fix consul test timeout (#1010)

- Improvement: Hub Consul client HTTP timeout defaults raised to 1s connect / 2s total so transient latency to a slow Consul agent no longer fails registration calls

4 files changed, 26 insertions, 13 deletions

diff --git a/CHANGELOG.md b/CHANGELOG.md
index c2d7928e3..732c19774 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,10 +1,11 @@
 ##
-- Improvement: Zen log messages are forwarded to trace as typed `ZenLog.*` events that preserve structured `fmt` args end-to-end, so the zen trace analyzer and other downstream consumers can re-render messages with full formatter support (nested widths, chrono specs, etc.). `--trace=log` now routes to the zen log channel (the upstream UE `log` channel is unused since zen no longer emits `Logging.*` events)
 - Improvement: `zen builds` zen-folder handling is now consistent per subcommand
   - `list-namespaces`, `list`, `list-blocks`, `ls`: no local scratch folder is created; responses stay in memory
   - `upload`, `fetch-blob`, `prime-cache`, `validate-part`: default to `<cwd>/.zen` (no change)
   - `download`: default to `<local-path>/.zen` (no change)
 - Improvement: Dashboard banner displays the zenserver version next to the wordmark
+- Improvement: Zen log messages are forwarded to trace as typed `ZenLog.*` events that preserve structured `fmt` args end-to-end, so the zen trace analyzer and other downstream consumers can re-render messages with full formatter support (nested widths, chrono specs, etc.). `--trace=log` now routes to the zen log channel (the upstream UE `log` channel is unused since zen no longer emits `Logging.*` events)
+- Improvement: Hub Consul client HTTP timeout defaults raised to 1s connect / 2s total so transient latency to a slow Consul agent no longer fails registration calls
 - Bugfix: `zen builds ls` no longer fails against cloud build storage (`--host`/`--url`) when `--storage-path` is not supplied
 - Bugfix: `NamedEvent` construction on Linux/macOS no longer races against a concurrent destructor's `unlink()` of the backing file; the IPC key is now derived via `fstat()` on the open fd instead of `ftok()` re-stat'ing the path
 - Bugfix: Hub provision requests now return 202 Accepted when the module is `Recovering` or `Waking` instead of rejecting
@@ -60,7 +61,6 @@
   - `zen cache record <path>` replaces `zen rpc-record-start`
   - `zen cache record stop` replaces `zen rpc-record-stop`
   - `zen cache replay` replaces `zen rpc-record-replay`
-- Improvement: `--zen-folder-path` is used verbatim as the zen state and temp folder (no `.zen` subfolder appended)
 - Bugfix: `builds download` partial-block fetch decisions now account for build storage host latency
 - Bugfix: Transfer rate displays in `builds` commands now smooth correctly
 - Bugfix: Structured cache PUT errors with a detail body no longer write the HTTP response twice
diff --git a/src/zenserver-test/hub-tests.cpp b/src/zenserver-test/hub-tests.cpp
index e83e18446..9d1ee44fb 100644
--- a/src/zenserver-test/hub-tests.cpp
+++ b/src/zenserver-test/hub-tests.cpp
@@ -374,6 +374,15 @@ TEST_CASE("hub.lifecycle.children")
 	CHECK(Result);
 }
 
+// Local agent talks on loopback but can still be slow on shared CI runners
+// (macOS in particular). Override ConsulClient's short production-default
+// timeouts so tests don't flake on first-call latency.
+static consul::ConsulClient::Configuration
+MakeTestConsulClientConfig()
+{
+	return {.BaseUri = "http://localhost:8500/", .ConnectTimeout = std::chrono::seconds{5}, .Timeout = std::chrono::seconds{5}};
+}
+
 static bool
 WaitForConsulService(consul::ConsulClient& Client, std::string_view ServiceId, bool ExpectedState, int TimeoutMs)
 {
@@ -400,7 +409,7 @@ TEST_CASE("hub.consul.kv")
 	consul::ConsulProcess ConsulProc;
 	ConsulProc.SpawnConsulAgent();
 
-	consul::ConsulClient Client({.BaseUri = "http://localhost:8500/"});
+	consul::ConsulClient Client(MakeTestConsulClientConfig());
 	Client.SetKeyValue("zen/hub/testkey", "testvalue");
 
 	std::string RetrievedValue = Client.GetKeyValue("zen/hub/testkey");
@@ -422,7 +431,7 @@ TEST_CASE("hub.consul.hub.registration")
 		   "--consul-health-interval-seconds=5 --consul-deregister-after-seconds=60");
 	REQUIRE(PortNumber != 0);
 
-	consul::ConsulClient Client({.BaseUri = "http://localhost:8500/"});
+	consul::ConsulClient Client(MakeTestConsulClientConfig());
 	REQUIRE(WaitForConsulService(Client, "zen-hub-test-instance", true, 5000));
 
 	// Verify custom intervals flowed through to the registered check
@@ -503,7 +512,7 @@ TEST_CASE("hub.consul.hub.registration.token")
 
 	// Use a plain client -- dev-mode Consul doesn't enforce ACLs, but the
 	// server has exercised the ConsulTokenEnv -> GetEnvVariable -> ConsulClient path.
-	consul::ConsulClient Client({.BaseUri = "http://localhost:8500/"});
+	consul::ConsulClient Client(MakeTestConsulClientConfig());
 
 	REQUIRE(WaitForConsulService(Client, "zen-hub-test-instance", true, 5000));
 
@@ -524,7 +533,7 @@ TEST_CASE("hub.consul.provision.registration")
 		Instance.SpawnServerAndWaitUntilReady("--consul-endpoint=http://localhost:8500/ --instance-id=test-instance");
 	REQUIRE(PortNumber != 0);
 
-	consul::ConsulClient Client({.BaseUri = "http://localhost:8500/"});
+	consul::ConsulClient Client(MakeTestConsulClientConfig());
 
 	REQUIRE(WaitForConsulService(Client, "zen-hub-test-instance", true, 5000));
 
diff --git a/src/zenutil/consul/consul.cpp b/src/zenutil/consul/consul.cpp
index 3d16a9188..762f06817 100644
--- a/src/zenutil/consul/consul.cpp
+++ b/src/zenutil/consul/consul.cpp
@@ -117,9 +117,9 @@ ConsulProcess::StopConsulAgent()
 
 ConsulClient::ConsulClient(const Configuration& Config)
 : m_Config(Config)
-, m_HttpClient(m_Config.BaseUri,
-			   HttpClientSettings{.ConnectTimeout = std::chrono::milliseconds{500}, .Timeout = std::chrono::milliseconds{500}},
-			   [this] { return m_Stop.load(); })
+, m_HttpClient(m_Config.BaseUri, HttpClientSettings{.ConnectTimeout = m_Config.ConnectTimeout, .Timeout = m_Config.Timeout}, [this] {
+	return m_Stop.load();
+})
 {
 	m_Worker = std::thread(&ConsulClient::WorkerLoop, this);
 }
@@ -790,7 +790,8 @@ TEST_CASE("util.consul.service_lifecycle")
 	TestHealthServer HealthServer;
 	HealthServer.Start();
 
-	ConsulClient Client({.BaseUri = "http://localhost:8500/"});
+	ConsulClient Client(
+		{.BaseUri = "http://localhost:8500/", .ConnectTimeout = std::chrono::seconds{5}, .Timeout = std::chrono::seconds{5}});
 
 	const std::string ServiceId = "test-health-svc";
 
diff --git a/src/zenutil/include/zenutil/consul.h b/src/zenutil/include/zenutil/consul.h
index 4efb10263..38d450583 100644
--- a/src/zenutil/include/zenutil/consul.h
+++ b/src/zenutil/include/zenutil/consul.h
@@ -7,6 +7,7 @@
 #include <zenhttp/httpclient.h>
 
 #include <atomic>
+#include <chrono>
 #include <cstdint>
 #include <string>
 #include <string_view>
@@ -33,9 +34,11 @@ class ConsulClient
 public:
 	struct Configuration
 	{
-		std::string BaseUri;
-		std::string StaticToken;
-		std::string TokenEnvName;
+		std::string				  BaseUri;
+		std::string				  StaticToken;
+		std::string				  TokenEnvName;
+		std::chrono::milliseconds ConnectTimeout{1000};
+		std::chrono::milliseconds Timeout{2000};
 	};
 
 	ConsulClient(const Configuration& Config);