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
Replace a composite's single output port (OutPort { node, field }) with
an ordered, named record (Vec<OutField { node, field, name }>). A
composite can now re-export K interior fields as one output; a consumer
selects one via the existing Edge::from_field — the same field-wise
selector that already works for multi-output leaf producers (OHLCV).
Why: multi-line indicators (MACD, Bollinger, Stochastic, Ichimoku) could
not be authored as a composition and re-exported as a unit — only one
line escaped the boundary. The MACD PoC was forced to expose only the
histogram. This lifts the three `field == 0` / `from_field == 0` caps at
the composite boundary (inline_composite nested arm, rewrite_edge
composite arm), range-checking the index instead.
Boundary completion, not an invariant change:
- C8/C7/C4 untouched — one port, one row per eval, K base columns (a
3-line MACD is identical in kind to OHLCV).
- C23 honoured — re-export names live at the blueprint boundary only and
are dropped in the compilat (raw index wiring). compiled_view_golden
stayed byte-identical (the regression guard): no name leaked into the
flat graph.
The MACD PoC now re-exports macd / signal / histogram as a record; the
strategy still trades the histogram, selected via from_field: 2. The
render shows K [out:<name>] markers per multi-output composite (input
roles stay [in:<index>] — naming them is the dependent #41).
Output naming ships with the capability (OutField is born name-ready) so
#41 — composite param aliasing + input-role naming — does not reopen the
type.
Verification: cargo build/test/clippy --workspace -- -D warnings all
green; aura-engine 62 tests (+3 capability, +1 through-run E2E), aura-cli
unchanged-count green; compiled_view_golden byte-identical.
Known debt (out of scope, pre-existing): the non-workspace construction-
layer fieldtests (fieldtests/milestone-construction-layer/mc_1..mc_4)
carry their OutField sweep but still do not compile standalone — they use
the Sma::new / BlueprintNode::from(Sma) API retired in the cycle-0016
value-empty migration, never propagated to these fixtures. Tracked as a
follow-up.
closes#40
End-to-end milestone fieldtest (closing gate) for the "Construction layer"
milestone (#12 composites + #13 aura graph render). Four real downstream tasks
authored against the PUBLIC interface only (ledger + doc-comments + re-exports
+ the aura CLI), under fieldtests/milestone-construction-layer/:
mc_1 — author a named sma_cross composite, build a Blueprint, compile +
bootstrap + run (12 populated equity rows);
mc_2 — correct vs fast/slow-swapped cross: labels + graph-as-data differ
observably (the headline mis-wire-visible property);
mc_3 — composite-nested-in-composite inlines and runs;
mc_4 — walk the built graph via the read-only accessors, no engine internals.
Roll-up: friction_found, NO bugs. The milestone delivers its core promise —
fractal authoring -> compile -> bootstrap -> run, introspection as graph-as-data,
and param-carrying labels that make a mis-wire readable. None of the findings
block the gate.
Findings filed to the forward queue (not fixed here):
- #28 (feature) — the headline friction: `aura graph` renders only the built-in
sample and the render adapter is CLI-private, so a consumer can't render their
OWN graph. Subsumes the reachability of #26 (the nested-render panic is
structurally unreachable until the render is parameterizable). Likely next
(consumer-project / World) milestone.
- #29 (idea) — aura-engine doesn't re-export the scalar vocabulary (ScalarKind
etc.) a graph-builder needs; one-crate ergonomics tidy.
- #16 (comment) — `aura graph` arg policy (help / unknown-arg) should unify with
the still-open `aura run` strictness question.
The fieldtester read no implementation source; all artefacts are the consumer
crate + the two live render captures (render_clustered.txt / render_compiled.txt,
byte-identical across runs).
Brummel