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 != "" {

internal/middleware/auth.go

@@ -4,6 +4,8 @@ import (
 	"log"
 	"net/http"
 	"strings"
+	"sync"
+	"time"
 
 	"gophergate/internal/db"
 	"gophergate/internal/models"
@@ -11,6 +13,15 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
+type tokenCacheEntry struct {
+	clientID  string
+	expiredAt time.Time
+}
+
+var (
+	tokenCache sync.Map // map[string]tokenCacheEntry
+)
+
 func AuthMiddleware(database *db.DB, requireAuth bool) gin.HandlerFunc {
 	return func(c *gin.Context) {
 		authHeader := c.GetHeader("Authorization")
@@ -52,11 +63,39 @@ func AuthMiddleware(database *db.DB, requireAuth bool) gin.HandlerFunc {
 			return
 		}
 
-		// Try to resolve client from database with a read-only SELECT
+		// Try to resolve client from cache first
 		var clientID string
-		err := database.Get(&clientID, "SELECT client_id FROM client_tokens WHERE token = ? AND is_active = 1", token)
+		var dbErr error
+		now := time.Now()
+		if cached, ok := tokenCache.Load(token); ok {
+			entry := cached.(tokenCacheEntry)
+			if now.Before(entry.expiredAt) {
+				clientID = entry.clientID
+			}
+		}
 
-		if err == nil {
+		// If cache miss (or expired), query database
+		if clientID == "" {
+			var fetchedID string
+			dbErr = database.Get(&fetchedID, "SELECT client_id FROM client_tokens WHERE token = ? AND is_active = 1", token)
+			if dbErr == nil {
+				clientID = fetchedID
+				// Cache valid token for 10 seconds
+				tokenCache.Store(token, tokenCacheEntry{
+					clientID:  clientID,
+					expiredAt: now.Add(10 * time.Second),
+				})
+			} else {
+				// If error (invalid/inactive token), cache negative result for 2 seconds
+				// to avoid hammering SQLite on repeated invalid requests
+				tokenCache.Store(token, tokenCacheEntry{
+					clientID:  "",
+					expiredAt: now.Add(2 * time.Second),
+				})
+			}
+		}
+
+		if clientID != "" {
 			c.Set("auth", models.AuthInfo{
 				Token:    token,
 				ClientID: clientID,
@@ -76,7 +115,11 @@ func AuthMiddleware(database *db.DB, requireAuth bool) gin.HandlerFunc {
 			if len(token) > 8 {
 				maskedToken = token[:3] + "••••" + token[len(token)-4:]
 			}
-			log.Printf("Token not found, inactive or error in DB: %s (err: %v)", maskedToken, err)
+			if dbErr != nil {
+				log.Printf("Token not found, inactive or error in DB: %s (err: %v)", maskedToken, dbErr)
+			} else {
+				log.Printf("Token not found or inactive: %s", maskedToken)
+			}
 			c.AbortWithStatusJSON(http.StatusUnauthorized, gin.H{
 				"error": gin.H{
 					"message": "Invalid or inactive client token.",