patches: glm53-dflash-01 v2 -- satisfy SupportsEagle3 by inheriting the Protocol

v1 hand-wrote set_aux_hidden_state_layers/get_eagle3_default_aux_hidden_state_layers
and the boot reproduced the identical 'Model does not support EAGLE3 interface'.
Reason: supports_eagle3() is an isinstance check against a runtime-checkable
Protocol whose members include a required ClassVar flag
(interfaces.py:1663 supports_eagle3: ClassVar[Literal[True]] = True), so methods
alone do not satisfy it. Inheriting SupportsEagle3 -- the idiom every model in
this image uses, including the fork's own DFlashLagunaForCausalLM -- supplies the
flag, SupportsEagleBase's has_own_lm_head/has_own_embed_tokens, and working
default implementations of both methods; the hand-written methods are deleted.

base 008eeaa2... -> patched 5eea89c5..., apply-verified against the pinned image.
Runbook: corrected method name, recorded the Protocol trap as the generalizable
lesson for future spec-decode ports.

serverAppConfigs-docs/LLM/frank-primary-glm53-flash-w4a16.md

@@ -299,7 +299,7 @@ The fork already maps that architecture:
 and the spec method is `"dflash"` (`config/speculative.py:67`). So the port is
 **target-side only**: the GLM trunk must expose auxiliary hidden states at those five
 layer indices, the same interface `deepseek_v2.py` (also MLA+MoE) implements —
-`set_aux_hidden_state_layers()` / `get_eagle3_aux_hidden_state_layers()` plus
+`set_aux_hidden_state_layers()` / `get_eagle3_default_aux_hidden_state_layers()` plus
 capture at `idx in self.aux_hidden_state_layers` in the layer loop. `glm5next`
 implements neither.
 
@@ -316,7 +316,7 @@ RuntimeError: Model does not support EAGLE3 interface
 So nothing about the drafter, the method name, or the payload is wrong — the GLM
 trunk simply does not implement the aux-hidden-state contract the dflash runner
 requires. The reference is in this same image, twice: `deepseek_v2.py`
-(`set_aux_hidden_state_layers` / `get_eagle3_aux_hidden_state_layers` at :1948-1951,
+(`set_aux_hidden_state_layers` / `get_eagle3_default_aux_hidden_state_layers` at :1948-1951,
 capture at :1554 and :1579) and the fork's own `qwen4_exp` trunk. The contract is
 small:
 
@@ -327,7 +327,7 @@ small:
   rank holds fewer tokens than `positions`);
 - `Glm5NextModel.forward` returns `(hidden_states, aux_hidden_states)` when the
   list is non-empty;
-- `get_eagle3_aux_hidden_state_layers()` supplies a default triple when the drafter
+- `get_eagle3_default_aux_hidden_state_layers()` supplies a default triple when the drafter
   config omits `target_layer_ids` (this drafter provides `[5, 14, 24, 33, 42]`, so
   the runner derives trunk indices `[6, 15, 25, 34, 43]`).
 
@@ -348,14 +348,30 @@ flat decode with a prefill regression like MTP's until the pointwise mass is fus
 
 **The port exists now: `scripts/patches/glm53-dflash-01-aux-hidden-states.patch`** (WIP,
 independent of the compile changelist — it patches the same file as compile-01, so
-compile-01 goes first if both are applied). It implements exactly the contract read out
-of this image: `EagleModelMixin` on `Glm5NextModel`, capture of the single-stream
-`hidden_states` ENTERING each requested layer in the loop, the conditional
-`(hidden_states, aux_hidden_states)` tuple return, and
-`set_aux_hidden_state_layers` / `get_eagle3_default_aux_hidden_state_layers` on
-`Glm5NextForCausalLM` (delegation shape from `kimi_k25.py:466`, `pixtral.py:503`;
-capture shape from `deepseek_v2.py:1551-1585`; tuple consumption at
-`v1/worker/gpu/cudagraph_utils.py:621`).
+compile-01 goes first if both are applied; base `008eeaa2…` → patched `5eea89c5…`). It
+implements exactly the contract read out of this image: `EagleModelMixin` on
+`Glm5NextModel`, capture of the single-stream `hidden_states` ENTERING each requested
+layer in the loop, the conditional `(hidden_states, aux_hidden_states)` tuple return, and
+`SupportsEagle3` among `Glm5NextForCausalLM`'s bases (capture shape from
+`deepseek_v2.py:1551-1585`; tuple consumption at `v1/worker/gpu/cudagraph_utils.py:621`).
+
+**The first version of that patch was wrong in an instructive way, and it is the trap to
+avoid on any future spec-decode port: `supports_eagle3` is a Protocol `isinstance`
+check, not duck typing.** It hand-wrote `set_aux_hidden_state_layers` and
+`get_eagle3_default_aux_hidden_state_layers` on the outer wrapper — the two methods the
+traceback's call site reads — and the boot reproduced the *identical*
+`RuntimeError: Model does not support EAGLE3 interface`. The reason is
+`interfaces.py:1663`: `SupportsEagle3` also declares
+`supports_eagle3: ClassVar[Literal[True]] = True`, and a runtime-checkable Protocol
+requires every member to be *present* on the instance. **Inherit the Protocol** — the
+idiom every model in the image uses (`LagunaForCausalLM`, `MiMoV2FlashForCausalLM`,
+`DFlashLagunaForCausalLM` all list `SupportsEagle3` in their bases) — which supplies the
+flag, `SupportsEagleBase`'s `has_own_lm_head` / `has_own_embed_tokens`, *and* working
+default implementations of both methods (they unwrap
+`holder = getattr(parent_ref, "model", parent_ref)`, assert it is an `EagleModelMixin`,
+and default to `(2, L // 2, L - 3)`). The lesson generalizes: when a runtime error names
+an interface, read the interface's declaration first — the methods a call site happens to
+invoke are not necessarily the whole contract.
 
 **Retired diagnostic (do not resurrect as-is): the `/probe` startup hook.** An
 `op_probe.py` + `sitecustomize.py` pair was mounted to wrap vLLM module forwards and