Lock data sources with an unreadable index in the selection

app/MindWork AI Studio/Tools/AllowedSelectedDataSources.cs

@@ -3,7 +3,7 @@ using AIStudio.Settings;
 namespace AIStudio.Tools;
 
 /// <summary>
-/// Contains the allowed and selected data sources, plus the ones waiting for their index.
+/// Contains the allowed and selected data sources, plus the ones which cannot be searched right now.
 /// </summary>
 /// <remarks>
 /// The selected data sources are a subset of the allowed data sources.
@@ -13,8 +13,13 @@ namespace AIStudio.Tools;
 /// -- takes it to mean "may be used to answer with", and a source whose index is being rebuilt
 /// cannot answer anything. It is listed separately so the user interface can still show it and say
 /// why it is greyed out, instead of letting it vanish without a word.
+///
+/// The same holds for the ones waiting for a repair, and they are a list of their own because the
+/// two reasons call for different words: one passes by itself, the other one waits for the user.
+/// A data source is in at most one of the two lists.
 /// </remarks>
 /// <param name="AllowedDataSources">The allowed data sources.</param>
 /// <param name="SelectedDataSources">The selected data sources, which are a subset of the allowed data sources.</param>
 /// <param name="DataSourcesAwaitingReindex">The data sources which passed every check but cannot be searched until their index has been rebuilt.</param>
-public readonly record struct AllowedSelectedDataSources(IReadOnlyList<IDataSource> AllowedDataSources, IReadOnlyList<IDataSource> SelectedDataSources, IReadOnlyList<IDataSource> DataSourcesAwaitingReindex);
+/// <param name="DataSourcesNeedingRepair">The data sources which passed every check but whose index cannot be read anymore, so that only the user can get them back.</param>
+public readonly record struct AllowedSelectedDataSources(IReadOnlyList<IDataSource> AllowedDataSources, IReadOnlyList<IDataSource> SelectedDataSources, IReadOnlyList<IDataSource> DataSourcesAwaitingReindex, IReadOnlyList<IDataSource> DataSourcesNeedingRepair);

app/MindWork AI Studio/Tools/Services/DataSourceEmbeddingService.cs

@@ -317,6 +317,22 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
         return runState is not DataSourceEmbeddingState.FAILED;
     }
 
+    /// <summary>
+    /// Whether a data source cannot be searched because its vector store cannot be read anymore.
+    /// </summary>
+    /// <remarks>
+    /// Unlike the re-index check above, this reads no database at all: the state comes from the run
+    /// or the search which ran into the unreadable store, and is kept in memory only. That it does
+    /// not survive a restart is deliberate. The very same store may well open on the next start,
+    /// and a mark written to disk would then be wrong with nobody noticing. Until something touches
+    /// the store again, the data source counts as usable, and a failing search says so on its own.
+    /// </remarks>
+    /// <param name="dataSource">The data source to ask about.</param>
+    /// <returns>True when the data source waits for the user to have its index rebuilt.</returns>
+    public bool NeedsIndexRepair(IDataSource dataSource) =>
+        this.statuses.TryGetValue(dataSource.Id, out var status) &&
+        status is { State: DataSourceEmbeddingState.FAILED, VectorStoreUnreadable: true };
+
     public Task QueueDataSourceAsync(IDataSource dataSource)
     {
         return this.QueueDataSourceAsync(dataSource, true, DataSourceEmbeddingRefreshMode.HASH_CHECK);

app/MindWork AI Studio/Tools/Services/DataSourceLocalRetrievalService.cs

@@ -188,7 +188,7 @@ public sealed class DataSourceLocalRetrievalService(
             // answer into one the user can do something about.
             //
             logger.LogWarning(exception, "Vector retrieval failed for data source '{DataSourceName}' ({DataSourceId}) because its vector store cannot be read.", dataSource.Name, dataSource.Id);
-            await this.ReportRetrievalGapAsync(dataSource, "vector-store-unreadable", string.Format(TB("The data source '{0}' was left out of the answer: its index cannot be read anymore. You can repair it on the background embeddings page."), dataSource.Name));
+            await this.ReportRetrievalGapAsync(dataSource, "vector-store-unreadable", string.Format(TB("The data source '{0}' was left out of the answer: its index cannot be read anymore. You can repair it in your data source settings."), dataSource.Name));
             return [];
         }
         catch (Exception exception)

app/MindWork AI Studio/Tools/Services/DataSourceService.cs

@@ -51,7 +51,7 @@ public sealed class DataSourceService
         if (selectedLLMProvider == Settings.Provider.NONE)
         {
             this.logger.LogWarning("The selected LLM provider is not set. We cannot filter the data sources by any means.");
-            return new([], [], []);
+            return new([], [], [], []);
         }
         
         var usingTrustedProvider = selectedLLMProvider.IsTrustedForDataSourceSecurityChecks(this.settingsManager);
@@ -83,12 +83,13 @@ public sealed class DataSourceService
         var allowedDataSources = await this.GetAllowedDataSources(usingTrustedProvider, participatingProviders, requestedDataSources);
 
         //
-        // Whoever asks this way has no list to show, so a data source waiting for its index is
+        // Whoever asks this way has no list to show, so a data source which cannot be searched is
         // dropped rather than marked. Handing it back would start a chat with a data source which
         // finds nothing -- the very thing being greyed out elsewhere is meant to prevent.
         //
-        var awaitingReindexIds = (await this.GetDataSourcesAwaitingReindex(allowedDataSources)).Select(source => source.Id).ToHashSet(StringComparer.Ordinal);
-        return allowedDataSources.Where(source => !awaitingReindexIds.Contains(source.Id)).ToList();
+        var unsearchableIds = (await this.GetDataSourcesAwaitingReindex(allowedDataSources)).Select(source => source.Id).ToHashSet(StringComparer.Ordinal);
+        unsearchableIds.UnionWith(this.GetDataSourcesNeedingRepair(allowedDataSources).Select(source => source.Id));
+        return allowedDataSources.Where(source => !unsearchableIds.Contains(source.Id)).ToList();
     }
     
     /// <summary>
@@ -109,7 +110,7 @@ public sealed class DataSourceService
         if (selectedLLMProvider is NoProvider)
         {
             this.logger.LogWarning("The selected LLM provider is the default provider. We cannot filter the data sources by any means.");
-            return new([], [], []);
+            return new([], [], [], []);
         }
         
         var usingTrustedProvider = selectedLLMProvider.IsTrustedForDataSourceSecurityChecks(this.settingsManager);
@@ -159,12 +160,21 @@ public sealed class DataSourceService
         // being rebuilt is usable again in a while, and saying so on its own row beats letting it
         // disappear from the selection without a word.
         //
-        var awaitingReindex = await this.GetDataSourcesAwaitingReindex(filteredDataSources);
-        var awaitingReindexIds = awaitingReindex.Select(source => source.Id).ToHashSet(StringComparer.Ordinal);
-        var usableDataSources = filteredDataSources.Where(source => !awaitingReindexIds.Contains(source.Id)).ToList();
+        // A source whose index cannot be read is asked about first and then kept out of the other
+        // list: both reasons can be true at once, and of the two it is the only one the user can do
+        // anything about. Telling them to wait instead would be telling them to wait forever.
+        //
+        var needingRepair = this.GetDataSourcesNeedingRepair(filteredDataSources);
+        var needingRepairIds = needingRepair.Select(source => source.Id).ToHashSet(StringComparer.Ordinal);
+        var awaitingReindex = (await this.GetDataSourcesAwaitingReindex(filteredDataSources)).Where(source => !needingRepairIds.Contains(source.Id)).ToList();
+
+        var blockedIds = awaitingReindex.Select(source => source.Id).ToHashSet(StringComparer.Ordinal);
+        blockedIds.UnionWith(needingRepairIds);
+
+        var usableDataSources = filteredDataSources.Where(source => !blockedIds.Contains(source.Id)).ToList();
         var filteredSelectedDataSources = usableDataSources.Where(source => previousSelectedDataSourceIds.Contains(source.Id)).ToList();
 
-        return new(usableDataSources, filteredSelectedDataSources, awaitingReindex);
+        return new(usableDataSources, filteredSelectedDataSources, awaitingReindex, needingRepair);
     }
 
     /// <summary>
@@ -195,6 +205,30 @@ public sealed class DataSourceService
         return awaitingReindex;
     }
 
+    /// <summary>
+    /// Picks out the data sources whose index cannot be read anymore, so that they wait for a repair.
+    /// </summary>
+    /// <remarks>
+    /// Reads nothing from a database, unlike the re-index check above: the state is held in memory
+    /// by the embedding service, which is why this one needs no parallelism and no timeout.
+    /// </remarks>
+    /// <param name="dataSources">The data sources which passed every other check.</param>
+    /// <returns>Those of them which wait for a repair, in the order they came in.</returns>
+    private IReadOnlyList<IDataSource> GetDataSourcesNeedingRepair(IReadOnlyList<IDataSource> dataSources)
+    {
+        var needingRepair = new List<IDataSource>();
+        foreach (var dataSource in dataSources)
+        {
+            if (!this.embeddingService.NeedsIndexRepair(dataSource))
+                continue;
+
+            this.logger.LogInformation("The index of data source '{DataSourceName}' ({DataSourceId}) cannot be read. It is shown, but cannot be selected until it was repaired.", dataSource.Name, dataSource.Id);
+            needingRepair.Add(dataSource);
+        }
+
+        return needingRepair;
+    }
+
     private async Task<IReadOnlyList<IDataSource>> GetAllowedDataSources(bool usingTrustedProvider, IReadOnlyList<ParticipatingProvider> participatingProviders, IReadOnlyCollection<IDataSource> requestedDataSources)
     {
         var filteredDataSources = new List<IDataSource>(requestedDataSources.Count);