context.dev 1.23.0 → 1.25.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 06d74970c8262066508dc949cda5c8cf8cc065d76197a3f1977e25a280cbdd8a
-  data.tar.gz: bb6600c170297a09820afcb9bc414dc299498605654a4cccb050f405f0f26fdb
+  metadata.gz: f1a0062418eca906ad8f308d3ab6541bd3a6c9f0b8bc1805b58a978e7aea61c2
+  data.tar.gz: a02eb3ec2fe28d611a14d976810b5ff51c2e2c49e432cdea9d89661eaae2de9c
 SHA512:
-  metadata.gz: 4c046ff15ab97003dbece42b1b44a9334e9085a4b8cc75a938cf9acf359044a9578bfa4614440db5f3cb137475823858e131b4d8d9795928cad5f5b9ab4dfb62
-  data.tar.gz: 9675303d36cf80718bdbbc12bb88f6ac44c2fc7ac9ec6c0bc3a3b9059c02255030726d376906cf42ddade4844c40fb12763cfb577fa91166e932b51ad3a8aba4
+  metadata.gz: 7b3c3c7ff3f1e75e6199c810205c287cb0b1e03ff2cf332a2392e5e5880a3722090959d96b39bd39dddefd1c4961faf569d03c10fbcda26e9231ad67875dd45b
+  data.tar.gz: 5aef11c0e5b365ad204eced64e126807a96dfe32351da7940a2f780c07c461bcf0e2e8542e2e2cbfc8af6fa41d49864788b9979101e3d42e8920fb853c4ce5da

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## 1.25.0 (2026-05-31)
+
+Full Changelog: [v1.24.0...v1.25.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.24.0...v1.25.0)
+
+### Features
+
+* **api:** manual updates ([688e5f5](https://github.com/context-dot-dev/context-ruby-sdk/commit/688e5f56137aeac7c5219383f241a459173f961f))
+
+## 1.24.0 (2026-05-30)
+
+Full Changelog: [v1.23.0...v1.24.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.23.0...v1.24.0)
+
+### Features
+
+* **api:** api update ([7948cbf](https://github.com/context-dot-dev/context-ruby-sdk/commit/7948cbf296742dd0fea7c08c148962a35ed88c20))
+
 ## 1.23.0 (2026-05-19)
 
 Full Changelog: [v1.22.0...v1.23.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v1.22.0...v1.23.0)

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", "~> 1.23.0"
+gem "context.dev", "~> 1.25.0"
 ```
 
 <!-- x-release-please-end -->

data/lib/context_dev/internal/type/base_model.rb

@@ -438,11 +438,11 @@ module ContextDev
         # @return [Hash{Symbol=>Object}]
         #
         # @example
-        #   # `web_extract_fonts_response` is a `ContextDev::Models::WebExtractFontsResponse`
-        #   web_extract_fonts_response => {
-        #     code: code,
-        #     domain: domain,
-        #     fonts: fonts
+        #   # `web_extract_response` is a `ContextDev::Models::WebExtractResponse`
+        #   web_extract_response => {
+        #     data: data,
+        #     metadata: metadata,
+        #     status: status
         #   }
         def deconstruct_keys(keys)
           (keys || self.class.known_fields.keys)

data/lib/context_dev/models/web_extract_fonts_params.rb

@@ -23,6 +23,15 @@ module ContextDev
       #   @return [String, nil]
       optional :domain, String
 
+      # @!attribute max_age_ms
+      #   Maximum age in milliseconds for cached data before the API performs a hard
+      #   refresh. Defaults to 3 months (7776000000 ms). Values below 1 day (86400000 ms)
+      #   are clamped to 1 day; values above 1 year (31536000000 ms) are clamped to 1
+      #   year.
+      #
+      #   @return [Integer, nil]
+      optional :max_age_ms, Integer
+
       # @!attribute timeout_ms
       #   Optional timeout in milliseconds for the request. If the request takes longer
       #   than this value, it will be aborted with a 408 status code. Maximum allowed
@@ -31,7 +40,7 @@ module ContextDev
       #   @return [Integer, nil]
       optional :timeout_ms, Integer
 
-      # @!method initialize(direct_url: nil, domain: nil, timeout_ms: nil, request_options: {})
+      # @!method initialize(direct_url: nil, domain: nil, max_age_ms: nil, timeout_ms: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebExtractFontsParams} for more details.
       #
@@ -39,6 +48,8 @@ module ContextDev
       #
       #   @param domain [String] Domain name to extract fonts from (e.g., 'example.com', 'google.com'). The domai
       #
+      #   @param max_age_ms [Integer] Maximum age in milliseconds for cached data before the API performs a hard refre
+      #
       #   @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
       #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]

data/lib/context_dev/models/web_extract_params.rb

@@ -0,0 +1,148 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Models
+    # @see ContextDev::Resources::Web#extract
+    class WebExtractParams < ContextDev::Internal::Type::BaseModel
+      extend ContextDev::Internal::Type::RequestParameters::Converter
+      include ContextDev::Internal::Type::RequestParameters
+
+      # @!attribute schema
+      #   JSON Schema for the returned data object. TypeScript Zod users can pass a JSON
+      #   Schema generated from a Zod object; Python users can pass the equivalent JSON
+      #   Schema object.
+      #
+      #   @return [Hash{Symbol=>Object}]
+      required :schema, ContextDev::Internal::Type::HashOf[ContextDev::Internal::Type::Unknown]
+
+      # @!attribute url
+      #   The starting website URL to crawl and extract from. Must include http:// or
+      #   https://.
+      #
+      #   @return [String]
+      required :url, String
+
+      # @!attribute fact_check
+      #   When true (default), every returned value must be grounded in facts stated on
+      #   the page; fields that cannot be supported by the page are returned as
+      #   null/empty. When false, the model may make reasonable inferences and derivations
+      #   from the page content (e.g. ideal customer, competitor analysis,
+      #   recommendations) while keeping verifiable specifics (names, quotes, URLs, dates,
+      #   metrics) faithful to the source.
+      #
+      #   @return [Boolean, nil]
+      optional :fact_check, ContextDev::Internal::Type::Boolean, api_name: :factCheck
+
+      # @!attribute follow_subdomains
+      #   When true, follow links on subdomains of the starting URL's domain.
+      #
+      #   @return [Boolean, nil]
+      optional :follow_subdomains, ContextDev::Internal::Type::Boolean, api_name: :followSubdomains
+
+      # @!attribute include_frames
+      #   When true, iframe contents are included in Markdown before extraction.
+      #
+      #   @return [Boolean, nil]
+      optional :include_frames, ContextDev::Internal::Type::Boolean, api_name: :includeFrames
+
+      # @!attribute instructions
+      #   Optional extraction guidance, such as which facts to prioritize or how to
+      #   interpret fields in the schema.
+      #
+      #   @return [String, nil]
+      optional :instructions, String
+
+      # @!attribute max_age_ms
+      #   Return cached scrape results if a prior scrape for the same parameters is
+      #   younger than this many milliseconds.
+      #
+      #   @return [Integer, nil]
+      optional :max_age_ms, Integer, api_name: :maxAgeMs
+
+      # @!attribute pdf
+      #
+      #   @return [ContextDev::Models::WebExtractParams::Pdf, nil]
+      optional :pdf, -> { ContextDev::WebExtractParams::Pdf }
+
+      # @!attribute stop_after_ms
+      #   Soft time budget for the crawl in milliseconds.
+      #
+      #   @return [Integer, nil]
+      optional :stop_after_ms, Integer, api_name: :stopAfterMs
+
+      # @!attribute timeout_ms
+      #   Optional timeout in milliseconds for the request. If the request takes longer
+      #   than this value, it will be aborted with a 408 status code. Maximum allowed
+      #   value is 300000ms (5 minutes).
+      #
+      #   @return [Integer, nil]
+      optional :timeout_ms, Integer, api_name: :timeoutMS
+
+      # @!attribute wait_for_ms
+      #   Optional browser wait time in milliseconds after initial page load for each
+      #   crawled page.
+      #
+      #   @return [Integer, nil]
+      optional :wait_for_ms, Integer, api_name: :waitForMs
+
+      # @!method initialize(schema:, url:, fact_check: nil, follow_subdomains: nil, include_frames: nil, instructions: nil, max_age_ms: nil, pdf: nil, stop_after_ms: nil, timeout_ms: nil, wait_for_ms: nil, request_options: {})
+      #   Some parameter documentations has been truncated, see
+      #   {ContextDev::Models::WebExtractParams} for more details.
+      #
+      #   @param schema [Hash{Symbol=>Object}] JSON Schema for the returned data object. TypeScript Zod users can pass a JSON S
+      #
+      #   @param url [String] The starting website URL to crawl and extract from. Must include http:// or http
+      #
+      #   @param fact_check [Boolean] When true (default), every returned value must be grounded in facts stated on th
+      #
+      #   @param follow_subdomains [Boolean] When true, follow links on subdomains of the starting URL's domain.
+      #
+      #   @param include_frames [Boolean] When true, iframe contents are included in Markdown before extraction.
+      #
+      #   @param instructions [String] Optional extraction guidance, such as which facts to prioritize or how to interp
+      #
+      #   @param max_age_ms [Integer] Return cached scrape results if a prior scrape for the same parameters is younge
+      #
+      #   @param pdf [ContextDev::Models::WebExtractParams::Pdf]
+      #
+      #   @param stop_after_ms [Integer] Soft time budget for the crawl in milliseconds.
+      #
+      #   @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
+      #
+      #   @param wait_for_ms [Integer] Optional browser wait time in milliseconds after initial page load for each craw
+      #
+      #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]
+
+      class Pdf < ContextDev::Internal::Type::BaseModel
+        # @!attribute end_
+        #   Last 1-based PDF page to parse. Must be greater than or equal to start when both
+        #   are provided.
+        #
+        #   @return [Integer, nil]
+        optional :end_, Integer, api_name: :end
+
+        # @!attribute should_parse
+        #   When true, PDF pages are fetched and parsed. When false, PDF pages are skipped.
+        #
+        #   @return [Boolean, nil]
+        optional :should_parse, ContextDev::Internal::Type::Boolean, api_name: :shouldParse
+
+        # @!attribute start
+        #   First 1-based PDF page to parse.
+        #
+        #   @return [Integer, nil]
+        optional :start, Integer
+
+        # @!method initialize(end_: nil, should_parse: nil, start: nil)
+        #   Some parameter documentations has been truncated, see
+        #   {ContextDev::Models::WebExtractParams::Pdf} for more details.
+        #
+        #   @param end_ [Integer] Last 1-based PDF page to parse. Must be greater than or equal to start when both
+        #
+        #   @param should_parse [Boolean] When true, PDF pages are fetched and parsed. When false, PDF pages are skipped.
+        #
+        #   @param start [Integer] First 1-based PDF page to parse.
+      end
+    end
+  end
+end

data/lib/context_dev/models/web_extract_response.rb

@@ -0,0 +1,83 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Models
+    # @see ContextDev::Resources::Web#extract
+    class WebExtractResponse < ContextDev::Internal::Type::BaseModel
+      # @!attribute data
+      #   Extracted data matching the request schema
+      #
+      #   @return [Hash{Symbol=>Object}]
+      required :data, ContextDev::Internal::Type::HashOf[ContextDev::Internal::Type::Unknown]
+
+      # @!attribute metadata
+      #
+      #   @return [ContextDev::Models::WebExtractResponse::Metadata]
+      required :metadata, -> { ContextDev::Models::WebExtractResponse::Metadata }
+
+      # @!attribute status
+      #   Status of the response, e.g., 'ok'
+      #
+      #   @return [String]
+      required :status, String
+
+      # @!attribute url
+      #   The starting URL that was analyzed
+      #
+      #   @return [String]
+      required :url, String
+
+      # @!attribute urls_analyzed
+      #   List of URLs whose Markdown was used for extraction
+      #
+      #   @return [Array<String>]
+      required :urls_analyzed, ContextDev::Internal::Type::ArrayOf[String]
+
+      # @!method initialize(data:, metadata:, status:, url:, urls_analyzed:)
+      #   @param data [Hash{Symbol=>Object}] Extracted data matching the request schema
+      #
+      #   @param metadata [ContextDev::Models::WebExtractResponse::Metadata]
+      #
+      #   @param status [String] Status of the response, e.g., 'ok'
+      #
+      #   @param url [String] The starting URL that was analyzed
+      #
+      #   @param urls_analyzed [Array<String>] List of URLs whose Markdown was used for extraction
+
+      # @see ContextDev::Models::WebExtractResponse#metadata
+      class Metadata < ContextDev::Internal::Type::BaseModel
+        # @!attribute max_crawl_depth
+        #
+        #   @return [Integer]
+        required :max_crawl_depth, Integer, api_name: :maxCrawlDepth
+
+        # @!attribute num_failed
+        #
+        #   @return [Integer]
+        required :num_failed, Integer, api_name: :numFailed
+
+        # @!attribute num_skipped
+        #
+        #   @return [Integer]
+        required :num_skipped, Integer, api_name: :numSkipped
+
+        # @!attribute num_succeeded
+        #
+        #   @return [Integer]
+        required :num_succeeded, Integer, api_name: :numSucceeded
+
+        # @!attribute num_urls
+        #
+        #   @return [Integer]
+        required :num_urls, Integer, api_name: :numUrls
+
+        # @!method initialize(max_crawl_depth:, num_failed:, num_skipped:, num_succeeded:, num_urls:)
+        #   @param max_crawl_depth [Integer]
+        #   @param num_failed [Integer]
+        #   @param num_skipped [Integer]
+        #   @param num_succeeded [Integer]
+        #   @param num_urls [Integer]
+      end
+    end
+  end
+end

data/lib/context_dev/models/web_extract_styleguide_params.rb

@@ -24,6 +24,15 @@ module ContextDev
       #   @return [String, nil]
       optional :domain, String
 
+      # @!attribute max_age_ms
+      #   Maximum age in milliseconds for cached data before the API performs a hard
+      #   refresh. Defaults to 3 months (7776000000 ms). Values below 1 day (86400000 ms)
+      #   are clamped to 1 day; values above 1 year (31536000000 ms) are clamped to 1
+      #   year.
+      #
+      #   @return [Integer, nil]
+      optional :max_age_ms, Integer
+
       # @!attribute timeout_ms
       #   Optional timeout in milliseconds for the request. If the request takes longer
       #   than this value, it will be aborted with a 408 status code. Maximum allowed
@@ -32,7 +41,7 @@ module ContextDev
       #   @return [Integer, nil]
       optional :timeout_ms, Integer
 
-      # @!method initialize(direct_url: nil, domain: nil, timeout_ms: nil, request_options: {})
+      # @!method initialize(direct_url: nil, domain: nil, max_age_ms: nil, timeout_ms: nil, request_options: {})
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebExtractStyleguideParams} for more details.
       #
@@ -40,6 +49,8 @@ module ContextDev
       #
       #   @param domain [String] Domain name to extract styleguide from (e.g., 'example.com', 'google.com'). The
       #
+      #   @param max_age_ms [Integer] Maximum age in milliseconds for cached data before the API performs a hard refre
+      #
       #   @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
       #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]

data/lib/context_dev/models.rb

@@ -69,6 +69,8 @@ module ContextDev
 
   WebExtractFontsParams = ContextDev::Models::WebExtractFontsParams
 
+  WebExtractParams = ContextDev::Models::WebExtractParams
+
   WebExtractStyleguideParams = ContextDev::Models::WebExtractStyleguideParams
 
   WebScreenshotParams = ContextDev::Models::WebScreenshotParams

data/lib/context_dev/resources/web.rb

@@ -3,18 +3,68 @@
 module ContextDev
   module Resources
     class Web
+      # Some parameter documentations has been truncated, see
+      # {ContextDev::Models::WebExtractParams} for more details.
+      #
+      # Crawl a website, convert pages to Markdown using the scrape cache, and extract
+      # structured data into the provided JSON Schema. The schema must describe the
+      # response data object. This endpoint does not accept targeted page-type
+      # selection.
+      #
+      # @overload extract(schema:, url:, fact_check: nil, follow_subdomains: nil, include_frames: nil, instructions: nil, max_age_ms: nil, pdf: nil, stop_after_ms: nil, timeout_ms: nil, wait_for_ms: nil, request_options: {})
+      #
+      # @param schema [Hash{Symbol=>Object}] JSON Schema for the returned data object. TypeScript Zod users can pass a JSON S
+      #
+      # @param url [String] The starting website URL to crawl and extract from. Must include http:// or http
+      #
+      # @param fact_check [Boolean] When true (default), every returned value must be grounded in facts stated on th
+      #
+      # @param follow_subdomains [Boolean] When true, follow links on subdomains of the starting URL's domain.
+      #
+      # @param include_frames [Boolean] When true, iframe contents are included in Markdown before extraction.
+      #
+      # @param instructions [String] Optional extraction guidance, such as which facts to prioritize or how to interp
+      #
+      # @param max_age_ms [Integer] Return cached scrape results if a prior scrape for the same parameters is younge
+      #
+      # @param pdf [ContextDev::Models::WebExtractParams::Pdf]
+      #
+      # @param stop_after_ms [Integer] Soft time budget for the crawl in milliseconds.
+      #
+      # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
+      #
+      # @param wait_for_ms [Integer] Optional browser wait time in milliseconds after initial page load for each craw
+      #
+      # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
+      #
+      # @return [ContextDev::Models::WebExtractResponse]
+      #
+      # @see ContextDev::Models::WebExtractParams
+      def extract(params)
+        parsed, options = ContextDev::WebExtractParams.dump_request(params)
+        @client.request(
+          method: :post,
+          path: "web/extract",
+          body: parsed,
+          model: ContextDev::Models::WebExtractResponse,
+          options: options
+        )
+      end
+
       # Some parameter documentations has been truncated, see
       # {ContextDev::Models::WebExtractFontsParams} for more details.
       #
       # Scrape font information from a website including font families, usage
       # statistics, fallbacks, and element/word counts.
       #
-      # @overload extract_fonts(direct_url: nil, domain: nil, timeout_ms: nil, request_options: {})
+      # @overload extract_fonts(direct_url: nil, domain: nil, max_age_ms: nil, timeout_ms: nil, request_options: {})
       #
       # @param direct_url [String] A specific URL to fetch fonts from directly, bypassing domain resolution (e.g.,
       #
       # @param domain [String] Domain name to extract fonts from (e.g., 'example.com', 'google.com'). The domai
       #
+      # @param max_age_ms [Integer] Maximum age in milliseconds for cached data before the API performs a hard refre
+      #
       # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
@@ -28,7 +78,11 @@ module ContextDev
         @client.request(
           method: :get,
           path: "web/fonts",
-          query: query.transform_keys(direct_url: "directUrl", timeout_ms: "timeoutMS"),
+          query: query.transform_keys(
+            direct_url: "directUrl",
+            max_age_ms: "maxAgeMs",
+            timeout_ms: "timeoutMS"
+          ),
           model: ContextDev::Models::WebExtractFontsResponse,
           options: options
         )
@@ -40,12 +94,14 @@ module ContextDev
       # Extract a comprehensive design system from a website including colors,
       # typography, spacing, shadows, and UI components.
       #
-      # @overload extract_styleguide(direct_url: nil, domain: nil, timeout_ms: nil, request_options: {})
+      # @overload extract_styleguide(direct_url: nil, domain: nil, max_age_ms: nil, timeout_ms: nil, request_options: {})
       #
       # @param direct_url [String] A specific URL to fetch the styleguide from directly, bypassing domain resolutio
       #
       # @param domain [String] Domain name to extract styleguide from (e.g., 'example.com', 'google.com'). The
       #
+      # @param max_age_ms [Integer] Maximum age in milliseconds for cached data before the API performs a hard refre
+      #
       # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
@@ -59,7 +115,11 @@ module ContextDev
         @client.request(
           method: :get,
           path: "web/styleguide",
-          query: query.transform_keys(direct_url: "directUrl", timeout_ms: "timeoutMS"),
+          query: query.transform_keys(
+            direct_url: "directUrl",
+            max_age_ms: "maxAgeMs",
+            timeout_ms: "timeoutMS"
+          ),
           model: ContextDev::Models::WebExtractStyleguideResponse,
           options: options
         )

data/lib/context_dev/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ContextDev
-  VERSION = "1.23.0"
+  VERSION = "1.25.0"
 end

data/lib/context_dev.rb

@@ -82,6 +82,8 @@ require_relative "context_dev/models/utility_prefetch_params"
 require_relative "context_dev/models/utility_prefetch_response"
 require_relative "context_dev/models/web_extract_fonts_params"
 require_relative "context_dev/models/web_extract_fonts_response"
+require_relative "context_dev/models/web_extract_params"
+require_relative "context_dev/models/web_extract_response"
 require_relative "context_dev/models/web_extract_styleguide_params"
 require_relative "context_dev/models/web_extract_styleguide_response"
 require_relative "context_dev/models/web_screenshot_params"

data/rbi/context_dev/models/web_extract_fonts_params.rbi

@@ -32,6 +32,16 @@ module ContextDev
       sig { params(domain: String).void }
       attr_writer :domain
 
+      # Maximum age in milliseconds for cached data before the API performs a hard
+      # refresh. Defaults to 3 months (7776000000 ms). Values below 1 day (86400000 ms)
+      # are clamped to 1 day; values above 1 year (31536000000 ms) are clamped to 1
+      # year.
+      sig { returns(T.nilable(Integer)) }
+      attr_reader :max_age_ms
+
+      sig { params(max_age_ms: Integer).void }
+      attr_writer :max_age_ms
+
       # Optional timeout in milliseconds for the request. If the request takes longer
       # than this value, it will be aborted with a 408 status code. Maximum allowed
       # value is 300000ms (5 minutes).
@@ -45,6 +55,7 @@ module ContextDev
         params(
           direct_url: String,
           domain: String,
+          max_age_ms: Integer,
           timeout_ms: Integer,
           request_options: ContextDev::RequestOptions::OrHash
         ).returns(T.attached_class)
@@ -58,6 +69,11 @@ module ContextDev
         # domain will be automatically normalized and validated. You must provide either
         # 'domain' or 'directUrl', but not both.
         domain: nil,
+        # Maximum age in milliseconds for cached data before the API performs a hard
+        # refresh. Defaults to 3 months (7776000000 ms). Values below 1 day (86400000 ms)
+        # are clamped to 1 day; values above 1 year (31536000000 ms) are clamped to 1
+        # year.
+        max_age_ms: nil,
         # Optional timeout in milliseconds for the request. If the request takes longer
         # than this value, it will be aborted with a 408 status code. Maximum allowed
         # value is 300000ms (5 minutes).
@@ -71,6 +87,7 @@ module ContextDev
           {
             direct_url: String,
             domain: String,
+            max_age_ms: Integer,
             timeout_ms: Integer,
             request_options: ContextDev::RequestOptions
           }