识别树根节点改为模型根节点

识别协议改用 trees[].root 并保留根节点非几何字段
同步根节点解析校验、提示词与 UI 树转换

apps/ai-game-creator-shell/src-tauri/src/ui_editor/commands/recognition.rs

@@ -12,7 +12,7 @@ use crate::ui_editor::layout::node::{Node as LayoutNode, NodeMetadata, NodeSourc
 use crate::ui_editor::layout::transform::Transform;
 use crate::ui_editor::resource::ui_design_image::UIDesignImage;
 use crate::ui_editor::state::{State, UITree};
-use crate::ui_editor::utils::{NodeId, UIDesignImageId};
+use crate::ui_editor::utils::{random_node_id, NodeId, UIDesignImageId};
 use nalgebra::{Point2, Vector2};
 use platform_llm::{
     LlmFunctionTool, LlmMessage, LlmMessageContentPart, LlmRunRequest, LlmToolChoice,
@@ -37,6 +37,7 @@ const SYSTEM_PROMPT: &str = r#"
 * 只识别 UI元素. 要区分动态内容, 不要白费力气识别应该由程序生成/绘制的内容.(此类内容应该用一个整体节点+自然语言描述) 除此之外必须完整包含所有元素,结构.
 * 无法确定类型、层级、关系时，在 UnSure 中写明原因。
 * 返回的 trees 必须与输入图片一一对应，每张输入图片只能有一棵树，不能合并多张图片的树。 每棵树的 src_ui_design_image_id 必须等于对应输入图片标注的 id。
+* 每棵树root的 global_pos_x_px、global_pos_y_px、width_px、height_px、local_anchor 仅为占位并会被忽略，给合法值即可.
 * 每棵树必须使用自己的输入图片原始像素坐标系(0,0 as left top)输出
   global_pos_x_px、global_pos_y_px、width_px、height_px；
 * 为了响应式布局, 我们提供了类似godot的Anchor参数,  可以使用语义化的预设或者可custom的直接操作min max, 请准确地根据父子布局的关系使用
@@ -122,7 +123,7 @@ struct RecognitionNode {
 #[schemars(deny_unknown_fields)]
 struct RecognitionTree {
     src_ui_design_image_id: UIDesignImageId,
-    children: Vec<RecognitionNode>,
+    root: RecognitionNode,
 }
 
 #[derive(Clone, Debug, Deserialize, PartialEq, Serialize, JsonSchema)]
@@ -150,10 +151,14 @@ fn validate_recognition_response_shape(value: &serde_json::Value) -> Result<(),
         return Err(format!("识别结果最多包含 {MAX_REFERENCES} 棵界面树"));
     }
     for tree in trees {
-        let children = tree
+        let root = tree
+            .get("root")
+            .and_then(serde_json::Value::as_object)
+            .ok_or_else(|| "识别树缺少 root 节点".to_string())?;
+        let children = root
             .get("children")
             .and_then(serde_json::Value::as_array)
-            .ok_or_else(|| "识别树缺少 children 数组".to_string())?;
+            .ok_or_else(|| "识别树根节点缺少 children 数组".to_string())?;
         let mut stack = children
             .iter()
             .map(|node| (node, 1usize))
@@ -365,7 +370,7 @@ fn validate_tree_image_ids(
         if !seen.insert(tree.src_ui_design_image_id.clone()) {
             return Err("LLM 为同一界面图返回了重复 UI 树".to_string());
         }
-        validate_confidence(&tree.children)?;
+        validate_confidence(std::slice::from_ref(&tree.root))?;
     }
     if seen.len() != allowed.len() {
         return Err("LLM 未为当前识别上下文的每张界面图返回 UI 树".to_string());
@@ -445,8 +450,8 @@ mod tests {
             .collect::<Vec<_>>();
         let response = serde_json::json!({
             "trees": [
-                {"children": leaves.clone()},
-                {"children": leaves}
+                {"root": {"children": leaves.clone()}},
+                {"root": {"children": leaves}}
             ]
         });
         validate_recognition_response_shape(&response)
@@ -459,7 +464,7 @@ mod tests {
             .map(|_| serde_json::json!({"children": []}))
             .collect::<Vec<_>>();
         assert!(validate_recognition_response_shape(&serde_json::json!({
-            "trees": [{"children": oversized}]
+            "trees": [{"root": {"children": oversized}}]
         }))
         .is_err());
 
@@ -468,7 +473,7 @@ mod tests {
             nested = serde_json::json!({"children": [nested]});
         }
         assert!(validate_recognition_response_shape(&serde_json::json!({
-            "trees": [{"children": [nested]}]
+            "trees": [{"root": {"children": [nested]}}]
         }))
         .is_err());
     }
@@ -587,7 +592,7 @@ mod tests {
         let slave = UIDesignImageId::new("slave").expect("valid image id");
         let tree = |id: UIDesignImageId| RecognitionTree {
             src_ui_design_image_id: id,
-            children: Vec::new(),
+            root: test_node(),
         };
 
         assert!(validate_tree_image_ids(
@@ -820,24 +825,32 @@ pub(crate) async fn recognize_ui_impl_with_provider(
                 .ok_or_else(|| format!("缺少界面图 {} 的识别树", image_id.as_str()))?;
             let size = image_layout_size(image)?;
             let root_rect = UIRect::new(Point2::origin(), size);
-            let children = tree
+            // The recognition root is a real UI node. Its pixel geometry and
+            // anchor are intentionally ignored; the page root always fills
+            // the design image while the other recognition fields take effect.
+            let recognition_root = tree.root;
+            let children = recognition_root
                 .children
                 .iter()
                 .map(|node| convert_node(node, &image_id, image, root_rect))
                 .collect::<Result<Vec<_>, _>>()?;
+            let root_layout_status = match recognition_root.confidence {
+                Confidence::Confident => StageStatus::NoProblem,
+                Confidence::UnSure(reason) => StageStatus::NeedReview(reason),
+            };
             let root = LayoutNode {
                 id: random_node_id(),
                 layout: ControlLayout::with_transform(Transform::stretch()),
                 metadata: NodeMetadata {
-                    name: "页面根节点".to_string(),
-                    description: String::new(),
-                    layout_status: StageStatus::NoProblem,
+                    name: recognition_root.name,
+                    description: recognition_root.description,
+                    layout_status: root_layout_status,
                     component_status: StageStatus::NoProblem,
                     allow_llm_edit_layout: true,
                     allow_llm_edit_component: true,
-                    source: NodeSource::System,
+                    source: NodeSource::Llm,
                 },
-                component: None,
+                component: recognition_root.component.into_option(),
                 children_display_mode: ChildrenDisplayMode::Stack,
                 children,
             };