Increase bounded PDF source limit to 100 MiB

Author: KSemenenko

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes to ManagedCode.FileContext are documented here.
 
+## 1.0.10
+
+- Raise the bounded PDF source read limit from 25 MiB to 100 MiB for scanned documents while retaining per-page pixel and PNG output limits.
+
 ## 1.0.9
 
 - Add a native bounded DOCX text tool with paragraph and character cursors for long documents.

Directory.Build.props

@@ -12,7 +12,7 @@
     <AnalysisMode>Recommended</AnalysisMode>
     <TreatWarningsAsErrors>true</TreatWarningsAsErrors>
     <NoWarn>$(NoWarn);CS1591;MAAI001</NoWarn>
-    <Version>1.0.9</Version>
+    <Version>1.0.10</Version>
     <PackageVersion>$(Version)</PackageVersion>
   </PropertyGroup>
 

README.md

@@ -187,7 +187,7 @@ Results include `StartLine`, `EndLine`, `HasMore`, and `TotalLines` when the end
 
 `IFileContextPdf.ReadPdfTextAsync(path)` returns bounded text, `PageCount`, and one-based `PagesWithoutText`. It does not perform OCR. A scanned page can instead be rendered with `RenderPdfPageAsync(path, pageNumber)`, which returns PNG `DataContent`. Use `CountPdfPageImagesAsync` and `ExtractPdfImageAsync` when the original embedded pictures are needed rather than the complete page. The four read-only `file_context_pdf_*` tools expose the same operations from scoped storage.
 
-For an authenticated PDF already held as bytes, `FileContextPdfTextExtractor.Extract`, `FileContextPdfImages.RenderPagePng`, and `FileContextPdfImages.ExtractPageImagesPng` work without storing it. Storage reads enforce `MaximumPdfReadBytes` (25 MiB by default); page rasterization caps pixels and PNG size. A host must pass image `DataContent` to its model as image content. A generic OpenAI Chat function result serializes it as text, so hosts must explicitly bridge image tool results into a multimodal model message.
+For an authenticated PDF already held as bytes, `FileContextPdfTextExtractor.Extract`, `FileContextPdfImages.RenderPagePng`, and `FileContextPdfImages.ExtractPageImagesPng` work without storing it. PDF source reads are capped at 100 MiB by default; page rasterization caps pixels and PNG size. A host must pass image `DataContent` to its model as image content. A generic OpenAI Chat function result serializes it as text, so hosts must explicitly bridge image tool results into a multimodal model message.
 
 `file_context_docx_text(path, startParagraph?, startCharacter?, paragraphCount?)` reads ordinary paragraph and table text from a scoped DOCX package. The result contains numbered paragraph segments and `nextParagraph`/`nextCharacter`; use that cursor to continue a long document. Reads are limited to 50 paragraphs and 20,000 characters per call, with a configurable 25 MiB source limit (`MaximumDocxReadBytes`). It does not OCR embedded images. DOCX and XLSX packages are excluded from generic text reads and grep.
 

src/ManagedCode.FileContext/FileContextDefaults.cs

@@ -1,11 +1,13 @@
+using ManagedCode.FileContext.Pdf;
+
 namespace ManagedCode.FileContext;
 
 /// <summary>Default limits and selectors used by <see cref="FileContextOptions" />.</summary>
 public static class FileContextDefaults
 {
     public const long MaximumGeneratedFileBytes = 64L * 1024L * 1024L;
     public const int FirstLineNumber = 1;
-    public const int MaximumPdfReadBytes = 25 * 1024 * 1024;
+    public const int MaximumPdfReadBytes = FileContextPdfImages.MaximumPdfBytes;
     public const int MaximumPdfTextCharacters = 50_000;
     public const int MaximumDocxReadBytes = 25 * 1024 * 1024;
     public const int MaximumDocxTextCharacters = 20_000;

src/ManagedCode.FileContext/Pdf/FileContextPdfImages.cs

@@ -6,7 +6,7 @@ namespace ManagedCode.FileContext.Pdf;
 /// <summary>Renders complete PDF pages and extracts embedded page images as PNG.</summary>
 public static class FileContextPdfImages
 {
-    public const int MaximumPdfBytes = 25 * 1024 * 1024;
+    public const int MaximumPdfBytes = 100 * 1024 * 1024;
     public const int MaximumImageBytes = 8 * 1024 * 1024;
     public const int MaximumPixels = 4_000_000;
     public const int MaximumImagesPerPage = 20;

tests/ManagedCode.FileContext.Tests/FileContextPdfTests.cs

@@ -93,6 +93,17 @@ public void Page_image_enforces_page_scale_and_input_limits()
         Should.Throw<ArgumentOutOfRangeException>(() => FileContextPdfImages.ExtractPageImagesPng(pdf, 2));
     }
 
+    [Fact]
+    public void Pdf_over_the_former_25_mib_limit_reaches_parsing()
+    {
+        var source = new byte[25 * 1024 * 1024 + 1];
+
+        var exception = Record.Exception(() => FileContextPdfImages.RenderPagePng(source, 1));
+
+        exception.ShouldNotBeNull();
+        exception.Message.ShouldNotContain("The PDF exceeds the read limit.");
+    }
+
     [Fact]
     public async Task Pdf_service_enforces_byte_and_image_index_limits()
     {