patches: glm53-dflash-01 v4 -- all three SupportsEagle3 members on the wrapper

The v4 window boot named the real presence-check rule: isinstance against a
runtime_checkable Protocol walks __protocol_attrs__ (which includes members
inherited from BASE protocols) and getattr_static()s each one off the instance,
breaking on the first missing attribute. SupportsEagleBase declares
has_own_lm_head/has_own_embed_tokens as plain instance-var annotations, so
v3's bare supports_eagle3 flag still failed. Replicated in-image with stock
typing: flag-only class -> False; flag + the two base members -> True.

v4 declares all three on Glm5NextForCausalLM:
    supports_eagle3: ClassVar[Literal[True]] = True
    has_own_lm_head: bool = False
    has_own_embed_tokens: bool = False
(False is correct for the two: the wrapper delegates embed/lm_head to its
trunk. The MRO-safe attribute path is kept from v3.)

base 008eeaa2... -> patched 60f27aad..., apply-verified against the pinned
image (patch -p1 reproduces the sha256 and matches the mounted file).

scripts/patches/glm53-dflash-01-aux-hidden-states.patch

@@ -29,8 +29,16 @@
 #         supports_eagle3: ClassVar[Literal[True]] = True
 #     which satisfies presence-based isinstance without touching the MRO, and pairs
 #     with the EagleModelMixin on the trunk that supplies the real aux-layer plumbing.
-#     (SupportsEagleBase's has_own_lm_head/has_own_embed_tokens default to False, which
-#     is what a wrapper that delegates embed/lm_head to its trunk wants.)
+#     CAUGHT LATE BY ANOTHER BOOT: the presence check walks ALL `__protocol_attrs__`
+#     INCLUDING base-protocol members (typing._ProtocolMeta.__instancecheck__ loops
+#     `getattr_static(instance, attr)` over every member and breaks on the first
+#     AttributeError).  SupportsEagleBase declares `has_own_lm_head: bool = False` and
+#     `has_own_embed_tokens: bool = False` (plain instance-var annotations), so the
+#     flag ALONE still fails isinstance -- replicated in-image with stock typing
+#     (flag-only class -> False; flag + the two base members -> True).  v4 therefore
+#     declares all three on the wrapper: supports_eagle3, has_own_lm_head,
+#     has_own_embed_tokens.  False is the right value for the two: the wrapper
+#     delegates embed/lm_head to its trunk.
 #   * interfaces.py:1673-1719 -- the inherited defaults unwrap
 #     `holder = getattr(parent_ref, "model", parent_ref)`, assert
 #     `isinstance(holder, EagleModelMixin)`, set `holder._set_aux_hidden_state_layers`, and
@@ -47,7 +55,8 @@
 # carries the already-summed single-stream state -- its non-mHC branch re-splits
 # `residual = hidden_states` inside the layer -- so this is the equivalent of
 # deepseek_v2's `hidden_states + residual`); the conditional tuple return; and
-# SupportsEagle3 among Glm5NextForCausalLM's bases.
+# the three SupportsEagle3 member attributes on Glm5NextForCausalLM (the flag plus
+# SupportsEagleBase's two defaults).
 #
 # HONEST SCOPE: this makes the interface PRESENT, which is exactly what the engine
 # checks -- it does not make drafts GOOD, and per the measured profile it is not a
@@ -57,12 +66,12 @@
 #
 # TARGET: vllm/models/glm5next/common/model.py   (inside the pinned image)
 #   base    sha256 008eeaa2a07e091465319f86900b5a321d921238723ccbe22e6b9e971e1d2b28
-#   patched sha256 4c9a632b5173fdefe0672b810b54f91b88ed65decf0f4a76fde92527970bee8e
+#   patched sha256 60f27aad36ab9610d335bd0d9a2e177d8e26b6af1e81b3a31adf5f5cca8cab68
 #
 # APPLY: `patch -p1` from the vllm package root, or bind-mount the patched file over
 # site-packages (which is what a scratch-launcher DFLASH_PATCH=1 does).
 --- orig/vllm/models/glm5next/common/model.py	2026-09-30 15:57:08.910029614 -0700
-+++ new/vllm/models/glm5next/common/model.py	2026-09-30 17:04:20.104521484 -0700
++++ new/vllm/models/glm5next/common/model.py	2026-09-30 17:22:36.124257958 -0700
 @@ -95,6 +95,12 @@
  logger = init_logger(__name__)
  
@@ -110,11 +119,13 @@
          return hidden_states
  
      def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
-@@ -937,6 +952,8 @@
+@@ -937,6 +952,10 @@
  class Glm5NextForCausalLM(
      nn.Module, HasInnerState, SupportsPP, MixtureOfExperts, IsHybrid
  ):
 +    supports_eagle3: ClassVar[Literal[True]] = True
++    has_own_lm_head: bool = False
++    has_own_embed_tokens: bool = False
 +
      def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
          super().__init__()