Avoid passing response_format to OpenAI's image generation API for the gpt-image-1 model

The API reference for `response_format` says:

> This parameter isn't supported for gpt-image-1 which will always return base64-encoded images.

Related to https://github.com/etkecc/baibot/issues/40

src/agent/provider/openai/controller.rs

@@ -36,6 +36,8 @@ use crate::{
 
 use super::config::Config;
 
+use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
+
 #[derive(Debug, Clone)]
 pub struct Controller {
     config: Config,
@@ -291,6 +293,7 @@ impl ControllerTrait for Controller {
             async_openai::types::ImageModel::DallE2 => Some(async_openai::types::ImageResponseFormat::B64Json),
             async_openai::types::ImageModel::DallE3 => Some(async_openai::types::ImageResponseFormat::B64Json),
             async_openai::types::ImageModel::Other(model_str) => match model_str.as_str() {
+                OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
                 _ => Some(async_openai::types::ImageResponseFormat::B64Json),
             },
         };

src/agent/provider/openai/mod.rs

@@ -16,6 +16,8 @@ use super::super::AgentInstantiationResult;
 use super::ConfigTrait;
 use super::controller::ControllerType;
 
+pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1: &str = "gpt-image-1";
+
 pub fn create_controller_from_yaml_value_config(
     agent_id: &str,
     config: serde_yaml::Value,