Indexed large data sources in steps so the others get their turn (#1052)

app/MindWork AI Studio/Tools/Services/Indexing/IndexedRunContext.cs

@@ -24,10 +24,12 @@ namespace AIStudio.Tools.Services.Indexing;
 /// <param name="vectorStore">The vector store, known to be available.</param>
 /// <param name="indexStore">The index store, known to be available.</param>
 /// <param name="manifest">What the index stores about the data source, made to match the current embedding configuration.</param>
+/// <param name="share">How much work the run does at most, as its kind of data source says.</param>
+/// <param name="pass">The pass the run is a step of, which knows what failed during the steps before.</param>
 /// <param name="settingsManager">The settings, which the provider reads when it embeds.</param>
 /// <param name="publishStatus">Hands a new status of the data source to the embedding service.</param>
 /// <param name="logger">The logger of the embedding service, so the log reads the same whoever writes it.</param>
-internal sealed class IndexedRunContext(IIndexedDataSource dataSource, EmbeddingProvider embeddingProvider, IProvider provider, VectorStoreClient vectorStore, IndexStoreClient indexStore, DataSourceEmbeddingManifest manifest, SettingsManager settingsManager, Action<DataSourceEmbeddingStatus> publishStatus, ILogger logger)
+internal sealed class IndexedRunContext(IIndexedDataSource dataSource, EmbeddingProvider embeddingProvider, IProvider provider, VectorStoreClient vectorStore, IndexStoreClient indexStore, DataSourceEmbeddingManifest manifest, RunShare share, IndexingPass pass, SettingsManager settingsManager, Action<DataSourceEmbeddingStatus> publishStatus, ILogger logger)
 {
     /// <summary>
     /// After how many stored chunks the collection is optimized while a run is still going.
@@ -58,6 +60,26 @@ internal sealed class IndexedRunContext(IIndexedDataSource dataSource, Embedding
 
     public string CollectionName { get; } = DataSourceEmbeddingNames.GetCollectionName(dataSource.Id);
 
+    public RunShare Share => share;
+
+    public IndexingPass Pass => pass;
+
+    /// <summary>
+    /// When the run first asked whether it did its share of the work, or null while it never did.
+    /// </summary>
+    /// <remarks>
+    /// The clock of the share starts then, cf. DocumentRunProgress.HasDoneItsShare. The embedding
+    /// service reads it once the run is over, to notice a kind of data source which never asks.
+    /// </remarks>
+    public DateTimeOffset? ShareStartedUtc { get; private set; }
+
+    /// <summary>
+    /// Starts the clock of the share of the work, unless it runs already.
+    /// </summary>
+    /// <param name="nowUtc">The current time.</param>
+    /// <returns>When the clock started.</returns>
+    public DateTimeOffset StartShareClock(DateTimeOffset nowUtc) => this.ShareStartedUtc ??= nowUtc;
+
     /// <summary>
     /// Tells the user interface about a new status of the data source.
     /// </summary>