e44b0cbb3e9fbbbfb885698b54be54e0fa02d2df
2 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Brummel
|
fc9cf23b87 |
feat(cli,docs): ship the ganged open examples + document the gang construct (#61 tasks 7-8)
The two open examples now expose their author-intended single knobs — the closed builders always bound these pairs to one value by hand; the open forms falsely offered them as independent axes: - r_breakout_open: channel_hi.length + channel_lo.length -> channel_length (the Donchian channel is structurally ONE parameter) - r_meanrev_open: mean_window.length + var_window.length -> window; the band factor stays an independent axis Regenerated via the emitters (never hand-edited); the closed examples are byte-unchanged. The carve builders gang in the open branch only. Test migration: the two axis-namespace pins, five --real e2e invocations (single gang axis, the 10,20 diagonal for the campaign pair — the mismatched 20,40/10,20 grid was exactly the configuration space the gang retires), and the param_stability row counts (4 -> 3). The r-sma walkforward golden anchor is untouched (it never swept a ganged pair). Docs: authoring-guide gains the seventh op + the third param state (open/bound/ganged) + the gang wrap note; README op list + Axis concept; glossary gang entry; ledger C24 records the gang verb and the pre-ship Tier-2 dormancy (no format-version bump while no out-of-repo reader exists). Verified: full workspace suite 1104/0 (--real e2e included, local data present), clippy -D warnings clean, cargo doc clean; live acceptance: introspect --params prints channel_length:I64 alone / window:I64 + band.factor:F64. closes #61 |
||
|
Brummel
|
257ab0b9f2 |
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
|