Implement generic pipeline caching in WgpuExecutor

[timon-schelling]

changing shader nodes to work with this will be done in a followup PR, for now they keep the separate ShaderRuntime.

[gemini-code-assist]

Code Review

This pull request refactors the WGPU pipeline execution model by introducing a dynamic, generic Pipeline trait system. Hardcoded compositor and resampler fields in WgpuExecutor are replaced with a thread-safe pipelines map that caches and runs pipelines dynamically. Additionally, the render_background and pixel_preview (renamed to render_pixel_preview) nodes have been refactored to use this new system. Feedback on these changes suggests adding an early return in render_background when viewport_zoom <= 0.0 to prevent uninitialized texture returns, simplifying the Pipeline trait using impl Future to avoid boxed future allocations, releasing the RwLockReadGuard earlier during pipeline retrieval, and cleaning up a verbose type signature in BackgroundCompositor::run.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

Since WgpuExecutor::run_pipeline always downcasts to the concrete pipeline type P, there is no need for a trait object or boxed futures. We can leverage Rust's support for impl Future in traits to define a single Pipeline trait without any boxing, eliminating the Box::pin allocation on every pipeline execution.

Suggested change

	pub trait Pipeline: std::any::Any + Send + Sync + Sized {
	type Args<'a>;
	type Out: Send;
	fn create(context: &WgpuContext) -> Self;
	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out>;
	}
	pub trait AsyncPipeline: std::any::Any + Send + Sync + Sized {
	type Args<'a>;
	type Out: Send;
	fn create(context: &WgpuContext) -> Self;
	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> impl Future<Output = Self::Out> + Send + 'a;
	}
	impl<P: AsyncPipeline> Pipeline for P {
	type Args<'a> = <P as AsyncPipeline>::Args<'a>;
	type Out = <P as AsyncPipeline>::Out;
	fn create(context: &WgpuContext) -> Self {
	<P as AsyncPipeline>::create(context)
	}
	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out> {
	Box::pin(<P as AsyncPipeline>::run(self, executor, args))
	}
	}
	pub trait Pipeline: std::any::Any + Send + Sync + Sized {
	type Args<'a>;
	type Out: Send;
	fn create(context: &WgpuContext) -> Self;
	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> impl Future<Output = Self::Out> + Send + 'a;
	}

[timon-schelling]

No

error: lifetime bound not satisfied
  --> node-graph/nodes/gstd/src/render_background.rs:17:1
   |
17 | #[node_macro::node(category(""))]
   | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   |
   = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information)
   = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info)

error: lifetime bound not satisfied
  --> node-graph/nodes/gstd/src/render_pixel_preview.rs:13:1
   |
13 | #[node_macro::node(category(""))]
   | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   |
   = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information)
   = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info)

[cubic-dev-ai]

7 issues found across 15 files

Confidence score: 2/5

• There is a concrete user-facing regression risk in node-graph/nodes/gstd/src/render_background.rs: the zoom <= 0 early return can skip compositing/copying and produce a blank render output.
• Several high-confidence panic paths were introduced (unwrap/expect and unwrapped application_io) across node-graph/nodes/gstd/src/render_background.rs and node-graph/libraries/wgpu-executor/src/lib.rs, which can crash runtime/executor flows instead of failing gracefully.
• Additional executor-path concerns in node-graph/libraries/wgpu-executor/src/pipeline.rs and node-graph/libraries/wgpu-executor/src/lib.rs (per-call boxing in a hot path, eager duplicate pipeline creation, and longer-than-needed lock scope) increase performance/concurrency risk but are secondary to correctness issues.
• Pay close attention to node-graph/nodes/gstd/src/render_background.rs, node-graph/libraries/wgpu-executor/src/lib.rs, node-graph/libraries/wgpu-executor/src/pipeline.rs - potential blank output, panic-on-error behavior, and executor hot-path regressions.

<sub>Reply with feedback, questions, or to request a fix.

Re-trigger cubic</sub>

[cubic-dev-ai]

1 issue found across 2 files (changes from recent commits).

<sub>Reply with feedback, questions, or to request a fix.

Re-trigger cubic</sub>