feat(std,cli): add the Scale node, retire the r-meanrev demo to data (#159 cut 3)

Cut 3 of the hard-wired demo retirement. Unlike r-sma/r-breakout, r-meanrev could
not round-trip as data: its band computes band_k*sigma (a constant times a stream)
and the closed 22-node std_vocabulary had no way to express it (EqConst is i64->bool,
Bias is clamp(signal/scale,±1), Mul is binary, LinComb is excluded as a
construction-arg node; no Div/Const/constant-emitter). Standard operators are missing
by chance, not by design, so this adds the one r-meanrev needs.

Scale node (aura-std): out = input * factor — one f64 input, one f64 `factor` param,
stateless, warm-up-filtered (the EqConst/Bias shape). A zero-input `Const` emitter was
rejected: the per-cycle eval loop gates every node through an input-firing test
(harness.rs `fires()`), so a node with no input never fires without an engine-core
change; `Scale` fits the existing model and, by IEEE-754 commutativity, reproduces the
retiring LinComb's band byte-for-byte. Rostered (`"Scale" => Scale`); the two
vocabulary count-pins bump 22 -> 23.

r-meanrev migration: r_meanrev_signal(window, band_k) is carved out of the fused
r_meanrev_graph as a #[cfg(test)] price->bias Composite whose band is `Scale` in place
of `LinComb(1)`; production loads the shipped JSON (examples/r_meanrev{,_open}.json),
never a builder. Before the fused builder was deleted, an equivalence test proved the
carved Scale-band signal reproduces its grade byte-for-byte on the synthetic stream
(window=3, band_k=2). Durable survivors: the byte-identity of the examples to the
carve, the loaded-grades-identically-to-carve proof, the closed/open introspect
anchors (mean_window.length, var_window.length, band.factor — band_k is now a
first-class sweepable param), and — re-pointed onto the carve rather than dropped —
the fades-short-above/long-below behavioural test, which becomes the durable
carve-correctness gate the deleted equivalence test used to be.

Deletions + the dead-code cascade the retirement opened: r_meanrev_graph,
r_meanrev_sweep_family, Strategy::RMeanRev (+ all arms). r-meanrev was the last reader
of run_sweep's grid, so the whole vestigial built-in-sweep grid apparatus retires with
it: run_sweep's `grid` param, the sweep call-site grid build, and SweepCmd's
--fast/--slow/--stop-length/--stop-k/--window/--band-k (sma/momentum sweeps build their
own blueprints and ignored these; the fast/slow/stop-* had been vestigial since r-sma's
cut 1b). RGrid the struct SURVIVES — the dissolved `generalize` verb resolves its
candidate from its fast/slow/stop_length/stop_k via generalize_args_from — so only its
window/band_k fields go; its stale doc-comment (r-sma-sweep / persist_traces_r / CLI
flags, all now gone) is rewritten to its true generalize-only role. Also retired as
transitively dead: persist_traces_r and the metrics_object test helper (their only
callers were the deleted families/tests); Add/Gt/Latch/Mul/Sqrt imports are now
#[cfg(test)] (their last production caller was r_meanrev_graph).

Test surface: the two built-in --strategy r-meanrev sweep tests drop; a new negative
pins that --strategy r-meanrev on both sweep and walkforward now falls into the generic
usage error; the grid-flag stray-positional negative is re-pointed to a surviving flag.

Verification (own, not the workflow's report): full `cargo test --workspace` green
(0 failed across 62 result lines); `cargo clippy --workspace --all-targets -- -D
warnings` clean, no dead-code residue; the r-sma + r-breakout anchors and the
dissolved-verb real goldens (generalize still reads RGrid) stay green. Bundled as one
commit (the Scale node's count-pin and the r-meanrev anchors share graph_construct.rs,
so a clean two-commit split was not path-separable); the implement-loop ran all three
plan tasks in one pass and the tree was verified by hand.

refs #159

crates/aura-cli/tests/graph_construct.rs

@@ -121,8 +121,8 @@ fn graph_introspect_vocabulary_lists_exactly_the_closed_roster_count() {
     let lines: Vec<&str> = stdout.lines().filter(|l| !l.is_empty()).collect();
     assert_eq!(
         lines.len(),
-        22,
-        "the std-only (no project) vocabulary has exactly the roster's 22 entries: {stdout}"
+        23,
+        "the std-only (no project) vocabulary has exactly the roster's 23 entries: {stdout}"
     );
 }
 
@@ -756,3 +756,28 @@ fn shipped_r_breakout_open_example_lists_its_axis_namespace() {
         "the raw open params, in order, from the public gallery copy"
     );
 }
+
+/// Property (#159 cut 3): the shipped closed example (`examples/r_meanrev.json`) is
+/// genuinely closed — `graph introspect --params` reports zero unbound params.
+#[test]
+fn shipped_r_meanrev_example_is_genuinely_closed() {
+    let dir = temp_cwd("r-meanrev-example-closed-params");
+    let (stdout, stderr, code) =
+        run_in(&dir, &["graph", "introspect", "--params", &example("r_meanrev.json")]);
+    assert_eq!(code, Some(0), "stdout: {stdout} stderr: {stderr}");
+    assert_eq!(stdout, "", "the closed example must leave zero params unbound");
+}
+
+/// Property (#159 cut 3): the shipped open example (`examples/r_meanrev_open.json`)
+/// lists its raw axis namespace, in lowering (node-add) order.
+#[test]
+fn shipped_r_meanrev_open_example_lists_its_axis_namespace() {
+    let dir = temp_cwd("r-meanrev-example-open-params");
+    let (stdout, stderr, code) =
+        run_in(&dir, &["graph", "introspect", "--params", &example("r_meanrev_open.json")]);
+    assert_eq!(code, Some(0), "stdout: {stdout} stderr: {stderr}");
+    assert_eq!(
+        stdout, "mean_window.length:I64\nvar_window.length:I64\nband.factor:F64\n",
+        "the raw open params, in lowering order"
+    );
+}