RubyGems - context.dev - Versions diffs - 2.3.0 → 2.4.0 - Mend

context.dev 2.3.0 → 2.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (11) hide show

checksums.yaml +4 -4
data/CHANGELOG.md +8 -0
data/README.md +9 -9
data/lib/context_dev/models/parse_handle_params.rb +126 -42
data/lib/context_dev/resources/parse.rb +7 -11
data/lib/context_dev/version.rb +1 -1
data/rbi/context_dev/models/parse_handle_params.rbi +238 -62
data/rbi/context_dev/resources/parse.rbi +17 -24
data/sig/context_dev/models/parse_handle_params.rbs +179 -31
data/sig/context_dev/resources/parse.rbs +2 -5
metadata +1 -1

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: adde8335edf19dff9d76bc4d66ae8a7a6593a7fe76b77400f1dc7f1d0306b545
-  data.tar.gz: 06d1ea73b8472749a835d88c6bad7c433976e6f06b5e7e873b42a9309b25df02
+  metadata.gz: 6e76a9e12d2d02a5a2fabf5f621579b215d278c973e9b88eb9c032ea9c5fee8f
+  data.tar.gz: 5bd0dda46235f5c51359bb91ad1bc53df70f13cb2f49120b6b1b4c5a23958389
 SHA512:
-  metadata.gz: d827c5bb02c124f85f5c36d0eee5870d6612e2973b550272074b3c0a6be77f5254ec42383ce8273feb02eb7ecedf0391a6678919004dc392548d4ee7f99a195b
-  data.tar.gz: cc18411a99e00820eab476005adaacf0ac158cb8a0d0c4e88e9e566be24c8decb1e91e7610864a9568145b28c8a33e97396fa8d7e4f01bfbed76dccd4afccb99
+  metadata.gz: c2c06bbf5e65076e9867a7beb132b243ecea991290c8c2a8492a0de26936225c1fa7346f0486f9889aa41d1f3b96f5e544d69269d964523169611b2e8256e849
+  data.tar.gz: 4a4e5d37a6a84ce2854b1dba0eb854312964a144a914db69f418f796b29aeed0e54102ce9b0c3bd03877f26bec65ed5b4979e10675fa547707509d4c1d609334

data/CHANGELOG.md CHANGED Viewed

@@ -1,5 +1,13 @@
 # Changelog
+## 2.4.0 (2026-07-12)
+Full Changelog: [v2.3.0...v2.4.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v2.3.0...v2.4.0)
+### Features
+* **api:** api update ([426deb1](https://github.com/context-dot-dev/context-ruby-sdk/commit/426deb18249b214c3ccaa44c1e654e75ef666dd2))
 ## 2.3.0 (2026-07-12)
 Full Changelog: [v2.2.0...v2.3.0](https://github.com/context-dot-dev/context-ruby-sdk/compare/v2.2.0...v2.3.0)

data/README.md CHANGED Viewed

@@ -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", "~> 2.3.0"
+gem "context.dev", "~> 2.4.0"
 ```
 <!-- x-release-please-end -->
@@ -213,25 +213,25 @@ context_dev.brand.retrieve(**params)
 Since this library does not depend on `sorbet-runtime`, it cannot provide [`T::Enum`](https://sorbet.org/docs/tenum) instances. Instead, we provide "tagged symbols" instead, which is always a primitive at runtime:
 ```ruby
-# :light
-puts(ContextDev::WebExtractStyleguideParams::ColorScheme::LIGHT)
+# :txt
+puts(ContextDev::ParseHandleParams::Extension::TXT)
-# Revealed type: `T.all(ContextDev::WebExtractStyleguideParams::ColorScheme, Symbol)`
-T.reveal_type(ContextDev::WebExtractStyleguideParams::ColorScheme::LIGHT)
+# Revealed type: `T.all(ContextDev::ParseHandleParams::Extension, Symbol)`
+T.reveal_type(ContextDev::ParseHandleParams::Extension::TXT)
 ```
 Enum parameters have a "relaxed" type, so you can either pass in enum constants or their literal value:
 ```ruby
 # Using the enum constants preserves the tagged type information:
-context_dev.web.extract_styleguide(
-  color_scheme: ContextDev::WebExtractStyleguideParams::ColorScheme::LIGHT,
+context_dev.parse.handle(
+  extension: ContextDev::ParseHandleParams::Extension::TXT,
   # …
 )
 # Literal values are also permissible:
-context_dev.web.extract_styleguide(
-  color_scheme: :light,
+context_dev.parse.handle(
+  extension: :txt,
   # …
 )
 ```

data/lib/context_dev/models/parse_handle_params.rb CHANGED Viewed

@@ -12,25 +12,12 @@ module ContextDev
       #   @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.
+      #   Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
+      #   ".pdf").
       #
-      #   @return [String, nil]
-      optional :filename, String
+      #   @return [Symbol, ContextDev::Models::ParseHandleParams::Extension, nil]
+      optional :extension, enum: -> { ContextDev::ParseHandleParams::Extension }
       # @!attribute include_images
       #   Include image references in Markdown output
@@ -45,26 +32,23 @@ module ContextDev
       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.
+      #   Gates all OCR. When true, PDFs get embedded-image OCR (recognized text inserted
+      #   at each image's position in page reading order, preserving the text layer;
+      #   pdf.start/pdf.end limit the page range), scanned PDFs with no text layer get
+      #   full-document OCR, and raster images get their visible text transcribed. When
+      #   false, no OCR runs: scanned PDFs may yield no content and images return only
+      #   format/dimension metadata. Calls where OCR actually runs cost 5 credits instead
+      #   of 1.
       #
       #   @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.
+      # @!attribute pdf
+      #   PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
+      #   to an inclusive 1-based page range.
       #
-      #   @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
+      #   @return [ContextDev::Models::ParseHandleParams::Pdf, nil]
+      optional :pdf, -> { ContextDev::ParseHandleParams::Pdf }
       # @!attribute shorten_base64_images
       #   Shorten base64-encoded image data in the Markdown output
@@ -78,33 +62,133 @@ module ContextDev
       #   @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: {})
+      # @!method initialize(body:, extension: nil, include_images: nil, include_links: nil, ocr: nil, pdf: 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 extension [Symbol, ContextDev::Models::ParseHandleParams::Extension] Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
       #
       #   @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 ocr [Boolean] Gates all OCR. When true, PDFs get embedded-image OCR (recognized text inserted
       #
-      #   @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 pdf [ContextDev::Models::ParseHandleParams::Pdf] PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
       #
       #   @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}]
+      # Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
+      # ".pdf").
+      module Extension
+        extend ContextDev::Internal::Type::Enum
+        TXT = :txt
+        TEXT = :text
+        MD = :md
+        MARKDOWN = :markdown
+        HTML = :html
+        HTM = :htm
+        XHTML = :xhtml
+        XML = :xml
+        RSS = :rss
+        ATOM = :atom
+        CSV = :csv
+        TSV = :tsv
+        YAML = :yaml
+        YML = :yml
+        PY = :py
+        JAVA = :java
+        JS = :js
+        JSX = :jsx
+        MJS = :mjs
+        CJS = :cjs
+        JSON = :json
+        JSONL = :jsonl
+        NDJSON = :ndjson
+        PHP = :php
+        SH = :sh
+        BASH = :bash
+        ZSH = :zsh
+        FISH = :fish
+        RB = :rb
+        TS = :ts
+        TSX = :tsx
+        RTF = :rtf
+        SRT = :srt
+        CSS = :css
+        SCSS = :scss
+        LESS = :less
+        STYL = :styl
+        SASS = :sass
+        SVG = :svg
+        PDF = :pdf
+        DOCX = :docx
+        DOC = :doc
+        XLSX = :xlsx
+        XLSM = :xlsm
+        XLSB = :xlsb
+        XLTX = :xltx
+        XLTM = :xltm
+        XLS = :xls
+        PPTX = :pptx
+        PPTM = :pptm
+        PPSX = :ppsx
+        PPSM = :ppsm
+        POTX = :potx
+        POTM = :potm
+        PPT = :ppt
+        PPS = :pps
+        POT = :pot
+        JPG = :jpg
+        JPEG = :jpeg
+        JPE = :jpe
+        PNG = :png
+        GIF = :gif
+        BMP = :bmp
+        TIFF = :tiff
+        TIF = :tif
+        WEBP = :webp
+        PPM = :ppm
+        PBM = :pbm
+        PGM = :pgm
+        PNM = :pnm
+        # @!method self.values
+        #   @return [Array<Symbol>]
+      end
+      class Pdf < ContextDev::Internal::Type::BaseModel
+        # @!attribute end_
+        #   Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
+        #   Must be greater than or equal to start when both are provided.
+        #
+        #   @return [Integer, nil]
+        optional :end_, Integer, api_name: :end
+        # @!attribute start
+        #   First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+        #
+        #   @return [Integer, nil]
+        optional :start, Integer
+        # @!method initialize(end_: nil, start: nil)
+        #   Some parameter documentations has been truncated, see
+        #   {ContextDev::Models::ParseHandleParams::Pdf} for more details.
+        #
+        #   PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
+        #   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 start [Integer] First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+      end
     end
   end
 end

data/lib/context_dev/resources/parse.rb CHANGED Viewed

@@ -7,27 +7,23 @@ module ContextDev
       # {ContextDev::Models::ParseHandleParams} for more details.
       #
       # Converts raw text, source code, web/data, PDF, Microsoft Office, and image bytes
-      # into LLM-usable Markdown.
+      # into LLM-usable Markdown. The base request costs 1 credit. When OCR runs
+      # (requires ocr=true), the entire call costs 5 credits; ocr=true requests where no
+      # OCR ends up running still cost 1 credit.
       #
-      # @overload handle(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: {})
+      # @overload handle(body:, extension: nil, include_images: nil, include_links: nil, ocr: nil, pdf: nil, shorten_base64_images: nil, use_main_content_only: nil, request_options: {})
       #
       # @param body [Pathname, StringIO, IO, String, ContextDev::FilePart] Body param
       #
-      # @param base_url [String] Query param: Optional HTTP(S) source document URL used to resolve relative links
-      #
-      # @param extension [String] Query param: Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
-      #
-      # @param filename [String] Query param: Optional filename hint used to infer the extension when extension i
+      # @param extension [Symbol, ContextDev::Models::ParseHandleParams::Extension] Query param: Optional file extension hint. Case-insensitive; a leading dot is ac
       #
       # @param include_images [Boolean] Query param: Include image references in Markdown output
       #
       # @param include_links [Boolean] Query param: Preserve hyperlinks in Markdown output
       #
-      # @param ocr [Boolean] Query param: When true for PDF inputs, detect and OCR images embedded in the sel
-      #
-      # @param pdf_end [Integer] Query param: Last 1-based PDF page to parse. When omitted, parsing ends at the l
+      # @param ocr [Boolean] Query param: Gates all OCR. When true, PDFs get embedded-image OCR (recognized t
       #
-      # @param pdf_start [Integer] Query param: First 1-based PDF page to parse. When omitted, parsing starts at th
+      # @param pdf [ContextDev::Models::ParseHandleParams::Pdf] Query param: PDF page-range controls. Use start/end to limit parsing (and OCR wh
       #
       # @param shorten_base64_images [Boolean] Query param: Shorten base64-encoded image data in the Markdown output
       #

data/lib/context_dev/version.rb CHANGED Viewed

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 module ContextDev
-  VERSION = "2.3.0"
+  VERSION = "2.4.0"
 end

data/rbi/context_dev/models/parse_handle_params.rbi CHANGED Viewed

@@ -14,29 +14,20 @@ module ContextDev
       sig { returns(ContextDev::Internal::FileInput) }
       attr_accessor :body
-      # Optional HTTP(S) source document URL used to resolve relative links and image
-      # references. Relative references remain relative when omitted.
-      sig { returns(T.nilable(String)) }
-      attr_reader :base_url
-      sig { params(base_url: String).void }
-      attr_writer :base_url
-      # Optional file extension hint, such as pdf, docx, xlsx, pptx, html, json, csv,
-      # md, py, rtf, jpg, png, or txt.
-      sig { returns(T.nilable(String)) }
+      # Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
+      # ".pdf").
+      sig do
+        returns(T.nilable(ContextDev::ParseHandleParams::Extension::OrSymbol))
+      end
       attr_reader :extension
-      sig { params(extension: String).void }
+      sig do
+        params(
+          extension: ContextDev::ParseHandleParams::Extension::OrSymbol
+        ).void
+      end
       attr_writer :extension
-      # Optional filename hint used to infer the extension when extension is omitted.
-      sig { returns(T.nilable(String)) }
-      attr_reader :filename
-      sig { params(filename: String).void }
-      attr_writer :filename
       # Include image references in Markdown output
       sig { returns(T.nilable(T::Boolean)) }
       attr_reader :include_images
@@ -51,30 +42,26 @@ module ContextDev
       sig { params(include_links: T::Boolean).void }
       attr_writer :include_links
-      # 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.
+      # Gates all OCR. When true, PDFs get embedded-image OCR (recognized text inserted
+      # at each image's position in page reading order, preserving the text layer;
+      # pdf.start/pdf.end limit the page range), scanned PDFs with no text layer get
+      # full-document OCR, and raster images get their visible text transcribed. When
+      # false, no OCR runs: scanned PDFs may yield no content and images return only
+      # format/dimension metadata. Calls where OCR actually runs cost 5 credits instead
+      # of 1.
       sig { returns(T.nilable(T::Boolean)) }
       attr_reader :ocr
       sig { params(ocr: T::Boolean).void }
       attr_writer :ocr
-      # 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.
-      sig { returns(T.nilable(Integer)) }
-      attr_reader :pdf_end
+      # PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
+      # to an inclusive 1-based page range.
+      sig { returns(T.nilable(ContextDev::ParseHandleParams::Pdf)) }
+      attr_reader :pdf
-      sig { params(pdf_end: Integer).void }
-      attr_writer :pdf_end
-      # First 1-based PDF page to parse. When omitted, parsing starts at the first page.
-      sig { returns(T.nilable(Integer)) }
-      attr_reader :pdf_start
-      sig { params(pdf_start: Integer).void }
-      attr_writer :pdf_start
+      sig { params(pdf: ContextDev::ParseHandleParams::Pdf::OrHash).void }
+      attr_writer :pdf
       # Shorten base64-encoded image data in the Markdown output
       sig { returns(T.nilable(T::Boolean)) }
@@ -93,14 +80,11 @@ module ContextDev
       sig do
         params(
           body: ContextDev::Internal::FileInput,
-          base_url: String,
-          extension: String,
-          filename: String,
+          extension: ContextDev::ParseHandleParams::Extension::OrSymbol,
           include_images: T::Boolean,
           include_links: T::Boolean,
           ocr: T::Boolean,
-          pdf_end: Integer,
-          pdf_start: Integer,
+          pdf: ContextDev::ParseHandleParams::Pdf::OrHash,
           shorten_base64_images: T::Boolean,
           use_main_content_only: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
@@ -108,28 +92,24 @@ module ContextDev
       end
       def self.new(
         body:,
-        # Optional HTTP(S) source document URL used to resolve relative links and image
-        # references. Relative references remain relative when omitted.
-        base_url: nil,
-        # Optional file extension hint, such as pdf, docx, xlsx, pptx, html, json, csv,
-        # md, py, rtf, jpg, png, or txt.
+        # Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
+        # ".pdf").
         extension: nil,
-        # Optional filename hint used to infer the extension when extension is omitted.
-        filename: nil,
         # Include image references in Markdown output
         include_images: nil,
         # Preserve hyperlinks in Markdown output
         include_links: nil,
-        # 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.
+        # Gates all OCR. When true, PDFs get embedded-image OCR (recognized text inserted
+        # at each image's position in page reading order, preserving the text layer;
+        # pdf.start/pdf.end limit the page range), scanned PDFs with no text layer get
+        # full-document OCR, and raster images get their visible text transcribed. When
+        # false, no OCR runs: scanned PDFs may yield no content and images return only
+        # format/dimension metadata. Calls where OCR actually runs cost 5 credits instead
+        # of 1.
         ocr: nil,
-        # 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.
-        pdf_end: nil,
-        # First 1-based PDF page to parse. When omitted, parsing starts at the first page.
-        pdf_start: nil,
+        # PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
+        # to an inclusive 1-based page range.
+        pdf: nil,
         # Shorten base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Extract only the main content from HTML-like inputs
@@ -142,14 +122,11 @@ module ContextDev
         override.returns(
           {
             body: ContextDev::Internal::FileInput,
-            base_url: String,
-            extension: String,
-            filename: String,
+            extension: ContextDev::ParseHandleParams::Extension::OrSymbol,
             include_images: T::Boolean,
             include_links: T::Boolean,
             ocr: T::Boolean,
-            pdf_end: Integer,
-            pdf_start: Integer,
+            pdf: ContextDev::ParseHandleParams::Pdf,
             shorten_base64_images: T::Boolean,
             use_main_content_only: T::Boolean,
             request_options: ContextDev::RequestOptions
@@ -158,6 +135,205 @@ module ContextDev
       end
       def to_hash
       end
+      # Optional file extension hint. Case-insensitive; a leading dot is accepted (e.g.
+      # ".pdf").
+      module Extension
+        extend ContextDev::Internal::Type::Enum
+        TaggedSymbol =
+          T.type_alias do
+            T.all(Symbol, ContextDev::ParseHandleParams::Extension)
+          end
+        OrSymbol = T.type_alias { T.any(Symbol, String) }
+        TXT =
+          T.let(:txt, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TEXT =
+          T.let(:text, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        MD = T.let(:md, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        MARKDOWN =
+          T.let(
+            :markdown,
+            ContextDev::ParseHandleParams::Extension::TaggedSymbol
+          )
+        HTML =
+          T.let(:html, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        HTM =
+          T.let(:htm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XHTML =
+          T.let(:xhtml, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XML =
+          T.let(:xml, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        RSS =
+          T.let(:rss, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        ATOM =
+          T.let(:atom, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        CSV =
+          T.let(:csv, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TSV =
+          T.let(:tsv, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        YAML =
+          T.let(:yaml, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        YML =
+          T.let(:yml, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PY = T.let(:py, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JAVA =
+          T.let(:java, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JS = T.let(:js, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JSX =
+          T.let(:jsx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        MJS =
+          T.let(:mjs, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        CJS =
+          T.let(:cjs, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JSON =
+          T.let(:json, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JSONL =
+          T.let(:jsonl, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        NDJSON =
+          T.let(:ndjson, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PHP =
+          T.let(:php, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        SH = T.let(:sh, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        BASH =
+          T.let(:bash, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        ZSH =
+          T.let(:zsh, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        FISH =
+          T.let(:fish, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        RB = T.let(:rb, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TS = T.let(:ts, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TSX =
+          T.let(:tsx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        RTF =
+          T.let(:rtf, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        SRT =
+          T.let(:srt, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        CSS =
+          T.let(:css, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        SCSS =
+          T.let(:scss, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        LESS =
+          T.let(:less, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        STYL =
+          T.let(:styl, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        SASS =
+          T.let(:sass, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        SVG =
+          T.let(:svg, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PDF =
+          T.let(:pdf, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        DOCX =
+          T.let(:docx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        DOC =
+          T.let(:doc, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLSX =
+          T.let(:xlsx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLSM =
+          T.let(:xlsm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLSB =
+          T.let(:xlsb, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLTX =
+          T.let(:xltx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLTM =
+          T.let(:xltm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        XLS =
+          T.let(:xls, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPTX =
+          T.let(:pptx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPTM =
+          T.let(:pptm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPSX =
+          T.let(:ppsx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPSM =
+          T.let(:ppsm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        POTX =
+          T.let(:potx, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        POTM =
+          T.let(:potm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPT =
+          T.let(:ppt, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPS =
+          T.let(:pps, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        POT =
+          T.let(:pot, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JPG =
+          T.let(:jpg, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JPEG =
+          T.let(:jpeg, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        JPE =
+          T.let(:jpe, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PNG =
+          T.let(:png, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        GIF =
+          T.let(:gif, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        BMP =
+          T.let(:bmp, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TIFF =
+          T.let(:tiff, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        TIF =
+          T.let(:tif, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        WEBP =
+          T.let(:webp, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PPM =
+          T.let(:ppm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PBM =
+          T.let(:pbm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PGM =
+          T.let(:pgm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        PNM =
+          T.let(:pnm, ContextDev::ParseHandleParams::Extension::TaggedSymbol)
+        sig do
+          override.returns(
+            T::Array[ContextDev::ParseHandleParams::Extension::TaggedSymbol]
+          )
+        end
+        def self.values
+        end
+      end
+      class Pdf < ContextDev::Internal::Type::BaseModel
+        OrHash =
+          T.type_alias do
+            T.any(
+              ContextDev::ParseHandleParams::Pdf,
+              ContextDev::Internal::AnyHash
+            )
+          end
+        # Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
+        # Must be greater than or equal to start when both are provided.
+        sig { returns(T.nilable(Integer)) }
+        attr_reader :end_
+        sig { params(end_: Integer).void }
+        attr_writer :end_
+        # First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+        sig { returns(T.nilable(Integer)) }
+        attr_reader :start
+        sig { params(start: Integer).void }
+        attr_writer :start
+        # PDF page-range controls. Use start/end to limit parsing (and OCR when ocr=true)
+        # to an inclusive 1-based page range.
+        sig { params(end_: Integer, start: Integer).returns(T.attached_class) }
+        def self.new(
+          # Last 1-based PDF page to parse. When omitted, parsing ends at the last page.
+          # Must be greater than or equal to start when both are provided.
+          end_: nil,
+          # First 1-based PDF page to parse. When omitted, parsing starts at the first page.
+          start: nil
+        )
+        end
+        sig { override.returns({ end_: Integer, start: Integer }) }
+        def to_hash
+        end
+      end
     end
   end
 end

data/rbi/context_dev/resources/parse.rbi CHANGED Viewed

@@ -4,18 +4,17 @@ module ContextDev
   module Resources
     class Parse
       # Converts raw text, source code, web/data, PDF, Microsoft Office, and image bytes
-      # into LLM-usable Markdown.
+      # into LLM-usable Markdown. The base request costs 1 credit. When OCR runs
+      # (requires ocr=true), the entire call costs 5 credits; ocr=true requests where no
+      # OCR ends up running still cost 1 credit.
       sig do
         params(
           body: ContextDev::Internal::FileInput,
-          base_url: String,
-          extension: String,
-          filename: String,
+          extension: ContextDev::ParseHandleParams::Extension::OrSymbol,
           include_images: T::Boolean,
           include_links: T::Boolean,
           ocr: T::Boolean,
-          pdf_end: Integer,
-          pdf_start: Integer,
+          pdf: ContextDev::ParseHandleParams::Pdf::OrHash,
           shorten_base64_images: T::Boolean,
           use_main_content_only: T::Boolean,
           request_options: ContextDev::RequestOptions::OrHash
@@ -24,30 +23,24 @@ module ContextDev
       def handle(
         # Body param
         body:,
-        # Query param: Optional HTTP(S) source document URL used to resolve relative links
-        # and image references. Relative references remain relative when omitted.
-        base_url: nil,
-        # Query param: Optional file extension hint, such as pdf, docx, xlsx, pptx, html,
-        # json, csv, md, py, rtf, jpg, png, or txt.
+        # Query param: Optional file extension hint. Case-insensitive; a leading dot is
+        # accepted (e.g. ".pdf").
         extension: nil,
-        # Query param: Optional filename hint used to infer the extension when extension
-        # is omitted.
-        filename: nil,
         # Query param: Include image references in Markdown output
         include_images: nil,
         # Query param: Preserve hyperlinks in Markdown output
         include_links: nil,
-        # Query param: 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.
+        # Query param: Gates all OCR. When true, PDFs get embedded-image OCR (recognized
+        # text inserted at each image's position in page reading order, preserving the
+        # text layer; pdf.start/pdf.end limit the page range), scanned PDFs with no text
+        # layer get full-document OCR, and raster images get their visible text
+        # transcribed. When false, no OCR runs: scanned PDFs may yield no content and
+        # images return only format/dimension metadata. Calls where OCR actually runs cost
+        # 5 credits instead of 1.
         ocr: nil,
-        # Query param: 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.
-        pdf_end: nil,
-        # Query param: First 1-based PDF page to parse. When omitted, parsing starts at
-        # the first page.
-        pdf_start: nil,
+        # Query param: PDF page-range controls. Use start/end to limit parsing (and OCR
+        # when ocr=true) to an inclusive 1-based page range.
+        pdf: nil,
         # Query param: Shorten base64-encoded image data in the Markdown output
         shorten_base64_images: nil,
         # Query param: Extract only the main content from HTML-like inputs

data/sig/context_dev/models/parse_handle_params.rbs CHANGED Viewed

@@ -3,14 +3,11 @@ module ContextDev
     type parse_handle_params =
       {
         body: ContextDev::Internal::file_input,
-        base_url: String,
-        extension: String,
-        filename: String,
+        extension: ContextDev::Models::ParseHandleParams::extension,
         include_images: bool,
         include_links: bool,
         ocr: bool,
-        pdf_end: Integer,
-        pdf_start: Integer,
+        pdf: ContextDev::ParseHandleParams::Pdf,
         :shorten_base64_images => bool,
         use_main_content_only: bool
       }
@@ -22,17 +19,11 @@ module ContextDev
       attr_accessor body: ContextDev::Internal::file_input
-      attr_reader base_url: String?
+      attr_reader extension: ContextDev::Models::ParseHandleParams::extension?
-      def base_url=: (String) -> String
-      attr_reader extension: String?
-      def extension=: (String) -> String
-      attr_reader filename: String?
-      def filename=: (String) -> String
+      def extension=: (
+        ContextDev::Models::ParseHandleParams::extension
+      ) -> ContextDev::Models::ParseHandleParams::extension
       attr_reader include_images: bool?
@@ -46,13 +37,11 @@ module ContextDev
       def ocr=: (bool) -> bool
-      attr_reader pdf_end: Integer?
+      attr_reader pdf: ContextDev::ParseHandleParams::Pdf?
-      def pdf_end=: (Integer) -> Integer
-      attr_reader pdf_start: Integer?
-      def pdf_start=: (Integer) -> Integer
+      def pdf=: (
+        ContextDev::ParseHandleParams::Pdf
+      ) -> ContextDev::ParseHandleParams::Pdf
       attr_reader shorten_base64_images: bool?
@@ -64,14 +53,11 @@ module ContextDev
       def initialize: (
         body: ContextDev::Internal::file_input,
-        ?base_url: String,
-        ?extension: String,
-        ?filename: String,
+        ?extension: ContextDev::Models::ParseHandleParams::extension,
         ?include_images: bool,
         ?include_links: bool,
         ?ocr: bool,
-        ?pdf_end: Integer,
-        ?pdf_start: Integer,
+        ?pdf: ContextDev::ParseHandleParams::Pdf,
         ?shorten_base64_images: bool,
         ?use_main_content_only: bool,
         ?request_options: ContextDev::request_opts
@@ -79,18 +65,180 @@ module ContextDev
       def to_hash: -> {
         body: ContextDev::Internal::file_input,
-        base_url: String,
-        extension: String,
-        filename: String,
+        extension: ContextDev::Models::ParseHandleParams::extension,
         include_images: bool,
         include_links: bool,
         ocr: bool,
-        pdf_end: Integer,
-        pdf_start: Integer,
+        pdf: ContextDev::ParseHandleParams::Pdf,
         :shorten_base64_images => bool,
         use_main_content_only: bool,
         request_options: ContextDev::RequestOptions
       }
+      type extension =
+        :txt
+        | :text
+        | :md
+        | :markdown
+        | :html
+        | :htm
+        | :xhtml
+        | :xml
+        | :rss
+        | :atom
+        | :csv
+        | :tsv
+        | :yaml
+        | :yml
+        | :py
+        | :java
+        | :js
+        | :jsx
+        | :mjs
+        | :cjs
+        | :json
+        | :jsonl
+        | :ndjson
+        | :php
+        | :sh
+        | :bash
+        | :zsh
+        | :fish
+        | :rb
+        | :ts
+        | :tsx
+        | :rtf
+        | :srt
+        | :css
+        | :scss
+        | :less
+        | :styl
+        | :sass
+        | :svg
+        | :pdf
+        | :docx
+        | :doc
+        | :xlsx
+        | :xlsm
+        | :xlsb
+        | :xltx
+        | :xltm
+        | :xls
+        | :pptx
+        | :pptm
+        | :ppsx
+        | :ppsm
+        | :potx
+        | :potm
+        | :ppt
+        | :pps
+        | :pot
+        | :jpg
+        | :jpeg
+        | :jpe
+        | :png
+        | :gif
+        | :bmp
+        | :tiff
+        | :tif
+        | :webp
+        | :ppm
+        | :pbm
+        | :pgm
+        | :pnm
+      module Extension
+        extend ContextDev::Internal::Type::Enum
+        TXT: :txt
+        TEXT: :text
+        MD: :md
+        MARKDOWN: :markdown
+        HTML: :html
+        HTM: :htm
+        XHTML: :xhtml
+        XML: :xml
+        RSS: :rss
+        ATOM: :atom
+        CSV: :csv
+        TSV: :tsv
+        YAML: :yaml
+        YML: :yml
+        PY: :py
+        JAVA: :java
+        JS: :js
+        JSX: :jsx
+        MJS: :mjs
+        CJS: :cjs
+        JSON: :json
+        JSONL: :jsonl
+        NDJSON: :ndjson
+        PHP: :php
+        SH: :sh
+        BASH: :bash
+        ZSH: :zsh
+        FISH: :fish
+        RB: :rb
+        TS: :ts
+        TSX: :tsx
+        RTF: :rtf
+        SRT: :srt
+        CSS: :css
+        SCSS: :scss
+        LESS: :less
+        STYL: :styl
+        SASS: :sass
+        SVG: :svg
+        PDF: :pdf
+        DOCX: :docx
+        DOC: :doc
+        XLSX: :xlsx
+        XLSM: :xlsm
+        XLSB: :xlsb
+        XLTX: :xltx
+        XLTM: :xltm
+        XLS: :xls
+        PPTX: :pptx
+        PPTM: :pptm
+        PPSX: :ppsx
+        PPSM: :ppsm
+        POTX: :potx
+        POTM: :potm
+        PPT: :ppt
+        PPS: :pps
+        POT: :pot
+        JPG: :jpg
+        JPEG: :jpeg
+        JPE: :jpe
+        PNG: :png
+        GIF: :gif
+        BMP: :bmp
+        TIFF: :tiff
+        TIF: :tif
+        WEBP: :webp
+        PPM: :ppm
+        PBM: :pbm
+        PGM: :pgm
+        PNM: :pnm
+        def self?.values: -> ::Array[ContextDev::Models::ParseHandleParams::extension]
+      end
+      type pdf = { end_: Integer, start: Integer }
+      class Pdf < ContextDev::Internal::Type::BaseModel
+        attr_reader end_: Integer?
+        def end_=: (Integer) -> Integer
+        attr_reader start: Integer?
+        def start=: (Integer) -> Integer
+        def initialize: (?end_: Integer, ?start: Integer) -> void
+        def to_hash: -> { end_: Integer, start: Integer }
+      end
     end
   end
 end

data/sig/context_dev/resources/parse.rbs CHANGED Viewed

@@ -3,14 +3,11 @@ module ContextDev
     class Parse
       def handle: (
         body: ContextDev::Internal::file_input,
-        ?base_url: String,
-        ?extension: String,
-        ?filename: String,
+        ?extension: ContextDev::Models::ParseHandleParams::extension,
         ?include_images: bool,
         ?include_links: bool,
         ?ocr: bool,
-        ?pdf_end: Integer,
-        ?pdf_start: Integer,
+        ?pdf: ContextDev::ParseHandleParams::Pdf,
         ?shorten_base64_images: bool,
         ?use_main_content_only: bool,
         ?request_options: ContextDev::request_opts

metadata CHANGED Viewed

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: context.dev
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.4.0
 platform: ruby
 authors:
 - Context Dev