Outbound data restrictions after searching data sources (#1106)

app/Tests/Tools/DataSourceRequirementsTests.cs

@@ -0,0 +1,73 @@
+using AIStudio.Provider;
+using AIStudio.Settings;
+using AIStudio.Settings.DataModel;
+using AIStudio.Tools.RAG;
+
+namespace AIStudio.Tests.Tools;
+
+/// <summary>
+/// Checks what a chat requires from now on, because passages of data sources reached the model.
+/// </summary>
+/// <remarks>
+/// Semantic Search and the classic RAG process both ask here, so that both demand the same of the
+/// same data sources. Only the data sources with passages count: one search in the wrong data
+/// source must not lock a chat for good. Of several equally strict data sources, the chat names
+/// the same one, whichever way searched them and in whichever order.
+/// </remarks>
+[TestFixture]
+public sealed class DataSourceRequirementsTests
+{
+    private static readonly IDataSource HANDBOOK = new DataSourceLocalDirectory { Num = 1, Id = "11111111-1111-1111-1111-111111111111", Name = "Handbook", MaxMatches = 10, ConfidenceLevel = ConfidenceLevel.HIGH };
+    private static readonly IDataSource MINUTES = new DataSourceLocalFile { Num = 2, Id = "22222222-2222-2222-2222-222222222222", Name = "Minutes", MaxMatches = 10, ConfidenceLevel = ConfidenceLevel.LOW, OutboundDataRestriction = OutboundDataRestriction.UNRESTRICTED };
+    private static readonly IDataSource INTRANET = new DataSourceERI_V1 { Num = 3, Id = "33333333-3333-3333-3333-333333333333", Name = "Intranet", MaxMatches = 10, SecurityPolicy = DataSourceSecurity.SELF_HOSTED };
+    private static readonly IDataSource ARCHIVE = new DataSourceLocalDirectory { Num = 4, Id = "44444444-4444-4444-4444-444444444444", Name = "Archive", MaxMatches = 10, ConfidenceLevel = ConfidenceLevel.LOW };
+
+    [Test]
+    public void ASearchWhichFoundNothingRequiresNothing() =>
+        Assert.That(DataSourceRequirements.Of([HANDBOOK, INTRANET], [0, 0], OutboundDataRestriction.UNRESTRICTED), Is.EqualTo(DataSourceRequirements.NONE));
+
+    [Test]
+    public void OnlyTheDataSourcesWithPassagesCount()
+    {
+        var requirements = DataSourceRequirements.Of([HANDBOOK, MINUTES, INTRANET], [0, 2, 0], OutboundDataRestriction.UNRESTRICTED);
+
+        Assert.That(requirements, Is.EqualTo(new DataSourceRequirements(ConfidenceLevel.LOW, DataSourceSecurity.ALLOW_ANY, OutboundDataRequirement.NONE)), "Only the minutes brought something in, and they allow every tool.");
+    }
+
+    [Test]
+    public void TheStrictestDataSourceDecides()
+    {
+        var requirements = DataSourceRequirements.Of([MINUTES, HANDBOOK, INTRANET], [1, 1, 1], OutboundDataRestriction.UNRESTRICTED);
+
+        Assert.Multiple(() =>
+        {
+            Assert.That(requirements.Confidence, Is.EqualTo(ConfidenceLevel.HIGH));
+            Assert.That(requirements.Security, Is.EqualTo(DataSourceSecurity.SELF_HOSTED));
+            Assert.That(requirements.OutboundData, Is.EqualTo(new OutboundDataRequirement(OutboundDataRestriction.ONLY_CONFIGURED_SERVICES, OutboundDataOrigin.DATA_SOURCE, INTRANET.Id)), "The intranet may only be seen by self-hosted providers.");
+        });
+    }
+
+    [Test]
+    public void OnATieTheFirstDataSourceByNumberIsNamed()
+    {
+        var expected = new OutboundDataRequirement(OutboundDataRestriction.ONLY_LINKS_FROM_CHAT, OutboundDataOrigin.DATA_SOURCE, HANDBOOK.Id);
+
+        Assert.Multiple(() =>
+        {
+            Assert.That(DataSourceRequirements.Of([HANDBOOK, ARCHIVE], [1, 1], OutboundDataRestriction.UNRESTRICTED).OutboundData, Is.EqualTo(expected));
+            Assert.That(DataSourceRequirements.Of([ARCHIVE, HANDBOOK], [1, 1], OutboundDataRestriction.UNRESTRICTED).OutboundData, Is.EqualTo(expected), "An agent may select the data sources in another order.");
+        });
+    }
+
+    [Test]
+    public void AnOrganizationMinimumTightensTheDataSource()
+    {
+        var requirements = DataSourceRequirements.Of([MINUTES], [1], OutboundDataRestriction.ONLY_LINKS_FROM_CHAT);
+
+        Assert.That(requirements.OutboundData, Is.EqualTo(new OutboundDataRequirement(OutboundDataRestriction.ONLY_LINKS_FROM_CHAT, OutboundDataOrigin.DATA_SOURCE, MINUTES.Id)), "The chat names the data source it found something in, even though the level comes from the organization.");
+    }
+
+    [Test]
+    public void CountsWhichDoNotMatchTheDataSourcesAreRefused() =>
+        Assert.That(() => DataSourceRequirements.Of([HANDBOOK, MINUTES], [1], OutboundDataRestriction.UNRESTRICTED), Throws.ArgumentException);
+}