e44b0cbb3e9fbbbfb885698b54be54e0fa02d2df
4 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
|
||
|
Brummel
|
5856cadadd |
refactor(cli): retire the r-breakout demo — topology now lives only as data (#159 cut 2)
Cut 2 of the hard-wired demo retirement, applying the r-sma template one level
down. The r-breakout signal leg was fused into r_breakout_graph (which also built
the whole pip/R harness inline), so this cut first carves the signal leg out as a
pure price->bias Composite, ships it as a proven blueprint example, then deletes
the fused builder and the built-in --strategy r-breakout surface. The r-breakout
topology now exists only as data (crates/aura-cli/examples/r_breakout{,_open}.json).
Carved: r_breakout_signal(channel) -> Composite, a verbatim lift of the fused
builder's signal leg (Delay/RollingMax/RollingMin/Gt/Latch/Sub) exposing the raw
exposure as "bias"; the generic wrap_r/run_signal_r path (unchanged) supplies the
pip/R harness. It is #[cfg(test)] — its only role is regenerating the examples and
pinning them to a faithful serialisation; production loads the shipped JSON, never
this builder (so no dead-code residue, no production topology constructor — #159's
invariant).
Proof: before the fused builder was deleted, an equivalence test proved the carved
signal, wrapped and run, reproduces the retiring r_breakout_graph grade byte-for-byte
on the synthetic stream at channel=3 with the shared default R-stop (metric
computation is identical on both paths). That gate is deleted with the builder it
references; the durable anchors that survive are the byte-identity of the shipped
examples to the carve, the loaded-example-grades-identically-to-the-carve proof, and
the closed-ness / open-axis introspect anchors (channel_hi.length, channel_lo.length
per-node — ganging is the separate #61).
Deleted: r_breakout_graph, r_breakout_sweep_family (aura sweep --strategy r-breakout),
Strategy::RBreakout + all four match arms, the r-breakout token from the --strategy
usage strings and docs, and the now-dead --channel flag + RGrid.channel field (its
sole reader was r_breakout_sweep_family). The data successors: aura run
examples/r_breakout.json, and aura sweep examples/r_breakout_open.json --axis
channel_hi.length --axis channel_lo.length.
Test surface: the three built-in-surface sweep tests drop; the walkforward
valid-but-unsupported-token test is re-pointed to momentum (the property is generic
and stays live until Cut 4); and a new negative pins that --strategy r-breakout on
both sweep and walkforward now falls into the generic usage error, not a
special-cased message — catching a half-finished retirement that left the token
parseable.
Verification (own, not the workflow's report): full `cargo test --workspace` green
(0 failed across every binary); `cargo clippy --workspace --all-targets -- -D warnings`
clean, no dead-code residue; the r-sma introspect + grade anchors and the
dissolved-verb real goldens stay green. The implement-loop ran both plan tasks in one
pass (task_range was not honoured); the tree was verified by hand — grep-confirmed the
retired surface is gone and the carve is #[cfg(test)]-scoped.
refs #159
|
||
|
Brummel
|
d7fa4b4743 |
feat(cli): ship r-sma demo as a proven blueprint-data example (#159 cut 1)
Cut 1 of the hard-wired demo retirement — the copy+prove phase. The r-sma demo strategy now ships as runnable blueprint data under crates/aura-cli/examples/ (r_sma.json closed 2/4, r_sma_open.json open), emitted from the current builder so it is byte-for-byte the builder's serialization. Two load-bearing proofs, captured while the builder is still alive: - byte-fidelity: the shipped examples equal blueprint_to_json(&sma_signal(..)) — the "the copy is identical to the original" evidence the retirement method requires before any original is removed; - grade anchor: `aura run examples/r_sma.json` reproduces the built-in `--harness r-sma` metrics byte-for-byte (expectancy_r/sqn/total_pips/n_trades). Plus two property tests on the shipped copies (beyond the plan, kept as on-topic proof strengthening): the closed example introspects to zero unbound params (genuinely closed), and the open example lists exactly its two SMA-length axes from the public gallery location. Purely additive: the builder (sma_signal) and every inline r-sma surface are retained. The recon showed deleting the builder has a large transitive closure (the synthetic inline surface, the Strategy::RSma enum, ~40 integration tests); that removal is cut 1b, a separate cycle, made safe by the byte-fidelity proof frozen here. Full workspace suite green; clippy -D warnings clean. refs #159 |