Show what happens to the data sources while they are re-indexed (#979)

app/MindWork AI Studio/Tools/Databases/IndexStore/DataSourceIndexState.cs

@@ -0,0 +1,19 @@
+namespace AIStudio.Tools.Databases.IndexStore;
+
+/// <summary>
+/// What the index knows about a data source as a whole, without its files.
+/// </summary>
+/// <remarks>
+/// The manifest answers the same question, but reads every file and every stored failure of the
+/// data source to do so. That is the right thing before a run, and far too much for a question
+/// asked about several data sources every time somebody opens the data source selection.
+///
+/// SourceHash is the telling one: it is written once a run has worked through the whole data
+/// source, and resetting the index deletes the row it lives in. So an empty hash means no run has
+/// finished since the index was last discarded.
+/// </remarks>
+/// <param name="EmbeddingProviderId">The embedding provider the stored vectors were created with.</param>
+/// <param name="EmbeddingSignature">Identifies the embedding configuration the stored vectors belong to.</param>
+/// <param name="SourceHash">The hash of the data source as a whole, written when a run completes.</param>
+/// <param name="VectorSize">The dimension of the stored vectors.</param>
+public sealed record DataSourceIndexState(string EmbeddingProviderId, string EmbeddingSignature, string SourceHash, int VectorSize);

app/MindWork AI Studio/Tools/Databases/IndexStore/IndexStoreClient.cs

@@ -6,6 +6,14 @@ public abstract class IndexStoreClient(string name, string path) : DatabaseClien
 {
     public abstract Task<DataSourceEmbeddingManifest> GetManifestAsync(string dataSourceId, CancellationToken token);
 
+    /// <summary>
+    /// Reads what the index knows about a data source as a whole, without its files.
+    /// </summary>
+    /// <param name="dataSourceId">The data source to read.</param>
+    /// <param name="token">The cancellation token.</param>
+    /// <returns>The stored state, or null when the index holds nothing about this data source.</returns>
+    public abstract Task<DataSourceIndexState?> GetDataSourceStateAsync(string dataSourceId, CancellationToken token);
+
     public abstract Task UpsertDataSourceAsync(
         string dataSourceId,
         string dataSourceType,

app/MindWork AI Studio/Tools/Databases/IndexStore/NoIndexStoreClient.cs

@@ -23,8 +23,9 @@ public sealed class NoIndexStoreClient(string name, string? unavailableReason, D
         await Task.CompletedTask;
     }
 
-    public override Task<DataSourceEmbeddingManifest> GetManifestAsync(string dataSourceId, CancellationToken token) =>
-        Task.FromResult(new DataSourceEmbeddingManifest());
+    public override Task<DataSourceEmbeddingManifest> GetManifestAsync(string dataSourceId, CancellationToken token) => Task.FromResult(new DataSourceEmbeddingManifest());
+
+    public override Task<DataSourceIndexState?> GetDataSourceStateAsync(string dataSourceId, CancellationToken token) => Task.FromResult<DataSourceIndexState?>(null);
 
     public override Task UpsertDataSourceAsync(
         string dataSourceId,

app/MindWork AI Studio/Tools/Databases/IndexStore/SqliteIndexStoreClientImplementation.cs

@@ -69,6 +69,16 @@ public sealed class SqliteIndexStoreClientImplementation(string name, string dat
         yield return (TB("Permanently skipped files"), (await context.PermanentIndexingFailures.CountAsync(CancellationToken.None)).ToString(CultureInfo.InvariantCulture));
     }
 
+    public override async Task<DataSourceIndexState?> GetDataSourceStateAsync(string dataSourceId, CancellationToken token)
+    {
+        await using var context = this.CreateContext();
+        return await context.DataSources
+            .AsNoTracking()
+            .Where(source => source.DataSourceId == dataSourceId)
+            .Select(source => new DataSourceIndexState(source.EmbeddingProviderId, source.EmbeddingSignature, source.SourceHash, source.VectorSize))
+            .FirstOrDefaultAsync(token);
+    }
+
     public override async Task<DataSourceEmbeddingManifest> GetManifestAsync(string dataSourceId, CancellationToken token)
     {
         await using var context = this.CreateContext();