context.dev 2.8.0 → 2.10.0

data/lib/context_dev/models/web_web_scrape_sitemap_response.rb

@@ -23,7 +23,8 @@ module ContextDev
       required :success, enum: -> { ContextDev::Models::WebWebScrapeSitemapResponse::Success }
 
       # @!attribute urls
-      #   Array of discovered page URLs from the sitemap (max 500)
+      #   Discovered page URLs from the sitemap, up to `maxLinks`. When `search` is set
+      #   these are only the matching pages, most relevant first.
       #
       #   @return [Array<String>]
       required :urls, ContextDev::Internal::Type::ArrayOf[String]
@@ -45,7 +46,7 @@ module ContextDev
       #
       #   @param success [Boolean, ContextDev::Models::WebWebScrapeSitemapResponse::Success] Indicates success
       #
-      #   @param urls [Array<String>] Array of discovered page URLs from the sitemap (max 500)
+      #   @param urls [Array<String>] Discovered page URLs from the sitemap, up to `maxLinks`. When `search` is set th
       #
       #   @param key_metadata [ContextDev::Models::WebWebScrapeSitemapResponse::KeyMetadata] Metadata about the API key used for the request. Included in every response when
 

data/lib/context_dev/models.rb

@@ -45,6 +45,8 @@ module ContextDev
 
   BatchCancelParams = ContextDev::Models::BatchCancelParams
 
+  BatchDeleteParams = ContextDev::Models::BatchDeleteParams
+
   BatchGetResultsParams = ContextDev::Models::BatchGetResultsParams
 
   BatchListParams = ContextDev::Models::BatchListParams
@@ -95,10 +97,14 @@ module ContextDev
 
   MonitorUpdateParams = ContextDev::Models::MonitorUpdateParams
 
+  NewsSearchParams = ContextDev::Models::NewsSearchParams
+
   PageErrorCount = ContextDev::Models::PageErrorCount
 
   ParseHandleParams = ContextDev::Models::ParseHandleParams
 
+  PersonEnrichParams = ContextDev::Models::PersonEnrichParams
+
   UtilityPrefetchParams = ContextDev::Models::UtilityPrefetchParams
 
   WebExtractCompetitorsParams = ContextDev::Models::WebExtractCompetitorsParams

data/lib/context_dev/resources/batch.rb

@@ -2,6 +2,7 @@
 
 module ContextDev
   module Resources
+    # Scrape many pages or crawl a site asynchronously.
     class Batch
       # Check progress, and get download links once the batch finishes.
       #
@@ -60,6 +61,27 @@ module ContextDev
         )
       end
 
+      # Permanently delete a finished batch and its stored results. Active batches must
+      # settle first.
+      #
+      # @overload delete(batch_id, request_options: {})
+      #
+      # @param batch_id [String] ID of the batch to retrieve or cancel.
+      #
+      # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
+      #
+      # @return [ContextDev::Models::BatchDeleteResponse]
+      #
+      # @see ContextDev::Models::BatchDeleteParams
+      def delete(batch_id, params = {})
+        @client.request(
+          method: :delete,
+          path: ["batch/%1$s", batch_id],
+          model: ContextDev::Models::BatchDeleteResponse,
+          options: params[:request_options]
+        )
+      end
+
       # Stop a batch from starting new pages. In-progress pages finish, and unused
       # credits are refunded.
       #
@@ -115,15 +137,17 @@ module ContextDev
       # Some parameter documentations has been truncated, see
       # {ContextDev::Models::BatchSubmitParams} for more details.
       #
-      # Retrieve and normalize a person profile from identifiers.
+      # Scrape 25K URLs or crawl large websites asynchronously.
+      #
+      # @overload submit(input:, tags: nil, webhook_url: nil, idempotency_key: nil, request_options: {})
       #
-      # @overload submit(identifiers:, tags: nil, timeout_ms: nil, request_options: {})
+      # @param input [ContextDev::Models::BatchSubmitParams::Input::Scrape, ContextDev::Models::BatchSubmitParams::Input::Crawl] Body param: Choose a URL list or a site crawl.
       #
-      # @param identifiers [ContextDev::Models::BatchSubmitParams::Identifiers] Known identifiers for the person. At least one identifier is required.
+      # @param tags [Array<String>] Body param: Tags stored on the batch. Filter the batch list by them later.
       #
-      # @param tags [Array<String>] Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.
+      # @param webhook_url [String] Body param: URL notified when the batch finishes.
       #
-      # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
+      # @param idempotency_key [String] Header param: Any string unique to this submission. Retries with the same key re
       #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
       #
@@ -132,10 +156,12 @@ module ContextDev
       # @see ContextDev::Models::BatchSubmitParams
       def submit(params)
         parsed, options = ContextDev::BatchSubmitParams.dump_request(params)
+        header_params = {idempotency_key: "idempotency-key"}
         @client.request(
           method: :post,
-          path: "people/retrieve",
-          body: parsed,
+          path: "batch/submit",
+          headers: parsed.slice(*header_params.keys).transform_keys(header_params),
+          body: parsed.except(*header_params.keys),
           model: ContextDev::Models::BatchSubmitResponse,
           options: options
         )

data/lib/context_dev/resources/brand.rb

@@ -68,20 +68,20 @@ module ContextDev
       # Some parameter documentations has been truncated, see
       # {ContextDev::Models::BrandSearchParams} for more details.
       #
-      # Search brands by name or domain and get back up to 10 lightweight matches
-      # (domain, name, logo), most popular first: by Tranco rank, then market cap for
-      # brands outside the Tranco list, with text relevance breaking ties. Matching is
-      # prefix-based with no typo tolerance, so it is suited to autocomplete. Only
-      # brands already in the Context.dev index are returned — use /brand/retrieve to
-      # fetch (and index) a specific domain. Free on Pro and Scale plans; costs 1 credit
-      # per request on the Free and Starter plans.
+      # Search indexed brands by name or domain
       #
-      # @overload search(query:, tags: nil, request_options: {})
+      # @overload search(query:, autocomplete: nil, query_by: nil, tags: nil, typo_tolerance: nil, request_options: {})
       #
-      # @param query [String] Search term, matched against brand names and domains by prefix (e.g. 'nike', 'ni
+      # @param query [String] Search term, matched against the fields selected by queryBy (e.g. 'nike', 'nike.
+      #
+      # @param autocomplete [Boolean] Whether the search term matches by prefix, so partial words match as they are ty
+      #
+      # @param query_by [Array<Symbol, ContextDev::Models::BrandSearchParams::QueryBy>] Fields to match the search term against, as a comma-separated list or repeated p
       #
       # @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are
       #
+      # @param typo_tolerance [Integer] Maximum number of typos tolerated when matching, from 0 to 2. Defaults to 0 (no
+      #
       # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
       #
       # @return [ContextDev::Models::BrandSearchResponse]
@@ -93,7 +93,7 @@ module ContextDev
         @client.request(
           method: :get,
           path: "brand/search",
-          query: query,
+          query: query.transform_keys(query_by: "queryBy", typo_tolerance: "typoTolerance"),
           model: ContextDev::Models::BrandSearchResponse,
           options: options
         )

data/lib/context_dev/resources/news.rb

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Resources
+    # Search live first-party RSS and free historical news data by company identity.
+    class News
+      # Searches live and historical company news for one company, identified in
+      # searchBy by name, domain, ticker (optionally disambiguated by exchange), or
+      # ISIN. Results can be filtered by publisher domain, publisher country, article
+      # language, article type, and published-at date, and include stable story IDs,
+      # source metadata, verified entity relevance, and cursor pagination.
+      #
+      # @overload search(search_by:, cursor: nil, filter_by: nil, limit: nil, sort_by: nil, tags: nil, request_options: {})
+      #
+      # @param search_by [ContextDev::Models::NewsSearchParams::SearchBy] What to search for.
+      #
+      # @param cursor [String, nil] Opaque next_cursor from the previous response, or null for the first page.
+      #
+      # @param filter_by [ContextDev::Models::NewsSearchParams::FilterBy] Optional result filters.
+      #
+      # @param limit [Integer] Maximum results to return. Defaults to 10.
+      #
+      # @param sort_by [ContextDev::Models::NewsSearchParams::SortBy] Result ordering. Defaults to newest.
+      #
+      # @param tags [Array<String>] Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.
+      #
+      # @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}, nil]
+      #
+      # @return [ContextDev::Models::NewsSearchResponse]
+      #
+      # @see ContextDev::Models::NewsSearchParams
+      def search(params)
+        parsed, options = ContextDev::NewsSearchParams.dump_request(params)
+        @client.request(
+          method: :post,
+          path: "news/search",
+          body: parsed,
+          model: ContextDev::Models::NewsSearchResponse,
+          options: options
+        )
+      end
+
+      # @api private
+      #
+      # @param client [ContextDev::Client]
+      def initialize(client:)
+        @client = client
+      end
+    end
+  end
+end

data/lib/context_dev/resources/parse.rb

@@ -17,19 +17,19 @@ module ContextDev
       #
       # @param extension [Symbol, ContextDev::Models::ParseHandleParams::Extension] Query param: Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
       #
-      # @param include_images [Boolean, Symbol, ContextDev::Models::ParseHandleParams::IncludeImages] Query param: Include image references in Markdown output
+      # @param include_images [Boolean] Query param: Include image references in Markdown output
       #
-      # @param include_links [Boolean, Symbol, ContextDev::Models::ParseHandleParams::IncludeLinks] Query param: Preserve hyperlinks in Markdown output
+      # @param include_links [Boolean] Query param: Preserve hyperlinks in Markdown output
       #
-      # @param ocr [Boolean, Symbol, ContextDev::Models::ParseHandleParams::Ocr] Query param: When true for PDF inputs, detect and OCR images embedded in the sel
+      # @param ocr [Boolean] Query param: When true for PDF inputs, OCR the selected pages that have no usabl
       #
       # @param pdf [ContextDev::Models::ParseHandleParams::Pdf] Query param: PDF page-range options as a JSON object, e.g. {"start": 2, "end": 5
       #
-      # @param shorten_base64_images [Boolean, Symbol, ContextDev::Models::ParseHandleParams::ShortenBase64Images] Query param: Shorten base64-encoded image data in the Markdown output
+      # @param shorten_base64_images [Boolean] Query param: Shorten base64-encoded image data in the Markdown output
       #
       # @param tags [Array<String>] Query param: Optional comma-separated caller-defined tags for tracking this requ
       #
-      # @param use_main_content_only [Boolean, Symbol, ContextDev::Models::ParseHandleParams::UseMainContentOnly] Query param: Extract only the main content from HTML-like inputs
+      # @param use_main_content_only [Boolean] Query param: Extract only the main content from HTML-like inputs
       #
       # @param zdr [Symbol, ContextDev::Models::ParseHandleParams::Zdr] Query param: Set to enabled to bypass shared caches and omit request and respons
       #

data/lib/context_dev/resources/people.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Resources
+    class People
+      # Some parameter documentations has been truncated, see
+      # {ContextDev::Models::PersonEnrichParams} for more details.
+      #
+      # Finds and normalizes the best available person candidate from additive identity
+      # clues, then assigns an identity match score from 0 to 100. Available on all paid
+      # plans. Successful requests cost 20 credits. Disposable and free email addresses
+      # (like gmail.com, yahoo.com) will throw a 422 error.
+      #
+      # @overload enrich(company: nil, education: nil, email: nil, location: nil, name: nil, social_urls: nil, tags: nil, timeout_ms: nil, request_options: {})
+      #
+      # @param company [ContextDev::Models::PersonEnrichParams::Company]
+      #
+      # @param education [Array<ContextDev::Models::PersonEnrichParams::Education>]
+      #
+      # @param email [String]
+      #
+      # @param location [ContextDev::Models::PersonEnrichParams::Location]
+      #
+      # @param name [ContextDev::Models::PersonEnrichParams::Name]
+      #
+      # @param social_urls [Array<String>]
+      #
+      # @param tags [Array<String>] Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.
+      #
+      # @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]
+      #
+      # @return [ContextDev::Models::PersonEnrichResponse]
+      #
+      # @see ContextDev::Models::PersonEnrichParams
+      def enrich(params = {})
+        parsed, options = ContextDev::PersonEnrichParams.dump_request(params)
+        @client.request(
+          method: :post,
+          path: "people/enrich",
+          body: parsed,
+          model: ContextDev::Models::PersonEnrichResponse,
+          options: options
+        )
+      end
+
+      # @api private
+      #
+      # @param client [ContextDev::Client]
+      def initialize(client:)
+        @client = client
+      end
+    end
+  end
+end

data/lib/context_dev/resources/utility.rb

@@ -6,16 +6,17 @@ module ContextDev
       # Some parameter documentations has been truncated, see
       # {ContextDev::Models::UtilityPrefetchParams} for more details.
       #
-      # Signal that you may fetch brand data soon to improve latency. The type field
-      # selects what to prefetch (currently only 'brand') and identifier carries exactly
-      # one lookup key: a domain, or an email whose domain is extracted and validated
-      # (free email providers and disposable email addresses are not allowed).
+      # Signal that you may fetch data soon to improve latency. The type field selects
+      # what to prefetch ('brand' queues a brand data fetch, 'styleguide' queues a
+      # styleguide extraction) and identifier carries exactly one lookup key: a domain,
+      # or an email whose domain is extracted and validated (free email providers and
+      # disposable email addresses are not allowed).
       #
       # @overload prefetch(identifier:, type:, tags: nil, timeout_ms: nil, request_options: {})
       #
-      # @param identifier [ContextDev::Models::UtilityPrefetchParams::Identifier::UtilityPrefetchDomainIdentifier, ContextDev::Models::UtilityPrefetchParams::Identifier::UtilityPrefetchEmailIdentifier] Identifier of the brand to prefetch. Provide exactly one of domain or email.
+      # @param identifier [ContextDev::Models::UtilityPrefetchParams::Identifier::UtilityPrefetchDomainIdentifier, ContextDev::Models::UtilityPrefetchParams::Identifier::UtilityPrefetchEmailIdentifier] Identifier of the target to prefetch. Provide exactly one of domain or email.
       #
-      # @param type [Symbol, ContextDev::Models::UtilityPrefetchParams::Type] What to prefetch. Currently only 'brand' is supported.
+      # @param type [Symbol, ContextDev::Models::UtilityPrefetchParams::Type] What to prefetch: 'brand' warms the brand data cache, 'styleguide' warms the sty
       #
       # @param tags [Array<String>] Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.
       #

data/lib/context_dev/resources/web.rb

@@ -188,7 +188,7 @@ module ContextDev
       #
       # @param full_screenshot [Symbol, ContextDev::Models::WebScreenshotParams::FullScreenshot] Optional parameter to determine screenshot type. If 'true', takes a full page sc
       #
-      # @param handle_cookie_popup [Boolean, Symbol, ContextDev::Models::WebScreenshotParams::HandleCookiePopup] Optional parameter to control cookie/consent popup handling. If 'true', we dismi
+      # @param handle_cookie_popup [Boolean] Optional parameter to control cookie/consent popup handling. If 'true', we dismi
       #
       # @param max_age_ms [Integer, nil] Return a cached screenshot if a prior screenshot for the same parameters exists
       #
@@ -359,7 +359,7 @@ module ContextDev
       #
       # @param headers [Hash{Symbol=>String}] Optional outbound HTTP headers forwarded only to the target URL, sent as deep-ob
       #
-      # @param include_frames [Boolean, Symbol, ContextDev::Models::WebWebScrapeHTMLParams::IncludeFrames] When true, iframes are rendered inline into the returned HTML.
+      # @param include_frames [Boolean] When true, iframes are rendered inline into the returned HTML.
       #
       # @param include_selectors [Array<String>, nil] CSS selectors. When provided, only matching subtrees (and their descendants) are
       #
@@ -367,13 +367,13 @@ module ContextDev
       #
       # @param pdf [ContextDev::Models::WebWebScrapeHTMLParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
-      # @param settle_animations [Boolean, Symbol, ContextDev::Models::WebWebScrapeHTMLParams::SettleAnimations] When true, waits briefly for CSS and transition animations to settle before extr
+      # @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before extr
       #
       # @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are
       #
       # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
-      # @param use_main_content_only [Boolean, Symbol, ContextDev::Models::WebWebScrapeHTMLParams::UseMainContentOnly] When true, return only the page's main content in the HTML response, excluding h
+      # @param use_main_content_only [Boolean] When true, return only the page's main content in the HTML response, excluding h
       #
       # @param wait_for_ms [Integer, nil] Optional browser wait time in milliseconds after initial page load. Min: 0. Max:
       #
@@ -420,7 +420,7 @@ module ContextDev
       #
       # @param actions [Array<ContextDev::Models::WebWebScrapeImagesParams::Action::Wait, ContextDev::Models::WebWebScrapeImagesParams::Action::Perform>, nil] Optional browser actions executed in array order after the page loads and before
       #
-      # @param dedupe [Boolean, Symbol, ContextDev::Models::WebWebScrapeImagesParams::Dedupe] When true, visually duplicate images are removed: every image is loaded and perc
+      # @param dedupe [Boolean] When true, visually duplicate images are removed: every image is loaded and perc
       #
       # @param enrichment [ContextDev::Models::WebWebScrapeImagesParams::Enrichment, nil] Optional per-image processing, sent as deep-object query params such as enrichme
       #
@@ -462,20 +462,33 @@ module ContextDev
       # responses from a recognized API key; use error_code to distinguish stable
       # failure categories.
       #
+      # ### YouTube
+      #
+      # YouTube URLs return the video or channel itself rather than the surrounding
+      # player and navigation chrome. A URL addressing a single video (`/watch`,
+      # `youtu.be`, `/shorts`, `/embed`, `/live`) returns its title, channel, duration,
+      # view count, keywords, full description, and the transcript when the video has
+      # captions that can be retrieved; videos without captions return everything except
+      # the transcript. A channel URL (`/channel/UC…`, `/@handle`, `/c/…`, `/user/…`)
+      # returns its name, handle, subscriber count, video count, and full description.
+      # When `includeImages=true`, video responses also include the thumbnail and
+      # channel responses include the avatar. Costs the same as any other scrape.
+      #
       # ### Billing & errors
       #
-      # | HTTP status | Billed?                                   | Meaning                                                                                  |
-      # | ----------- | ----------------------------------------- | ---------------------------------------------------------------------------------------- |
-      # | 200         | Yes — 1 credit, or 2 credits with actions | Successful scrape, including a zero-length result when includeSelectors matched nothing  |
-      # | 400         | No                                        | Invalid input, skipped PDF, or the page could not be scraped                             |
-      # | 401 / 403   | No                                        | Invalid/disabled key, insufficient permissions, or credits exhausted; inspect error_code |
-      # | 404         | No                                        | Target page returned or fingerprinted as not found                                       |
-      # | 408         | No                                        | Request timed out                                                                        |
-      # | 415         | No                                        | Unsupported content type                                                                 |
-      # | 429         | No                                        | Per-minute rate limit exceeded; honor Retry-After                                        |
-      # | 500         | No                                        | Internal error                                                                           |
+      # | HTTP status | Billed?                                   | Meaning                                                                                                                                                                                                                                                                                                       |
+      # | ----------- | ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+      # | 200         | Yes — 1 credit, or 2 credits with actions | Successful scrape, including a zero-length result when includeSelectors matched nothing                                                                                                                                                                                                                       |
+      # | 400         | No                                        | Invalid input, skipped PDF, or the page could not be scraped. error_code WEBSITE_BLOCKED specifically means the site answered with an anti-bot challenge, CAPTCHA wall, or login shell instead of the page (even when the site returned HTTP 200) — retrying later or from another country sometimes succeeds |
+      # | 401 / 403   | No                                        | Invalid/disabled key, insufficient permissions, or credits exhausted; inspect error_code                                                                                                                                                                                                                      |
+      # | 404         | No                                        | Target page returned or fingerprinted as not found                                                                                                                                                                                                                                                            |
+      # | 408         | No                                        | Request timed out                                                                                                                                                                                                                                                                                             |
+      # | 413         | No                                        | Target content exceeds the maximum supported size (20 MB)                                                                                                                                                                                                                                                     |
+      # | 415         | No                                        | Unsupported content type                                                                                                                                                                                                                                                                                      |
+      # | 429         | No                                        | Per-minute rate limit exceeded; honor Retry-After                                                                                                                                                                                                                                                             |
+      # | 500         | No                                        | Internal error                                                                                                                                                                                                                                                                                                |
       #
-      # @overload web_scrape_md(url:, actions: nil, country: nil, exclude_selectors: nil, headers: nil, include_frames: nil, include_images: nil, include_links: nil, include_selectors: nil, max_age_ms: nil, pdf: nil, settle_animations: nil, shorten_base64_images: nil, tags: nil, timeout_ms: nil, use_main_content_only: nil, wait_for_ms: nil, zdr: nil, request_options: {})
+      # @overload web_scrape_md(url:, actions: nil, country: nil, exclude_selectors: nil, headers: nil, include_frames: nil, include_html: nil, include_images: nil, include_links: nil, include_selectors: nil, max_age_ms: nil, pdf: nil, settle_animations: nil, shorten_base64_images: nil, tags: nil, timeout_ms: nil, use_main_content_only: nil, wait_for_ms: nil, zdr: nil, request_options: {})
       #
       # @param url [String] Full URL to scrape into LLM usable Markdown (must include http:// or https:// pr
       #
@@ -487,11 +500,13 @@ module ContextDev
       #
       # @param headers [Hash{Symbol=>String}] Optional outbound HTTP headers forwarded only to the target URL, sent as deep-ob
       #
-      # @param include_frames [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeFrames] When true, the contents of iframes are rendered to Markdown.
+      # @param include_frames [Boolean] When true, the contents of iframes are rendered to Markdown.
       #
-      # @param include_images [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeImages] Include image references in Markdown output
+      # @param include_html [Boolean] When true, the response also includes an `html` field with the page HTML the Mar
       #
-      # @param include_links [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::IncludeLinks] Preserve hyperlinks in Markdown output
+      # @param include_images [Boolean] Include image references in Markdown output
+      #
+      # @param include_links [Boolean] Preserve hyperlinks in Markdown output
       #
       # @param include_selectors [Array<String>, nil] CSS selectors. When provided, only matching HTML subtrees (and their descendants
       #
@@ -499,15 +514,15 @@ module ContextDev
       #
       # @param pdf [ContextDev::Models::WebWebScrapeMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
-      # @param settle_animations [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::SettleAnimations] When true, waits briefly for CSS and transition animations to settle before conv
+      # @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before conv
       #
-      # @param shorten_base64_images [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::ShortenBase64Images] Shorten base64-encoded image data in the Markdown output
+      # @param shorten_base64_images [Boolean] Shorten base64-encoded image data in the Markdown output
       #
       # @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are
       #
       # @param timeout_ms [Integer] Optional timeout in milliseconds for the request. If the request takes longer th
       #
-      # @param use_main_content_only [Boolean, Symbol, ContextDev::Models::WebWebScrapeMdParams::UseMainContentOnly] Extract only the main content of the page, excluding headers, footers, sidebars,
+      # @param use_main_content_only [Boolean] Extract only the main content of the page, excluding headers, footers, sidebars,
       #
       # @param wait_for_ms [Integer, nil] Optional browser wait time in milliseconds after initial page load before conver
       #
@@ -527,6 +542,7 @@ module ContextDev
           query: query.transform_keys(
             exclude_selectors: "excludeSelectors",
             include_frames: "includeFrames",
+            include_html: "includeHTML",
             include_images: "includeImages",
             include_links: "includeLinks",
             include_selectors: "includeSelectors",
@@ -545,9 +561,13 @@ module ContextDev
       # Some parameter documentations has been truncated, see
       # {ContextDev::Models::WebWebScrapeSitemapParams} for more details.
       #
-      # Crawl an entire website's sitemap and return all discovered page URLs.
+      # Crawl an entire website's sitemap and return all discovered page URLs. Pass
+      # `search` to have the crawled sitemap filtered down to the pages about a phrase
+      # (for example `pricing and plans` or `api authentication docs`), most relevant
+      # first — a searched crawl scans the whole sitemap and costs 2 credits instead
+      # of 1.
       #
-      # @overload web_scrape_sitemap(domain:, headers: nil, max_links: nil, sitemap_url: nil, tags: nil, timeout_ms: nil, url_regex: nil, zdr: nil, request_options: {})
+      # @overload web_scrape_sitemap(domain:, headers: nil, max_links: nil, search: nil, sitemap_url: nil, tags: nil, timeout_ms: nil, url_regex: nil, zdr: nil, request_options: {})
       #
       # @param domain [String] Domain to build a sitemap for
       #
@@ -555,6 +575,8 @@ module ContextDev
       #
       # @param max_links [Integer] Maximum number of links to return from the sitemap crawl. Defaults to 10,000. Mi
       #
+      # @param search [String] Optional search phrase. When provided, the crawled sitemap is filtered to the pa
+      #
       # @param sitemap_url [String] Optional explicit sitemap URL. When provided, exactly this sitemap is crawled in
       #
       # @param tags [Array<String>] Optional comma-separated caller-defined tags for tracking this request. Tags are

data/lib/context_dev/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ContextDev
-  VERSION = "2.8.0"
+  VERSION = "2.10.0"
 end

data/lib/context_dev.rb

@@ -58,6 +58,8 @@ require_relative "context_dev/models/ai_extract_products_params"
 require_relative "context_dev/models/ai_extract_products_response"
 require_relative "context_dev/models/batch_cancel_params"
 require_relative "context_dev/models/batch_cancel_response"
+require_relative "context_dev/models/batch_delete_params"
+require_relative "context_dev/models/batch_delete_response"
 require_relative "context_dev/models/batch_get_results_params"
 require_relative "context_dev/models/batch_get_results_response"
 require_relative "context_dev/models/batch_list_params"
@@ -105,9 +107,13 @@ require_relative "context_dev/models/monitor_run_params"
 require_relative "context_dev/models/monitor_run_response"
 require_relative "context_dev/models/monitor_update_params"
 require_relative "context_dev/models/monitor_update_response"
+require_relative "context_dev/models/news_search_params"
+require_relative "context_dev/models/news_search_response"
 require_relative "context_dev/models/page_error_count"
 require_relative "context_dev/models/parse_handle_params"
 require_relative "context_dev/models/parse_handle_response"
+require_relative "context_dev/models/person_enrich_params"
+require_relative "context_dev/models/person_enrich_response"
 require_relative "context_dev/models/utility_prefetch_params"
 require_relative "context_dev/models/utility_prefetch_response"
 require_relative "context_dev/models/web_extract_competitors_params"
@@ -139,6 +145,8 @@ require_relative "context_dev/resources/batch"
 require_relative "context_dev/resources/brand"
 require_relative "context_dev/resources/industry"
 require_relative "context_dev/resources/monitors"
+require_relative "context_dev/resources/news"
 require_relative "context_dev/resources/parse"
+require_relative "context_dev/resources/people"
 require_relative "context_dev/resources/utility"
 require_relative "context_dev/resources/web"

data/rbi/context_dev/client.rbi

@@ -38,9 +38,17 @@ module ContextDev
     sig { returns(ContextDev::Resources::Monitors) }
     attr_reader :monitors
 
+    # Scrape many pages or crawl a site asynchronously.
     sig { returns(ContextDev::Resources::Batch) }
     attr_reader :batch
 
+    sig { returns(ContextDev::Resources::People) }
+    attr_reader :people
+
+    # Search live first-party RSS and free historical news data by company identity.
+    sig { returns(ContextDev::Resources::News) }
+    attr_reader :news
+
     # @api private
     sig { override.returns(T::Hash[String, String]) }
     private def auth_headers

data/rbi/context_dev/models/batch_delete_params.rbi

@@ -0,0 +1,40 @@
+# typed: strong
+
+module ContextDev
+  module Models
+    class BatchDeleteParams < ContextDev::Internal::Type::BaseModel
+      extend ContextDev::Internal::Type::RequestParameters::Converter
+      include ContextDev::Internal::Type::RequestParameters
+
+      OrHash =
+        T.type_alias do
+          T.any(ContextDev::BatchDeleteParams, ContextDev::Internal::AnyHash)
+        end
+
+      # ID of the batch to retrieve or cancel.
+      sig { returns(String) }
+      attr_accessor :batch_id
+
+      sig do
+        params(
+          batch_id: String,
+          request_options: ContextDev::RequestOptions::OrHash
+        ).returns(T.attached_class)
+      end
+      def self.new(
+        # ID of the batch to retrieve or cancel.
+        batch_id:,
+        request_options: {}
+      )
+      end
+
+      sig do
+        override.returns(
+          { batch_id: String, request_options: ContextDev::RequestOptions }
+        )
+      end
+      def to_hash
+      end
+    end
+  end
+end