Harden speaker identity samples

MeetingAssistant.Tests/SpeakerIdentityServiceTests.cs

@@ -199,6 +199,60 @@ public sealed class SpeakerIdentityServiceTests
         Assert.Contains("Guest01 was identified as Manuel", File.ReadAllText(learned.References.Single().TranscriptPath));
     }
 
+    [Fact]
+    public async Task UnmatchedSpeakerIsNotLearnedWhenSecondaryValidationRejectsSample()
+    {
+        await using var fixture = await SpeakerIdentityFixture.CreateAsync();
+        fixture.MatchValidator.SampleIsValid = false;
+        var service = fixture.CreateService();
+
+        await service.ProcessFinishedTranscriptAsync(
+            fixture.CreateRequest(
+                ["Manuel"],
+                [new TranscriptionSegment(TimeSpan.Zero, TimeSpan.FromSeconds(4), "Guest01", "unknown")]),
+            CancellationToken.None);
+
+        Assert.Empty(fixture.Context.SpeakerIdentities);
+    }
+
+    [Fact]
+    public async Task FinishedSnippetExtractionWaitsForMinimumContinuousSpeechDuration()
+    {
+        await using var fixture = await SpeakerIdentityFixture.CreateAsync(options =>
+            options.MinimumSampleSpeechDuration = TimeSpan.FromSeconds(30));
+        var service = fixture.CreateService();
+
+        await service.ProcessFinishedTranscriptAsync(
+            fixture.CreateRequest(
+                ["Manuel"],
+                [new TranscriptionSegment(TimeSpan.Zero, TimeSpan.FromSeconds(20), "Guest01", "short")]),
+            CancellationToken.None);
+
+        Assert.Equal(0, fixture.SnippetExtractor.ExtractCalls);
+        Assert.Empty(fixture.Context.SpeakerIdentities);
+    }
+
+    [Fact]
+    public async Task FinishedSnippetExtractionDoesNotCombineAcrossSpeakerInterruption()
+    {
+        await using var fixture = await SpeakerIdentityFixture.CreateAsync(options =>
+            options.MinimumSampleSpeechDuration = TimeSpan.FromSeconds(30));
+        var service = fixture.CreateService();
+
+        await service.ProcessFinishedTranscriptAsync(
+            fixture.CreateRequest(
+                ["Manuel"],
+                [
+                    new TranscriptionSegment(TimeSpan.Zero, TimeSpan.FromSeconds(20), "Guest01", "first"),
+                    new TranscriptionSegment(TimeSpan.FromSeconds(20), TimeSpan.FromSeconds(22), "Guest02", "interrupting"),
+                    new TranscriptionSegment(TimeSpan.FromSeconds(22), TimeSpan.FromSeconds(35), "Guest01", "second")
+                ]),
+            CancellationToken.None);
+
+        Assert.Equal(0, fixture.SnippetExtractor.ExtractCalls);
+        Assert.Empty(fixture.Context.SpeakerIdentities);
+    }
+
     [Fact]
     public async Task SuppliedSpeakerSamplesAreUsedBeforeExtractingFromAudioFile()
     {
@@ -450,6 +504,87 @@ public sealed class SpeakerIdentityServiceTests
         File.Delete(dbPath);
     }
 
+    [Fact]
+    public async Task SpeakerOverrideCreatesIdentityWhenLegacyTranscriptionCountHasNoDatabaseDefault()
+    {
+        var dbPath = Path.Combine(Path.GetTempPath(), "meeting-assistant-tests", $"{Guid.NewGuid():N}.db");
+        Directory.CreateDirectory(Path.GetDirectoryName(dbPath)!);
+        await using var context = new SpeakerIdentityDbContext(new DbContextOptionsBuilder<SpeakerIdentityDbContext>()
+            .UseSqlite($"Data Source={dbPath};Pooling=False")
+            .Options);
+        await context.Database.ExecuteSqlRawAsync(
+            """
+            CREATE TABLE "SpeakerIdentities" (
+                "Id" INTEGER NOT NULL CONSTRAINT "PK_SpeakerIdentities" PRIMARY KEY AUTOINCREMENT,
+                "CanonicalName" TEXT NULL,
+                "TranscriptionCount" INTEGER NOT NULL,
+                "CreatedAt" TEXT NOT NULL,
+                "UpdatedAt" TEXT NOT NULL
+            );
+            """);
+        await context.Database.ExecuteSqlRawAsync(
+            """
+            CREATE TABLE "SpeakerCandidateNames" (
+                "Id" INTEGER NOT NULL CONSTRAINT "PK_SpeakerCandidateNames" PRIMARY KEY AUTOINCREMENT,
+                "SpeakerIdentityId" INTEGER NOT NULL,
+                "Name" TEXT NOT NULL,
+                CONSTRAINT "FK_SpeakerCandidateNames_SpeakerIdentities_SpeakerIdentityId"
+                    FOREIGN KEY ("SpeakerIdentityId") REFERENCES "SpeakerIdentities" ("Id") ON DELETE CASCADE
+            );
+            """);
+        await context.Database.ExecuteSqlRawAsync(
+            """
+            CREATE TABLE "SpeakerSnippets" (
+                "Id" INTEGER NOT NULL CONSTRAINT "PK_SpeakerSnippets" PRIMARY KEY AUTOINCREMENT,
+                "SpeakerIdentityId" INTEGER NOT NULL,
+                "WavBytes" BLOB NOT NULL,
+                "CreatedAt" TEXT NOT NULL,
+                CONSTRAINT "FK_SpeakerSnippets_SpeakerIdentities_SpeakerIdentityId"
+                    FOREIGN KEY ("SpeakerIdentityId") REFERENCES "SpeakerIdentities" ("Id") ON DELETE CASCADE
+            );
+            """);
+        var options = new SpeakerIdentificationOptions
+        {
+            DatabasePath = dbPath,
+            MinimumSampleSpeechDuration = TimeSpan.Zero
+        };
+        var service = new SpeakerIdentityService(
+            new TestSpeakerIdentityDbContextFactory(dbPath),
+            new FakeSpeakerSnippetExtractor(),
+            new FakeSpeakerIdentityMatcher(),
+            Options.Create(new MeetingAssistantOptions { SpeakerIdentification = options }),
+            NullLogger<SpeakerIdentityService>.Instance,
+            new FakeSpeakerIdentityMatchValidator());
+        var segment = new TranscriptionSegment(TimeSpan.Zero, TimeSpan.FromSeconds(5), "Guest-01", "hello from Daniel");
+        var root = Path.GetDirectoryName(dbPath)!;
+        var transcriptPath = Path.Combine(root, "transcript.md");
+        await File.WriteAllTextAsync(transcriptPath, "Transcript");
+        var request = new SpeakerIdentificationRequest(
+            "test.wav",
+            new MeetingNote(
+                Path.Combine(root, "meeting.md"),
+                new MeetingNoteFrontmatter
+                {
+                    Title = "Test Meeting",
+                    StartTime = DateTimeOffset.Parse("2026-05-28T10:00:00+02:00"),
+                    Attendees = ["Hecht, Daniel"],
+                    Transcript = transcriptPath,
+                    AssistantContext = Path.Combine(root, "context.md"),
+                    Summary = Path.Combine(root, "summary.md")
+                },
+                ""),
+            [segment],
+            [new SpeakerAudioSample("Guest-01", segment, [8, 8, 8], 95)]);
+
+        await service.ApplySpeakerOverrideAsync(request, "Guest-01", "Hecht, Daniel", CancellationToken.None);
+
+        context.ChangeTracker.Clear();
+        var saved = await context.SpeakerIdentities.SingleAsync();
+        Assert.Equal("Hecht, Daniel", saved.CanonicalName);
+        Assert.Equal(0, saved.TranscriptionCount);
+        File.Delete(dbPath);
+    }
+
     private sealed class SpeakerIdentityFixture : IAsyncDisposable
     {
         private readonly string tempDirectory;
@@ -472,6 +607,8 @@ public sealed class SpeakerIdentityServiceTests
 
         public FakeSpeakerIdentityMatcher Matcher { get; } = new();
 
+        public FakeSpeakerIdentityMatchValidator MatchValidator { get; } = new();
+
         public FakeSpeakerSnippetExtractor SnippetExtractor { get; } = new();
 
         public static async Task<SpeakerIdentityFixture> CreateAsync(
@@ -484,7 +621,8 @@ public sealed class SpeakerIdentityServiceTests
             {
                 DatabasePath = dbPath,
                 MaxSnippetsPerSpeaker = 3,
-                MatchBatchSize = 6
+                MatchBatchSize = 6,
+                MinimumSampleSpeechDuration = TimeSpan.Zero
             };
             configureOptions?.Invoke(options);
             var context = new SpeakerIdentityDbContext(new DbContextOptionsBuilder<SpeakerIdentityDbContext>()
@@ -501,7 +639,8 @@ public sealed class SpeakerIdentityServiceTests
                 SnippetExtractor,
                 Matcher,
                 Options.Create(new MeetingAssistantOptions { SpeakerIdentification = options }),
-                NullLogger<SpeakerIdentityService>.Instance);
+                NullLogger<SpeakerIdentityService>.Instance,
+                MatchValidator);
         }
 
         public SpeakerIdentityAttendeeCanonicalizer CreateAttendeeCanonicalizer()
@@ -627,6 +766,11 @@ public sealed class SpeakerIdentityServiceTests
             IReadOnlyList<TranscriptionSegment> speakerSegments,
             CancellationToken cancellationToken)
         {
+            if (speakerSegments.Count == 0)
+            {
+                return Task.FromResult<byte[]>([]);
+            }
+
             ExtractCalls++;
             return Task.FromResult<byte[]>([7, 8, 9]);
         }
@@ -657,4 +801,23 @@ public sealed class SpeakerIdentityServiceTests
             return Task.FromResult<SpeakerIdentityMatch?>(new SpeakerIdentityMatch(MatchIdentityId.Value));
         }
     }
+
+    private sealed class FakeSpeakerIdentityMatchValidator : ISpeakerIdentityMatchValidator
+    {
+        public bool SampleIsValid { get; set; } = true;
+
+        public Task<bool> ValidateSampleAsync(
+            byte[] wavBytes,
+            CancellationToken cancellationToken)
+        {
+            return Task.FromResult(SampleIsValid);
+        }
+
+        public Task<bool> ValidateMatchAsync(
+            SpeakerIdentityMatchValidationRequest request,
+            CancellationToken cancellationToken)
+        {
+            return Task.FromResult(true);
+        }
+    }
 }