feat(openzaak): bounded retry + flagged write divergence (WP-60)

Local aanvraag/document writes and their paired ZGW writes aren't transactional; a ZGW failure after the local write succeeds used to diverge silently. ZgwHttpClient now retries transport-shaped failures (not 500, which can follow a partial commit on the non-idempotent statussen/rollen POSTs), and a ZGW failure that survives retry sets Aanvraag.ZgwError plus a zgw:divergence audit row instead of failing or diverging quietly. No outbox/reconcile job: three request-triggered write paths don't justify a persisted queue that would also need to carry citizen PII for the JWT audit claims. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-30 18:11:55 +02:00
parent 67abc58052
commit 3ff80c124f
18 changed files with 855 additions and 82 deletions
@@ -33,6 +33,13 @@ public sealed class Aanvraag
  /// endpoint does, via <see cref="ApplicationStore.SetZaakUrl"/>) to keep the seam's write
  /// surface at "return data", not "reach into another store".</summary>
  public string? ZaakUrl { get; set; }
+
+  /// <summary>WP-60: non-null means the ZGW side of this submit (or its document link) did not
+  /// complete — the local aanvraag is authoritative and is NOT rolled back (that risks an
+  /// orphan zaak if the failure landed after the zaak POST succeeded). The zaak, if it exists,
+  /// is re-findable by <c>identificatie == Referentie</c>. Cleared by a future repair path;
+  /// none exists yet (see openzaak-integration.md's "Write resilience" section).</summary>
+  public string? ZgwError { get; set; }
 }

 /// <summary>
@@ -193,4 +200,18 @@ public static class ApplicationStore
      db.SaveChanges();
    }
  }
+
+  /// <summary>Flag (or clear, once a repair path exists) that this aanvraag's ZGW write did
+  /// not complete — see <see cref="Aanvraag.ZgwError"/>. No-op if the aanvraag is gone.</summary>
+  public static void SetZgwError(string id, string? error)
+  {
+    lock (_gate)
+    {
+      using var db = Db.Create();
+      var a = db.Applications.Find(id);
+      if (a is null) return;
+      a.ZgwError = error;
+      db.SaveChanges();
+    }
+  }
 }
@@ -0,0 +1,282 @@
+// <auto-generated />
+using System;
+using BigRegister.Api.Data;
+using Microsoft.EntityFrameworkCore;
+using Microsoft.EntityFrameworkCore.Infrastructure;
+using Microsoft.EntityFrameworkCore.Migrations;
+using Microsoft.EntityFrameworkCore.Storage.ValueConversion;
+
+#nullable disable
+
+namespace BigRegister.Api.Data.Migrations
+{
+    [DbContext(typeof(AppDbContext))]
+    [Migration("20260730155659_ZgwSyncError")]
+    partial class ZgwSyncError
+    {
+        /// <inheritdoc />
+        protected override void BuildTargetModel(ModelBuilder modelBuilder)
+        {
+#pragma warning disable 612, 618
+            modelBuilder.HasAnnotation("ProductVersion", "10.0.9");
+
+            modelBuilder.Entity("BigRegister.Api.Data.Aanvraag", b =>
+                {
+                    b.Property<string>("Id")
+                        .HasColumnType("TEXT");
+
+                    b.Property<bool>("AutoApprovable")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<DateTimeOffset>("CreatedAt")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("DocumentIds")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Draft")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Owner")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Reden")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Referentie")
+                        .HasColumnType("TEXT");
+
+                    b.Property<int>("StepCount")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<int>("StepIndex")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<bool>("Submitted")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<DateTimeOffset?>("SubmittedAt")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Type")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<DateTimeOffset>("UpdatedAt")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("ZaakUrl")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("ZgwError")
+                        .HasColumnType("TEXT");
+
+                    b.HasKey("Id");
+
+                    b.ToTable("Applications");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.AuditEntry", b =>
+                {
+                    b.Property<long>("Id")
+                        .ValueGeneratedOnAdd()
+                        .HasColumnType("INTEGER");
+
+                    b.Property<string>("Action")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Actor")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<DateTimeOffset>("At")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("CategoryId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("DocumentId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.HasKey("Id");
+
+                    b.ToTable("AuditEntries");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.AuthzAuditEntry", b =>
+                {
+                    b.Property<long>("Id")
+                        .ValueGeneratedOnAdd()
+                        .HasColumnType("INTEGER");
+
+                    b.Property<string>("Action")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<DateTimeOffset>("At")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("CorrelationId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Decision")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Resource")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Role")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.HasKey("Id");
+
+                    b.ToTable("AuthzAudit");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.BriefEntity", b =>
+                {
+                    b.Property<string>("BriefId")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("ArchivedHtml")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Beroep")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("DrafterId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Owner")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Placeholders")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Sections")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<int?>("SentOrgTemplateVersion")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<string>("Status")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("SubOrgId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("TemplateId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.HasKey("BriefId");
+
+                    b.HasIndex("Owner")
+                        .IsUnique();
+
+                    b.ToTable("Briefs");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.FeatureFlagEntity", b =>
+                {
+                    b.Property<string>("Key")
+                        .HasColumnType("TEXT");
+
+                    b.Property<bool>("Enabled")
+                        .HasColumnType("INTEGER");
+
+                    b.HasKey("Key");
+
+                    b.ToTable("FeatureFlags");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.OrgTemplateEntity", b =>
+                {
+                    b.Property<string>("SubOrgId")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Draft")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("History")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<int>("PublishedVersion")
+                        .HasColumnType("INTEGER");
+
+                    b.HasKey("SubOrgId");
+
+                    b.ToTable("OrgTemplates");
+                });
+
+            modelBuilder.Entity("BigRegister.Api.Data.StoredDocument", b =>
+                {
+                    b.Property<string>("DocumentId")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("CategoryId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<byte[]>("Content")
+                        .IsRequired()
+                        .HasColumnType("BLOB");
+
+                    b.Property<string>("ContentType")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("DrcUrl")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("FileName")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<bool>("Linked")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<string>("LocalId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("Owner")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.Property<long>("SizeBytes")
+                        .HasColumnType("INTEGER");
+
+                    b.Property<DateTimeOffset>("UploadedAt")
+                        .HasColumnType("TEXT");
+
+                    b.Property<string>("WizardId")
+                        .IsRequired()
+                        .HasColumnType("TEXT");
+
+                    b.HasKey("DocumentId");
+
+                    b.ToTable("Documents");
+                });
+#pragma warning restore 612, 618
+        }
+    }
+}
@@ -0,0 +1,28 @@
+using Microsoft.EntityFrameworkCore.Migrations;
+
+#nullable disable
+
+namespace BigRegister.Api.Data.Migrations
+{
+  /// <inheritdoc />
+  public partial class ZgwSyncError : Migration
+  {
+    /// <inheritdoc />
+    protected override void Up(MigrationBuilder migrationBuilder)
+    {
+      migrationBuilder.AddColumn<string>(
+          name: "ZgwError",
+          table: "Applications",
+          type: "TEXT",
+          nullable: true);
+    }
+
+    /// <inheritdoc />
+    protected override void Down(MigrationBuilder migrationBuilder)
+    {
+      migrationBuilder.DropColumn(
+          name: "ZgwError",
+          table: "Applications");
+    }
+  }
+}
@@ -67,6 +67,9 @@ namespace BigRegister.Api.Data.Migrations
                    b.Property<string>("ZaakUrl")
                        .HasColumnType("TEXT");

+                    b.Property<string>("ZgwError")
+                        .HasColumnType("TEXT");
+
                    b.HasKey("Id");

                    b.ToTable("Applications");
@@ -58,9 +58,12 @@ if (zgw.Enabled)
 {
  builder.Services.AddSingleton(zgw);
  builder.Services.AddSingleton<ZgwTokenProvider>();
-  builder.Services.AddHttpClient<IZaakSource, OpenZaakZaakSource>();
+  // WP-60: a bounded client timeout matters once ZgwHttpClient retries — without one, the
+  // sources' sync-over-async call (no CancellationToken threaded through) could block a
+  // thread-pool thread for HttpClient's 100s default times 3 attempts.
+  builder.Services.AddHttpClient<IZaakSource, OpenZaakZaakSource>(c => c.Timeout = TimeSpan.FromSeconds(15));
  // WP-51: the documents (Documenten API / DRC) seam — same pattern as IZaakSource above.
-  builder.Services.AddHttpClient<IDocumentSource, OpenZaakDocumentSource>();
+  builder.Services.AddHttpClient<IDocumentSource, OpenZaakDocumentSource>(c => c.Timeout = TimeSpan.FromSeconds(15));
 }
 else
 {
@@ -351,13 +354,38 @@ api.MapPost("/applications/{id}/submit", (string id, SubmitApplicationRequest re
  // in OpenZaak and maps its result back into this same response shape (ADR-0001/ADR-0005:
  // zero FE contract change either way). WP-53: the caller is threaded through so the minted
  // ZGW JWT's user_id/user_representation reflect the acting citizen, not a static config value.
-  var (referentie, status, zaakUrl) = zaken.CreateZaak(submitted, DateTimeOffset.UtcNow, ctx.Caller());
-  if (zaakUrl is not null) ApplicationStore.SetZaakUrl(id, zaakUrl);
+  //
+  // WP-60: the local submit above already committed — it is never rolled back on a ZGW
+  // failure (an orphan zaak from a rolled-back-then-retried submit is worse than a flagged
+  // one, see openzaak-integration.md's "Write resilience" section). Each ZGW half is caught
+  // separately so a create-zaak failure doesn't also skip the (still-local) document link.
+  var referentie = submitted.Referentie!;
+  var status = submitted.ToStatusDto(DateTimeOffset.UtcNow);
+  string? zaakUrl = null;
+  try
+  {
+    (referentie, status, zaakUrl) = zaken.CreateZaak(submitted, DateTimeOffset.UtcNow, ctx.Caller());
+    if (zaakUrl is not null) ApplicationStore.SetZaakUrl(id, zaakUrl);
+  }
+  catch (Exception ex)
+  {
+    RecordZgwDivergence(ctx, id, referentie, ex);
+  }

  // WP-51: link the submitted documents to the zaak — LocalDocumentSource is exactly the
  // DocumentStore.Link call this used to make inline; OpenZaakDocumentSource additionally
  // POSTs a zaakinformatieobject per document, now that the zaak (zaakUrl) exists.
-  if (documentIds is not null) documents.LinkToZaak(documentIds, zaakUrl, ctx.Caller());
+  if (documentIds is not null)
+  {
+    try
+    {
+      documents.LinkToZaak(documentIds, zaakUrl, ctx.Caller());
+    }
+    catch (Exception ex)
+    {
+      RecordZgwDivergence(ctx, id, referentie, ex);
+    }
+  }

  return Results.Ok(new SubmitApplicationResponse(referentie, status));
 })
@@ -676,6 +704,18 @@ void AuditAuthz(HttpContext ctx, string action, string resource, bool allowed, P
  AuthzAuditStore.Record(action, resource, allowed, principal.Role.ToString(), cid);
 }

+// WP-60: the local write already committed — this records that its ZGW counterpart didn't,
+// rather than letting the two sides diverge silently (openzaak-integration.md's "Write
+// resilience" section). Same audit trail AuditAuthz writes to (/beheer/audit), so a
+// divergence is visible next to every other decision, not a separate mechanism.
+void RecordZgwDivergence(HttpContext ctx, string id, string referentie, Exception ex)
+{
+  app.Logger.LogError(ex, "zgw divergence aanvraag={Id} reference={Reference}", id, referentie);
+  ApplicationStore.SetZgwError(id, ex.Message);
+  var cid = ctx.Items.TryGetValue("CorrelationId", out var v) ? (string)v! : "none";
+  AuthzAuditStore.Record("zgw:divergence", referentie, allowed: false, Authz.ResolvePrincipal(ctx).Role.ToString(), cid);
+}
+
 // Keep the last `keep` characters, mask the rest — mirrors the FE maskTail
 // (src/app/shared/ui/debug-state/mask.ts) so wire redaction and the dev panel agree.
 static string MaskTail(string value, int keep) =>
@@ -4,6 +4,7 @@ using BigRegister.Api.Contracts;
 using BigRegister.Api.Data;
 using BigRegister.Domain.Authorization;
 using BigRegister.Stamdata;
+using Microsoft.Extensions.Logging;

 namespace BigRegister.Api.Zgw;

@@ -20,7 +21,9 @@ namespace BigRegister.Api.Zgw;
 /// <see cref="OpenZaakZaakSource"/> — creating a document needs write scope on Documenten;
 /// linking one to a zaak needs write scope on Zaken (the zaakinformatieobject resource).
 /// </summary>
-public sealed class OpenZaakDocumentSource(HttpClient http, ZgwTokenProvider tokens, ZgwOptions options) : IDocumentSource
+public sealed class OpenZaakDocumentSource(
+    HttpClient http, ZgwTokenProvider tokens, ZgwOptions options, ILogger<OpenZaakDocumentSource>? log = null)
+    : IDocumentSource
 {
  private readonly ZgwHttpClient zgw = new(http, tokens);

@@ -41,37 +44,54 @@ public sealed class OpenZaakDocumentSource(HttpClient http, ZgwTokenProvider tok
      UploadAsync(localId, categoryId, wizardId, fileName, contentType, content, caller)
          .GetAwaiter().GetResult();

+  // WP-60: once DocumentStore.Add (below) has committed, the local document is the record of
+  // truth (per the class doc above) — a ZGW failure past that point is caught, logged, and
+  // leaves DrcUrl null rather than throwing. DrcUrl == null is already the meaningful "not
+  // registered in ZGW yet" detector LinkToZaak skips on, so no separate flag column is needed
+  // here the way ApplicationStore.ZgwError is for the zaak side (see openzaak-integration.md's
+  // "Write resilience" section for why the two write paths differ).
  private async Task<UploadResponse> UploadAsync(
      string localId, string categoryId, string wizardId, string fileName, string contentType,
      byte[] content, CallerIdentity caller)
  {
    var doc = DocumentStore.Add(localId, categoryId, wizardId, fileName, contentType, content, caller.Bsn);

-    if (!options.InformatieobjecttypeUrls.TryGetValue(categoryId, out var informatieobjecttypeUrl))
-      throw new InvalidOperationException(
-          $"Zgw:InformatieobjecttypeUrls has no entry for category '{categoryId}'.");
+    try
+    {
+      if (!options.InformatieobjecttypeUrls.TryGetValue(categoryId, out var informatieobjecttypeUrl))
+        throw new InvalidOperationException(
+            $"Zgw:InformatieobjecttypeUrls has no entry for category '{categoryId}'.");

-    var eio = await zgw.PostAsync<Eio>($"{options.DrcBaseUrl}/enkelvoudiginformatieobjecten", new CreateEioRequest(
-        Bronorganisatie: options.Bronorganisatie,
-        Creatiedatum: DateOnly.FromDateTime(doc.UploadedAt.UtcDateTime),
-        Titel: fileName,
-        Auteur: options.UserRepresentation,
-        Taal: "nld",
-        Formaat: contentType,
-        Bestandsnaam: fileName,
-        Inhoud: Convert.ToBase64String(content),
-        Informatieobjecttype: informatieobjecttypeUrl,
-        Identificatie: doc.DocumentId,
-        Vertrouwelijkheidaanduiding: ConfidentialiteitFor(categoryId)), caller);
+      var eio = await zgw.PostAsync<Eio>($"{options.DrcBaseUrl}/enkelvoudiginformatieobjecten", new CreateEioRequest(
+          Bronorganisatie: options.Bronorganisatie,
+          Creatiedatum: DateOnly.FromDateTime(doc.UploadedAt.UtcDateTime),
+          Titel: fileName,
+          Auteur: options.UserRepresentation,
+          Taal: "nld",
+          Formaat: contentType,
+          Bestandsnaam: fileName,
+          Inhoud: Convert.ToBase64String(content),
+          Informatieobjecttype: informatieobjecttypeUrl,
+          Identificatie: doc.DocumentId,
+          Vertrouwelijkheidaanduiding: ConfidentialiteitFor(categoryId)), caller);
+
+      DocumentStore.SetDrcUrl(doc.DocumentId, eio.Url);
+    }
+    catch (Exception ex)
+    {
+      log?.LogError(ex, "zgw divergence document={DocumentId} category={CategoryId}", doc.DocumentId, categoryId);
+    }

-    DocumentStore.SetDrcUrl(doc.DocumentId, eio.Url);
    return new UploadResponse(doc.DocumentId, doc.LocalId);
  }

  /// <summary>Local link always happens (dual-write, same reasoning as upload); additionally,
  /// once a zaak exists, POST a zaakinformatieobject for every document that has a DRC url —
  /// documents uploaded before Zgw:Enabled was ever true (or under a config gap) simply have
-  /// no DrcUrl yet and are skipped, matching "nothing extra to link" for the local case.</summary>
+  /// no DrcUrl yet and are skipped, matching "nothing extra to link" for the local case.
+  /// WP-60: unlike Upload, a ZGW failure here still throws — DocumentStore.Link (the local
+  /// half) already ran above, so the caller (Program.cs's submit endpoint) catching this and
+  /// recording it as a flagged divergence is what closes the gap, not a try/catch in here.</summary>
  public void LinkToZaak(IReadOnlyList<string> documentIds, string? zaakUrl, CallerIdentity caller)
  {
    DocumentStore.Link(documentIds);
@@ -86,10 +86,12 @@ public sealed class OpenZaakZaakSource(HttpClient http, ZgwTokenProvider tokens,
  /// reason as <see cref="ListCases"/> (see the ponytail note there) — a submit is already a
  /// single request/response round trip, so no extra concurrency concern.
  ///
-  /// ponytail: no compensating transaction — if any ZGW call here throws, the aanvraag is
-  /// already marked Submitted locally (ApplicationStore.Submit already ran) but has no zaak.
-  /// Acceptable for a first write slice against a demo backend; a production arc would need a
-  /// retry/reconciliation story (or an outbox) before this dual-write can be trusted.
+  /// WP-60: still no compensating transaction — if any call here throws (after
+  /// <see cref="ZgwHttpClient"/>'s retry gives up), the aanvraag stays Submitted locally with
+  /// no zaak; rolling it back risks an orphan zaak if the failure landed after the zaak POST
+  /// succeeded. The caller (Program.cs's submit endpoint) catches this and records it as a
+  /// flagged divergence (Aanvraag.ZgwError) instead of letting it fail (or diverge) silently —
+  /// see openzaak-integration.md's "Write resilience" section.
  public (string Referentie, AanvraagStatusDto Status, string? ZaakUrl) CreateZaak(Aanvraag aanvraag, DateTimeOffset now, CallerIdentity caller) =>
      CreateZaakAsync(aanvraag, now, caller).GetAwaiter().GetResult();

@@ -1,3 +1,4 @@
+using System.Net;
 using System.Net.Http.Headers;
 using System.Net.Http.Json;
 using BigRegister.Domain.Authorization;
@@ -14,26 +15,77 @@ namespace BigRegister.Api.Zgw;
 /// </summary>
 internal sealed class ZgwHttpClient(HttpClient http, ZgwTokenProvider tokens)
 {
+  // WP-60: bounded retry for transport-shaped failures only (gateway restarts, timeouts) —
+  // never a substitute for reconciliation. 3 attempts, doubling from 200ms.
+  private const int MaxAttempts = 3;
+  private static readonly TimeSpan BaseDelay = TimeSpan.FromMilliseconds(200);
+
  public async Task<T> GetAsync<T>(string url, CallerIdentity? caller = null)
  {
-    using var req = new HttpRequestMessage(HttpMethod.Get, url);
-    Authorize(req, caller);
-    using var res = await http.SendAsync(req);
-    res.EnsureSuccessStatusCode();
+    using var res = await SendWithRetryAsync(() => new HttpRequestMessage(HttpMethod.Get, url), caller);
    return (await res.Content.ReadFromJsonAsync<T>())
        ?? throw new InvalidOperationException($"ZGW GET {url} returned null body.");
  }

  public async Task<T> PostAsync<T>(string url, object body, CallerIdentity? caller = null)
  {
-    using var req = new HttpRequestMessage(HttpMethod.Post, url) { Content = JsonContent.Create(body) };
-    Authorize(req, caller);
-    using var res = await http.SendAsync(req);
-    res.EnsureSuccessStatusCode();
+    using var res = await SendWithRetryAsync(
+        () => new HttpRequestMessage(HttpMethod.Post, url) { Content = JsonContent.Create(body) }, caller);
    return (await res.Content.ReadFromJsonAsync<T>())
        ?? throw new InvalidOperationException($"ZGW POST {url} returned null body.");
  }

+  /// <summary>
+  /// A fresh <see cref="HttpRequestMessage"/> (and JWT) per attempt — a sent request/content
+  /// cannot be resent. Only transport-shaped failures are retried (429/502/503/504/408, plus
+  /// connection errors and timeouts); 500 is deliberately excluded because it can follow a
+  /// partial commit on the two non-idempotent ZGW POSTs (<c>/statussen</c>, <c>/rollen</c>) and
+  /// retrying risks a duplicate write — the create-zaak/document POSTs are additionally
+  /// protected by OpenZaak's own uniqueness constraint on (bronorganisatie, identificatie).
+  /// A non-transient (or exhausted) failure throws with the status + a body snippet, which
+  /// <c>Program.cs</c>'s submit endpoint catches and records as a flagged divergence rather
+  /// than letting it diverge silently (see openzaak-integration.md's "Write resilience" section).
+  /// </summary>
+  private async Task<HttpResponseMessage> SendWithRetryAsync(Func<HttpRequestMessage> newRequest, CallerIdentity? caller)
+  {
+    for (var attempt = 1; ; attempt++)
+    {
+      using var req = newRequest();
+      Authorize(req, caller);
+
+      HttpResponseMessage res;
+      try
+      {
+        res = await http.SendAsync(req);
+      }
+      catch (Exception ex) when (attempt < MaxAttempts && ex is HttpRequestException or TaskCanceledException)
+      {
+        await Task.Delay(BaseDelay * (1 << (attempt - 1)));
+        continue;
+      }
+
+      if (res.IsSuccessStatusCode) return res;
+
+      if (attempt < MaxAttempts && IsTransient(res.StatusCode))
+      {
+        res.Dispose();
+        await Task.Delay(BaseDelay * (1 << (attempt - 1)));
+        continue;
+      }
+
+      var body = await res.Content.ReadAsStringAsync();
+      var snippet = body.Length > 500 ? body[..500] : body;
+      var message = $"ZGW {req.Method} {req.RequestUri} failed: {(int)res.StatusCode} {snippet}";
+      var status = res.StatusCode;
+      res.Dispose();
+      throw new HttpRequestException(message, null, status);
+    }
+  }
+
+  private static bool IsTransient(HttpStatusCode status) => status is
+      HttpStatusCode.RequestTimeout or HttpStatusCode.TooManyRequests or
+      HttpStatusCode.BadGateway or HttpStatusCode.ServiceUnavailable or HttpStatusCode.GatewayTimeout;
+
  private void Authorize(HttpRequestMessage req, CallerIdentity? caller)
  {
    req.Headers.Authorization = new AuthenticationHeaderValue("Bearer", caller is null ? tokens.Mint() : tokens.Mint(caller));
@@ -1,3 +1,4 @@
+using System.Net;
 using BigRegister.Api.Data;
 using BigRegister.Api.Zgw;
 using BigRegister.Domain.Authorization;
@@ -77,15 +78,38 @@ public class OpenZaakDocumentSourceTests
    Assert.Contains("\"vertrouwelijkheidaanduiding\":\"openbaar\"", body);
  }

+  // WP-60: once DocumentStore.Add has committed, a ZGW-side failure (config gap or transport)
+  // no longer throws — the local document is authoritative and DrcUrl stays null (the same
+  // detector LinkToZaak already skips on for pre-Zgw documents).
+
  [Fact]
-  public void Upload_throws_when_the_category_has_no_configured_informatieobjecttype()
+  public void Upload_keeps_the_local_document_when_the_category_has_no_configured_informatieobjecttype()
  {
    var options = Options();
    var handler = new ZgwStubHandler(url => throw new InvalidOperationException($"no HTTP call expected, got {url}"));
    var source = new OpenZaakDocumentSource(new HttpClient(handler), new ZgwTokenProvider(options), options);

-    Assert.Throws<InvalidOperationException>(() =>
-        source.Upload("local-1", "unknown-category", "registratie", "f.pdf", "application/pdf", [1, 2, 3], Caller));
+    var response = source.Upload("local-1", "unknown-category", "registratie", "f.pdf", "application/pdf", [1, 2, 3], Caller);
+
+    Assert.Equal("local-1", response.LocalId);
+    Assert.Empty(handler.Requests);
+    Assert.Null(DocumentStore.Get(response.DocumentId)!.DrcUrl);
+  }
+
+  [Fact]
+  public void Upload_keeps_the_local_document_and_does_not_throw_when_drc_rejects_it()
+  {
+    var options = Options();
+    var handler = new ZgwStubHandler(
+        url => throw new InvalidOperationException($"unexpected success body requested for {url}"),
+        (_, _) => HttpStatusCode.BadRequest);
+    var source = new OpenZaakDocumentSource(new HttpClient(handler), new ZgwTokenProvider(options), options);
+
+    var response = source.Upload("local-1", "identiteit", "registratie", "paspoort.pdf", "application/pdf",
+        "%PDF-1.4 fake"u8.ToArray(), Caller);
+
+    Assert.Equal("local-1", response.LocalId);
+    Assert.Null(DocumentStore.Get(response.DocumentId)!.DrcUrl);
  }

  [Fact]
@@ -1,3 +1,4 @@
+using System.Net;
 using BigRegister.Api.Data;
 using BigRegister.Api.Zgw;
 using BigRegister.Domain.Authorization;
@@ -159,4 +160,95 @@ public class OpenZaakZaakSourceTests

    Assert.Throws<InvalidOperationException>(() => source.CreateZaak(aanvraag, DateTimeOffset.UtcNow, caller));
  }
+
+  // --- WP-60: bounded retry in ZgwHttpClient, exercised through the create-zaak write path ---
+
+  private static (ZgwOptions options, Aanvraag aanvraag, CallerIdentity caller) CreateZaakFixture()
+  {
+    const string zaaktypeUrl = $"{ZtBase}/zaaktypen/zt-registratie";
+    var options = new ZgwOptions
+    {
+      ZrcBaseUrl = ZrcBase,
+      ZtcBaseUrl = ZtBase,
+      ClientId = "c",
+      Secret = "s",
+      Bronorganisatie = "123443210",
+      VerantwoordelijkeOrganisatie = "123443210",
+      ZaaktypeUrls = new() { ["registratie"] = zaaktypeUrl },
+    };
+    var aanvraag = new Aanvraag { Id = "a1", Type = "registratie", Owner = "111222333", Referentie = "BIG-2026-000123" };
+    var caller = new CallerIdentity(aanvraag.Owner, "Dr. Test", PrincipalRole.Drafter);
+    return (options, aanvraag, caller);
+  }
+
+  private static string RespondFor(string zaaktypeUrl, string url) => url switch
+  {
+    _ when url == $"{ZrcBase}/zaken" => $$"""
+      { "url": "{{ZrcBase}}/zaken/uuid-new", "identificatie": "BIG-2026-000123",
+        "zaaktype": "{{zaaktypeUrl}}", "startdatum": "2026-07-28",
+        "einddatum": null, "registratiedatum": "2026-07-28" }
+      """,
+    _ when url.StartsWith($"{ZtBase}/statustypen") => """
+      { "count": 1, "next": null,
+        "results": [ { "url": "https://oz.example/catalogi/api/v1/statustypen/st-1", "volgnummer": 1 } ] }
+      """,
+    _ when url.StartsWith($"{ZtBase}/roltypen") => """
+      { "count": 1, "next": null,
+        "results": [ { "url": "https://oz.example/catalogi/api/v1/roltypen/rt-initiator" } ] }
+      """,
+    _ when url == $"{ZrcBase}/statussen" => "{}",
+    _ when url == $"{ZrcBase}/rollen" => "{}",
+    _ => throw new InvalidOperationException($"unexpected ZGW call {url}"),
+  };
+
+  [Fact]
+  public void CreateZaak_retries_a_transient_failure_and_then_succeeds()
+  {
+    var (options, aanvraag, caller) = CreateZaakFixture();
+    var zaaktypeUrl = options.ZaaktypeUrls["registratie"];
+    var handler = new ZgwStubHandler(
+        url => RespondFor(zaaktypeUrl, url),
+        (url, attempt) => url == $"{ZrcBase}/zaken" && attempt == 0 ? HttpStatusCode.ServiceUnavailable : HttpStatusCode.OK);
+    var source = new OpenZaakZaakSource(new HttpClient(handler), new ZgwTokenProvider(options), options);
+
+    var (referentie, _, zaakUrl) = source.CreateZaak(aanvraag, new DateTimeOffset(2026, 7, 28, 12, 0, 0, TimeSpan.Zero), caller);
+
+    Assert.Equal("BIG-2026-000123", referentie);
+    Assert.Equal($"{ZrcBase}/zaken/uuid-new", zaakUrl);
+    Assert.Equal(2, handler.Requests.Count(r => r == $"{ZrcBase}/zaken"));
+  }
+
+  [Fact]
+  public void CreateZaak_gives_up_after_three_attempts_on_a_persistent_transient_failure()
+  {
+    var (options, aanvraag, caller) = CreateZaakFixture();
+    var zaaktypeUrl = options.ZaaktypeUrls["registratie"];
+    var handler = new ZgwStubHandler(
+        url => RespondFor(zaaktypeUrl, url),
+        (url, _) => url == $"{ZrcBase}/zaken" ? HttpStatusCode.ServiceUnavailable : HttpStatusCode.OK);
+    var source = new OpenZaakZaakSource(new HttpClient(handler), new ZgwTokenProvider(options), options);
+
+    var ex = Assert.Throws<HttpRequestException>(() => source.CreateZaak(aanvraag, DateTimeOffset.UtcNow, caller));
+
+    Assert.Contains("503", ex.Message);
+    Assert.Equal(3, handler.Requests.Count(r => r == $"{ZrcBase}/zaken"));
+  }
+
+  [Fact]
+  public void CreateZaak_does_not_retry_a_permanent_rejection()
+  {
+    var (options, aanvraag, caller) = CreateZaakFixture();
+    var zaaktypeUrl = options.ZaaktypeUrls["registratie"];
+    var handler = new ZgwStubHandler(
+        url => RespondFor(zaaktypeUrl, url),
+        (url, _) => url == $"{ZrcBase}/statussen" ? HttpStatusCode.BadRequest : HttpStatusCode.OK);
+    var source = new OpenZaakZaakSource(new HttpClient(handler), new ZgwTokenProvider(options), options);
+
+    Assert.Throws<HttpRequestException>(() => source.CreateZaak(aanvraag, DateTimeOffset.UtcNow, caller));
+
+    // No retry on 400, and — the property that makes the whole design safe — no duplicate
+    // zaak was created by a retry that never should have happened.
+    Assert.Equal(1, handler.Requests.Count(r => r == $"{ZrcBase}/statussen"));
+    Assert.Equal(1, handler.Requests.Count(r => r == $"{ZrcBase}/zaken"));
+  }
 }
@@ -0,0 +1,120 @@
+using System.Net;
+using System.Net.Http.Json;
+using BigRegister.Api.Contracts;
+using BigRegister.Api.Data;
+using Microsoft.AspNetCore.Hosting;
+using Microsoft.AspNetCore.Mvc.Testing;
+using Microsoft.Extensions.DependencyInjection;
+
+namespace BigRegister.Tests;
+
+/// <summary>
+/// WP-60's required verification: a ZGW failure mid-submit must not leave the two write sides
+/// silently diverged — it's flagged (<see cref="Aanvraag.ZgwError"/>, an audit row) instead.
+/// Not an <see cref="IClassFixture{TFixture}"/> off <see cref="TestWebApplicationFactory"/>: that
+/// fixture hardcodes <c>Zgw:Enabled=false</c>, so this builds its own factory the same way
+/// <see cref="OpenZaakIntegrationTests"/> does, but with a stub primary handler
+/// (<see cref="ZgwStubHandler"/>) instead of a live OpenZaak.
+/// </summary>
+public class ZgwDivergenceTests
+{
+  private const string ZrcBase = "https://oz.example/zaken/api/v1";
+  private const string ZtBase = "https://oz.example/catalogi/api/v1";
+  private const string ZaaktypeUrl = $"{ZtBase}/zaaktypen/zt-1";
+
+  private static WebApplicationFactory<Program> Factory(ZgwStubHandler stub)
+  {
+    var dbPath = Path.Combine(Path.GetTempPath(), $"bigregister-zgw-divergence-{Guid.NewGuid():N}.db");
+    return new WebApplicationFactory<Program>().WithWebHostBuilder(builder => builder
+        .UseSetting("ConnectionStrings:AppDb", $"Data Source={dbPath}")
+        .UseSetting("Zgw:Enabled", "true")
+        .UseSetting("Zgw:ZrcBaseUrl", ZrcBase)
+        .UseSetting("Zgw:ZtcBaseUrl", ZtBase)
+        .UseSetting("Zgw:ClientId", "c")
+        .UseSetting("Zgw:Secret", "s")
+        .UseSetting("Zgw:Bronorganisatie", "123443210")
+        .UseSetting("Zgw:VerantwoordelijkeOrganisatie", "123443210")
+        .UseSetting("Zgw:ZaaktypeUrls:registratie", ZaaktypeUrl)
+        .ConfigureServices(services => services.ConfigureHttpClientDefaults(b =>
+            b.ConfigurePrimaryHttpMessageHandler(() => stub))));
+  }
+
+  /// <summary>Doesn't call GET /applications first (unlike ApplicationTests.Create) — under
+  /// Zgw:Enabled=true that route goes through IZaakSource too, which this test's stub doesn't
+  /// need to answer since every test here uses a fresh db and creates exactly one aanvraag.</summary>
+  private static async Task<string> CreateConcept(HttpClient client, string type = "registratie")
+  {
+    var res = await client.PostAsJsonAsync("/api/v1/applications", new { type });
+    res.EnsureSuccessStatusCode();
+    var body = (await res.Content.ReadFromJsonAsync<ApplicationDetailDto>())!;
+    return body.Id;
+  }
+
+  private static string SuccessBody(string url) => url switch
+  {
+    _ when url == $"{ZrcBase}/zaken" => $$"""
+      { "url": "{{ZrcBase}}/zaken/uuid-new", "identificatie": "BIG-2026-000123",
+        "zaaktype": "{{ZaaktypeUrl}}", "startdatum": "2026-07-30",
+        "einddatum": null, "registratiedatum": "2026-07-30" }
+      """,
+    _ when url.StartsWith($"{ZtBase}/statustypen") => """
+      { "count": 1, "next": null,
+        "results": [ { "url": "https://oz.example/catalogi/api/v1/statustypen/st-1", "volgnummer": 1 } ] }
+      """,
+    _ when url.StartsWith($"{ZtBase}/roltypen") => """
+      { "count": 1, "next": null,
+        "results": [ { "url": "https://oz.example/catalogi/api/v1/roltypen/rt-initiator" } ] }
+      """,
+    _ when url == $"{ZrcBase}/statussen" => "{}",
+    _ when url == $"{ZrcBase}/rollen" => "{}",
+    _ => throw new InvalidOperationException($"unexpected ZGW call {url}"),
+  };
+
+  [Fact]
+  public async Task Submit_with_a_failing_zgw_flags_the_divergence_instead_of_diverging_silently()
+  {
+    var stub = new ZgwStubHandler(SuccessBody, (url, _) => url == $"{ZrcBase}/zaken" ? HttpStatusCode.ServiceUnavailable : HttpStatusCode.OK);
+    using var factory = Factory(stub);
+    using var client = factory.CreateClient();
+
+    var id = await CreateConcept(client);
+    var res = await client.PostAsJsonAsync($"/api/v1/applications/{id}/submit", new { diplomaHerkomst = "duo" });
+
+    // The local write is still authoritative: 200 with a real reference, not a 500.
+    res.EnsureSuccessStatusCode();
+    var body = (await res.Content.ReadFromJsonAsync<SubmitApplicationResponse>())!;
+    Assert.NotEmpty(body.Referentie);
+
+    var stored = ApplicationStore.ListAll().Single(a => a.Id == id);
+    Assert.Null(stored.ZaakUrl);
+    Assert.NotNull(stored.ZgwError);
+
+    var audit = await client.SendAsync(AdminRequest(HttpMethod.Get, "/api/v1/admin/audit"));
+    audit.EnsureSuccessStatusCode();
+    var entries = (await audit.Content.ReadFromJsonAsync<List<AuthzAuditDto>>())!;
+    Assert.Contains(entries, e => e.Action == "zgw:divergence" && e.Decision == "deny" && e.Resource == body.Referentie);
+  }
+
+  [Fact]
+  public async Task Submit_with_a_healthy_zgw_leaves_no_divergence_flag()
+  {
+    var stub = new ZgwStubHandler(SuccessBody);
+    using var factory = Factory(stub);
+    using var client = factory.CreateClient();
+
+    var id = await CreateConcept(client);
+    var res = await client.PostAsJsonAsync($"/api/v1/applications/{id}/submit", new { diplomaHerkomst = "duo" });
+    res.EnsureSuccessStatusCode();
+
+    var stored = ApplicationStore.ListAll().Single(a => a.Id == id);
+    Assert.Equal($"{ZrcBase}/zaken/uuid-new", stored.ZaakUrl);
+    Assert.Null(stored.ZgwError);
+  }
+
+  private static HttpRequestMessage AdminRequest(HttpMethod method, string path)
+  {
+    var req = new HttpRequestMessage(method, path);
+    req.Headers.Add("X-Role", "admin");
+    return req;
+  }
+}
@@ -9,8 +9,15 @@ namespace BigRegister.Tests;
 /// URL across GET/POST). Records every request's url/body/auth-scheme for assertion.
 /// Factored out of OpenZaakZaakSourceTests once OpenZaakDocumentSourceTests needed the
 /// identical stub.
+///
+/// WP-60: an optional <paramref name="status"/> callback lets a test inject a failing status
+/// for a given url on a given (0-based) attempt — e.g. "503 on the first call to /zaken, then
+/// let it through" — to exercise ZgwHttpClient's retry without a live server. When it returns
+/// a non-2xx code, <paramref name="respond"/> is not called for that attempt (so a test that
+/// models an "always fails" url never has to also teach `respond` a success body it never
+/// reaches).
 /// </summary>
-internal sealed class ZgwStubHandler(Func<string, string> respond) : HttpMessageHandler
+internal sealed class ZgwStubHandler(Func<string, string> respond, Func<string, int, HttpStatusCode>? status = null) : HttpMessageHandler
 {
  public List<string> Requests { get; } = new();
  public List<string?> AuthSchemes { get; } = new();
@@ -21,9 +28,18 @@ internal sealed class ZgwStubHandler(Func<string, string> respond) : HttpMessage
  protected override Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken cancellationToken)
  {
    var url = request.RequestUri!.ToString();
+    var attempt = Requests.Count(r => r == url);
    Requests.Add(url);
    AuthSchemes.Add(request.Headers.Authorization?.Scheme);
    Bodies.Add(request.Content?.ReadAsStringAsync(cancellationToken).GetAwaiter().GetResult() ?? "");
+
+    var code = status?.Invoke(url, attempt) ?? HttpStatusCode.OK;
+    if (!((int)code >= 200 && (int)code < 300))
+      return Task.FromResult(new HttpResponseMessage(code)
+      {
+        Content = new StringContent("{\"detail\":\"stub failure\"}", Encoding.UTF8, "application/json"),
+      });
+
    return Task.FromResult(new HttpResponseMessage(HttpStatusCode.OK)
    {
      Content = new StringContent(respond(url), Encoding.UTF8, "application/json"),