Add PII redaction POC for secure LLM prompting.

Implements detect-redact-sanitize pipeline with regex, domain rules, and ONNX NER before the LLM boundary, plus NUnit tests and Xenovex push documentation.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/PiiRedaction.Core.Tests/Integration/GoldenPromptTests.cs

@@ -0,0 +1,25 @@
+using FluentAssertions;
+using PiiRedaction.Core.Models;
+using PiiRedaction.Core.Tests.TestSupport;
+
+namespace PiiRedaction.Core.Tests.Integration;
+
+[TestFixture]
+public sealed class GoldenPromptTests
+{
+    [TestCaseSource(typeof(PromptScenarioCatalog), nameof(PromptScenarioCatalog.AllScenarios))]
+    public void Sanitize_PromptScenario_ProducesExpectedOutput(PromptScenario scenario)
+    {
+        var sanitizer = ProductionPipelineFactory.CreateForScenario(scenario);
+        var result = sanitizer.Sanitize(new SanitizationRequest(scenario.Prompt));
+
+        result.SanitizedPrompt.Should().Be(scenario.ExpectedSanitized, because: scenario.Name);
+        result.DetectedEntities.Select(entity => entity.Type)
+            .Should().BeEquivalentTo(scenario.ExpectedTypes, because: scenario.Name);
+
+        foreach (var forbidden in scenario.MustNotContainInSanitized)
+        {
+            result.SanitizedPrompt.Should().NotContain(forbidden, because: scenario.Name);
+        }
+    }
+}

tests/PiiRedaction.Core.Tests/Integration/LlmBoundaryTests.cs

@@ -0,0 +1,52 @@
+using FluentAssertions;
+using PiiRedaction.Core.Abstractions;
+using PiiRedaction.Core.Models;
+using PiiRedaction.Core.Tests.TestSupport;
+using PiiRedaction.Infrastructure.Llm;
+
+namespace PiiRedaction.Core.Tests.Integration;
+
+[TestFixture]
+public sealed class LlmBoundaryTests
+{
+    [Test]
+    public async Task SendPromptAsync_DoesNotTransmitOriginalPii()
+    {
+        var capturingClient = new CapturingChatClient();
+        ILlmPromptService service = new MockLlmPromptService(capturingClient);
+
+        const string sanitized = "Customer <PERSON_1> with email <EMAIL_1>.";
+        await service.SendPromptAsync(sanitized);
+
+        capturingClient.LastUserMessage.Should().Be(sanitized);
+        capturingClient.LastUserMessage.Should().NotContain("ravi.kumar@gmail.com");
+        capturingClient.LastUserMessage.Should().NotContain("Ravi Kumar");
+    }
+
+    [Test]
+    public async Task SendPromptAsync_AfterSanitization_OnlyPlaceholdersReachLlm()
+    {
+        var capturingClient = new CapturingChatClient();
+        var sanitizer = ProductionPipelineFactory.Create().Sanitizer;
+        ILlmPromptService service = new MockLlmPromptService(capturingClient);
+
+        const string prompt = "Email ravi.kumar@gmail.com please.";
+        var result = sanitizer.Sanitize(new SanitizationRequest(prompt));
+
+        result.SanitizedPrompt.Should().Contain("<EMAIL_1>");
+        await service.SendPromptAsync(result.SanitizedPrompt);
+
+        capturingClient.LastUserMessage.Should().Contain("<EMAIL_1>");
+        capturingClient.LastUserMessage.Should().NotContain("ravi.kumar@gmail.com");
+    }
+
+    [TestCase(null)]
+    [TestCase("")]
+    [TestCase("   ")]
+    public void SendPromptAsync_InvalidSanitizedPrompt_ThrowsArgumentException(string? prompt)
+    {
+        ILlmPromptService service = new MockLlmPromptService(new MockChatClient());
+        var action = async () => await service.SendPromptAsync(prompt!);
+        action.Should().ThrowAsync<ArgumentException>();
+    }
+}

tests/PiiRedaction.Core.Tests/Integration/RealNerPipelineTests.cs

@@ -0,0 +1,127 @@
+using FluentAssertions;
+
+using PiiRedaction.Core.Abstractions;
+
+using PiiRedaction.Core.Models;
+
+using PiiRedaction.Core.Tests.TestSupport;
+
+using PiiRedaction.Tests.Shared;
+
+
+
+namespace PiiRedaction.Core.Tests.Integration;
+
+
+
+/// <summary>
+
+/// End-to-end pipeline proof using the real ONNX NER model (no fakes).
+
+/// </summary>
+
+[TestFixture]
+
+[Category("RealModel")]
+
+public sealed class RealNerPipelineTests : RealNerModelFixture
+
+{
+
+    private IPromptSanitizer _sanitizer = null!;
+
+
+
+    [OneTimeSetUp]
+
+    public void OneTimeSetUpPipeline()
+
+    {
+
+        _sanitizer = ProductionPipelineFactory.CreateWithRealModel(Runner);
+
+    }
+
+
+
+    [Test]
+
+    public void Sanitize_FullFinancialWithCustomer_RedactsAllPiiTypes()
+
+    {
+
+        const string prompt =
+
+            "Customer Ravi Kumar with email ravi.kumar@gmail.com and phone 9876543210 has LoanNumber LN-456789 and PAN ABCDE1234F. Please summarize this customer issue.";
+
+
+
+        var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
+
+
+
+        result.SanitizedPrompt.Should().Be(
+
+            "Customer <PERSON_1> with email <EMAIL_1> and phone <PHONE_1> has LoanNumber <LOAN_NUMBER_1> and PAN <PAN_1>. Please summarize this customer issue.");
+
+
+
+        result.SanitizedPrompt.Should().NotContainAny("Ravi Kumar", "ravi.kumar@gmail.com", "9876543210", "LN-456789", "ABCDE1234F");
+
+        result.DetectedEntities.Should().Contain(entity =>
+
+            entity.Type == PiiEntityType.Person && entity.Source == PiiDetectionSource.Ner);
+
+    }
+
+
+
+    [Test]
+
+    public void Sanitize_TwoCustomersInOnePrompt_RedactsBothPeople()
+
+    {
+
+        const string prompt = "Customer Ravi Kumar and Customer Priya Nair disputed the same charge.";
+
+
+
+        var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
+
+
+
+        result.SanitizedPrompt.Should().Contain("<PERSON_1>");
+
+        result.SanitizedPrompt.Should().Contain("<PERSON_2>");
+
+        result.SanitizedPrompt.Should().NotContainAny("Ravi Kumar", "Priya Nair");
+
+        result.DetectedEntities.Count(entity => entity.Type == PiiEntityType.Person).Should().BeGreaterThanOrEqualTo(2);
+
+    }
+
+
+
+    [Test]
+
+    public void Sanitize_NoPiiCleanTicket_PassesThroughUnchanged()
+
+    {
+
+        const string prompt = "What is the status of ticket TKT-99887 and when will the API maintenance end?";
+
+
+
+        var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
+
+
+
+        result.SanitizedPrompt.Should().Be(prompt);
+
+        result.DetectedEntities.Should().BeEmpty();
+
+    }
+
+}
+
+