docs+scaffold: engine/project split (C16-C18), aura-std, usage doc

Refine the structure per interview: aura is the reusable engine, research projects are separate external repos depending on it (C16). Add aura-std (universal standard-node tier) to the workspace; remove nodes/ from the engine (project concept). Record authoring-surface = Claude Code + skills pipeline, no embedded coding-LLM (C17), and project management = one-repo-one-project + Aura-native run registry (C18). Add CLAUDE.md invariants 9-10, code_roots -> [crates], and docs/project-layout.md documenting the day-in-the-life and project repo layout.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-03 02:04:18 +02:00
parent 3d33cc6fe5
commit b99912ca59
9 changed files with 190 additions and 19 deletions
+88
View File
@@ -0,0 +1,88 @@
# How aura is used — engine, projects, and a day in the life
This document describes the *outside* of aura: how you sit in front of it and
what a research session looks like. The *inside* (the engine's contracts) is the
design ledger (`docs/design/INDEX.md`).
## Engine vs. project (the game-engine split)
aura is a **game engine for traders**, and like any game engine it is separate
from the things built with it:
- **This repo (`aura`)** is the **engine**: `aura-core` (the shared contract),
`aura-std` (universal standard nodes), `aura-engine` (the deterministic sim
runtime), `aura-cli` (the `aura` binary), and later the egui playground. It
ships at most `examples/` fixture nodes for its own tests — never your real
signals.
- **A research project** is its **own external repo** (e.g. `~/dev/ger40-lab/`),
with its own git history, its own Gitea repo (its own forward-queue), and a
cargo dependency on aura. This is where you and Claude author signals and where
the runs live. (See contract **C16**.)
The `aura` CLI is a tool you run *inside* a project directory — it finds the
project root by walking up to an `Aura.toml`, the way `cargo` finds `Cargo.toml`.
## A project repo
```
ger40-lab/ # your research project — a separate repo
├── Aura.toml # project config: symbols in scope, default data
│ # window, broker profile, runs dir (schema TBD)
├── Cargo.toml # depends on aura-core (+ shared node crates)
├── CLAUDE.md # the project's own skills wiring (authoring discipline)
├── .claude/dev-cycle-profile.yml
├── nodes/ # project-local, experimental nodes (cdylib)
│ └── third-candle-long/
├── runs/ # the run registry: manifest + metrics per run
└── (frozen bots, results, …)
```
## Where reusable nodes live (three tiers)
Everything that plugs into the engine is fractally a `Node`. Reuse is plain
cargo, layered by maturity (contract C16):
1. **`aura-std`** — universal blocks shipped with the engine (SMA/ATR/RSI,
resamplers, the `SessionNode`, standard combinators, broker profiles).
2. **Shared node crates** — cross-project-reusable blocks in their own repos
(e.g. `Brummel/aura-nodes-fx`), pulled in as cargo git dependencies.
3. **Project-local `nodes/`** — experimental, project-specific blocks.
Promotion is the ordinary Rust gradient: a node proves itself project-local →
gets extracted into a shared crate → if it turns universal, into `aura-std`.
Shared nodes are `rlib` dependencies; the hot-reload unit stays the project-side
`cdylib` that composes them, so editing a shared node still rebuilds and reloads
the dependent.
## Authoring happens in Claude Code (contract C17)
aura has no built-in coding-LLM. You author by talking to Claude Code, which
writes the node crate, builds it, runs it, and reports back. IONOS LLMs appear
only as a *runtime data source* (e.g. a news-agent node emitting a bias),
recorded before it enters a backtest, and only with your per-session consent.
## A day in the life
1. **You** (in Claude Code, inside `ger40-lab/`): "I suspect the 3rd 15m candle
after GER40 open is long-biased when the first two close bullish — build it as
a signal."
2. **Claude** (via the skills pipeline) writes `nodes/third-candle-long/`,
implements `schema` + `eval` against `aura-core`.
3. **Backtest:** `aura backtest nodes/third-candle-long --symbol GER40
--from 2020 --to 2024 --broker pepperstone` → a metrics table (trades,
hit-rate, P&L, max-DD, Sharpe) + a run record (manifest + metrics) under
`runs/`.
4. **Sweep + Monte-Carlo:** `aura sweep … --grid lookback=5..50,thresh=0.5..0.9
--mc-seeds 1000` → a distribution of metrics, best params, robustness bands.
5. **Compose:** "combine it with `momentum-filter` as a weighted sum" → Claude
writes a composite node (fractal, C9).
6. **Walk-forward:** `aura walkforward …` → an out-of-sample verdict.
7. **Freeze:** `aura freeze nodes/strategy-y --broker pepperstone
--out bots/strategy-y` → a standalone, statically-linked bot (C13).
8. **(Later) Look:** `aura play` opens the egui playground — equity curve, trade
overlays on the chart, sweep heatmaps. For *looking*, not authoring (C14).
CLI command names and `Aura.toml` are illustrative; the concrete surface is
designed with the relevant milestone (see the open threads in the design ledger).
The forward-queue — what to try next — lives in the project's Gitea tracker, not
in code (contract C18).