context.dev 1.6.0 → 1.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0e9ffccdbada64211d1e7ddc15ce648d6e4ec77637768a30f71d754d9a8ff788
-  data.tar.gz: a95c5065d4f22c3a1269026fd93b936086316cb9a1a9e8de5af8e7c6021f0bcc
+  metadata.gz: 968dddadfbf1199743ee57bc82a47fd2d7b882da416170b13f41bf0574828d5d
+  data.tar.gz: 5e35c5601c635fdc8182a81e5738418f4e4d879231cbaea89b1722ba5f28db00
 SHA512:
-  metadata.gz: 1bf660423aa6381d2301614c3987aedcf0edf8bec72bd2eca8b1ee88d4190cb5a4f8c8dd453783632ad1ed79da87bddbfadf09341c870947cba5784d08600610
-  data.tar.gz: aa6851f96a3b0295cbc4386ea424b6e4f856889aac74bcd21e8ad7fd6735f5822ae5ed68306891ef3779dfdf1b590fcc32ffb8f069bd78599f8eacb4c6b5b882
+  metadata.gz: 9ffe4d5dde7376e41afd9607af63fcecd7ab97d8abf26a2adceef1a30594ec54dd10356c731c54dd97ebad44e00eb2d24132ebe27c25a95acfd8a568578557a9
+  data.tar.gz: 2fc80f2bc42e75a0dc03f4c3692f45e6eadce167280695690d69bc408c87eb9504fb557cd661c33041bff9c59876a6f47bbd8ba360b092ab762e70221b79e3ff

data/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## 1.8.0 (2026-04-24)
+
+Full Changelog: [v1.7.0...v1.8.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.7.0...v1.8.0)
+
+### Features
+
+* **api:** api update ([84bfef2](https://github.com/context-dot-dev/context-ruby-sdk/commit/84bfef260d99a7a444c243edc4be1c72191929dd))
+* **api:** api update ([5405b96](https://github.com/context-dot-dev/context-ruby-sdk/commit/5405b9676800e2004d92dd9f621dfc56972bacd2))
+
+## 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)

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", "~> 1.6.0"
+gem "context.dev", "~> 1.8.0"
 ```
 
 <!-- x-release-please-end -->

data/lib/context_dev/models/ai_extract_product_response.rb

@@ -70,6 +70,12 @@ module ContextDev
         #   @return [String]
         required :name, String
 
+        # @!attribute sku
+        #   Stock Keeping Unit (product identifier). Null if no identifier is found.
+        #
+        #   @return [String, nil]
+        required :sku, String, nil?: true
+
         # @!attribute tags
         #   Tags associated with the product
         #
@@ -128,7 +134,7 @@ module ContextDev
         #   @return [String, nil]
         optional :url, String, nil?: true
 
-        # @!method initialize(description:, features:, images:, name:, tags:, target_audience:, billing_frequency: nil, category: nil, currency: nil, image_url: nil, price: nil, pricing_model: nil, url: nil)
+        # @!method initialize(description:, features:, images:, name:, sku:, tags:, target_audience:, billing_frequency: nil, category: nil, currency: nil, image_url: nil, price: nil, pricing_model: nil, url: nil)
         #   The extracted product data, or null if not a product page
         #
         #   @param description [String] Description of the product
@@ -139,6 +145,8 @@ module ContextDev
         #
         #   @param name [String] Name of the product
         #
+        #   @param sku [String, nil] Stock Keeping Unit (product identifier). Null if no identifier is found.
+        #
         #   @param tags [Array<String>] Tags associated with the product
         #
         #   @param target_audience [Array<String>] Target audience for the product (array of strings)

data/lib/context_dev/models/ai_extract_products_response.rb

@@ -39,6 +39,12 @@ module ContextDev
         #   @return [String]
         required :name, String
 
+        # @!attribute sku
+        #   Stock Keeping Unit (product identifier). Null if no identifier is found.
+        #
+        #   @return [String, nil]
+        required :sku, String, nil?: true
+
         # @!attribute tags
         #   Tags associated with the product
         #
@@ -97,7 +103,7 @@ module ContextDev
         #   @return [String, nil]
         optional :url, String, nil?: true
 
-        # @!method initialize(description:, features:, images:, name:, tags:, target_audience:, billing_frequency: nil, category: nil, currency: nil, image_url: nil, price: nil, pricing_model: nil, url: nil)
+        # @!method initialize(description:, features:, images:, name:, sku:, tags:, target_audience:, billing_frequency: nil, category: nil, currency: nil, image_url: nil, price: nil, pricing_model: nil, url: nil)
         #   @param description [String] Description of the product
         #
         #   @param features [Array<String>] List of product features
@@ -106,6 +112,8 @@ module ContextDev
         #
         #   @param name [String] Name of the product
         #
+        #   @param sku [String, nil] Stock Keeping Unit (product identifier). Null if no identifier is found.
+        #
         #   @param tags [Array<String>] Tags associated with the product
         #
         #   @param target_audience [Array<String>] Target audience for the product (array of strings)

data/lib/context_dev/models/web_web_crawl_md_params.rb

@@ -53,6 +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
       #
@@ -72,7 +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_age_ms: 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.
       #
@@ -90,6 +98,8 @@ module ContextDev
       #
       #   @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/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_age_ms: 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)
       #
@@ -121,6 +121,8 @@ module ContextDev
       #
       # @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.
@@ -148,12 +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]
@@ -165,7 +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
         )
@@ -201,7 +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
       #
@@ -211,6 +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,
@@ -230,6 +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"
           ),

data/lib/context_dev/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ContextDev
-  VERSION = "1.6.0"
+  VERSION = "1.8.0"
 end

data/rbi/context_dev/models/ai_extract_product_response.rbi

@@ -155,6 +155,10 @@ module ContextDev
         sig { returns(String) }
         attr_accessor :name
 
+        # Stock Keeping Unit (product identifier). Null if no identifier is found.
+        sig { returns(T.nilable(String)) }
+        attr_accessor :sku
+
         # Tags associated with the product
         sig { returns(T::Array[String]) }
         attr_accessor :tags
@@ -210,6 +214,7 @@ module ContextDev
             features: T::Array[String],
             images: T::Array[String],
             name: String,
+            sku: T.nilable(String),
             tags: T::Array[String],
             target_audience: T::Array[String],
             billing_frequency:
@@ -236,6 +241,8 @@ module ContextDev
           images:,
           # Name of the product
           name:,
+          # Stock Keeping Unit (product identifier). Null if no identifier is found.
+          sku:,
           # Tags associated with the product
           tags:,
           # Target audience for the product (array of strings)
@@ -264,6 +271,7 @@ module ContextDev
               features: T::Array[String],
               images: T::Array[String],
               name: String,
+              sku: T.nilable(String),
               tags: T::Array[String],
               target_audience: T::Array[String],
               billing_frequency:

data/rbi/context_dev/models/ai_extract_products_response.rbi

@@ -81,6 +81,10 @@ module ContextDev
         sig { returns(String) }
         attr_accessor :name
 
+        # Stock Keeping Unit (product identifier). Null if no identifier is found.
+        sig { returns(T.nilable(String)) }
+        attr_accessor :sku
+
         # Tags associated with the product
         sig { returns(T::Array[String]) }
         attr_accessor :tags
@@ -135,6 +139,7 @@ module ContextDev
             features: T::Array[String],
             images: T::Array[String],
             name: String,
+            sku: T.nilable(String),
             tags: T::Array[String],
             target_audience: T::Array[String],
             billing_frequency:
@@ -161,6 +166,8 @@ module ContextDev
           images:,
           # Name of the product
           name:,
+          # Stock Keeping Unit (product identifier). Null if no identifier is found.
+          sku:,
           # Tags associated with the product
           tags:,
           # Target audience for the product (array of strings)
@@ -189,6 +196,7 @@ module ContextDev
               features: T::Array[String],
               images: T::Array[String],
               name: String,
+              sku: T.nilable(String),
               tags: T::Array[String],
               target_audience: T::Array[String],
               billing_frequency:

data/rbi/context_dev/models/web_web_crawl_md_params.rbi

@@ -61,6 +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
@@ -92,6 +101,7 @@ module ContextDev
           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,
@@ -117,6 +127,10 @@ module ContextDev
         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.
@@ -138,6 +152,7 @@ module ContextDev
             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/resources/web.rbi

@@ -108,6 +108,7 @@ module ContextDev
           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,
@@ -133,6 +134,10 @@ module ContextDev
         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.
@@ -149,6 +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
@@ -159,6 +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
@@ -186,6 +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
@@ -203,6 +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,

data/sig/context_dev/models/ai_extract_product_response.rbs

@@ -47,6 +47,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           billing_frequency: ContextDev::Models::AIExtractProductResponse::Product::billing_frequency?,
@@ -67,6 +68,8 @@ module ContextDev
 
         attr_accessor name: String
 
+        attr_accessor sku: String?
+
         attr_accessor tags: ::Array[String]
 
         attr_accessor target_audience: ::Array[String]
@@ -90,6 +93,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           ?billing_frequency: ContextDev::Models::AIExtractProductResponse::Product::billing_frequency?,
@@ -106,6 +110,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           billing_frequency: ContextDev::Models::AIExtractProductResponse::Product::billing_frequency?,

data/sig/context_dev/models/ai_extract_products_response.rbs

@@ -26,6 +26,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           billing_frequency: ContextDev::Models::AIExtractProductsResponse::Product::billing_frequency?,
@@ -46,6 +47,8 @@ module ContextDev
 
         attr_accessor name: String
 
+        attr_accessor sku: String?
+
         attr_accessor tags: ::Array[String]
 
         attr_accessor target_audience: ::Array[String]
@@ -69,6 +72,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           ?billing_frequency: ContextDev::Models::AIExtractProductsResponse::Product::billing_frequency?,
@@ -85,6 +89,7 @@ module ContextDev
           features: ::Array[String],
           images: ::Array[String],
           name: String,
+          sku: String?,
           tags: ::Array[String],
           target_audience: ::Array[String],
           billing_frequency: ContextDev::Models::AIExtractProductsResponse::Product::billing_frequency?,

data/sig/context_dev/models/web_web_crawl_md_params.rbs

@@ -9,6 +9,7 @@ module ContextDev
         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
@@ -45,6 +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
@@ -65,6 +70,7 @@ module ContextDev
         ?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,
@@ -79,6 +85,7 @@ module ContextDev
         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/resources/web.rbs

@@ -32,6 +32,7 @@ module ContextDev
         ?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,
@@ -41,6 +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
 
@@ -54,6 +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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: context.dev
 version: !ruby/object:Gem::Version
-  version: 1.6.0
+  version: 1.8.0
 platform: ruby
 authors:
 - Context Dev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-23 00:00:00.000000000 Z
+date: 2026-04-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cgi