Brummel a1cd7bc6f5 feat(campaign): monte_carlo stage arm + campaign-scope generalize phase (0108 tasks 3-4)
The mc arm bootstraps the stage's incoming R-evidence with one
semantics, input-shaped by position (#200 decision 1): after a
walk_forward it pools the wf family's per-window OOS trade_rs in roll
order into ONE r_bootstrap (PooledOos); after sweep/gates it
bootstraps each surviving member's fresh in-memory series
(PerSurvivor, ordinals into the population family; a zero-trade
member records the engine's defined all-zero degenerate). Seeded from
the campaign doc's seed (C1). The wf family is read by reference from
the cell's families vec — no clone. run_cell's Generalize arm is an
explicit no-op naming the campaign scope.

The generalize phase runs after the cell loop (#200 decision 2):
nominees (last wf window's OOS report, else the sweep winner; None on
gate truncation) grouped by (strategy, window) across instruments via
a BTreeMap (deterministic order); >= 2 winners feed the shipped
generalization(), fewer record the shortfall (generalization: None,
missing named) — divergent per-instrument winners are exposed via
their params, never averaged away.

Gates: campaign 40/0 (4 execute_mc + 3 execute_generalize new),
workspace build clean; the known-RED cli integration test flips in
task 5.

refs #200
2026-07-04 00:57:35 +02:00
2026-07-04 00:09:39 +02:00

aura

aura is a "game engine for traders." It is a Rust framework — and a playground — for authoring trading strategies as composable dataflow nodes, backtesting them deterministically and massively in parallel, validating them (sweep / Monte-Carlo / walk-forward), and freezing a validated strategy into a standalone bot with a broker connection. Its differentiator is the World: a program that constructs and orchestrates whole families of backtests, not the single run.

This README is a discoverability map of the shipped aura CLI — what commands exist and what they do. It deliberately keeps per-flag detail light; the two authoritative sources for exact syntax are always:

  • aura <command> --help — the exhaustive flag grammar.
  • The design ledger (docs/design/INDEX.md) and glossary (docs/glossary.md) — the concepts and invariants behind the surface.

Build & run

aura is a Cargo workspace. Build everything and you get one binary named aura:

cargo build --workspace          # binary at target/debug/aura
cargo build --workspace --release  # optimized, at target/release/aura

Invoke it as aura <command> … (examples below use the plain name).

Concepts in one breath

  • Blueprint — a serialized signal graph as data: a param-generic price → bias node graph. A blueprint file (blueprint.json) is the unit a downstream consumer loads and drives verbs over.
  • Open vs. closed — a blueprint with unbound (free) numeric knobs is open; one with every knob bound is closed. Different verbs want different states (see each verb below).
  • Family — the set of runs one verb produces over a blueprint (a sweep grid, a Monte-Carlo seed set, a walk-forward window sequence). Families are persisted in a content-addressed store and can be listed, ranked, and reproduced.
  • Axis — one named, sweepable knob of a blueprint (e.g. graph.fast.length), bound with a comma-separated value list.

Running & orchestrating a loaded blueprint

These verbs all take the blueprint file as their first positional argument and drive a family of runs over it. (Each verb also has a legacy built-in form selected by --strategy/--harness instead of a .json path, for the engine's own bundled example strategies — see --help.)

Command Purpose
aura run <bp.json> Run one backtest of a closed blueprint and print its report. An open (free-knob) blueprint is refused with a clean error — bind it, or use sweep.
aura sweep <bp.json> --list-axes Discover the blueprint's open, sweepable knobs. Prints each as <name>:<kind>. Run this first to learn the axis names.
aura sweep <bp.json> --axis <name>=<csv> [--axis …] Run a grid family over the named axes and persist it.
aura mc <bp.json> --seeds <n> Run a Monte-Carlo family of n seeded realizations. Wants a closed blueprint (the inverse of sweep).
aura walkforward <bp.json> --axis <name>=<csv> [--axis …] Run an in-sample-refit walk-forward family — rolling optimize + out-of-sample test across windows, stitched into one verdict + parameter stability. --select chooses the per-window objective.
aura runs families List every persisted family (id, kind, member count).
aura runs family <id> [rank <metric>] List one family's members, optionally ranked best-first by an R metric (e.g. sqn_normalized, expectancy_r).
aura reproduce <family-id> Re-derive every member of a persisted family from the content-addressed store and check it is bit-identical (the C18/C1 determinism guarantee).

Important contract — every open knob is mandatory. On sweep and walkforward, the knobs enumerated by --list-axes are all required: you must supply an --axis for each open knob. There is no default value — pin a knob you don't want to vary with a single-value axis (--axis name=4). Omitting one is a clean error naming the missing knob, not a silent default.

Use aura <cmd> --help for the full data-window (--real/--from/--to), naming (--name/--trace), and selection (--select) flags.

Authoring & introspecting topology

A blueprint is authored declaratively from a JSON op-list: an ordered list of by-identifier construction ops replayed against the standard node vocabulary.

Command Purpose
aura graph build Read an op-list document on stdin, build the blueprint, and print its canonical JSON to stdout (no trailing newline — it is the content-addressed artifact).
aura graph introspect --vocabulary List every node type available to op-lists.
aura graph introspect --node <T> Show one type's input ports, output fields, and param paths (with the bind-value form).
aura graph introspect --unwired Read a partial op-list on stdin and list its still-open interior slots.
aura graph introspect --content-id Read an op-list on stdin and print the SHA-256 content id of the blueprint it would build.
aura graph introspect --identity-id Read an op-list on stdin and print the SHA-256 identity id — the topology's debug-name-blind id, so two documents (or an op-script and a Rust-built blueprint) expressing the same topology print the same id. Combinable with --content-id (both ids, one per line, content id first).

Op-list shape

Each element is one op, tagged by "op". Node params are bound with the typed Scalar form — a tagged, capitalized-kind object: {"I64": 5}, {"F64": 1.5}, {"Bool": true}. A worked example (an SMA-crossover → bias signal):

[
  {"op":"source","role":"price","kind":"F64"},
  {"op":"add","type":"SMA","name":"fast","bind":{"length":{"I64":2}}},
  {"op":"add","type":"SMA","name":"slow","bind":{"length":{"I64":4}}},
  {"op":"add","type":"Sub"},
  {"op":"add","type":"Bias"},
  {"op":"feed","role":"price","into":["fast.series","slow.series"]},
  {"op":"connect","from":"fast.value","to":"sub.lhs"},
  {"op":"connect","from":"slow.value","to":"sub.rhs"},
  {"op":"connect","from":"sub.value","to":"bias.signal"},
  {"op":"expose","from":"bias.bias","as":"bias"}
]

Piping this document into aura graph build emits a blueprint.json you can then feed to run / sweep / mc / walkforward above:

aura graph build < crossover.ops.json > crossover.bp.json
aura sweep crossover.bp.json --list-axes

The op kinds are source, input, add, feed, connect, and expose. See aura graph introspect --node <T> for a type's exact ports and the op-script grammar in the design ledger for the full semantics.

Where to go deeper

  • aura <command> --help — exhaustive, always-current flag grammar.
  • docs/design/INDEX.md — the design ledger: architecture, invariants, the World.
  • docs/glossary.md — canonical terminology (blueprint, family, axis, sweep / Monte-Carlo / walk-forward, R, content-id, …).
S
Description
No description provided
Readme 18 MiB
Languages
Rust 68.9%
JavaScript 24.4%
HTML 6%
Shell 0.6%
CSS 0.1%