SIGN IN SIGN UP

[Agent docs] some updated based on recent integration (#14452)

* Add agent-doc lessons from the Wan-Animate-2 modular integration

- models.md: document _skip_keys (group offloading exclude_kwargs +
  device_map dispatch skip_keys) with the in-tree cache examples
- modular.md: canonical flat-blockset packing (standalone children,
  InsertableDict groups, no cross-preset-file imports); variant presets
  carry their own model_name + mapping entry (#14451); composed-blockset
  inputs/outputs overrides; guider ownership and
  requires_unconditional_embeds; always ship modular_model_index.json;
  auto-docstring drift + check_forward_call_docstrings checklist items;
  randn_tensor gotcha
- pipelines.md: the same randn_tensor gotcha

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Address review comments

Reword the `_skip_keys` guidance: "non-tensor runtime objects holding large tensors"
contradicted itself, say "state the model places itself" instead.

Drop the paragraph claiming the guider spec is declared only by the denoise blocks —
`WanTextEncoderStep` declares one too, and the codebase is inconsistent enough that no
rule can be stated yet (see #14469).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Y
YiYi Xu committed
35ab485bdea676dbcbc77de60d77f7acb4f390fd
Parent: 788e802
Committed by GitHub <noreply@github.com> on 8/13/2026, 8:52:44 PM