ebe85683c9
Architect drift review (holds: C14 headless authoring, C16/C17 no-DSL with aura-research a true leaf, content-id move behaviour-preserving per the untouched id goldens). Resolution per item: - fix (docs): C18 gains the cycle-0106 realization note (processes/ + campaigns/ stores, document canonical form, the content-id primitive's library home, the referential tier, no-executor status); the #109 analysis-meta-level open thread records the artifact half shipped v1 and what stays open (executor question, verb dissolution 'once it carries', the remaining #188 amendment package). Glossary: new campaign document + process document entries; content id generalized to all three artifact classes; experiment marked superseded by the campaign document (#188 re-cut of the builder-API thread). - fix (code): the --unwired guide advertised an identity_id process ref that validate_campaign refuses — the process.ref open-slot hint now says content-id-only (strategy refs keep both); lib + seam pins updated. - filed forward: #190 (metric-vocabulary single-sourcing, the 0105 roster drift class), #191 (identity-ref store scan is O(store), performance only). - carry-on: regression gates green by hand — cargo test --workspace 916/0, clippy -D warnings clean, cargo doc --no-deps 0 warnings; no baseline to ratify (project has no metric baseline scripts). Cycle 0106 spec and plan retired per convention (git rm); durable record is the ledger notes above plus #188/#189. refs #189
422 lines
18 KiB
Rust
422 lines
18 KiB
Rust
//! End-to-end coverage for the `aura process` verb family (#188/#189): drives
|
|
//! the built `aura` binary over argv/file, the exact surface a data-level
|
|
//! author uses.
|
|
|
|
use std::path::{Path, PathBuf};
|
|
use std::sync::OnceLock;
|
|
|
|
/// A fresh, unique working directory for a process test that persists
|
|
/// content-addressed documents under `./runs/` (so `aura process register`
|
|
/// never dirties the repo). Unique per test + per process; no external
|
|
/// tempfile dependency (mirrors `cli_run.rs` / `cli_broken_pipe.rs`).
|
|
fn temp_cwd(name: &str) -> PathBuf {
|
|
let dir = std::env::temp_dir().join(format!("aura-cli-{}-{}", std::process::id(), name));
|
|
let _ = std::fs::remove_dir_all(&dir);
|
|
std::fs::create_dir_all(&dir).expect("create temp cwd");
|
|
dir
|
|
}
|
|
|
|
fn run_code_in(dir: &Path, args: &[&str]) -> (String, Option<i32>) {
|
|
let out = std::process::Command::new(env!("CARGO_BIN_EXE_aura"))
|
|
.args(args)
|
|
.current_dir(dir)
|
|
.output()
|
|
.expect("binary runs");
|
|
let text = format!(
|
|
"{}{}",
|
|
String::from_utf8_lossy(&out.stdout),
|
|
String::from_utf8_lossy(&out.stderr)
|
|
);
|
|
(text, out.status.code())
|
|
}
|
|
|
|
fn run_code(args: &[&str]) -> (String, Option<i32>) {
|
|
run_code_in(Path::new("."), args)
|
|
}
|
|
|
|
const PROCESS_DOC: &str = r#"{
|
|
"format_version": 1,
|
|
"kind": "process",
|
|
"name": "wf-deflated-screen",
|
|
"pipeline": [
|
|
{ "block": "std::sweep", "metric": "net_expectancy_r", "select": "plateau:worst", "deflate": true },
|
|
{ "block": "std::gate", "all": [
|
|
{ "metric": "net_expectancy_r", "cmp": "gt", "value": 0.0 },
|
|
{ "metric": "overfit_probability", "cmp": "lt", "value": 0.1 } ] },
|
|
{ "block": "std::walk_forward", "folds": 4, "in_sample_bars": 4000,
|
|
"out_of_sample_bars": 1000, "metric": "net_expectancy_r", "select": "argmax" }
|
|
]
|
|
}"#;
|
|
|
|
fn write_doc(dir: &Path, name: &str, text: &str) -> PathBuf {
|
|
let p = dir.join(name);
|
|
std::fs::write(&p, text).expect("write doc");
|
|
p
|
|
}
|
|
|
|
#[test]
|
|
fn process_validate_reports_intrinsic_ok() {
|
|
let dir = temp_cwd("process-validate-ok");
|
|
write_doc(&dir, "p.process.json", PROCESS_DOC);
|
|
let (out, code) = run_code_in(&dir, &["process", "validate", "p.process.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
assert!(out.contains("process document valid (intrinsic): 3 pipeline blocks, 2 gate predicates"));
|
|
}
|
|
|
|
#[test]
|
|
fn process_validate_refuses_unknown_metric_as_prose_exit_1() {
|
|
let dir = temp_cwd("process-validate-bad-metric");
|
|
let bad = PROCESS_DOC.replacen(
|
|
"net_expectancy_r\", \"select\": \"plateau:worst",
|
|
"netto_r\", \"select\": \"plateau:worst",
|
|
1,
|
|
);
|
|
write_doc(&dir, "bad.process.json", &bad);
|
|
let (out, code) = run_code_in(&dir, &["process", "validate", "bad.process.json"]);
|
|
assert_eq!(code, Some(1));
|
|
assert!(out.contains("unknown metric \"netto_r\""));
|
|
assert!(!out.contains("UnknownMetric"), "Debug leak: {out}");
|
|
}
|
|
|
|
#[test]
|
|
fn process_introspect_vocabulary_block_and_content_id() {
|
|
let (out, code) = run_code(&["process", "introspect", "--vocabulary"]);
|
|
assert_eq!(code, Some(0));
|
|
for id in ["std::sweep", "std::gate", "std::walk_forward", "std::monte_carlo", "std::generalize"] {
|
|
assert!(out.contains(id), "vocabulary misses {id}: {out}");
|
|
}
|
|
let (out, code) = run_code(&["process", "introspect", "--block", "std::sweep"]);
|
|
assert_eq!(code, Some(0));
|
|
assert!(out.contains("metric"));
|
|
assert!(out.contains("required"));
|
|
|
|
let dir = temp_cwd("process-introspect-content-id");
|
|
write_doc(&dir, "p.process.json", PROCESS_DOC);
|
|
let (out, code) = run_code_in(&dir, &["process", "introspect", "--content-id", "p.process.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
let line = out.lines().find(|l| l.starts_with("content:")).expect("id line");
|
|
assert_eq!(line.len(), "content:".len() + 64);
|
|
}
|
|
|
|
#[test]
|
|
fn process_introspect_unknown_block_is_prose_exit_1() {
|
|
let (out, code) = run_code(&["process", "introspect", "--block", "std::nope"]);
|
|
assert_eq!(code, Some(1), "stdout/stderr: {out}");
|
|
assert!(out.contains("unknown block \"std::nope\""), "stdout/stderr: {out}");
|
|
}
|
|
|
|
#[test]
|
|
fn process_introspect_unwired_lists_open_slots() {
|
|
let dir = temp_cwd("process-introspect-unwired");
|
|
let partial = r#"{ "format_version": 1, "kind": "process",
|
|
"pipeline": [ { "block": "std::sweep", "metric": "sqn" } ] }"#;
|
|
write_doc(&dir, "partial.process.json", partial);
|
|
let (out, code) = run_code_in(&dir, &["process", "introspect", "--unwired", "partial.process.json"]);
|
|
assert_eq!(code, Some(0));
|
|
assert!(out.contains("open slot: name"));
|
|
assert!(out.contains("open slot: pipeline[0].select"));
|
|
}
|
|
|
|
#[test]
|
|
fn process_introspect_no_flag_is_usage_exit_2() {
|
|
let (_out, code) = run_code(&["process", "introspect"]);
|
|
assert_eq!(code, Some(2));
|
|
}
|
|
|
|
#[test]
|
|
fn process_register_stores_content_addressed_under_runs_root() {
|
|
let dir = temp_cwd("process-register");
|
|
write_doc(&dir, "p.process.json", PROCESS_DOC);
|
|
let (out, code) = run_code_in(&dir, &["process", "register", "p.process.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
let line = out.lines().find(|l| l.starts_with("registered process content:")).expect("line");
|
|
let id = line
|
|
.trim_start_matches("registered process content:")
|
|
.split(' ')
|
|
.next()
|
|
.expect("id");
|
|
assert!(dir.join("runs").join("processes").join(format!("{id}.json")).is_file());
|
|
}
|
|
|
|
/// The demo-project fixture (Aura.toml present), built once — mirrors
|
|
/// `project_load.rs`'s `built_fixture` (a separate test binary, so it needs
|
|
/// its own `OnceLock`, but `cargo build` is idempotent).
|
|
fn built_project() -> &'static PathBuf {
|
|
static BUILT: OnceLock<PathBuf> = OnceLock::new();
|
|
BUILT.get_or_init(|| {
|
|
let dir = Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/fixtures/demo-project");
|
|
let out = std::process::Command::new("cargo")
|
|
.arg("build")
|
|
.current_dir(&dir)
|
|
.output()
|
|
.expect("spawn cargo build for the fixture project");
|
|
assert!(
|
|
out.status.success(),
|
|
"fixture build failed:\n{}",
|
|
String::from_utf8_lossy(&out.stderr)
|
|
);
|
|
dir
|
|
})
|
|
}
|
|
|
|
/// A scratch filesystem entry this test writes under the git-tracked
|
|
/// demo-project fixture root (only `runs/` there is fixture-gitignored),
|
|
/// removed on drop — including during a mid-test panic — so a failed
|
|
/// assertion never leaks scratch docs into tracked working-tree state.
|
|
enum ScratchPath {
|
|
File(PathBuf),
|
|
Dir(PathBuf),
|
|
}
|
|
|
|
struct ScratchGuard(Vec<ScratchPath>);
|
|
|
|
impl Drop for ScratchGuard {
|
|
fn drop(&mut self) {
|
|
for p in &self.0 {
|
|
match p {
|
|
ScratchPath::File(p) => {
|
|
let _ = std::fs::remove_file(p);
|
|
}
|
|
ScratchPath::Dir(p) => {
|
|
let _ = std::fs::remove_dir_all(p);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/// The `aura campaign validate` referential tier (the campaign family's
|
|
/// headline addition over the intrinsic-only process family), exercised at
|
|
/// the CLI seam inside a real project: a fully-resolved document prints the
|
|
/// "valid (referential)" success line, and an unresolved reference prints
|
|
/// the "do not resolve" fault block through `ref_fault_prose`. The
|
|
/// constituents (`validate_campaign_refs`, `ref_fault_prose`) are unit-
|
|
/// tested elsewhere; this pins that `aura campaign validate` actually wires
|
|
/// them together end to end.
|
|
#[test]
|
|
fn campaign_validate_in_project_reports_referential_tier_end_to_end() {
|
|
let dir = built_project();
|
|
let runs_dir = dir.join("runs");
|
|
std::fs::remove_dir_all(&runs_dir).ok();
|
|
let _cleanup = ScratchGuard(vec![
|
|
ScratchPath::Dir(runs_dir.clone()),
|
|
ScratchPath::File(dir.join("seed.process.json")),
|
|
ScratchPath::File(dir.join("ref-ok.campaign.json")),
|
|
ScratchPath::File(dir.join("ref-bad.campaign.json")),
|
|
]);
|
|
|
|
// Seed one real, content-addressed, open-param blueprint into the
|
|
// project's own store via a real sweep (mirrors `project_load.rs`'s
|
|
// anchor test).
|
|
let open_bp = format!("{}/tests/fixtures/sma_signal_open.json", env!("CARGO_MANIFEST_DIR"));
|
|
let (sweep_out, sweep_code) = run_code_in(
|
|
dir,
|
|
&[
|
|
"sweep",
|
|
&open_bp,
|
|
"--axis",
|
|
"sma_signal.fast.length=2,4",
|
|
"--axis",
|
|
"sma_signal.slow.length=8,16",
|
|
"--name",
|
|
"campaign-ref-seed",
|
|
],
|
|
);
|
|
assert_eq!(sweep_code, Some(0), "seed sweep failed: {sweep_out}");
|
|
let bp_id = std::fs::read_dir(runs_dir.join("blueprints"))
|
|
.expect("blueprints dir")
|
|
.next()
|
|
.expect("one stored blueprint")
|
|
.expect("dir entry")
|
|
.path()
|
|
.file_stem()
|
|
.expect("stem")
|
|
.to_string_lossy()
|
|
.into_owned();
|
|
|
|
// Register a valid process into the same project store.
|
|
write_doc(dir, "seed.process.json", PROCESS_DOC);
|
|
let (proc_out, proc_code) = run_code_in(dir, &["process", "register", "seed.process.json"]);
|
|
assert_eq!(proc_code, Some(0), "seed process register failed: {proc_out}");
|
|
let proc_id = proc_out
|
|
.lines()
|
|
.find(|l| l.starts_with("registered process content:"))
|
|
.expect("register line")
|
|
.trim_start_matches("registered process content:")
|
|
.split(' ')
|
|
.next()
|
|
.expect("id")
|
|
.to_string();
|
|
|
|
// "fast.length": the axis name is the RAW composite's `param_space` name.
|
|
// `validate_campaign_refs` loads the stored blueprint bare, unlike the
|
|
// sweep's `wrap_r`-wrapped axis probe, so it does NOT carry the
|
|
// "sma_signal." prefix `aura sweep --axis` binds against.
|
|
let campaign = format!(
|
|
r#"{{
|
|
"format_version": 1,
|
|
"kind": "campaign",
|
|
"name": "ref-check",
|
|
"data": {{ "instruments": ["GER40"], "windows": [ {{ "from_ms": 1, "to_ms": 2 }} ] }},
|
|
"strategies": [ {{ "ref": {{ "content_id": "{bp}" }},
|
|
"axes": {{ "fast.length": {{ "kind": "I64", "values": [2] }} }} }} ],
|
|
"process": {{ "ref": {{ "content_id": "{proc}" }} }},
|
|
"seed": 1,
|
|
"presentation": {{ "persist_taps": [], "emit": ["family_table"] }}
|
|
}}"#,
|
|
bp = bp_id,
|
|
proc = proc_id
|
|
);
|
|
write_doc(dir, "ref-ok.campaign.json", &campaign);
|
|
let (out, code) = run_code_in(dir, &["campaign", "validate", "ref-ok.campaign.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
assert!(out.contains(
|
|
"campaign document valid (referential): all references resolve, axes are in the param space"
|
|
));
|
|
|
|
// An unresolved process reference: the fault block + `ref_fault_prose`
|
|
// mapping, prose exit 1, at the same CLI seam.
|
|
let bad = campaign.replace(&proc_id, "0000000000000000000000000000000000000000000000000000000000000000");
|
|
write_doc(dir, "ref-bad.campaign.json", &bad);
|
|
let (out2, code2) = run_code_in(dir, &["campaign", "validate", "ref-bad.campaign.json"]);
|
|
assert_eq!(code2, Some(1));
|
|
assert!(out2.contains("campaign references do not resolve:"), "stdout/stderr: {out2}");
|
|
assert!(out2.contains("not found in the project store"), "stdout/stderr: {out2}");
|
|
|
|
// `_cleanup` (a `ScratchGuard`) removes the scratch docs and `runs/` on
|
|
// drop, at the end of this scope — including on a mid-test panic.
|
|
}
|
|
|
|
const CAMPAIGN_DOC: &str = r#"{
|
|
"format_version": 1,
|
|
"kind": "campaign",
|
|
"name": "screen",
|
|
"data": { "instruments": ["GER40"], "windows": [ { "from_ms": 1, "to_ms": 2 } ] },
|
|
"strategies": [ { "ref": { "content_id": "9f3a" },
|
|
"axes": { "fast": { "kind": "I64", "values": [8] } } } ],
|
|
"process": { "ref": { "content_id": "4e2d" } },
|
|
"seed": 1,
|
|
"presentation": { "persist_taps": [], "emit": ["family_table"] }
|
|
}"#;
|
|
|
|
#[test]
|
|
fn campaign_validate_outside_project_skips_referential_tier() {
|
|
let dir = temp_cwd("campaign-validate-outside-project");
|
|
write_doc(&dir, "c.campaign.json", CAMPAIGN_DOC);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "validate", "c.campaign.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
assert!(out.contains("campaign document valid (intrinsic):"));
|
|
assert!(out.contains("referential checks skipped (no Aura.toml found up from "));
|
|
}
|
|
|
|
#[test]
|
|
fn campaign_validate_refuses_empty_axis_prose_exit_1() {
|
|
let dir = temp_cwd("campaign-validate-empty-axis");
|
|
let bad = CAMPAIGN_DOC.replacen(r#""values": [8]"#, r#""values": []"#, 1);
|
|
write_doc(&dir, "bad.campaign.json", &bad);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "validate", "bad.campaign.json"]);
|
|
assert_eq!(code, Some(1));
|
|
assert!(out.contains("axes.fast: an axis is a non-empty finite set"));
|
|
assert!(!out.contains("EmptyAxis"), "Debug leak: {out}");
|
|
}
|
|
|
|
#[test]
|
|
fn campaign_introspect_vocabulary_lists_sections() {
|
|
let (out, code) = run_code(&["campaign", "introspect", "--vocabulary"]);
|
|
assert_eq!(code, Some(0));
|
|
for id in ["std::data", "std::strategy", "std::process_ref", "std::presentation"] {
|
|
assert!(out.contains(id), "vocabulary misses {id}: {out}");
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn campaign_introspect_unwired_reports_the_spec_example_slots() {
|
|
let dir = temp_cwd("campaign-introspect-unwired");
|
|
let draft = r#"{ "format_version": 1, "kind": "campaign", "name": "draft",
|
|
"data": { "instruments": ["GER40"], "windows": [ { "from_ms": 1, "to_ms": 2 } ] },
|
|
"strategies": [ { "ref": { "content_id": "9f3a" },
|
|
"axes": { "slow": { "kind": "I64", "values": [] } } } ],
|
|
"seed": 1,
|
|
"presentation": { "persist_taps": [], "emit": [] } }"#;
|
|
write_doc(&dir, "draft.campaign.json", draft);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "introspect", "--unwired", "draft.campaign.json"]);
|
|
assert_eq!(code, Some(0));
|
|
assert!(out.contains("open slot: process.ref (required, content id of a process document)"));
|
|
assert!(out.contains("open slot: strategies[0].axes.slow (axis declared empty — a P1 axis is a non-empty finite set)"));
|
|
}
|
|
|
|
/// The campaign twin of `process_introspect_vocabulary_block_and_content_id`'s
|
|
/// `--content-id` branch: pins that `campaign introspect --content-id` wires
|
|
/// `parse_valid_campaign` + `campaign_to_json` + `content_id_of` end to end
|
|
/// (the process branch was covered; this one was not).
|
|
#[test]
|
|
fn campaign_introspect_content_id_prints_hash() {
|
|
let dir = temp_cwd("campaign-introspect-content-id");
|
|
write_doc(&dir, "c.campaign.json", CAMPAIGN_DOC);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "introspect", "--content-id", "c.campaign.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
let line = out.lines().find(|l| l.starts_with("content:")).expect("id line");
|
|
assert_eq!(line.len(), "content:".len() + 64);
|
|
}
|
|
|
|
#[test]
|
|
fn campaign_register_stores_content_addressed_under_runs_root() {
|
|
let dir = temp_cwd("campaign-register");
|
|
write_doc(&dir, "c.campaign.json", CAMPAIGN_DOC);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "register", "c.campaign.json"]);
|
|
assert_eq!(code, Some(0), "stdout/stderr: {out}");
|
|
let line = out.lines().find(|l| l.starts_with("registered campaign content:")).expect("line");
|
|
let id = line
|
|
.trim_start_matches("registered campaign content:")
|
|
.split(' ')
|
|
.next()
|
|
.expect("id");
|
|
assert!(dir.join("runs").join("campaigns").join(format!("{id}.json")).is_file());
|
|
}
|
|
|
|
/// `guard_one_mode` is shared, family-parameterized code (`process` and
|
|
/// `campaign` both route through it). The process family already pins the
|
|
/// zero-flags arm; this pins that the campaign family gets its own family
|
|
/// name threaded into the usage line, not a copy-pasted "process" string.
|
|
#[test]
|
|
fn campaign_introspect_no_flag_usage_names_the_campaign_family() {
|
|
let (out, code) = run_code(&["campaign", "introspect"]);
|
|
assert_eq!(code, Some(2), "stdout/stderr: {out}");
|
|
assert!(
|
|
out.contains("Usage: aura campaign introspect --vocabulary | --block <ID> | --unwired <FILE> | --content-id <FILE>"),
|
|
"stdout/stderr: {out}"
|
|
);
|
|
}
|
|
|
|
/// `guard_one_mode` requires *exactly* one mode: the zero-flags arm is
|
|
/// pinned elsewhere, but nothing previously exercised the over-selection
|
|
/// arm (`selected_modes() != 1` is not just `== 0`). Two modes at once must
|
|
/// refuse with the same usage-exit-2 idiom, not silently pick one.
|
|
#[test]
|
|
fn campaign_introspect_two_flags_is_usage_exit_2() {
|
|
let (out, code) = run_code(&["campaign", "introspect", "--vocabulary", "--block", "std::data"]);
|
|
assert_eq!(code, Some(2), "stdout/stderr: {out}");
|
|
assert!(out.contains("Usage: aura campaign introspect"), "stdout/stderr: {out}");
|
|
}
|
|
|
|
/// Register must be a gate, not a passthrough: an invalid document is
|
|
/// refused with prose (exit 1) and — the property that matters for a
|
|
/// content-addressed store — no file is ever written under `runs/campaigns/`
|
|
/// for it. A store that could contain unvalidated documents would make
|
|
/// every downstream reader re-derive the checks register was supposed to
|
|
/// have already made.
|
|
#[test]
|
|
fn campaign_register_refuses_invalid_document_and_writes_nothing() {
|
|
let dir = temp_cwd("campaign-register-invalid");
|
|
let bad = CAMPAIGN_DOC.replacen(r#""values": [8]"#, r#""values": []"#, 1);
|
|
write_doc(&dir, "bad.campaign.json", &bad);
|
|
let (out, code) = run_code_in(&dir, &["campaign", "register", "bad.campaign.json"]);
|
|
assert_eq!(code, Some(1), "stdout/stderr: {out}");
|
|
assert!(out.contains("refusing to register:"), "stdout/stderr: {out}");
|
|
assert!(out.contains("axes.fast: an axis is a non-empty finite set"), "stdout/stderr: {out}");
|
|
assert!(
|
|
!dir.join("runs").join("campaigns").exists(),
|
|
"register must not create a store entry for an invalid document"
|
|
);
|
|
}
|