feat(aura-cli): aura run --real <SYMBOL> backtests the sample on real M1 bars

The first real-data backtest from the CLI: `aura run --real <SYMBOL>
[--from <ms>] [--to <ms>]` runs the existing built-in sample signal-quality
harness over real M1 *close* bars instead of synthetic prices, printing the
same RunReport JSON as `aura run`. Bars are streamed lazily through
aura_ingest::M1FieldSource (a Box<dyn Source>) — dogfooding the #71 Source
seam, O(one chunk) resident, never eager. aura-ingest + data-server enter
aura-cli's deps (data-server git line mirrored from aura-ingest).

M1 only this cycle, deliberately. The TickSource is deferred: raw ticks are
the wrong input for the bar-semantic SMA sample (an SMA over ticks is
microstructure noise until a resampler node exists, C2), and tick's real
driver is the realistic broker's bid/ask execution (C10) — it should arrive
with that consumer, not speculatively here. Tick data is also local to only
EURUSD/XAUUSD/GER40, whereas M1 covers the test symbol AAPL.US.

Shape: run_sample_real builds sample_harness(), guards has_symbol /
M1FieldSource::open (unknown symbol or empty window -> 'aura: no local data'
+ exit 2, never a panic), and reuses sim_optimal_manifest + the run_sample
fold. parse_real_args is a pure, unit-tested grammar (mandatory symbol, then
--from/--to in any order; bad/missing/duplicate flag -> Err). Data path is
data_server::DEFAULT_DATA_PATH (no --data-path flag this cycle).

Known simplification: the manifest window is derived by draining a *separate*
single-pass probe source for first/last ts, so an unbounded window streams
the archive twice (once to bound, once to run). Acceptable and O(1)-resident
for now; a future Harness::run could surface the first/last cycle ts to drop
the probe pass.

Verified: cargo build/test/clippy --workspace all green; the gated
run_sample_real_streams_real_close_bars_deterministically RAN (not skipped)
over AAPL.US 2006-08; manual CLI smoke of the success + two error paths.
This commit is contained in:
2026-06-15 11:13:14 +02:00
parent 682e459554
commit 0ce843bada
3 changed files with 173 additions and 1 deletions
Generated
+2
View File
@@ -52,8 +52,10 @@ version = "0.1.0"
dependencies = [
"aura-core",
"aura-engine",
"aura-ingest",
"aura-registry",
"aura-std",
"data-server",
]
[[package]]
+4
View File
@@ -14,3 +14,7 @@ aura-core = { path = "../aura-core" }
aura-engine = { path = "../aura-engine" }
aura-registry = { path = "../aura-registry" }
aura-std = { path = "../aura-std" }
aura-ingest = { path = "../aura-ingest" }
# data-server: the local M1 archive `aura run --real` streams from. Mirrors the
# git line in crates/aura-ingest/Cargo.toml verbatim (same source of truth).
data-server = { git = "http://192.168.178.103:3000/Brummel/data-server.git", branch = "main" }
+167 -1
View File
@@ -158,6 +158,94 @@ fn run_sample() -> RunReport {
}
}
/// `aura run --real <SYMBOL>`: run the built-in sample harness over real M1 close
/// bars streamed lazily from the local data-server archive through the #71 Source
/// seam (`M1FieldSource`, a `Box<dyn Source>`), not the synthetic `VecSource`. Same
/// fold as `run_sample`. The manifest window is read from a *separate* probe source
/// (a Source is single-pass), so the run source streams the window untouched.
/// A no-local-data condition (unknown symbol, or a window overlapping no file / no
/// bars) is a usage error: stderr + exit(2), not a panic.
fn run_sample_real(symbol: &str, from_ms: Option<i64>, to_ms: Option<i64>) -> RunReport {
let (mut h, rx_eq, rx_ex) = sample_harness();
let server = std::sync::Arc::new(data_server::DataServer::new(data_server::DEFAULT_DATA_PATH));
let no_data = || -> ! {
eprintln!(
"aura: no local data for symbol '{symbol}' at {}",
data_server::DEFAULT_DATA_PATH
);
std::process::exit(2)
};
if !server.has_symbol(symbol) {
no_data();
}
let open = || aura_ingest::M1FieldSource::open(&server, symbol, from_ms, to_ms, aura_ingest::M1Field::Close);
// Manifest window: drain a separate probe (single-pass Source) for first/last ts.
let mut probe = match open() {
Some(p) => p,
None => no_data(),
};
let first = match aura_engine::Source::peek(&probe) {
Some(t) => t,
None => no_data(),
};
let mut last = first;
while let Some((t, _)) = aura_engine::Source::next(&mut probe) {
last = t;
}
let window = (first, last);
let source: Box<dyn aura_engine::Source> = match open() {
Some(s) => Box::new(s),
None => no_data(),
};
h.run(vec![source]);
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: sim_optimal_manifest(
vec![
("sma_fast".to_string(), 2.0),
("sma_slow".to_string(), 4.0),
("exposure_scale".to_string(), 0.5),
],
window,
),
metrics,
}
}
/// Parse the `run --real` tail: a mandatory `<SYMBOL>` then zero-or-more
/// `--from <ms>` / `--to <ms>` pairs in any order. Pure (no I/O, no exit) so the
/// arg grammar is unit-testable; `main` does the side effects. An unknown token, a
/// flag without its value, a non-`i64` ms, or a repeated flag is an `Err` carrying
/// a short usage message.
fn parse_real_args(rest: &[&str]) -> Result<(String, Option<i64>, Option<i64>), String> {
let usage = || "run --real <SYMBOL> [--from <ms>] [--to <ms>]".to_string();
let (symbol, mut tail) = match rest.split_first() {
Some((sym, t)) if !sym.is_empty() => (*sym, t),
_ => return Err(usage()),
};
let mut from: Option<i64> = None;
let mut to: Option<i64> = None;
while let Some((flag, t)) = tail.split_first() {
let (value, t) = t.split_first().ok_or_else(usage)?;
let ms: i64 = value.parse().map_err(|_| usage())?;
match *flag {
"--from" if from.is_none() => from = Some(ms),
"--to" if to.is_none() => to = Some(ms),
_ => return Err(usage()),
}
tail = t;
}
Ok((symbol.to_string(), from, to))
}
/// The SMA-cross signal as a named composite (price -> fast/slow SMA -> spread).
/// CLI-local sample builder; the engine ships no sample (the duplication with
/// `blueprint.rs`'s test helper is the dedup tracked in #14). Value-empty: the SMA
@@ -482,7 +570,7 @@ fn run_macd() -> RunReport {
}
const USAGE: &str =
"usage: aura run [--macd] | aura graph | aura sweep | aura runs list | aura runs rank <metric>";
"usage: aura run [--macd] | aura run --real <SYMBOL> [--from <ms>] [--to <ms>] | aura graph | aura sweep | aura runs list | aura runs rank <metric>";
fn main() {
// Collect argv and match the whole vector: every accepted form is exhaustive,
@@ -492,6 +580,13 @@ fn main() {
match args.iter().map(String::as_str).collect::<Vec<_>>().as_slice() {
["run"] => println!("{}", run_sample().to_json()),
["run", "--macd"] => println!("{}", run_macd().to_json()),
["run", "--real", rest @ ..] => match parse_real_args(rest) {
Ok((sym, from, to)) => println!("{}", run_sample_real(&sym, from, to).to_json()),
Err(msg) => {
eprintln!("aura: {msg}");
std::process::exit(2);
}
},
["graph"] => print!("{}", render::render_html(&sample_blueprint())),
["sweep"] => run_sweep(),
["runs", "list"] => runs_list(),
@@ -607,6 +702,77 @@ mod tests {
);
}
/// `aura run --real <SYMBOL>` dogfoods the #71 streaming Source seam: the same
/// built-in sample signal-quality harness, but fed real M1 **close** bars
/// streamed lazily through `aura_ingest::M1FieldSource` (a `Box<dyn Source>`),
/// not synthetic `VecSource` prices. The property: over a bounded real window,
/// `run_sample_real` yields a `RunReport` whose `total_pips` is finite and is
/// C1-deterministic — two runs of the same window are bit-identical JSON.
///
/// Gated like the ingest `streaming_seam` test: skip (early return) when the
/// local Pepperstone archive is absent, so the spec never fails on a machine
/// without the data. Uses the verified bounded 2006-08 `AAPL.US` window (the
/// same FROM_MS/TO_MS the ingest seam test drives) so the two-run determinism
/// check stays fast.
#[test]
fn run_sample_real_streams_real_close_bars_deterministically() {
// Same bounded 2006-08 inclusive-ms window the ingest streaming_seam test
// uses; AAPL.US M1 data is present there on a data-bearing machine.
const SYMBOL: &str = "AAPL.US";
const FROM_MS: i64 = 1_154_390_400_000;
const TO_MS: i64 = 1_157_068_799_999;
// Mirror skip_if_no_data: never fail where the local archive is absent.
let server = std::sync::Arc::new(data_server::DataServer::new(
data_server::DEFAULT_DATA_PATH,
));
if !server.has_symbol(SYMBOL) {
eprintln!(
"skip: no local data at {} (symbol {SYMBOL} absent)",
data_server::DEFAULT_DATA_PATH
);
return;
}
// The headline: a real-data run over the bounded window yields a finite,
// C1-deterministic RunReport.
let r1 = run_sample_real(SYMBOL, Some(FROM_MS), Some(TO_MS));
let r2 = run_sample_real(SYMBOL, Some(FROM_MS), Some(TO_MS));
assert!(
r1.metrics.total_pips.is_finite(),
"real-data run must yield finite pips: {:?}",
r1.metrics
);
// C1 at the CLI edge: the same real window streamed twice is bit-identical.
assert_eq!(
r1.to_json(),
r2.to_json(),
"two real-data runs of the same window must be bit-identical (C1)"
);
}
/// `parse_real_args` accepts a bare symbol (no window) and a full
/// symbol + `--from`/`--to` pair in any order, and rejects a flag missing its
/// value — the pure arg grammar `main` relies on for `run --real`.
#[test]
fn parse_real_args_accepts_symbol_and_optional_window() {
assert_eq!(parse_real_args(&["EURUSD"]), Ok(("EURUSD".to_string(), None, None)));
assert_eq!(
parse_real_args(&["EURUSD", "--from", "100", "--to", "200"]),
Ok(("EURUSD".to_string(), Some(100), Some(200)))
);
// flags in any order
assert_eq!(
parse_real_args(&["EURUSD", "--to", "200", "--from", "100"]),
Ok(("EURUSD".to_string(), Some(100), Some(200)))
);
// a flag without its value, an empty symbol, and a non-numeric ms all reject
assert!(parse_real_args(&["EURUSD", "--from"]).is_err());
assert!(parse_real_args(&[]).is_err());
assert!(parse_real_args(&["EURUSD", "--from", "notanumber"]).is_err());
}
#[test]
fn run_sample_is_deterministic_and_non_trivial() {
let r1 = run_sample();