fixed test flakiness in replication tests

go.mod

@@ -6,7 +6,7 @@ require (
 	github.com/PuerkitoBio/goquery v1.8.1
 	github.com/cockroachdb/apd/v3 v3.2.3
 	github.com/cockroachdb/errors v1.7.5
-	github.com/dolthub/dolt/go v0.40.5-0.20260715222552-6bea62fec1d6
+	github.com/dolthub/dolt/go v0.40.5-0.20260717023913-8de32a8c8d8e
 	github.com/dolthub/eventsapi_schema v0.0.0-20260715220557-d9b4a1c6b4d4
 	github.com/dolthub/flatbuffers/v23 v23.3.3-dh.2
 	github.com/dolthub/go-mysql-server v0.20.1-0.20260715210958-36c4fed9afa6

go.sum

@@ -246,8 +246,8 @@ github.com/dolthub/aws-sdk-go-ini-parser v0.0.0-20250305001723-2821c37f6c12 h1:I
 github.com/dolthub/aws-sdk-go-ini-parser v0.0.0-20250305001723-2821c37f6c12/go.mod h1:rN7X8BHwkjPcfMQQ2QTAq/xM3leUSGLfb+1Js7Y6TVo=
 github.com/dolthub/dolt-mcp v0.3.4 h1:AyG5cw+fNWXDHXujtQnqUPZrpWtPg6FN6yYtjv1pP44=
 github.com/dolthub/dolt-mcp v0.3.4/go.mod h1:bCZ7KHvDYs+M0e+ySgmGiNvLhcwsN7bbf5YCyillLrk=
-github.com/dolthub/dolt/go v0.40.5-0.20260715222552-6bea62fec1d6 h1:abnk5UJQMJue6ZHFl4VIOUWSMV3/mjq/a3tAyLhVrFI=
-github.com/dolthub/dolt/go v0.40.5-0.20260715222552-6bea62fec1d6/go.mod h1:NeIUHB089JzLdjA37lExTUW0oOj9ck5LPTpRMquVpb4=
+github.com/dolthub/dolt/go v0.40.5-0.20260717023913-8de32a8c8d8e h1:Z9v7eg3MNs1OGSngDL/MI2cyC8M6GxUFeXqWYjfCU2k=
+github.com/dolthub/dolt/go v0.40.5-0.20260717023913-8de32a8c8d8e/go.mod h1:3y+3STq+7aushqr4sLOW3fzRC+TT1xD0LeaYDbmvaEY=
 github.com/dolthub/eventsapi_schema v0.0.0-20260715220557-d9b4a1c6b4d4 h1:0mg9QEFdkkBwJMxvz1tCjHYmfG2iIC6aShj1InDq9/M=
 github.com/dolthub/eventsapi_schema v0.0.0-20260715220557-d9b4a1c6b4d4/go.mod h1:SSLraQS/jGLYFgff3vuZ+JbVUct6vyEeMzjLBqWqoyM=
 github.com/dolthub/flatbuffers/v23 v23.3.3-dh.2 h1:u3PMzfF8RkKd3lB9pZ2bfn0qEG+1Gms9599cr0REMww=

integration-tests/go-sql-server-driver/driver/cmd.go

@@ -41,7 +41,12 @@ var DelvePath string
 const TestUserName = "Bats Tests"
 const TestEmailAddress = "bats@email.fake"
 
-const ConnectAttempts = 50
+// ConnectAttempts and RetrySleepDuration are used by the test driver to retry connections to a doltgres server
+// that is starting up. Besides server startup, the retries must also absorb cluster replication being
+// eventually consistent: connections default to the "postgres" database, and on a freshly-booted standby
+// that database only exists once its first push from the primary lands (which on a slow CI host can take
+// many seconds of first-contact setup). ~30 seconds, matching statusEventualConsistencyAttempts.
+const ConnectAttempts = 600
 const RetrySleepDuration = 50 * time.Millisecond
 
 // EnvDoltgresBinPath is the environment variable used to locate the doltgres

integration-tests/go-sql-server-driver/testdef.go

@@ -22,6 +22,7 @@ import (
 	"io"
 	"os"
 	"path/filepath"
+	"strings"
 	"sync"
 	"testing"
 	"text/template"
@@ -59,7 +60,11 @@ type Test struct {
 // Set this environment variable to effectively disable timeouts for debugging.
 const debugEnvKey = "DOLTGRES_SQL_SERVER_TEST_DEBUG"
 
-var timeout = 20 * time.Second
+// timeout bounds each individual query in a test. It must comfortably exceed the
+// dolt_cluster_ack_writes_timeout_secs values used in the cluster replication tests (60s): a write on the
+// primary legitimately blocks for up to that long waiting for standbys to acknowledge replication, e.g.
+// when a standby is slow to complete first contact (jwks setup plus create-on-push) on a loaded CI host.
+var timeout = 90 * time.Second
 
 func init() {
 	_, ok := os.LookupEnv(debugEnvKey)
@@ -629,12 +634,33 @@ func RetryTestRun(t *testing.T, attempts int, test func(TestingT)) {
 	rtt.try(attempts, test)
 }
 
+// statusEventualConsistencyAttempts bounds how long RunQuery waits for a cluster
+// replication status query to converge to its expected result.
+// Retries are quite forgiving in these tests because the default `postgres` database in most of these tests is never
+// written to, which means it get replicated async by a background thread, rather than by a user write.
+// At driver.RetrySleepDuration (50ms) per attempt this is roughly 30 seconds, which also makes status
+// queries usable as explicit quiesce barriers before graceful role transitions (which have a fixed
+// 10-second internal budget for standbys to catch up).
+const statusEventualConsistencyAttempts = 600
+
 func RunQuery(t *testing.T, conn *sql.Conn, q driver.Query, ports *DynamicResources) {
-	RetryTestRun(t, q.RetryAttempts, func(t TestingT) {
+	attempts := q.RetryAttempts
+	// Replication status is eventually consistent, so status queries always get at
+	// least the generous eventual-consistency budget, even if the test set a smaller
+	// (or no) retry_attempts.
+	if observesReplicationStatus(q) && attempts < statusEventualConsistencyAttempts {
+		attempts = statusEventualConsistencyAttempts
+	}
+	RetryTestRun(t, attempts, func(t TestingT) {
 		RunQueryAttempt(t, conn, q, ports)
 	})
 }
 
+// observesReplicationStatus reports whether the query reads the dolt_cluster_status system table
+func observesReplicationStatus(q driver.Query) bool {
+	return q.Query != "" && strings.Contains(strings.ToLower(q.Query), "dolt_cluster_status")
+}
+
 func RunQueryAttempt(t TestingT, conn *sql.Conn, q driver.Query, ports *DynamicResources) {
 	args := make([]any, len(q.Args))
 	for i := range q.Args {