## What & why S-16c, the last of the S-16 (#17) split, on top of the backplane (#122) and distributed tracing (#123). The five .NET services now expose OpenTelemetry **metrics** in Prometheus format at `/metrics`; Prometheus scrapes each (one job per service); and Grafana ships a pre-built **Request path — golden signals** dashboard (traffic / errors / latency / saturation), split by service. Closes #124 ### How - Each service adds `.WithMetrics(AddAspNetCoreInstrumentation + AddHttpClientInstrumentation + AddMeter("System.Runtime") + AddPrometheusExporter)` and maps `/metrics`. Same shape as the S-16b tracing wiring already in these `Program.cs` files. - `infra/observability/prometheus/prometheus.yml`: one scrape job per service (`acl`, `domain`, `bff`, `event-subscriber`, `projection-api`), reached by compose service name. - `infra/observability/grafana/provisioning/dashboards/`: dashboard provider + `golden-signals.json` (baked into the Grafana image by the existing `COPY provisioning/`). - `verify-metrics` (new CI verify-stack step + Makefile target): generates BFF traffic and asserts Prometheus scraped the golden-signal metric from every service. Mirrors `verify-tracing`. ### Dependency (CLAUDE.md §13/§14) Adds `OpenTelemetry.Exporter.Prometheus.AspNetCore` `1.17.0-beta.1` (matched to the `1.17.0` core already in use). It gives the OTel-native `/metrics` pull endpoint; replacing it would mean hand-rolling Prometheus exposition over a `MeterListener`; the risk is that it is a **prerelease** package (the whole OTel .NET Prometheus line is `-beta`) — pinned, wired only in `Program.cs`, and gated by `verify-metrics`. Recorded in **ADR-0024**. ## Definition of Done - [x] Linked Gitea issue (#124). - [x] Failing test committed before the implementation (`test(bff): /metrics exposes http-server request duration`). - [x] Implementation makes the test pass. - [ ] CI green — pending Gitea Actions run. - [x] `docker compose up` reaches green health within 3 min (backplane images unchanged in shape; not on the health gate, ADR-0023). - [x] Docs updated — demo-script S-16c entry. - [x] ADR added — ADR-0024. - [x] Demo note in `docs/demo-script.md`. ## Notes for reviewers - `/health` polls are counted as traffic (metrics aren't path-filtered, unlike traces). Fine for a demo dashboard and honest — real load stacks on top. - `projection-api` has no Stryker config (unchanged); the four mutated services carry the metrics wiring in `Program.cs`, same as the merged S-16b tracing code. - Metric names verified against a live service: `http_server_request_duration_seconds{,_bucket,_count}`, label `http_response_status_code`, `dotnet_process_cpu_time_seconds_total`. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Reviewed-on: #129
101 lines
4.7 KiB
C#
101 lines
4.7 KiB
C#
using Acl.Application;
|
|
using Acl.Infrastructure;
|
|
using OpenTelemetry.Metrics;
|
|
using OpenTelemetry.Resources;
|
|
using OpenTelemetry.Trace;
|
|
|
|
var builder = WebApplication.CreateBuilder(args);
|
|
|
|
// OpenTelemetry tracing (S-16b, ADR-0023): auto-instrument incoming ASP.NET Core requests and
|
|
// outgoing HttpClient calls (the ACL → OpenZaak hop), exported over OTLP to Tempo. Service name +
|
|
// OTLP endpoint come from OTEL_* env (compose); the exporter no-ops when Tempo is unreachable.
|
|
builder.Services.AddOpenTelemetry()
|
|
.ConfigureResource(r => r.AddService(
|
|
builder.Configuration["OTEL_SERVICE_NAME"] ?? builder.Environment.ApplicationName))
|
|
.WithTracing(tracing => tracing
|
|
.AddAspNetCoreInstrumentation(o => o.Filter = ctx => ctx.Request.Path != "/health")
|
|
.AddHttpClientInstrumentation()
|
|
.AddOtlpExporter())
|
|
// OpenTelemetry metrics (S-16c, ADR-0023): golden signals for the request path —
|
|
// http.server.request.duration (traffic/errors/latency) + http.client.* for downstream hops, plus
|
|
// the built-in System.Runtime meter for saturation (GC, CPU, thread pool). Prometheus scrapes these
|
|
// from /metrics (mapped below); metrics aren't pushed over OTLP, so no collector hop (ADR-0023).
|
|
.WithMetrics(metrics => metrics
|
|
.AddAspNetCoreInstrumentation()
|
|
.AddHttpClientInstrumentation()
|
|
.AddMeter("System.Runtime")
|
|
.AddPrometheusExporter());
|
|
|
|
builder.Services.AddSingleton<IClock, SystemClock>();
|
|
builder.Services.AddSingleton(sp => sp.GetRequiredService<IConfiguration>()
|
|
.GetSection("Acl:Defaults").Get<AclDefaults>()
|
|
?? throw new InvalidOperationException("Missing configuration section 'Acl:Defaults'"));
|
|
builder.Services.AddSingleton(sp => sp.GetRequiredService<IConfiguration>()
|
|
.GetSection("Acl:OpenZaak").Get<OpenZaakOptions>()
|
|
?? throw new InvalidOperationException("Missing configuration section 'Acl:OpenZaak'"));
|
|
builder.Services.AddHttpClient<IZaakGateway, OpenZaakGateway>();
|
|
// Singleton so the resolved zaaktype/informatieobjecttype URLs are cached across requests (S-27).
|
|
builder.Services.AddSingleton<IZaaktypeCatalog, CachedZaaktypeCatalog>();
|
|
builder.Services.AddScoped<AclService>();
|
|
|
|
var app = builder.Build();
|
|
|
|
app.MapGet("/health", () => "Healthy");
|
|
|
|
// Prometheus scrape endpoint (S-16c): exposes the OTel metrics above in Prometheus text format.
|
|
app.MapPrometheusScrapingEndpoint();
|
|
|
|
// The ACL's single operation, exposed as a service endpoint.
|
|
app.MapPost("/zaken", async (OpenZaakRequest body, AclService acl, CancellationToken ct) =>
|
|
{
|
|
var zaakUrl = await acl.OpenZaakAsync(new DomainRegistration(body.Bsn, body.Reference), ct);
|
|
return Results.Ok(new { zaakUrl = zaakUrl.ToString() });
|
|
});
|
|
|
|
// Approve a zaak: set it to its zaaktype's eindstatus (S-09b). The domain hands over only the zaak
|
|
// URL; the ACL owns the ZGW statustype resolution (§8.1).
|
|
app.MapPost("/statussen", async (SetStatusRequest body, AclService acl, CancellationToken ct) =>
|
|
{
|
|
await acl.ApproveZaakAsync(new Uri(body.ZaakUrl), ct);
|
|
return Results.NoContent();
|
|
});
|
|
|
|
// Cancel a zaak on document-timeout expiry (S-10c): set it to its zaaktype's cancellation statustype
|
|
// + resultaat. The domain hands over only the zaak URL; the ACL owns the ZGW resolution (§8.1).
|
|
app.MapPost("/annuleringen", async (CancelZaakRequest body, AclService acl, CancellationToken ct) =>
|
|
{
|
|
await acl.CancelZaakAsync(new Uri(body.ZaakUrl), ct);
|
|
return Results.NoContent();
|
|
});
|
|
|
|
// Read a zaak's public-safe reference (its identificatie). The Event Subscriber calls this to enrich
|
|
// the read projection without reading ZGW itself (§8.1, #78).
|
|
app.MapPost("/zaken/reference", async (ZaakReferenceRequest body, AclService acl, CancellationToken ct) =>
|
|
{
|
|
var reference = await acl.GetZaakReferenceAsync(new Uri(body.ZaakUrl), ct);
|
|
return Results.Ok(new { reference });
|
|
});
|
|
|
|
// Store an uploaded diploma against a zaak (S-10b): the domain sends the file as base64; the ACL
|
|
// creates the ZGW enkelvoudiginformatieobject and relates it to the zaak (§8.1). Returns its URL.
|
|
app.MapPost("/documenten", async (StoreDocumentRequest body, AclService acl, CancellationToken ct) =>
|
|
{
|
|
var url = await acl.StoreDiplomaAsync(
|
|
new Uri(body.ZaakUrl), Convert.FromBase64String(body.ContentBase64), body.FileName, body.ContentType, ct);
|
|
return Results.Ok(new { informatieobjectUrl = url.ToString() });
|
|
});
|
|
|
|
app.Run();
|
|
|
|
public sealed record OpenZaakRequest(string Bsn, string Reference);
|
|
|
|
public sealed record SetStatusRequest(string ZaakUrl);
|
|
|
|
public sealed record CancelZaakRequest(string ZaakUrl);
|
|
|
|
public sealed record ZaakReferenceRequest(string ZaakUrl);
|
|
|
|
public sealed record StoreDocumentRequest(string ZaakUrl, string ContentBase64, string FileName, string ContentType);
|
|
|
|
public partial class Program;
|