Map "MODEL_3D" input type to MultiType socket (mirror upstream union)

Follow-up to PR #20: the `MODEL_3D` input wire type now resolves to
an `IO.MultiType.Input(types=[IO.File3DGLB, IO.File3DOBJ,
IO.File3DFBX, IO.File3DAny])` socket — symmetric counterpart of the
existing `"MODEL_3D"` entry in `_OUTPUT_CLASSES` that maps to
`IO.File3DGLB.Output`.

Previously the descriptor wire type `"MODEL_3D"` fell through to the
opaque `IO.Custom("MODEL_3D").Input(...)` socket, which is a
single-comfytype socket the frontend only allows connections from
identically-tagged outputs. Real upstream 3D sources expose
different comfytypes:

- `Load3D` outputs `IO.File3DAny` (comfytype `FILE_3D`).
- Meshy / Hunyuan3D / Tripo / Rodin partner nodes output
  `IO.File3DGLB` (comfytype `FILE_3D_GLB`) via the existing
  `_OUTPUT_CLASSES["MODEL_3D"]` mapping.
- Meshy's dual `FILE_3D_FBX` output socket emits `FILE_3D_FBX`.

None of these connect to `IO.Custom("MODEL_3D")`. The upstream
Tencent Hunyuan3D MODEL_3D-input nodes (`TencentModelTo3DUVNode` /
`Tencent3DTextureEditNode` / `Tencent3DPartNode` /
`TencentSmartTopologyNode`) all use `IO.MultiType.Input(types=[...])`
to accept the union; mirroring that union here keeps the proxy
socket compatible with every existing 3D-emitting node.

`get_io_type()` on `IO.MultiType.Input` returns the comma-joined
inner type IDs (e.g. `"FILE_3D_GLB,FILE_3D_OBJ,FILE_3D_FBX,FILE_3D"`)
— matches the convention SxS workflows already use for their
`SaveGLB` connector inputs.

Per-node format validation (e.g. 3DTextureEdit's FBX-only
enforcement, 3DPart's FBX-only enforcement) is done server-side in
each provider's `execute()` against the inline envelope's `format`
extra; this socket-level filter is purely about frontend connection
validity.

Unblocks the paired comfy-rnp-server PR (`TencentModelTo3DUVNode_RNP`
+ `Tencent3DPartNode_RNP`) which uses the `["MODEL_3D", {}]` wire
shape.

Co-authored-by: Amp <amp@ampcode.com>
Amp-Thread-ID: https://ampcode.com/threads/T-019e362f-db40-7338-8ca4-99f617d89812

proxy_node.py

@@ -695,6 +695,30 @@ def _build_input(name: str, io_type: Any, options: dict[str, Any], optional: boo
         return IO.Audio.Input(name, **primitive_common)
     if io_type == "MASK":
         return IO.Mask.Input(name, **primitive_common)
+    if io_type == "MODEL_3D":
+        # 3D MODEL input: symmetric counterpart of the ``"MODEL_3D"``
+        # entry in ``_OUTPUT_CLASSES`` above. The Tencent Hunyuan3D
+        # MODEL_3D-input nodes (``TencentModelTo3DUVNode`` /
+        # ``Tencent3DTextureEditNode`` / ``Tencent3DPartNode`` /
+        # ``TencentSmartTopologyNode``) all declare their model_3d
+        # input as ``IO.MultiType.Input(types=[IO.File3DGLB,
+        # IO.File3DOBJ, IO.File3DFBX, IO.File3DAny])`` so the socket
+        # accepts any upstream 3D source: ``Load3D``'s ``File3DAny``
+        # output, Meshy / Hunyuan3D / Tripo / Rodin's per-format
+        # outputs (``FILE_3D_GLB`` / ``FILE_3D_OBJ`` / ``FILE_3D_FBX``),
+        # etc. Mirror that union here so the proxy socket accepts the
+        # same set of comfytypes upstream does. Per-node format
+        # validation (e.g. 3DTextureEdit's FBX-only enforcement) is
+        # done server-side in the provider's ``execute()`` against
+        # the inline envelope's ``format`` extra; this socket-level
+        # filter is purely about frontend connection validity.
+        return IO.MultiType.Input(
+            name,
+            types=[
+                IO.File3DGLB, IO.File3DOBJ, IO.File3DFBX, IO.File3DAny,
+            ],
+            **primitive_common,
+        )
     if io_type == "DYNAMIC_COMBO":
         # Wire shape: ``["DYNAMIC_COMBO", {"options": [{"key": str,
         # "inputs": [[name, io_type, opts], ...]}, ...], "tooltip": ...}]``.
@@ -1546,6 +1570,8 @@ async def _encode_inputs(
     * ``torch.Tensor`` rank 3 with last-dim != 3/4 → mask envelope (B,H,W).
       Rank-2 (H,W) tensors are also treated as masks.
     * ``dict`` with ``waveform`` + ``sample_rate`` → audio envelope.
+    * ``VideoInput`` subclass (duck-typed via ``save_to`` +
+      ``get_duration``) → mp4-base64 video envelope.
     * Everything else passes through as-is (already JSON-serializable).
 
     When ``max_inline_bytes`` is set, any envelope whose inline payload
@@ -1694,6 +1720,10 @@ def _encode_one(
 ) -> Any:
     if serialization.is_audio_input(value):
         return serialization.encode_audio_input(value)
+    if serialization.is_video_input(value):
+        return serialization.encode_video_input(value)
+    if serialization.is_model3d_input(value):
+        return serialization.encode_model3d_input(value)
     if not serialization._is_torch_tensor(value):
         return value
     rank = value.dim()

serialization.py

@@ -465,9 +465,44 @@ def decode_audio_envelope(envelope: dict[str, Any]) -> dict[str, Any]:
 
 
 # ---------------------------------------------------------------------------
-# Video decode (encode lands when a remote node accepts VIDEO inputs)
+# Video encode / decode
 # ---------------------------------------------------------------------------
 
+def encode_video_input(video: Any) -> dict[str, Any]:
+    """Encode a ComfyUI VIDEO (``VideoInput`` subclass) as an mp4-base64
+    video envelope.
+
+    Mirrors the AUDIO encoder above: re-encodes the Video object to an
+    in-memory mp4/H.264 byte buffer (matches upstream
+    ``comfy_api_nodes/util/conversions.py`` ``video_to_base64_string``)
+    and base64-encodes it. Populates ``duration_s`` metadata when the
+    Video object exposes ``get_duration()`` so server-side providers
+    (e.g. ``GrokVideoExtendProvider._validate_video_duration_envelope``)
+    can range-check without demuxing the MP4.
+    """
+    from comfy_api_nodes.util.conversions import video_to_base64_string
+
+    b64 = video_to_base64_string(video)
+    extra: dict[str, Any] = {}
+    duration_s: float | None = None
+    try:
+        getter = getattr(video, "get_duration", None)
+        if callable(getter):
+            d = getter()
+            if d is not None:
+                duration_s = float(d)
+    except Exception:
+        duration_s = None
+    if duration_s is not None:
+        extra["duration_s"] = duration_s
+    return {
+        "type":     "video",
+        "encoding": "mp4_base64",
+        "data":     b64,
+        **extra,
+    }
+
+
 def decode_video_envelope(envelope: dict[str, Any]) -> Any:
     """Decode a video envelope into a ComfyUI Video object (mp4 inline)."""
     encoding = envelope.get("encoding")
@@ -481,9 +516,69 @@ def decode_video_envelope(envelope: dict[str, Any]) -> Any:
 
 
 # ---------------------------------------------------------------------------
-# 3D model decode (encode lands when a remote node accepts MODEL_3D inputs)
+# 3D model encode / decode
 # ---------------------------------------------------------------------------
 
+def encode_model3d_input(model_3d: Any) -> dict[str, Any]:
+    """Encode a ComfyUI ``File3D`` (or compatible) as an inline
+    single-file 3D-model envelope.
+
+    Mirrors the AUDIO / VIDEO encoders above: reads the primary mesh
+    bytes (via the ``File3D`` API: ``get_data().read()`` returns a
+    ``BytesIO`` payload; falling back to ``read_bytes()`` for older
+    sources) and base64-encodes them. The envelope's ``encoding`` is
+    ``"glb_inline"`` (the generic single-file inline encoding the
+    server-side decoder dispatches on at :func:`decode_model3d_envelope`
+    — the decoder hands the bytes to ``File3D(BytesIO(...), format)``
+    regardless of whether the actual format is glb / obj / fbx / etc.,
+    so the ``encoding`` name is a logical "inline single-file 3D" tag
+    and the ``format`` extra picks the file extension).
+
+    Multi-file bundles (``BundledFile3D``-style values where every
+    companion file matters — e.g. an OBJ with a sibling .mtl + texture
+    PNGs) are not yet supported on the encode path: this PR ships the
+    minimal wire shape needed for the Tencent Hunyuan3D MODEL_3D-input
+    nodes which all upload a single file via ``upload_3d_model_to_comfyapi``
+    upstream. Bundle encode (``bundle_inline``) lands when a partner
+    node actually needs the companion bytes.
+    """
+    file_format = ""
+    fmt_attr = getattr(model_3d, "format", None)
+    if isinstance(fmt_attr, str):
+        file_format = fmt_attr.lower()
+
+    # ``File3D.get_data()`` returns a ``BytesIO`` (per
+    # ``comfy_api.latest._util.geometry_types.File3D``). Other File3D-
+    # compatible classes may instead expose ``read_bytes`` returning
+    # raw bytes; fall back to that for compatibility.
+    raw: bytes
+    get_data = getattr(model_3d, "get_data", None)
+    if callable(get_data):
+        buf = get_data()
+        if hasattr(buf, "seek"):
+            buf.seek(0)
+        raw = buf.read() if hasattr(buf, "read") else bytes(buf)
+    else:
+        read_bytes = getattr(model_3d, "read_bytes", None)
+        if callable(read_bytes):
+            raw = read_bytes()
+        else:
+            raise RnpProtocolError(
+                f"unsupported 3D model value: {type(model_3d).__name__!r} "
+                f"has no get_data() or read_bytes()",
+                code=ErrorCode.INTERNAL,
+            )
+
+    envelope: dict[str, Any] = {
+        "type":     "model_3d",
+        "encoding": "glb_inline",
+        "data":     base64.b64encode(raw).decode("ascii"),
+    }
+    if file_format:
+        envelope["format"] = file_format
+    return envelope
+
+
 # ---------------------------------------------------------------------------
 # Multi-file 3D bundle: a ``File3D``-compatible class that carries the
 # primary mesh plus N companion files (textures / .mtl / .bin / etc.).
@@ -837,6 +932,47 @@ def is_audio_input(value: Any) -> bool:
     )
 
 
+def is_video_input(value: Any) -> bool:
+    """Best-effort check for a ComfyUI ``VideoInput`` subclass.
+
+    Duck-types on the ``save_to`` + ``get_duration`` method pair: both
+    are defined on the ``VideoInput`` abstract base in
+    ``comfy_api.latest._input`` and present on every concrete subclass
+    (``VideoFromFile`` / ``VideoFromComponents``). Avoids importing
+    ``VideoInput`` at module load (which would pull torch via the
+    ``comfy_api`` tree).
+    """
+    if isinstance(value, dict):
+        return False
+    return (
+        callable(getattr(value, "save_to", None))
+        and callable(getattr(value, "get_duration", None))
+    )
+
+
+def is_model3d_input(value: Any) -> bool:
+    """Best-effort check for a ComfyUI ``File3D`` (or compatible).
+
+    Duck-types on the ``format`` string attribute + ``get_data``
+    callable: both are present on the ``File3D`` class in
+    ``comfy_api.latest._util.geometry_types`` and the
+    ``BundledFile3D`` subclass built lazily in
+    :func:`_bundled_file3d_class`. Avoids importing ``File3D`` at
+    module load (which would pull torch via the ``comfy_api`` tree).
+
+    The ``VideoInput`` shape (``save_to`` + ``get_duration``) does not
+    expose a ``format`` string property, so VIDEO and MODEL_3D values
+    don't collide; caller (:func:`_encode_one`) still dispatches
+    AUDIO / VIDEO before MODEL_3D as defense-in-depth.
+    """
+    if isinstance(value, dict):
+        return False
+    return (
+        isinstance(getattr(value, "format", None), str)
+        and callable(getattr(value, "get_data", None))
+    )
+
+
 def _is_torch_tensor(value: Any) -> bool:
     try:
         import torch
@@ -853,7 +989,9 @@ __all__ = [
     "decode_mask_envelope",
     "encode_audio_input",
     "decode_audio_envelope",
+    "encode_video_input",
     "decode_video_envelope",
+    "encode_model3d_input",
     "decode_model3d_envelope",
     "_bundled_file3d_class",
     "decode_envelope",
@@ -861,4 +999,6 @@ __all__ = [
     "is_image_tensor",
     "is_mask_tensor",
     "is_audio_input",
+    "is_video_input",
+    "is_model3d_input",
 ]