A cycle-0091 design analysis (adversarially verified) of "does invariant 9
survive lifting blueprints onto the data plane?" records a load-bearing finding
in the C24 entry.
Pre-C24 a blueprint referencing another project's node was a compile error
(topology was in-process Rust — structurally impossible). Post-C24 it is a
type-id string refused only by the injected resolver's closed set
(UnknownNodeType). The anti-NIH rationale survives (logic stays cargo+Gitea-only;
the format distributes topology-as-content, never logic, C17) and std_vocabulary
stays a compiled-in dispatch table, not a registry — but enforcement of the
engine/project boundary degrades from compiler-guaranteed to resolver-seam
discipline. Two consequences recorded: #160 becomes the data-plane face of that
boundary (no longer droppable; its own drift still fails safe), and the injected
per-project resolver is the genuinely new, deferred invariant-9 surface (a
project can express a marketplace one layer above the engine contract) — a
World/C21-layer charter point. Invariant 8 (frozen) is reframed alongside:
runtime topology generation (research plane) + frozen deploy artifact +
deterministic-once-instantiated (C1).
refs #160
Brummel
df228986c4