📄 CodeRabbit inference engine (AGENTS.md)

**/*: Keep changes and file scope as small and direct as possible; prefer practical fixes, minimal dependencies, existing patterns, and removal of obsolete code.
Preserve existing APIs, node names, model-loading behavior, file layout, and workflow compatibility unless replacement is intentional.
Do not add core ComfyUI code that makes outbound internet requests, including telemetry, analytics, tracking, reporting, update checks, remote configuration, licensing checks, or background network activity. User-authorized model downloads are permitted only for the requested artifact and without telemetry.
Keep state and capability flags on the object that owns the behavior; prefer explicit parent-owned attributes over probing child objects with getattr for parent control flow.
Preserve shared method signatures, argument conventions, return types, side effects, and error behavior unless the shared contract and all affected callers are intentionally updated.

Files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py

📄 CodeRabbit inference engine (AGENTS.md)

**/*.py: Do not add torch.no_grad, torch.inference_mode, inference-mode wrappers, or explicit model freeze/trainability toggles; only disable globally enabled inference mode when a training path needs gradients.
Remove inference-only training behavior such as dropout while preserving checkpoint and state-dict compatibility; use nn.Identity when removing a module would alter keys or ordering.
Keep imports at module scope except for established optional-backend probes or import-cycle avoidance; avoid unnecessary exception handling and use specific exception types with useful fallbacks.
Do not add code for unsupported pinned library versions or obsolete PyTorch workarounds; unsupported formats, invalid quantization metadata, and bad states should fail clearly rather than silently degrading output.
Match local Python style, keep comments sparse and useful, and remove comments that merely restate obvious code.
Treat dtype, device placement, VRAM usage, and offloading as correctness concerns; use existing ComfyUI cast, offload, cleanup, quantization, and memory helpers.
Model implementations must use an existing optimized Comfy Kitchen, ComfyUI, quantization, or backend operation when it supports the required math, layout, dtype, device, memory, and interface contracts; inspect available operations before writing local kernels.
Retain local or differentiable fallbacks only when no optimized operation satisfies the required math or patch/autograd contract; adapt inputs to shared operation layouts while preserving exact model behavior.
Treat optimized attention and similar backend-selected callables as opaque; callers must rely on documented interfaces and result contracts rather than function identity, names, modules, or implementation details.
Do not duplicate existing inference operations with custom float32-upcasting implementations, such as custom RMSNorm variants; use generic ComfyUI or native torch operations.
If a model constructor has an operations parame...

Files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py

⚙️ CodeRabbit configuration file

**: IMPORTANT: Only comment on issues directly introduced by this PR's code changes.
Treat AGENTS.md as mandatory repository policy, not optional style guidance.
Flag PR changes that violate AGENTS.md even when the code is otherwise functional.
In particular, enforce architecture boundaries, dtype/device/memory rules,
interface contracts, import style, no unnecessary try/except blocks, no inline
imports, no outbound internet paths in core ComfyUI, and narrow scoped fixes.
Prefer direct findings over suggestions when a rule is violated. Only ignore
AGENTS.md when it clearly conflicts with a newer explicit maintainer instruction
in the PR.
Do NOT flag pre-existing issues in code that was merely moved, re-indented,
de-indented, or reformatted without logic changes. If code appears in the diff
only due to whitespace or structural reformatting (e.g., removing a with: block),
treat it as unchanged. Contributors should not feel obligated to address
pre-existing issues outside the scope of their contribution.

Files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py

⚙️ CodeRabbit configuration file

comfy/**: Core ML/diffusion engine. Focus on:

• Backward compatibility (breaking changes affect all custom nodes)
• Memory management and GPU resource handling
• Performance implications in hot paths
• Thread safety for concurrent execution

Files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py

Learnt from: pythongosssss
Repo: Comfy-Org/ComfyUI PR: 12555
File: comfy_extras/nodes_glsl.py:719-724
Timestamp: 2026-02-21T14:01:41.482Z
Learning: In PyOpenGL, bare Python scalars can be accepted for 1-element array parameters by NumberHandler. This means you can pass an int/float directly to OpenGL texture deletion (e.g., glDeleteTextures(tex)) without wrapping in a list. Verify function-specific expectations and ensure types match what the OpenGL call expects; use explicit lists only when the API requires an array.

Applied to files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py

Learnt from: rattus128
Repo: Comfy-Org/ComfyUI PR: 13062
File: comfy/ldm/lightricks/vae/causal_video_autoencoder.py:782-785
Timestamp: 2026-03-19T09:09:31.674Z
Learning: Do not require/flag per-layer handling of odd temporal tails in `SpaceToDepthDownsample.forward` (in `comfy/ldm/lightricks/vae/causal_video_autoencoder.py`). This method’s `torch.split` will not produce a partial final temporal chunk because `VideoVAE.encode` truncates the input to `1 + 8k` frames (making the tail after the first frame a multiple of 8) and `Encoder.forward_orig` restricts `chunk_t` to `{2, 4, 8*m}` (all divisors of 8). As a result, any chunk reaching the downsample layers has temporal length divisible by `stride[0]=2`; the absence of internal remainder buffering is expected behavior, not a bug.

Applied to files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py

Learnt from: rattus128
Repo: Comfy-Org/ComfyUI PR: 13802
File: comfy/pinned_memory.py:19-30
Timestamp: 2026-05-13T12:31:45.069Z
Learning: When reviewing code that uses comfy/pinned_memory.py’s `HostBuffer.extend(size=..., reallocate=...)`: by default (`reallocate` is not True / False), `extend(size=...)` is a *relative increment* that grows the buffer by `size` bytes—so slicing like `[offset:offset+size]` after `hostbuf.extend(size=size)` is correct and the argument should not be rewritten to `offset + size`. Only in the single-segment reallocation mode (`reallocate=True`, e.g., as used by `resize_pin_buffer()` in `comfy/model_management.py`) should `size` be treated as an *absolute target* and the call/arguments should be checked accordingly.

Applied to files:

• comfy/ldm/lightricks/vae/causal_video_autoencoder.py
• comfy/ldm/lightricks/vae/causal_conv3d.py