context.dev 1.5.0 → 1.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3f1e1d592ab2aa15df4461bc35f04e15efa1b44be4b88d19089042a707ee48c9
-  data.tar.gz: 7c2386bf4040b419009b3a68a366ff3d6a044116b71590d2036dfe69df4c24de
+  metadata.gz: cdcc91e409d0287f98b023ccbf680145a44d7c7ac9dffbf7be5fd1251fdbcc97
+  data.tar.gz: f5b48e008a3ed93e386513f9fcd8d215888ce5f8adfbc909cac3adcc5b313a27
 SHA512:
-  metadata.gz: 701c64ee8193b73126b354a672c698f41e240d49c96885f0aef670b7ef78e4bad4ad59a21b1ed3d43f16b4a84911ae8931519c09b3702c03c7ec3e86c85a0ca8
-  data.tar.gz: 74cc296a2d2d6d9a09a3105dc09813fca9de9ea5d98b193ab002fc07bd5cf169019897bff847fdb4291ccb0f4bbdddfd741256489642b42a317ade298e3f2dcd
+  metadata.gz: 37ab631ac032f9e15ff462159936d5a3b0e572890552853c4a22603530ae9f56cece10ee3e67a4a4a6e46f7b5f3bbbadcd6beebd2d8bf183243206e97e4f812c
+  data.tar.gz: 80757fb5ae2d334ec0716246dfd4702754fb442f6bb2b367b41419cd4f6274d6971b6c5ca7eeb5ff18972eda0c6d2bca9d2f609222e44c97627e1d5f3cc22777

data/CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## 1.7.0 (2026-04-24)
+
+Full Changelog: [v1.6.0...v1.7.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.6.0...v1.7.0)
+
+### Features
+
+* **api:** api update ([9c8b4d9](https://github.com/context-dot-dev/context-ruby-sdk/commit/9c8b4d9b1d813c5b7992998a3fa23cde63fe2f4c))
+
+## 1.6.0 (2026-04-23)
+
+Full Changelog: [v1.5.0...v1.6.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.5.0...v1.6.0)
+
+### Features
+
+* **api:** api update ([c1543f7](https://github.com/context-dot-dev/context-ruby-sdk/commit/c1543f7513b2d88b0c8ad8e209e62075bd9658bc))
+* **api:** api update ([9c98e20](https://github.com/context-dot-dev/context-ruby-sdk/commit/9c98e20725dcda8466a2274b61be75943d0564d9))
+* **api:** api update ([8ccafd9](https://github.com/context-dot-dev/context-ruby-sdk/commit/8ccafd9625079f40393fe23890958a80d8bdb4e8))
+
+
+### Chores
+
+* **internal:** more robust bootstrap script ([57b2d93](https://github.com/context-dot-dev/context-ruby-sdk/commit/57b2d93877e5ceeb388679f239e21c09b087b2a1))
+
 ## 1.5.0 (2026-04-19)
 
 Full Changelog: [v1.4.0...v1.5.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.4.0...v1.5.0)

data/README.md

@@ -26,7 +26,7 @@ To use this gem, install via Bundler by adding the following to your application
 <!-- x-release-please-start-version -->
 
 ```ruby
-gem "context.dev", "~> 1.5.0"
+gem "context.dev", "~> 1.7.0"
 ```
 
 <!-- x-release-please-end -->

data/lib/context_dev/models/web_extract_fonts_response.rb

@@ -29,7 +29,20 @@ module ContextDev
       #   @return [String]
       required :status, String
 
-      # @!method initialize(code:, domain:, fonts:, status:)
+      # @!attribute font_links
+      #   Font assets keyed by family name as it appears in the fonts array (non-generic
+      #   names only). Clients match entries in fonts to pick a file URL from files.
+      #   Omitted when no families resolve to Google or custom @font-face URLs.
+      #
+      #   @return [Hash{Symbol=>ContextDev::Models::WebExtractFontsResponse::FontLink}, nil]
+      optional :font_links,
+               -> { ContextDev::Internal::Type::HashOf[ContextDev::Models::WebExtractFontsResponse::FontLink] },
+               api_name: :fontLinks
+
+      # @!method initialize(code:, domain:, fonts:, status:, font_links: nil)
+      #   Some parameter documentations has been truncated, see
+      #   {ContextDev::Models::WebExtractFontsResponse} for more details.
+      #
       #   @param code [Integer] HTTP status code, e.g., 200
       #
       #   @param domain [String] The normalized domain that was processed
@@ -37,6 +50,8 @@ module ContextDev
       #   @param fonts [Array<ContextDev::Models::WebExtractFontsResponse::Font>] Array of font usage information
       #
       #   @param status [String] Status of the response, e.g., 'ok'
+      #
+      #   @param font_links [Hash{Symbol=>ContextDev::Models::WebExtractFontsResponse::FontLink}] Font assets keyed by family name as it appears in the fonts array (non-generic n
 
       class Font < ContextDev::Internal::Type::BaseModel
         # @!attribute fallbacks
@@ -96,6 +111,58 @@ module ContextDev
         #
         #   @param uses [Array<String>] Array of CSS selectors or element types where this font is used
       end
+
+      class FontLink < ContextDev::Internal::Type::BaseModel
+        # @!attribute files
+        #   Upright font files keyed by weight string (e.g. "400" for regular, "500",
+        #   "700"). Values are absolute URLs.
+        #
+        #   @return [Hash{Symbol=>String}]
+        required :files, ContextDev::Internal::Type::HashOf[String]
+
+        # @!attribute type
+        #
+        #   @return [Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink::Type]
+        required :type, enum: -> { ContextDev::Models::WebExtractFontsResponse::FontLink::Type }
+
+        # @!attribute category
+        #   Google Fonts category when type is google (e.g. sans-serif, serif, monospace,
+        #   display, handwriting). Omitted for custom fonts when unknown.
+        #
+        #   @return [String, nil]
+        optional :category, String
+
+        # @!attribute display_name
+        #   Present when type is custom: human-readable name derived from the fontLinks key
+        #   (strip build/hash suffixes, split camelCase / PascalCase, normalize separators).
+        #   Google entries omit this.
+        #
+        #   @return [String, nil]
+        optional :display_name, String, api_name: :displayName
+
+        # @!method initialize(files:, type:, category: nil, display_name: nil)
+        #   Some parameter documentations has been truncated, see
+        #   {ContextDev::Models::WebExtractFontsResponse::FontLink} for more details.
+        #
+        #   @param files [Hash{Symbol=>String}] Upright font files keyed by weight string (e.g. "400" for regular, "500", "700")
+        #
+        #   @param type [Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink::Type]
+        #
+        #   @param category [String] Google Fonts category when type is google (e.g. sans-serif, serif, monospace, di
+        #
+        #   @param display_name [String] Present when type is custom: human-readable name derived from the fontLinks key
+
+        # @see ContextDev::Models::WebExtractFontsResponse::FontLink#type
+        module Type
+          extend ContextDev::Internal::Type::Enum
+
+          GOOGLE = :google
+          CUSTOM = :custom
+
+          # @!method self.values
+          #   @return [Array<Symbol>]
+        end
+      end
     end
   end
 end

data/lib/context_dev/models/web_web_crawl_md_params.rb

@@ -33,6 +33,14 @@ module ContextDev
       #   @return [Boolean, nil]
       optional :include_links, ContextDev::Internal::Type::Boolean, api_name: :includeLinks
 
+      # @!attribute max_age_ms
+      #   Return a cached result if a prior scrape for the same parameters exists and is
+      #   younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
+      #   omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
+      #
+      #   @return [Integer, nil]
+      optional :max_age_ms, Integer, api_name: :maxAgeMs
+
       # @!attribute max_depth
       #   Maximum link depth from the starting URL (0 = only the starting page)
       #
@@ -45,6 +53,14 @@ module ContextDev
       #   @return [Integer, nil]
       optional :max_pages, Integer, api_name: :maxPages
 
+      # @!attribute parse_pdf
+      #   When true (default), PDF pages are fetched and their text layer is extracted and
+      #   converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+      #   entirely (not included in results and not counted as failures).
+      #
+      #   @return [Boolean, nil]
+      optional :parse_pdf, ContextDev::Internal::Type::Boolean, api_name: :parsePDF
+
       # @!attribute shorten_base64_images
       #   Truncate base64-encoded image data in the Markdown output
       #
@@ -64,7 +80,7 @@ module ContextDev
       #   @return [Boolean, nil]
       optional :use_main_content_only, ContextDev::Internal::Type::Boolean, api_name: :useMainContentOnly
 
-      # @!method initialize(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_depth: nil, max_pages: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
+      # @!method initialize(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebCrawlMdParams} for more details.
       #
@@ -76,10 +92,14 @@ module ContextDev
       #
       #   @param include_links [Boolean] Preserve hyperlinks in the Markdown output
       #
+      #   @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
+      #
       #   @param max_depth [Integer] Maximum link depth from the starting URL (0 = only the starting page)
       #
       #   @param max_pages [Integer] Maximum number of pages to crawl. Hard cap: 500.
       #
+      #   @param parse_pdf [Boolean] When true (default), PDF pages are fetched and their text layer is extracted and
+      #
       #   @param shorten_base64_images [Boolean] Truncate base64-encoded image data in the Markdown output
       #
       #   @param url_regex [String] Regex pattern. Only URLs matching this pattern will be followed and scraped.

data/lib/context_dev/models/web_web_crawl_md_response.rb

@@ -33,6 +33,12 @@ module ContextDev
         #   @return [Integer]
         required :num_failed, Integer, api_name: :numFailed
 
+        # @!attribute num_skipped
+        #   Number of URLs skipped (PDFs when parsePDF=false, or URLs not matching urlRegex)
+        #
+        #   @return [Integer]
+        required :num_skipped, Integer, api_name: :numSkipped
+
         # @!attribute num_succeeded
         #   Number of pages successfully crawled
         #
@@ -45,11 +51,16 @@ module ContextDev
         #   @return [Integer]
         required :num_urls, Integer, api_name: :numUrls
 
-        # @!method initialize(max_crawl_depth:, num_failed:, num_succeeded:, num_urls:)
+        # @!method initialize(max_crawl_depth:, num_failed:, num_skipped:, num_succeeded:, num_urls:)
+        #   Some parameter documentations has been truncated, see
+        #   {ContextDev::Models::WebWebCrawlMdResponse::Metadata} for more details.
+        #
         #   @param max_crawl_depth [Integer] Maximum crawl depth reached during the crawl
         #
         #   @param num_failed [Integer] Number of pages that failed to crawl
         #
+        #   @param num_skipped [Integer] Number of URLs skipped (PDFs when parsePDF=false, or URLs not matching urlRegex)
+        #
         #   @param num_succeeded [Integer] Number of pages successfully crawled
         #
         #   @param num_urls [Integer] Total number of URLs crawled

data/lib/context_dev/models/web_web_scrape_html_params.rb

@@ -21,7 +21,15 @@ module ContextDev
       #   @return [Integer, nil]
       optional :max_age_ms, Integer
 
-      # @!method initialize(url:, max_age_ms: nil, request_options: {})
+      # @!attribute parse_pdf
+      #   When true (default), PDF URLs are fetched and their text layer is extracted and
+      #   returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+      #   and a 400 WEBSITE_ACCESS_ERROR is returned.
+      #
+      #   @return [Boolean, nil]
+      optional :parse_pdf, ContextDev::Internal::Type::Boolean
+
+      # @!method initialize(url:, max_age_ms: nil, parse_pdf: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeHTMLParams} for more details.
       #
@@ -29,6 +37,8 @@ module ContextDev
       #
       #   @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
+      #   @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
+      #
       #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]
     end
   end

data/lib/context_dev/models/web_web_scrape_md_params.rb

@@ -34,6 +34,14 @@ module ContextDev
       #   @return [Integer, nil]
       optional :max_age_ms, Integer
 
+      # @!attribute parse_pdf
+      #   When true (default), PDF URLs are fetched and their text layer is extracted and
+      #   converted to Markdown. When false, PDF URLs are skipped and a 400
+      #   WEBSITE_ACCESS_ERROR is returned.
+      #
+      #   @return [Boolean, nil]
+      optional :parse_pdf, ContextDev::Internal::Type::Boolean
+
       # @!attribute shorten_base64_images
       #   Shorten base64-encoded image data in the Markdown output
       #
@@ -47,7 +55,7 @@ module ContextDev
       #   @return [Boolean, nil]
       optional :use_main_content_only, ContextDev::Internal::Type::Boolean
 
-      # @!method initialize(url:, include_images: nil, include_links: nil, max_age_ms: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
+      # @!method initialize(url:, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeMdParams} for more details.
       #
@@ -59,6 +67,8 @@ module ContextDev
       #
       #   @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
+      #   @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
+      #
       #   @param shorten_base64_images [Boolean] Shorten base64-encoded image data in the Markdown output
       #
       #   @param use_main_content_only [Boolean] Extract only the main content of the page, excluding headers, footers, sidebars,

data/lib/context_dev/models/web_web_scrape_sitemap_params.rb

@@ -20,7 +20,14 @@ module ContextDev
       #   @return [Integer, nil]
       optional :max_links, Integer
 
-      # @!method initialize(domain:, max_links: nil, request_options: {})
+      # @!attribute url_regex
+      #   Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+      #   returned and counted against maxLinks.
+      #
+      #   @return [String, nil]
+      optional :url_regex, String
+
+      # @!method initialize(domain:, max_links: nil, url_regex: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeSitemapParams} for more details.
       #
@@ -28,6 +35,8 @@ module ContextDev
       #
       #   @param max_links [Integer] Maximum number of links to return from the sitemap crawl. Defaults to 10,000. Mi
       #
+      #   @param url_regex [String] Optional RE2-compatible regex pattern. Only URLs matching this pattern are retur
+      #
       #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]
     end
   end

data/lib/context_dev/resources/web.rb

@@ -105,7 +105,7 @@ module ContextDev
       # Performs a crawl starting from a given URL, extracts page content as Markdown,
       # and returns results for all crawled pages.
       #
-      # @overload web_crawl_md(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_depth: nil, max_pages: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
+      # @overload web_crawl_md(url:, follow_subdomains: nil, include_images: nil, include_links: nil, max_age_ms: nil, max_depth: nil, max_pages: nil, parse_pdf: nil, shorten_base64_images: nil, url_regex: nil, use_main_content_only: nil, request_options: {})
       #
       # @param url [String] The starting URL for the crawl (must include http:// or https:// protocol)
       #
@@ -115,10 +115,14 @@ module ContextDev
       #
       # @param include_links [Boolean] Preserve hyperlinks in the Markdown output
       #
+      # @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
+      #
       # @param max_depth [Integer] Maximum link depth from the starting URL (0 = only the starting page)
       #
       # @param max_pages [Integer] Maximum number of pages to crawl. Hard cap: 500.
       #
+      # @param parse_pdf [Boolean] When true (default), PDF pages are fetched and their text layer is extracted and
+      #
       # @param shorten_base64_images [Boolean] Truncate base64-encoded image data in the Markdown output
       #
       # @param url_regex [String] Regex pattern. Only URLs matching this pattern will be followed and scraped.
@@ -146,12 +150,14 @@ module ContextDev
       #
       # Scrapes the given URL and returns the raw HTML content of the page.
       #
-      # @overload web_scrape_html(url:, max_age_ms: nil, request_options: {})
+      # @overload web_scrape_html(url:, max_age_ms: nil, parse_pdf: nil, request_options: {})
       #
       # @param url [String] Full URL to scrape (must include http:// or https:// protocol)
       #
       # @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
+      # @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
+      #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
       #
       # @return [ContextDev::Models::WebWebScrapeHTMLResponse]
@@ -163,7 +169,7 @@ module ContextDev
         @client.request(
           method: :get,
           path: "web/scrape/html",
-          query: query.transform_keys(max_age_ms: "maxAgeMs"),
+          query: query.transform_keys(max_age_ms: "maxAgeMs", parse_pdf: "parsePDF"),
           model: ContextDev::Models::WebWebScrapeHTMLResponse,
           options: options
         )
@@ -199,7 +205,7 @@ module ContextDev
       #
       # Scrapes the given URL into LLM usable Markdown.
       #
-      # @overload web_scrape_md(url:, include_images: nil, include_links: nil, max_age_ms: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
+      # @overload web_scrape_md(url:, include_images: nil, include_links: nil, max_age_ms: nil, parse_pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
       #
       # @param url [String] Full URL to scrape into LLM usable Markdown (must include http:// or https:// pr
       #
@@ -209,6 +215,8 @@ module ContextDev
       #
       # @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
+      # @param parse_pdf [Boolean] When true (default), PDF URLs are fetched and their text layer is extracted and
+      #
       # @param shorten_base64_images [Boolean] Shorten base64-encoded image data in the Markdown output
       #
       # @param use_main_content_only [Boolean] Extract only the main content of the page, excluding headers, footers, sidebars,
@@ -228,6 +236,7 @@ module ContextDev
             include_images: "includeImages",
             include_links: "includeLinks",
             max_age_ms: "maxAgeMs",
+            parse_pdf: "parsePDF",
             shorten_base64_images: "shortenBase64Images",
             use_main_content_only: "useMainContentOnly"
           ),
@@ -241,12 +250,14 @@ module ContextDev
       #
       # Crawl an entire website's sitemap and return all discovered page URLs.
       #
-      # @overload web_scrape_sitemap(domain:, max_links: nil, request_options: {})
+      # @overload web_scrape_sitemap(domain:, max_links: nil, url_regex: nil, request_options: {})
       #
       # @param domain [String] Domain to build a sitemap for
       #
       # @param max_links [Integer] Maximum number of links to return from the sitemap crawl. Defaults to 10,000. Mi
       #
+      # @param url_regex [String] Optional RE2-compatible regex pattern. Only URLs matching this pattern are retur
+      #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
       #
       # @return [ContextDev::Models::WebWebScrapeSitemapResponse]
@@ -258,7 +269,7 @@ module ContextDev
         @client.request(
           method: :get,
           path: "web/scrape/sitemap",
-          query: query.transform_keys(max_links: "maxLinks"),
+          query: query.transform_keys(max_links: "maxLinks", url_regex: "urlRegex"),
           model: ContextDev::Models::WebWebScrapeSitemapResponse,
           options: options
         )

data/lib/context_dev/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ContextDev
-  VERSION = "1.5.0"
+  VERSION = "1.7.0"
 end

data/rbi/context_dev/models/web_extract_fonts_response.rbi

@@ -29,13 +29,44 @@ module ContextDev
       sig { returns(String) }
       attr_accessor :status
 
+      # Font assets keyed by family name as it appears in the fonts array (non-generic
+      # names only). Clients match entries in fonts to pick a file URL from files.
+      # Omitted when no families resolve to Google or custom @font-face URLs.
+      sig do
+        returns(
+          T.nilable(
+            T::Hash[
+              Symbol,
+              ContextDev::Models::WebExtractFontsResponse::FontLink
+            ]
+          )
+        )
+      end
+      attr_reader :font_links
+
+      sig do
+        params(
+          font_links:
+            T::Hash[
+              Symbol,
+              ContextDev::Models::WebExtractFontsResponse::FontLink::OrHash
+            ]
+        ).void
+      end
+      attr_writer :font_links
+
       sig do
         params(
           code: Integer,
           domain: String,
           fonts:
             T::Array[ContextDev::Models::WebExtractFontsResponse::Font::OrHash],
-          status: String
+          status: String,
+          font_links:
+            T::Hash[
+              Symbol,
+              ContextDev::Models::WebExtractFontsResponse::FontLink::OrHash
+            ]
         ).returns(T.attached_class)
       end
       def self.new(
@@ -46,7 +77,11 @@ module ContextDev
         # Array of font usage information
         fonts:,
         # Status of the response, e.g., 'ok'
-        status:
+        status:,
+        # Font assets keyed by family name as it appears in the fonts array (non-generic
+        # names only). Clients match entries in fonts to pick a file URL from files.
+        # Omitted when no families resolve to Google or custom @font-face URLs.
+        font_links: nil
       )
       end
 
@@ -56,7 +91,12 @@ module ContextDev
             code: Integer,
             domain: String,
             fonts: T::Array[ContextDev::Models::WebExtractFontsResponse::Font],
-            status: String
+            status: String,
+            font_links:
+              T::Hash[
+                Symbol,
+                ContextDev::Models::WebExtractFontsResponse::FontLink
+              ]
           }
         )
       end
@@ -145,6 +185,117 @@ module ContextDev
         def to_hash
         end
       end
+
+      class FontLink < ContextDev::Internal::Type::BaseModel
+        OrHash =
+          T.type_alias do
+            T.any(
+              ContextDev::Models::WebExtractFontsResponse::FontLink,
+              ContextDev::Internal::AnyHash
+            )
+          end
+
+        # Upright font files keyed by weight string (e.g. "400" for regular, "500",
+        # "700"). Values are absolute URLs.
+        sig { returns(T::Hash[Symbol, String]) }
+        attr_accessor :files
+
+        sig do
+          returns(
+            ContextDev::Models::WebExtractFontsResponse::FontLink::Type::TaggedSymbol
+          )
+        end
+        attr_accessor :type
+
+        # Google Fonts category when type is google (e.g. sans-serif, serif, monospace,
+        # display, handwriting). Omitted for custom fonts when unknown.
+        sig { returns(T.nilable(String)) }
+        attr_reader :category
+
+        sig { params(category: String).void }
+        attr_writer :category
+
+        # Present when type is custom: human-readable name derived from the fontLinks key
+        # (strip build/hash suffixes, split camelCase / PascalCase, normalize separators).
+        # Google entries omit this.
+        sig { returns(T.nilable(String)) }
+        attr_reader :display_name
+
+        sig { params(display_name: String).void }
+        attr_writer :display_name
+
+        sig do
+          params(
+            files: T::Hash[Symbol, String],
+            type:
+              ContextDev::Models::WebExtractFontsResponse::FontLink::Type::OrSymbol,
+            category: String,
+            display_name: String
+          ).returns(T.attached_class)
+        end
+        def self.new(
+          # Upright font files keyed by weight string (e.g. "400" for regular, "500",
+          # "700"). Values are absolute URLs.
+          files:,
+          type:,
+          # Google Fonts category when type is google (e.g. sans-serif, serif, monospace,
+          # display, handwriting). Omitted for custom fonts when unknown.
+          category: nil,
+          # Present when type is custom: human-readable name derived from the fontLinks key
+          # (strip build/hash suffixes, split camelCase / PascalCase, normalize separators).
+          # Google entries omit this.
+          display_name: nil
+        )
+        end
+
+        sig do
+          override.returns(
+            {
+              files: T::Hash[Symbol, String],
+              type:
+                ContextDev::Models::WebExtractFontsResponse::FontLink::Type::TaggedSymbol,
+              category: String,
+              display_name: String
+            }
+          )
+        end
+        def to_hash
+        end
+
+        module Type
+          extend ContextDev::Internal::Type::Enum
+
+          TaggedSymbol =
+            T.type_alias do
+              T.all(
+                Symbol,
+                ContextDev::Models::WebExtractFontsResponse::FontLink::Type
+              )
+            end
+          OrSymbol = T.type_alias { T.any(Symbol, String) }
+
+          GOOGLE =
+            T.let(
+              :google,
+              ContextDev::Models::WebExtractFontsResponse::FontLink::Type::TaggedSymbol
+            )
+          CUSTOM =
+            T.let(
+              :custom,
+              ContextDev::Models::WebExtractFontsResponse::FontLink::Type::TaggedSymbol
+            )
+
+          sig do
+            override.returns(
+              T::Array[
+                ContextDev::Models::WebExtractFontsResponse::FontLink::Type::TaggedSymbol
+              ]
+            )
+          end
+          def self.values
+          end
+        end
+      end
     end
   end
 end

data/rbi/context_dev/models/web_web_crawl_md_params.rbi

@@ -38,6 +38,15 @@ module ContextDev
       sig { params(include_links: T::Boolean).void }
       attr_writer :include_links
 
+      # Return a cached result if a prior scrape for the same parameters exists and is
+      # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
+      # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
+      sig { returns(T.nilable(Integer)) }
+      attr_reader :max_age_ms
+
+      sig { params(max_age_ms: Integer).void }
+      attr_writer :max_age_ms
+
       # Maximum link depth from the starting URL (0 = only the starting page)
       sig { returns(T.nilable(Integer)) }
       attr_reader :max_depth
@@ -52,6 +61,15 @@ module ContextDev
       sig { params(max_pages: Integer).void }
       attr_writer :max_pages
 
+      # When true (default), PDF pages are fetched and their text layer is extracted and
+      # converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+      # entirely (not included in results and not counted as failures).
+      sig { returns(T.nilable(T::Boolean)) }
+      attr_reader :parse_pdf
+
+      sig { params(parse_pdf: T::Boolean).void }
+      attr_writer :parse_pdf
+
       # Truncate base64-encoded image data in the Markdown output
       sig { returns(T.nilable(T::Boolean)) }
       attr_reader :shorten_base64_images
@@ -80,8 +98,10 @@ module ContextDev
           follow_subdomains: T::Boolean,
           include_images: T::Boolean,
           include_links: T::Boolean,
+          max_age_ms: Integer,
           max_depth: Integer,
           max_pages: Integer,
+          parse_pdf: T::Boolean,
           shorten_base64_images: T::Boolean,
           url_regex: String,
           use_main_content_only: T::Boolean,
@@ -99,10 +119,18 @@ module ContextDev
         include_images: nil,
         # Preserve hyperlinks in the Markdown output
         include_links: nil,
+        # Return a cached result if a prior scrape for the same parameters exists and is
+        # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
+        # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
+        max_age_ms: nil,
         # Maximum link depth from the starting URL (0 = only the starting page)
         max_depth: nil,
         # Maximum number of pages to crawl. Hard cap: 500.
         max_pages: nil,
+        # When true (default), PDF pages are fetched and their text layer is extracted and
+        # converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+        # entirely (not included in results and not counted as failures).
+        parse_pdf: nil,
         # Truncate base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Regex pattern. Only URLs matching this pattern will be followed and scraped.
@@ -121,8 +149,10 @@ module ContextDev
             follow_subdomains: T::Boolean,
             include_images: T::Boolean,
             include_links: T::Boolean,
+            max_age_ms: Integer,
             max_depth: Integer,
             max_pages: Integer,
+            parse_pdf: T::Boolean,
             shorten_base64_images: T::Boolean,
             url_regex: String,
             use_main_content_only: T::Boolean,

data/rbi/context_dev/models/web_web_crawl_md_response.rbi

@@ -64,6 +64,10 @@ module ContextDev
         sig { returns(Integer) }
         attr_accessor :num_failed
 
+        # Number of URLs skipped (PDFs when parsePDF=false, or URLs not matching urlRegex)
+        sig { returns(Integer) }
+        attr_accessor :num_skipped
+
         # Number of pages successfully crawled
         sig { returns(Integer) }
         attr_accessor :num_succeeded
@@ -76,6 +80,7 @@ module ContextDev
           params(
             max_crawl_depth: Integer,
             num_failed: Integer,
+            num_skipped: Integer,
             num_succeeded: Integer,
             num_urls: Integer
           ).returns(T.attached_class)
@@ -85,6 +90,8 @@ module ContextDev
           max_crawl_depth:,
           # Number of pages that failed to crawl
           num_failed:,
+          # Number of URLs skipped (PDFs when parsePDF=false, or URLs not matching urlRegex)
+          num_skipped:,
           # Number of pages successfully crawled
           num_succeeded:,
           # Total number of URLs crawled
@@ -97,6 +104,7 @@ module ContextDev
             {
               max_crawl_depth: Integer,
               num_failed: Integer,
+              num_skipped: Integer,
               num_succeeded: Integer,
               num_urls: Integer
             }

data/rbi/context_dev/models/web_web_scrape_html_params.rbi

@@ -27,10 +27,20 @@ module ContextDev
       sig { params(max_age_ms: Integer).void }
       attr_writer :max_age_ms
 
+      # When true (default), PDF URLs are fetched and their text layer is extracted and
+      # returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+      # and a 400 WEBSITE_ACCESS_ERROR is returned.
+      sig { returns(T.nilable(T::Boolean)) }
+      attr_reader :parse_pdf
+
+      sig { params(parse_pdf: T::Boolean).void }
+      attr_writer :parse_pdf
+
       sig do
         params(
           url: String,
           max_age_ms: Integer,
+          parse_pdf: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
         ).returns(T.attached_class)
       end
@@ -41,6 +51,10 @@ module ContextDev
         # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
         # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
         max_age_ms: nil,
+        # When true (default), PDF URLs are fetched and their text layer is extracted and
+        # returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+        # and a 400 WEBSITE_ACCESS_ERROR is returned.
+        parse_pdf: nil,
         request_options: {}
       )
       end
@@ -50,6 +64,7 @@ module ContextDev
           {
             url: String,
             max_age_ms: Integer,
+            parse_pdf: T::Boolean,
             request_options: ContextDev::RequestOptions
           }
         )

data/rbi/context_dev/models/web_web_scrape_md_params.rbi

@@ -39,6 +39,15 @@ module ContextDev
       sig { params(max_age_ms: Integer).void }
       attr_writer :max_age_ms
 
+      # When true (default), PDF URLs are fetched and their text layer is extracted and
+      # converted to Markdown. When false, PDF URLs are skipped and a 400
+      # WEBSITE_ACCESS_ERROR is returned.
+      sig { returns(T.nilable(T::Boolean)) }
+      attr_reader :parse_pdf
+
+      sig { params(parse_pdf: T::Boolean).void }
+      attr_writer :parse_pdf
+
       # Shorten base64-encoded image data in the Markdown output
       sig { returns(T.nilable(T::Boolean)) }
       attr_reader :shorten_base64_images
@@ -60,6 +69,7 @@ module ContextDev
           include_images: T::Boolean,
           include_links: T::Boolean,
           max_age_ms: Integer,
+          parse_pdf: T::Boolean,
           shorten_base64_images: T::Boolean,
           use_main_content_only: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
@@ -77,6 +87,10 @@ module ContextDev
         # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
         # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
         max_age_ms: nil,
+        # When true (default), PDF URLs are fetched and their text layer is extracted and
+        # converted to Markdown. When false, PDF URLs are skipped and a 400
+        # WEBSITE_ACCESS_ERROR is returned.
+        parse_pdf: nil,
         # Shorten base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Extract only the main content of the page, excluding headers, footers, sidebars,
@@ -93,6 +107,7 @@ module ContextDev
             include_images: T::Boolean,
             include_links: T::Boolean,
             max_age_ms: Integer,
+            parse_pdf: T::Boolean,
             shorten_base64_images: T::Boolean,
             use_main_content_only: T::Boolean,
             request_options: ContextDev::RequestOptions

data/rbi/context_dev/models/web_web_scrape_sitemap_params.rbi

@@ -26,10 +26,19 @@ module ContextDev
       sig { params(max_links: Integer).void }
       attr_writer :max_links
 
+      # Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+      # returned and counted against maxLinks.
+      sig { returns(T.nilable(String)) }
+      attr_reader :url_regex
+
+      sig { params(url_regex: String).void }
+      attr_writer :url_regex
+
       sig do
         params(
           domain: String,
           max_links: Integer,
+          url_regex: String,
           request_options: ContextDev::RequestOptions::OrHash
         ).returns(T.attached_class)
       end
@@ -39,6 +48,9 @@ module ContextDev
         # Maximum number of links to return from the sitemap crawl. Defaults to 10,000.
         # Minimum is 1, maximum is 100,000.
         max_links: nil,
+        # Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+        # returned and counted against maxLinks.
+        url_regex: nil,
         request_options: {}
       )
       end
@@ -48,6 +60,7 @@ module ContextDev
           {
             domain: String,
             max_links: Integer,
+            url_regex: String,
             request_options: ContextDev::RequestOptions
           }
         )

data/rbi/context_dev/resources/web.rbi

@@ -105,8 +105,10 @@ module ContextDev
           follow_subdomains: T::Boolean,
           include_images: T::Boolean,
           include_links: T::Boolean,
+          max_age_ms: Integer,
           max_depth: Integer,
           max_pages: Integer,
+          parse_pdf: T::Boolean,
           shorten_base64_images: T::Boolean,
           url_regex: String,
           use_main_content_only: T::Boolean,
@@ -124,10 +126,18 @@ module ContextDev
         include_images: nil,
         # Preserve hyperlinks in the Markdown output
         include_links: nil,
+        # Return a cached result if a prior scrape for the same parameters exists and is
+        # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
+        # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
+        max_age_ms: nil,
         # Maximum link depth from the starting URL (0 = only the starting page)
         max_depth: nil,
         # Maximum number of pages to crawl. Hard cap: 500.
         max_pages: nil,
+        # When true (default), PDF pages are fetched and their text layer is extracted and
+        # converted to Markdown alongside HTML pages. When false, PDF pages are skipped
+        # entirely (not included in results and not counted as failures).
+        parse_pdf: nil,
         # Truncate base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Regex pattern. Only URLs matching this pattern will be followed and scraped.
@@ -144,6 +154,7 @@ module ContextDev
         params(
           url: String,
           max_age_ms: Integer,
+          parse_pdf: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
         ).returns(ContextDev::Models::WebWebScrapeHTMLResponse)
       end
@@ -154,6 +165,10 @@ module ContextDev
         # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
         # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
         max_age_ms: nil,
+        # When true (default), PDF URLs are fetched and their text layer is extracted and
+        # returned wrapped in <html><pdf>…</pdf></html>. When false, PDF URLs are skipped
+        # and a 400 WEBSITE_ACCESS_ERROR is returned.
+        parse_pdf: nil,
         request_options: {}
       )
       end
@@ -181,6 +196,7 @@ module ContextDev
           include_images: T::Boolean,
           include_links: T::Boolean,
           max_age_ms: Integer,
+          parse_pdf: T::Boolean,
           shorten_base64_images: T::Boolean,
           use_main_content_only: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
@@ -198,6 +214,10 @@ module ContextDev
         # younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
         # omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
         max_age_ms: nil,
+        # When true (default), PDF URLs are fetched and their text layer is extracted and
+        # converted to Markdown. When false, PDF URLs are skipped and a 400
+        # WEBSITE_ACCESS_ERROR is returned.
+        parse_pdf: nil,
         # Shorten base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Extract only the main content of the page, excluding headers, footers, sidebars,
@@ -212,6 +232,7 @@ module ContextDev
         params(
           domain: String,
           max_links: Integer,
+          url_regex: String,
           request_options: ContextDev::RequestOptions::OrHash
         ).returns(ContextDev::Models::WebWebScrapeSitemapResponse)
       end
@@ -221,6 +242,9 @@ module ContextDev
         # Maximum number of links to return from the sitemap crawl. Defaults to 10,000.
         # Minimum is 1, maximum is 100,000.
         max_links: nil,
+        # Optional RE2-compatible regex pattern. Only URLs matching this pattern are
+        # returned and counted against maxLinks.
+        url_regex: nil,
         request_options: {}
       )
       end

data/sig/context_dev/models/web_extract_fonts_response.rbs

@@ -5,7 +5,8 @@ module ContextDev
         code: Integer,
         domain: String,
         fonts: ::Array[ContextDev::Models::WebExtractFontsResponse::Font],
-        status: String
+        status: String,
+        font_links: ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]
       }
 
     class WebExtractFontsResponse < ContextDev::Internal::Type::BaseModel
@@ -17,18 +18,26 @@ module ContextDev
 
       attr_accessor status: String
 
+      attr_reader font_links: ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]?
+
+      def font_links=: (
+        ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]
+      ) -> ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]
+
       def initialize: (
         code: Integer,
         domain: String,
         fonts: ::Array[ContextDev::Models::WebExtractFontsResponse::Font],
-        status: String
+        status: String,
+        ?font_links: ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]
       ) -> void
 
       def to_hash: -> {
         code: Integer,
         domain: String,
         fonts: ::Array[ContextDev::Models::WebExtractFontsResponse::Font],
-        status: String
+        status: String,
+        font_links: ::Hash[Symbol, ContextDev::Models::WebExtractFontsResponse::FontLink]
       }
 
       type font =
@@ -77,6 +86,53 @@ module ContextDev
           uses: ::Array[String]
         }
       end
+
+      type font_link =
+        {
+          files: ::Hash[Symbol, String],
+          type: ContextDev::Models::WebExtractFontsResponse::FontLink::type_,
+          category: String,
+          display_name: String
+        }
+
+      class FontLink < ContextDev::Internal::Type::BaseModel
+        attr_accessor files: ::Hash[Symbol, String]
+
+        attr_accessor type: ContextDev::Models::WebExtractFontsResponse::FontLink::type_
+
+        attr_reader category: String?
+
+        def category=: (String) -> String
+
+        attr_reader display_name: String?
+
+        def display_name=: (String) -> String
+
+        def initialize: (
+          files: ::Hash[Symbol, String],
+          type: ContextDev::Models::WebExtractFontsResponse::FontLink::type_,
+          ?category: String,
+          ?display_name: String
+        ) -> void
+
+        def to_hash: -> {
+          files: ::Hash[Symbol, String],
+          type: ContextDev::Models::WebExtractFontsResponse::FontLink::type_,
+          category: String,
+          display_name: String
+        }
+
+        type type_ = :google | :custom
+
+        module Type
+          extend ContextDev::Internal::Type::Enum
+
+          GOOGLE: :google
+          CUSTOM: :custom
+
+          def self?.values: -> ::Array[ContextDev::Models::WebExtractFontsResponse::FontLink::type_]
+        end
+      end
     end
   end
 end

data/sig/context_dev/models/web_web_crawl_md_params.rbs

@@ -6,8 +6,10 @@ module ContextDev
         follow_subdomains: bool,
         include_images: bool,
         include_links: bool,
+        max_age_ms: Integer,
         max_depth: Integer,
         max_pages: Integer,
+        parse_pdf: bool,
         :shorten_base64_images => bool,
         url_regex: String,
         use_main_content_only: bool
@@ -32,6 +34,10 @@ module ContextDev
 
       def include_links=: (bool) -> bool
 
+      attr_reader max_age_ms: Integer?
+
+      def max_age_ms=: (Integer) -> Integer
+
       attr_reader max_depth: Integer?
 
       def max_depth=: (Integer) -> Integer
@@ -40,6 +46,10 @@ module ContextDev
 
       def max_pages=: (Integer) -> Integer
 
+      attr_reader parse_pdf: bool?
+
+      def parse_pdf=: (bool) -> bool
+
       attr_reader shorten_base64_images: bool?
 
       def shorten_base64_images=: (bool) -> bool
@@ -57,8 +67,10 @@ module ContextDev
         ?follow_subdomains: bool,
         ?include_images: bool,
         ?include_links: bool,
+        ?max_age_ms: Integer,
         ?max_depth: Integer,
         ?max_pages: Integer,
+        ?parse_pdf: bool,
         ?shorten_base64_images: bool,
         ?url_regex: String,
         ?use_main_content_only: bool,
@@ -70,8 +82,10 @@ module ContextDev
         follow_subdomains: bool,
         include_images: bool,
         include_links: bool,
+        max_age_ms: Integer,
         max_depth: Integer,
         max_pages: Integer,
+        parse_pdf: bool,
         :shorten_base64_images => bool,
         url_regex: String,
         use_main_content_only: bool,

data/sig/context_dev/models/web_web_crawl_md_response.rbs

@@ -25,6 +25,7 @@ module ContextDev
         {
           max_crawl_depth: Integer,
           num_failed: Integer,
+          num_skipped: Integer,
           num_succeeded: Integer,
           num_urls: Integer
         }
@@ -34,6 +35,8 @@ module ContextDev
 
         attr_accessor num_failed: Integer
 
+        attr_accessor num_skipped: Integer
+
         attr_accessor num_succeeded: Integer
 
         attr_accessor num_urls: Integer
@@ -41,6 +44,7 @@ module ContextDev
         def initialize: (
           max_crawl_depth: Integer,
           num_failed: Integer,
+          num_skipped: Integer,
           num_succeeded: Integer,
           num_urls: Integer
         ) -> void
@@ -48,6 +52,7 @@ module ContextDev
         def to_hash: -> {
           max_crawl_depth: Integer,
           num_failed: Integer,
+          num_skipped: Integer,
           num_succeeded: Integer,
           num_urls: Integer
         }

data/sig/context_dev/models/web_web_scrape_html_params.rbs

@@ -1,7 +1,7 @@
 module ContextDev
   module Models
     type web_web_scrape_html_params =
-      { url: String, max_age_ms: Integer }
+      { url: String, max_age_ms: Integer, parse_pdf: bool }
       & ContextDev::Internal::Type::request_parameters
 
     class WebWebScrapeHTMLParams < ContextDev::Internal::Type::BaseModel
@@ -14,15 +14,21 @@ module ContextDev
 
       def max_age_ms=: (Integer) -> Integer
 
+      attr_reader parse_pdf: bool?
+
+      def parse_pdf=: (bool) -> bool
+
       def initialize: (
         url: String,
         ?max_age_ms: Integer,
+        ?parse_pdf: bool,
         ?request_options: ContextDev::request_opts
       ) -> void
 
       def to_hash: -> {
         url: String,
         max_age_ms: Integer,
+        parse_pdf: bool,
         request_options: ContextDev::RequestOptions
       }
     end

data/sig/context_dev/models/web_web_scrape_md_params.rbs

@@ -6,6 +6,7 @@ module ContextDev
         include_images: bool,
         include_links: bool,
         max_age_ms: Integer,
+        parse_pdf: bool,
         :shorten_base64_images => bool,
         use_main_content_only: bool
       }
@@ -29,6 +30,10 @@ module ContextDev
 
       def max_age_ms=: (Integer) -> Integer
 
+      attr_reader parse_pdf: bool?
+
+      def parse_pdf=: (bool) -> bool
+
       attr_reader shorten_base64_images: bool?
 
       def shorten_base64_images=: (bool) -> bool
@@ -42,6 +47,7 @@ module ContextDev
         ?include_images: bool,
         ?include_links: bool,
         ?max_age_ms: Integer,
+        ?parse_pdf: bool,
         ?shorten_base64_images: bool,
         ?use_main_content_only: bool,
         ?request_options: ContextDev::request_opts
@@ -52,6 +58,7 @@ module ContextDev
         include_images: bool,
         include_links: bool,
         max_age_ms: Integer,
+        parse_pdf: bool,
         :shorten_base64_images => bool,
         use_main_content_only: bool,
         request_options: ContextDev::RequestOptions

data/sig/context_dev/models/web_web_scrape_sitemap_params.rbs

@@ -1,7 +1,7 @@
 module ContextDev
   module Models
     type web_web_scrape_sitemap_params =
-      { domain: String, max_links: Integer }
+      { domain: String, max_links: Integer, url_regex: String }
       & ContextDev::Internal::Type::request_parameters
 
     class WebWebScrapeSitemapParams < ContextDev::Internal::Type::BaseModel
@@ -14,15 +14,21 @@ module ContextDev
 
       def max_links=: (Integer) -> Integer
 
+      attr_reader url_regex: String?
+
+      def url_regex=: (String) -> String
+
       def initialize: (
         domain: String,
         ?max_links: Integer,
+        ?url_regex: String,
         ?request_options: ContextDev::request_opts
       ) -> void
 
       def to_hash: -> {
         domain: String,
         max_links: Integer,
+        url_regex: String,
         request_options: ContextDev::RequestOptions
       }
     end

data/sig/context_dev/resources/web.rbs

@@ -29,8 +29,10 @@ module ContextDev
         ?follow_subdomains: bool,
         ?include_images: bool,
         ?include_links: bool,
+        ?max_age_ms: Integer,
         ?max_depth: Integer,
         ?max_pages: Integer,
+        ?parse_pdf: bool,
         ?shorten_base64_images: bool,
         ?url_regex: String,
         ?use_main_content_only: bool,
@@ -40,6 +42,7 @@ module ContextDev
       def web_scrape_html: (
         url: String,
         ?max_age_ms: Integer,
+        ?parse_pdf: bool,
         ?request_options: ContextDev::request_opts
       ) -> ContextDev::Models::WebWebScrapeHTMLResponse
 
@@ -53,6 +56,7 @@ module ContextDev
         ?include_images: bool,
         ?include_links: bool,
         ?max_age_ms: Integer,
+        ?parse_pdf: bool,
         ?shorten_base64_images: bool,
         ?use_main_content_only: bool,
         ?request_options: ContextDev::request_opts
@@ -61,6 +65,7 @@ module ContextDev
       def web_scrape_sitemap: (
         domain: String,
         ?max_links: Integer,
+        ?url_regex: String,
         ?request_options: ContextDev::request_opts
       ) -> ContextDev::Models::WebWebScrapeSitemapResponse
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: context.dev
 version: !ruby/object:Gem::Version
-  version: 1.5.0
+  version: 1.7.0
 platform: ruby
 authors:
 - Context Dev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-19 00:00:00.000000000 Z
+date: 2026-04-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cgi