ai2web 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 892b44b396f60be4ebd7af6bca0c19be6b1c3d8fdbdd2a66b2ed9235915c8690
-  data.tar.gz: a6705de41a0928bdddcf5787b13b72b53f0d45b6e47c4805deff898e5c650fad
+  metadata.gz: 1fe0e944f49b6072c4ae055b3d2db69492580564a0b2ea05f0f3ecf76bc98474
+  data.tar.gz: 62c79d2ecfc8f24a9351ba4cb6d82868f7c1877f2e1c16dd060dc1c2b3997384
 SHA512:
-  metadata.gz: 675f6db1358bf674c7579b27db5b5ca46f4e44be3cd76abacf793f4e10a25ef4f2b83fff596bf8bd65010476004c6c3e7b629e31344e6b8ee47de50fca91c1d6
-  data.tar.gz: df4a693934c5e3838a2e016034a79d4ca838295a0842d77117fbd52ba1fe17551ac50791e9dc156c4830a896633bd31a12802d58f0b14901cad6b6b24673eb3d
+  metadata.gz: 809c65cb23a78846e260ff419aecabcc99eb22ab03802349bf22c51a90b9d513abbe5f5336d6792e727aa11c1dc1f604bc4508281a6a0253490c6cd3363a94af
+  data.tar.gz: 732da62ffbf60019317538d5fbcc56c74bcc73291c9e6d65afd09b073aced6d35bdd392d19198a94289dbebd1c34796b32ae17bfa5293e2e3109c5d2b7f31bea

data/lib/ai2web/export.rb

@@ -87,10 +87,84 @@ module Ai2Web
         }
       }
     end
+
+    # OAuth 2.0 Protected Resource metadata (RFC 9728), for
+    # /.well-known/oauth-protected-resource. MCP clients read this to discover which
+    # authorization server guards the resource before starting a flow.
+    #
+    # Returns nil when the site does not advertise oauth2, so an auth surface the site cannot
+    # honour is never published.
+    def to_oauth_protected_resource(manifest)
+      m = Util.deep_stringify(manifest)
+      auth = m["auth"].is_a?(Hash) ? m["auth"] : {}
+      return nil unless Array(auth["methods"]).include?("oauth2")
+
+      site = m["site"].is_a?(Hash) ? m["site"] : {}
+      base = Util.trim_url(site["url"].to_s)
+      oauth2 = auth["oauth2"].is_a?(Hash) ? auth["oauth2"] : {}
+      issuer = base
+      authz = oauth2["authorization_url"].to_s
+      unless authz.empty?
+        begin
+          u = URI.parse(authz)
+          issuer = "#{u.scheme}://#{u.host}#{u.port && ![80, 443].include?(u.port) ? ":#{u.port}" : ""}" if u.scheme && u.host
+        rescue URI::InvalidURIError
+          # keep the site base as issuer
+        end
+      end
+      doc = {
+        "resource" => "#{base}/ai2w",
+        "authorization_servers" => [issuer],
+        "bearer_methods_supported" => ["header"]
+      }
+      scopes = oauth2["scopes"]
+      doc["scopes_supported"] = Array(scopes) if scopes && !Array(scopes).empty?
+      doc
+    end
+
+    # Map usage_policy onto Content Signals tokens. `search` stays yes because AI2Web exists to
+    # be discoverable; the AI signals are only asserted when the manifest states them, so an
+    # unset policy is never reported as a refusal. Nil when no policy is declared.
+    def to_content_signals(manifest)
+      m = Util.deep_stringify(manifest)
+      p = m["usage_policy"]
+      return nil unless p.is_a?(Hash) && !p.empty?
+
+      signals = ["search=yes"]
+      signals << "ai-input=#{p["content_reproduction"] ? "yes" : "no"}" if [true, false].include?(p["content_reproduction"])
+      signals << "ai-train=#{p["model_training"] ? "yes" : "no"}" if [true, false].include?(p["model_training"])
+      signals.join(", ")
+    end
+
+    # A robots.txt FRAGMENT carrying the usage policy and a pointer to the manifest. Append it to
+    # an existing robots.txt; it is never a replacement, and emits no Disallow rules.
+    def to_robots_txt(manifest)
+      m = Util.deep_stringify(manifest)
+      site = m["site"].is_a?(Hash) ? m["site"] : {}
+      base = Util.trim_url(site["url"].to_s)
+      lines = ["# AI2Web usage policy, projected from #{base}/ai2w", "User-agent: *"]
+      signals = to_content_signals(m)
+      lines << "Content-Signal: #{signals}" unless signals.nil?
+      lines << "# bulk_extraction: false - please use the /ai2w endpoints instead of crawling" if
+        m["usage_policy"].is_a?(Hash) && m["usage_policy"]["bulk_extraction"] == false
+      lines << "# AI2Web-Manifest: #{base}/ai2w"
+      "#{lines.join("\n")}\n"
+    end
+
+    # Value for an HTTP Link header advertising the manifest to non-HTML clients.
+    def to_discovery_link_header(manifest)
+      m = Util.deep_stringify(manifest)
+      site = m["site"].is_a?(Hash) ? m["site"] : {}
+      "<#{Util.trim_url(site["url"].to_s)}/ai2w>; rel=\"ai2w\""
+    end
   end
 
   module_function
 
   def to_llms_txt(manifest) = Export.to_llms_txt(manifest)
   def to_agent_json(manifest) = Export.to_agent_json(manifest)
+  def to_oauth_protected_resource(manifest) = Export.to_oauth_protected_resource(manifest)
+  def to_content_signals(manifest) = Export.to_content_signals(manifest)
+  def to_robots_txt(manifest) = Export.to_robots_txt(manifest)
+  def to_discovery_link_header(manifest) = Export.to_discovery_link_header(manifest)
 end

data/lib/ai2web/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Ai2Web
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ai2web
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - AI2Web Foundation
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-07-21 00:00:00.000000000 Z
+date: 2026-07-23 00:00:00.000000000 Z
 dependencies: []
 description: The Ruby implementation of the AI2Web protocol - describe your website
   once and make it understandable and actionable to any AI agent. Fluent manifest