Brummel
257ab0b9f2
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
1 line
1.4 KiB
JSON
1 line
1.4 KiB
JSON
{"format_version":1,"blueprint":{"name":"r_meanrev_signal","nodes":[{"primitive":{"type":"EMA","name":"mean_window"}},{"primitive":{"type":"Sub"}},{"primitive":{"type":"Mul"}},{"primitive":{"type":"EMA","name":"var_window"}},{"primitive":{"type":"Sqrt"}},{"primitive":{"type":"Scale","name":"band"}},{"primitive":{"type":"Add"}},{"primitive":{"type":"Sub"}},{"primitive":{"type":"Gt"}},{"primitive":{"type":"Gt"}},{"primitive":{"type":"Latch"}},{"primitive":{"type":"Latch"}},{"primitive":{"type":"Sub"}}],"edges":[{"from":0,"to":1,"slot":1,"from_field":0},{"from":1,"to":2,"slot":0,"from_field":0},{"from":1,"to":2,"slot":1,"from_field":0},{"from":2,"to":3,"slot":0,"from_field":0},{"from":3,"to":4,"slot":0,"from_field":0},{"from":4,"to":5,"slot":0,"from_field":0},{"from":0,"to":6,"slot":0,"from_field":0},{"from":5,"to":6,"slot":1,"from_field":0},{"from":0,"to":7,"slot":0,"from_field":0},{"from":5,"to":7,"slot":1,"from_field":0},{"from":6,"to":8,"slot":1,"from_field":0},{"from":7,"to":9,"slot":0,"from_field":0},{"from":8,"to":10,"slot":0,"from_field":0},{"from":9,"to":10,"slot":1,"from_field":0},{"from":9,"to":11,"slot":0,"from_field":0},{"from":8,"to":11,"slot":1,"from_field":0},{"from":11,"to":12,"slot":0,"from_field":0},{"from":10,"to":12,"slot":1,"from_field":0}],"input_roles":[{"name":"price","targets":[{"node":0,"slot":0},{"node":1,"slot":0},{"node":8,"slot":0},{"node":9,"slot":1}],"source":"F64"}],"output":[{"node":12,"field":0,"name":"bias"}]}} |