refactor: Enhance user context and quota management

- Add new context keys for user-related information
- Modify user cache and authentication middleware to populate context
- Refactor quota and notification services to use context-based user data
- Remove redundant database queries by leveraging context information
- Update various components to use new context-based user retrieval methods

relay/relay-text.go

@@ -248,6 +248,7 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 	if userQuota-preConsumedQuota < 0 {
 		return 0, 0, service.OpenAIErrorWrapperLocal(fmt.Errorf("chat pre-consumed quota failed, user quota: %s, need quota: %s", common.FormatQuota(userQuota), common.FormatQuota(preConsumedQuota)), "insufficient_user_quota", http.StatusForbidden)
 	}
+	relayInfo.UserQuota = userQuota
 	if userQuota > 100*preConsumedQuota {
 		// 用户额度充足，判断令牌额度是否充足
 		if !relayInfo.TokenUnlimited {
@@ -267,7 +268,7 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 	}
 
 	if preConsumedQuota > 0 {
-		err = service.PreConsumeTokenQuota(relayInfo, preConsumedQuota)
+		err := service.PreConsumeTokenQuota(relayInfo, preConsumedQuota)
 		if err != nil {
 			return 0, 0, service.OpenAIErrorWrapperLocal(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}