context.dev 2.1.0 → 2.3.0

data/lib/context_dev/models/monitor_update_response.rb

@@ -103,7 +103,15 @@ module ContextDev
       #   @return [ContextDev::Models::MonitorUpdateResponse::Webhook, nil]
       optional :webhook, -> { ContextDev::Models::MonitorUpdateResponse::Webhook }, nil?: true
 
-      # @!method initialize(id:, change_detection:, created_at:, mode:, name:, schedule:, status:, target:, updated_at:, baseline: nil, last_change_at: nil, last_error: nil, last_run_at: nil, next_run_at: nil, tags: nil, webhook: nil)
+      # @!attribute webhook_failure
+      #   Present while webhook deliveries are failing consecutively; null when deliveries
+      #   are healthy or no webhook is configured. Cleared on the next successful delivery
+      #   and when the webhook URL changes.
+      #
+      #   @return [ContextDev::Models::MonitorUpdateResponse::WebhookFailure, nil]
+      optional :webhook_failure, -> { ContextDev::Models::MonitorUpdateResponse::WebhookFailure }, nil?: true
+
+      # @!method initialize(id:, change_detection:, created_at:, mode:, name:, schedule:, status:, target:, updated_at:, baseline: nil, last_change_at: nil, last_error: nil, last_run_at: nil, next_run_at: nil, tags: nil, webhook: nil, webhook_failure: nil)
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::MonitorUpdateResponse} for more details.
       #
@@ -141,6 +149,8 @@ module ContextDev
       #   @param tags [Array<String>] User-defined tags for grouping and filtering monitors and their changes.
       #
       #   @param webhook [ContextDev::Models::MonitorUpdateResponse::Webhook, nil]
+      #
+      #   @param webhook_failure [ContextDev::Models::MonitorUpdateResponse::WebhookFailure, nil] Present while webhook deliveries are failing consecutively; null when deliveries
 
       # Discriminated union describing how changes are detected.
       #
@@ -153,7 +163,7 @@ module ContextDev
         # Detect exact changes. For page targets, this means visible text diffs. For sitemap targets, this means URL additions and removals.
         variant :exact, -> { ContextDev::Models::MonitorUpdateResponse::ChangeDetection::Exact }
 
-        # Detect meaning-level changes to the extracted data, ignoring cosmetic or paraphrase-only differences. What is watched is determined by the extract target's `schema` and `instructions`.
+        # Detect meaning-level changes to tracked page content, ignoring cosmetic or paraphrase-only differences. Which changes are meaningful is judged against the extract target's `instructions` (and `schema`, when provided).
         variant :semantic, -> { ContextDev::Models::MonitorUpdateResponse::ChangeDetection::Semantic }
 
         class Exact < ContextDev::Internal::Type::BaseModel
@@ -181,9 +191,9 @@ module ContextDev
           optional :confidence_threshold, Float
 
           # @!method initialize(confidence_threshold: nil, type: :semantic)
-          #   Detect meaning-level changes to the extracted data, ignoring cosmetic or
-          #   paraphrase-only differences. What is watched is determined by the extract
-          #   target's `schema` and `instructions`.
+          #   Detect meaning-level changes to tracked page content, ignoring cosmetic or
+          #   paraphrase-only differences. Which changes are meaningful is judged against the
+          #   extract target's `instructions` (and `schema`, when provided).
           #
           #   @param confidence_threshold [Float]
           #   @param type [Symbol, :semantic]
@@ -295,7 +305,7 @@ module ContextDev
         # Watch a sitemap for URL additions and removals. Crawled URLs are normalized (lowercased host, no trailing slash/fragment) and scoped to the monitored site and its subdomains before comparison. On a detected difference the sitemap is re-fetched within the same run and only URLs both observations agree on are reported, suppressing transient crawl flaps.
         variant :sitemap, -> { ContextDev::Models::MonitorUpdateResponse::Target::Sitemap }
 
-        # Watch the monitor-relevant pages of a site for meaningful changes. A crawl guided by `schema`/`instructions` selects up to `max_pages` relevant pages to track; each run re-checks exactly those pages, and confirmed content changes are judged against the monitor's instructions. The tracked page set is refreshed by a periodic re-discovery crawl.
+        # Watch the monitor-relevant pages of a site for meaningful changes. A crawl guided by `schema`/`instructions` selects up to `max_pages` relevant pages to track; each run re-checks exactly those pages, and confirmed content changes are judged for relevance against the monitor's `instructions` (and `schema`, when provided). The tracked page set is refreshed by a periodic re-discovery crawl.
         variant :extract, -> { ContextDev::Models::MonitorUpdateResponse::Target::Extract }
 
         class Page < ContextDev::Internal::Type::BaseModel
@@ -410,9 +420,14 @@ module ContextDev
           optional :max_pages, Integer
 
           # @!attribute schema
-          #   JSON Schema describing the data you care about. It guides which pages are
-          #   selected for tracking and gives the change judge context on what matters. If
-          #   omitted, a default summary + key-points schema is used.
+          #   JSON Schema describing the data you care about. It is used three ways: it guides
+          #   which pages are selected for tracking, it gives the change judge extra context
+          #   on which changes matter (alongside `instructions`), and it defines the shape of
+          #   the baseline `data` snapshot on GET /monitors/{monitor_id} (refreshed at most
+          #   about once a day). It is not a response format for changes: change events and
+          #   webhook payloads always contain diffs, summaries, and evidence excerpts — never
+          #   data in this schema's shape. If omitted, a default summary + key-points schema
+          #   is used.
           #
           #   @return [Hash{Symbol=>Object}, nil]
           optional :schema, ContextDev::Internal::Type::HashOf[ContextDev::Internal::Type::Unknown]
@@ -424,8 +439,8 @@ module ContextDev
           #   Watch the monitor-relevant pages of a site for meaningful changes. A crawl
           #   guided by `schema`/`instructions` selects up to `max_pages` relevant pages to
           #   track; each run re-checks exactly those pages, and confirmed content changes are
-          #   judged against the monitor's instructions. The tracked page set is refreshed by
-          #   a periodic re-discovery crawl.
+          #   judged for relevance against the monitor's `instructions` (and `schema`, when
+          #   provided). The tracked page set is refreshed by a periodic re-discovery crawl.
           #
           #   @param instructions [String] Natural-language instructions guiding which pages and facts to track and which c
           #
@@ -437,7 +452,7 @@ module ContextDev
           #
           #   @param max_pages [Integer] Maximum number of pages to track.
           #
-          #   @param schema [Hash{Symbol=>Object}] JSON Schema describing the data you care about. It guides which pages are select
+          #   @param schema [Hash{Symbol=>Object}] JSON Schema describing the data you care about. It is used three ways: it guides
           #
           #   @param type [Symbol, :extract]
         end
@@ -578,11 +593,21 @@ module ContextDev
       # @see ContextDev::Models::MonitorUpdateResponse#webhook
       class Webhook < ContextDev::Internal::Type::BaseModel
         # @!attribute url
-        #   Webhook URL called when a change is detected.
+        #   Webhook URL events are delivered to.
         #
         #   @return [String]
         required :url, String
 
+        # @!attribute events
+        #   Events delivered to this endpoint. `change.detected` fires only when a run
+        #   detects a change; `run.completed` fires on every completed run — including runs
+        #   that detected no change — and embeds the change when one was detected. Defaults
+        #   to `["change.detected"]` when omitted.
+        #
+        #   @return [Array<Symbol, ContextDev::Models::MonitorUpdateResponse::Webhook::Event>, nil]
+        optional :events,
+                 -> { ContextDev::Internal::Type::ArrayOf[enum: ContextDev::Models::MonitorUpdateResponse::Webhook::Event] }
+
         response_only do
           # @!attribute secret
           #   Signing secret used to verify webhook authenticity. Each delivery includes an
@@ -595,13 +620,85 @@ module ContextDev
           optional :secret, String
         end
 
-        # @!method initialize(url:, secret: nil)
+        # @!method initialize(url:, events: nil, secret: nil)
         #   Some parameter documentations has been truncated, see
         #   {ContextDev::Models::MonitorUpdateResponse::Webhook} for more details.
         #
-        #   @param url [String] Webhook URL called when a change is detected.
+        #   @param url [String] Webhook URL events are delivered to.
+        #
+        #   @param events [Array<Symbol, ContextDev::Models::MonitorUpdateResponse::Webhook::Event>] Events delivered to this endpoint. `change.detected` fires only when a run detec
         #
         #   @param secret [String] Signing secret used to verify webhook authenticity. Each delivery includes an `X
+
+        module Event
+          extend ContextDev::Internal::Type::Enum
+
+          CHANGE_DETECTED = :"change.detected"
+          RUN_COMPLETED = :"run.completed"
+
+          # @!method self.values
+          #   @return [Array<Symbol>]
+        end
+      end
+
+      # @see ContextDev::Models::MonitorUpdateResponse#webhook_failure
+      class WebhookFailure < ContextDev::Internal::Type::BaseModel
+        # @!attribute consecutive_failures
+        #   Number of consecutive delivery attempts that did not succeed.
+        #
+        #   @return [Integer]
+        required :consecutive_failures, Integer
+
+        # @!attribute last_failed_at
+        #
+        #   @return [Time]
+        required :last_failed_at, Time
+
+        # @!attribute last_message
+        #   Human-readable description of the most recent failure.
+        #
+        #   @return [String]
+        required :last_message, String
+
+        # @!attribute last_status
+        #   Outcome of the most recent failed delivery. rejected means a non-2xx response;
+        #   failed means no HTTP response was received; skipped_unsafe_url means the URL
+        #   failed the public-endpoint safety check.
+        #
+        #   @return [Symbol, ContextDev::Models::MonitorUpdateResponse::WebhookFailure::LastStatus]
+        required :last_status, enum: -> { ContextDev::Models::MonitorUpdateResponse::WebhookFailure::LastStatus }
+
+        # @!method initialize(consecutive_failures:, last_failed_at:, last_message:, last_status:)
+        #   Some parameter documentations has been truncated, see
+        #   {ContextDev::Models::MonitorUpdateResponse::WebhookFailure} for more details.
+        #
+        #   Present while webhook deliveries are failing consecutively; null when deliveries
+        #   are healthy or no webhook is configured. Cleared on the next successful delivery
+        #   and when the webhook URL changes.
+        #
+        #   @param consecutive_failures [Integer] Number of consecutive delivery attempts that did not succeed.
+        #
+        #   @param last_failed_at [Time]
+        #
+        #   @param last_message [String] Human-readable description of the most recent failure.
+        #
+        #   @param last_status [Symbol, ContextDev::Models::MonitorUpdateResponse::WebhookFailure::LastStatus] Outcome of the most recent failed delivery. rejected means a non-2xx response; f
+
+        # Outcome of the most recent failed delivery. rejected means a non-2xx response;
+        # failed means no HTTP response was received; skipped_unsafe_url means the URL
+        # failed the public-endpoint safety check.
+        #
+        # @see ContextDev::Models::MonitorUpdateResponse::WebhookFailure#last_status
+        module LastStatus
+          extend ContextDev::Internal::Type::Enum
+
+          REJECTED = :rejected
+          FAILED = :failed
+          SKIPPED_UNSAFE_URL = :skipped_unsafe_url
+
+          # @!method self.values
+          #   @return [Array<Symbol>]
+        end
       end
     end
   end

data/lib/context_dev/models/parse_handle_params.rb

@@ -0,0 +1,110 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Models
+    # @see ContextDev::Resources::Parse#handle
+    class ParseHandleParams < ContextDev::Internal::Type::BaseModel
+      extend ContextDev::Internal::Type::RequestParameters::Converter
+      include ContextDev::Internal::Type::RequestParameters
+
+      # @!attribute body
+      #
+      #   @return [Pathname, StringIO, IO, String, ContextDev::FilePart]
+      required :body, ContextDev::Internal::Type::FileInput
+
+      # @!attribute base_url
+      #   Optional HTTP(S) source document URL used to resolve relative links and image
+      #   references. Relative references remain relative when omitted.
+      #
+      #   @return [String, nil]
+      optional :base_url, String
+
+      # @!attribute extension
+      #   Optional file extension hint, such as pdf, docx, xlsx, pptx, html, json, csv,
+      #   md, py, rtf, jpg, png, or txt.
+      #
+      #   @return [String, nil]
+      optional :extension, String
+
+      # @!attribute filename
+      #   Optional filename hint used to infer the extension when extension is omitted.
+      #
+      #   @return [String, nil]
+      optional :filename, String
+
+      # @!attribute include_images
+      #   Include image references in Markdown output
+      #
+      #   @return [Boolean, nil]
+      optional :include_images, ContextDev::Internal::Type::Boolean
+
+      # @!attribute include_links
+      #   Preserve hyperlinks in Markdown output
+      #
+      #   @return [Boolean, nil]
+      optional :include_links, ContextDev::Internal::Type::Boolean
+
+      # @!attribute ocr
+      #   When true for PDF inputs, detect and OCR images embedded in the selected pages,
+      #   inserting recognized text at each image's position in page reading order while
+      #   preserving the PDF text layer. pdfStart/pdfEnd limit the inclusive page range.
+      #   This is separate from automatic scanned-PDF OCR fallback.
+      #
+      #   @return [Boolean, nil]
+      optional :ocr, ContextDev::Internal::Type::Boolean
+
+      # @!attribute pdf_end
+      #   Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
+      #   Must be greater than or equal to pdfStart when both are provided.
+      #
+      #   @return [Integer, nil]
+      optional :pdf_end, Integer
+
+      # @!attribute pdf_start
+      #   First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+      #
+      #   @return [Integer, nil]
+      optional :pdf_start, Integer
+
+      # @!attribute shorten_base64_images
+      #   Shorten base64-encoded image data in the Markdown output
+      #
+      #   @return [Boolean, nil]
+      optional :shorten_base64_images, ContextDev::Internal::Type::Boolean
+
+      # @!attribute use_main_content_only
+      #   Extract only the main content from HTML-like inputs
+      #
+      #   @return [Boolean, nil]
+      optional :use_main_content_only, ContextDev::Internal::Type::Boolean
+
+      # @!method initialize(body:, base_url: nil, extension: nil, filename: nil, include_images: nil, include_links: nil, ocr: nil, pdf_end: nil, pdf_start: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
+      #   Some parameter documentations has been truncated, see
+      #   {ContextDev::Models::ParseHandleParams} for more details.
+      #
+      #   @param body [Pathname, StringIO, IO, String, ContextDev::FilePart]
+      #
+      #   @param base_url [String] Optional HTTP(S) source document URL used to resolve relative links and image re
+      #
+      #   @param extension [String] Optional file extension hint, such as pdf, docx, xlsx, pptx, html, json, csv, md
+      #
+      #   @param filename [String] Optional filename hint used to infer the extension when extension is omitted.
+      #
+      #   @param include_images [Boolean] Include image references in Markdown output
+      #
+      #   @param include_links [Boolean] Preserve hyperlinks in Markdown output
+      #
+      #   @param ocr [Boolean] When true for PDF inputs, detect and OCR images embedded in the selected pages,
+      #
+      #   @param pdf_end [Integer] Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Mus
+      #
+      #   @param pdf_start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+      #
+      #   @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 from HTML-like inputs
+      #
+      #   @param request_options [ContextDev::RequestOptions, Hash{Symbol=>Object}]
+    end
+  end
+end

data/lib/context_dev/models/parse_handle_response.rb

@@ -0,0 +1,132 @@
+# frozen_string_literal: true
+
+module ContextDev
+  module Models
+    # @see ContextDev::Resources::Parse#handle
+    class ParseHandleResponse < ContextDev::Internal::Type::BaseModel
+      # @!attribute markdown
+      #   Input bytes converted to GitHub Flavored Markdown
+      #
+      #   @return [String]
+      required :markdown, String
+
+      # @!attribute success
+      #   Indicates success
+      #
+      #   @return [Boolean, ContextDev::Models::ParseHandleResponse::Success]
+      required :success, enum: -> { ContextDev::Models::ParseHandleResponse::Success }
+
+      # @!attribute type
+      #   Detected content type used for parsing
+      #
+      #   @return [Symbol, ContextDev::Models::ParseHandleResponse::Type]
+      required :type, enum: -> { ContextDev::Models::ParseHandleResponse::Type }
+
+      # @!attribute key_metadata
+      #   Metadata about the API key used for the request. Included in every response
+      #   whenever a valid API key is provided, even when the response status is not 200.
+      #
+      #   @return [ContextDev::Models::ParseHandleResponse::KeyMetadata, nil]
+      optional :key_metadata, -> { ContextDev::Models::ParseHandleResponse::KeyMetadata }
+
+      # @!method initialize(markdown:, success:, type:, key_metadata: nil)
+      #   Some parameter documentations has been truncated, see
+      #   {ContextDev::Models::ParseHandleResponse} for more details.
+      #
+      #   @param markdown [String] Input bytes converted to GitHub Flavored Markdown
+      #
+      #   @param success [Boolean, ContextDev::Models::ParseHandleResponse::Success] Indicates success
+      #
+      #   @param type [Symbol, ContextDev::Models::ParseHandleResponse::Type] Detected content type used for parsing
+      #
+      #   @param key_metadata [ContextDev::Models::ParseHandleResponse::KeyMetadata] Metadata about the API key used for the request. Included in every response when
+
+      # Indicates success
+      #
+      # @see ContextDev::Models::ParseHandleResponse#success
+      module Success
+        extend ContextDev::Internal::Type::Enum
+
+        TRUE = true
+
+        # @!method self.values
+        #   @return [Array<Boolean>]
+      end
+
+      # Detected content type used for parsing
+      #
+      # @see ContextDev::Models::ParseHandleResponse#type
+      module Type
+        extend ContextDev::Internal::Type::Enum
+
+        HTML = :html
+        XML = :xml
+        JSON = :json
+        JSONL = :jsonl
+        TEXT = :text
+        CSV = :csv
+        TSV = :tsv
+        MARKDOWN = :markdown
+        YAML = :yaml
+        PYTHON = :python
+        JAVA = :java
+        JAVASCRIPT = :javascript
+        PHP = :php
+        SHELL = :shell
+        RUBY = :ruby
+        TYPESCRIPT = :typescript
+        RTF = :rtf
+        SRT = :srt
+        CSS = :css
+        SCSS = :scss
+        LESS = :less
+        STYLUS = :stylus
+        SASS = :sass
+        SVG = :svg
+        PDF = :pdf
+        DOCX = :docx
+        DOC = :doc
+        XLSX = :xlsx
+        XLS = :xls
+        PPTX = :pptx
+        PPT = :ppt
+        JPG = :jpg
+        PNG = :png
+        GIF = :gif
+        BMP = :bmp
+        TIFF = :tiff
+        WEBP = :webp
+        PPM = :ppm
+        PBM = :pbm
+        PGM = :pgm
+        PNM = :pnm
+
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+
+      # @see ContextDev::Models::ParseHandleResponse#key_metadata
+      class KeyMetadata < ContextDev::Internal::Type::BaseModel
+        # @!attribute credits_consumed
+        #   The number of credits consumed by this request.
+        #
+        #   @return [Integer]
+        required :credits_consumed, Integer
+
+        # @!attribute credits_remaining
+        #   The number of credits remaining for your organization after this request.
+        #
+        #   @return [Integer]
+        required :credits_remaining, Integer
+
+        # @!method initialize(credits_consumed:, credits_remaining:)
+        #   Metadata about the API key used for the request. Included in every response
+        #   whenever a valid API key is provided, even when the response status is not 200.
+        #
+        #   @param credits_consumed [Integer] The number of credits consumed by this request.
+        #
+        #   @param credits_remaining [Integer] The number of credits remaining for your organization after this request.
+      end
+    end
+  end
+end

data/lib/context_dev/models/web_web_crawl_md_params.rb

@@ -86,8 +86,8 @@ module ContextDev
       optional :max_pages, Integer, api_name: :maxPages
 
       # @!attribute pdf
-      #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-      #   inclusive 1-based page range.
+      #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+      #   detection/OCR to an inclusive 1-based page range.
       #
       #   @return [ContextDev::Models::WebWebCrawlMdParams::Pdf, nil]
       optional :pdf, -> { ContextDev::WebWebCrawlMdParams::Pdf }
@@ -169,7 +169,7 @@ module ContextDev
       #
       #   @param max_pages [Integer] Maximum number of pages to crawl. Hard cap: 500.
       #
-      #   @param pdf [ContextDev::Models::WebWebCrawlMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and OCR to an inclu
+      #   @param pdf [ContextDev::Models::WebWebCrawlMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
       #   @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before extr
       #
@@ -410,6 +410,14 @@ module ContextDev
         #   @return [Integer, nil]
         optional :end_, Integer, api_name: :end
 
+        # @!attribute ocr
+        #   When true, detect and OCR images embedded in the selected PDF pages, inserting
+        #   recognized text at each image's position in page reading order while preserving
+        #   the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
+        #
+        #   @return [Boolean, nil]
+        optional :ocr, ContextDev::Internal::Type::Boolean
+
         # @!attribute should_parse
         #   When true, PDF pages are fetched and parsed. When false, PDF pages are skipped
         #   entirely (not included in results and not counted as failures).
@@ -423,15 +431,17 @@ module ContextDev
         #   @return [Integer, nil]
         optional :start, Integer
 
-        # @!method initialize(end_: nil, should_parse: nil, start: nil)
+        # @!method initialize(end_: nil, ocr: nil, should_parse: nil, start: nil)
         #   Some parameter documentations has been truncated, see
         #   {ContextDev::Models::WebWebCrawlMdParams::Pdf} for more details.
         #
-        #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-        #   inclusive 1-based page range.
+        #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+        #   detection/OCR to an inclusive 1-based page range.
         #
         #   @param end_ [Integer] Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Mus
         #
+        #   @param ocr [Boolean] When true, detect and OCR images embedded in the selected PDF pages, inserting r
+        #
         #   @param should_parse [Boolean] When true, PDF pages are fetched and parsed. When false, PDF pages are skipped e
         #
         #   @param start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.

data/lib/context_dev/models/web_web_scrape_html_params.rb

@@ -59,8 +59,8 @@ module ContextDev
       optional :max_age_ms, Integer
 
       # @!attribute pdf
-      #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-      #   inclusive 1-based page range.
+      #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+      #   detection/OCR to an inclusive 1-based page range.
       #
       #   @return [ContextDev::Models::WebWebScrapeHTMLParams::Pdf, nil]
       optional :pdf, -> { ContextDev::WebWebScrapeHTMLParams::Pdf }
@@ -113,7 +113,7 @@ module ContextDev
       #
       #   @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
-      #   @param pdf [ContextDev::Models::WebWebScrapeHTMLParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and OCR to an inclu
+      #   @param pdf [ContextDev::Models::WebWebScrapeHTMLParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
       #   @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before extr
       #
@@ -347,6 +347,14 @@ module ContextDev
         #   @return [Integer, nil]
         optional :end_, Integer, api_name: :end
 
+        # @!attribute ocr
+        #   When true, detect and OCR images embedded in the selected PDF pages, inserting
+        #   recognized text at each image's position in page reading order while preserving
+        #   the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
+        #
+        #   @return [Boolean, nil]
+        optional :ocr, ContextDev::Internal::Type::Boolean
+
         # @!attribute should_parse
         #   When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
         #   a 400 WEBSITE_ACCESS_ERROR is returned.
@@ -360,15 +368,17 @@ module ContextDev
         #   @return [Integer, nil]
         optional :start, Integer
 
-        # @!method initialize(end_: nil, should_parse: nil, start: nil)
+        # @!method initialize(end_: nil, ocr: nil, should_parse: nil, start: nil)
         #   Some parameter documentations has been truncated, see
         #   {ContextDev::Models::WebWebScrapeHTMLParams::Pdf} for more details.
         #
-        #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-        #   inclusive 1-based page range.
+        #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+        #   detection/OCR to an inclusive 1-based page range.
         #
         #   @param end_ [Integer] Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Mus
         #
+        #   @param ocr [Boolean] When true, detect and OCR images embedded in the selected PDF pages, inserting r
+        #
         #   @param should_parse [Boolean] When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
         #
         #   @param start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.

data/lib/context_dev/models/web_web_scrape_md_params.rb

@@ -72,8 +72,8 @@ module ContextDev
       optional :max_age_ms, Integer
 
       # @!attribute pdf
-      #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-      #   inclusive 1-based page range.
+      #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+      #   detection/OCR to an inclusive 1-based page range.
       #
       #   @return [ContextDev::Models::WebWebScrapeMdParams::Pdf, nil]
       optional :pdf, -> { ContextDev::WebWebScrapeMdParams::Pdf }
@@ -136,7 +136,7 @@ module ContextDev
       #
       #   @param max_age_ms [Integer] Return a cached result if a prior scrape for the same parameters exists and is y
       #
-      #   @param pdf [ContextDev::Models::WebWebScrapeMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and OCR to an inclu
+      #   @param pdf [ContextDev::Models::WebWebScrapeMdParams::Pdf] PDF parsing controls. Use start/end to limit text extraction and embedded-image
       #
       #   @param settle_animations [Boolean] When true, waits briefly for CSS and transition animations to settle before conv
       #
@@ -372,6 +372,14 @@ module ContextDev
         #   @return [Integer, nil]
         optional :end_, Integer, api_name: :end
 
+        # @!attribute ocr
+        #   When true, detect and OCR images embedded in the selected PDF pages, inserting
+        #   recognized text at each image's position in page reading order while preserving
+        #   the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
+        #
+        #   @return [Boolean, nil]
+        optional :ocr, ContextDev::Internal::Type::Boolean
+
         # @!attribute should_parse
         #   When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
         #   a 400 WEBSITE_ACCESS_ERROR is returned.
@@ -385,15 +393,17 @@ module ContextDev
         #   @return [Integer, nil]
         optional :start, Integer
 
-        # @!method initialize(end_: nil, should_parse: nil, start: nil)
+        # @!method initialize(end_: nil, ocr: nil, should_parse: nil, start: nil)
         #   Some parameter documentations has been truncated, see
         #   {ContextDev::Models::WebWebScrapeMdParams::Pdf} for more details.
         #
-        #   PDF parsing controls. Use start/end to limit text extraction and OCR to an
-        #   inclusive 1-based page range.
+        #   PDF parsing controls. Use start/end to limit text extraction and embedded-image
+        #   detection/OCR to an inclusive 1-based page range.
         #
         #   @param end_ [Integer] Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Mus
         #
+        #   @param ocr [Boolean] When true, detect and OCR images embedded in the selected PDF pages, inserting r
+        #
         #   @param should_parse [Boolean] When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and
         #
         #   @param start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.

data/lib/context_dev/models/web_web_scrape_md_response.rb

@@ -4,6 +4,14 @@ module ContextDev
   module Models
     # @see ContextDev::Resources::Web#web_scrape_md
     class WebWebScrapeMdResponse < ContextDev::Internal::Type::BaseModel
+      # @!attribute content_length
+      #   UTF-8 byte length of the returned Markdown. Use 0 to identify an empty result
+      #   and compare small values against your workload's minimum useful-content
+      #   threshold.
+      #
+      #   @return [Integer]
+      required :content_length, Integer, api_name: :contentLength
+
       # @!attribute markdown
       #   Page content converted to GitHub Flavored Markdown
       #
@@ -35,10 +43,12 @@ module ContextDev
       #   @return [ContextDev::Models::WebWebScrapeMdResponse::KeyMetadata, nil]
       optional :key_metadata, -> { ContextDev::Models::WebWebScrapeMdResponse::KeyMetadata }
 
-      # @!method initialize(markdown:, metadata:, success:, url:, key_metadata: nil)
+      # @!method initialize(content_length:, markdown:, metadata:, success:, url:, key_metadata: nil)
       #   Some parameter documentations has been truncated, see
       #   {ContextDev::Models::WebWebScrapeMdResponse} for more details.
       #
+      #   @param content_length [Integer] UTF-8 byte length of the returned Markdown. Use 0 to identify an empty result an
+      #
       #   @param markdown [String] Page content converted to GitHub Flavored Markdown
       #
       #   @param metadata [ContextDev::Models::WebWebScrapeMdResponse::Metadata] Metadata extracted from the scraped page HTML.