context.dev 2.8.0 → 2.10.0

data/lib/context_dev/models/web_web_scrape_images_params.rb

@@ -31,8 +31,8 @@ module ContextDev
       #   group is kept. Images that cannot be downloaded or hashed are kept. Default:
       #   false.
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Dedupe, nil]
-      optional :dedupe, union: -> { ContextDev::WebWebScrapeImagesParams::Dedupe }
+      #   @return [Boolean, nil]
+      optional :dedupe, ContextDev::Internal::Type::Boolean
 
       # @!attribute enrichment
       #   Optional per-image processing, sent as deep-object query params such as
@@ -87,7 +87,7 @@ module ContextDev
       #
       #   @param actions [Array<ContextDev::Models::WebWebScrapeImagesParams::Action::Wait, ContextDev::Models::WebWebScrapeImagesParams::Action::Perform>, nil] Optional browser actions executed in array order after the page loads and before
       #
-      #   @param dedupe [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Dedupe] When true, visually duplicate images are removed: every image is loaded and perc
+      #   @param dedupe [Boolean] When true, visually duplicate images are removed: every image is loaded and perc
       #
       #   @param enrichment [ContextDev::Models::WebWebScrapeImagesParams::Enrichment, nil] Optional per-image processing, sent as deep-object query params such as enrichme
       #
@@ -156,49 +156,19 @@ module ContextDev
         #   @return [Array(ContextDev::Models::WebWebScrapeImagesParams::Action::Wait, ContextDev::Models::WebWebScrapeImagesParams::Action::Perform)]
       end
 
-      # When true, visually duplicate images are removed: every image is loaded and
-      # perceptually hashed, and only the highest-resolution copy of each duplicate
-      # group is kept. Images that cannot be downloaded or hashed are kept. Default:
-      # false.
-      module Dedupe
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Dedupe::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Dedupe::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeImagesParams::Dedupe::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
       class Enrichment < ContextDev::Internal::Type::BaseModel
         # @!attribute classification
         #   Classify each image by visual asset type.
         #
-        #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Classification, nil]
-        optional :classification, union: -> { ContextDev::WebWebScrapeImagesParams::Enrichment::Classification }
+        #   @return [Boolean, nil]
+        optional :classification, ContextDev::Internal::Type::Boolean
 
         # @!attribute hosted_url
         #   Host materializable images on the Brand.dev CDN and return their URL and MIME
         #   type.
         #
-        #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::HostedURL, nil]
-        optional :hosted_url,
-                 union: -> { ContextDev::WebWebScrapeImagesParams::Enrichment::HostedURL },
-                 api_name: :hostedUrl
+        #   @return [Boolean, nil]
+        optional :hosted_url, ContextDev::Internal::Type::Boolean, api_name: :hostedUrl
 
         # @!attribute max_time_per_ms
         #   Per-image enrichment timeout in milliseconds. Default: 30000. Maximum: 60000.
@@ -209,8 +179,8 @@ module ContextDev
         # @!attribute resolution
         #   Measure image width and height when possible.
         #
-        #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Resolution, nil]
-        optional :resolution, union: -> { ContextDev::WebWebScrapeImagesParams::Enrichment::Resolution }
+        #   @return [Boolean, nil]
+        optional :resolution, ContextDev::Internal::Type::Boolean
 
         # @!method initialize(classification: nil, hosted_url: nil, max_time_per_ms: nil, resolution: nil)
         #   Some parameter documentations has been truncated, see
@@ -219,95 +189,13 @@ module ContextDev
         #   Optional per-image processing, sent as deep-object query params such as
         #   enrichment[resolution]=true.
         #
-        #   @param classification [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Classification] Classify each image by visual asset type.
+        #   @param classification [Boolean] Classify each image by visual asset type.
         #
-        #   @param hosted_url [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::HostedURL] Host materializable images on the Brand.dev CDN and return their URL and MIME ty
+        #   @param hosted_url [Boolean] Host materializable images on the Brand.dev CDN and return their URL and MIME ty
         #
         #   @param max_time_per_ms [Integer] Per-image enrichment timeout in milliseconds. Default: 30000. Maximum: 60000.
         #
-        #   @param resolution [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Resolution] Measure image width and height when possible.
-
-        # Classify each image by visual asset type.
-        #
-        # @see ContextDev::Models::WebWebScrapeImagesParams::Enrichment#classification
-        module Classification
-          extend ContextDev::Internal::Type::Union
-
-          variant ContextDev::Internal::Type::Boolean
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Classification::TRUE }
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Classification::FALSE }
-
-          # @!method self.variants
-          #   @return [Array(Boolean, Symbol)]
-
-          define_sorbet_constant!(:Variants) do
-            T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeImagesParams::Enrichment::Classification::TaggedSymbol) }
-          end
-
-          # @!group
-
-          TRUE = :true
-          FALSE = :false
-
-          # @!endgroup
-        end
-
-        # Host materializable images on the Brand.dev CDN and return their URL and MIME
-        # type.
-        #
-        # @see ContextDev::Models::WebWebScrapeImagesParams::Enrichment#hosted_url
-        module HostedURL
-          extend ContextDev::Internal::Type::Union
-
-          variant ContextDev::Internal::Type::Boolean
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::HostedURL::TRUE }
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::HostedURL::FALSE }
-
-          # @!method self.variants
-          #   @return [Array(Boolean, Symbol)]
-
-          define_sorbet_constant!(:Variants) do
-            T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeImagesParams::Enrichment::HostedURL::TaggedSymbol) }
-          end
-
-          # @!group
-
-          TRUE = :true
-          FALSE = :false
-
-          # @!endgroup
-        end
-
-        # Measure image width and height when possible.
-        #
-        # @see ContextDev::Models::WebWebScrapeImagesParams::Enrichment#resolution
-        module Resolution
-          extend ContextDev::Internal::Type::Union
-
-          variant ContextDev::Internal::Type::Boolean
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Resolution::TRUE }
-
-          variant const: -> { ContextDev::Models::WebWebScrapeImagesParams::Enrichment::Resolution::FALSE }
-
-          # @!method self.variants
-          #   @return [Array(Boolean, Symbol)]
-
-          define_sorbet_constant!(:Variants) do
-            T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeImagesParams::Enrichment::Resolution::TaggedSymbol) }
-          end
-
-          # @!group
-
-          TRUE = :true
-          FALSE = :false
-
-          # @!endgroup
-        end
+        #   @param resolution [Boolean] Measure image width and height when possible.
       end
     end
   end

data/lib/context_dev/models/web_web_scrape_md_params.rb

@@ -50,20 +50,28 @@ module ContextDev
       # @!attribute include_frames
       #   When true, the contents of iframes are rendered to Markdown.
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeFrames, nil]
-      optional :include_frames, union: -> { ContextDev::WebWebScrapeMdParams::IncludeFrames }
+      #   @return [Boolean, nil]
+      optional :include_frames, ContextDev::Internal::Type::Boolean
+
+      # @!attribute include_html
+      #   When true, the response also includes an `html` field with the page HTML the
+      #   Markdown was converted from — the same body the Scrape HTML endpoint returns for
+      #   the equivalent request.
+      #
+      #   @return [Boolean, nil]
+      optional :include_html, ContextDev::Internal::Type::Boolean
 
       # @!attribute include_images
       #   Include image references in Markdown output
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeImages, nil]
-      optional :include_images, union: -> { ContextDev::WebWebScrapeMdParams::IncludeImages }
+      #   @return [Boolean, nil]
+      optional :include_images, ContextDev::Internal::Type::Boolean
 
       # @!attribute include_links
       #   Preserve hyperlinks in Markdown output
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeLinks, nil]
-      optional :include_links, union: -> { ContextDev::WebWebScrapeMdParams::IncludeLinks }
+      #   @return [Boolean, nil]
+      optional :include_links, ContextDev::Internal::Type::Boolean
 
       # @!attribute include_selectors
       #   CSS selectors. When provided, only matching HTML subtrees (and their
@@ -93,14 +101,14 @@ module ContextDev
       #   converting to Markdown. Defaults to false. This adds a bit of latency in
       #   exchange for more stable output on animated pages.
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::SettleAnimations, nil]
-      optional :settle_animations, union: -> { ContextDev::WebWebScrapeMdParams::SettleAnimations }
+      #   @return [Boolean, nil]
+      optional :settle_animations, ContextDev::Internal::Type::Boolean
 
       # @!attribute shorten_base64_images
       #   Shorten base64-encoded image data in the Markdown output
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::ShortenBase64Images, nil]
-      optional :shorten_base64_images, union: -> { ContextDev::WebWebScrapeMdParams::ShortenBase64Images }
+      #   @return [Boolean, nil]
+      optional :shorten_base64_images, ContextDev::Internal::Type::Boolean
 
       # @!attribute tags
       #   Optional comma-separated caller-defined tags for tracking this request. Tags are
@@ -122,8 +130,8 @@ module ContextDev
       #   Extract only the main content of the page, excluding headers, footers, sidebars,
       #   and navigation
       #
-      #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::UseMainContentOnly, nil]
-      optional :use_main_content_only, union: -> { ContextDev::WebWebScrapeMdParams::UseMainContentOnly }
+      #   @return [Boolean, nil]
+      optional :use_main_content_only, ContextDev::Internal::Type::Boolean
 
       # @!attribute wait_for_ms
       #   Optional browser wait time in milliseconds after initial page load before
@@ -141,7 +149,7 @@ module ContextDev
       #   @return [Symbol, ContextDev::Models::WebWebScrapeMdParams::Zdr, nil]
       optional :zdr, enum: -> { ContextDev::WebWebScrapeMdParams::Zdr }
 
-      # @!method initialize(url:, actions: nil, country: nil, exclude_selectors: nil, headers: nil, include_frames: nil, include_images: nil, include_links: nil, include_selectors: nil, max_age_ms: nil, pdf: nil, settle_animations: nil, shorten_base64_images: nil, tags: nil, timeout_ms: nil, use_main_content_only: nil, wait_for_ms: nil, zdr: nil, request_options: {})
+      # @!method initialize(url:, actions: nil, country: nil, exclude_selectors: nil, headers: nil, include_frames: nil, include_html: nil, include_images: nil, include_links: nil, include_selectors: nil, max_age_ms: nil, pdf: nil, settle_animations: nil, shorten_base64_images: nil, tags: nil, timeout_ms: nil, use_main_content_only: nil, wait_for_ms: nil, zdr: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeMdParams} for more details.
       #
@@ -155,11 +163,13 @@ module ContextDev
       #
       #   @param headers [Hash{Symbol=>String}] Optional outbound HTTP headers forwarded only to the target URL, sent as deep-ob
       #
-      #   @param include_frames [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeFrames] When true, the contents of iframes are rendered to Markdown.
+      #   @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown.
       #
-      #   @param include_images [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeImages] Include image references in Markdown output
+      #   @param include_html [Boolean] When true, the response also includes an `html` field with the page HTML the Mar
       #
-      #   @param include_links [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeLinks] Preserve hyperlinks in Markdown output
+      #   @param include_images [Boolean] Include image references in Markdown output
+      #
+      #   @param include_links [Boolean] Preserve hyperlinks in Markdown output
       #
       #   @param include_selectors [Array<String>, nil] CSS selectors. When provided, only matching HTML subtrees (and their descendants
       #
@@ -167,15 +177,15 @@ module ContextDev
       #
       #   @param pdf [ContextDev::Models::WebWebScrapeMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
-      #   @param settle_animations [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::SettleAnimations] When true, waits briefly for CSS and transition animations to settle before conv
+      #   @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before conv
       #
-      #   @param shorten_base64_images [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::ShortenBase64Images] Shorten base64-encoded image data in the Markdown output
+      #   @param shorten_base64_images [Boolean] Shorten base64-encoded image data in the Markdown output
       #
       #   @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are
       #
       #   @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
-      #   @param use_main_content_only [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::UseMainContentOnly] Extract only the main content of the page, excluding headers, footers, sidebars,
+      #   @param use_main_content_only [Boolean] Extract only the main content of the page, excluding headers, footers, sidebars,
       #
       #   @param wait_for_ms [Integer, nil] Optional browser wait time in milliseconds after initial page load before conver
       #
@@ -450,81 +460,6 @@ module ContextDev
         #   @return [Array<Symbol>]
       end
 
-      # When true, the contents of iframes are rendered to Markdown.
-      module IncludeFrames
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeFrames::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeFrames::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::IncludeFrames::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
-      # Include image references in Markdown output
-      module IncludeImages
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeImages::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeImages::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::IncludeImages::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
-      # Preserve hyperlinks in Markdown output
-      module IncludeLinks
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeLinks::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::IncludeLinks::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::IncludeLinks::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
       class Pdf < ContextDev::Internal::Type::BaseModel
         # @!attribute end_
         #   Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
@@ -534,21 +469,20 @@ module ContextDev
         optional :end_, Integer, api_name: :end
 
         # @!attribute ocr
-        #   When true, detect and OCR images embedded in the selected PDF pages, inserting
-        #   recognized text at each image's position in page reading order while preserving
-        #   the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
+        #   When true, OCR the selected PDF pages that have no usable text layer (scans),
+        #   replacing each recovered page's text with the OCR result while pages with a real
+        #   text layer keep it. Billed at 1 credit per page OCR actually recovered, on top
+        #   of the base request cost. When false, no OCR runs.
         #
-        #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::Pdf::Ocr, nil]
-        optional :ocr, union: -> { ContextDev::WebWebScrapeMdParams::Pdf::Ocr }
+        #   @return [Boolean, nil]
+        optional :ocr, ContextDev::Internal::Type::Boolean
 
         # @!attribute should_parse
         #   When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
-        #   a 400 WEBSITE_ACCESS_ERROR is returned.
+        #   a 400 PDF_SKIPPED is returned.
         #
-        #   @return [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::Pdf::ShouldParse, nil]
-        optional :should_parse,
-                 union: -> { ContextDev::WebWebScrapeMdParams::Pdf::ShouldParse },
-                 api_name: :shouldParse
+        #   @return [Boolean, nil]
+        optional :should_parse, ContextDev::Internal::Type::Boolean, api_name: :shouldParse
 
         # @!attribute start
         #   First 1-based PDF page to parse. When omitted, parsing starts at the first page.
@@ -565,146 +499,11 @@ module ContextDev
         #
         #   @param end_ [Integer] Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Mus
         #
-        #   @param ocr [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::Pdf::Ocr] When true, detect and OCR images embedded in the selected PDF pages, inserting r
+        #   @param ocr [Boolean] When true, OCR the selected PDF pages that have no usable text layer (scans), re
         #
-        #   @param should_parse [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::Pdf::ShouldParse] When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
+        #   @param should_parse [Boolean] When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
         #
         #   @param start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.
-
-        # When true, detect and OCR images embedded in the selected PDF pages, inserting
-        # recognized text at each image's position in page reading order while preserving
-        # the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
-        #
-        # @see ContextDev::Models::WebWebScrapeMdParams::Pdf#ocr
-        module Ocr
-          extend ContextDev::Internal::Type::Union
-
-          variant ContextDev::Internal::Type::Boolean
-
-          variant const: -> { ContextDev::Models::WebWebScrapeMdParams::Pdf::Ocr::TRUE }
-
-          variant const: -> { ContextDev::Models::WebWebScrapeMdParams::Pdf::Ocr::FALSE }
-
-          # @!method self.variants
-          #   @return [Array(Boolean, Symbol)]
-
-          define_sorbet_constant!(:Variants) do
-            T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::Pdf::Ocr::TaggedSymbol) }
-          end
-
-          # @!group
-
-          TRUE = :true
-          FALSE = :false
-
-          # @!endgroup
-        end
-
-        # When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
-        # a 400 WEBSITE_ACCESS_ERROR is returned.
-        #
-        # @see ContextDev::Models::WebWebScrapeMdParams::Pdf#should_parse
-        module ShouldParse
-          extend ContextDev::Internal::Type::Union
-
-          variant ContextDev::Internal::Type::Boolean
-
-          variant const: -> { ContextDev::Models::WebWebScrapeMdParams::Pdf::ShouldParse::TRUE }
-
-          variant const: -> { ContextDev::Models::WebWebScrapeMdParams::Pdf::ShouldParse::FALSE }
-
-          # @!method self.variants
-          #   @return [Array(Boolean, Symbol)]
-
-          define_sorbet_constant!(:Variants) do
-            T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::Pdf::ShouldParse::TaggedSymbol) }
-          end
-
-          # @!group
-
-          TRUE = :true
-          FALSE = :false
-
-          # @!endgroup
-        end
-      end
-
-      # When true, waits briefly for CSS and transition animations to settle before
-      # converting to Markdown. Defaults to false. This adds a bit of latency in
-      # exchange for more stable output on animated pages.
-      module SettleAnimations
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::SettleAnimations::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::SettleAnimations::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::SettleAnimations::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
-      # Shorten base64-encoded image data in the Markdown output
-      module ShortenBase64Images
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::ShortenBase64Images::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::ShortenBase64Images::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::ShortenBase64Images::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
-      end
-
-      # Extract only the main content of the page, excluding headers, footers, sidebars,
-      # and navigation
-      module UseMainContentOnly
-        extend ContextDev::Internal::Type::Union
-
-        variant ContextDev::Internal::Type::Boolean
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::UseMainContentOnly::TRUE }
-
-        variant const: -> { ContextDev::Models::WebWebScrapeMdParams::UseMainContentOnly::FALSE }
-
-        # @!method self.variants
-        #   @return [Array(Boolean, Symbol)]
-
-        define_sorbet_constant!(:Variants) do
-          T.type_alias { T.any(T::Boolean, ContextDev::WebWebScrapeMdParams::UseMainContentOnly::TaggedSymbol) }
-        end
-
-        # @!group
-
-        TRUE = :true
-        FALSE = :false
-
-        # @!endgroup
       end
 
       # Set to enabled to bypass shared caches and omit request and response content

data/lib/context_dev/models/web_web_scrape_md_response.rb

@@ -51,6 +51,14 @@ module ContextDev
       #   @return [Boolean, nil]
       optional :actions_html_stale, ContextDev::Internal::Type::Boolean, api_name: :actionsHtmlStale
 
+      # @!attribute html
+      #   Only present when includeHTML=true: the page HTML the Markdown was converted
+      #   from — the same body the Scrape HTML endpoint returns for the equivalent
+      #   request.
+      #
+      #   @return [String, nil]
+      optional :html, String
+
       # @!attribute key_metadata
       #   Metadata about the API key used for the request. Included in every response
       #   whenever a valid API key is provided, even when the response status is not 200.
@@ -58,7 +66,7 @@ module ContextDev
       #   @return [ContextDev::Models::WebWebScrapeMdResponse::KeyMetadata, nil]
       optional :key_metadata, -> { ContextDev::Models::WebWebScrapeMdResponse::KeyMetadata }
 
-      # @!method initialize(content_length:, markdown:, metadata:, success:, url:, actions_applied: nil, actions_html_stale: nil, key_metadata: nil)
+      # @!method initialize(content_length:, markdown:, metadata:, success:, url:, actions_applied: nil, actions_html_stale: nil, html: nil, key_metadata: nil)
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeMdResponse} for more details.
       #
@@ -76,6 +84,8 @@ module ContextDev
       #
       #   @param actions_html_stale [Boolean] True when an action was applied but the returned content could not be refreshed
       #
+      #   @param html [String] Only present when includeHTML=true: the page HTML the Markdown was converted fro
+      #
       #   @param key_metadata [ContextDev::Models::WebWebScrapeMdResponse::KeyMetadata] Metadata about the API key used for the request. Included in every response when
 
       # @see ContextDev::Models::WebWebScrapeMdResponse#metadata
@@ -132,6 +142,14 @@ module ContextDev
         #   @return [String, nil]
         optional :favicon, String
 
+        # @!attribute headings
+        #   Page headings (h1–h6) in document order, extracted from the unfiltered document.
+        #   Capped at the first 500 headings. Omitted when the page has none.
+        #
+        #   @return [Array<ContextDev::Models::WebWebScrapeMdResponse::Metadata::Heading>, nil]
+        optional :headings,
+                 -> { ContextDev::Internal::Type::ArrayOf[ContextDev::Models::WebWebScrapeMdResponse::Metadata::Heading] }
+
         # @!attribute image
         #   Primary resolved preview image from Open Graph, Twitter, or image metadata.
         #
@@ -203,7 +221,7 @@ module ContextDev
         optional :twitter,
                  -> { ContextDev::Internal::Type::HashOf[union: ContextDev::Models::WebWebScrapeMdResponse::Metadata::Twitter] }
 
-        # @!method initialize(final_url:, source_url:, additional_meta: nil, alternates: nil, author: nil, canonical_url: nil, description: nil, favicon: nil, image: nil, json_ld: nil, keywords: nil, language: nil, modified_time: nil, open_graph: nil, published_time: nil, robots: nil, site_name: nil, title: nil, twitter: nil)
+        # @!method initialize(final_url:, source_url:, additional_meta: nil, alternates: nil, author: nil, canonical_url: nil, description: nil, favicon: nil, headings: nil, image: nil, json_ld: nil, keywords: nil, language: nil, modified_time: nil, open_graph: nil, published_time: nil, robots: nil, site_name: nil, title: nil, twitter: nil)
         #   Some parameter documentations has been truncated, see
         #   {ContextDev::Models::WebWebScrapeMdResponse::Metadata} for more details.
         #
@@ -225,6 +243,8 @@ module ContextDev
         #
         #   @param favicon [String] Resolved favicon URL, when present.
         #
+        #   @param headings [Array<ContextDev::Models::WebWebScrapeMdResponse::Metadata::Heading>] Page headings (h1–h6) in document order, extracted from the unfiltered document.
+        #
         #   @param image [String] Primary resolved preview image from Open Graph, Twitter, or image metadata.
         #
         #   @param json_ld [Array<Hash{Symbol=>Object}>] JSON-LD structured data blocks parsed from the page.
@@ -296,6 +316,25 @@ module ContextDev
           #   @param type [String] Alternate resource MIME type, when present.
         end
 
+        class Heading < ContextDev::Internal::Type::BaseModel
+          # @!attribute level
+          #   Heading level, 1–6 (from h1–h6).
+          #
+          #   @return [Integer]
+          required :level, Integer
+
+          # @!attribute text
+          #   Heading text with whitespace collapsed, truncated to 1000 characters.
+          #
+          #   @return [String]
+          required :text, String
+
+          # @!method initialize(level:, text:)
+          #   @param level [Integer] Heading level, 1–6 (from h1–h6).
+          #
+          #   @param text [String] Heading text with whitespace collapsed, truncated to 1000 characters.
+        end
+
         module OpenGraph
           extend ContextDev::Internal::Type::Union
 

data/lib/context_dev/models/web_web_scrape_sitemap_params.rb

@@ -28,6 +28,14 @@ module ContextDev
       #   @return [Integer, nil]
       optional :max_links, Integer
 
+      # @!attribute search
+      #   Optional search phrase. When provided, the crawled sitemap is filtered to the
+      #   pages whose URLs are about that phrase, most relevant first, and the request
+      #   costs 2 credits instead of 1.
+      #
+      #   @return [String, nil]
+      optional :search, String
+
       # @!attribute sitemap_url
       #   Optional explicit sitemap URL. When provided, exactly this sitemap is crawled
       #   instead of discovering the domain's sitemaps.
@@ -67,7 +75,7 @@ module ContextDev
       #   @return [Symbol, ContextDev::Models::WebWebScrapeSitemapParams::Zdr, nil]
       optional :zdr, enum: -> { ContextDev::WebWebScrapeSitemapParams::Zdr }
 
-      # @!method initialize(domain:, headers: nil, max_links: nil, sitemap_url: nil, tags: nil, timeout_ms: nil, url_regex: nil, zdr: nil, request_options: {})
+      # @!method initialize(domain:, headers: nil, max_links: nil, search: nil, sitemap_url: nil, tags: nil, timeout_ms: nil, url_regex: nil, zdr: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeSitemapParams} for more details.
       #
@@ -77,6 +85,8 @@ module ContextDev
       #
       #   @param max_links [Integer] Maximum number of links to return from the sitemap crawl. Defaults to 10,000. Mi
       #
+      #   @param search [String] Optional search phrase. When provided, the crawled sitemap is filtered to the pa
+      #
       #   @param sitemap_url [String] Optional explicit sitemap URL. When provided, exactly this sitemap is crawled in
       #
       #   @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are