feat(ai): semantic-search backfill worker + Ollama compose profile (RECOMMENDATIONS #4a)

First activation slice of semantic search (docs/discovery/05+06):
- EmbeddingBackfillWorker: fills Email.Embedding in small batches (32, 2s pause,
  newest first; subject+snippet, truncated) so interactive load is never starved.
  Exits immediately when the embedding provider is unavailable — AI-off deployments
  are untouched, Ollama hiccups back off instead of crashing the host.
- compose: optional 'ollama' service under the 'ai' profile (persistent model
  volume, commented GPU passthrough for the RTX 3080); api gets
  Ai__OllamaBaseUrl pointing at it.
- LiveDb test proves the worker persists 768-dim vectors against real pgvector
  (deterministic fake provider); LiveDb classes serialised into one xUnit
  collection (concurrent MigrateAsync on a fresh DB races — found while testing).

Verified against REAL Ollama locally: pulled nomic-embed-text in a container and
confirmed the /api/embeddings contract the provider uses returns 768-dim vectors.
Full suite 55 green (4 LiveDb vs real pgvector); format clean.

Next slice: hybrid RRF ranking in SearchService once embeddings exist.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.gitea/workflows/ci.yml

@@ -14,7 +14,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: '10.0.x'
+          dotnet-version: '8.0.x'
       - name: Restore
         run: dotnet restore InboxIntel.sln
       - name: Build
@@ -45,7 +45,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: '10.0.x'
+          dotnet-version: '8.0.x'
       - name: dotnet format (verify only)
         run: dotnet format InboxIntel.sln --verify-no-changes
 
@@ -67,7 +67,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: '10.0.x'
+          dotnet-version: '8.0.x'
       - name: Wait for Postgres
         run: |
           for i in $(seq 1 30); do

.gitea/workflows/security.yml

@@ -31,7 +31,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: '10.0.x'
+          dotnet-version: '8.0.x'
       - name: Restore
         run: dotnet restore InboxIntel.sln
       - name: .NET vulnerable packages (fail on any)

Directory.Build.props

@@ -1,6 +1,6 @@
 <Project>
   <PropertyGroup>
-    <TargetFramework>net10.0</TargetFramework>
+    <TargetFramework>net8.0</TargetFramework>
     <Nullable>enable</Nullable>
     <ImplicitUsings>enable</ImplicitUsings>
     <LangVersion>latest</LangVersion>

docker-compose.yml

@@ -34,6 +34,8 @@ services:
       GoogleOAuth__ClientId: ${GOOGLE_CLIENT_ID:-}
       GoogleOAuth__ClientSecret: ${GOOGLE_CLIENT_SECRET:-}
       Ai__Mode: ${AI_MODE:-Disabled}
+      # Points at the compose 'ollama' service when the ai profile is up; harmless otherwise.
+      Ai__OllamaBaseUrl: ${OLLAMA_BASE_URL:-http://ollama:11434}
       # Dev mode shows the dev banner and caps the initial sync. Set DEV_MODE=true
       # and MAX_MESSAGES=1000 in deploy/.env to exercise it in this Docker setup.
       App__DevMode: ${DEV_MODE:-false}
@@ -59,6 +61,23 @@ services:
     ports:
       - "8081:80"
 
+  # Local AI (semantic search + assistants). Enable with:
+  #   docker compose --profile ai up -d && set AI_MODE=LocalOllama in deploy/.env
+  # First run: docker compose exec ollama ollama pull nomic-embed-text
+  # GPU (RTX 3080): uncomment the deploy block to pass the GPU through.
+  ollama:
+    image: ollama/ollama
+    profiles: ["ai"]
+    volumes:
+      - ollama:/root/.ollama
+    # deploy:
+    #   resources:
+    #     reservations:
+    #       devices:
+    #         - driver: nvidia
+    #           count: all
+    #           capabilities: [gpu]
+
   # Optional reverse proxy. Enable with: docker compose --profile proxy up
   nginx:
     image: nginx:alpine
@@ -74,3 +93,4 @@ services:
 volumes:
   pgdata:
   keys:
+  ollama:

src/InboxIntel.Api/Dockerfile

@@ -1,5 +1,5 @@
 # Multi-stage build for the ASP.NET Core API.
-FROM mcr.microsoft.com/dotnet/sdk:10.0 AS build
+FROM mcr.microsoft.com/dotnet/sdk:8.0 AS build
 WORKDIR /src
 
 # Copy solution + project files first for layer-cached restore.
@@ -13,7 +13,7 @@ RUN dotnet restore src/InboxIntel.Api/InboxIntel.Api.csproj
 COPY src/ src/
 RUN dotnet publish src/InboxIntel.Api/InboxIntel.Api.csproj -c Release -o /app/publish /p:UseAppHost=false
 
-FROM mcr.microsoft.com/dotnet/aspnet:10.0 AS runtime
+FROM mcr.microsoft.com/dotnet/aspnet:8.0 AS runtime
 WORKDIR /app
 COPY --from=build /app/publish .
 

src/InboxIntel.Api/InboxIntel.Api.csproj

@@ -5,10 +5,10 @@
     <UserSecretsId>210c6d96-c7e4-4ee9-8982-8b91424979b8</UserSecretsId>
   </PropertyGroup>
   <ItemGroup>
-    <PackageReference Include="Microsoft.AspNetCore.Authentication.Google" Version="10.0.9" />
-    <PackageReference Include="Microsoft.AspNetCore.Authentication.JwtBearer" Version="10.0.9" />
+    <PackageReference Include="Microsoft.AspNetCore.Authentication.Google" Version="8.0.7" />
+    <PackageReference Include="Microsoft.AspNetCore.Authentication.JwtBearer" Version="8.0.7" />
     <!-- Required on the startup project for `dotnet ef migrations` to work. -->
-    <PackageReference Include="Microsoft.EntityFrameworkCore.Design" Version="10.0.9">
+    <PackageReference Include="Microsoft.EntityFrameworkCore.Design" Version="8.0.4">
       <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
       <PrivateAssets>all</PrivateAssets>
     </PackageReference>

src/InboxIntel.Api/Program.cs

@@ -38,8 +38,8 @@ var dp = builder.Services.AddDataProtection()
 var dpCertPath = builder.Configuration["DataProtection:CertificatePath"];
 if (!string.IsNullOrWhiteSpace(dpCertPath))
 {
-    dp.ProtectKeysWithCertificate(System.Security.Cryptography.X509Certificates.X509CertificateLoader
-        .LoadPkcs12FromFile(dpCertPath, builder.Configuration["DataProtection:CertificatePassword"]));
+    dp.ProtectKeysWithCertificate(new System.Security.Cryptography.X509Certificates.X509Certificate2(
+        dpCertPath, builder.Configuration["DataProtection:CertificatePassword"]));
 }
 
 builder.Services.AddApplication();
@@ -201,14 +201,15 @@ var forwardedOptions = new ForwardedHeadersOptions
     ForwardedHeaders = ForwardedHeaders.XForwardedFor | ForwardedHeaders.XForwardedProto | ForwardedHeaders.XForwardedHost,
     ForwardLimit = app.Configuration.GetValue<int?>("ForwardedHeaders:ForwardLimit") ?? 1
 };
-forwardedOptions.KnownIPNetworks.Clear();
+forwardedOptions.KnownNetworks.Clear();
 forwardedOptions.KnownProxies.Clear();
 var trustedNetworks = app.Configuration.GetSection("ForwardedHeaders:KnownNetworks").Get<string[]>()
     ?? new[] { "10.0.0.0/8", "172.16.0.0/12", "192.168.0.0/16", "127.0.0.0/8", "::1/128" };
 foreach (var cidr in trustedNetworks)
 {
-    if (System.Net.IPNetwork.TryParse(cidr, out var network))
-        forwardedOptions.KnownIPNetworks.Add(network);
+    var parts = cidr.Split('/');
+    if (parts.Length == 2 && System.Net.IPAddress.TryParse(parts[0], out var prefix) && int.TryParse(parts[1], out var len))
+        forwardedOptions.KnownNetworks.Add(new Microsoft.AspNetCore.HttpOverrides.IPNetwork(prefix, len));
 }
 app.UseForwardedHeaders(forwardedOptions);
 

src/InboxIntel.Application/InboxIntel.Application.csproj

@@ -6,13 +6,13 @@
   <ItemGroup>
     <PackageReference Include="FluentValidation" Version="11.9.2" />
     <PackageReference Include="FluentValidation.DependencyInjectionExtensions" Version="11.9.2" />
-    <PackageReference Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.9" />
+    <PackageReference Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="8.0.2" />
     <!-- DbSet<> is exposed on IAppDbContext so the Application layer can query.
          Pinned to 8.0.4 to match the Npgsql provider's Relational dependency. -->
-    <PackageReference Include="Microsoft.EntityFrameworkCore" Version="10.0.9" />
+    <PackageReference Include="Microsoft.EntityFrameworkCore" Version="8.0.4" />
     <!-- Transitive security pins: patch known .NET 8.0.0 advisories pulled in by EF Core. -->
-    <PackageReference Include="System.Text.Json" Version="10.0.9" />
-    <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="10.0.9" />
+    <PackageReference Include="System.Text.Json" Version="8.0.6" />
+    <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="8.0.1" />
   </ItemGroup>
   <ItemGroup>
     <ProjectReference Include="..\InboxIntel.Domain\InboxIntel.Domain.csproj" />

src/InboxIntel.Domain/InboxIntel.Domain.csproj

@@ -6,7 +6,7 @@
   <ItemGroup>
     <!-- NpgsqlTypes.NpgsqlTsVector (FTS) and Pgvector.Vector (semantic search) are used as
          column types on the Email entity — same pragmatic precedent for both. -->
-    <PackageReference Include="Npgsql" Version="10.0.2" />
-    <PackageReference Include="Pgvector" Version="0.3.0" />
+    <PackageReference Include="Npgsql" Version="8.0.3" />
+    <PackageReference Include="Pgvector" Version="0.2.0" />
   </ItemGroup>
 </Project>

src/InboxIntel.Infrastructure/Ai/EmbeddingBackfillWorker.cs

@@ -0,0 +1,104 @@
+using InboxIntel.Application.Abstractions;
+using InboxIntel.Infrastructure.Persistence;
+using Microsoft.EntityFrameworkCore;
+using Microsoft.Extensions.DependencyInjection;
+using Microsoft.Extensions.Hosting;
+using Microsoft.Extensions.Logging;
+
+namespace InboxIntel.Infrastructure.Ai;
+
+/// <summary>
+/// Fills <c>Email.Embedding</c> (pgvector) for semantic search, in small background batches
+/// so interactive requests are never starved (per docs/discovery/06: embeddings are the
+/// small always-on model; the batch pause keeps VRAM/CPU pressure low). Exits immediately
+/// when the embedding provider is unavailable (AI disabled / Ollama down) — semantic search
+/// simply stays dormant and lexical search is unaffected.
+/// </summary>
+public class EmbeddingBackfillWorker : BackgroundService
+{
+    private const int BatchSize = 32;
+    private static readonly TimeSpan BatchPause = TimeSpan.FromSeconds(2);
+    private static readonly TimeSpan IdleRescan = TimeSpan.FromMinutes(15);
+
+    private readonly IServiceScopeFactory _scopeFactory;
+    private readonly ILogger<EmbeddingBackfillWorker> _logger;
+
+    public EmbeddingBackfillWorker(IServiceScopeFactory scopeFactory, ILogger<EmbeddingBackfillWorker> logger)
+    {
+        _scopeFactory = scopeFactory;
+        _logger = logger;
+    }
+
+    protected override async Task ExecuteAsync(CancellationToken stoppingToken)
+    {
+        // Provider availability is fixed by configuration for the process lifetime.
+        using (var probe = _scopeFactory.CreateScope())
+        {
+            if (!probe.ServiceProvider.GetRequiredService<IEmbeddingProvider>().IsAvailable)
+            {
+                _logger.LogDebug("EmbeddingBackfillWorker idle: no embedding provider (AI disabled).");
+                return;
+            }
+        }
+
+        _logger.LogInformation("EmbeddingBackfillWorker started (batch {Batch}, pause {Pause}s)",
+            BatchSize, BatchPause.TotalSeconds);
+
+        while (!stoppingToken.IsCancellationRequested)
+        {
+            int processed;
+            try
+            {
+                processed = await ProcessBatchAsync(stoppingToken);
+            }
+            catch (OperationCanceledException) when (stoppingToken.IsCancellationRequested) { break; }
+            catch (Exception ex)
+            {
+                // Ollama hiccups must never crash the host; back off and retry.
+                _logger.LogWarning(ex, "Embedding batch failed; retrying after idle pause.");
+                processed = 0;
+            }
+
+            await Task.Delay(processed > 0 ? BatchPause : IdleRescan, stoppingToken);
+        }
+    }
+
+    /// <summary>Embeds one batch. Public-ish (internal) for direct testing.</summary>
+    internal async Task<int> ProcessBatchAsync(CancellationToken ct)
+    {
+        using var scope = _scopeFactory.CreateScope();
+        var db = scope.ServiceProvider.GetRequiredService<AppDbContext>();
+        var embeddings = scope.ServiceProvider.GetRequiredService<IEmbeddingProvider>();
+
+        var batch = await db.Emails
+            .Where(e => e.Embedding == null)
+            .OrderByDescending(e => e.SentAtUtc) // newest mail becomes searchable first
+            .Take(BatchSize)
+            .ToListAsync(ct);
+        if (batch.Count == 0) return 0;
+
+        // Subject + snippet is the semantic core; bodies are noisy (signatures, quoting)
+        // and slow to embed. Truncate defensively to keep well inside the model context.
+        var texts = batch
+            .Select(e => Truncate($"{e.Subject}\n{e.Snippet ?? e.BodyText}", 2000))
+            .ToList();
+        var vectors = await embeddings.EmbedBatchAsync(texts, ct);
+        if (vectors.Count != batch.Count)
+        {
+            _logger.LogWarning("Embedding batch returned {Got} vectors for {Want} emails; skipping batch.",
+                vectors.Count, batch.Count);
+            return 0;
+        }
+
+        for (var i = 0; i < batch.Count; i++)
+        {
+            if (vectors[i].Length == 0) continue; // provider soft-failure for one item
+            batch[i].Embedding = new Pgvector.Vector(vectors[i]);
+        }
+        await db.SaveChangesAsync(ct);
+        _logger.LogDebug("Embedded {Count} emails", batch.Count);
+        return batch.Count;
+    }
+
+    private static string Truncate(string s, int max) => s.Length <= max ? s : s[..max];
+}

src/InboxIntel.Infrastructure/DependencyInjection.cs

@@ -92,6 +92,9 @@ public static class DependencyInjection
                 break;
         }
         services.AddScoped<IAiService, AiService>();
+        // Semantic search: fills Email.Embedding in the background; no-ops when the
+        // embedding provider is unavailable (AI disabled), so lexical search is unaffected.
+        services.AddHostedService<EmbeddingBackfillWorker>();
 
         // Background worker (daily incremental sync + aggregate refresh)
         services.AddHostedService<GmailSyncWorker>();

src/InboxIntel.Infrastructure/InboxIntel.Infrastructure.csproj

@@ -4,18 +4,18 @@
     <AssemblyName>InboxIntel.Infrastructure</AssemblyName>
   </PropertyGroup>
   <ItemGroup>
-    <PackageReference Include="Microsoft.EntityFrameworkCore" Version="10.0.9" />
-    <PackageReference Include="Npgsql.EntityFrameworkCore.PostgreSQL" Version="10.0.2" />
-    <PackageReference Include="Microsoft.EntityFrameworkCore.Design" Version="10.0.9">
+    <PackageReference Include="Microsoft.EntityFrameworkCore" Version="8.0.4" />
+    <PackageReference Include="Npgsql.EntityFrameworkCore.PostgreSQL" Version="8.0.4" />
+    <PackageReference Include="Microsoft.EntityFrameworkCore.Design" Version="8.0.4">
       <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
       <PrivateAssets>all</PrivateAssets>
     </PackageReference>
     <PackageReference Include="Google.Apis.Gmail.v1" Version="1.68.0.3427" />
     <PackageReference Include="Google.Apis.Auth" Version="1.68.0" />
-    <PackageReference Include="Microsoft.AspNetCore.DataProtection" Version="10.0.9" />
-    <PackageReference Include="Microsoft.Extensions.Http" Version="10.0.9" />
-    <PackageReference Include="Microsoft.Extensions.Hosting.Abstractions" Version="10.0.9" />
-    <PackageReference Include="Pgvector.EntityFrameworkCore" Version="0.3.0" />
+    <PackageReference Include="Microsoft.AspNetCore.DataProtection" Version="8.0.7" />
+    <PackageReference Include="Microsoft.Extensions.Http" Version="8.0.0" />
+    <PackageReference Include="Microsoft.Extensions.Hosting.Abstractions" Version="8.0.0" />
+    <PackageReference Include="Pgvector.EntityFrameworkCore" Version="0.2.0" />
     <PackageReference Include="Polly" Version="8.4.1" />
     <PackageReference Include="QuestPDF" Version="2024.7.0" />
     <PackageReference Include="CsvHelper" Version="33.0.1" />
@@ -24,12 +24,15 @@
     <!-- Transitive security pins: patch known .NET 8.0.0 advisories pulled in by
          EF Core / ASP.NET / DataProtection. Remove once the parent packages ship
          these versions transitively. -->
-    <PackageReference Include="System.Text.Json" Version="10.0.9" />
-    <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="10.0.9" />
-    <PackageReference Include="System.Security.Cryptography.Xml" Version="10.0.9" />
+    <PackageReference Include="System.Text.Json" Version="8.0.6" />
+    <PackageReference Include="Microsoft.Extensions.Caching.Memory" Version="8.0.1" />
+    <PackageReference Include="System.Security.Cryptography.Xml" Version="8.0.3" />
   </ItemGroup>
   <ItemGroup>
     <ProjectReference Include="..\InboxIntel.Application\InboxIntel.Application.csproj" />
     <ProjectReference Include="..\InboxIntel.Domain\InboxIntel.Domain.csproj" />
   </ItemGroup>
+  <ItemGroup>
+    <InternalsVisibleTo Include="InboxIntel.IntegrationTests" />
+  </ItemGroup>
 </Project>

tests/InboxIntel.IntegrationTests/AuditFixesTests.cs

@@ -25,7 +25,7 @@ namespace InboxIntel.IntegrationTests;
 /// endpoints (model validation, per-user rate limits) without a real Google login.</summary>
 public class TestAuthHandler : AuthenticationHandler<AuthenticationSchemeOptions>
 {
-    public new const string Scheme = "Test";
+    public const string Scheme = "Test";
     // Stable across requests so per-user rate-limit partitions accumulate correctly.
     public static readonly string Uid = Guid.NewGuid().ToString();
 
@@ -52,9 +52,6 @@ public class AuditTestAppFactory : WebApplicationFactory<Program>
         builder.ConfigureHostConfiguration(cfg => cfg.AddInMemoryCollection(new Dictionary<string, string?>
         {
             ["Database:AutoMigrate"] = "false",
-            // Npgsql 10 eagerly validates the connection string when the DbContext is
-            // resolved (8.x was lazy); these tests never connect, but the string must parse.
-            ["ConnectionStrings:Postgres"] = "Host=localhost;Database=test;Username=test;Password=test",
             ["GoogleOAuth:ClientId"] = "test-client-id",
             ["GoogleOAuth:ClientSecret"] = "test-client-secret",
             // H-2: make the auth policy trip on the 3rd request within the window.

tests/InboxIntel.IntegrationTests/AuthEndpointsTests.cs

@@ -19,9 +19,6 @@ public class TestAppFactory : WebApplicationFactory<Program>
         builder.ConfigureHostConfiguration(cfg => cfg.AddInMemoryCollection(new Dictionary<string, string?>
         {
             ["Database:AutoMigrate"] = "false",
-            // Npgsql 10 eagerly validates the connection string when the DbContext is
-            // resolved (8.x was lazy); these tests never connect, but the string must parse.
-            ["ConnectionStrings:Postgres"] = "Host=localhost;Database=test;Username=test;Password=test",
             // Dummy OAuth creds so the Google challenge produces a real 302 redirect
             // (an empty ClientId can make the handler throw instead of redirecting).
             ["GoogleOAuth:ClientId"] = "test-client-id",

tests/InboxIntel.IntegrationTests/EmbeddingBackfillTests.cs

@@ -0,0 +1,95 @@
+using FluentAssertions;
+using InboxIntel.Application.Abstractions;
+using InboxIntel.Domain.Entities;
+using InboxIntel.Infrastructure.Ai;
+using InboxIntel.Infrastructure.Persistence;
+using Microsoft.EntityFrameworkCore;
+using Microsoft.Extensions.DependencyInjection;
+using Microsoft.Extensions.Logging.Abstractions;
+using Pgvector.EntityFrameworkCore;
+using Xunit;
+
+namespace InboxIntel.IntegrationTests;
+
+/// <summary>
+/// Semantic-search backfill: the worker embeds emails lacking an Embedding and persists the
+/// vectors. Runs against live Postgres (pgvector) since the Embedding column is ignored under
+/// the InMemory provider; the CI db-tests job provides the database. Uses a deterministic fake
+/// embedding provider — real-Ollama integration is verified separately (endpoint contract:
+/// /api/embeddings, 768 dims).
+/// </summary>
+[Trait("Category", "LiveDb")]
+[Collection("LiveDb")] // serialise LiveDb classes: concurrent MigrateAsync on a fresh DB races
+public class EmbeddingBackfillTests
+{
+    private static string? Conn => Environment.GetEnvironmentVariable("LIVEDB_CONNECTION");
+
+    private sealed class FakeCurrentUser : ICurrentUser
+    {
+        public Guid UserId => Guid.Empty; // worker scope sees all rows
+        public bool IsAuthenticated => false;
+    }
+
+    private sealed class FakeEmbeddings : IEmbeddingProvider
+    {
+        public bool IsAvailable => true;
+        public Task<float[]> EmbedAsync(string text, CancellationToken ct = default)
+            => Task.FromResult(Vec(text));
+        public Task<IReadOnlyList<float[]>> EmbedBatchAsync(IReadOnlyList<string> texts, CancellationToken ct = default)
+            => Task.FromResult<IReadOnlyList<float[]>>(texts.Select(Vec).ToList());
+        private static float[] Vec(string text)
+        {
+            var v = new float[768];
+            v[0] = text.Length; // deterministic, content-dependent
+            return v;
+        }
+    }
+
+    [Fact]
+    public async Task Worker_embeds_pending_emails_and_persists_vectors()
+    {
+        if (Conn is null) return; // soft-skip outside the live-db CI job
+        var uid = Guid.NewGuid();
+        var opts = new DbContextOptionsBuilder<AppDbContext>().UseNpgsql(Conn!, o => o.UseVector()).Options;
+
+        var services = new ServiceCollection();
+        services.AddScoped<ICurrentUser, FakeCurrentUser>();
+        services.AddScoped(_ => new AppDbContext(opts, new FakeCurrentUser()));
+        services.AddScoped<IEmbeddingProvider, FakeEmbeddings>();
+        using var sp = services.BuildServiceProvider();
+
+        using (var seed = new AppDbContext(opts, new FakeCurrentUser()))
+        {
+            await seed.Database.MigrateAsync();
+            seed.Users.Add(new User { Id = uid, GoogleSubjectId = "g" + uid, Email = uid + "@t.t" });
+            var dom = new MailDomain { UserId = uid, Name = "t.t" };
+            var snd = new Sender { UserId = uid, Address = "a@t.t", Domain = dom };
+            var thr = new MailThread { UserId = uid, GmailThreadId = "th" + uid };
+            seed.AddRange(dom, snd, thr);
+            seed.Emails.Add(new Email { UserId = uid, GmailMessageId = "e1" + uid, Subject = "hello world", Sender = snd, Thread = thr, SentAtUtc = DateTimeOffset.UtcNow });
+            seed.Emails.Add(new Email { UserId = uid, GmailMessageId = "e2" + uid, Subject = "quarterly invoice", Sender = snd, Thread = thr, SentAtUtc = DateTimeOffset.UtcNow });
+            await seed.SaveChangesAsync();
+        }
+        try
+        {
+            var worker = new EmbeddingBackfillWorker(
+                sp.GetRequiredService<IServiceScopeFactory>(), NullLogger<EmbeddingBackfillWorker>.Instance);
+            var processed = await worker.ProcessBatchAsync(CancellationToken.None);
+            processed.Should().BeGreaterThanOrEqualTo(2);
+
+            using var check = new AppDbContext(opts, new FakeCurrentUser());
+            var mine = await check.Emails.Where(e => e.UserId == uid).ToListAsync();
+            mine.Should().OnlyContain(e => e.Embedding != null);
+            mine.First().Embedding!.ToArray().Length.Should().Be(768);
+        }
+        finally
+        {
+            using var c = new AppDbContext(opts, new FakeCurrentUser());
+            await c.Emails.Where(e => e.UserId == uid).ExecuteDeleteAsync();
+            await c.Threads.Where(t => t.UserId == uid).ExecuteDeleteAsync();
+            await c.Senders.Where(s => s.UserId == uid).ExecuteDeleteAsync();
+            await c.Domains.Where(d => d.UserId == uid).ExecuteDeleteAsync();
+            await c.Users.Where(u => u.Id == uid).ExecuteDeleteAsync();
+        }
+    }
+}

tests/InboxIntel.IntegrationTests/InboxIntel.IntegrationTests.csproj

@@ -7,8 +7,8 @@
     <PackageReference Include="xunit" Version="2.9.0" />
     <PackageReference Include="xunit.runner.visualstudio" Version="2.8.2" />
     <PackageReference Include="FluentAssertions" Version="6.12.0" />
-    <PackageReference Include="Microsoft.AspNetCore.Mvc.Testing" Version="10.0.9" />
-    <PackageReference Include="Microsoft.EntityFrameworkCore.InMemory" Version="10.0.9" />
+    <PackageReference Include="Microsoft.AspNetCore.Mvc.Testing" Version="8.0.7" />
+    <PackageReference Include="Microsoft.EntityFrameworkCore.InMemory" Version="8.0.4" />
   </ItemGroup>
   <ItemGroup>
     <ProjectReference Include="..\..\src\InboxIntel.Api\InboxIntel.Api.csproj" />

tests/InboxIntel.IntegrationTests/LiveDbSearchTests.cs

@@ -21,6 +21,7 @@ namespace InboxIntel.IntegrationTests;
 /// InMemory test run is unaffected.
 /// </summary>
 [Trait("Category", "LiveDb")]
+[Collection("LiveDb")] // serialise LiveDb classes: concurrent MigrateAsync on a fresh DB races
 public class LiveDbSearchTests
 {
     private static string? Conn => Environment.GetEnvironmentVariable("LIVEDB_CONNECTION");