Inboxintel/tests/InboxIntel.IntegrationTests/EmbeddingBackfillTests.cs

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();
        }
    }
}