Retry config sync on concurrent changes

Author: michaelw

docs/development/index.md

@@ -9,3 +9,12 @@ description: Developer documentation for Thand Agent
 # Development
 
 Documentation for developers contributing to or extending the Thand Agent.
+
+## Config Mutation Invariant
+
+Configuration definition maps should be treated as immutable snapshots.
+When config changes, prefer replacing whole entries or whole definition maps
+instead of mutating nested state in place. Some older code paths still perform
+mutation-prone updates; keep new code aligned with the invariant and track
+cleanup of legacy exceptions in follow-up issues rather than extending them.
+Current cleanup work is tracked in [#306](https://github.com/thand-io/agent/issues/306).

internal/config/config.go

@@ -358,6 +358,7 @@ func (c *Config) ReloadConfig() error {
 			logrus.Infoln("Loaded workflows from external source:", len(workflows))
 			c.mu.Lock()
 			c.Workflows.Definitions = workflows
+			c.configGeneration++
 			c.mu.Unlock()
 		} else {
 			logrus.Warningln("No workflows loaded from external source")
@@ -376,6 +377,7 @@ func (c *Config) ReloadConfig() error {
 			logrus.Infoln("Loaded providers from external source:", len(providers))
 			c.mu.Lock()
 			c.Providers.Definitions = providers
+			c.configGeneration++
 			c.mu.Unlock()
 		} else {
 			logrus.Warningln("No providers loaded from external source")
@@ -392,6 +394,7 @@ func (c *Config) ReloadConfig() error {
 			logrus.Infoln("Loaded roles from external source:", len(roles))
 			c.mu.Lock()
 			c.Roles.Definitions = roles
+			c.configGeneration++
 			c.mu.Unlock()
 		} else {
 			logrus.Warningln("No roles loaded from external source")

internal/config/model.go

@@ -64,6 +64,12 @@ type Config struct {
 	logger thandLogger
 	mu     sync.RWMutex
 
+	// Incremented whenever synced config definitions actually change.
+	// Definition maps should be treated as immutable snapshots: callers should
+	// replace whole entries or whole maps rather than mutating nested state
+	// in place. Legacy mutation-prone paths are being tracked in issue #306.
+	configGeneration uint64
+
 	// Cached services client
 	initializeServiceClientOnce sync.Once
 	servicesClient              models.ServicesClientImpl