From 0e2b84d8e3628dc24569072ea57873cda1e7338b Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Fri, 22 May 2026 19:39:54 +0000
Subject: [PATCH] feat(distributed): add configurable NATS backend
 install/upgrade timeouts

Adds BackendInstallTimeout and BackendUpgradeTimeout to DistributedConfig
with 15m defaults, following the existing MCPToolTimeout / WorkerWaitTimeout
pattern. These will replace the hardcoded literals in RemoteUnloaderAdapter
so admin-driven backend installs across the cluster survive long OCI image
pulls that previously timed out at 3m.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 core/config/distributed_config.go      | 29 +++++++++++++++++++++
 core/config/distributed_config_test.go | 36 ++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)
 create mode 100644 core/config/distributed_config_test.go

diff --git a/core/config/distributed_config.go b/core/config/distributed_config.go
index 0b77d1ffd..f427c23b8 100644
--- a/core/config/distributed_config.go
+++ b/core/config/distributed_config.go
@@ -42,6 +42,9 @@ type DistributedConfig struct {
 
 	MCPCIJobTimeout     time.Duration // MCP CI job execution timeout (default 10m)
 
+	BackendInstallTimeout time.Duration // NATS round-trip timeout for backend.install (default 15m)
+	BackendUpgradeTimeout time.Duration // NATS round-trip timeout for backend.upgrade (default 15m)
+
 	MaxUploadSize int64 // Maximum upload body size in bytes (default 50 GB)
 
 	AgentWorkerConcurrency int `yaml:"agent_worker_concurrency" json:"agent_worker_concurrency" env:"LOCALAI_AGENT_WORKER_CONCURRENCY"`
@@ -75,6 +78,8 @@ func (c DistributedConfig) Validate() error {
 		"health-check-interval": c.HealthCheckInterval,
 		"stale-node-threshold":  c.StaleNodeThreshold,
 		"mcp-ci-job-timeout":    c.MCPCIJobTimeout,
+		"backend-install-timeout": c.BackendInstallTimeout,
+		"backend-upgrade-timeout": c.BackendUpgradeTimeout,
 	} {
 		if d < 0 {
 			return fmt.Errorf("%s must not be negative", name)
@@ -137,6 +142,18 @@ func WithStorageSecretKey(key string) AppOption {
 	}
 }
 
+func WithBackendInstallTimeout(d time.Duration) AppOption {
+	return func(o *ApplicationConfig) {
+		o.Distributed.BackendInstallTimeout = d
+	}
+}
+
+func WithBackendUpgradeTimeout(d time.Duration) AppOption {
+	return func(o *ApplicationConfig) {
+		o.Distributed.BackendUpgradeTimeout = d
+	}
+}
+
 var EnableAutoApproveNodes = func(o *ApplicationConfig) {
 	o.Distributed.AutoApproveNodes = true
 }
@@ -150,11 +167,23 @@ const (
 	DefaultHealthCheckInterval = 15 * time.Second
 	DefaultStaleNodeThreshold  = 60 * time.Second
 	DefaultMCPCIJobTimeout     = 10 * time.Minute
+	DefaultBackendInstallTimeout = 15 * time.Minute
+	DefaultBackendUpgradeTimeout = 15 * time.Minute
 )
 
 // DefaultMaxUploadSize is the default maximum upload body size (50 GB).
 const DefaultMaxUploadSize int64 = 50 << 30
 
+// BackendInstallTimeoutOrDefault returns the configured timeout or the default.
+func (c DistributedConfig) BackendInstallTimeoutOrDefault() time.Duration {
+	return cmp.Or(c.BackendInstallTimeout, DefaultBackendInstallTimeout)
+}
+
+// BackendUpgradeTimeoutOrDefault returns the configured timeout or the default.
+func (c DistributedConfig) BackendUpgradeTimeoutOrDefault() time.Duration {
+	return cmp.Or(c.BackendUpgradeTimeout, DefaultBackendUpgradeTimeout)
+}
+
 // MCPToolTimeoutOrDefault returns the configured timeout or the default.
 func (c DistributedConfig) MCPToolTimeoutOrDefault() time.Duration {
 	return cmp.Or(c.MCPToolTimeout, DefaultMCPToolTimeout)
diff --git a/core/config/distributed_config_test.go b/core/config/distributed_config_test.go
new file mode 100644
index 000000000..8fae7ef72
--- /dev/null
+++ b/core/config/distributed_config_test.go
@@ -0,0 +1,36 @@
+package config_test
+
+import (
+	"time"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"github.com/mudler/LocalAI/core/config"
+)
+
+var _ = Describe("DistributedConfig backend NATS timeouts", func() {
+	Context("BackendInstallTimeoutOrDefault", func() {
+		It("returns 15 minutes when unset", func() {
+			c := config.DistributedConfig{}
+			Expect(c.BackendInstallTimeoutOrDefault()).To(Equal(15 * time.Minute))
+		})
+
+		It("returns the configured value when set", func() {
+			c := config.DistributedConfig{BackendInstallTimeout: 42 * time.Minute}
+			Expect(c.BackendInstallTimeoutOrDefault()).To(Equal(42 * time.Minute))
+		})
+	})
+
+	Context("BackendUpgradeTimeoutOrDefault", func() {
+		It("returns 15 minutes when unset", func() {
+			c := config.DistributedConfig{}
+			Expect(c.BackendUpgradeTimeoutOrDefault()).To(Equal(15 * time.Minute))
+		})
+
+		It("returns the configured value when set", func() {
+			c := config.DistributedConfig{BackendUpgradeTimeout: 30 * time.Minute}
+			Expect(c.BackendUpgradeTimeoutOrDefault()).To(Equal(30 * time.Minute))
+		})
+	})
+})