Fixed Semantic Search with external data sources (ERI servers) (#1090)

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

app/MindWork AI Studio/Provider/BaseProvider.cs

@@ -1445,9 +1445,22 @@ public abstract class BaseProvider : IProvider, ISecretId
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// The ID and whether the provider is self-hosted come along, because the data source checks
+    /// trust a provider by them: Semantic Search decides with these settings which data sources
+    /// it offers, while the classic RAG process asks this provider itself. Without them, a
+    /// self-hosted provider, or one the organization trusts, could search a data source which asks
+    /// for such a provider in one process but not in the other.<br/><br/>
+    /// With the ID, the settings also know what the provider's own model list reported, e.g., the
+    /// context window of a self-hosted model, see ProviderExtensions.GetAutomaticModelProfile. So
+    /// the tools of a request and the way images are passed on see the model as the configured
+    /// provider does.
+    /// </remarks>
     public AIStudio.Settings.Provider CreateSettingsProvider(Model chatModel) => new()
     {
+        Id = this.ConfiguredProviderId,
         UsedLLMProvider = this.Provider,
+        IsSelfHosted = this.Provider is LLMProviders.SELF_HOSTED,
         Model = chatModel,
         InstanceName = this.InstanceName,
         CapabilityOverrides = this.CapabilityOverrides,