Merge pull request #22 from Comfy-Org/feat/encode-nested-autogrow-dicts

fix(encoder): recurse into nested AUTOGROW / DYNAMIC_COMBO runtime dicts

notes/run_encode_nested_dicts.py

@@ -0,0 +1,360 @@
+"""Smoke test for nested dict recursion in ``_encode_one`` /
+``_encode_inputs`` / ``_externalize_nested``.
+
+Background: ComfyUI's V3 ``build_nested_inputs`` rebuilds AUTOGROW and
+DYNAMIC_COMBO runtime kwargs into nested dicts (e.g. ``{"reference_images":
+{"image1": <tensor>, "image2": <tensor>}}`` for a top-level AG, or
+``{"model": {"branch": "wan2.7-r2v", "video_refs": {"video1":
+<VideoInput>}}}`` for AG-inside-DC). Before this fix, ``_encode_one``
+returned a non-tensor non-VideoInput non-audio dict unchanged, which
+meant per-slot tensors / VideoInputs survived past encoding and would
+either crash at ``json.dumps`` time or violate the server's contract
+(comfy_rnp_server's ``_ordered_wan_videoedit_image_envelopes`` etc.
+expect each slot value to already be an RNP envelope).
+
+Asserts:
+
+1. Top-level AG-of-IMAGE dict: each ``image<N>`` tensor becomes an
+   image envelope; the wrapping dict structure is preserved.
+2. Top-level AG-of-VIDEO dict: each ``video<N>`` VideoInput becomes a
+   video envelope.
+3. DC-wrapping-AG: top-level dict carries a branch key (string) AND a
+   nested AG dict of tensors / VideoInputs; encoder recurses one level
+   deeper and encodes the leaves while leaving the branch key untouched.
+4. AUDIO input is NOT swallowed by the dict-recursion branch: the
+   ``{"waveform": ..., "sample_rate": ...}`` shape still routes to
+   ``encode_audio_input``.
+5. Already-encoded envelope dicts pass through unchanged (no double-
+   encoding) — protects against re-running the encoder on a value that
+   the caller pre-encoded.
+6. Plain scalar config dicts (``{"width": 1024, "height": 576}``) pass
+   through unchanged.
+7. ``_externalize_nested`` walks the same shape: a nested AG dict of
+   oversize envelopes uploads each envelope via the stubbed externalize
+   path and the envelope's ``data`` field is swapped for ``uri``;
+   non-envelope siblings are untouched; the wrapping dict structure is
+   preserved.
+8. JSON-serializability post-condition: ``json.dumps`` round-trips the
+   full encoded payload (regression guard for the exact bug fixed).
+9. Single-tensor / single-VideoInput / single-audio top-level inputs
+   still encode the same way they did before (no regression for the
+   existing leaf path).
+
+Run with any python that has ``torch`` available (uses the ComfyUI
+venv on this workstation):
+
+    python notes/run_encode_nested_dicts.py
+
+The test loads ``_encode_one`` / ``_encode_inputs`` / ``_externalize_nested``
+out of ``proxy_node.py`` via AST extraction so we don't pay the cost
+of importing ComfyUI's ``comfy_api`` / ``comfy_api_nodes`` packages
+(which those helpers don't touch). Same standalone pattern as
+``run_image_max_batch.py``.
+"""
+from __future__ import annotations
+
+import ast
+import asyncio
+import importlib.util
+import json
+import os
+import sys
+import types
+
+import torch
+
+# ---------------------------------------------------------------------------
+# Locate the worktree under test (this file's parent's parent).
+# ---------------------------------------------------------------------------
+
+_HERE = os.path.dirname(os.path.abspath(__file__))
+_CLIENT_DIR = os.path.dirname(_HERE)
+
+
+def _load_protocol() -> types.ModuleType:
+    """Load ``protocol.py`` standalone (no relative imports)."""
+    path = os.path.join(_CLIENT_DIR, "protocol.py")
+    spec = importlib.util.spec_from_file_location("rnp_smoke_protocol", path)
+    mod = importlib.util.module_from_spec(spec)
+    sys.modules[spec.name] = mod
+    spec.loader.exec_module(mod)
+    return mod
+
+
+class _FakeVideoInput:
+    """Duck-typed VideoInput stand-in: ``save_to`` + ``get_duration``
+    are the only attrs ``serialization.is_video_input`` checks for."""
+    def __init__(self, tag: str, duration: float = 4.0) -> None:
+        self.tag = tag
+        self._duration = duration
+
+    def save_to(self, *args, **kwargs):  # pragma: no cover — never called by stub
+        return None
+
+    def get_duration(self) -> float:
+        return self._duration
+
+
+def _build_serialization_stub(protocol: types.ModuleType) -> types.ModuleType:
+    """Minimal ``serialization`` shim covering exactly the surface the
+    helpers under test use."""
+    mod = types.ModuleType("rnp_smoke_serialization")
+
+    def _is_torch_tensor(value):  # noqa: ANN001
+        return isinstance(value, torch.Tensor)
+
+    def is_audio_input(value):  # noqa: ANN001
+        return (
+            isinstance(value, dict)
+            and {"waveform", "sample_rate"} <= set(value.keys())
+        )
+
+    def is_video_input(value):  # noqa: ANN001
+        return (
+            callable(getattr(value, "save_to", None))
+            and callable(getattr(value, "get_duration", None))
+        )
+
+    def is_model3d_input(value):  # noqa: ANN001
+        return False  # unused in this test
+
+    def encode_image_tensor(tensor, *, accepts_batch=False):  # noqa: ANN001, ARG001
+        return {
+            "type": "image",
+            "encoding": "png_base64",
+            "data": f"img:{int(tensor.shape[0])}",
+        }
+
+    def encode_mask_tensor(tensor):  # noqa: ANN001, ARG001
+        return {"type": "mask", "encoding": "png_base64", "data": "mask"}
+
+    def encode_audio_input(value):  # noqa: ANN001, ARG001
+        return {"type": "audio", "encoding": "mp3_base64", "data": "aud"}
+
+    def encode_video_input(value):  # noqa: ANN001
+        return {
+            "type": "video",
+            "encoding": "mp4_base64",
+            "data": f"vid:{getattr(value, 'tag', '?')}",
+        }
+
+    def encode_model3d_input(value):  # noqa: ANN001, ARG001  # pragma: no cover
+        return {"type": "model_3d", "encoding": "glb_base64", "data": "m3d"}
+
+    HEAVY_TYPES = {"image", "mask", "audio", "video", "model_3d"}
+
+    def is_envelope(value):  # noqa: ANN001
+        return (
+            isinstance(value, dict)
+            and isinstance(value.get("type"), str)
+            and value.get("type") in HEAVY_TYPES
+            and isinstance(value.get("encoding"), str)
+        )
+
+    # Cap-aware ``maybe_externalize`` stub: swap ``data`` for ``uri`` when
+    # the inline payload would exceed ``max_inline_bytes``. Lets us prove
+    # that ``_externalize_nested`` reaches every per-slot envelope.
+    upload_log: list[str] = []
+
+    async def maybe_externalize(
+        envelope,  # noqa: ANN001
+        *, server_url=None, max_inline_bytes=None, auth_headers=None,  # noqa: ANN001, ARG001
+    ):
+        if not server_url or max_inline_bytes is None:
+            return envelope
+        data = envelope.get("data")
+        if not isinstance(data, str):
+            return envelope
+        if len(data) <= max_inline_bytes:
+            return envelope
+        upload_log.append(f"{envelope.get('type')}:{data}")
+        out = {k: v for k, v in envelope.items() if k != "data"}
+        out["uri"] = f"https://upload/{envelope.get('type')}/{len(upload_log)}"
+        return out
+
+    mod._is_torch_tensor = _is_torch_tensor
+    mod.is_audio_input = is_audio_input
+    mod.is_video_input = is_video_input
+    mod.is_model3d_input = is_model3d_input
+    mod.encode_image_tensor = encode_image_tensor
+    mod.encode_mask_tensor = encode_mask_tensor
+    mod.encode_audio_input = encode_audio_input
+    mod.encode_video_input = encode_video_input
+    mod.encode_model3d_input = encode_model3d_input
+    mod.is_envelope = is_envelope
+    mod.maybe_externalize = maybe_externalize
+    mod._upload_log = upload_log  # exposed for assertions
+    return mod
+
+
+def _build_proxy_node_stub(
+    protocol: types.ModuleType, serialization: types.ModuleType,
+) -> types.ModuleType:
+    """Extract the helpers under test from ``proxy_node.py``."""
+    mod = types.ModuleType("rnp_smoke_proxy_node")
+    mod.__dict__.update({
+        "Any": object,
+        "log": types.SimpleNamespace(warning=lambda *a, **kw: None),
+        "serialization": serialization,
+        "RnpProtocolError": protocol.RnpProtocolError,
+        "ErrorCode": protocol.ErrorCode,
+    })
+    src_path = os.path.join(_CLIENT_DIR, "proxy_node.py")
+    with open(src_path, "r", encoding="utf-8") as fh:
+        src = fh.read()
+    tree = ast.parse(src)
+    wanted = {
+        "_enforce_local_validate",
+        "_check_image_max_batch",
+        "_encode_one",
+        "_encode_inputs",
+        "_externalize_nested",
+    }
+    nodes = [
+        n for n in tree.body
+        if isinstance(n, (ast.AsyncFunctionDef, ast.FunctionDef))
+        and n.name in wanted
+    ]
+    snippet = ast.Module(body=nodes, type_ignores=[])
+    code = compile(snippet, src_path, "exec")
+    exec(code, mod.__dict__)
+    missing = wanted - set(mod.__dict__)
+    if missing:
+        raise RuntimeError(f"proxy_node helpers missing from extract: {missing}")
+    return mod
+
+
+# ---------------------------------------------------------------------------
+# Tests
+# ---------------------------------------------------------------------------
+
+async def main() -> int:
+    protocol = _load_protocol()
+    serialization = _build_serialization_stub(protocol)
+    proxy_node = _build_proxy_node_stub(protocol, serialization)
+
+    img1 = torch.zeros((1, 64, 64, 3), dtype=torch.float32)
+    img2 = torch.zeros((1, 32, 32, 3), dtype=torch.float32)
+    vid1 = _FakeVideoInput("v1")
+    vid2 = _FakeVideoInput("v2")
+    audio = {
+        "waveform": torch.zeros((1, 1, 1000), dtype=torch.float32),
+        "sample_rate": 16000,
+    }
+
+    # ---- 1. Top-level AG-of-IMAGE dict encodes per-slot
+    out = await proxy_node._encode_inputs(
+        {"reference_images": {"image1": img1, "image2": img2}},
+    )
+    refs = out["reference_images"]
+    assert isinstance(refs, dict) and set(refs.keys()) == {"image1", "image2"}, refs
+    assert refs["image1"]["type"] == "image" and refs["image1"]["data"] == "img:1"
+    assert refs["image2"]["type"] == "image" and refs["image2"]["data"] == "img:1"
+    print("ok: top-level AG-of-IMAGE encoded per slot")
+
+    # ---- 2. Top-level AG-of-VIDEO dict encodes per-slot
+    out = await proxy_node._encode_inputs(
+        {"video_refs": {"video1": vid1, "video2": vid2}},
+    )
+    vrefs = out["video_refs"]
+    assert isinstance(vrefs, dict) and set(vrefs.keys()) == {"video1", "video2"}, vrefs
+    assert vrefs["video1"]["type"] == "video" and vrefs["video1"]["data"] == "vid:v1"
+    assert vrefs["video2"]["type"] == "video" and vrefs["video2"]["data"] == "vid:v2"
+    print("ok: top-level AG-of-VIDEO encoded per slot")
+
+    # ---- 3. DC-wrapping-AG: branch key untouched, nested AG dict encoded
+    dc_value = {
+        "model": "wan2.7-r2v",
+        "video_refs": {"video1": vid1},
+        "reference_images": {"image1": img1, "image2": img2},
+        "duration": 5,
+    }
+    out = await proxy_node._encode_inputs({"model": dc_value})
+    enc = out["model"]
+    assert enc["model"] == "wan2.7-r2v", enc
+    assert enc["duration"] == 5, enc
+    assert enc["video_refs"]["video1"]["type"] == "video"
+    assert enc["reference_images"]["image1"]["type"] == "image"
+    assert enc["reference_images"]["image2"]["type"] == "image"
+    print("ok: DC-wrapping-AG encoded leaves at every level")
+
+    # ---- 4. AUDIO dict is encoded, NOT recursed into
+    out = await proxy_node._encode_inputs({"audio": audio})
+    assert out["audio"] == {"type": "audio", "encoding": "mp3_base64", "data": "aud"}
+    print("ok: AUDIO dict still routes to encode_audio_input")
+
+    # ---- 5. Already-encoded envelope passes through (no double-encode)
+    pre_encoded = {"type": "image", "encoding": "png_base64", "data": "preimg"}
+    out = await proxy_node._encode_inputs({"images": pre_encoded})
+    assert out["images"] == pre_encoded, out
+    print("ok: pre-encoded envelope passed through unchanged")
+
+    # ---- 6. Plain scalar config dict passes through unchanged
+    out = await proxy_node._encode_inputs(
+        {"config": {"width": 1024, "height": 576, "name": "x"}},
+    )
+    assert out["config"] == {"width": 1024, "height": 576, "name": "x"}, out
+    print("ok: scalar config dict passed through unchanged")
+
+    # ---- 7. _externalize_nested walks per-slot envelopes
+    serialization._upload_log.clear()
+    big_img = torch.zeros((1, 64, 64, 3), dtype=torch.float32)
+    # encode_image_tensor stub emits ``data="img:1"`` (5 chars). Cap at 3
+    # to force every slot to externalize.
+    out = await proxy_node._encode_inputs(
+        {"reference_images": {"image1": big_img, "image2": big_img}},
+        server_url="https://fake.server",
+        max_inline_bytes=3,
+    )
+    refs = out["reference_images"]
+    assert refs["image1"].get("uri", "").startswith("https://upload/image/"), refs
+    assert refs["image2"].get("uri", "").startswith("https://upload/image/"), refs
+    assert "data" not in refs["image1"] and "data" not in refs["image2"]
+    assert len(serialization._upload_log) == 2, serialization._upload_log
+    print("ok: nested AG envelopes externalized per slot")
+
+    # ---- 7b. _externalize_nested leaves non-envelope siblings alone
+    serialization._upload_log.clear()
+    out = await proxy_node._encode_inputs(
+        {"model": {
+            "model": "wan2.7-r2v",
+            "duration": 5,
+            "reference_images": {"image1": big_img},
+        }},
+        server_url="https://fake.server",
+        max_inline_bytes=3,
+    )
+    enc = out["model"]
+    assert enc["model"] == "wan2.7-r2v" and enc["duration"] == 5, enc
+    assert enc["reference_images"]["image1"]["uri"].startswith("https://upload/image/")
+    print("ok: scalar siblings preserved alongside externalized envelopes")
+
+    # ---- 8. JSON-serializability post-condition
+    payload = await proxy_node._encode_inputs({
+        "reference_images": {"image1": img1, "image2": img2},
+        "video_refs": {"video1": vid1},
+        "audio": audio,
+        "config": {"width": 1024},
+        "scalar": "hello",
+        "n": 42,
+    })
+    json.dumps(payload)  # would raise TypeError pre-fix
+    print("ok: full encoded payload is JSON-serializable")
+
+    # ---- 9. Leaf-path regression: single-tensor / single-video / single-audio
+    out = await proxy_node._encode_inputs({"image": img1})
+    assert out["image"]["type"] == "image", out
+    out = await proxy_node._encode_inputs({"video": vid1})
+    assert out["video"]["type"] == "video", out
+    out = await proxy_node._encode_inputs({"audio": audio})
+    assert out["audio"]["type"] == "audio", out
+    out = await proxy_node._encode_inputs({"prompt": "hi", "seed": 7})
+    assert out == {"prompt": "hi", "seed": 7}, out
+    print("ok: top-level leaf path unchanged")
+
+    print("ALL OK")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(asyncio.run(main()))

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
@@ -1574,17 +1600,65 @@ async def _encode_inputs(
             name, value, validate_map.get(name) or {}, node_id=node_id,
         )
         encoded = _encode_one(name, value, serialization_map.get(name))
-        # Only envelope-shaped values can be externalized; scalars pass
-        # straight through ``maybe_externalize`` unchanged.
-        if serialization.is_envelope(encoded):
-            encoded = await serialization.maybe_externalize(
-                encoded,
+        # Externalize any envelope payloads, walking into nested dicts so
+        # AUTOGROW slot values and DYNAMIC_COMBO sub-inputs whose encoded
+        # form is a per-slot envelope are uploaded the same way a
+        # top-level singleton envelope is. ``_externalize_nested`` is a
+        # no-op on plain scalars and on dicts that contain no envelopes.
+        encoded = await _externalize_nested(
+            encoded,
+            server_url=server_url,
+            max_inline_bytes=max_inline_bytes,
+            auth_headers=auth_headers,
+        )
+        out[name] = encoded
+    return out
+
+
+async def _externalize_nested(
+    value: Any,
+    *,
+    server_url: str | None,
+    max_inline_bytes: int | None,
+    auth_headers: dict[str, str] | None,
+) -> Any:
+    """Recursively externalize any RNP envelopes inside ``value``.
+
+    Mirrors :func:`_encode_one`'s dict-recursion: ComfyUI hands the
+    proxy_node nested AUTOGROW / DYNAMIC_COMBO runtime dicts
+    (e.g. ``{"reference_images": {"image1": <env>, "image2": <env>}}``
+    or ``{"model": {"branch": "wan2.7-r2v",
+    "video_refs": {"video1": <env>}}}``); without this walk the
+    per-slot envelopes would ship inline regardless of
+    ``max_inline_bytes`` because :func:`_encode_inputs` only inspected
+    the top-level value.
+
+    Stops at envelope leaves (delegates the per-envelope decision to
+    :func:`serialization.maybe_externalize`) and at plain scalars (leaves
+    them unchanged). Lists are intentionally left alone — AG/DC runtime
+    shapes always materialize as dicts, never lists, and recursing into
+    arbitrary lists would touch opaque payloads. Recursion is bounded
+    by the AUTOGROW max slot count (100) and the maximum DC branch
+    nesting depth (1 today), so an in-place ``async def`` walk is fine.
+    """
+    if serialization.is_envelope(value):
+        return await serialization.maybe_externalize(
+            value,
+            server_url=server_url,
+            max_inline_bytes=max_inline_bytes,
+            auth_headers=auth_headers,
+        )
+    if isinstance(value, dict):
+        out: dict[str, Any] = {}
+        for k, v in value.items():
+            out[k] = await _externalize_nested(
+                v,
                 server_url=server_url,
                 max_inline_bytes=max_inline_bytes,
                 auth_headers=auth_headers,
             )
-        out[name] = encoded
-    return out
+        return out
+    return value
 
 
 def _enforce_local_validate(
@@ -1692,8 +1766,28 @@ def _encode_one(
     value: Any,
     accepted_encodings: list[str] | None = None,
 ) -> Any:
+    # ComfyUI's V3 ``build_nested_inputs`` rebuilds AUTOGROW / DYNAMIC_COMBO
+    # runtime kwargs into nested dicts (``{"reference_images": {"image1":
+    # <tensor>, ...}}`` for top-level AG; ``{"<dc-name>": branch_key,
+    # "<nested-ag>": {"video1": <VideoInput>, ...}}`` for AG-inside-DC).
+    # Recurse into plain dicts so heavy leaves anywhere in that tree get
+    # encoded — without this an AG-of-IMAGE slot would ship the raw
+    # torch.Tensor inside a dict and crash at ``json.dumps`` time. Stops
+    # at envelope dicts (already-encoded payloads) so we don't double-
+    # encode wire-shape values that happen to be dicts.
+    if serialization.is_envelope(value):
+        return value
+    if isinstance(value, dict) and not serialization.is_audio_input(value):
+        return {
+            k: _encode_one(f"{name}.{k}", v, accepted_encodings)
+            for k, v in value.items()
+        }
     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",
 ]