P04 · Foundry knowledge node
Autonomous repo-to-block foundry Automate source understanding, boundary extraction and adaptation evidence while keeping semantic reuse-shape decisions explicit and reviewable.
What we learned Current synthesis from the research packet. Exact records and complete source artifacts remain visible below.
Research conclusions A repository is a source container, not the reusable unit. Choose service, module, transplant, package, adapter, pattern, template or custom-delta shape before extraction. Identity, dependency closure and human shape choice precede normalization surgery. What it owns Source identity and architecture map Capability boundary detection Dependency closure Adaptation recipe and packaging Generated contracts and qualification evidence What research already tells us Phase 8 defined source shapes, stages and 23 negative paths Full automation is the wrong target: shape choice and semantic adaptation need judgment A repository can yield several blocks or no block Open first-principles questions What can AST/runtime probes establish autonomously? How do we detect hidden auth, settings and migration ownership? What diff/adaptation budget predicts a bad candidate? How is an upstream update replayed safely? Inputs Repository Target host contract Desired capability Outputs PackagedAsset CapabilityContract AdaptationRecipe QualificationDossier Agent-sized workstream Build the reusable conversion protocol and three worked traces: intact service, transplanted subsystem and extracted package.
Linked research Repo-to-block pipeline research/actionmodel-builder-research-2026-08-26/phase-8/lanes/04-repo-to-block-mechanics/outputs/repo-to-block-pipeline.mdUniversal Block Framework research/actionmodel-builder-research-2026-08-26/phase-8/lanes/01-universal-block-framework/outputs/universal-block-framework.mdBlock Contract v1 research/actionmodel-builder-research-2026-08-26/phase-2/outputs/block-contract-v1.mdConnected knowledge nodes Where this beats a generator Generation-first builders have no way to absorb existing software: their only import path is a one-way git export, and they cannot start from an existing codebase at all. The foundry is the machine that converts the open-source estate into supply, which is a capital asset rather than a per-build cost.
← P03 · Curated capability shelf P05 · Living UI component layer → Source: site/system-map/data/parts.json#P04 · preserved research datasets remain inline below their source-backed synthesis.