accept std/media/v1/Image payloads

dora's typed image is an Arrow struct of width, height, encoding and data --
it carries inside the payload what this node has been reading out of message
metadata. The decoder now takes either shape: a struct describes itself and
its metadata is ignored, a flat UInt8 buffer is described by width/height/
encoding beside it, and everything after unpacking is common.

The declared contract stays std/core/v1/UInt8, deliberately. Type
compatibility is directional -- Image satisfies a Bytes input, but a
std/core/v1/UInt8 output wired into an std/media/v1/Image input is a validate
error -- and dora-zed declares image_bgr as std/core/v1/UInt8. Flipping this
manifest now would break the camera. Accepting both shapes first is what lets
the producers move before the contract does.

output_framing is not part of this. It selects the wire format, raw or
arrow-ipc, and is not required for images: a struct payload was verified to
arrive identically under both framings, and validate does not ask for
arrow-ipc when an output is annotated std/media/v1/Image. It earns its keep
when the wire must be self-describing, such as crossing languages or
recording.

dora_image_view/decode.py

@@ -1,4 +1,12 @@
-"""Decoding of the `image` input into a BGR frame that can be drawn on."""
+"""Decoding of the `image` input into a BGR frame that can be drawn on.
+
+Two payload shapes are accepted, because dora has both in the field. The typed
+one is `std/media/v1/Image`: an Arrow struct carrying width, height, encoding
+and data together, so the frame is self-describing. The older one is a flat
+UInt8 buffer whose dimensions and encoding travel beside it in the message
+metadata, which is what a node declaring `std/core/v1/UInt8` sends -- dora-zed
+among them. Everything after unpacking is identical.
+"""
 
 import io
 
@@ -14,13 +22,18 @@ SELF_DESCRIBING = frozenset({"jpeg", "jpg", "jpe", "bmp", "webp", "png"})
 SUPPORTED = SELF_DESCRIBING | {"bgr8", "rgb8", "yuv420", "avif"}
 
 
-def to_bgr(storage, encoding: str, width: int | None, height: int | None) -> np.ndarray:
+# The fields of std/media/v1/Image. A payload carrying them describes itself and
+# its metadata is not consulted.
+IMAGE_FIELDS = ("width", "height", "encoding", "data")
+
+
+def to_bgr(storage, metadata: dict) -> np.ndarray:
     """Decode one `image` payload into a writable BGR array.
 
-    `width` and `height` come from the message metadata and are only required by
-    the raw encodings, which carry no dimensions of their own.
+    Accepts either an `std/media/v1/Image` struct or a flat buffer described by
+    the message metadata.
     """
-    buffer = storage.to_numpy().astype(np.uint8)
+    buffer, encoding, width, height = unpack(storage, metadata)
 
     if encoding == "bgr8":
         # Copy so the frame can be annotated: to_numpy() may be a view on the
@@ -53,6 +66,36 @@ def to_bgr(storage, encoding: str, width: int | None, height: int | None) -> np.
     raise RuntimeError(f"unsupported image encoding: {encoding}")
 
 
+def unpack(storage, metadata: dict) -> tuple[np.ndarray, str, int | None, int | None]:
+    """Split a payload of either shape into buffer, encoding, width and height."""
+    if _is_image_struct(storage):
+        # One image per message: the struct is a single-row array.
+        row = storage[0].as_py()
+        return (
+            np.frombuffer(row["data"], dtype=np.uint8),
+            str(row["encoding"]).lower(),
+            row["width"],
+            row["height"],
+        )
+
+    return (
+        storage.to_numpy().astype(np.uint8),
+        str(metadata.get("encoding", "bgr8")).lower(),
+        metadata.get("width"),
+        metadata.get("height"),
+    )
+
+
+def _is_image_struct(storage) -> bool:
+    """Whether the payload is an Arrow struct with the std/media/v1/Image fields."""
+    fields = getattr(getattr(storage, "type", None), "fields", None)
+
+    if fields is None:
+        return False
+
+    return all(name in {field.name for field in fields} for name in IMAGE_FIELDS)
+
+
 def _reshape(buffer: np.ndarray, width: int | None, height: int | None, encoding: str):
     width, height = _dimensions(width, height, encoding)
     return _take(buffer, width * height * 3, encoding).reshape(height, width, 3)

dora_image_view/main.py

@@ -67,12 +67,7 @@ def _decode_panel(event_id: str, value, metadata: dict) -> tuple[str, np.ndarray
     event loop to treat it as overlay state instead.
     """
     if event_id == "image":
-        return "image", decode.to_bgr(
-            value,
-            metadata.get("encoding", "bgr8").lower(),
-            metadata.get("width"),
-            metadata.get("height"),
-        )
+        return "image", decode.to_bgr(value, metadata)
 
     if event_id == "depth":
         return "depth", depth.colorize(depth.to_millimetres(value, metadata))