Files
Aura/crates/aura-ingest/tests/real_bars.rs
T
Brummel 0a06afed29 feat(0078): cross-instrument generalization as a validation step
Last piece of the Inferential-validation milestone (#146): a new
`aura generalize` subcommand grades how consistently a single candidate
holds across a set of instruments — the across-instrument axis of the
same anti-false-discovery concern as trials-deflation (#144, within one
family) and plateau-over-peak (#145, within one instrument's surface).

Aggregator/validator, not a third selector (user-ratified): it runs a
brought candidate (a single-cell stage1-r grid — --fast/--slow/--stop-
length/--stop-k pinned to single values) across an instrument list
(--real SYM1,SYM2,...), collects per-instrument R-metrics, and reduces
them to a worst-case floor (min over instruments) + a sign-agreement
count + the per-instrument breakdown. R-only (C10 — R is the only
account/instrument-agnostic unit); the worst-case min is the cross-
instrument sibling of PlateauMode::Worst and satisfies the non-
domination constraint by construction (a strong instrument cannot lift
a min). Rejected: a cross-instrument t-stat mean/std*sqrt(M), which
reintroduces the pooled mean the milestone warns against.

- RunManifest gains a first-class `instrument` lineage field (serde-
  widened, C14/C18 — legacy lines load as None, existing manifest bytes
  unchanged); the compat read-mirror threads it in lockstep.
- FamilyKind::CrossInstrument (C12 comparison axis); the M per-instrument
  runs persist as a CrossInstrument family, each member self-identifying
  via its stamped instrument. The aggregate is recomputable from the
  members (McAggregate precedent), printed live.
- The generalization reduction lives registry-side beside optimize_
  deflated/optimize_plateau (C9), reusing resolve_metric/metric_value/
  is_r_metric; check_r_metric is the data-free pre-check the CLI runs
  before evaluating any instrument.
- Additive: existing sweep/walkforward/mc/standalone paths stay byte-
  identical (C23 — instrument omitted when None via skip_serializing_if).

Verified by the orchestrator: cargo test --workspace green (0 failed —
the new generalization_*, check_r_metric, parse_generalize_*, and the
gated cross-instrument E2E all pass; the E2E ran the real GER40/USDJPY
path on this host, exit 0); cargo clippy --workspace --all-targets
-D warnings clean.

closes #146
2026-06-26 19:04:53 +02:00

125 lines
5.1 KiB
Rust

//! Gated integration test: a real data-server M1 close stream driven through
//! the cycle-0007 signal-quality sample harness (SMA-cross → Bias →
//! SimBroker), folded into a `RunReport`. Skips with a note where the local
//! Pepperstone data directory is absent, so `cargo test --workspace` stays green
//! anywhere; it exercises the real ingestion path where data exists.
use std::sync::mpsc;
use std::sync::Arc;
use aura_core::{Firing, NodeSchema, PortSpec, Scalar, ScalarKind, Timestamp};
use aura_engine::{
f64_field, summarize, Edge, FlatGraph, Harness, RunManifest, RunReport, SourceSpec, Target,
VecSource,
};
use aura_ingest::load_m1_window;
use aura_std::{Bias, Recorder, SimBroker, Sma, Sub};
use data_server::{DataServer, DEFAULT_DATA_PATH};
/// Bootstrap the cycle-0007 two-sink signal-quality harness (mirrors
/// `aura-engine`'s `report::tests::build_two_sink_harness`, with the shipped
/// `aura_std::Recorder`), run it on `prices`, and fold the recorded equity +
/// exposure into a `RunReport` whose window is the first/last real bar ts.
fn run_sample_over(prices: Vec<(Timestamp, Scalar)>) -> RunReport {
let (tx_eq, rx_eq) = mpsc::channel();
let (tx_ex, rx_ex) = mpsc::channel();
let f64_recorder_sig = || NodeSchema {
inputs: vec![PortSpec { kind: ScalarKind::F64, firing: Firing::Any, name: "in".into() }],
output: vec![],
params: vec![],
};
let mut h = Harness::bootstrap(FlatGraph {
nodes: vec![
Box::new(Sma::new(2)), // 0
Box::new(Sma::new(4)), // 1
Box::new(Sub::new()), // 2
Box::new(Bias::new(0.5)), // 3
Box::new(SimBroker::new(0.0001)), // 4
Box::new(Recorder::new(&[ScalarKind::F64], Firing::Any, tx_eq)), // 5 equity sink
Box::new(Recorder::new(&[ScalarKind::F64], Firing::Any, tx_ex)), // 6 exposure sink
],
signatures: vec![
Sma::builder().schema().clone(),
Sma::builder().schema().clone(),
Sub::builder().schema().clone(),
Bias::builder().schema().clone(),
SimBroker::builder(0.0001).schema().clone(),
f64_recorder_sig(),
f64_recorder_sig(),
],
sources: vec![SourceSpec {
kind: ScalarKind::F64,
targets: vec![
Target { node: 0, slot: 0 },
Target { node: 1, slot: 0 },
Target { node: 4, slot: 1 }, // price into the broker
],
}],
edges: vec![
Edge { from: 0, to: 2, slot: 0, from_field: 0 },
Edge { from: 1, to: 2, slot: 1, from_field: 0 },
Edge { from: 2, to: 3, slot: 0, from_field: 0 },
Edge { from: 3, to: 4, slot: 0, from_field: 0 },
Edge { from: 4, to: 5, slot: 0, from_field: 0 }, // equity -> sink 5
Edge { from: 3, to: 6, slot: 0, from_field: 0 }, // exposure -> sink 6
],
})
.expect("valid signal-quality DAG");
let window = (
prices.first().map(|&(t, _)| t).unwrap_or(Timestamp(0)),
prices.last().map(|&(t, _)| t).unwrap_or(Timestamp(0)),
);
h.run(vec![Box::new(VecSource::new(prices))]);
let eq_rows: Vec<(Timestamp, Vec<Scalar>)> = rx_eq.try_iter().collect();
let ex_rows: Vec<(Timestamp, Vec<Scalar>)> = rx_ex.try_iter().collect();
let equity = f64_field(&eq_rows, 0);
let exposure = f64_field(&ex_rows, 0);
let metrics = summarize(&equity, &exposure);
RunReport {
manifest: RunManifest {
commit: "real-bars-test".to_string(),
params: vec![
("sma_fast".to_string(), Scalar::i64(2)),
("sma_slow".to_string(), Scalar::i64(4)),
("bias_scale".to_string(), Scalar::f64(0.5)),
],
window,
seed: 0,
broker: "sim-optimal(pip_size=0.0001)".to_string(),
selection: None,
instrument: None,
},
metrics,
}
}
#[test]
fn sample_strategy_runs_over_real_m1_bars_deterministically() {
let server = Arc::new(DataServer::new(DEFAULT_DATA_PATH));
if !server.has_symbol("AAPL.US") {
eprintln!("skip: no local data at {DEFAULT_DATA_PATH} (symbol AAPL.US absent)");
return; // hermetic elsewhere; exercises the real path where files exist
}
// 2006-08 in inclusive Unix-ms (data-server skips files outside the window).
let (from_ms, to_ms) = (1_154_390_400_000_i64, 1_157_068_799_999_i64);
let load = || {
load_m1_window(&server, "AAPL.US", Some(from_ms), Some(to_ms))
.expect("AAPL.US has data in the 2006-08 window")
.close_stream()
};
let prices = load();
assert!(!prices.is_empty(), "window resolved to zero bars");
let r1 = run_sample_over(prices);
assert!(r1.metrics.total_pips.is_finite(), "a backtest ran over real bars");
// same window -> bit-identical report (C1).
let r2 = run_sample_over(load());
assert_eq!(r1.to_json(), r2.to_json());
}