Added the Batch Processing Assistant (#901)

Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>

app/MindWork AI Studio/Tools/AssistantVisibilityExtensions.cs

@@ -60,6 +60,7 @@ public static class AssistantVisibilityExtensions
             Components.BIAS_DAY_ASSISTANT => ConfigurableAssistant.BIAS_DAY_ASSISTANT,
             Components.ERI_ASSISTANT => ConfigurableAssistant.ERI_ASSISTANT,
             Components.DOCUMENT_ANALYSIS_ASSISTANT => ConfigurableAssistant.DOCUMENT_ANALYSIS_ASSISTANT,
+            Components.BATCH_PROCESSING_ASSISTANT => ConfigurableAssistant.BATCH_PROCESSING_ASSISTANT,
             Components.SLIDE_BUILDER_ASSISTANT => ConfigurableAssistant.SLIDE_BUILDER_ASSISTANT,
             Components.VISUAL_BRIEFING_ASSISTANT => ConfigurableAssistant.VISUAL_BRIEFING_ASSISTANT,
             Components.I18N_ASSISTANT => ConfigurableAssistant.I18N_ASSISTANT,

app/MindWork AI Studio/Tools/Components.cs

@@ -37,4 +37,5 @@ public enum Components
     AGENT_ASSISTANT_PLUGIN_AUDIT,
     LOG_VIEWER_ASSISTANT,
     VISUAL_BRIEFING_ASSISTANT,
+    BATCH_PROCESSING_ASSISTANT,
 }

app/MindWork AI Studio/Tools/ComponentsExtensions.cs

@@ -65,6 +65,7 @@ public static class ComponentsExtensions
         Components.BIAS_DAY_ASSISTANT => false,
         Components.I18N_ASSISTANT => false,
         Components.DOCUMENT_ANALYSIS_ASSISTANT => false,
+        Components.BATCH_PROCESSING_ASSISTANT => false,
         Components.LOG_VIEWER_ASSISTANT => false,
         
         Components.APP_SETTINGS => false,
@@ -97,6 +98,7 @@ public static class ComponentsExtensions
         Components.ERI_ASSISTANT => TB("ERI Server"),
         Components.I18N_ASSISTANT => TB("Localization Assistant"),
         Components.DOCUMENT_ANALYSIS_ASSISTANT => TB("Document Analysis Assistant"),
+        Components.BATCH_PROCESSING_ASSISTANT => TB("Batch Processing Assistant"),
         Components.SLIDE_BUILDER_ASSISTANT => TB("Slide Planner Assistant"),
         Components.VISUAL_BRIEFING_ASSISTANT => TB("Visual Briefing Assistant"),
         Components.META_ASSISTANT => TB("Assistant Builder"),
@@ -155,6 +157,10 @@ public static class ComponentsExtensions
         // We do this inside the Document Analysis Assistant component:
         Components.DOCUMENT_ANALYSIS_ASSISTANT => ConfidenceLevel.NONE,
 
+        // A policy-specific minimum is merged with this component default inside
+        // the Batch Processing Assistant; the stricter level wins.
+        Components.BATCH_PROCESSING_ASSISTANT => settingsManager.ConfigurationData.BatchProcessing.PreselectOptions ? settingsManager.ConfigurationData.BatchProcessing.MinimumProviderConfidence : default,
+
         _ => default,
     };
 
@@ -186,6 +192,8 @@ public static class ComponentsExtensions
             // The provider is selected per policy instead. We do this inside the Document Analysis Assistant component.
             Components.DOCUMENT_ANALYSIS_ASSISTANT => Settings.Provider.NONE,
 
+            Components.BATCH_PROCESSING_ASSISTANT => settingsManager.ConfigurationData.BatchProcessing.PreselectOptions ? settingsManager.ConfigurationData.Providers.FirstOrDefault(x => x.Id == settingsManager.ConfigurationData.BatchProcessing.PreselectedProvider) : null,
+
             Components.CHAT => settingsManager.ConfigurationData.Chat.PreselectOptions ? settingsManager.ConfigurationData.Providers.FirstOrDefault(x => x.Id == settingsManager.ConfigurationData.Chat.PreselectedProvider) : null,
 
             Components.AGENT_TEXT_CONTENT_CLEANER => settingsManager.ConfigurationData.TextContentCleaner.PreselectAgentOptions ? settingsManager.ConfigurationData.Providers.FirstOrDefault(x => x.Id == settingsManager.ConfigurationData.TextContentCleaner.PreselectedAgentProvider) : null,
@@ -230,4 +238,4 @@ public static class ComponentsExtensions
         
         _ => ChatTemplate.NO_CHAT_TEMPLATE,
     };
-}
+}

app/MindWork AI Studio/Tools/PluginSystem/PluginConfiguration.cs

@@ -337,6 +337,29 @@ public sealed class PluginConfiguration(bool isInternal, LuaState state, PluginT
         ManagedConfiguration.TryProcessConfiguration(x => x.Chat, x => x.PreselectedDataSourceIds, this.Id, settingsTable, dryRun);
         ManagedConfiguration.TryProcessConfiguration(x => x.Chat, x => x.SendToChatDataSourceBehavior, this.Id, settingsTable, dryRun);
 
+        // Config: Batch Processing Assistant defaults?
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.PreselectOptions, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.InputDirectory, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.OutputDirectory, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.FilePatterns, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.IncludeSubdirectories, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.PromptSource, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.FreePrompt, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.PromptFilePath, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.PreselectedPolicyId, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.OutputMode, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.CsvFileName, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.ResultColumnHeader, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.CsvSeparator, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.CustomCsvSeparator, this.Id, settingsTable, dryRun);
+        
+        var minimumDelayIsValid = ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.MinimumDelaySeconds, this.Id, settingsTable, dryRun, validator: value => value is >= DataBatchProcessing.MIN_DELAY_SECONDS and <= DataBatchProcessing.MAX_DELAY_SECONDS);
+        if (!minimumDelayIsValid && settingsTable.TryGetValue("DataBatchProcessing.MinimumDelaySeconds", out _))
+            LOG.LogWarning("The Batch Processing minimum delay configured by plugin {ConfigPluginId} must be between {MinimumDelaySeconds} and {MaximumDelaySeconds} seconds.", this.Id, DataBatchProcessing.MIN_DELAY_SECONDS, DataBatchProcessing.MAX_DELAY_SECONDS);
+
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.MinimumProviderConfidence, this.Id, settingsTable, dryRun);
+        ManagedConfiguration.TryProcessConfiguration(x => x.BatchProcessing, x => x.PreselectedProvider, Guid.Empty, this.Id, settingsTable, dryRun);
+
         // Config: transcription provider?
         ManagedConfiguration.TryProcessConfiguration(x => x.App, x => x.UseTranscriptionProvider, Guid.Empty, this.Id, settingsTable, dryRun);
 
@@ -572,4 +595,4 @@ public sealed class PluginConfiguration(bool isInternal, LuaState state, PluginT
                 LOG.LogWarning("The table 'INTRODUCTIONS' entry at index {Index} does not contain a valid introduction (config plugin id: {ConfigPluginId}).", i, this.Id);
         }
     }
-}
+}

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

@@ -50,6 +50,7 @@ public static class FileTypes
 
     // Document hierarchy
     public static readonly FileTypeFilter PDF         = FileTypeFilter.Leaf("PDF", "pdf");
+    public static readonly FileTypeFilter MARKDOWN    = FileTypeFilter.Leaf("Markdown", "md");
     public static readonly FileTypeFilter TEXT        = FileTypeFilter.Leaf(TB("Text"), "txt", "md", "rtf");
     public static readonly FileTypeFilter TABULAR     = FileTypeFilter.Leaf(TB("Tabular text"), "csv", "tsv");
     public static readonly FileTypeFilter MS_WORD     = FileTypeFilter.Leaf("Microsoft Word", "docx");

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

@@ -61,6 +61,9 @@ public sealed class MediaTranscriptionService(
             return this.activeBatches.Contains(owner);
     }
 
+    /// <summary>Gets whether the currently configured transcription provider can be used.</summary>
+    public bool HasUsableTranscriptionProvider => this.ResolveProvider() is not null;
+
     /// <summary>Gets the last retained state for one owner.</summary>
     public MediaImportSnapshot? GetSnapshot(MediaImportOwner owner)
     {
@@ -403,12 +406,12 @@ public sealed class MediaTranscriptionService(
     }
 
     /// <summary>
-    /// Transcribes a voice recording independently of the visible import lane.
+    /// Transcribes an audio or video file without starting a visible import operation.
     /// </summary>
-    /// <param name="mediaPath">Voice recording path.</param>
+    /// <param name="mediaPath">Audio or video file path.</param>
     /// <param name="token">Caller cancellation token.</param>
     /// <returns>A typed terminal result.</returns>
-    public async Task<MediaTranscriptionResult> TranscribeVoiceAsync(string mediaPath, CancellationToken token = default)
+    public async Task<MediaTranscriptionResult> TranscribeAsync(string mediaPath, CancellationToken token = default)
     {
         this.ThrowIfDisposed();
         var operation = this.CreateOperation(null, token);
@@ -423,6 +426,14 @@ public sealed class MediaTranscriptionService(
         }
     }
 
+    /// <summary>
+    /// Transcribes a voice recording independently of the visible import lane.
+    /// </summary>
+    /// <param name="mediaPath">Voice recording path.</param>
+    /// <param name="token">Caller cancellation token.</param>
+    /// <returns>A typed terminal result.</returns>
+    public Task<MediaTranscriptionResult> TranscribeVoiceAsync(string mediaPath, CancellationToken token = default) => this.TranscribeAsync(mediaPath, token);
+
     /// <summary>Cancels only the queued or active operation belonging to one owner.</summary>
     public async Task StopAsync(MediaImportOwner owner)
     {