Aura/crates/aura-cli/tests/cli_run.rs

//! Integration test: drive the built `aura` binary as a downstream user would,
//! asserting the `run` subcommand's stdout/exit contract and the bad-args path.

use std::process::Command;

/// Path to the freshly-built `aura` binary (Cargo sets this env var for the test
/// crate; the binary is named `aura` in `Cargo.toml`).
const BIN: &str = env!("CARGO_BIN_EXE_aura");

/// A fresh, unique working directory for a process test that persists run
/// records (so `aura sweep`'s `./runs/runs.jsonl` never dirties the repo).
/// Unique per test + per process; no external tempfile dependency.
fn temp_cwd(name: &str) -> std::path::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
}

#[test]
fn run_prints_json_and_exits_zero() {
    let out = Command::new(BIN).arg("run").output().expect("spawn aura run");
    assert!(out.status.success(), "exit status: {:?}", out.status);

    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    // exactly one line (the JSON object + a trailing newline from println!).
    assert_eq!(stdout.lines().count(), 1, "stdout was: {stdout:?}");
    let line = stdout.trim_end();

    // canonical cycle-0009 JSON shape: nested manifest + metrics, stable keys.
    // The manifest leads with a `commit` field; its value is the build's git
    // identity (asserted by `run_manifest_commit_carries_real_git_head`), so
    // this shape check pins only the surrounding structure, not the value.
    assert!(line.starts_with("{\"manifest\":{\"commit\":\""), "got: {line}");
    assert!(line.contains("\"broker\":\"sim-optimal(pip_size=0.0001)\""), "got: {line}");
    assert!(line.contains("\"window\":[1,7]"), "got: {line}");
    assert!(line.contains("\"metrics\":{\"total_pips\":"), "got: {line}");
    // the integer sign-flip count is stable across float renderings.
    assert!(line.ends_with("\"exposure_sign_flips\":1}}"), "got: {line}");
}

/// Property: the RunManifest is self-identifying — its `commit` carries the
/// real code identity that produced the run, not a placeholder. C8/C18 audit
/// trail (this run = this commit): once runs are archived, `manifest.commit`
/// must point back at the source. The build captures the current git HEAD at
/// compile time; the `"unknown"` literal survives only when there is no git.
///
/// Structural assertion (not exact-equality) on purpose: the working tree may
/// be dirty when this runs (e.g. this very test file uncommitted), so a build
/// that appends a `-dirty` suffix would not equal `rev-parse HEAD` verbatim.
/// The honest contract is: the field CONTAINS the current HEAD sha AND is not
/// the bare `"unknown"` placeholder — true regardless of dirtiness/suffix.
#[test]
fn run_manifest_commit_carries_real_git_head() {
    // The current HEAD sha, obtained the same way the build is expected to.
    let head = Command::new("git")
        .args(["rev-parse", "HEAD"])
        .output()
        .expect("spawn git rev-parse HEAD");
    assert!(head.status.success(), "git rev-parse HEAD failed");
    let head_sha = String::from_utf8(head.stdout).expect("utf-8 sha");
    let head_sha = head_sha.trim();
    assert!(!head_sha.is_empty(), "empty HEAD sha");

    // Drive the binary and pull `manifest.commit` out of the single JSON line.
    let out = Command::new(BIN).arg("run").output().expect("spawn aura run");
    assert!(out.status.success(), "exit status: {:?}", out.status);
    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    let line = stdout.trim_end();

    // Locate the `"commit":"<value>"` value without a JSON dependency (the
    // sibling tests parse this output by substring too).
    let key = "\"commit\":\"";
    let start = line.find(key).expect("manifest has a commit field") + key.len();
    let rest = &line[start..];
    let end = rest.find('"').expect("commit field is a closed string");
    let commit = &rest[..end];

    assert_ne!(
        commit, "unknown",
        "manifest.commit is still the placeholder: {line}"
    );
    assert!(
        commit.contains(head_sha),
        "manifest.commit {commit:?} should contain the current HEAD sha {head_sha:?}; line: {line}"
    );
}

/// Property: `aura run` is strict about its argument vector — a trailing
/// unexpected token (e.g. a typo'd flag like `aura run --sweep`) takes the
/// error path (usage on stderr, exit 2), never a silent full run. This is the
/// strict reading ratified in #16: keying only on the first token being `run`
/// and ignoring the rest would let a typo masquerade as a successful run.
/// The same test pins positive-preservation — bare `aura run` still emits the
/// JSON report on stdout and exits 0 — so the strict guard cannot regress the
/// happy path.
#[test]
fn run_with_trailing_token_is_strict_and_exits_two() {
    // Negative: an unexpected trailing token is rejected like a bad-args call.
    let out = Command::new(BIN)
        .args(["run", "extra-garbage"])
        .output()
        .expect("spawn aura run extra-garbage");
    assert_eq!(
        out.status.code(),
        Some(2),
        "`aura run extra-garbage` must reject the trailing token: {:?}",
        out.status
    );
    assert!(
        out.stdout.is_empty(),
        "stdout should be empty on the usage path, got: {:?}",
        String::from_utf8_lossy(&out.stdout)
    );
    let stderr = String::from_utf8(out.stderr).expect("utf-8 stderr");
    assert!(stderr.contains("usage"), "stderr was: {stderr:?}");

    // Positive-preservation: bare `aura run` still runs and prints the report.
    let ok = Command::new(BIN).arg("run").output().expect("spawn aura run");
    assert_eq!(
        ok.status.code(),
        Some(0),
        "bare `aura run` must still succeed: {:?}",
        ok.status
    );
    let ok_stdout = String::from_utf8(ok.stdout).expect("utf-8 stdout");
    assert!(
        ok_stdout.trim_start().starts_with("{\"manifest\":"),
        "bare `aura run` should print the JSON report, got: {ok_stdout:?}"
    );
}

#[test]
fn run_real_unspecced_symbol_refuses_with_exit_2() {
    // The instrument_spec lookup precedes any data access, so an un-specced symbol
    // refuses with NO local data required (CI-safe). "NONEXISTENT" is not in the
    // vetted table.
    let out = std::process::Command::new(env!("CARGO_BIN_EXE_aura"))
        .args(["run", "--real", "NONEXISTENT"])
        .output()
        .expect("spawn aura");
    assert_eq!(out.status.code(), Some(2), "expected exit 2");
    let stderr = String::from_utf8_lossy(&out.stderr);
    assert!(
        stderr.contains("no vetted pip/instrument spec for symbol 'NONEXISTENT'"),
        "expected the per-instrument-pip refusal message, got: {stderr}"
    );
}

/// Property: the un-specced-symbol refusal is a CLEAN refusal — it emits NOTHING
/// on stdout, never a partial `RunReport`. The #22 acceptance is "refuse INSTEAD
/// of emitting nonsense": the pip lookup precedes harness construction and data
/// access, so a `None` spec must short-circuit to `exit(2)` before any JSON line
/// can reach stdout. A regression that moved the lookup after a partial run would
/// leak a `{"manifest":...}` line here while still exiting non-zero; this pins
/// that it cannot. Archive-independent (the lookup never touches local data).
#[test]
fn run_real_unspecced_symbol_emits_no_stdout_report() {
    let out = std::process::Command::new(env!("CARGO_BIN_EXE_aura"))
        .args(["run", "--real", "NONEXISTENT"])
        .output()
        .expect("spawn aura");
    assert_eq!(out.status.code(), Some(2), "expected exit 2: {:?}", out.status);
    assert!(
        out.stdout.is_empty(),
        "the refusal must not leak a partial report to stdout, got: {:?}",
        String::from_utf8_lossy(&out.stdout)
    );
}

/// Property: the pip-honesty refusal keys on the SYMBOL being un-specced, not on
/// `--real` being taken at all. A *vetted* symbol (`EURUSD`, in the instrument
/// table) gets PAST the `instrument_spec` lookup, so it never produces the
/// pip-refusal message — it either runs to a report (local data present) or hits
/// the DISTINCT no-local-data usage path ("no local data for symbol"). Either
/// way the "no vetted pip/instrument spec" string is absent. This distinguishes
/// the per-instrument-pip honesty lever from the unrelated arg-grammar / no-data
/// error paths, and is archive-independent (asserts only on the absence of the
/// pip-refusal string, true whether or not EURUSD data is on the machine).
#[test]
fn run_real_vetted_symbol_never_hits_the_pip_refusal() {
    let out = std::process::Command::new(env!("CARGO_BIN_EXE_aura"))
        .args(["run", "--real", "EURUSD"])
        .output()
        .expect("spawn aura");
    let stderr = String::from_utf8_lossy(&out.stderr);
    assert!(
        !stderr.contains("no vetted pip/instrument spec"),
        "a vetted symbol must clear the pip lookup, never the pip-refusal; stderr: {stderr}"
    );
    // It resolves to exactly one of the two legitimate outcomes: a clean report
    // (exit 0, data present) or the distinct no-local-data refusal (exit 2).
    match out.status.code() {
        Some(0) => assert!(
            String::from_utf8_lossy(&out.stdout)
                .trim_start()
                .starts_with("{\"manifest\":"),
            "exit 0 must carry a JSON report, got: {:?}",
            String::from_utf8_lossy(&out.stdout)
        ),
        Some(2) => assert!(
            stderr.contains("no local data for symbol 'EURUSD'"),
            "exit 2 for a vetted symbol must be the no-data path, got: {stderr}"
        ),
        other => panic!("unexpected exit for a vetted real run: {other:?}; stderr: {stderr}"),
    }
}

/// Property: a vetted symbol threads its looked-up pip all the way to the binary's
/// emitted manifest — `aura run --real GER40` renders the INDEX pip
/// `sim-optimal(pip_size=1)`, not the FX `0.0001` literal the synthetic path uses.
/// This is the #22 headline at the built-binary boundary (criterion 2: GER40=1.0
/// vs EURUSD=0.0001 vs un-specced→refuse): the metadata channel reaches stdout, so
/// equity is honestly scaled per instrument. Gated on local GER40 data — skip
/// cleanly when the archive is absent (the project's skip-on-no-data convention),
/// so it never fails on a data-less machine; the no-data path is the distinct
/// "no local data" refusal (exit 2), not the pip-refusal, asserted above.
#[test]
fn run_real_vetted_index_pip_reaches_the_emitted_manifest() {
    // The vetted GER40 Sept-2024 window (inclusive Unix-ms), the same calendar
    // month the gated ingest path drives; bounding it keeps the run fast.
    const FROM_MS: &str = "1725148800000";
    const TO_MS: &str = "1727740799999";
    let out = std::process::Command::new(env!("CARGO_BIN_EXE_aura"))
        .args(["run", "--real", "GER40", "--from", FROM_MS, "--to", TO_MS])
        .output()
        .expect("spawn aura");

    // Skip on a data-less machine: a vetted symbol with no local data takes the
    // distinct no-data path (exit 2, "no local data"), never the pip-refusal.
    if out.status.code() == Some(2) {
        let stderr = String::from_utf8_lossy(&out.stderr);
        assert!(
            stderr.contains("no local data for symbol 'GER40'"),
            "exit 2 for vetted GER40 must be the no-data path, got: {stderr}"
        );
        eprintln!("skip: no local GER40 data");
        return;
    }

    assert_eq!(out.status.code(), Some(0), "exit: {:?}", out.status);
    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    let line = stdout.trim_end();
    // the looked-up index pip (1.0 -> "1") reaches the manifest, not the FX 0.0001.
    assert!(
        line.contains("\"broker\":\"sim-optimal(pip_size=1)\""),
        "GER40 must render the index pip in the manifest, got: {line}"
    );
}

#[test]
fn run_trace_persists_taps_and_plain_run_writes_no_traces() {
    let cwd = temp_cwd("run-trace");

    // plain `aura run` (no --trace) persists nothing to disk.
    let plain = Command::new(BIN).arg("run").current_dir(&cwd).output().expect("spawn aura run");
    assert!(plain.status.success(), "plain run exit: {:?}", plain.status);
    assert!(!cwd.join("runs/traces").exists(), "plain run must write no trace files");

    // `aura run --trace demo` persists the two taps + index, and still prints the report.
    let traced = Command::new(BIN)
        .args(["run", "--trace", "demo"])
        .current_dir(&cwd)
        .output()
        .expect("spawn aura run --trace");
    assert!(traced.status.success(), "traced run exit: {:?}", traced.status);
    let stdout = String::from_utf8(traced.stdout).expect("utf-8 stdout");
    assert!(stdout.trim_end().starts_with("{\"manifest\":{"), "report still printed: {stdout:?}");
    assert!(cwd.join("runs/traces/demo/index.json").exists(), "index.json written");
    assert!(cwd.join("runs/traces/demo/equity.json").exists(), "equity tap written");
    assert!(cwd.join("runs/traces/demo/exposure.json").exists(), "exposure tap written");

    let _ = std::fs::remove_dir_all(&cwd);
}

/// Property: a persisted `<tap>.json` is the **columnar SoA form** a downstream
/// chart can consume, not an opaque blob — it carries the four
/// `tap`/`kinds`/`ts`/`columns` keys, the equity tap is kind-tagged `["F64"]`
/// (C7: the base type survives on disk), and the SoA invariant holds: `ts` has one
/// entry per recorded cycle and EVERY column has exactly that many entries (parallel
/// arrays, one timestamp per row). This is acceptance criterion 2 at the built-binary
/// file boundary — the unit round-trip pins the in-memory transpose, but only an
/// end-to-end run pins that the bytes actually written to disk hold that shape.
/// Asserts on structure + array-length parity, never on the exact float values
/// (pip equity's low bits vary build-to-build), so it stays deterministic.
#[test]
fn run_trace_persists_columnar_soa_shape_on_disk() {
    let cwd = temp_cwd("run-trace-shape");
    let out = Command::new(BIN)
        .args(["run", "--trace", "demo"])
        .current_dir(&cwd)
        .output()
        .expect("spawn aura run --trace");
    assert!(out.status.success(), "traced run exit: {:?}", out.status);

    let equity = std::fs::read_to_string(cwd.join("runs/traces/demo/equity.json"))
        .expect("read equity.json");
    // The four SoA keys are present, equity is f64-kind-tagged, and the parallel
    // arrays open as expected (the synthetic sample harness has a single column).
    assert!(equity.contains("\"tap\":\"equity\""), "tap name missing: {equity}");
    assert!(equity.contains("\"kinds\":[\"F64\"]"), "F64 kind tag missing: {equity}");
    assert!(equity.contains("\"ts\":["), "ts axis missing: {equity}");
    assert!(equity.contains("\"columns\":[["), "columns array missing: {equity}");

    // SoA invariant: one timestamp per row, and every column has exactly that many
    // entries. Count the ts entries (the synthetic window is 7 cycles) and the
    // single column's entries by their comma-separated cardinality.
    let ts_body = json_array_body(&equity, "\"ts\":[");
    let col_body = json_array_body(&equity, "\"columns\":[[");
    let ts_len = ts_body.split(',').count();
    let col_len = col_body.split(',').count();
    assert_eq!(ts_len, 7, "synthetic run records 7 cycles; ts was: {ts_body:?}");
    assert_eq!(
        col_len, ts_len,
        "SoA parity broken: ts has {ts_len} entries but the column has {col_len}; file: {equity}"
    );

    let _ = std::fs::remove_dir_all(&cwd);
}

/// Property: `index.json` is the run's **table of contents** — it carries the run's
/// `RunManifest` (so a chart page can show run context: commit, broker, window) and
/// the tap names in a **deterministic order** (`["equity","exposure"]`). The serve
/// half (`aura chart`, iteration 2) reads taps in this index order; a regression that
/// dropped the manifest, or made the tap list order-unstable, would silently corrupt
/// the chart header / the per-series mapping. Asserts on the manifest's structural
/// presence (the commit value is the volatile git HEAD, pinned elsewhere) and the
/// exact deterministic tap order.
#[test]
fn run_trace_index_carries_manifest_and_ordered_tap_list() {
    let cwd = temp_cwd("run-trace-index");
    let out = Command::new(BIN)
        .args(["run", "--trace", "demo"])
        .current_dir(&cwd)
        .output()
        .expect("spawn aura run --trace");
    assert!(out.status.success(), "traced run exit: {:?}", out.status);

    let index = std::fs::read_to_string(cwd.join("runs/traces/demo/index.json"))
        .expect("read index.json");
    // The manifest is embedded with its identifying context for the chart header.
    assert!(index.contains("\"manifest\":{\"commit\":\""), "manifest missing: {index}");
    assert!(index.contains("\"window\":[1,7]"), "window missing from manifest: {index}");
    assert!(
        index.contains("\"broker\":\"sim-optimal(pip_size=0.0001)\""),
        "broker label missing: {index}"
    );
    // The tap list is the deterministic read order the serve path depends on.
    assert!(
        index.contains("\"taps\":[\"equity\",\"exposure\"]"),
        "tap order must be deterministic [equity, exposure]: {index}"
    );

    let _ = std::fs::remove_dir_all(&cwd);
}

/// Property: `--trace` is an **orthogonal modifier** — it composes with `aura run
/// --real <SYM>`, not only plain `run`, and is strictly **additive**: the looked-up
/// instrument pip still reaches stdout byte-for-byte while the same two taps land on
/// disk. The spec's headline is "one shared persist helper, every run form"; the
/// existing E2E only exercised the synthetic `run` path. Gated on local GER40 data
/// (skip cleanly when absent, the project convention) so it never fails on a
/// data-less machine; the no-data path is the distinct "no local data" refusal.
#[test]
fn run_real_with_trace_persists_taps_and_keeps_stdout_unchanged() {
    const FROM_MS: &str = "1725148800000";
    const TO_MS: &str = "1727740799999";
    let cwd = temp_cwd("run-real-trace");
    let out = Command::new(BIN)
        .args(["run", "--real", "GER40", "--from", FROM_MS, "--to", TO_MS, "--trace", "ger"])
        .current_dir(&cwd)
        .output()
        .expect("spawn aura run --real --trace");

    // Skip on a data-less machine: vetted GER40 with no local data takes the
    // distinct no-data path (exit 2), never the pip-refusal, and writes no traces.
    if out.status.code() == Some(2) {
        let stderr = String::from_utf8_lossy(&out.stderr);
        assert!(
            stderr.contains("no local data for symbol 'GER40'"),
            "exit 2 for vetted GER40 --trace must be the no-data path, got: {stderr}"
        );
        eprintln!("skip: no local GER40 data");
        let _ = std::fs::remove_dir_all(&cwd);
        return;
    }

    assert_eq!(out.status.code(), Some(0), "real --trace exit: {:?}", out.status);
    // Additive: the index-pip report still reaches stdout unchanged.
    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    let line = stdout.trim_end();
    assert!(line.starts_with("{\"manifest\":{"), "report still printed: {line}");
    assert!(
        line.contains("\"broker\":\"sim-optimal(pip_size=1)\""),
        "real --trace must keep the GER40 index pip on stdout: {line}"
    );
    // And the same two taps landed under the named run dir.
    assert!(cwd.join("runs/traces/ger/index.json").exists(), "index.json written");
    assert!(cwd.join("runs/traces/ger/equity.json").exists(), "equity tap written");
    assert!(cwd.join("runs/traces/ger/exposure.json").exists(), "exposure tap written");

    let _ = std::fs::remove_dir_all(&cwd);
}

/// Extract the body of a JSON array opened by `marker` (e.g. `"ts":[`) up to its
/// closing `]`, by substring — no serde dependency, mirroring the sibling tests'
/// substring parsing. Used only to count comma-separated entries for the SoA
/// length-parity check.
fn json_array_body<'a>(json: &'a str, marker: &str) -> &'a str {
    let start = json.find(marker).expect("array marker present") + marker.len();
    let rest = &json[start..];
    let end = rest.find(']').expect("array is closed");
    &rest[..end]
}

#[test]
fn no_args_prints_usage_and_exits_two() {
    let out = Command::new(BIN).output().expect("spawn aura");
    assert_eq!(out.status.code(), Some(2), "exit status: {:?}", out.status);
    assert!(out.stdout.is_empty(), "stdout should be empty on the usage path");
    let stderr = String::from_utf8(out.stderr).expect("utf-8 stderr");
    assert!(stderr.contains("usage"), "stderr was: {stderr:?}");
}

/// Property: `--help`/`-h` is the success-path help affordance, not the error
/// path. A newcomer's reflex first command (C22 first-contact ergonomics, #20)
/// prints the usage to stdout and exits 0; the conventional `-h` alias behaves
/// identically. An *unknown* subcommand keeps the error path (exit 2) so the
/// help fix does not regress bad-args handling.
#[test]
fn help_flag_prints_usage_to_stdout_and_exits_zero() {
    for flag in ["--help", "-h"] {
        let out = Command::new(BIN).arg(flag).output().expect("spawn aura --help");
        assert_eq!(out.status.code(), Some(0), "`aura {flag}` exit: {:?}", out.status);
        let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
        assert!(
            !stdout.trim().is_empty(),
            "`aura {flag}` should print help to stdout, got: {stdout:?}"
        );
        // The usage names the only subcommand a newcomer can run.
        assert!(
            stdout.contains("run"),
            "`aura {flag}` help should mention the `run` subcommand, got: {stdout:?}"
        );
    }

    // Negative-preservation: an unknown subcommand is still the error path.
    let out = Command::new(BIN).arg("frobnicate").output().expect("spawn aura frobnicate");
    assert_eq!(
        out.status.code(),
        Some(2),
        "unknown subcommand must stay exit 2: {:?}",
        out.status
    );
}

/// Property: `aura graph` emits a single self-contained HTML page — the
/// interactive pin-graph viewer with the deterministic model inlined and the
/// vendored Graphviz-WASM + pan-zoom inlined (no remote fetch). Driven through
/// the built binary so it pins the observable CLI contract. The DOT/SVG are
/// Graphviz-version-dependent and not asserted (the prototype is the by-hand
/// visual reference); this pins the page envelope + the retirement of the old
/// ascii-dag notation.
#[test]
fn graph_emits_self_contained_html_viewer() {
    let out = Command::new(BIN).arg("graph").output().expect("spawn aura graph");
    assert_eq!(out.status.code(), Some(0), "`aura graph` exit: {:?}", out.status);
    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    // a self-contained HTML document...
    assert!(
        stdout.trim_start().starts_with("<!doctype html>"),
        "not an HTML doc: {:?}",
        &stdout[..stdout.len().min(80)]
    );
    // ...with the deterministic model inlined as the viewer's data source...
    assert!(stdout.contains("window.AURA_MODEL = {\"root\":"), "model not inlined: {stdout:?}");
    // ...the Graphviz-WASM bootstrap present, and no remote asset fetch.
    assert!(stdout.contains("Viz.instance"), "viewer bootstrap missing");
    assert!(!stdout.contains("<script src"), "assets must be inlined, found remote <script src>");
    // the retired ascii-dag invented notation is gone.
    assert!(!stdout.contains("Sub(#Sf,#Ss)"), "retired ascii-dag notation must be gone: {stdout}");
}

#[test]
fn sweep_prints_four_family_json_lines_and_exits_zero() {
    let cwd = temp_cwd("sweep4");
    let out = Command::new(BIN).arg("sweep").current_dir(&cwd).output().expect("spawn aura sweep");
    assert!(out.status.success(), "exit status: {:?}", out.status);

    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    assert_eq!(stdout.lines().count(), 4, "stdout was: {stdout:?}");
    let first = stdout.lines().next().unwrap();
    // each line is now a family member: the assigned `family_id` plus the nested
    // RunReport (C18/C21 lineage). The first run assigns `sweep-0`; the nested
    // report is serialized via `serde_json`, so the manifest's fields lead with
    // `broker` (the commit value is the volatile git HEAD, pinned by params below).
    assert!(first.starts_with("{\"family_id\":\"sweep-0\",\"report\":{\"manifest\":{"), "got: {stdout}");
    assert!(
        first.contains("\"params\":[[\"signals.trend.fast.length\",{\"I64\":2}],[\"signals.trend.slow.length\",{\"I64\":4}],[\"signals.momentum.fast.length\",{\"I64\":2}],[\"signals.momentum.slow.length\",{\"I64\":4}],[\"signals.momentum.signal.length\",{\"I64\":3}],[\"signals.blend.weights[0]\",{\"F64\":1.0}],[\"signals.blend.weights[1]\",{\"F64\":1.0}],[\"exposure.scale\",{\"F64\":0.5}]]"),
        "got: {stdout}"
    );
    let _ = std::fs::remove_dir_all(&cwd);
}

#[test]
fn sweep_with_trailing_token_is_strict_and_exits_two() {
    // strict-arg reading (#16): an unexpected trailing token is a usage error.
    let out = Command::new(BIN).args(["sweep", "extra"]).output().expect("spawn aura");
    assert_eq!(out.status.code(), Some(2), "exit status: {:?}", out.status);
}

/// Property: `aura mc` runs the built-in Monte-Carlo family end-to-end through the
/// binary — it prints one member line per seed (carrying the assigned `family_id`)
/// plus one `mc_aggregate` line, exits 0, and persists the draws as a discoverable
/// `MonteCarlo` family (C12 axis 4 / C18/C21). Driven through the built binary so
/// it pins the observable CLI contract, not just the in-crate render helper.
#[test]
fn mc_runs_persists_a_monte_carlo_family_and_lists_it() {
    let cwd = temp_cwd("mc-family");
    let out = Command::new(BIN).arg("mc").current_dir(&cwd).output().expect("spawn aura mc");
    assert!(out.status.success(), "mc exit: {:?}", out.status);

    let stdout = String::from_utf8(out.stdout).expect("utf-8 stdout");
    let lines: Vec<&str> = stdout.lines().collect();
    // three built-in seeds -> three member lines + one aggregate line.
    assert_eq!(lines.len(), 4, "mc stdout: {stdout:?}");
    for line in &lines[..3] {
        assert!(line.contains("\"family_id\":\"mc-0\""), "member missing family_id: {line}");
        assert!(line.contains("\"seed\":"), "member missing seed: {line}");
    }
    assert!(lines[3].contains("\"mc_aggregate\":"), "missing aggregate line: {}", lines[3]);

    // the run persisted the draws as a discoverable MonteCarlo family.
    let fams = Command::new(BIN).args(["runs", "families"]).current_dir(&cwd).output().expect("spawn families");
    assert!(fams.status.success(), "families exit: {:?}", fams.status);
    let fams_out = String::from_utf8(fams.stdout).expect("utf-8");
    assert_eq!(fams_out.lines().count(), 1, "families: {fams_out:?}");
    assert!(fams_out.contains("\"family_id\":\"mc-0\""), "families: {fams_out:?}");
    assert!(fams_out.contains("\"kind\":\"MonteCarlo\""), "families: {fams_out:?}");
    assert!(fams_out.contains("\"members\":3"), "families: {fams_out:?}");

    let _ = std::fs::remove_dir_all(&cwd);
}

#[test]
fn runs_families_list_and_per_family_rank_across_invocations() {
    let cwd = temp_cwd("runs-flow");
    // two sweeps accumulate two families (sweep-0, sweep-1) over time, each a
    // related set of 4 records (C18/C21 lineage), in the sibling family store.
    for _ in 0..2 {
        let out = Command::new(BIN).arg("sweep").current_dir(&cwd).output().expect("spawn sweep");
        assert!(out.status.success(), "sweep exit: {:?}", out.status);
    }

    // `runs families` shows both stored families in first-seen order, each with
    // its kind + member count.
    let fams = Command::new(BIN).args(["runs", "families"]).current_dir(&cwd).output().expect("spawn families");
    assert!(fams.status.success(), "families exit: {:?}", fams.status);
    let fams_out = String::from_utf8(fams.stdout).expect("utf-8");
    let fam_lines: Vec<&str> = fams_out.lines().collect();
    assert_eq!(fam_lines.len(), 2, "families: {fams_out:?}");
    assert!(fam_lines[0].contains("\"family_id\":\"sweep-0\""), "fam0: {fams_out:?}");
    assert!(fam_lines[1].contains("\"family_id\":\"sweep-1\""), "fam1: {fams_out:?}");
    assert!(fam_lines.iter().all(|l| l.contains("\"members\":4")), "members: {fams_out:?}");

    // `runs family sweep-0 rank total_pips`: the family's 4 members, highest
    // total_pips first.
    let rank = Command::new(BIN)
        .args(["runs", "family", "sweep-0", "rank", "total_pips"])
        .current_dir(&cwd)
        .output()
        .expect("spawn rank");
    assert!(rank.status.success(), "rank exit: {:?}", rank.status);
    let rank_out = String::from_utf8(rank.stdout).expect("utf-8");
    assert_eq!(rank_out.lines().count(), 4, "rank: {rank_out:?}");
    assert!(rank_out.lines().all(|l| l.starts_with("{\"manifest\":{")), "rank shape: {rank_out:?}");
    let pips: Vec<f64> = rank_out
        .lines()
        .map(|l| {
            let key = "\"total_pips\":";
            let start = l.find(key).expect("line has total_pips") + key.len();
            let tail = &l[start..];
            let end = tail.find([',', '}']).expect("token end");
            tail[..end].parse().expect("total_pips is an f64")
        })
        .collect();
    assert!(pips.windows(2).all(|w| w[0] >= w[1]), "rank not descending: {pips:?}");

    // an unknown metric is a usage error
    let bogus = Command::new(BIN)
        .args(["runs", "family", "sweep-0", "rank", "bogus"])
        .current_dir(&cwd)
        .output()
        .expect("spawn bogus");
    assert_eq!(bogus.status.code(), Some(2), "bogus exit: {:?}", bogus.status);

    // an unknown family id is an empty family: zero lines, exit 0.
    let unknown = Command::new(BIN)
        .args(["runs", "family", "nope-9"])
        .current_dir(&cwd)
        .output()
        .expect("spawn unknown");
    assert!(unknown.status.success(), "unknown family exit: {:?}", unknown.status);
    assert_eq!(unknown.stdout.len(), 0, "unknown family stdout: {:?}", unknown.stdout);

    let _ = std::fs::remove_dir_all(&cwd);
}

#[test]
fn runs_list_and_rank_are_retired_and_exit_two() {
    // `aura runs list` / `runs rank <metric>` were retired (#73): families
    // (sweep/mc/walkforward, C21) subsume standalone over-time comparison. The
    // dropped subcommands now fall through to the strict-arg usage error (exit 2),
    // before any registry access.
    let list = Command::new(BIN).args(["runs", "list"]).output().expect("spawn list");
    assert_eq!(list.status.code(), Some(2), "retired `runs list` must exit 2: {:?}", list.status);
    let rank = Command::new(BIN).args(["runs", "rank", "total_pips"]).output().expect("spawn rank");
    assert_eq!(rank.status.code(), Some(2), "retired `runs rank` must exit 2: {:?}", rank.status);
}

#[test]
fn runs_bare_subcommand_is_strict_and_exits_two() {
    // `aura runs` with no/unknown sub-subcommand is a usage error (#16 strict).
    let out = Command::new(BIN).arg("runs").output().expect("spawn aura runs");
    assert_eq!(out.status.code(), Some(2), "exit status: {:?}", out.status);
}