test(infra): verify-tracing asserts one connected trace across services in Tempo (refs #123)

Generates anonymous BFF→projection-api traffic and asserts Tempo holds a single trace containing both service.names — proving OTLP export plus traceparent propagation across the HttpClient hop. Fails until the services are instrumented (next commit). Runs in-network like the other verify checks. refs #123
2026-07-23 14:30:59 +02:00
parent 4274fd30d1
commit b32c352f20
4 changed files with 116 additions and 1 deletions
@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+"""S-16b (#123): prove distributed tracing works end to end.
+
+Generate anonymous BFF traffic (GET /openbaar/register, which the BFF serves by
+calling projection-api — no auth, no OpenZaak egress), then query Tempo and assert
+that ONE trace contains spans from both `bff` and `projection-api`. That proves the
+services export OTLP to Tempo AND that the W3C traceparent propagates across the
+HttpClient hop, stitching the request into a single connected trace.
+
+Stdlib only (urllib/json) so it runs in a bare python:3-slim container in-network.
+"""
+import json
+import os
+import sys
+import time
+import urllib.error
+import urllib.parse
+import urllib.request
+
+BFF = os.environ["BFF"]        # http://<bff-ip>:8080
+TEMPO = os.environ["TEMPO"]    # http://<tempo-ip>:3200
+TIMEOUT = int(os.environ.get("TRACING_TIMEOUT", "90"))
+WANT = {"bff", "projection-api"}  # the two services that must share one trace
+
+
+def _get(url):
+    with urllib.request.urlopen(url, timeout=10) as r:
+        return r.read()
+
+
+def generate_traffic():
+    # A non-2xx still produces spans; only total unreachability of the BFF is fatal.
+    for _ in range(3):
+        try:
+            _get(f"{BFF}/openbaar/register")
+        except urllib.error.HTTPError:
+            pass
+
+
+def search_trace_ids():
+    q = urllib.parse.quote('{ resource.service.name = "bff" }')
+    try:
+        data = json.loads(_get(f"{TEMPO}/api/search?q={q}&limit=50"))
+    except Exception:
+        return []
+    return [t["traceID"] for t in data.get("traces", [])]
+
+
+def services_in_trace(trace_id):
+    try:
+        data = json.loads(_get(f"{TEMPO}/api/traces/{trace_id}"))
+    except Exception:
+        return set()
+    names = set()
+    for batch in data.get("batches", []):
+        for attr in batch.get("resource", {}).get("attributes", []):
+            if attr.get("key") == "service.name":
+                names.add(attr.get("value", {}).get("stringValue"))
+    return names
+
+
+def main():
+    deadline = time.time() + TIMEOUT
+    generate_traffic()
+    seen = set()
+    while time.time() < deadline:
+        for tid in search_trace_ids():
+            names = services_in_trace(tid)
+            seen |= names
+            if WANT.issubset(names):
+                print(f"OK — trace {tid} spans {sorted(names)}")
+                return 0
+        time.sleep(3)
+        generate_traffic()
+    print(f"FAIL — no single trace spanned {sorted(WANT)}; services seen: {sorted(seen)}",
+          file=sys.stderr)
+    return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())