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/TestSupport/CapturingChatClient.cs

@@ -0,0 +1,38 @@
+using System.Runtime.CompilerServices;
+using Microsoft.Extensions.AI;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+public sealed class CapturingChatClient : IChatClient
+{
+    public string? LastUserMessage { get; private set; }
+
+    public Task<ChatResponse> GetResponseAsync(
+        IEnumerable<ChatMessage> messages,
+        ChatOptions? options = null,
+        CancellationToken cancellationToken = default)
+    {
+        LastUserMessage = messages.LastOrDefault(message => message.Role == ChatRole.User)?.Text;
+
+        var response = new ChatResponse(new ChatMessage(
+            ChatRole.Assistant,
+            $"Captured {LastUserMessage?.Length ?? 0} chars."));
+
+        return Task.FromResult(response);
+    }
+
+    public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
+        IEnumerable<ChatMessage> messages,
+        ChatOptions? options = null,
+        [EnumeratorCancellation] CancellationToken cancellationToken = default)
+    {
+        var response = await GetResponseAsync(messages, options, cancellationToken).ConfigureAwait(false);
+        yield return new ChatResponseUpdate(ChatRole.Assistant, response.Messages.Last().Text);
+    }
+
+    public object? GetService(Type serviceType, object? serviceKey = null) => null;
+
+    public void Dispose()
+    {
+    }
+}

tests/PiiRedaction.Core.Tests/TestSupport/FakeOnnxNerModelRunner.cs

@@ -0,0 +1,19 @@
+using PiiRedaction.Core.Detection;
+using PiiRedaction.Core.Models;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+public sealed class FakeOnnxNerModelRunner : IOnnxNerModelRunner
+{
+    public bool IsModelAvailable { get; set; }
+
+    public IReadOnlyList<PiiEntity> EntitiesToReturn { get; set; } = [];
+
+    public string? LastPredictedText { get; private set; }
+
+    public IReadOnlyList<PiiEntity> PredictEntities(string text)
+    {
+        LastPredictedText = text;
+        return EntitiesToReturn;
+    }
+}

tests/PiiRedaction.Core.Tests/TestSupport/NerEntityBuilder.cs

@@ -0,0 +1,33 @@
+using PiiRedaction.Core.Models;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+public static class NerEntityBuilder
+{
+    public static IReadOnlyList<PiiEntity> BuildFromScenario(PromptScenario scenario)
+    {
+        var entities = new List<PiiEntity>();
+
+        foreach (var (type, value) in scenario.ExpectedTypes.Zip(scenario.MustNotContainInSanitized))
+        {
+            if (type != PiiEntityType.Person)
+            {
+                continue;
+            }
+
+            var searchStart = 0;
+            while ((searchStart = scenario.Prompt.IndexOf(value, searchStart, StringComparison.Ordinal)) >= 0)
+            {
+                entities.Add(new PiiEntity(
+                    PiiEntityType.Person,
+                    value,
+                    searchStart,
+                    value.Length,
+                    PiiDetectionSource.Ner));
+                searchStart += value.Length;
+            }
+        }
+
+        return entities;
+    }
+}

tests/PiiRedaction.Core.Tests/TestSupport/ProductionPipelineFactory.cs

@@ -0,0 +1,49 @@
+using PiiRedaction.Core.Abstractions;
+using PiiRedaction.Core.Detection;
+using PiiRedaction.Core.Redaction;
+using PiiRedaction.Core.Sanitization;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+public static class ProductionPipelineFactory
+{
+    public static IPromptSanitizer CreateWithRealModel(IOnnxNerModelRunner runner) =>
+        new PromptSanitizer(CreateCompositeDetector(runner), new PlaceholderPiiRedactor());
+
+    public static IPiiDetector CreateCompositeDetector(IOnnxNerModelRunner runner) =>
+        new CompositePiiDetector(
+        [
+            new DomainRulePiiDetector(),
+            new RegexPiiDetector(),
+            new OnnxNerPiiDetector(runner)
+        ]);
+
+    public static (IPromptSanitizer Sanitizer, FakeOnnxNerModelRunner NerRunner) Create(
+        bool modelAvailable = false,
+        IReadOnlyList<Models.PiiEntity>? nerEntities = null)
+    {
+        var nerRunner = CreateNerRunner(modelAvailable, nerEntities);
+        var sanitizer = new PromptSanitizer(CreateCompositeDetector(nerRunner), new PlaceholderPiiRedactor());
+        return (sanitizer, nerRunner);
+    }
+
+    public static IPromptSanitizer CreateForScenario(PromptScenario scenario)
+    {
+        var nerEntities = NerEntityBuilder.BuildFromScenario(scenario);
+        return Create(modelAvailable: nerEntities.Count > 0, nerEntities: nerEntities).Sanitizer;
+    }
+
+    public static IPiiDetector CreateCompositeDetector(
+        bool modelAvailable = false,
+        IReadOnlyList<Models.PiiEntity>? nerEntities = null) =>
+        CreateCompositeDetector(CreateNerRunner(modelAvailable, nerEntities));
+
+    private static FakeOnnxNerModelRunner CreateNerRunner(
+        bool modelAvailable,
+        IReadOnlyList<Models.PiiEntity>? nerEntities) =>
+        new()
+        {
+            IsModelAvailable = modelAvailable,
+            EntitiesToReturn = nerEntities ?? []
+        };
+}

tests/PiiRedaction.Core.Tests/TestSupport/PromptScenario.cs

@@ -0,0 +1,10 @@
+using PiiRedaction.Core.Models;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+public sealed record PromptScenario(
+    string Name,
+    string Prompt,
+    string ExpectedSanitized,
+    PiiEntityType[] ExpectedTypes,
+    string[] MustNotContainInSanitized);

tests/PiiRedaction.Core.Tests/TestSupport/PromptScenarioCatalog.cs

@@ -0,0 +1,68 @@
+using NUnit.Framework;
+using PiiRedaction.Core.Models;
+
+namespace PiiRedaction.Core.Tests.TestSupport;
+
+/// <summary>
+/// Focused end-to-end scenarios that exercise the full sanitizer pipeline beyond what unit tests cover in isolation.
+/// </summary>
+public static class PromptScenarioCatalog
+{
+    public static IEnumerable<TestCaseData> AllScenarios()
+    {
+        foreach (var scenario in BuildScenarios())
+        {
+            yield return new TestCaseData(scenario).SetName(scenario.Name);
+        }
+    }
+
+    private static IEnumerable<PromptScenario> BuildScenarios()
+    {
+        yield return CanonicalScenario();
+        yield return MultiRegexScenario();
+        yield return DuplicatePeopleScenario();
+        yield return OverlapScenario();
+        yield return NoPiiScenario();
+    }
+
+    private static PromptScenario CanonicalScenario()
+    {
+        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.";
+
+        return new PromptScenario(
+            "Canonical_DemoPrompt",
+            prompt,
+            "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.",
+            [PiiEntityType.Person, PiiEntityType.Email, PiiEntityType.Phone, PiiEntityType.LoanNumber, PiiEntityType.Pan],
+            ["Ravi Kumar", "ravi.kumar@gmail.com", "9876543210", "LN-456789", "ABCDE1234F"]);
+    }
+
+    private static PromptScenario MultiRegexScenario() => new(
+        "Full_AllRegexTypes",
+        "Email a@b.co phone 9001234567 PAN ABCDE1234F aadhaar 1234 5678 9012 card 4111-1111-1111-1111.",
+        "Email <EMAIL_1> phone <PHONE_1> PAN <PAN_1> aadhaar <AADHAAR_1> card <CREDIT_CARD_1>.",
+        [PiiEntityType.Email, PiiEntityType.Phone, PiiEntityType.Pan, PiiEntityType.Aadhaar, PiiEntityType.CreditCard],
+        ["a@b.co", "9001234567", "ABCDE1234F", "1234 5678 9012", "4111-1111-1111-1111"]);
+
+    private static PromptScenario DuplicatePeopleScenario() => new(
+        "Duplicate_TwoPeople",
+        "Customer Ravi Kumar and Customer Priya Nair.",
+        "Customer <PERSON_2> and Customer <PERSON_1>.",
+        [PiiEntityType.Person, PiiEntityType.Person],
+        ["Ravi Kumar", "Priya Nair"]);
+
+    private static PromptScenario OverlapScenario() => new(
+        "Overlap_AadhaarAndPhone",
+        "Aadhaar 987654321012 and phone 9876543210.",
+        "Aadhaar <AADHAAR_1> and phone <PHONE_1>.",
+        [PiiEntityType.Aadhaar, PiiEntityType.Phone],
+        ["9876543210"]);
+
+    private static PromptScenario NoPiiScenario() => new(
+        "Negative_NoPii",
+        "Please summarize the general policy on refunds.",
+        "Please summarize the general policy on refunds.",
+        [],
+        []);
+}