.0/24"),     // TEST-NET-3
-		netip.MustParsePrefix("240.0.0.0/4"),        // Reserved
-		netip.MustParsePrefix("255.255.255.255/32"), // Broadcast
-		netip.MustParsePrefix("fc00::/7"),           // Unique local address
-		netip.MustParsePrefix("fe80::/10"),          // Link-local
-		netip.MustParsePrefix("::1/128"),            // Loopback
-		netip.MustParsePrefix("::/128"),             // Unspecified
-		netip.MustParsePrefix("100::/64"),           // Discard-only
-		netip.MustParsePrefix("2001:db8::/32"),      // Documentation
-	} {
-		result.table.Insert(pfx, &iptoasnv1.LookupResponse{Announced: false})
-	}
-
-	return result
-}
-
-func (ip2asn *IPToASNWithCache) Lookup(ctx context.Context, lr *iptoasnv1.LookupRequest, opts ...grpc.CallOption) (*iptoasnv1.LookupResponse, error) {
-	addr, err := netip.ParseAddr(lr.GetIpAddress())
-	if err != nil {
-		return nil, fmt.Errorf("input is not an IP address: %w", err)
-	}
-
-	cachedResponse, ok := ip2asn.table.Lookup(addr)
-	if ok {
-		return cachedResponse, nil
-	}
-
-	resp, err := ip2asn.next.Lookup(ctx, lr, opts...)
-	if err != nil {
-		return nil, err
-	}
-
-	var errs []error
-	for _, cidr := range resp.GetCidr() {
-		pfx, err := netip.ParsePrefix(cidr)
-		if err != nil {
-			errs = append(errs, err)
-			continue
-		}
-		ip2asn.table.Insert(pfx, resp)
-	}
-
-	if len(errs) != 0 {
-		slog.Error("errors parsing IP prefixes", "err", errors.Join(errs...))
-	}
-
-	return resp, nil
-}

internal/thoth/context.go

@@ -1,14 +0,0 @@
-package thoth
-
-import "context"
-
-type ctxKey struct{}
-
-func With(ctx context.Context, cli *Client) context.Context {
-	return context.WithValue(ctx, ctxKey{}, cli)
-}
-
-func FromContext(ctx context.Context) (*Client, bool) {
-	cli, ok := ctx.Value(ctxKey{}).(*Client)
-	return cli, ok
-}

internal/thoth/geoipchecker.go

@@ -1,68 +0,0 @@
-package thoth
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"log/slog"
-	"net/http"
-	"strings"
-	"time"
-
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-)
-
-func (c *Client) GeoIPCheckerFor(countries []string) checker.Impl {
-	countryMap := map[string]struct{}{}
-	var sb strings.Builder
-	fmt.Fprintln(&sb, "GeoIPChecker")
-	for _, cc := range countries {
-		countryMap[cc] = struct{}{}
-		fmt.Fprintln(&sb, cc)
-	}
-
-	return &GeoIPChecker{
-		IPToASN:   c.IPToASN,
-		Countries: countryMap,
-		hash:      sb.String(),
-	}
-}
-
-type GeoIPChecker struct {
-	IPToASN   iptoasnv1.IpToASNServiceClient
-	Countries map[string]struct{}
-	hash      string
-}
-
-func (gipc *GeoIPChecker) Check(r *http.Request) (bool, error) {
-	ctx, cancel := context.WithTimeout(r.Context(), 500*time.Millisecond)
-	defer cancel()
-
-	ipInfo, err := gipc.IPToASN.Lookup(ctx, &iptoasnv1.LookupRequest{
-		IpAddress: r.Header.Get("X-Real-Ip"),
-	})
-	if err != nil {
-		switch {
-		case errors.Is(err, context.DeadlineExceeded):
-			slog.Debug("error contacting thoth", "err", err, "actionable", false)
-			return false, nil
-		default:
-			slog.Error("error contacting thoth, please contact support", "err", err, "actionable", true)
-			return false, nil
-		}
-	}
-
-	// If IP is not publicly announced, return false
-	if !ipInfo.GetAnnounced() {
-		return false, nil
-	}
-
-	_, ok := gipc.Countries[strings.ToLower(ipInfo.GetCountryCode())]
-
-	return ok, nil
-}
-
-func (gipc *GeoIPChecker) Hash() string {
-	return gipc.hash
-}

internal/thoth/geoipchecker_test.go

@@ -1,63 +0,0 @@
-package thoth_test
-
-import (
-	"fmt"
-	"net/http/httptest"
-	"testing"
-
-	"github.com/TecharoHQ/anubis/internal/thoth"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
-)
-
-var _ checker.Impl = &thoth.GeoIPChecker{}
-
-func TestGeoIPChecker(t *testing.T) {
-	cli := loadSecrets(t)
-
-	asnc := cli.GeoIPCheckerFor([]string{"us"})
-
-	for _, cs := range []struct {
-		ipAddress string
-		wantMatch bool
-		wantError bool
-	}{
-		{
-			ipAddress: "1.1.1.1",
-			wantMatch: true,
-			wantError: false,
-		},
-		{
-			ipAddress: "2.2.2.2",
-			wantMatch: false,
-			wantError: false,
-		},
-		{
-			ipAddress: "taco",
-			wantMatch: false,
-			wantError: false,
-		},
-		{
-			ipAddress: "127.0.0.1",
-			wantMatch: false,
-			wantError: false,
-		},
-	} {
-		t.Run(fmt.Sprintf("%v", cs), func(t *testing.T) {
-			req := httptest.NewRequest("GET", "/", nil)
-			req.Header.Set("X-Real-Ip", cs.ipAddress)
-
-			match, err := asnc.Check(req)
-
-			if match != cs.wantMatch {
-				t.Errorf("Wanted match: %v, got: %v", cs.wantMatch, match)
-			}
-
-			switch {
-			case err != nil && !cs.wantError:
-				t.Errorf("Did not want error but got: %v", err)
-			case err == nil && cs.wantError:
-				t.Error("Wanted error but got none")
-			}
-		})
-	}
-}

internal/thoth/thoth.go

@@ -1,88 +0,0 @@
-package thoth
-
-import (
-	"context"
-	"crypto/tls"
-	"fmt"
-	"time"
-
-	"github.com/TecharoHQ/anubis"
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-	grpcprom "github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus"
-	"github.com/grpc-ecosystem/go-grpc-middleware/v2/interceptors/timeout"
-	"github.com/prometheus/client_golang/prometheus"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials"
-	"google.golang.org/grpc/credentials/insecure"
-	healthv1 "google.golang.org/grpc/health/grpc_health_v1"
-)
-
-type Client struct {
-	conn    *grpc.ClientConn
-	health  healthv1.HealthClient
-	IPToASN iptoasnv1.IpToASNServiceClient
-}
-
-func New(ctx context.Context, thothURL, apiToken string, plaintext bool) (*Client, error) {
-	clMetrics := grpcprom.NewClientMetrics(
-		grpcprom.WithClientHandlingTimeHistogram(
-			grpcprom.WithHistogramBuckets([]float64{0.001, 0.01, 0.1, 0.3, 0.6, 1, 3, 6, 9, 20, 30, 60, 90, 120}),
-		),
-	)
-	prometheus.DefaultRegisterer.Register(clMetrics)
-
-	do := []grpc.DialOption{
-		grpc.WithChainUnaryInterceptor(
-			timeout.UnaryClientInterceptor(500*time.Millisecond),
-			clMetrics.UnaryClientInterceptor(),
-			authUnaryClientInterceptor(apiToken),
-		),
-		grpc.WithChainStreamInterceptor(
-			clMetrics.StreamClientInterceptor(),
-			authStreamClientInterceptor(apiToken),
-		),
-		grpc.WithUserAgent(fmt.Sprint("Techaro/anubis:", anubis.Version)),
-	}
-
-	if plaintext {
-		do = append(do, grpc.WithTransportCredentials(insecure.NewCredentials()))
-	} else {
-		do = append(do, grpc.WithTransportCredentials(credentials.NewTLS(&tls.Config{})))
-	}
-
-	conn, err := grpc.NewClient(
-		thothURL,
-		do...,
-	)
-	if err != nil {
-		return nil, fmt.Errorf("can't dial thoth at %s: %w", thothURL, err)
-	}
-
-	hc := healthv1.NewHealthClient(conn)
-
-	resp, err := hc.Check(ctx, &healthv1.HealthCheckRequest{})
-	if err != nil {
-		return nil, fmt.Errorf("can't verify thoth health at %s: %w", thothURL, err)
-	}
-
-	if resp.Status != healthv1.HealthCheckResponse_SERVING {
-		return nil, fmt.Errorf("thoth is not healthy, wanted %s but got %s", healthv1.HealthCheckResponse_SERVING, resp.Status)
-	}
-
-	return &Client{
-		conn:    conn,
-		health:  hc,
-		IPToASN: NewIpToASNWithCache(iptoasnv1.NewIpToASNServiceClient(conn)),
-	}, nil
-}
-
-func (c *Client) Close() error {
-	if c.conn != nil {
-		return c.conn.Close()
-	}
-	return nil
-}
-
-func (c *Client) WithIPToASNService(impl iptoasnv1.IpToASNServiceClient) {
-	c.IPToASN = impl
-}

internal/thoth/thoth_test.go

@@ -1,36 +0,0 @@
-package thoth_test
-
-import (
-	"os"
-	"testing"
-
-	"github.com/TecharoHQ/anubis/internal/thoth"
-	"github.com/TecharoHQ/anubis/internal/thoth/thothmock"
-	"github.com/joho/godotenv"
-)
-
-func loadSecrets(t testing.TB) *thoth.Client {
-	t.Helper()
-
-	if err := godotenv.Load(); err != nil {
-		t.Log("using mock thoth")
-		result := &thoth.Client{}
-		result.WithIPToASNService(thothmock.MockIpToASNService())
-		return result
-	}
-
-	cli, err := thoth.New(t.Context(), os.Getenv("THOTH_URL"), os.Getenv("THOTH_API_KEY"), false)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return cli
-}
-
-func TestNew(t *testing.T) {
-	cli := loadSecrets(t)
-
-	if err := cli.Close(); err != nil {
-		t.Fatal(err)
-	}
-}

internal/thoth/thothmock/iptoasn.go

@@ -1,59 +0,0 @@
-package thothmock
-
-import (
-	"context"
-	"net/netip"
-
-	iptoasnv1 "github.com/TecharoHQ/thoth-proto/gen/techaro/thoth/iptoasn/v1"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/codes"
-	"google.golang.org/grpc/status"
-)
-
-func MockIpToASNService() *IpToASNService {
-	responses := map[string]*iptoasnv1.LookupResponse{
-		"127.0.0.1": {Announced: false},
-		"::1":       {Announced: false},
-		"10.10.10.10": {
-			Announced:   true,
-			AsNumber:    13335,
-			Cidr:        []string{"1.1.1.0/24"},
-			CountryCode: "US",
-			Description: "Cloudflare",
-		},
-		"2.2.2.2": {
-			Announced:   true,
-			AsNumber:    420,
-			Cidr:        []string{"2.2.2.0/24"},
-			CountryCode: "CA",
-			Description: "test canada",
-		},
-		"1.1.1.1": {
-			Announced:   true,
-			AsNumber:    13335,
-			Cidr:        []string{"1.1.1.0/24"},
-			CountryCode: "US",
-			Description: "Cloudflare",
-		},
-	}
-
-	return &IpToASNService{Responses: responses}
-}
-
-type IpToASNService struct {
-	iptoasnv1.UnimplementedIpToASNServiceServer
-	Responses map[string]*iptoasnv1.LookupResponse
-}
-
-func (ip2asn *IpToASNService) Lookup(ctx context.Context, lr *iptoasnv1.LookupRequest, opts ...grpc.CallOption) (*iptoasnv1.LookupResponse, error) {
-	if _, err := netip.ParseAddr(lr.GetIpAddress()); err != nil {
-		return nil, err
-	}
-
-	resp, ok := ip2asn.Responses[lr.GetIpAddress()]
-	if !ok {
-		return nil, status.Error(codes.NotFound, "IP address not found in mock")
-	}
-
-	return resp, nil
-}

internal/thoth/thothmock/withthothmock.go

@@ -1,17 +0,0 @@
-package thothmock
-
-import (
-	"context"
-	"testing"
-
-	"github.com/TecharoHQ/anubis/internal/thoth"
-)
-
-func WithMockThoth(t *testing.T) context.Context {
-	t.Helper()
-
-	thothCli := &thoth.Client{}
-	thothCli.WithIPToASNService(MockIpToASNService())
-	ctx := thoth.With(t.Context(), thothCli)
-	return ctx
-}

lib/anubis.go

@@ -26,7 +26,6 @@ import (
 	"github.com/TecharoHQ/anubis/internal/ogtags"
 	"github.com/TecharoHQ/anubis/lib/challenge"
 	"github.com/TecharoHQ/anubis/lib/policy"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
 	"github.com/TecharoHQ/anubis/lib/policy/config"
 
 	// challenge implementations
@@ -90,7 +89,7 @@ func (s *Server) challengeFor(r *http.Request, difficulty int) string {
 		fp,
 		difficulty,
 	)
-	return internal.FastHash(challengeData)
+	return internal.SHA256sum(challengeData)
 }
 
 func (s *Server) maybeReverseProxyHttpStatusOnly(w http.ResponseWriter, r *http.Request) {
@@ -289,15 +288,15 @@ func (s *Server) MakeChallenge(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	lg = lg.With("check_result", cr)
-	chal := s.challengeFor(r, rule.Challenge.Difficulty)
+	challenge := s.challengeFor(r, rule.Challenge.Difficulty)
 
-	s.SetCookie(w, anubis.TestCookieName, chal, "/")
+	s.SetCookie(w, anubis.TestCookieName, challenge, "/")
 
 	err = encoder.Encode(struct {
 		Rules     *config.ChallengeRules `json:"rules"`
 		Challenge string                 `json:"challenge"`
 	}{
-		Challenge: chal,
+		Challenge: challenge,
 		Rules:     rule.Challenge,
 	})
 	if err != nil {
@@ -305,7 +304,7 @@ func (s *Server) MakeChallenge(w http.ResponseWriter, r *http.Request) {
 		w.WriteHeader(http.StatusInternalServerError)
 		return
 	}
-	lg.Debug("made challenge", "challenge", chal, "rules", rule.Challenge, "cr", cr)
+	lg.Debug("made challenge", "challenge", challenge, "rules", rule.Challenge, "cr", cr)
 	challengesIssued.WithLabelValues("api").Inc()
 }
 
@@ -318,7 +317,7 @@ func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {
 		cookiePath = strings.TrimSuffix(anubis.BasePrefix, "/") + "/"
 	}
 
-	if _, err := r.Cookie(anubis.TestCookieName); errors.Is(err, http.ErrNoCookie) {
+	if _, err := r.Cookie(anubis.TestCookieName); err == http.ErrNoCookie {
 		s.ClearCookie(w, s.cookieName, cookiePath)
 		s.ClearCookie(w, anubis.TestCookieName, "/")
 		lg.Warn("user has cookies disabled, this is not an anubis bug")
@@ -366,7 +365,7 @@ func (s *Server) PassChallenge(w http.ResponseWriter, r *http.Request) {
 	challengeStr := s.challengeFor(r, rule.Challenge.Difficulty)
 
 	if err := impl.Validate(r, lg, rule, challengeStr); err != nil {
-		failedValidations.WithLabelValues(rule.Challenge.Algorithm).Inc()
+		failedValidations.WithLabelValues(string(rule.Challenge.Algorithm)).Inc()
 		var cerr *challenge.Error
 		s.ClearCookie(w, s.cookieName, cookiePath)
 		lg.Debug("challenge validate call failed", "err", err)
@@ -484,7 +483,7 @@ func (s *Server) check(r *http.Request) (policy.CheckResult, *policy.Bot, error)
 			ReportAs:   s.policy.DefaultDifficulty,
 			Algorithm:  config.DefaultAlgorithm,
 		},
-		Rules: &checker.List{},
+		Rules: &policy.CheckerList{},
 	}, nil
 }
 

lib/anubis_test.go

@@ -15,7 +15,6 @@ import (
 	"github.com/TecharoHQ/anubis"
 	"github.com/TecharoHQ/anubis/data"
 	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/internal/thoth/thothmock"
 	"github.com/TecharoHQ/anubis/lib/policy"
 	"github.com/TecharoHQ/anubis/lib/policy/config"
 )
@@ -27,9 +26,7 @@ func init() {
 func loadPolicies(t *testing.T, fname string) *policy.ParsedConfig {
 	t.Helper()
 
-	ctx := thothmock.WithMockThoth(t)
-
-	anubisPolicy, err := LoadPoliciesOrDefault(ctx, fname, anubis.DefaultDifficulty)
+	anubisPolicy, err := LoadPoliciesOrDefault(fname, anubis.DefaultDifficulty)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -167,7 +164,7 @@ func TestLoadPolicies(t *testing.T) {
 			}
 			defer fin.Close()
 
-			if _, err := policy.ParseConfig(t.Context(), fin, fname, 4); err != nil {
+			if _, err := policy.ParseConfig(fin, fname, 4); err != nil {
 				t.Fatal(err)
 			}
 		})
@@ -316,7 +313,7 @@ func TestCheckDefaultDifficultyMatchesPolicy(t *testing.T) {
 
 	for i := 1; i < 10; i++ {
 		t.Run(fmt.Sprint(i), func(t *testing.T) {
-			anubisPolicy, err := LoadPoliciesOrDefault(t.Context(), "", i)
+			anubisPolicy, err := LoadPoliciesOrDefault("", i)
 			if err != nil {
 				t.Fatal(err)
 			}
@@ -635,102 +632,3 @@ func TestRuleChange(t *testing.T) {
 		t.Errorf("wanted %d, got: %d", http.StatusFound, resp.StatusCode)
 	}
 }
-
-func TestStripBasePrefixFromRequest(t *testing.T) {
-	testCases := []struct {
-		name            string
-		basePrefix      string
-		stripBasePrefix bool
-		requestPath     string
-		expectedPath    string
-	}{
-		{
-			name:            "strip disabled - no change",
-			basePrefix:      "/foo",
-			stripBasePrefix: false,
-			requestPath:     "/foo/bar",
-			expectedPath:    "/foo/bar",
-		},
-		{
-			name:            "strip enabled - removes prefix",
-			basePrefix:      "/foo",
-			stripBasePrefix: true,
-			requestPath:     "/foo/bar",
-			expectedPath:    "/bar",
-		},
-		{
-			name:            "strip enabled - root becomes slash",
-			basePrefix:      "/foo",
-			stripBasePrefix: true,
-			requestPath:     "/foo",
-			expectedPath:    "/",
-		},
-		{
-			name:            "strip enabled - trailing slash on base prefix",
-			basePrefix:      "/foo/",
-			stripBasePrefix: true,
-			requestPath:     "/foo/bar",
-			expectedPath:    "/bar",
-		},
-		{
-			name:            "strip enabled - no prefix match",
-			basePrefix:      "/foo",
-			stripBasePrefix: true,
-			requestPath:     "/other/bar",
-			expectedPath:    "/other/bar",
-		},
-		{
-			name:            "strip enabled - empty base prefix",
-			basePrefix:      "",
-			stripBasePrefix: true,
-			requestPath:     "/foo/bar",
-			expectedPath:    "/foo/bar",
-		},
-		{
-			name:            "strip enabled - nested path",
-			basePrefix:      "/app",
-			stripBasePrefix: true,
-			requestPath:     "/app/api/v1/users",
-			expectedPath:    "/api/v1/users",
-		},
-		{
-			name:            "strip enabled - exact match becomes root",
-			basePrefix:      "/myapp",
-			stripBasePrefix: true,
-			requestPath:     "/myapp/",
-			expectedPath:    "/",
-		},
-	}
-
-	for _, tc := range testCases {
-		t.Run(tc.name, func(t *testing.T) {
-			srv := &Server{
-				opts: Options{
-					BasePrefix:      tc.basePrefix,
-					StripBasePrefix: tc.stripBasePrefix,
-				},
-			}
-
-			req := httptest.NewRequest(http.MethodGet, tc.requestPath, nil)
-			originalPath := req.URL.Path
-
-			result := srv.stripBasePrefixFromRequest(req)
-
-			if result.URL.Path != tc.expectedPath {
-				t.Errorf("expected path %q, got %q", tc.expectedPath, result.URL.Path)
-			}
-
-			// Ensure original request is not modified when no stripping should occur
-			if !tc.stripBasePrefix || tc.basePrefix == "" || !strings.HasPrefix(tc.requestPath, strings.TrimSuffix(tc.basePrefix, "/")) {
-				if result != req {
-					t.Error("expected same request object when no modification needed")
-				}
-			} else {
-				// Ensure original request is not modified when stripping occurs
-				if req.URL.Path != originalPath {
-					t.Error("original request was modified")
-				}
-			}
-		})
-	}
-}

lib/challenge/error.go

@@ -22,9 +22,9 @@ func NewError(verb, publicReason string, privateReason error) *Error {
 }
 
 type Error struct {
-	PrivateReason error
 	Verb          string
 	PublicReason  string
+	PrivateReason error
 	StatusCode    int
 }
 

lib/config.go

@@ -1,7 +1,6 @@
 package lib
 
 import (
-	"context"
 	"crypto/ed25519"
 	"crypto/rand"
 	"errors"
@@ -37,14 +36,13 @@ type Options struct {
 	PrivateKey           ed25519.PrivateKey
 	CookieExpiration     time.Duration
 	OGTimeToLive         time.Duration
-	StripBasePrefix      bool
 	OGCacheConsidersHost bool
 	OGPassthrough        bool
 	CookiePartitioned    bool
 	ServeRobotsTXT       bool
 }
 
-func LoadPoliciesOrDefault(ctx context.Context, fname string, defaultDifficulty int) (*policy.ParsedConfig, error) {
+func LoadPoliciesOrDefault(fname string, defaultDifficulty int) (*policy.ParsedConfig, error) {
 	var fin io.ReadCloser
 	var err error
 
@@ -68,10 +66,7 @@ func LoadPoliciesOrDefault(ctx context.Context, fname string, defaultDifficulty
 		}
 	}(fin)
 
-	anubisPolicy, err := policy.ParseConfig(ctx, fin, fname, defaultDifficulty)
-	if err != nil {
-		return nil, fmt.Errorf("can't parse policy file %s: %w", fname, err)
-	}
+	anubisPolicy, err := policy.ParseConfig(fin, fname, defaultDifficulty)
 	var validationErrs []error
 
 	for _, b := range anubisPolicy.Bots {
@@ -159,7 +154,7 @@ func New(opts Options) (*Server, error) {
 		// make-challenge is only used in tests. Only enable while version is devel
 		registerWithPrefix(anubis.APIPrefix+"make-challenge", http.HandlerFunc(result.MakeChallenge), "POST")
 	}
-
+  
 	for _, implKind := range challenge.Methods() {
 		impl, _ := challenge.Get(implKind)
 		impl.Setup(mux)

lib/config_test.go

@@ -7,12 +7,11 @@ import (
 	"testing"
 
 	"github.com/TecharoHQ/anubis"
-	"github.com/TecharoHQ/anubis/internal/thoth/thothmock"
 	"github.com/TecharoHQ/anubis/lib/policy"
 )
 
 func TestInvalidChallengeMethod(t *testing.T) {
-	if _, err := LoadPoliciesOrDefault(t.Context(), "testdata/invalid-challenge-method.yaml", 4); !errors.Is(err, policy.ErrChallengeRuleHasWrongAlgorithm) {
+	if _, err := LoadPoliciesOrDefault("testdata/invalid-challenge-method.yaml", 4); !errors.Is(err, policy.ErrChallengeRuleHasWrongAlgorithm) {
 		t.Fatalf("wanted error %v but got %v", policy.ErrChallengeRuleHasWrongAlgorithm, err)
 	}
 }
@@ -26,7 +25,7 @@ func TestBadConfigs(t *testing.T) {
 	for _, st := range finfos {
 		st := st
 		t.Run(st.Name(), func(t *testing.T) {
-			if _, err := LoadPoliciesOrDefault(t.Context(), filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err == nil {
+			if _, err := LoadPoliciesOrDefault(filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err == nil {
 				t.Fatal(err)
 			} else {
 				t.Log(err)
@@ -44,18 +43,9 @@ func TestGoodConfigs(t *testing.T) {
 	for _, st := range finfos {
 		st := st
 		t.Run(st.Name(), func(t *testing.T) {
-			t.Run("with-thoth", func(t *testing.T) {
-				ctx := thothmock.WithMockThoth(t)
-				if _, err := LoadPoliciesOrDefault(ctx, filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err != nil {
-					t.Fatal(err)
-				}
-			})
-
-			t.Run("without-thoth", func(t *testing.T) {
-				if _, err := LoadPoliciesOrDefault(t.Context(), filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err != nil {
-					t.Fatal(err)
-				}
-			})
+			if _, err := LoadPoliciesOrDefault(filepath.Join("policy", "config", "testdata", "good", st.Name()), anubis.DefaultDifficulty); err != nil {
+				t.Fatal(err)
+			}
 		})
 	}
 }

lib/http.go

@@ -134,32 +134,6 @@ func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	s.mux.ServeHTTP(w, r)
 }
 
-func (s *Server) stripBasePrefixFromRequest(r *http.Request) *http.Request {
-	if !s.opts.StripBasePrefix || s.opts.BasePrefix == "" {
-		return r
-	}
-
-	basePrefix := strings.TrimSuffix(s.opts.BasePrefix, "/")
-	path := r.URL.Path
-
-	if !strings.HasPrefix(path, basePrefix) {
-		return r
-	}
-
-	trimmedPath := strings.TrimPrefix(path, basePrefix)
-	if trimmedPath == "" {
-		trimmedPath = "/"
-	}
-
-	// Clone the request and URL
-	reqCopy := r.Clone(r.Context())
-	urlCopy := *r.URL
-	urlCopy.Path = trimmedPath
-	reqCopy.URL = &urlCopy
-
-	return reqCopy
-}
-
 func (s *Server) ServeHTTPNext(w http.ResponseWriter, r *http.Request) {
 	if s.next == nil {
 		redir := r.FormValue("redir")
@@ -184,7 +158,6 @@ func (s *Server) ServeHTTPNext(w http.ResponseWriter, r *http.Request) {
 		).ServeHTTP(w, r)
 	} else {
 		requestsProxied.WithLabelValues(r.Host).Inc()
-		r = s.stripBasePrefixFromRequest(r)
 		s.next.ServeHTTP(w, r)
 	}
 }

lib/policy/bot.go

@@ -4,18 +4,17 @@ import (
 	"fmt"
 
 	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
 	"github.com/TecharoHQ/anubis/lib/policy/config"
 )
 
 type Bot struct {
-	Rules     checker.Impl
+	Rules     Checker
 	Challenge *config.ChallengeRules
-	Weight    *config.Weight
 	Name      string
 	Action    config.Rule
+	Weight    *config.Weight
 }
 
 func (b Bot) Hash() string {
-	return internal.FastHash(fmt.Sprintf("%s::%s", b.Name, b.Rules.Hash()))
+	return internal.SHA256sum(fmt.Sprintf("%s::%s", b.Name, b.Rules.Hash()))
 }

lib/policy/celchecker.go

@@ -63,7 +63,7 @@ func NewCELChecker(cfg *config.ExpressionOrList) (*CELChecker, error) {
 }
 
 func (cc *CELChecker) Hash() string {
-	return internal.FastHash(cc.src)
+	return internal.SHA256sum(cc.src)
 }
 
 func (cc *CELChecker) Check(r *http.Request) (bool, error) {

lib/policy/checker.go

@@ -3,20 +3,50 @@ package policy
 import (
 	"errors"
 	"fmt"
+	"net"
 	"net/http"
-	"net/netip"
 	"regexp"
 	"strings"
 
 	"github.com/TecharoHQ/anubis/internal"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
-	"github.com/gaissmai/bart"
+	"github.com/yl2chen/cidranger"
 )
 
 var (
 	ErrMisconfiguration = errors.New("[unexpected] policy: administrator misconfiguration")
 )
 
+type Checker interface {
+	Check(*http.Request) (bool, error)
+	Hash() string
+}
+
+type CheckerList []Checker
+
+func (cl CheckerList) Check(r *http.Request) (bool, error) {
+	for _, c := range cl {
+		ok, err := c.Check(r)
+		if err != nil {
+			return ok, err
+		}
+		if ok {
+			return ok, nil
+		}
+	}
+
+	return false, nil
+}
+
+func (cl CheckerList) Hash() string {
+	var sb strings.Builder
+
+	for _, c := range cl {
+		fmt.Fprintln(&sb, c.Hash())
+	}
+
+	return internal.SHA256sum(sb.String())
+}
+
 type staticHashChecker struct {
 	hash string
 }
@@ -27,30 +57,35 @@ func (staticHashChecker) Check(r *http.Request) (bool, error) {
 
 func (s staticHashChecker) Hash() string { return s.hash }
 
-func NewStaticHashChecker(hashable string) checker.Impl {
-	return staticHashChecker{hash: internal.FastHash(hashable)}
+func NewStaticHashChecker(hashable string) Checker {
+	return staticHashChecker{hash: internal.SHA256sum(hashable)}
 }
 
 type RemoteAddrChecker struct {
-	prefixTable *bart.Lite
-	hash        string
+	ranger cidranger.Ranger
+	hash   string
 }
 
-func NewRemoteAddrChecker(cidrs []string) (checker.Impl, error) {
-	table := new(bart.Lite)
+func NewRemoteAddrChecker(cidrs []string) (Checker, error) {
+	ranger := cidranger.NewPCTrieRanger()
+	var sb strings.Builder
 
 	for _, cidr := range cidrs {
-		prefix, err := netip.ParsePrefix(cidr)
+		_, rng, err := net.ParseCIDR(cidr)
 		if err != nil {
 			return nil, fmt.Errorf("%w: range %s not parsing: %w", ErrMisconfiguration, cidr, err)
 		}
 
-		table.Insert(prefix)
+		err = ranger.Insert(cidranger.NewBasicRangerEntry(*rng))
+		if err != nil {
+			return nil, fmt.Errorf("%w: error inserting ip range: %w", ErrMisconfiguration, err)
+		}
+		fmt.Fprintln(&sb, cidr)
 	}
 
 	return &RemoteAddrChecker{
-		prefixTable: table,
-		hash:        internal.FastHash(strings.Join(cidrs, ",")),
+		ranger: ranger,
+		hash:   internal.SHA256sum(sb.String()),
 	}, nil
 }
 
@@ -60,12 +95,21 @@ func (rac *RemoteAddrChecker) Check(r *http.Request) (bool, error) {
 		return false, fmt.Errorf("%w: header X-Real-Ip is not set", ErrMisconfiguration)
 	}
 
-	addr, err := netip.ParseAddr(host)
-	if err != nil {
-		return false, fmt.Errorf("%w: %s is not an IP address: %w", ErrMisconfiguration, host, err)
+	addr := net.ParseIP(host)
+	if addr == nil {
+		return false, fmt.Errorf("%w: %s is not an IP address", ErrMisconfiguration, host)
 	}
 
-	return rac.prefixTable.Contains(addr), nil
+	ok, err := rac.ranger.Contains(addr)
+	if err != nil {
+		return false, err
+	}
+
+	if ok {
+		return true, nil
+	}
+
+	return false, nil
 }
 
 func (rac *RemoteAddrChecker) Hash() string {
@@ -78,16 +122,16 @@ type HeaderMatchesChecker struct {
 	hash   string
 }
 
-func NewUserAgentChecker(rexStr string) (checker.Impl, error) {
+func NewUserAgentChecker(rexStr string) (Checker, error) {
 	return NewHeaderMatchesChecker("User-Agent", rexStr)
 }
 
-func NewHeaderMatchesChecker(header, rexStr string) (checker.Impl, error) {
+func NewHeaderMatchesChecker(header, rexStr string) (Checker, error) {
 	rex, err := regexp.Compile(strings.TrimSpace(rexStr))
 	if err != nil {
 		return nil, fmt.Errorf("%w: regex %s failed parse: %w", ErrMisconfiguration, rexStr, err)
 	}
-	return &HeaderMatchesChecker{strings.TrimSpace(header), rex, internal.FastHash(header + ": " + rexStr)}, nil
+	return &HeaderMatchesChecker{strings.TrimSpace(header), rex, internal.SHA256sum(header + ": " + rexStr)}, nil
 }
 
 func (hmc *HeaderMatchesChecker) Check(r *http.Request) (bool, error) {
@@ -107,12 +151,12 @@ type PathChecker struct {
 	hash   string
 }
 
-func NewPathChecker(rexStr string) (checker.Impl, error) {
+func NewPathChecker(rexStr string) (Checker, error) {
 	rex, err := regexp.Compile(strings.TrimSpace(rexStr))
 	if err != nil {
 		return nil, fmt.Errorf("%w: regex %s failed parse: %w", ErrMisconfiguration, rexStr, err)
 	}
-	return &PathChecker{rex, internal.FastHash(rexStr)}, nil
+	return &PathChecker{rex, internal.SHA256sum(rexStr)}, nil
 }
 
 func (pc *PathChecker) Check(r *http.Request) (bool, error) {
@@ -127,7 +171,7 @@ func (pc *PathChecker) Hash() string {
 	return pc.hash
 }
 
-func NewHeaderExistsChecker(key string) checker.Impl {
+func NewHeaderExistsChecker(key string) Checker {
 	return headerExistsChecker{strings.TrimSpace(key)}
 }
 
@@ -144,11 +188,11 @@ func (hec headerExistsChecker) Check(r *http.Request) (bool, error) {
 }
 
 func (hec headerExistsChecker) Hash() string {
-	return internal.FastHash(hec.header)
+	return internal.SHA256sum(hec.header)
 }
 
-func NewHeadersChecker(headermap map[string]string) (checker.Impl, error) {
-	var result checker.List
+func NewHeadersChecker(headermap map[string]string) (Checker, error) {
+	var result CheckerList
 	var errs []error
 
 	for key, rexStr := range headermap {
@@ -163,7 +207,7 @@ func NewHeadersChecker(headermap map[string]string) (checker.Impl, error) {
 			continue
 		}
 
-		result = append(result, &HeaderMatchesChecker{key, rex, internal.FastHash(key + ": " + rexStr)})
+		result = append(result, &HeaderMatchesChecker{key, rex, internal.SHA256sum(key + ": " + rexStr)})
 	}
 
 	if len(errs) != 0 {

lib/policy/checker/checker.go

@@ -1,41 +0,0 @@
-// Package checker defines the Checker interface and a helper utility to avoid import cycles.
-package checker
-
-import (
-	"fmt"
-	"net/http"
-	"strings"
-
-	"github.com/TecharoHQ/anubis/internal"
-)
-
-type Impl interface {
-	Check(*http.Request) (bool, error)
-	Hash() string
-}
-
-type List []Impl
-
-func (l List) Check(r *http.Request) (bool, error) {
-	for _, c := range l {
-		ok, err := c.Check(r)
-		if err != nil {
-			return ok, err
-		}
-		if ok {
-			return ok, nil
-		}
-	}
-
-	return false, nil
-}
-
-func (l List) Hash() string {
-	var sb strings.Builder
-
-	for _, c := range l {
-		fmt.Fprintln(&sb, c.Hash())
-	}
-
-	return internal.FastHash(sb.String())
-}

lib/policy/config/asn.go

@@ -1,44 +0,0 @@
-package config
-
-import (
-	"errors"
-	"fmt"
-)
-
-var (
-	ErrPrivateASN = errors.New("bot.ASNs: you have specified a private use ASN")
-)
-
-type ASNs struct {
-	Match []uint32 `json:"match"`
-}
-
-func (a *ASNs) Valid() error {
-	var errs []error
-
-	for _, asn := range a.Match {
-		if isPrivateASN(asn) {
-			errs = append(errs, fmt.Errorf("%w: %d is private (see RFC 6996)", ErrPrivateASN, asn))
-		}
-	}
-
-	if len(errs) != 0 {
-		return fmt.Errorf("bot.ASNs: invalid ASN settings: %w", errors.Join(errs...))
-	}
-
-	return nil
-}
-
-// isPrivateASN checks if an ASN is in the private use area.
-//
-// Based on RFC 6996 and IANA allocations.
-func isPrivateASN(asn uint32) bool {
-	switch {
-	case asn >= 64512 && asn <= 65534:
-		return true
-	case asn >= 4200000000 && asn <= 4294967294:
-		return true
-	default:
-		return false
-	}
-}

lib/policy/config/config.go

@@ -46,19 +46,15 @@ const (
 const DefaultAlgorithm = "fast"
 
 type BotConfig struct {
-	UserAgentRegex *string           `json:"user_agent_regex,omitempty" yaml:"user_agent_regex,omitempty"`
-	PathRegex      *string           `json:"path_regex,omitempty" yaml:"path_regex,omitempty"`
-	HeadersRegex   map[string]string `json:"headers_regex,omitempty" yaml:"headers_regex,omitempty"`
-	Expression     *ExpressionOrList `json:"expression,omitempty" yaml:"expression,omitempty"`
-	Challenge      *ChallengeRules   `json:"challenge,omitempty" yaml:"challenge,omitempty"`
-	Weight         *Weight           `json:"weight,omitempty" yaml:"weight,omitempty"`
-	Name           string            `json:"name" yaml:"name"`
-	Action         Rule              `json:"action" yaml:"action"`
-	RemoteAddr     []string          `json:"remote_addresses,omitempty" yaml:"remote_addresses,omitempty"`
-
-	// Thoth features
-	GeoIP *GeoIP `json:"geoip,omitempty"`
-	ASNs  *ASNs  `json:"asns,omitempty"`
+	UserAgentRegex *string           `json:"user_agent_regex,omitempty"`
+	PathRegex      *string           `json:"path_regex,omitempty"`
+	HeadersRegex   map[string]string `json:"headers_regex,omitempty"`
+	Expression     *ExpressionOrList `json:"expression,omitempty"`
+	Challenge      *ChallengeRules   `json:"challenge,omitempty"`
+	Weight         *Weight           `json:"weight,omitempty"`
+	Name           string            `json:"name"`
+	Action         Rule              `json:"action"`
+	RemoteAddr     []string          `json:"remote_addresses,omitempty"`
 }
 
 func (b BotConfig) Zero() bool {
@@ -70,8 +66,6 @@ func (b BotConfig) Zero() bool {
 		b.Action != "",
 		len(b.RemoteAddr) != 0,
 		b.Challenge != nil,
-		b.GeoIP != nil,
-		b.ASNs != nil,
 	} {
 		if cond {
 			return false
@@ -91,9 +85,7 @@ func (b *BotConfig) Valid() error {
 	allFieldsEmpty := b.UserAgentRegex == nil &&
 		b.PathRegex == nil &&
 		len(b.RemoteAddr) == 0 &&
-		len(b.HeadersRegex) == 0 &&
-		b.ASNs == nil &&
-		b.GeoIP == nil
+		len(b.HeadersRegex) == 0
 
 	if allFieldsEmpty && b.Expression == nil {
 		errs = append(errs, ErrBotMustHaveUserAgentOrPath)
@@ -178,9 +170,9 @@ func (b *BotConfig) Valid() error {
 }
 
 type ChallengeRules struct {
-	Algorithm  string `json:"algorithm,omitempty" yaml:"algorithm,omitempty"`
-	Difficulty int    `json:"difficulty,omitempty" yaml:"difficulty,omitempty"`
-	ReportAs   int    `json:"report_as,omitempty" yaml:"report_as,omitempty"`
+	Algorithm  string `json:"algorithm"`
+	Difficulty int    `json:"difficulty"`
+	ReportAs   int    `json:"report_as"`
 }
 
 var (

lib/policy/config/expressionorlist.go

@@ -13,9 +13,9 @@ var (
 )
 
 type ExpressionOrList struct {
-	Expression string   `json:"-" yaml:"-"`
-	All        []string `json:"all,omitempty" yaml:"all,omitempty"`
-	Any        []string `json:"any,omitempty" yaml:"any,omitempty"`
+	Expression string   `json:"-"`
+	All        []string `json:"all,omitempty"`
+	Any        []string `json:"any,omitempty"`
 }
 
 func (eol ExpressionOrList) Equal(rhs *ExpressionOrList) bool {
@@ -34,43 +34,6 @@ func (eol ExpressionOrList) Equal(rhs *ExpressionOrList) bool {
 	return true
 }
 
-func (eol *ExpressionOrList) MarshalYAML() (any, error) {
-	switch {
-	case len(eol.All) == 1 && len(eol.Any) == 0:
-		eol.Expression = eol.All[0]
-		eol.All = nil
-	case len(eol.Any) == 1 && len(eol.All) == 0:
-		eol.Expression = eol.Any[0]
-		eol.Any = nil
-	}
-
-	if eol.Expression != "" {
-		return eol.Expression, nil
-	}
-
-	type RawExpressionOrList ExpressionOrList
-	return RawExpressionOrList(*eol), nil
-}
-
-func (eol *ExpressionOrList) MarshalJSON() ([]byte, error) {
-	switch {
-	case len(eol.All) == 1 && len(eol.Any) == 0:
-		eol.Expression = eol.All[0]
-		eol.All = nil
-	case len(eol.Any) == 1 && len(eol.All) == 0:
-		eol.Expression = eol.Any[0]
-		eol.Any = nil
-	}
-
-	if eol.Expression != "" {
-		return json.Marshal(string(eol.Expression))
-	}
-
-	type RawExpressionOrList ExpressionOrList
-	val := RawExpressionOrList(*eol)
-	return json.Marshal(val)
-}
-
 func (eol *ExpressionOrList) UnmarshalJSON(data []byte) error {
 	switch string(data[0]) {
 	case `"`: // string

lib/policy/config/expressionorlist_test.go

@@ -1,147 +1,12 @@
 package config
 
 import (
-	"bytes"
 	"encoding/json"
 	"errors"
 	"testing"
-
-	yaml "sigs.k8s.io/yaml/goyaml.v3"
 )
 
-func TestExpressionOrListMarshalJSON(t *testing.T) {
-	for _, tt := range []struct {
-		name   string
-		input  *ExpressionOrList
-		output []byte
-		err    error
-	}{
-		{
-			name: "single expression",
-			input: &ExpressionOrList{
-				Expression: "true",
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-		{
-			name: "all",
-			input: &ExpressionOrList{
-				All: []string{"true", "true"},
-			},
-			output: []byte(`{"all":["true","true"]}`),
-			err:    nil,
-		},
-		{
-			name: "all one",
-			input: &ExpressionOrList{
-				All: []string{"true"},
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-		{
-			name: "any",
-			input: &ExpressionOrList{
-				Any: []string{"true", "false"},
-			},
-			output: []byte(`{"any":["true","false"]}`),
-			err:    nil,
-		},
-		{
-			name: "any one",
-			input: &ExpressionOrList{
-				Any: []string{"true"},
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			result, err := json.Marshal(tt.input)
-			if !errors.Is(err, tt.err) {
-				t.Errorf("wanted marshal error: %v but got: %v", tt.err, err)
-			}
-
-			if !bytes.Equal(result, tt.output) {
-				t.Logf("wanted: %s", string(tt.output))
-				t.Logf("got:    %s", string(result))
-				t.Error("mismatched output")
-			}
-		})
-	}
-}
-
-func TestExpressionOrListMarshalYAML(t *testing.T) {
-	for _, tt := range []struct {
-		name   string
-		input  *ExpressionOrList
-		output []byte
-		err    error
-	}{
-		{
-			name: "single expression",
-			input: &ExpressionOrList{
-				Expression: "true",
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-		{
-			name: "all",
-			input: &ExpressionOrList{
-				All: []string{"true", "true"},
-			},
-			output: []byte(`all:
-    - "true"
-    - "true"`),
-			err: nil,
-		},
-		{
-			name: "all one",
-			input: &ExpressionOrList{
-				All: []string{"true"},
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-		{
-			name: "any",
-			input: &ExpressionOrList{
-				Any: []string{"true", "false"},
-			},
-			output: []byte(`any:
-    - "true"
-    - "false"`),
-			err: nil,
-		},
-		{
-			name: "any one",
-			input: &ExpressionOrList{
-				Any: []string{"true"},
-			},
-			output: []byte(`"true"`),
-			err:    nil,
-		},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			result, err := yaml.Marshal(tt.input)
-			if !errors.Is(err, tt.err) {
-				t.Errorf("wanted marshal error: %v but got: %v", tt.err, err)
-			}
-
-			result = bytes.TrimSpace(result)
-
-			if !bytes.Equal(result, tt.output) {
-				t.Logf("wanted: %q", string(tt.output))
-				t.Logf("got:    %q", string(result))
-				t.Error("mismatched output")
-			}
-		})
-	}
-}
-
-func TestExpressionOrListUnmarshalJSON(t *testing.T) {
+func TestExpressionOrListUnmarshal(t *testing.T) {
 	for _, tt := range []struct {
 		err      error
 		validErr error

lib/policy/config/geoip.go

@@ -1,36 +0,0 @@
-package config
-
-import (
-	"errors"
-	"fmt"
-	"regexp"
-	"strings"
-)
-
-var (
-	countryCodeRegexp = regexp.MustCompile(`^\w{2}$`)
-
-	ErrNotCountryCode = errors.New("config.Bot: invalid country code")
-)
-
-type GeoIP struct {
-	Countries []string `json:"countries"`
-}
-
-func (g *GeoIP) Valid() error {
-	var errs []error
-
-	for i, cc := range g.Countries {
-		if !countryCodeRegexp.MatchString(cc) {
-			errs = append(errs, fmt.Errorf("%w: %s", ErrNotCountryCode, cc))
-		}
-
-		g.Countries[i] = strings.ToLower(cc)
-	}
-
-	if len(errs) != 0 {
-		return fmt.Errorf("bot.GeoIP: invalid GeoIP settings: %w", errors.Join(errs...))
-	}
-
-	return nil
-}

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

@@ -1,6 +0,0 @@
-bots:
-  - name: challenge-cloudflare
-    action: CHALLENGE
-    asns:
-      match:
-        - 13335 # Cloudflare

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

@@ -1,6 +0,0 @@
-bots:
-  - name: compute-tarrif-us
-    action: CHALLENGE
-    geoip:
-      countries:
-        - US

lib/policy/config/weight.go

@@ -1,5 +1,5 @@
 package config
 
 type Weight struct {
-	Adjust int `json:"adjust" yaml:"adjust"`
+	Adjust int `json:"adjust"`
 }

lib/policy/policy.go

@@ -1,14 +1,10 @@
 package policy
 
 import (
-	"context"
 	"errors"
 	"fmt"
 	"io"
-	"log/slog"
 
-	"github.com/TecharoHQ/anubis/internal/thoth"
-	"github.com/TecharoHQ/anubis/lib/policy/checker"
 	"github.com/TecharoHQ/anubis/lib/policy/config"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/promauto"
@@ -39,7 +35,7 @@ func NewParsedConfig(orig *config.Config) *ParsedConfig {
 	}
 }
 
-func ParseConfig(ctx context.Context, fin io.Reader, fname string, defaultDifficulty int) (*ParsedConfig, error) {
+func ParseConfig(fin io.Reader, fname string, defaultDifficulty int) (*ParsedConfig, error) {
 	c, err := config.Load(fin, fname)
 	if err != nil {
 		return nil, err
@@ -47,8 +43,6 @@ func ParseConfig(ctx context.Context, fin io.Reader, fname string, defaultDiffic
 
 	var validationErrs []error
 
-	tc, hasThothClient := thoth.FromContext(ctx)
-
 	result := NewParsedConfig(c)
 	result.DefaultDifficulty = defaultDifficulty
 
@@ -63,7 +57,7 @@ func ParseConfig(ctx context.Context, fin io.Reader, fname string, defaultDiffic
 			Action: b.Action,
 		}
 
-		cl := checker.List{}
+		cl := CheckerList{}
 
 		if len(b.RemoteAddr) > 0 {
 			c, err := NewRemoteAddrChecker(b.RemoteAddr)
@@ -110,24 +104,6 @@ func ParseConfig(ctx context.Context, fin io.Reader, fname string, defaultDiffic
 			}
 		}
 
-		if b.ASNs != nil {
-			if !hasThothClient {
-				slog.Warn("You have specified a Thoth specific check but you have no Thoth client configured. Please read https://anubis.techaro.lol/docs/admin/thoth for more information", "check", "asn", "settings", b.ASNs)
-				continue
-			}
-
-			cl = append(cl, tc.ASNCheckerFor(b.ASNs.Match))
-		}
-
-		if b.GeoIP != nil {
-			if !hasThothClient {
-				slog.Warn("You have specified a Thoth specific check but you have no Thoth client configured. Please read https://anubis.techaro.lol/docs/admin/thoth for more information", "check", "geoip", "settings", b.GeoIP)
-				continue
-			}
-
-			cl = append(cl, tc.GeoIPCheckerFor(b.GeoIP.Countries))
-		}
-
 		if b.Challenge == nil {
 			parsedBot.Challenge = &config.ChallengeRules{
 				Difficulty: defaultDifficulty,

lib/policy/policy_test.go

@@ -7,25 +7,21 @@ import (
 
 	"github.com/TecharoHQ/anubis"
 	"github.com/TecharoHQ/anubis/data"
-	"github.com/TecharoHQ/anubis/internal/thoth/thothmock"
 )
 
 func TestDefaultPolicyMustParse(t *testing.T) {
-	ctx := thothmock.WithMockThoth(t)
-
 	fin, err := data.BotPolicies.Open("botPolicies.json")
 	if err != nil {
 		t.Fatal(err)
 	}
 	defer fin.Close()
 
-	if _, err := ParseConfig(ctx, fin, "botPolicies.json", anubis.DefaultDifficulty); err != nil {
+	if _, err := ParseConfig(fin, "botPolicies.json", anubis.DefaultDifficulty); err != nil {
 		t.Fatalf("can't parse config: %v", err)
 	}
 }
 
 func TestGoodConfigs(t *testing.T) {
-
 	finfos, err := os.ReadDir("config/testdata/good")
 	if err != nil {
 		t.Fatal(err)
@@ -34,37 +30,20 @@ func TestGoodConfigs(t *testing.T) {
 	for _, st := range finfos {
 		st := st
 		t.Run(st.Name(), func(t *testing.T) {
-			t.Run("with-thoth", func(t *testing.T) {
-				fin, err := os.Open(filepath.Join("config", "testdata", "good", st.Name()))
-				if err != nil {
-					t.Fatal(err)
-				}
-				defer fin.Close()
+			fin, err := os.Open(filepath.Join("config", "testdata", "good", st.Name()))
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer fin.Close()
 
-				ctx := thothmock.WithMockThoth(t)
-				if _, err := ParseConfig(ctx, fin, fin.Name(), anubis.DefaultDifficulty); err != nil {
-					t.Fatal(err)
-				}
-			})
-
-			t.Run("without-thoth", func(t *testing.T) {
-				fin, err := os.Open(filepath.Join("config", "testdata", "good", st.Name()))
-				if err != nil {
-					t.Fatal(err)
-				}
-				defer fin.Close()
-
-				if _, err := ParseConfig(t.Context(), fin, fin.Name(), anubis.DefaultDifficulty); err != nil {
-					t.Fatal(err)
-				}
-			})
+			if _, err := ParseConfig(fin, fin.Name(), anubis.DefaultDifficulty); err != nil {
+				t.Fatal(err)
+			}
 		})
 	}
 }
 
 func TestBadConfigs(t *testing.T) {
-	ctx := thothmock.WithMockThoth(t)
-
 	finfos, err := os.ReadDir("config/testdata/bad")
 	if err != nil {
 		t.Fatal(err)
@@ -79,7 +58,7 @@ func TestBadConfigs(t *testing.T) {
 			}
 			defer fin.Close()
 
-			if _, err := ParseConfig(ctx, fin, fin.Name(), anubis.DefaultDifficulty); err == nil {
+			if _, err := ParseConfig(fin, fin.Name(), anubis.DefaultDifficulty); err == nil {
 				t.Fatal(err)
 			} else {
 				t.Log(err)

test/go.mod

@@ -5,28 +5,22 @@ go 1.24.2
 replace github.com/TecharoHQ/anubis => ..
 
 require (
-	github.com/TecharoHQ/anubis v1.19.1
+	github.com/TecharoHQ/anubis v1.18.0
 	github.com/facebookgo/flagenv v0.0.0-20160425205200-fcd59fca7456
 	github.com/google/uuid v1.6.0
 )
 
 require (
-	buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 // indirect
 	cel.dev/expr v0.24.0 // indirect
-	github.com/TecharoHQ/thoth-proto v0.4.0 // indirect
-	github.com/a-h/templ v0.3.898 // indirect
+	github.com/a-h/templ v0.3.865 // indirect
 	github.com/antlr4-go/antlr/v4 v4.13.1 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/facebookgo/ensure v0.0.0-20200202191622-63f1cf65ac4c // indirect
 	github.com/facebookgo/subset v0.0.0-20200203212716-c811ad88dec4 // indirect
-	github.com/gaissmai/bart v0.20.4 // indirect
 	github.com/golang-jwt/jwt/v5 v5.2.2 // indirect
 	github.com/google/cel-go v0.25.0 // indirect
-	github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1 // indirect
-	github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0 // indirect
-	github.com/joho/godotenv v1.5.1 // indirect
 	github.com/jsha/minica v1.1.0 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
@@ -38,12 +32,11 @@ require (
 	github.com/stoewer/go-strcase v1.3.0 // indirect
 	github.com/yl2chen/cidranger v1.0.2 // indirect
 	golang.org/x/exp v0.0.0-20250506013437-ce4c2cf36ca6 // indirect
-	golang.org/x/net v0.41.0 // indirect
+	golang.org/x/net v0.40.0 // indirect
 	golang.org/x/sys v0.33.0 // indirect
-	golang.org/x/text v0.26.0 // indirect
+	golang.org/x/text v0.25.0 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20250519155744-55703ea1f237 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237 // indirect
-	google.golang.org/grpc v1.72.2 // indirect
 	google.golang.org/protobuf v1.36.6 // indirect
 	k8s.io/apimachinery v0.33.1 // indirect
 	sigs.k8s.io/json v0.0.0-20241014173422-cfa47c3a1cc8 // indirect

test/go.sum

@@ -1,11 +1,7 @@
-buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1 h1:YhMSc48s25kr7kv31Z8vf7sPUIq5YJva9z1mn/hAt0M=
-buf.build/gen/go/bufbuild/protovalidate/protocolbuffers/go v1.36.6-20250425153114-8976f5be98c1.1/go.mod h1:avRlCjnFzl98VPaeCtJ24RrV/wwHFzB8sWXhj26+n/U=
 cel.dev/expr v0.24.0 h1:56OvJKSH3hDGL0ml5uSxZmz3/3Pq4tJ+fb1unVLAFcY=
 cel.dev/expr v0.24.0/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
-github.com/TecharoHQ/thoth-proto v0.4.0 h1:UbkvfgCku0Dm1R6O4ug3HOsJNnE6F3wB8x+Dpw2lzFI=
-github.com/TecharoHQ/thoth-proto v0.4.0/go.mod h1:IcGnZt3iYUZQVEa0Lwk5l4ix0hCeXlWUV1TJMZvbWx0=
-github.com/a-h/templ v0.3.898 h1:g9oxL/dmM6tvwRe2egJS8hBDQTncokbMoOFk1oJMX7s=
-github.com/a-h/templ v0.3.898/go.mod h1:oLBbZVQ6//Q6zpvSMPTuBK0F3qOtBdFBcGRspcT+VNQ=
+github.com/a-h/templ v0.3.865 h1:nYn5EWm9EiXaDgWcMQaKiKvrydqgxDUtT1+4zU2C43A=
+github.com/a-h/templ v0.3.865/go.mod h1:oLBbZVQ6//Q6zpvSMPTuBK0F3qOtBdFBcGRspcT+VNQ=
 github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ=
 github.com/antlr4-go/antlr/v4 v4.13.1/go.mod h1:GKmUxMtwp6ZgGwZSva4eWPC5mS6vUAmOABFgjdkM7Nw=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
@@ -25,16 +21,8 @@ github.com/facebookgo/stack v0.0.0-20160209184415-751773369052 h1:JWuenKqqX8nojt
 github.com/facebookgo/stack v0.0.0-20160209184415-751773369052/go.mod h1:UbMTZqLaRiH3MsBH8va0n7s1pQYcu3uTb8G4tygF4Zg=
 github.com/facebookgo/subset v0.0.0-20200203212716-c811ad88dec4 h1:7HZCaLC5+BZpmbhCOZJ293Lz68O7PYrF2EzeiFMwCLk=
 github.com/facebookgo/subset v0.0.0-20200203212716-c811ad88dec4/go.mod h1:5tD+neXqOorC30/tWg0LCSkrqj/AR6gu8yY8/fpw1q0=
-github.com/gaissmai/bart v0.20.4 h1:Ik47r1fy3jRVU+1eYzKSW3ho2UgBVTVnUS8O993584U=
-github.com/gaissmai/bart v0.20.4/go.mod h1:cEed+ge8dalcbpi8wtS9x9m2hn/fNJH5suhdGQOHnYk=
-github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
-github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
-github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
-github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 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/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
-github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
 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=
@@ -42,12 +30,6 @@ 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/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1 h1:qnpSQwGEnkcRpTqNOIR6bJbR0gAorgP9CSALpRcKoAA=
-github.com/grpc-ecosystem/go-grpc-middleware/providers/prometheus v1.0.1/go.mod h1:lXGCsh6c22WGtjr+qGHj1otzZpV/1kwTMAqkwZsnWRU=
-github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0 h1:pRhl55Yx1eC7BZ1N+BBWwnKaMyD8uC+34TLdndZMAKk=
-github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.1.0/go.mod h1:XKMd7iuf/RGPSMJ/U4HP0zS2Z9Fh8Ps9a+6X26m/tmI=
-github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
-github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 github.com/jsha/minica v1.1.0 h1:O2ZbzAN75w4RTB+5+HfjIEvY5nxRqDlwj3ZlLVG5JD8=
 github.com/jsha/minica v1.1.0/go.mod h1:dxC3wNmD+gU1ewXo/R8jB2ihB6wNpyXrG8aUk5Iuf/k=
 github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
@@ -87,32 +69,18 @@ github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOf
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/yl2chen/cidranger v1.0.2 h1:lbOWZVCG1tCRX4u24kuM1Tb4nHqWkDxwLdoS+SevawU=
 github.com/yl2chen/cidranger v1.0.2/go.mod h1:9U1yz7WPYDwf0vpNWFaeRh0bjwz5RVgRy/9UEQfHl0g=
-go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
-go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
-go.opentelemetry.io/otel v1.34.0 h1:zRLXxLCgL1WyKsPVrgbSdMN4c0FMkDAskSTQP+0hdUY=
-go.opentelemetry.io/otel v1.34.0/go.mod h1:OWFPOQ+h4G8xpyjgqo4SxJYdDQ/qmRH+wivy7zzx9oI=
-go.opentelemetry.io/otel/metric v1.34.0 h1:+eTR3U0MyfWjRDhmFMxe2SsW64QrZ84AOhvqS7Y+PoQ=
-go.opentelemetry.io/otel/metric v1.34.0/go.mod h1:CEDrp0fy2D0MvkXE+dPV7cMi8tWZwX3dmaIhwPOaqHE=
-go.opentelemetry.io/otel/sdk v1.34.0 h1:95zS4k/2GOy069d321O8jWgYsW3MzVV+KuSPKp7Wr1A=
-go.opentelemetry.io/otel/sdk v1.34.0/go.mod h1:0e/pNiaMAqaykJGKbi+tSjWfNNHMTxoC9qANsCzbyxU=
-go.opentelemetry.io/otel/sdk/metric v1.34.0 h1:5CeK9ujjbFVL5c1PhLuStg1wxA7vQv7ce1EK0Gyvahk=
-go.opentelemetry.io/otel/sdk/metric v1.34.0/go.mod h1:jQ/r8Ze28zRKoNRdkjCZxfs6YvBTG1+YIqyFVFYec5w=
-go.opentelemetry.io/otel/trace v1.34.0 h1:+ouXS2V8Rd4hp4580a8q23bg0azF2nI8cqLYnC8mh/k=
-go.opentelemetry.io/otel/trace v1.34.0/go.mod h1:Svm7lSjQD7kG7KJ/MUHPVXSDGz2OX4h0M2jHBhmSfRE=
 golang.org/x/exp v0.0.0-20250506013437-ce4c2cf36ca6 h1:y5zboxd6LQAqYIhHnB48p0ByQ/GnQx2BE33L8BOHQkI=
 golang.org/x/exp v0.0.0-20250506013437-ce4c2cf36ca6/go.mod h1:U6Lno4MTRCDY+Ba7aCcauB9T60gsv5s4ralQzP72ZoQ=
-golang.org/x/net v0.41.0 h1:vBTly1HeNPEn3wtREYfy4GZ/NECgw2Cnl+nK6Nz3uvw=
-golang.org/x/net v0.41.0/go.mod h1:B/K4NNqkfmg07DQYrbwvSluqCJOOXwUjeb/5lOisjbA=
+golang.org/x/net v0.40.0 h1:79Xs7wF06Gbdcg4kdCCIQArK11Z1hr5POQ6+fIYHNuY=
+golang.org/x/net v0.40.0/go.mod h1:y0hY0exeL2Pku80/zKK7tpntoX23cqL3Oa6njdgRtds=
 golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
 golang.org/x/sys v0.33.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
-golang.org/x/text v0.26.0 h1:P42AVeLghgTYr4+xUnTRKDMqpar+PtX7KWuNQL21L8M=
-golang.org/x/text v0.26.0/go.mod h1:QK15LZJUUQVJxhz7wXgxSy/CJaTFjd0G+YLonydOVQA=
+golang.org/x/text v0.25.0 h1:qVyWApTSYLk/drJRO5mDlNYskwQznZmkpV2c8q9zls4=
+golang.org/x/text v0.25.0/go.mod h1:WEdwpYrmk1qmdHvhkSTNPm3app7v4rsT8F2UD6+VHIA=
 google.golang.org/genproto/googleapis/api v0.0.0-20250519155744-55703ea1f237 h1:Kog3KlB4xevJlAcbbbzPfRG0+X9fdoGM+UBRKVz6Wr0=
 google.golang.org/genproto/googleapis/api v0.0.0-20250519155744-55703ea1f237/go.mod h1:ezi0AVyMKDWy5xAncvjLWH7UcLBB5n7y2fQ8MzjJcto=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237 h1:cJfm9zPbe1e873mHJzmQ1nwVEeRDU/T1wXDK2kUSU34=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
-google.golang.org/grpc v1.72.2 h1:TdbGzwb82ty4OusHWepvFWGLgIbNo1/SUynEN0ssqv8=
-google.golang.org/grpc v1.72.2/go.mod h1:wH5Aktxcg25y1I3w7H69nHfXdOG3UiadoBtjh3izSDM=
 google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
 google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

test/ssh-ci/Dockerfile

@@ -1,5 +0,0 @@
-ARG ALPINE_VERSION=3.22
-
-FROM alpine:${ALPINE_VERSION}
-RUN apk add -U go nodejs git build-base git npm bash zstd brotli gzip
-LABEL org.opencontainers.image.source="https://github.com/TecharoHQ/anubis"

test/ssh-ci/in-container.sh

@@ -1,8 +0,0 @@
-#!/usr/bin/env sh
-
-set -euo pipefail
-set -x
-
-npm ci
-npm run build
-SKIP_INTEGRATION=1 go test ./...

test/ssh-ci/rigging.sh

@@ -1,33 +0,0 @@
-#!/usr/bin/env bash
-
-set -euo pipefail
-[ ! -z "${DEBUG:-}" ] && set -x
-
-if [ "$#" -ne 1 ]; then
-    echo "Usage: rigging.sh <user@host>"
-fi
-
-CIRunnerImage="ghcr.io/techarohq/anubis/ci-runner:latest"
-RunID=${GITHUB_RUN_ID:-$(uuidgen)}
-RunFolder="anubis/runs/${RunID}"
-Target="${1}"
-
-ssh "${Target}" uname -av
-ssh "${Target}" mkdir -p "${RunFolder}"
-git archive HEAD | ssh "${Target}" tar xC "${RunFolder}"
-
-ssh "${Target}" << EOF
-  set -euo pipefail
-  set -x
-  mkdir -p "anubis/cache/{go,go-build,node}"
-  podman pull ${CIRunnerImage}
-  podman run --rm -it \
-    -v "\$HOME/${RunFolder}:/app/anubis" \
-    -v "\$HOME/anubis/cache/go:/root/go" \
-    -v "\$HOME/anubis/cache/go-build:/root/.cache/go-build" \
-    -v "\$HOME/anubis/cache/node:/root/.npm" \
-    -w /app/anubis \
-    ${CIRunnerImage} \
-    sh /app/anubis/test/ssh-ci/in-container.sh
-  ssh "${Target}" rm -rf "${RunFolder}"
-EOF

yeetfile.js

@@ -22,7 +22,6 @@ $`npm run assets`;
 
         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`;
-            $`go build -o ${bin}/anubis-robots2policy -ldflags '-s -w -extldflags "-static" -X "github.com/TecharoHQ/anubis.Version=${git.tag()}"' ./cmd/robots2policy`;
 
             file.install("./run/anubis@.service", `${systemd}/anubis@.service`);
             file.install("./run/default.env", `${etc}/default.env`);