feat: add token caching middleware and max history messages config

internal/config/config.go

@@ -19,10 +19,11 @@ type Config struct {
 }
 
 type ServerConfig struct {
-	Port            int      `mapstructure:"port"`
-	Host            string   `mapstructure:"host"`
-	AuthTokens      []string `mapstructure:"auth_tokens"`
-	WSAllowedOrigin string   `mapstructure:"ws_allowed_origin"`
+	Port               int      `mapstructure:"port"`
+	Host               string   `mapstructure:"host"`
+	AuthTokens         []string `mapstructure:"auth_tokens"`
+	WSAllowedOrigin    string   `mapstructure:"ws_allowed_origin"`
+	MaxHistoryMessages int      `mapstructure:"max_history_messages"`
 }
 
 type DatabaseConfig struct {
@@ -96,6 +97,7 @@ func Load() (*Config, error) {
 	v.SetDefault("server.port", 8080)
 	v.SetDefault("server.host", "0.0.0.0")
 	v.SetDefault("server.auth_tokens", []string{})
+	v.SetDefault("server.max_history_messages", 0)
 	v.SetDefault("database.path", "./data/llm_proxy.db")
 	v.SetDefault("database.max_connections", 10)
 
@@ -142,6 +144,7 @@ func Load() (*Config, error) {
 	v.BindEnv("encryption_key", "LLM_PROXY__ENCRYPTION_KEY")
 	v.BindEnv("server.port", "LLM_PROXY__SERVER__PORT")
 	v.BindEnv("server.host", "LLM_PROXY__SERVER__HOST")
+	v.BindEnv("server.max_history_messages", "LLM_PROXY__SERVER__MAX_HISTORY_MESSAGES")
 	v.BindEnv("providers.ollama.enabled", "LLM_PROXY__PROVIDERS__OLLAMA__ENABLED")
 	v.BindEnv("providers.ollama.base_url", "LLM_PROXY__PROVIDERS__OLLAMA__BASE_URL")
 	v.BindEnv("providers.ollama.models", "LLM_PROXY__PROVIDERS__OLLAMA__MODELS")
@@ -174,6 +177,9 @@ func Load() (*Config, error) {
 		cfg.Server.Host = host
 
 	}
+	if maxHistory := os.Getenv("LLM_PROXY__SERVER__MAX_HISTORY_MESSAGES"); maxHistory != "" {
+		fmt.Sscanf(maxHistory, "%d", &cfg.Server.MaxHistoryMessages)
+	}
 
 	// Ollama overrides
 	if enabled := os.Getenv("LLM_PROXY__PROVIDERS__OLLAMA__ENABLED"); enabled != "" {