Fixed PDFs and other formats requiring Pandoc although they do not use it

app/MindWork AI Studio/Chat/ContentText.cs

@@ -5,6 +5,7 @@ using AIStudio.Provider;
 using AIStudio.Settings;
 using AIStudio.Tools.PluginSystem;
 using AIStudio.Tools.RAG.RAGProcesses;
+using AIStudio.Tools.Rust;
 
 namespace AIStudio.Chat;
 
@@ -282,15 +283,23 @@ public sealed class ContentText : IContent
             // Only proceed if there are existing, allowed documents:
             if (existingDocuments.Count > 0)
             {
-                // Check Pandoc availability once before processing file attachments
+                //
+                // Pandoc is only needed for the few formats we convert with it. PDFs, text files,
+                // spreadsheets, and presentations are read by the runtime itself, so a missing
+                // Pandoc installation must not stop them.
+                //
+                var pandocIsUsable = true;
+                if (existingDocuments.Any(document => FileTypes.RequiresPandoc(document.FilePath)))
+                {
                     var pandocState = await Pandoc.CheckAvailabilityAsync(Program.RUST_SERVICE, showMessages: true, showSuccessMessage: false);
+                    pandocIsUsable = pandocState is { IsAvailable: true, CheckWasSuccessful: true };
 
                     if (!pandocState.IsAvailable)
-                    LOGGER.LogWarning("File attachments could not be processed because Pandoc is not available.");
+                        LOGGER.LogWarning("File attachments which need Pandoc could not be processed because Pandoc is not available.");
                     else if (!pandocState.CheckWasSuccessful)
-                    LOGGER.LogWarning("File attachments could not be processed because the Pandoc version check failed.");
+                        LOGGER.LogWarning("File attachments which need Pandoc could not be processed because the Pandoc version check failed.");
-                else
+                }
-                {
+
                 //
                 // The document blocks are collected separately, so we only announce attached
                 // files when at least one of them could actually be read. Announcing files we
@@ -305,6 +314,13 @@ public sealed class ContentText : IContent
                         continue;
                     }
 
+                    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)));
+                        continue;
+                    }
+
                     var extraction = await Program.RUST_SERVICE.ReadArbitraryFileData(document.FilePath, int.MaxValue);
                     if (!extraction.HasUsableContent)
                     {
@@ -348,7 +364,6 @@ public sealed class ContentText : IContent
                 }
             }
         }
-        }
         
         return sb.ToString();
     }

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

@@ -443,19 +443,27 @@ public partial class AttachDocuments : MSGComponentBase
         var mediaPaths = existingPaths.Where(IsTranscribableMedia).ToList();
         var regularPaths = existingPaths.Except(mediaPaths).ToList();
 
-        var canAddRegularFiles = true;
+        //
-        if (regularPaths.Count > 0)
+        // Only the formats we convert with Pandoc depend on a Pandoc installation. Everything
+        // else, PDFs in particular, is read by the Rust runtime itself, so those files must stay
+        // attachable without Pandoc.
+        //
+        var canAddPandocFiles = true;
+        if (regularPaths.Any(FileTypes.RequiresPandoc))
         {
             var pandocState = await this.PandocAvailabilityService.EnsureAvailabilityAsync(
                 showSuccessMessage: false,
                 showDialog: true);
-            canAddRegularFiles = pandocState.IsAvailable;
+            canAddPandocFiles = pandocState.IsAvailable;
         }
 
         foreach (var path in regularPaths)
         {
-            if (!canAddRegularFiles)
+            if (!canAddPandocFiles && FileTypes.RequiresPandoc(path))
-                break;
+            {
+                this.Logger.LogWarning("The file '{Path}' needs Pandoc and was not attached.", path);
+                continue;
+            }
 
             if (!await FileExtensionValidation.IsExtensionValidWithNotifyAsync(FileExtensionValidation.UseCase.ATTACHING_CONTENT, path, this.ValidateMediaFileTypes, this.Provider))
                 continue;

app/MindWork AI Studio/Tools/Rust/FileTypes.cs

@@ -84,6 +84,23 @@ public static class FileTypes
     public static readonly FileTypeFilter EXECUTABLES = FileTypeFilter.Leaf(TB("Executable"), "exe", "app", "bin", "appimage");
     public static readonly FileTypeFilter PLUGIN_ARCHIVE = FileTypeFilter.Leaf(TB("Plugin archive"), PluginArchive.PLUGIN_FILE_EXTENSION.TrimStart('.'), "zip");
     
+    /// <summary>
+    /// The file types AI Studio converts using Pandoc.
+    /// </summary>
+    /// <remarks>
+    /// This is not a user-selectable type, it mirrors the formats the Rust runtime hands to
+    /// Pandoc. Every other document type is read by the runtime itself, so it must never depend
+    /// on a Pandoc installation. The name is not localized because it is never shown.
+    /// </remarks>
+    private static readonly FileTypeFilter PANDOC_CONVERTED = FileTypeFilter.Leaf("Pandoc conversion", "docx", "odt", "html", "htm");
+
+    /// <summary>
+    /// Determines whether reading the given file needs Pandoc.
+    /// </summary>
+    /// <param name="filePath">The path of the file to check.</param>
+    /// <returns>True, when reading the file needs Pandoc.</returns>
+    public static bool RequiresPandoc(string filePath) => IsAllowedPath(filePath, PANDOC_CONVERTED);
+
     public static FileTypeFilter? AsOneFileType(params FileTypeFilter[]? types)
     {
         if (types == null || types.Length == 0)