diff --git a/server-rs/crates/platform-image/src/image_provider/protocol/request.rs b/server-rs/crates/platform-image/src/image_provider/protocol/request.rs
index f93f23705..23470a04e 100644
--- a/server-rs/crates/platform-image/src/image_provider/protocol/request.rs
+++ b/server-rs/crates/platform-image/src/image_provider/protocol/request.rs
@@ -130,6 +130,12 @@ pub fn resolve_image_provider(model: &str) -> Result<ImageProvider, &'static str
     }
 }
 
+/// 尺寸钳制族判定：回答「这个模型值按 GPT Image 2 的像素预算处理吗」。
+///
+/// 中文注释：这里刻意包含业务模型名 `gpt-image-2.5`，因为业务边界可能直接用它
+/// 计算尺寸；而 `resolve_image_provider` 回答的是「发给哪个 provider」，所以
+/// 必须先在任务边界把业务名解析成 concrete key、收到业务名即拒绝。两处白名单
+/// 口径不同是有意设计，不要为了“对齐”把业务名放进 provider 白名单。
 pub(crate) fn is_gpt_image_2_family_model(model: &str) -> bool {
     matches!(
         normalize_image_model(model),