The four standalone construction-layer fieldtest bins (mc_1..mc_4) no
longer compiled: they are their own workspace root, so the engine's
`cargo build --workspace` never touched them and two waves of API drift
went latent.
Two breakage classes, both confined to the fixture files (no engine
change):
- Stale cycle-0016 authoring. `BlueprintNode::from(<Node>::new(..))`
relied on the `From<NodeType>` impls retired in the value-empty
migration; only `From<LeafFactory>` survives. Ported to
`<Node>::factory().into()` — nodes are value-empty blueprint items,
params bound at compile. Knock-on in mc_4 `describe_node`: a blueprint
leaf is now a `&LeafFactory` with no pre-build schema, so leaf
introspection reports the render label + declared param count (inputs
/ outputs exist only on the compiled flat node, post-build).
- Cycle-0018 (#40) OutPort -> OutField slice drift. `Composite::output()`
now returns `&[OutField]`; the mc_4 read sites were still treating it
as a single port. Ported to index the record; the walk assertion now
also pins the arity (one re-exported field), which is the #40 shape.
Faithful ports, not assertion-gutting: each fixture still exercises its
axis (composite build+run / miswire render / nested composite / graph
introspection), verified by running all four bins to their `OK:` line.
One genuine semantic drift flagged in mc_2: the blueprint-view label is
now the bare value-empty type ("SMA"), so two same-type leaves share a
label and are disambiguated by the slot/edge table; the valued
SMA(2)/SMA(4) label lives on the compiled view. The fixture asserts what
the blueprint view actually exposes and keeps the load-bearing edge-table
observability check untouched.
closes#42
Brummel
241bb626e6