main
4 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Brummel
|
41cbb5506f |
feat(aura-engine): name the composite boundary — input roles + param aliases
Brings the other two composite-boundary edge-kinds to the named-projection shape #40 gave outputs. input_roles changes from a bare Vec<Vec<Target>> to Vec<Role { name, targets }> (rendered [in:<name>]); a composite gains params: Vec<ParamAlias { name, node, slot }> that relabels an interior leaf param slot's surface name in param_space() (rendered [param:<name>]). Param aliasing is a PURE NAMING OVERLAY, not curation (the load-bearing decision, per spec 0019): every interior param slot stays in param_space() and sweepable; the alias only relabels in place, never reorders or hides. Proven empirically — the MACD run is byte-identical (total_pips 0.1637945563898923, 3 sign flips), only the param labels improved: param_space() now surfaces [macd.fast, macd.slow, macd.signal] instead of three indistinguishable macd.length, and the manifest reads ema_fast/ ema_slow/ema_signal. C23 honoured: role/param/output names are non-load-bearing debug symbols dropped at lowering; identity is positional (role index, param slot, output field). compiled_view_golden is byte-identical (verified: the golden region is untouched in the diff). An out-of-range alias (missing/ non-leaf node or slot past the leaf's param count) is rejected at compile_with_params as BadInteriorIndex, mirroring the output range-check (no new variant). Orthogonal to #36 — purely additive at the composite level. Aliasing is demonstrated on the CLI MACD site only (the spec's worked example + a new E2E test macd_param_space_surfaces_the_three_named_aliases); sma_cross, the engine test fixtures, and the construction-layer fieldtests get the forced role-name + empty params, so the param_space C23 anchor goldens (param_space_mirrors_compiled_flat_node_param_order + siblings) stay byte-identical. Verification (orchestrator-run, not trusted from the agent report): cargo build/test/clippy --workspace -D warnings all green (engine 66, cli 12); the separate-workspace construction-layer fieldtest crate builds (guards the #42 latent-drift recurrence); compiled_view_golden + MACD determinism unchanged. Two faithful repairs to the plan's literal test/code bodies, no semantic change: the out-of-range test uses .err()/Some(BadInteriorIndex) (the Ok arm Vec<Box<dyn Node>> is not Debug, so .unwrap_err() would not compile), and the inline_composite destructure binds params as `param_aliases` to avoid shadowing the injected `params: &[Scalar]` arg. closes #41 |
||
|
Brummel
|
241bb626e6 |
fix(fieldtests): port construction-layer fixtures to current authoring API
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
|
784e6c917a |
feat(aura-engine): composite output is a named multi-field record
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
|
||
|
Brummel
|
7e195f66b7 |
fieldtest: milestone construction-layer — 4 examples, 7 findings
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). |