feat(api): support asImage=true on screen and zoom

server/app.py

@@ -5,7 +5,7 @@ import time
 import uuid
 from typing import Literal, Optional
 
-from fastapi import Depends, FastAPI, Header, HTTPException
+from fastapi import Depends, FastAPI, Header, HTTPException, Response
 from pydantic import BaseModel, Field, model_validator
 
 
@@ -160,13 +160,17 @@ def _capture_screen():
         return image, {"x": mon["left"], "y": mon["top"], "width": mon["width"], "height": mon["height"]}
 
 
-def _encode_image(image, image_format: str, jpeg_quality: int) -> str:
+def _serialize_image(image, image_format: str, jpeg_quality: int) -> bytes:
     buf = io.BytesIO()
     if image_format == "jpeg":
         image.save(buf, format="JPEG", quality=jpeg_quality)
     else:
         image.save(buf, format="PNG")
-    return base64.b64encode(buf.getvalue()).decode("ascii")
+    return buf.getvalue()
+
+
+def _encode_image(image, image_format: str, jpeg_quality: int) -> str:
+    return base64.b64encode(_serialize_image(image, image_format, jpeg_quality)).decode("ascii")
 
 
 def _draw_grid(image, region_x: int, region_y: int, rows: int, cols: int, include_labels: bool):
@@ -335,6 +339,7 @@ def screen(
     include_labels: bool = True,
     image_format: Literal["png", "jpeg"] = "png",
     jpeg_quality: int = 85,
+    asImage: bool = False,
     _: None = Depends(_auth),
 ):
     req = ScreenRequest(
@@ -354,6 +359,11 @@ def screen(
         out_img, grid_meta = _draw_grid(base_img, mon["x"], mon["y"], req.grid_rows, req.grid_cols, req.include_labels)
         meta.update(grid_meta)
 
+    if asImage:
+        image_bytes = _serialize_image(out_img, req.image_format, req.jpeg_quality)
+        media_type = "image/jpeg" if req.image_format == "jpeg" else "image/png"
+        return Response(content=image_bytes, media_type=media_type)
+
     encoded = _encode_image(out_img, req.image_format, req.jpeg_quality)
     return {
         "ok": True,
@@ -370,7 +380,7 @@ def screen(
 
 
 @app.post("/zoom")
-def zoom(req: ZoomRequest, _: None = Depends(_auth)):
+def zoom(req: ZoomRequest, asImage: bool = False, _: None = Depends(_auth)):
     base_img, mon = _capture_screen()
 
     cx = req.center_x - mon["x"]
@@ -404,6 +414,11 @@ def zoom(req: ZoomRequest, _: None = Depends(_auth)):
         out_img, grid_meta = _draw_grid(crop, region_x, region_y, req.grid_rows, req.grid_cols, req.include_labels)
         meta.update(grid_meta)
 
+    if asImage:
+        image_bytes = _serialize_image(out_img, req.image_format, req.jpeg_quality)
+        media_type = "image/jpeg" if req.image_format == "jpeg" else "image/png"
+        return Response(content=image_bytes, media_type=media_type)
+
     encoded = _encode_image(out_img, req.image_format, req.jpeg_quality)
 
     return {