Fixed local source links being refused by Word and LibreOffice

app/MindWork AI Studio/Chat/IContentExtensions.cs

@@ -55,8 +55,11 @@ public static class IContentExtensions
     /// </remarks>
     /// <param name="content">The content to read.</param>
     /// <param name="markdown">The Markdown text including its sources, or an empty string when there is none.</param>
+    /// <param name="keepPageAnchors">Whether a link into a local file may name its page. Only a
+    /// format whose reader stumbles over such a link says no here; the clipboard and every text
+    /// format keep the page.</param>
     /// <returns>True, when this content carries Markdown text.</returns>
-    public static bool TryGetExportMarkdown(this IContent content, out string markdown)
+    public static bool TryGetExportMarkdown(this IContent content, out string markdown, bool keepPageAnchors = true)
     {
         if (content is not ContentText text)
         {
@@ -65,7 +68,7 @@ public static class IContentExtensions
         }
 
         var answer = text.Text.Trim();
-        var sources = text.Sources.ToExportMarkdown();
+        var sources = text.Sources.ToExportMarkdown(keepPageAnchors);
         if (sources.Length == 0)
         {
             markdown = answer;

app/MindWork AI Studio/Tools/FileExportFormatExtensions.cs

@@ -204,6 +204,26 @@ public static class FileExportFormatExtensions
         _ => WITHOUT_BYTE_ORDER_MARK,
     };
 
+    /// <summary>
+    /// Determines whether a link into a local file may name the page it points at.
+    /// </summary>
+    /// <remarks>
+    /// A page is named by the fragment of the link, the way the PDF open parameters call for. A
+    /// browser and a PDF reader follow that and open the document on the page; Word and LibreOffice
+    /// take the fragment for part of the file name, look for a file which does not exist, and refuse
+    /// the link altogether. There the page is dropped, so the link at least opens the document --
+    /// which page it was stays in the title of the source. Verified on 2026-09-15 with LibreOffice
+    /// on an exported .odt. A format added later keeps the page unless it is known to stumble too.
+    /// </remarks>
+    /// <param name="format">The format.</param>
+    /// <returns>True, when a reader of this format follows such a link.</returns>
+    public static bool FollowsPageAnchors(this FileExportFormat format) => format switch
+    {
+        FileExportFormat.MICROSOFT_WORD or FileExportFormat.OPEN_DOCUMENT_TEXT => false,
+
+        _ => true,
+    };
+
     /// <summary>
     /// Returns the name Pandoc knows the format by.
     /// </summary>

app/MindWork AI Studio/Tools/PandocExport.cs

@@ -118,7 +118,7 @@ public static class PandocExport
         // We read the text before we ask for a path: when there is nothing to convert, the user
         // should learn that right away instead of picking a file first and getting an error afterwards.
         //
-        if (!markdownContent.TryGetExportMarkdown(out var markdownText))
+        if (!markdownContent.TryGetExportMarkdown(out var markdownText, format.FollowsPageAnchors()))
         {
             LOGGER.LogWarning("Cannot export the content as {ExportFormat}, because it carries no text.", format);
             await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Cancel, TB("Only text messages can be exported.")));

app/MindWork AI Studio/Tools/SourceExtensions.cs

@@ -138,8 +138,9 @@ public static partial class SourceExtensions
     /// Converts a list of sources to a markdown-formatted string.
     /// </summary>
     /// <param name="sources">The list of sources to convert.</param>
+    /// <param name="keepPageAnchors">Whether a link into a local file may name its page; see the method below.</param>
     /// <returns>A markdown-formatted string representing the sources.</returns>
-    public static string ToMarkdown(this IList<Source> sources)
+    public static string ToMarkdown(this IList<Source> sources, bool keepPageAnchors = true)
     {
         var sb = new StringBuilder();
         foreach (var group in sources.GroupSources())
@@ -152,8 +153,9 @@ public static partial class SourceExtensions
 
             foreach (var numberedSource in group.Sources)
             {
+                var url = keepPageAnchors ? numberedSource.Source.URL : WithoutPageAnchor(numberedSource.Source.URL);
                 sb.Append($"- [{numberedSource.Number}] ");
-                AppendMarkdownLink(sb, numberedSource.Source.Title, numberedSource.Source.URL);
+                AppendMarkdownLink(sb, numberedSource.Source.Title, url);
                 sb.AppendLine();
             }
         }
@@ -161,6 +163,29 @@ public static partial class SourceExtensions
         return sb.ToString();
     }
 
+    /// <summary>
+    /// Takes the page off a link into a local file, for a reader which cannot follow it.
+    /// </summary>
+    /// <remarks>
+    /// Everything a local link carries in its fragment is dropped, not only a page: a chunk is no
+    /// use to any reader either, and what breaks such a link is the fragment itself rather than what
+    /// stands in it. A web address keeps its fragment untouched, because there the fragment is part
+    /// of the address and naming a section of a page is exactly what it is for.
+    /// </remarks>
+    /// <param name="url">The link of the source.</param>
+    /// <returns>The link without its fragment, or the link itself when it carries none.</returns>
+    private static string WithoutPageAnchor(string url)
+    {
+        if (string.IsNullOrWhiteSpace(url))
+            return url;
+
+        var cleanedUrl = url.Trim().Replace("\r", string.Empty).Replace("\n", string.Empty);
+        if (!Uri.TryCreate(cleanedUrl, UriKind.Absolute, out var absoluteUri) || !absoluteUri.IsFile || absoluteUri.Fragment.Length == 0)
+            return url;
+
+        return absoluteUri.GetComponents(UriComponents.AbsoluteUri & ~UriComponents.Fragment, UriFormat.UriEscaped);
+    }
+
     /// <summary>
     /// Converts a list of sources to a markdown-formatted string, headed by a title of its own.
     /// </summary>
@@ -171,10 +196,11 @@ public static partial class SourceExtensions
     /// for this and the chat does not.
     /// </remarks>
     /// <param name="sources">The list of sources to convert.</param>
+    /// <param name="keepPageAnchors">Whether a link into a local file may name its page.</param>
     /// <returns>A markdown-formatted string representing the sources, or an empty string when there are none.</returns>
-    public static string ToExportMarkdown(this IList<Source> sources)
+    public static string ToExportMarkdown(this IList<Source> sources, bool keepPageAnchors = true)
     {
-        var sourcesMarkdown = sources.ToMarkdown();
+        var sourcesMarkdown = sources.ToMarkdown(keepPageAnchors);
         if (string.IsNullOrWhiteSpace(sourcesMarkdown))
             return string.Empty;
 

app/Tests/Tools/FileExportFormatTests.cs

@@ -0,0 +1,39 @@
+using AIStudio.Tools;
+
+namespace AIStudio.Tests.Tools;
+
+/// <summary>
+/// Checks what AI Studio assumes about the readers of the formats it writes.
+/// </summary>
+[TestFixture]
+public sealed class FileExportFormatTests
+{
+    [Test]
+    public void OnlyTheTwoOfficeFormatsRefuseAPageInALocalLink()
+    {
+        Assert.Multiple(() =>
+        {
+            Assert.That(FileExportFormat.MICROSOFT_WORD.FollowsPageAnchors(), Is.False, "Word looks for a file whose name ends in the fragment, finds none, and refuses the link.");
+            Assert.That(FileExportFormat.OPEN_DOCUMENT_TEXT.FollowsPageAnchors(), Is.False, "LibreOffice does the same, verified on 2026-09-15 with an exported .odt.");
+            Assert.That(FileExportFormat.HTML.FollowsPageAnchors(), Is.True, "A browser opens the document on the page the fragment names.");
+            Assert.That(FileExportFormat.MARKDOWN.FollowsPageAnchors(), Is.True);
+            Assert.That(FileExportFormat.LATEX.FollowsPageAnchors(), Is.True);
+        });
+    }
+
+    [Test]
+    public void EveryFormatAnAnswerIsWrittenAsHasAnAnswerHere()
+    {
+        // Whoever adds a format decides what its reader can follow, rather than inheriting an
+        // assumption. This fails for a format which nobody thought about, because the list below
+        // has to name it:
+        Assert.That(FileExportFormatExtensions.ANSWER_FORMATS, Is.EquivalentTo(new[]
+        {
+            FileExportFormat.MICROSOFT_WORD,
+            FileExportFormat.OPEN_DOCUMENT_TEXT,
+            FileExportFormat.LATEX,
+            FileExportFormat.MARKDOWN,
+            FileExportFormat.HTML,
+        }), "A format was added to or removed from the export menu: say in FollowsPageAnchors whether its reader follows a page in a local link, then name it here.");
+    }
+}

app/Tests/Tools/SourceExtensionsTests.cs

@@ -137,6 +137,36 @@ public sealed class SourceExtensionsTests
             Assert.That(entries[index], Does.StartWith($"- [{listed[index].Number}] ").And.Contains(listed[index].Source.Title), "The Markdown and the chat read the same grouping, so a source cannot be numbered one way here and another way there.");
     }
 
+    [Test]
+    public void AReaderWhichCannotFollowAPageGetsTheDocumentWithoutOne()
+    {
+        IList<Source> sources =
+        [
+            new("Handbook (Page 266)", "file:///Users/someone/My Documents/handbook.pdf#page=266", SourceOrigin.RAG),
+            new("An older answer", "file:///Users/someone/handbook.pdf#chunk=3", SourceOrigin.RAG),
+            new("A section of an article", "https://example.org/article#results", SourceOrigin.LLM),
+        ];
+
+        Assert.That(EntriesOf(sources.ToMarkdown(keepPageAnchors: false)), Is.EqualTo(new[]
+        {
+            "- [1] [A section of an article](<https://example.org/article#results>)",
+            "- [2] [Handbook (Page 266)](<file:///Users/someone/My%20Documents/handbook.pdf>)",
+            "- [3] [An older answer](<file:///Users/someone/handbook.pdf>)",
+        }), "Word and LibreOffice take the fragment of a local link for part of the file name and refuse the link, so the local links lose it -- and the web link keeps its own, where a fragment names a section of the page and belongs to the address.");
+    }
+
+    [Test]
+    public void AReaderWhichFollowsAPageIsToldIt()
+    {
+        IList<Source> sources = [new("Handbook (Page 266)", "file:///Users/someone/handbook.pdf#page=266", SourceOrigin.RAG)];
+
+        Assert.Multiple(() =>
+        {
+            Assert.That(EntriesOf(sources.ToMarkdown()).Single(), Does.EndWith("handbook.pdf#page=266>)"), "A browser and a PDF reader open the document where the passage is, so they are told the page.");
+            Assert.That(EntriesOf(sources.ToExportMarkdown()).Single(), Does.EndWith("handbook.pdf#page=266>)"), "The clipboard and every text format keep it as well; only the two office formats ask for it to be dropped.");
+        });
+    }
+
     [Test]
     public void AKnownPageRidesInTheLinkOfASource()
     {