feat(aura-engine): Op::Use splices a registered blueprint; open patterns build

The construction session gains the use op: Op::Use { ref_id, name, bind }
resolves through a second injected closure (subgraph: &dyn Fn(&str) ->
Option<Composite>, mirroring vocab's closed-lookup posture — the engine never
touches the store) and pushes the fetched composite as BlueprintNode::Composite,
renamed to the instance identifier (names are identity-blind debug symbols),
with path-qualified binds applied at splice time. Port resolution, kind checks,
the eager cycle gate, and the holistic finish gates all walk the existing
Composite arm — the session storage already carried it; the
"sessions only ever add primitives" unreachable! is retired by construction.

Open patterns (ratified mid-cycle, #317 comment 4627): finish() drops the
root-role gate; compile/bootstrap keep it. An op-script's explicit input roles
are a pattern's formal parameters — buildable, registerable, splicable; running
one standalone still refuses at bootstrap. The pinned finish-refusal test flips
to assert the new split (finish OK, compile refuses). No shipped fixture used
the input op; no corpus behaviour moves.

Gang integrity at the use seam (review finding): binding a ganged member's raw
path refused via the new BindOpError::AlreadyGanged { param, gang } (aura-core)
instead of silently de-fusing the gang — membership keyed on the same
(node, original_pos) coordinate collect_params/check_gangs use, per nesting
level. The gang's public knob stays unbindable at the seam (recorded residue).

Correctness oracle: use_op_splices_byte_identical_to_the_rust_built_twin pins
blueprint_to_json byte-equality against the GraphBuilder twin AND a
bit-identical recorded run (C1). Seven further use_op_* tests cover the fault
surfaces; open_input_pattern_finishes_registers_shaped_and_splices covers the
open-pattern round trip build -> serialize -> reload -> splice -> run.

No blueprint-format change: the serialized form already nests composites
recursively; the golden byte pin stays untouched.

refs #317
This commit is contained in:
2026-07-24 19:44:51 +02:00
parent 7392075aa6
commit 9e26be60f3
4 changed files with 607 additions and 46 deletions
+3 -3
View File
@@ -58,7 +58,7 @@ fn signal_ops() -> Vec<Op> {
#[test]
fn replayed_construction_compiles_identically_to_graphbuilder() {
// (a) op-script replay through the public construction surface.
let replay_flat = replay("root", signal_ops(), &std_vocabulary)
let replay_flat = replay("root", signal_ops(), &std_vocabulary, &|_: &str| None)
.expect("op-script resolves")
.compile_with_params(&params())
.expect("replay compiles");
@@ -103,7 +103,7 @@ fn replay_attributes_eager_fault_to_its_op_index() {
];
// `.err().unwrap()` (not `unwrap_err`): the Ok arm `Composite` holds build
// closures and is not `Debug`, which `unwrap_err`'s bound would require.
let err = replay("g", ops, &std_vocabulary).err().unwrap();
let err = replay("g", ops, &std_vocabulary, &|_: &str| None).err().unwrap();
assert_eq!(err, (2, OpError::UnknownNodeType("Nope".into())));
}
@@ -128,7 +128,7 @@ fn replay_attributes_holistic_fault_to_finalize_step() {
// sub.rhs deliberately left unwired -> only finalize can decide totality.
];
let finalize_index = ops.len(); // 6 — the implicit finalize step
let err = replay("g", ops, &std_vocabulary).err().unwrap();
let err = replay("g", ops, &std_vocabulary, &|_: &str| None).err().unwrap();
assert!(matches!(&err, (i, OpError::UnconnectedPort { .. }) if *i == finalize_index),
"the holistic fault is still attributed to the finalize step, got {err:?}");
}