Added structured extraction errors to the content stream handling

app/MindWork AI Studio/Tools/ContentStreamErrorDetails.cs

@@ -0,0 +1,38 @@
+using System.Text.Json.Serialization;
+
+namespace AIStudio.Tools;
+
+// ReSharper disable UnusedAutoPropertyAccessor.Global
+// ReSharper disable ClassNeverInstantiated.Global
+public sealed class ContentStreamErrorDetails
+{
+    [JsonPropertyName("code")]
+    public string? Code { get; init; }
+
+    [JsonPropertyName("message")]
+    public string? Message { get; init; }
+
+    /// <summary>
+    /// The page the failure belongs to, when the failure affects a single page only.
+    /// </summary>
+    [JsonPropertyName("page_number")]
+    public int? PageNumber { get; init; }
+
+    /// <summary>
+    /// Gets the parsed error code.
+    /// </summary>
+    /// <remarks>
+    /// Codes this version does not know map to <see cref="FileExtractionErrorCode.UNKNOWN"/>
+    /// instead of failing the deserialization. A failed deserialization would turn the reported
+    /// error back into empty file content, which is exactly what we want to avoid here.
+    /// </remarks>
+    [JsonIgnore]
+    public FileExtractionErrorCode ParsedCode => Enum.TryParse<FileExtractionErrorCode>(this.Code, ignoreCase: true, out var parsedCode) ? parsedCode : FileExtractionErrorCode.UNKNOWN;
+
+    /// <summary>
+    /// Gets a value indicating whether this failure affects one part of the file only, while the
+    /// remaining content is still usable.
+    /// </summary>
+    [JsonIgnore]
+    public bool IsPartialFailure => this.ParsedCode is FileExtractionErrorCode.PAGE_EXTRACTION_FAILED;
+}

app/MindWork AI Studio/Tools/ContentStreamErrorMetadata.cs

@@ -0,0 +1,11 @@
+using System.Text.Json.Serialization;
+
+namespace AIStudio.Tools;
+
+// ReSharper disable UnusedAutoPropertyAccessor.Global
+// ReSharper disable ClassNeverInstantiated.Global
+public sealed class ContentStreamErrorMetadata : ContentStreamSseMetadata
+{
+    [JsonPropertyName("Error")]
+    public ContentStreamErrorDetails? Error { get; init; }
+}

app/MindWork AI Studio/Tools/ContentStreamMetadataJsonConverter.cs

@@ -23,6 +23,7 @@ public sealed class ContentStreamMetadataJsonConverter : JsonConverter<ContentSt
             "Presentation" => JsonSerializer.Deserialize<ContentStreamPresentationMetadata?>(rawText, options),
             "Image" => JsonSerializer.Deserialize<ContentStreamImageMetadata?>(rawText, options),
             "Document" => JsonSerializer.Deserialize<ContentStreamDocumentMetadata?>(rawText, options),
+            "Error" => JsonSerializer.Deserialize<ContentStreamErrorMetadata?>(rawText, options),
 
             _ => null
         };

app/MindWork AI Studio/Tools/ContentStreamProcessedEvent.cs

@@ -0,0 +1,23 @@
+namespace AIStudio.Tools;
+
+/// <summary>
+/// The outcome of processing one content stream event: either content to append, or a reported
+/// failure.
+/// </summary>
+/// <remarks>
+/// Content and error are kept apart on purpose. A reported failure must never be appended as
+/// content, because that would hand the failure to the AI as if it were part of the document.
+/// </remarks>
+/// <param name="Content">The content to append, or null when this event carries none.</param>
+/// <param name="Error">The reported failure, or null when the event was processed successfully.</param>
+public readonly record struct ContentStreamProcessedEvent(string? Content, ContentStreamErrorDetails? Error)
+{
+    /// <summary>
+    /// An event which neither produced content nor reported a failure.
+    /// </summary>
+    public static readonly ContentStreamProcessedEvent NOTHING = new(null, null);
+
+    public static ContentStreamProcessedEvent FromContent(string? content) => new(content, null);
+
+    public static ContentStreamProcessedEvent FromError(ContentStreamErrorDetails? error) => new(null, error);
+}

app/MindWork AI Studio/Tools/ContentStreamSseHandler.cs

@@ -8,7 +8,7 @@ public static class ContentStreamSseHandler
     private static readonly ConcurrentDictionary<string, List<ContentStreamPptxImageData>> CHUNKED_IMAGES = new();
     private static readonly ConcurrentDictionary<string, SlideManager> SLIDE_MANAGERS = new();
 
-    public static string? ProcessEvent(ContentStreamSseEvent? sseEvent, bool extractImages = true)
+    public static ContentStreamProcessedEvent ProcessEvent(ContentStreamSseEvent? sseEvent, bool extractImages = true)
     {
         switch (sseEvent)
         {
@@ -16,15 +16,15 @@ public static class ContentStreamSseHandler
                 switch (sseEvent.Metadata)
                 {
                     case ContentStreamTextMetadata:
-                        return sseEvent.Content;
+                        return ContentStreamProcessedEvent.FromContent(sseEvent.Content);
 
                     case ContentStreamPdfMetadata pdfMetadata:
                         var pageNumber = pdfMetadata.Pdf?.PageNumber ?? 0;
-                        return $"""
+                        return ContentStreamProcessedEvent.FromContent($"""
                                 # Page {pageNumber}
                                 {sseEvent.Content}
 
-                                """;
+                                """);
 
                     case ContentStreamSpreadsheetMetadata spreadsheetMetadata:
                         var sheetName = spreadsheetMetadata.Spreadsheet?.SheetName;
@@ -37,11 +37,11 @@ public static class ContentStreamSseHandler
                         }
 
                         spreadSheetResult.Append(sseEvent.Content);
-                        return spreadSheetResult.ToString();
+                        return ContentStreamProcessedEvent.FromContent(spreadSheetResult.ToString());
 
                     case ContentStreamDocumentMetadata:
                     case ContentStreamImageMetadata:
-                        return sseEvent.Content;
+                        return ContentStreamProcessedEvent.FromContent(sseEvent.Content);
 
                     case ContentStreamPresentationMetadata presentationMetadata:
                         var slideManager = SLIDE_MANAGERS.GetOrAdd(
@@ -50,17 +50,25 @@ public static class ContentStreamSseHandler
                         );
 
                         slideManager.AddSlide(presentationMetadata, sseEvent.Content, extractImages);
-                        return null;
+                        return ContentStreamProcessedEvent.NOTHING;
+
+                    //
+                    // The runtime reported a failure. It must not contribute any content: an empty
+                    // or partial document would otherwise be handed to the AI as if it were the
+                    // real file content.
+                    //
+                    case ContentStreamErrorMetadata errorMetadata:
+                        return ContentStreamProcessedEvent.FromError(errorMetadata.Error);
 
                     default:
-                        return sseEvent.Content;
+                        return ContentStreamProcessedEvent.FromContent(sseEvent.Content);
                 }
 
             case { Content: not null, Metadata: null }:
-                return sseEvent.Content;
+                return ContentStreamProcessedEvent.FromContent(sseEvent.Content);
 
             default:
-                return null;
+                return ContentStreamProcessedEvent.NOTHING;
         }
     }
 

app/MindWork AI Studio/Tools/FileExtractionErrorCode.cs

@@ -0,0 +1,26 @@
+namespace AIStudio.Tools;
+
+/// <summary>
+/// Why reading a file failed. The Rust runtime reports these codes as part of the content
+/// stream, so the app can tell the user what happened instead of showing an empty document.
+/// </summary>
+public enum FileExtractionErrorCode
+{
+    /// <summary>
+    /// A code this version does not know, e.g. from a newer runtime.
+    /// </summary>
+    UNKNOWN,
+
+    INVALID_REQUEST,
+    FILE_NOT_FOUND,
+    FILE_NOT_READABLE,
+    FORMAT_DETECTION_FAILED,
+    NOT_A_VALID_PDF,
+    NOT_A_VALID_SPREADSHEET,
+    PDFIUM_UNAVAILABLE,
+    PDF_ENCRYPTED,
+    PAGE_EXTRACTION_FAILED,
+    NO_TEXT_EXTRACTED,
+    UNSUPPORTED,
+    INTERNAL,
+}

app/MindWork AI Studio/Tools/Services/RustService.Retrieval.cs

@@ -48,9 +48,19 @@ public sealed partial class RustService
                     var sseEvent = JsonSerializer.Deserialize<ContentStreamSseEvent>(jsonContent);
                     if (sseEvent is not null)
                     {
-                        var content = ContentStreamSseHandler.ProcessEvent(sseEvent, extractImages);
+                        var processedEvent = ContentStreamSseHandler.ProcessEvent(sseEvent, extractImages);
-                        if (content is not null)
+                        if (processedEvent.Error is not null)
-                            resultBuilder.AppendLine(content);
+                        {
+                            this.logger?.LogError(
+                                "The runtime reported a failure while reading '{Path}': code={ErrorCode}, page={PageNumber}, partial={IsPartialFailure}, message='{Message}'",
+                                path,
+                                processedEvent.Error.ParsedCode,
+                                processedEvent.Error.PageNumber,
+                                processedEvent.Error.IsPartialFailure,
+                                processedEvent.Error.Message);
+                        }
+                        else if (processedEvent.Content is not null)
+                            resultBuilder.AppendLine(processedEvent.Content);
 
                         chunkCount++;
                     }