Improved file loading so every caller reports failures instead of empty content

app/MindWork AI Studio/Assistants/DocumentAnalysis/DocumentAnalysisAssistant.razor.cs

@@ -716,7 +716,21 @@ public partial class DocumentAnalysisAssistant : AssistantBaseCore<NoSettingsPan
                 continue;
             }
 
-            var fileContent = (await this.RustService.ReadArbitraryFileData(document.FilePath, int.MaxValue)).Content;
+            var extraction = await this.RustService.ReadArbitraryFileData(document.FilePath, int.MaxValue);
+            if (!extraction.HasUsableContent)
+            {
+                this.Logger.LogError("Reading the document '{FilePath}' failed and it will not be analyzed: code={ErrorCode}, message='{ErrorMessage}'.", document.FilePath, extraction.ErrorCode, extraction.ErrorMessage);
+                await this.MessageBus.SendError(new(Icons.Material.Filled.Description, extraction.ToUserMessage(document.FileName)));
+                continue;
+            }
+
+            if (extraction.Outcome is FileExtractionOutcome.PARTIAL)
+            {
+                this.Logger.LogWarning("Parts of the document '{FilePath}' could not be read: pages={FailedPages}.", document.FilePath, string.Join(", ", extraction.FailedPages));
+                await this.MessageBus.SendWarning(new(Icons.Material.Filled.Description, extraction.ToPartialUserMessage(document.FileName)));
+            }
+
+            var fileContent = extraction.Content;
             sb.AppendLine($"""
                            
                            ## DOCUMENT {numDocuments}:

app/MindWork AI Studio/Assistants/PromptOptimizer/AssistantPromptOptimizer.razor.cs

@@ -579,9 +579,10 @@ public partial class AssistantPromptOptimizer : AssistantBaseCore<SettingsDialog
         try
         {
             this.isLoadingCustomPromptGuide = true;
-            this.customPromptingGuidelineContent = await UserFile.LoadFileData(fileAttachment.FilePath, this.RustService, this.DialogService);
+
-            if (string.IsNullOrWhiteSpace(this.customPromptingGuidelineContent))
+            // A failure was already reported by UserFile.LoadFileData, so we only keep the content:
-                await this.MessageBus.SendWarning(new(Icons.Material.Filled.Description, T("The custom prompt guide file is empty or could not be read.")));
+            var extraction = await UserFile.LoadFileData(fileAttachment.FilePath, this.RustService, this.DialogService);
+            this.customPromptingGuidelineContent = extraction.HasUsableContent ? extraction.Content : string.Empty;
         }
         catch
         {

app/MindWork AI Studio/Assistants/SlideBuilder/SlideAssistant.razor.cs

@@ -382,7 +382,21 @@ public partial class SlideAssistant : AssistantBaseCore<SettingsDialogSlideBuild
                 continue;
             }
 
-            var fileContent = (await this.RustService.ReadArbitraryFileData(document.FilePath, int.MaxValue)).Content;
+            var extraction = await this.RustService.ReadArbitraryFileData(document.FilePath, int.MaxValue);
+            if (!extraction.HasUsableContent)
+            {
+                this.Logger.LogError("Reading the document '{FilePath}' failed and it will not be used: code={ErrorCode}, message='{ErrorMessage}'.", document.FilePath, extraction.ErrorCode, extraction.ErrorMessage);
+                await this.MessageBus.SendError(new(Icons.Material.Filled.Description, extraction.ToUserMessage(document.FileName)));
+                continue;
+            }
+
+            if (extraction.Outcome is FileExtractionOutcome.PARTIAL)
+            {
+                this.Logger.LogWarning("Parts of the document '{FilePath}' could not be read: pages={FailedPages}.", document.FilePath, string.Join(", ", extraction.FailedPages));
+                await this.MessageBus.SendWarning(new(Icons.Material.Filled.Description, extraction.ToPartialUserMessage(document.FileName)));
+            }
+
+            var fileContent = extraction.Content;
             sb.AppendLine($"""
                            
                            ## DOCUMENT {numDocuments}:

app/MindWork AI Studio/Chat/ContentText.cs

@@ -317,7 +317,7 @@ public sealed class ContentText : IContent
                     if (!pandocIsUsable && FileTypes.RequiresPandoc(document.FilePath))
                     {
                         LOGGER.LogWarning("The file attachment '{FilePath}' needs Pandoc and will be skipped.", document.FilePath);
-                        await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Description, string.Format(TB("The file '{0}' needs Pandoc to be read and was not sent."), document.FileName)));
+                        await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Description, FileExtractionErrorCode.PANDOC_UNAVAILABLE.ToUserMessage(document.FileName)));
                         continue;
                     }
 

app/MindWork AI Studio/Components/ReadFileContent.razor.cs

@@ -324,8 +324,13 @@ public partial class ReadFileContent : MSGComponentBase
 
         try
         {
-            var fileContent = await UserFile.LoadFileData(filePath, this.RustService, this.DialogService);
+            var extraction = await UserFile.LoadFileData(filePath, this.RustService, this.DialogService);
-            await this.ApplyFileContentAsync(fileContent, filePath);
+
+            // The failure was already reported by UserFile.LoadFileData, so we only stop here:
+            if (!extraction.HasUsableContent)
+                return false;
+
+            await this.ApplyFileContentAsync(extraction.Content, filePath);
             this.Logger.LogInformation("Successfully loaded file content: {FilePath}", filePath);
             return true;
         }

app/MindWork AI Studio/Dialogs/DocumentCheckDialog.razor

@@ -33,6 +33,12 @@
                 @T("The specified file could not be found. The file have been moved, deleted, renamed, or is otherwise inaccessible.")
             </MudAlert>
         }
+        else if (this.loadFailureMessage is not null)
+        {
+            <MudAlert Severity="Severity.Error" Variant="Variant.Filled" Class="my-2">
+                @this.loadFailureMessage
+            </MudAlert>
+        }
         else
         {
             <MudTabs Elevation="0" Rounded="true" ApplyEffectsToContainer="true" Outlined="true" PanelClass="pa-2" Class="mb-2">

app/MindWork AI Studio/Dialogs/DocumentCheckDialog.razor.cs

@@ -20,6 +20,11 @@ public partial class DocumentCheckDialog : MSGComponentBase
     
     [Parameter]
     public string FileContent { get; set; } = string.Empty;
+
+    /// <summary>
+    /// Set when reading the file failed, so the dialog shows the reason instead of empty content.
+    /// </summary>
+    private string? loadFailureMessage;
     
     [Inject]
     private RustService RustService { get; init; } = null!;
@@ -38,14 +43,22 @@ public partial class DocumentCheckDialog : MSGComponentBase
             {
                 if (!this.Document.IsImage)
                 {
-                    var fileContent = await UserFile.LoadFileData(this.Document.FilePath, this.RustService, this.DialogService);
+                    var extraction = await UserFile.LoadFileData(this.Document.FilePath, this.RustService, this.DialogService);
-                    this.FileContent = fileContent;
+                    this.FileContent = extraction.Content;
+
+                    //
+                    // This dialog exists so the user can check what we hand to the AI. Showing an
+                    // empty document when reading the file failed would answer that question wrong.
+                    //
+                    if (!extraction.HasUsableContent)
+                        this.loadFailureMessage = extraction.ToUserMessage(this.Document.FileName);
                 }
             }
             catch (Exception ex)
             {
                 this.Logger.LogError(ex, "Failed to load file content from '{FilePath}'", this.Document);
                 this.FileContent = string.Empty;
+                this.loadFailureMessage = FileExtractionErrorCode.INTERNAL.ToUserMessage(this.Document.FileName);
             }
             
             this.StateHasChanged();

app/MindWork AI Studio/Tools/FileExtractionErrorCode.cs

@@ -37,6 +37,11 @@ public enum FileExtractionErrorCode
     // Codes reported by the app itself:
     //
 
+    /// <summary>
+    /// Reading the file needs Pandoc, which is not available.
+    /// </summary>
+    PANDOC_UNAVAILABLE,
+
     /// <summary>
     /// The runtime answered with an unsuccessful HTTP status.
     /// </summary>

app/MindWork AI Studio/Tools/FileExtractionResultExtensions.cs

@@ -20,7 +20,19 @@ internal static class FileExtractionResultExtensions
     /// <param name="result">The extraction result.</param>
     /// <param name="fileName">The name of the file, as shown to the user.</param>
     /// <returns>The localized message.</returns>
-    internal static string ToUserMessage(this FileExtractionResult result, string fileName) => string.Format(ToUserMessageFormat(result.ErrorCode), fileName);
+    internal static string ToUserMessage(this FileExtractionResult result, string fileName) => result.ErrorCode.ToUserMessage(fileName);
+
+    /// <summary>
+    /// Gets the localized message which explains why a file could not be read.
+    /// </summary>
+    /// <remarks>
+    /// This overload exists for the places which know the reason before an extraction was even
+    /// attempted, so both ways of skipping a file tell the user the same thing.
+    /// </remarks>
+    /// <param name="code">The stable failure code.</param>
+    /// <param name="fileName">The name of the file, as shown to the user.</param>
+    /// <returns>The localized message.</returns>
+    internal static string ToUserMessage(this FileExtractionErrorCode code, string fileName) => string.Format(ToUserMessageFormat(code), fileName);
 
     /// <summary>
     /// Gets the localized message for a file which was read, but lost some of its pages.
@@ -45,6 +57,8 @@ internal static class FileExtractionResultExtensions
         FileExtractionErrorCode.NOT_A_VALID_SPREADSHEET => TB("The file '{0}' is not a readable spreadsheet and was not sent. It might be damaged or transferred incompletely."),
         FileExtractionErrorCode.PDF_ENCRYPTED => TB("The file '{0}' is protected and could not be opened, so it was not sent."),
         FileExtractionErrorCode.PDFIUM_UNAVAILABLE => TB("AI Studio was not able to start its PDF engine, so the file '{0}' was not sent."),
+
+        FileExtractionErrorCode.PANDOC_UNAVAILABLE => TB("Reading the file '{0}' needs Pandoc, which is not available, so the file was not sent."),
         FileExtractionErrorCode.NO_TEXT_EXTRACTED => TB("No text could be read from the file '{0}', so it was not sent. The file might consist of scanned images without a text layer."),
         FileExtractionErrorCode.NO_CONTENT => TB("The file '{0}' did not provide any content and was not sent."),
         FileExtractionErrorCode.FORMAT_DETECTION_FAILED => TB("The file type of '{0}' could not be determined, so the file was not sent."),

app/MindWork AI Studio/Tools/UserFile.cs

@@ -1,5 +1,6 @@
 using AIStudio.Dialogs;
 using AIStudio.Tools.PluginSystem;
+using AIStudio.Tools.Rust;
 using AIStudio.Tools.Services;
 using DialogOptions = AIStudio.Dialogs.DialogOptions;
 
@@ -14,38 +15,64 @@ public static class UserFile
     /// <summary>
     /// Attempts to load the content of a file at the specified path, ensuring Pandoc is installed and available before proceeding.
     /// </summary>
+    /// <remarks>
+    /// This is the one place which reports a failed load to the user, so callers neither have to
+    /// repeat that nor may they treat a failure as an empty file.
+    /// </remarks>
     /// <param name="filePath">The full path to the file to be read. Must not be null or empty.</param>
     /// <param name="rustService">Rust service used to read file content.</param>
     /// <param name="dialogService">Dialogservice used to display the Pandoc installation dialog if needed.</param>
-    public static async Task<string> LoadFileData(string filePath, RustService rustService, IDialogService dialogService)
+    /// <returns>The result of reading the file.</returns>
+    public static async Task<FileExtractionResult> LoadFileData(string filePath, RustService rustService, IDialogService dialogService)
     {
         if (string.IsNullOrEmpty(filePath))
         {
             LOGGER.LogError("Can't load from an empty or null file path.");
             await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Cancel, TB("The file path is null or empty and the file therefore can not be loaded.")));
+            return FileExtractionResult.Failed(FileExtractionErrorCode.INVALID_REQUEST, "The file path is null or empty.");
         }
-        
+
-        // Ensure that Pandoc is installed and ready:
+        var fileName = Path.GetFileName(filePath);
-        var pandocState = await Pandoc.CheckAvailabilityAsync(rustService, showSuccessMessage: false);
+
-        if (!pandocState.IsAvailable)
+        //
+        // Ensure that Pandoc is installed and ready. This is only needed for the formats we
+        // convert with it: PDFs and the other document types are read by the Rust runtime itself.
+        //
+        if (FileTypes.RequiresPandoc(filePath))
         {
-            var dialogParameters = new DialogParameters<PandocDialog>
+            var pandocState = await Pandoc.CheckAvailabilityAsync(rustService, showSuccessMessage: false);
-            {
-                { x => x.ShowInitialResultInSnackbar, false },
-            };
-                
-            var dialogReference = await dialogService.ShowAsync<PandocDialog>(TB("Pandoc Installation"), dialogParameters, DialogOptions.FULLSCREEN);
-            await dialogReference.Result;
-                
-            pandocState = await Pandoc.CheckAvailabilityAsync(rustService, showSuccessMessage: true);
             if (!pandocState.IsAvailable)
             {
-                LOGGER.LogError("Pandoc is not available after installation attempt.");
+                var dialogParameters = new DialogParameters<PandocDialog>
-                await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Cancel, TB("Pandoc may be required for importing files.")));
+                {
+                    { x => x.ShowInitialResultInSnackbar, false },
+                };
+
+                var dialogReference = await dialogService.ShowAsync<PandocDialog>(TB("Pandoc Installation"), dialogParameters, DialogOptions.FULLSCREEN);
+                await dialogReference.Result;
+
+                pandocState = await Pandoc.CheckAvailabilityAsync(rustService, showSuccessMessage: true);
+                if (!pandocState.IsAvailable)
+                {
+                    LOGGER.LogError("Pandoc is not available after installation attempt, so '{FilePath}' cannot be read.", filePath);
+                    await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Cancel, FileExtractionErrorCode.PANDOC_UNAVAILABLE.ToUserMessage(fileName)));
+                    return FileExtractionResult.Failed(FileExtractionErrorCode.PANDOC_UNAVAILABLE, "Pandoc is required to read this file, but it is not available.");
+                }
             }
         }
-        
+
-        var fileContent = await rustService.ReadArbitraryFileData(filePath, int.MaxValue);
+        var result = await rustService.ReadArbitraryFileData(filePath, int.MaxValue);
-        return fileContent.Content;
+        if (!result.HasUsableContent)
+        {
+            LOGGER.LogError("Reading the file '{FilePath}' failed: code={ErrorCode}, message='{ErrorMessage}'.", filePath, result.ErrorCode, result.ErrorMessage);
+            await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Description, result.ToUserMessage(fileName)));
+        }
+        else if (result.Outcome is FileExtractionOutcome.PARTIAL)
+        {
+            LOGGER.LogWarning("Parts of the file '{FilePath}' could not be read: pages={FailedPages}.", filePath, string.Join(", ", result.FailedPages));
+            await MessageBus.INSTANCE.SendWarning(new(Icons.Material.Filled.Description, result.ToPartialUserMessage(fileName)));
+        }
+
+        return result;
     }
 }