asset-pipeline-guidelisted

# Asset pipeline Guidelines An asset pipeline turns editable authored sources into runtime-ready data and keeps the two in sync as content changes. The pipeline has two halves: a stable raw/intermediate representation that stays close to the original file, and a derived runtime representation produced by deterministic compile steps whose results are cached by content hash. How assets are modeled as typed objects with stable references is owned by data-model-guide; the memory layout of the cooked output is owned by data-oriented-design-guide; the discipline of writing reloadable C is owned by c99-opinionated-guide. ## Essentials - **Two representations** - Keep an editable raw/intermediate form separate from the compiled runtime form; never edit the runtime form directly, see [references/raw-vs-runtime-formats.md](references/raw-vs-runtime-formats.md) - **Importers per format, compilers per type** - Source files enter through a format importer keyed by extension; each asset type owns a deterministic compiler that cooks it to runtime data, see [references/import-and-compile.md](references/import-and-compile.md) - **Settings are compile inputs** - Import/compile options (mip count, compression, quantization, target platform) are part of the input, not side state, see [references/import-and-compile.md](references/import-and-compile.md) - **Hash inputs to a cache key** - Compute a content hash over source bytes plus settings plus the input hashes of dependencies; key the cache