feat(runtime): capture step evidence in console

core/models.py

@@ -113,6 +113,9 @@ class Scene:
     width: int
     height: int
     elements: list[SceneElement] = field(default_factory=list)
+    # Keep raw OCR observations for local execution evidence without duplicating
+    # them in the normalized, LLM-facing scene payload.
+    ocr_elements: list[SceneElement] = field(default_factory=list)
 
     def to_dict(self) -> dict[str, Any]:
         return {
@@ -120,6 +123,9 @@ class Scene:
             "elements": [element.to_dict() for element in self.elements],
         }
 
+    def ocr_results_to_dict(self) -> list[dict[str, Any]]:
+        return [element.to_dict() for element in self.ocr_elements]
+
     @classmethod
     def from_dict(cls, data: dict[str, Any]) -> "Scene":
         screen = data.get("screen") or {}
@@ -127,8 +133,11 @@ class Scene:
             width=int(screen.get("width") or data.get("width") or 0),
             height=int(screen.get("height") or data.get("height") or 0),
             elements=[
+                SceneElement.from_dict(element) for element in data.get("elements", [])
+            ],
+            ocr_elements=[
                 SceneElement.from_dict(element)
-                for element in data.get("elements", [])
+                for element in data.get("ocr_elements", [])
             ],
         )
 
@@ -179,4 +188,3 @@ class Step:
             "result": self.result,
             "error": self.error,
         }
-