fix(data): add services folder to embedded filesystem

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

.github/workflows/docker-pr.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-tags: true
           fetch-depth: 0
@@ -25,7 +25,7 @@ jobs:
         uses: Homebrew/actions/setup-homebrew@main
 
       - name: Setup Homebrew cellar cache
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
         with:
           path: |
             /home/linuxbrew/.linuxbrew/Cellar
@@ -47,7 +47,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f # v5.8.0
         with:
           images: ghcr.io/${{ github.repository }}
 

.github/workflows/docker.yml

@@ -21,7 +21,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-tags: true
           fetch-depth: 0
@@ -35,7 +35,7 @@ jobs:
         uses: Homebrew/actions/setup-homebrew@main
 
       - name: Setup Homebrew cellar cache
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
         with:
           path: |
             /home/linuxbrew/.linuxbrew/Cellar
@@ -56,7 +56,7 @@ jobs:
           brew bundle
 
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1 # v3.5.0
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
@@ -64,7 +64,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f # v5.8.0
         with:
           images: ${{ env.IMAGE }}
 
@@ -78,7 +78,7 @@ jobs:
           SLOG_LEVEL: debug
 
       - name: Generate artifact attestation
-        uses: actions/attest-build-provenance@e8998f949152b193b063cb0ec769d69d929409be # v2.4.0
+        uses: actions/attest-build-provenance@977bb373ede98d70efdf65b84cb5f73e068dcc2a # v3.0.0
         with:
           subject-name: ${{ env.IMAGE }}
           subject-digest: ${{ steps.build.outputs.digest }}

.github/workflows/docs-deploy.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-24.04
 
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
 
@@ -25,7 +25,7 @@ jobs:
         uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1 # v3.5.0
         with:
           registry: ghcr.io
           username: techarohq
@@ -33,7 +33,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f # v5.8.0
         with:
           images: ghcr.io/techarohq/anubis/docs
           tags: |
@@ -53,14 +53,14 @@ jobs:
           push: true
 
       - name: Apply k8s manifests to limsa lominsa
-        uses: actions-hub/kubectl@b5b19eeb6a0ffde16637e398f8b96ef01eb8fdb7 # v1.33.3
+        uses: actions-hub/kubectl@af345ed727f0268738e65be48422e463cc67c220 # v1.34.0
         env:
           KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
         with:
           args: apply -k docs/manifest
 
       - name: Apply k8s manifests to limsa lominsa
-        uses: actions-hub/kubectl@b5b19eeb6a0ffde16637e398f8b96ef01eb8fdb7 # v1.33.3
+        uses: actions-hub/kubectl@af345ed727f0268738e65be48422e463cc67c220 # v1.34.0
         env:
           KUBE_CONFIG: ${{ secrets.LIMSA_LOMINSA_KUBECONFIG }}
         with:

.github/workflows/docs-test.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-24.04
 
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
 
@@ -22,7 +22,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f # v5.8.0
         with:
           images: ghcr.io/techarohq/anubis/docs
           tags: |

.github/workflows/go.yml

@@ -15,7 +15,7 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+    - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
       with:
         persist-credentials: false
 
@@ -28,7 +28,7 @@ jobs:
       uses: Homebrew/actions/setup-homebrew@main
 
     - name: Setup Homebrew cellar cache
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
       with:
         path: |
           /home/linuxbrew/.linuxbrew/Cellar
@@ -49,7 +49,7 @@ jobs:
         brew bundle
 
     - name: Setup Golang caches
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
       with:
         path: |
           ~/.cache/go-build
@@ -59,7 +59,7 @@ jobs:
           ${{ runner.os }}-golang-
 
     - name: Cache playwright binaries
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
       id: playwright-cache
       with:
         path: |

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

@@ -14,7 +14,7 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
           fetch-tags: true
@@ -29,7 +29,7 @@ jobs:
         uses: Homebrew/actions/setup-homebrew@main
 
       - name: Setup Homebrew cellar cache
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
         with:
           path: |
             /home/linuxbrew/.linuxbrew/Cellar
@@ -50,7 +50,7 @@ jobs:
           brew bundle
 
       - name: Setup Golang caches
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
         with:
           path: |
             ~/.cache/go-build

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

@@ -15,7 +15,7 @@ jobs:
     #runs-on: alrest-techarohq
     runs-on: ubuntu-24.04
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+    - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
       with:
         persist-credentials: false
         fetch-tags: true
@@ -30,7 +30,7 @@ jobs:
       uses: Homebrew/actions/setup-homebrew@main
 
     - name: Setup Homebrew cellar cache
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
       with:
         path: |
           /home/linuxbrew/.linuxbrew/Cellar
@@ -51,7 +51,7 @@ jobs:
         brew bundle
 
     - name: Setup Golang caches
-      uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
       with:
         path: |
           ~/.cache/go-build

.github/workflows/smoke-tests.yml

@@ -24,7 +24,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
 

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

@@ -18,13 +18,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-tags: true
           fetch-depth: 0
           persist-credentials: false
       - name: Log into registry
-        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
+        uses: docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1 # v3.5.0
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}

.github/workflows/ssh-ci.yml

@@ -20,7 +20,7 @@ jobs:
           - ci@ppc64le.techaro.lol
     steps:
       - name: Checkout code
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           fetch-tags: true
           fetch-depth: 0

.github/workflows/zizmor.yml

@@ -16,12 +16,12 @@ jobs:
       security-events: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
         with:
           persist-credentials: false
 
       - name: Install the latest version of uv
-        uses: astral-sh/setup-uv@e92bafb6253dcd438e0484186d7669ea7a8ca1cc # v6.4.3
+        uses: astral-sh/setup-uv@4959332f0f014c5280e7eac8b70c90cb574c9f9b # v6.6.0
 
       - name: Run zizmor 🌈
         run: uvx zizmor --format sarif . > results.sarif 
@@ -29,7 +29,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} 
 
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@4e828ff8d448a8a6e532957b1811f387a63867e8 # v3.29.4
+        uses: github/codeql-action/upload-sarif@3c3833e0f8c1c83d449a7478aa59c036a9165498 # v3.29.11
         with:
           sarif_file: results.sarif
           category: zizmor

cmd/robots2policy/main.go

@@ -29,7 +29,7 @@ var (
 )
 
 type RobotsRule struct {
-	UserAgent   string
+	UserAgents  []string
 	Disallows   []string
 	Allows      []string
 	CrawlDelay  int
@@ -130,10 +130,26 @@ func main() {
 	}
 }
 
+func createRuleFromAccumulated(userAgents, disallows, allows []string, crawlDelay int) RobotsRule {
+	rule := RobotsRule{
+		UserAgents: make([]string, len(userAgents)),
+		Disallows:  make([]string, len(disallows)),
+		Allows:     make([]string, len(allows)),
+		CrawlDelay: crawlDelay,
+	}
+	copy(rule.UserAgents, userAgents)
+	copy(rule.Disallows, disallows)
+	copy(rule.Allows, allows)
+	return rule
+}
+
 func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
 	scanner := bufio.NewScanner(input)
 	var rules []RobotsRule
-	var currentRule *RobotsRule
+	var currentUserAgents []string
+	var currentDisallows []string
+	var currentAllows []string
+	var currentCrawlDelay int
 
 	for scanner.Scan() {
 		line := strings.TrimSpace(scanner.Text())
@@ -154,38 +170,42 @@ func parseRobotsTxt(input io.Reader) ([]RobotsRule, error) {
 
 		switch directive {
 		case "user-agent":
-			// Start a new rule section
+			// If we have accumulated rules with directives and encounter a new user-agent,
-			if currentRule != nil {
+			// flush the current rules
-				rules = append(rules, *currentRule)
+			if len(currentUserAgents) > 0 && (len(currentDisallows) > 0 || len(currentAllows) > 0 || currentCrawlDelay > 0) {
-			}
+				rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
-			currentRule = &RobotsRule{
+				rules = append(rules, rule)
-				UserAgent: value,
+				// Reset for next group
-				Disallows: make([]string, 0),
+				currentUserAgents = nil
-				Allows:    make([]string, 0),
+				currentDisallows = nil
+				currentAllows = nil
+				currentCrawlDelay = 0
 			}
+			currentUserAgents = append(currentUserAgents, value)
 
 		case "disallow":
-			if currentRule != nil && value != "" {
+			if len(currentUserAgents) > 0 && value != "" {
-				currentRule.Disallows = append(currentRule.Disallows, value)
+				currentDisallows = append(currentDisallows, value)
 			}
 
 		case "allow":
-			if currentRule != nil && value != "" {
+			if len(currentUserAgents) > 0 && value != "" {
-				currentRule.Allows = append(currentRule.Allows, value)
+				currentAllows = append(currentAllows, value)
 			}
 
 		case "crawl-delay":
-			if currentRule != nil {
+			if len(currentUserAgents) > 0 {
 				if delay, err := parseIntSafe(value); err == nil {
-					currentRule.CrawlDelay = delay
+					currentCrawlDelay = delay
 				}
 			}
 		}
 	}
 
-	// Don't forget the last rule
+	// Don't forget the last group of rules
-	if currentRule != nil {
+	if len(currentUserAgents) > 0 {
-		rules = append(rules, *currentRule)
+		rule := createRuleFromAccumulated(currentUserAgents, currentDisallows, currentAllows, currentCrawlDelay)
+		rules = append(rules, rule)
 	}
 
 	// Mark blacklisted user agents (those with "Disallow: /")
@@ -211,10 +231,11 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 	var anubisRules []AnubisRule
 	ruleCounter := 0
 
+	// Process each robots rule individually
 	for _, robotsRule := range robotsRules {
-		userAgent := robotsRule.UserAgent
+		userAgents := robotsRule.UserAgents
 
-		// Handle crawl delay as weight adjustment (do this first before any continues)
+		// Handle crawl delay
 		if robotsRule.CrawlDelay > 0 && *crawlDelay > 0 {
 			ruleCounter++
 			rule := AnubisRule{
@@ -223,20 +244,32 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 				Weight: &config.Weight{Adjust: *crawlDelay},
 			}
 
-			if userAgent == "*" {
+			if len(userAgents) == 1 && userAgents[0] == "*" {
 				rule.Expression = &config.ExpressionOrList{
 					All: []string{"true"}, // Always applies
 				}
-			} else {
+			} else if len(userAgents) == 1 {
 				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgents[0])},
+				}
+			} else {
+				// Multiple user agents - use any block
+				var expressions []string
+				for _, ua := range userAgents {
+					if ua == "*" {
+						expressions = append(expressions, "true")
+					} else {
+						expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
+					}
+				}
+				rule.Expression = &config.ExpressionOrList{
+					Any: expressions,
 				}
 			}
-
 			anubisRules = append(anubisRules, rule)
 		}
 
-		// Handle blacklisted user agents (complete deny/challenge)
+		// Handle blacklisted user agents
 		if robotsRule.IsBlacklist {
 			ruleCounter++
 			rule := AnubisRule{
@@ -244,21 +277,36 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 				Action: *userAgentDeny,
 			}
 
-			if userAgent == "*" {
+			if len(userAgents) == 1 {
-				// This would block everything - convert to a weight adjustment instead
+				userAgent := userAgents[0]
-				rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
+				if userAgent == "*" {
-				rule.Action = "WEIGH"
+					// This would block everything - convert to a weight adjustment instead
-				rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
+					rule.Name = fmt.Sprintf("%s-global-restriction-%d", *policyName, ruleCounter)
-				rule.Expression = &config.ExpressionOrList{
+					rule.Action = "WEIGH"
-					All: []string{"true"}, // Always applies
+					rule.Weight = &config.Weight{Adjust: 20} // Increase difficulty significantly
+					rule.Expression = &config.ExpressionOrList{
+						All: []string{"true"}, // Always applies
+					}
+				} else {
+					rule.Expression = &config.ExpressionOrList{
+						All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					}
 				}
 			} else {
+				// Multiple user agents - use any block
+				var expressions []string
+				for _, ua := range userAgents {
+					if ua == "*" {
+						expressions = append(expressions, "true")
+					} else {
+						expressions = append(expressions, fmt.Sprintf("userAgent.contains(%q)", ua))
+					}
+				}
 				rule.Expression = &config.ExpressionOrList{
-					All: []string{fmt.Sprintf("userAgent.contains(%q)", userAgent)},
+					Any: expressions,
 				}
 			}
 			anubisRules = append(anubisRules, rule)
-			continue
 		}
 
 		// Handle specific disallow rules
@@ -276,9 +324,33 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 			// Build CEL expression
 			var conditions []string
 
-			// Add user agent condition if not wildcard
+			// Add user agent conditions
-			if userAgent != "*" {
+			if len(userAgents) == 1 && userAgents[0] == "*" {
-				conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgent))
+				// Wildcard user agent - no user agent condition needed
+			} else if len(userAgents) == 1 {
+				conditions = append(conditions, fmt.Sprintf("userAgent.contains(%q)", userAgents[0]))
+			} else {
+				// For multiple user agents, we need to use a more complex expression
+				// This is a limitation - we can't easily combine any for user agents with all for path
+				// So we'll create separate rules for each user agent
+				for _, ua := range userAgents {
+					if ua == "*" {
+						continue // Skip wildcard as it's handled separately
+					}
+					ruleCounter++
+					subRule := AnubisRule{
+						Name:   fmt.Sprintf("%s-disallow-%d", *policyName, ruleCounter),
+						Action: *baseAction,
+						Expression: &config.ExpressionOrList{
+							All: []string{
+								fmt.Sprintf("userAgent.contains(%q)", ua),
+								buildPathCondition(disallow),
+							},
+						},
+					}
+					anubisRules = append(anubisRules, subRule)
+				}
+				continue
 			}
 
 			// Add path condition
@@ -291,7 +363,6 @@ func convertToAnubisRules(robotsRules []RobotsRule) []AnubisRule {
 
 			anubisRules = append(anubisRules, rule)
 		}
-
 	}
 
 	return anubisRules

cmd/robots2policy/robots2policy_test.go

@@ -78,6 +78,12 @@ func TestDataFileConversion(t *testing.T) {
 			expectedFile: "complex.yaml",
 			options:      TestOptions{format: "yaml", crawlDelayWeight: 5},
 		},
+		{
+			name:         "consecutive_user_agents",
+			robotsFile:   "consecutive.robots.txt",
+			expectedFile: "consecutive.yaml",
+			options:      TestOptions{format: "yaml", crawlDelayWeight: 3},
+		},
 	}
 
 	for _, tc := range testCases {

cmd/robots2policy/testdata/blacklist.yaml

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

cmd/robots2policy/testdata/complex.yaml

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

cmd/robots2policy/testdata/consecutive.robots.txt

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

cmd/robots2policy/testdata/consecutive.yaml

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

cmd/robots2policy/testdata/simple.json

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

data/embed.go

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

docs/docs/CHANGELOG.md

@@ -13,7 +13,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- This changes the project to: -->
 
+- Document missing environment variables in installation guide: `SLOG_LEVEL`, `COOKIE_PREFIX`, `FORCED_LANGUAGE`, and `TARGET_DISABLE_KEEPALIVE` ([#1086](https://github.com/TecharoHQ/anubis/pull/1086))
+- Fixed `robots2policy` to properly group consecutive user agents into `any:` instead of only processing the last one ([#925](https://github.com/TecharoHQ/anubis/pull/925))
 - Add the [`s3api` storage backend](./admin/policies.mdx#s3api) to allow Anubis to use S3 API compatible object storage as its storage backend.
+- Add the `services` folder to the embedded data filesystem.
+
+### Bug Fixes
+
+Sometimes the enhanced temporal assurance in [#1038](https://github.com/TecharoHQ/anubis/pull/1038) and [#1068](https://github.com/TecharoHQ/anubis/pull/1068) could backfire because Chromium and its ilk randomize the amount of time they wait in order to avoid a timing side channel attack. This has been fixed by both increasing the amount of time a client has to wait for the metarefresh and preact challenges as well as making the server side logic more permissive.
 
 ## v1.22.0: Yda Hext
 

docs/docs/admin/installation.mdx

@@ -59,7 +59,7 @@ Currently the following settings are configurable via the policy file:
 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 (everything starting with `/.within.website/x/anubis/`). 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.                                                                                                                                                                                                                                                                                                                                                              |
@@ -67,6 +67,7 @@ Anubis uses these environment variables for configuration:
 | `COOKIE_DYNAMIC_DOMAIN`        | false                   | If set to true, automatically set cookie domain fields based on the hostname of the request. EG: if you are making a request to `anubis.techaro.lol`, the Anubis cookie will be valid for any subdomain of `techaro.lol`.                                                                                                                                                                                                                                                                               |
 | `COOKIE_EXPIRATION_TIME`       | `168h`                  | The amount of time the authorization cookie is valid for.                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | `COOKIE_PARTITIONED`           | `false`                 | If set to `true`, enables the [partitioned (CHIPS) flag](https://developers.google.com/privacy-sandbox/cookies/chips), meaning that Anubis inside an iframe has a different set of cookies than the domain hosting the iframe.                                                                                                                                                                                                                                                                          |
+| `COOKIE_PREFIX`                | `anubis-cookie`         | The prefix used for browser cookies created by Anubis. Useful for customization or avoiding conflicts with other applications.                                                                                                                                                                                                                                                                                                                                                                          |
 | `COOKIE_SECURE`                | `true`                  | If set to `true`, enables the [Secure flag](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Cookies#block_access_to_your_cookies), meaning that the cookies will only be transmitted over HTTPS. If Anubis is used in an unsecure context (plain HTTP), this will be need to be set to false                                                                                                                                                                                                   |
 | `DIFFICULTY`                   | `4`                     | The difficulty of the challenge, or the number of leading zeroes that must be in successful responses.                                                                                                                                                                                                                                                                                                                                                                                                  |
 | `ED25519_PRIVATE_KEY_HEX`      | unset                   | The hex-encoded ed25519 private key used to sign Anubis responses. If this is not set, Anubis will generate one for you. This should be exactly 64 characters long. When running multiple instances on the same base domain, the key must be the same across all instances. See below for details.                                                                                                                                                                                                      |
@@ -81,6 +82,7 @@ Anubis uses these environment variables for configuration:
 | `PUBLIC_URL`                   | unset                   | The externally accessible URL for this Anubis instance, used for constructing redirect URLs (e.g., for Traefik forwardAuth).                                                                                                                                                                                                                                                                                                                                                                            |
 | `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.                                                                                                                                                                                                                |
+| `SLOG_LEVEL`                   | `INFO`                  | The log level for structured logging. Valid values are `DEBUG`, `INFO`, `WARN`, and `ERROR`. Set to `DEBUG` to see all requests, evaluations, and detailed diagnostic information.                                                                                                                                                                                                                                                                                                                      |
 | `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`.                                                                                                                                                                                                                                                                                                                                            |
@@ -100,10 +102,12 @@ If you don't know or understand what these settings mean, ignore them. These are
 
 | Environment Variable          | Default value | Explanation                                                                                                                                                             |
 | :---------------------------- | :------------ | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `TARGET_SNI`                  | unset         | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`.                                                                                         |
+| `FORCED_LANGUAGE`             | unset         | If set, forces Anubis to display challenge pages in the specified language instead of using the browser's Accept-Language header. Use ISO 639-1 language codes (e.g., `de` for German, `fr` for French). |
+| `HS512_SECRET`                | unset         | Secret string for JWT HS512 algorithm. If this is not set, Anubis will use ED25519 as defined via the variables above. The longer the better; 128 chars should suffice. |
+| `TARGET_DISABLE_KEEPALIVE`    | `false`       | If `true`, disables HTTP keep-alive for connections to the target backend. Useful for backends that don't handle keep-alive properly.                                   |
 | `TARGET_HOST`                 | unset         | If set, overrides the Host header in requests forwarded to `TARGET`.                                                                                                    |
 | `TARGET_INSECURE_SKIP_VERIFY` | `false`       | If `true`, skip TLS certificate validation for targets that listen over `https`. If your backend does not listen over `https`, ignore this setting.                     |
-| `HS512_SECRET`                | unset         | Secret string for JWT HS512 algorithm. If this is not set, Anubis will use ED25519 as defined via the variables above. The longer the better; 128 chars should suffice. |
+| `TARGET_SNI`                  | unset         | If set, overrides the TLS handshake hostname in requests forwarded to `TARGET`.                                                                                         |
 
 </details>
 

lib/challenge/metarefresh/metarefresh.go

@@ -43,7 +43,7 @@ func (i *Impl) Issue(r *http.Request, lg *slog.Logger, in *challenge.IssueInput)
 }
 
 func (i *Impl) Validate(r *http.Request, lg *slog.Logger, in *challenge.ValidateInput) error {
-	wantTime := in.Challenge.IssuedAt.Add(time.Duration(in.Rule.Challenge.Difficulty) * 950 * time.Millisecond)
+	wantTime := in.Challenge.IssuedAt.Add(time.Duration(in.Rule.Challenge.Difficulty) * 800 * time.Millisecond)
 
 	if time.Now().Before(wantTime) {
 		return challenge.NewError("validate", "insufficent time", fmt.Errorf("%w: wanted user to wait until at least %s", challenge.ErrFailed, wantTime.Format(time.RFC3339)))

lib/challenge/metarefresh/metarefresh.templ

@@ -13,6 +13,6 @@ templ page(redir string, difficulty int, loc *localization.SimpleLocalizer) {
 		<img style="display:none;" style="width:100%;max-width:256px;" src={ anubis.BasePrefix + "/.within.website/x/cmd/anubis/static/img/happy.webp?cacheBuster=" + anubis.Version }/>
 		<p id="status">{ loc.T("loading") }</p>
 		<p>{ loc.T("connection_security") }</p>
-		<meta http-equiv="refresh" content={ fmt.Sprintf("%d; url=%s", difficulty, redir) }/>
+		<meta http-equiv="refresh" content={ fmt.Sprintf("%d; url=%s", difficulty+1, redir) }/>
 	</div>
 }

lib/challenge/preact/js/app.jsx

@@ -32,7 +32,7 @@ const App = () => {
   useEffect(() => {
     const timer = setTimeout(() => {
       setPassed(true);
-    }, state.difficulty * 100);
+    }, state.difficulty * 125);
 
     return () => clearTimeout(timer);
   }, [challenge]);

lib/challenge/preact/preact.go

@@ -57,7 +57,7 @@ func (i *impl) Issue(r *http.Request, lg *slog.Logger, in *challenge.IssueInput)
 }
 
 func (i *impl) Validate(r *http.Request, lg *slog.Logger, in *challenge.ValidateInput) error {
-	wantTime := in.Challenge.IssuedAt.Add(time.Duration(in.Rule.Challenge.Difficulty) * 95 * time.Millisecond)
+	wantTime := in.Challenge.IssuedAt.Add(time.Duration(in.Rule.Challenge.Difficulty) * 80 * time.Millisecond)
 
 	if time.Now().Before(wantTime) {
 		return challenge.NewError("validate", "insufficent time", fmt.Errorf("%w: wanted user to wait until at least %s", challenge.ErrFailed, wantTime.Format(time.RFC3339)))