fix(runner): retry convergence confirmation after restore

2026-10-26 17:41:57 +00:00
parent b944eca41d
commit ccc29d5acc
2 changed files with 38 additions and 2 deletions
@@ -93,9 +93,15 @@ def assert_serving(domain: str, meta) -> None:
    Steps 1–2 are BOUNDED POLLS (no bare sleep), so a state-mutating op (upgrade/restore) that leaves
    the app briefly reconverging settles, while a persistent failure still fails within the timeout."""
    deadline = time.time() + meta.DEPLOY_TIMEOUT
-    while time.time() < deadline and not lifecycle.services_converged(domain):
+    converged = False
+    while time.time() < deadline:
+        # Keep both observations inside the retry budget: a service may restart
+        # between the initial convergence sample and its confirmation.
+        if lifecycle.services_converged(domain) and lifecycle.services_converged(domain):
+            converged = True
+            break
        time.sleep(5)
-    assert lifecycle.services_converged(domain), f"{domain}: services did not converge"
+    assert converged, f"{domain}: services did not converge"

    path = meta.HEALTH_PATH
    ok = tuple(meta.HEALTH_OK)