统一缺省图片模型的归一化结果

normalize_image_model 的空白模型回退改为 GPT_IMAGE_2_5_GENERATION_MODEL，与 build_image_request_body 默认值一致

补充单测断言空白模型与默认生成模型产出同一请求体

server-rs/crates/platform-image/src/image_provider/protocol/request.rs

@@ -87,9 +87,14 @@ pub fn build_nanobanana_generate_content_request_body(
     })
 }
 
+/// 归一化调用方传入的模型字符串。
+///
+/// 只处理缺省场景：空/空白输入落到当前默认生成模型 `GPT_IMAGE_2_5_GENERATION_MODEL`，
+/// 与 `build_image_request_body` 的默认值保持一致；显式传入的模型（含历史
+/// `gpt-image-2` 等旧值）原样保留，交给 `resolve_image_provider` 做路由。
 pub fn normalize_image_model(model: &str) -> &str {
     match model.trim() {
-        "" => GPT_IMAGE_2_MODEL,
+        "" => GPT_IMAGE_2_5_GENERATION_MODEL,
         value => value,
     }
 }

server-rs/crates/platform-image/tests/image_provider.rs

@@ -59,6 +59,15 @@ fn image_provider_clamps_gpt_image_2_explicit_pixel_sizes_to_its_supported_pixel
     assert_eq!(poster["size"], "1280x720");
 }
 
+#[test]
+fn image_provider_blank_model_falls_back_to_default_generation_model() {
+    let blank = build_image_request_body_with_model("  ", "空模型", None, "1024x1024", 1, &[]);
+    let default = build_image_request_body("空模型", None, "1024x1024", 1, &[]);
+
+    assert_eq!(blank["model"], GPT_IMAGE_2_5_GENERATION_MODEL);
+    assert_eq!(blank["model"], default["model"]);
+}
+
 #[test]
 fn image_provider_normalizes_2k_landscape_spec_size() {
     let body = build_image_request_body("生成规范图", None, "2048x1152", 1, &[]);