Compare commits

..

1 Commits

Author SHA1 Message Date
cesnimda 7b8d609185 feat(platform): feature flags + user settings foundation (RECOMMENDATIONS #10)
CI / backend (pull_request) Successful in 58s
CI / frontend (pull_request) Successful in 14s
CI / format (pull_request) Successful in 53s
CI / db-tests (pull_request) Successful in 59s
Security / secrets (pull_request) Successful in 4s
Security / dependencies (pull_request) Successful in 59s
Implements the flag/settings backend from docs/discovery/multi-provider/04:
feature_flags + user_settings tables (migration seeds behaviour-preserving
defaults, verified on a fresh real Postgres); IFeatureFlags (15s cache,
FAIL-CLOSED); IAiGate (ai.enabled master flag beats any user opt-in; absent row
= default opt-in). UserSetting tenant-filtered, PK-shared with User. 4 contract
tests; suite 59 green.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-02 17:32:55 +02:00
26 changed files with 21 additions and 309 deletions
-13
View File
@@ -1,13 +0,0 @@
# Root editor/formatter config. end_of_line=lf makes dotnet-format agree with
# .gitattributes (eol=lf) — without this, format-on-Windows wants CRLF while git
# stores LF, and the pre-commit/CI format gates flip-flop forever.
root = true
[*]
end_of_line = lf
insert_final_newline = true
charset = utf-8
[*.cs]
indent_style = space
indent_size = 4
-18
View File
@@ -52,21 +52,3 @@ jobs:
# (Vite/PostCSS/etc.) shouldn't block a merge.
working-directory: frontend
run: npm audit --omit=dev --audit-level=high
# RECOMMENDATIONS #9: SAST. Semgrep community rules for C#/JS + OWASP/secrets patterns —
# catches injection/crypto-misuse classes the other gates (gitleaks, dep-audit, tests)
# don't look for. Advisory at first (not a required check); promote once tuned.
sast:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
# The runner image lacks pip, and a semgrep job-container lacks the node that
# actions/checkout needs — so install pip via apt on the standard image.
- name: Install semgrep
run: |
sudo apt-get update -qq && sudo apt-get install -y -qq python3-pip pipx
pipx install semgrep
- name: Semgrep scan
run: |
export PATH="$HOME/.local/bin:$PATH"
semgrep scan --config p/csharp --config p/javascript --config p/security-audit --exclude 'frontend/dist' --exclude '**/bin' --exclude '**/obj' --error --quiet
-12
View File
@@ -67,8 +67,6 @@ services:
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}
# OTLP export activates only when set (e.g. http://lgtm:4317 with the observability profile).
OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_ENDPOINT:-}
# 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}
@@ -111,16 +109,6 @@ services:
# count: all
# capabilities: [gpu]
# Observability (RECOMMENDATIONS #5): all-in-one Grafana+Tempo+Prometheus+Loki.
# Enable with: docker compose --profile observability up -d
# then set OTEL_ENDPOINT=http://lgtm:4317 in deploy/.env and restart the api.
# Grafana UI: http://localhost:3000 (admin/admin on first run).
lgtm:
image: grafana/otel-lgtm
profiles: ["observability"]
ports:
- "127.0.0.1:3000:3000"
# Optional reverse proxy. Enable with: docker compose --profile proxy up
nginx:
image: nginx:alpine
-5
View File
@@ -15,11 +15,6 @@
<PackageReference Include="Asp.Versioning.Mvc" Version="8.1.0" />
<PackageReference Include="Asp.Versioning.Mvc.ApiExplorer" Version="8.1.0" />
<PackageReference Include="FluentValidation.AspNetCore" Version="11.3.0" />
<PackageReference Include="Npgsql.OpenTelemetry" Version="10.0.3" />
<PackageReference Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" Version="1.16.0" />
<PackageReference Include="OpenTelemetry.Extensions.Hosting" Version="1.16.0" />
<PackageReference Include="OpenTelemetry.Instrumentation.AspNetCore" Version="1.16.0" />
<PackageReference Include="OpenTelemetry.Instrumentation.Http" Version="1.16.0" />
<PackageReference Include="Serilog.AspNetCore" Version="8.0.1" />
<PackageReference Include="Serilog.Sinks.Console" Version="5.0.1" />
<PackageReference Include="Swashbuckle.AspNetCore" Version="6.6.2" />
-26
View File
@@ -16,10 +16,6 @@ using Microsoft.AspNetCore.HttpOverrides;
using Microsoft.AspNetCore.RateLimiting;
using Microsoft.EntityFrameworkCore;
using Microsoft.Extensions.Options;
using Npgsql;
using OpenTelemetry.Metrics;
using OpenTelemetry.Resources;
using OpenTelemetry.Trace;
using Serilog;
var builder = WebApplication.CreateBuilder(args);
@@ -126,28 +122,6 @@ builder.Services.AddAuthentication(options =>
builder.Services.AddAuthorization();
// RECOMMENDATIONS #5: OpenTelemetry traces + metrics (ASP.NET, outbound HTTP, Npgsql).
// The OTLP exporter only activates when Otel:Endpoint (or the standard
// OTEL_EXPORTER_OTLP_ENDPOINT env var) is configured — zero overhead otherwise.
// Logs stay on Serilog. Pair with the compose "observability" profile (grafana/otel-lgtm).
var otlpEndpoint = builder.Configuration["Otel:Endpoint"]
?? Environment.GetEnvironmentVariable("OTEL_EXPORTER_OTLP_ENDPOINT");
if (!string.IsNullOrWhiteSpace(otlpEndpoint))
{
builder.Services.AddOpenTelemetry()
.ConfigureResource(r => r.AddService("inboxintel-api"))
.WithTracing(t => t
.AddAspNetCoreInstrumentation()
.AddHttpClientInstrumentation()
.AddNpgsql()
.AddOtlpExporter(o => o.Endpoint = new Uri(otlpEndpoint)))
.WithMetrics(m => m
.AddAspNetCoreInstrumentation()
.AddHttpClientInstrumentation()
.AddNpgsqlInstrumentation()
.AddOtlpExporter(o => o.Endpoint = new Uri(otlpEndpoint)));
}
builder.Services.AddApiVersioning(o =>
{
o.DefaultApiVersion = new ApiVersion(1, 0);
@@ -23,9 +23,4 @@ public record SearchRequestDto(
bool? IsTrashed = null,
string? GmailLabel = null, // e.g. "SENT", "DRAFT", "SPAM"
string? Category = null, // EmailCategory name, e.g. "Finance"
long? MinSizeBytes = null,
// Keyset cursor for the date-ordered browse path (RECOMMENDATIONS #8): pass the last
// row's SentAtUtc+Id to fetch the next window without OFFSET (O(pageSize), not O(page)).
// When set, TotalCount is not recomputed (-1). Additive; offset paging still works.
DateTimeOffset? AfterSentAtUtc = null,
Guid? AfterId = null);
long? MinSizeBytes = null);
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using System;
using System;
using Microsoft.EntityFrameworkCore.Migrations;
using NpgsqlTypes;
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using System;
using System;
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Migrations;
using NpgsqlTypes;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Migrations;
using Pgvector;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -1,4 +1,4 @@
using System;
using System;
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
@@ -1,4 +1,4 @@
// <auto-generated />
// <auto-generated />
using System;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
@@ -5,7 +5,6 @@ using InboxIntel.Domain.Entities;
using InboxIntel.Domain.Enums;
using InboxIntel.Infrastructure.Persistence;
using Microsoft.EntityFrameworkCore;
using Pgvector.EntityFrameworkCore;
namespace InboxIntel.Infrastructure.Search;
@@ -19,13 +18,7 @@ namespace InboxIntel.Infrastructure.Search;
public class SearchService : ISearchService
{
private readonly AppDbContext _db;
private readonly IEmbeddingProvider? _embeddings;
public SearchService(AppDbContext db, IEmbeddingProvider? embeddings = null)
{
_db = db;
_embeddings = embeddings;
}
public SearchService(AppDbContext db) => _db = db;
public async Task<PagedResult<EmailSummaryDto>> SearchAsync(Guid userId, SearchRequestDto r, CancellationToken ct = default)
{
@@ -80,18 +73,6 @@ public class SearchService : ISearchService
var total = await matched.CountAsync(ct);
// Hybrid semantic fusion (docs/discovery/05): when embeddings are available, fuse
// lexical top-K with vector top-K via Reciprocal Rank Fusion. Runs BEFORE the fuzzy
// fallback so a query with ZERO lexical hits (pure semantic recall — "gym receipt"
// phrased differently) still surfaces results. Exact lexical hits keep winning (they
// rank in both lists). Deeper pages fall through to lexical paging; any failure
// (Ollama down, nothing embedded yet) silently degrades to the lexical/fuzzy path.
if (hasFreeTextQuery && _embeddings is { IsAvailable: true })
{
var hybrid = await TryHybridAsync(structured, matched, term, total, r, ct);
if (hybrid is not null) return hybrid;
}
// Fuzzy/typo fallback: ONLY when a free-text search found nothing exact. word_similarity
// with an explicit 0.3 threshold — pg_trgm's default 0.6 misses real typos
// ("recieved" -> "received" scores ~0.39). Rare path, so the (non-indexed) scan over the
@@ -114,23 +95,9 @@ public class SearchService : ISearchService
ranked = matched.OrderByDescending(e => e.SearchVector!.RankCoverDensity(EF.Functions.WebSearchToTsQuery("english", term)))
.ThenByDescending(e => e.SentAtUtc);
else
ranked = matched.OrderByDescending(e => e.SentAtUtc).ThenByDescending(e => e.Id);
ranked = matched.OrderByDescending(e => e.SentAtUtc);
// Keyset (cursor) pagination for the browse path: O(pageSize) regardless of depth,
// vs OFFSET's O(page*pageSize). The (SentAtUtc, Id) pair with the Id tie-break above
// makes the ordering total, so windows never duplicate or skip rows.
IQueryable<Email> paged;
if (!hasFreeTextQuery && r is { AfterSentAtUtc: { } afterAt, AfterId: { } afterId })
{
paged = ranked
.Where(e => e.SentAtUtc < afterAt || (e.SentAtUtc == afterAt && e.Id.CompareTo(afterId) < 0))
.Take(r.PageSize);
total = -1; // not recomputed on cursor windows (that's the point)
}
else
{
paged = ranked.Skip((r.Page - 1) * r.PageSize).Take(r.PageSize);
}
var paged = ranked.Skip((r.Page - 1) * r.PageSize).Take(r.PageSize);
// "Why this matched" ts_headline only for EXACT free-text hits (fuzzy/browse get no
// highlight — a fuzzy hit has no literal match to headline). Unconditional projections
@@ -170,73 +137,4 @@ public class SearchService : ISearchService
TotalCount = total
};
}
private const int HybridK = 50; // candidates taken from each layer
private const int RrfConstant = 60; // standard RRF dampening constant
/// <summary>
/// RRF fusion of lexical and vector candidates. Returns null when the requested page
/// lies beyond the fused window or anything fails — caller falls back to lexical.
/// </summary>
private async Task<PagedResult<EmailSummaryDto>?> TryHybridAsync(
IQueryable<Email> structured, IQueryable<Email> lexical, string term, int lexicalTotal,
SearchRequestDto r, CancellationToken ct)
{
try
{
var lexIds = await lexical
.OrderByDescending(e => e.SearchVector!.RankCoverDensity(EF.Functions.WebSearchToTsQuery("english", term)))
.ThenByDescending(e => e.SentAtUtc)
.Take(HybridK).Select(e => e.Id).ToListAsync(ct);
var queryVec = await _embeddings!.EmbedAsync(term, ct);
List<Guid> vecIds = new();
if (queryVec.Length > 0)
{
var qv = new Pgvector.Vector(queryVec);
vecIds = await structured
.Where(e => e.Embedding != null)
.OrderBy(e => e.Embedding!.CosineDistance(qv))
.Take(HybridK).Select(e => e.Id).ToListAsync(ct);
}
if (vecIds.Count == 0) return null; // nothing embedded yet → lexical path
var scores = new Dictionary<Guid, double>();
for (var i = 0; i < lexIds.Count; i++)
scores[lexIds[i]] = scores.GetValueOrDefault(lexIds[i]) + 1.0 / (RrfConstant + i + 1);
for (var i = 0; i < vecIds.Count; i++)
scores[vecIds[i]] = scores.GetValueOrDefault(vecIds[i]) + 1.0 / (RrfConstant + i + 1);
var fused = scores.OrderByDescending(kv => kv.Value).Select(kv => kv.Key).ToList();
var pageIds = fused.Skip((r.Page - 1) * r.PageSize).Take(r.PageSize).ToList();
if (pageIds.Count == 0 && r.Page > 1) return null; // deep page → lexical paging
var headlineOpts =
$"StartSel={(char)0xE000},StopSel={(char)0xE001},MaxWords=16,MinWords=5,ShortWord=2,HighlightAll=false";
var rows = await _db.Emails.AsNoTracking()
.Where(e => pageIds.Contains(e.Id))
.Select(e => new EmailSummaryDto(
e.Id, e.GmailMessageId, e.Subject, e.Snippet,
e.Sender!.Address, e.Sender.DisplayName, e.SentAtUtc,
e.IsUnread, e.IsStarred, e.HasAttachments, e.SizeEstimateBytes, e.Category,
e.HasListUnsubscribe, e.SupportsOneClickUnsubscribe,
EF.Functions.WebSearchToTsQuery("english", term).GetResultHeadline("english", e.BodyText ?? "", headlineOpts)))
.ToListAsync(ct);
var byId = rows.ToDictionary(x => x.Id);
var items = pageIds.Where(byId.ContainsKey).Select(id => byId[id]).ToList();
return new PagedResult<EmailSummaryDto>
{
Items = items,
Page = r.Page,
PageSize = r.PageSize,
// Semantic recall can exceed the lexical match count.
TotalCount = Math.Max(lexicalTotal, fused.Count)
};
}
catch
{
return null; // AI must never break search — degrade to lexical
}
}
}
@@ -1,57 +0,0 @@
using FluentAssertions;
using InboxIntel.Application.Abstractions;
using InboxIntel.Application.DTOs;
using InboxIntel.Domain.Entities;
using InboxIntel.Infrastructure.Persistence;
using InboxIntel.Infrastructure.Search;
using Microsoft.EntityFrameworkCore;
using Xunit;
namespace InboxIntel.IntegrationTests;
/// <summary>
/// RECOMMENDATIONS #8: keyset (cursor) pagination for the browse path — the window after a
/// (SentAtUtc, Id) cursor returns the next rows with no duplicates/skips and no OFFSET scan.
/// </summary>
public class KeysetPaginationTests
{
private sealed class FakeCurrentUser : ICurrentUser
{
public Guid UserId { get; set; }
public bool IsAuthenticated => UserId != Guid.Empty;
}
[Fact]
public async Task Cursor_window_continues_exactly_after_the_previous_page()
{
var user = Guid.NewGuid();
var opts = new DbContextOptionsBuilder<AppDbContext>()
.UseInMemoryDatabase(nameof(Cursor_window_continues_exactly_after_the_previous_page)).Options;
var baseline = DateTimeOffset.UtcNow;
using (var seed = new AppDbContext(opts, new FakeCurrentUser()))
{
var sender = new Sender { UserId = user, Address = "s@x.x" };
seed.Senders.Add(sender);
for (var i = 0; i < 5; i++)
seed.Emails.Add(new Email { UserId = user, GmailMessageId = $"m{i}", Sender = sender, SentAtUtc = baseline.AddMinutes(-i) });
await seed.SaveChangesAsync();
}
using var ctx = new AppDbContext(opts, new FakeCurrentUser { UserId = user });
var svc = new SearchService(ctx);
// First window via offset (page 1, size 2): m0, m1 (newest first).
var page1 = await svc.SearchAsync(user, new SearchRequestDto(null, null, null, null, null, null, null, false, 1, 2));
page1.Items.Select(i => i.GmailMessageId).Should().Equal("m0", "m1");
// Next window via cursor from the last row of page 1.
var last = page1.Items[^1];
var page2 = await svc.SearchAsync(user, new SearchRequestDto(
null, null, null, null, null, null, null, false, 1, 2,
AfterSentAtUtc: last.SentAtUtc, AfterId: last.Id));
page2.Items.Select(i => i.GmailMessageId).Should().Equal("m2", "m3"); // no dupes, no skips
page2.TotalCount.Should().Be(-1, "cursor windows skip the COUNT — that's the perf win");
}
}
@@ -123,54 +123,4 @@ public class LiveDbSearchTests
}
finally { await CleanupAsync(opts, uid); }
}
private sealed class DirectionalFakeEmbeddings : IEmbeddingProvider
{
public bool IsAvailable => true;
public Task<float[]> EmbedAsync(string text, CancellationToken ct = default)
{
// Deterministic "semantics": anything fruit-flavoured points one way, else the other.
var v = new float[768];
if (text.Contains("banana") || text.Contains("tropical")) v[0] = 1; else v[1] = 1;
return Task.FromResult(v);
}
public async Task<IReadOnlyList<float[]>> EmbedBatchAsync(IReadOnlyList<string> texts, CancellationToken ct = default)
{
var list = new List<float[]>();
foreach (var t in texts) list.Add(await EmbedAsync(t, ct));
return list;
}
}
[Fact]
public async Task Hybrid_search_surfaces_semantic_match_with_zero_keyword_overlap()
{
if (Conn is null) return;
var opts = Options();
var uid = await SeedAsync(opts);
try
{
var embeddings = new DirectionalFakeEmbeddings();
using (var prep = new AppDbContext(opts, new FakeCurrentUser()))
{
// "Weekly notes" gets a fruit-direction embedding (semantically related to the
// query); "Invoice March" points elsewhere. Neither subject contains "banana".
var near = await prep.Emails.FirstAsync(e => e.UserId == uid && e.Subject == "Weekly notes");
near.Embedding = new Vector(await embeddings.EmbedAsync("tropical"));
var far = await prep.Emails.FirstAsync(e => e.UserId == uid && e.Subject == "Invoice March");
far.Embedding = new Vector(await embeddings.EmbedAsync("finance"));
await prep.SaveChangesAsync();
}
using var ctx = new AppDbContext(opts, new FakeCurrentUser { UserId = uid });
var res = await new SearchService(ctx, embeddings)
.SearchAsync(uid, GmailQueryParser.Parse("banana", 1, 10));
// Zero lexical hits for "banana" — hybrid must still surface the semantically
// nearest email, ranked first.
res.Items.Should().NotBeEmpty("semantic recall should fire with zero keyword overlap");
res.Items[0].Subject.Should().Be("Weekly notes");
}
finally { await CleanupAsync(opts, uid); }
}
}