agent-joule/crates/joule_coded/tests/headless_run.rs

//! The headless keystone, deterministically: drive the worker's real `run_loop`
//! (which writes edits to disk through the same `FsDocument` path the daemon uses)
//! and `record_trace` (which seals each edit into a signed session ledger), with a
//! scripted on-device model standing in for JouleClaw's GGUF runtime. Proves a
//! real coding op closes headlessly and produces an intact, signed receipt — no
//! GUI, no window, no model download.

use ed25519_dalek::SigningKey;
use joule_coded::{record_trace, run_loop, run_loop_metered, seed_from};
use joule_core::journal::EnergyReader;
use joule_core::sessions::{SessionGrant, SessionManager};
use std::cell::Cell;
use std::rc::Rc;

#[test]
fn headless_run_edits_a_file_and_seals_a_signed_op() {
    // A scratch checkout with one file the agent will rewrite. The primary session
    // makes it accountable without needing a git worktree.
    let root = std::env::temp_dir().join(format!("jc-headless-{}", std::process::id()));
    let src = root.join("src");
    std::fs::create_dir_all(&src).unwrap();
    std::fs::write(src.join("lib.rs"), "fn answer() -> i32 { 0 }\n").unwrap();

    let key = SigningKey::from_bytes(&seed_from(&root.to_string_lossy()));
    let author = key.verifying_key().to_bytes();
    let grant = SessionGrant {
        tiers: vec!["l0".into(), "l1".into(), "l2".into(), "l3".into()],
        joule_ceiling_uj: 1_000_000_000,
    };
    let mut sessions = SessionManager::with_primary(
        root.clone(),
        key,
        root.join(".joule").join("worktrees"),
        grant,
        "test-worker",
    );

    // The scripted "model": edit the file, then finish. Exactly the wire the
    // on-device runtime would emit, so this exercises the real loop + tool parsing.
    let turns = [
        "<<<TOOL edit_file>>>\nsrc/lib.rs\nfn answer() -> i32 { 42 }\n<<<END>>>",
        "<<<TOOL finish>>>\n",
    ];
    let mut step = 0usize;
    let trace = run_loop(&root, "make answer return 42", 8, |_prompt| {
        let turn = turns[step.min(turns.len() - 1)];
        step += 1;
        Ok(turn.to_string())
    });

    // The loop applied exactly one edit, and it is already on disk (the daemon's
    // apply_edit wrote it through FsDocument).
    assert_eq!(trace.applied.len(), 1, "expected one applied edit");
    assert_eq!(trace.applied[0].0, "src/lib.rs");
    let on_disk = std::fs::read_to_string(src.join("lib.rs")).unwrap();
    assert!(on_disk.contains("{ 42 }"), "edit not on disk: {on_disk:?}");

    // Recording seals the edit as a content-addressed op into the primary
    // session's signed chain — the headless receipt.
    let before = sessions
        .primary()
        .unwrap()
        .events()
        .iter()
        .filter(|e| e.kind == "op")
        .count();
    let recorded = record_trace(&mut sessions, None, author, "make answer return 42", 12_345, &trace);
    assert_eq!(recorded, 1, "expected one op recorded");

    let primary = sessions.primary().unwrap();
    let ops_after = primary.events().iter().filter(|e| e.kind == "op").count();
    assert_eq!(ops_after, before + 1, "ledger did not grow by one op");
    assert!(primary.verify_chain(), "the signed ledger chain must verify");
    assert_eq!(primary.energy_uj(), 12_345, "op energy folded into the session");

    std::fs::remove_dir_all(&root).ok();
}

#[test]
fn metered_run_records_per_step_energy() {
    let root = std::env::temp_dir().join(format!("jc-metered-{}", std::process::id()));
    let src = root.join("src");
    std::fs::create_dir_all(&src).unwrap();
    std::fs::write(src.join("lib.rs"), "fn answer() -> i32 { 0 }\n").unwrap();

    // A fake host counter that advances 1000 µJ per read. `measure` reads it twice
    // per step (before + after), so each recorded step's energy is exactly 1000 µJ —
    // a deterministic stand-in for a real RAPL/IOReport counter.
    let reader: EnergyReader = Rc::new({
        let cumulative = Cell::new(0u64);
        move || {
            let value = cumulative.get();
            cumulative.set(value + 1000);
            (value, "hw_shunt")
        }
    });

    // Scripted model: edit the file, then finish. Each turn is one `generate` step;
    // the edit is one `edit` step — all metered independently.
    let turns = [
        "<<<TOOL edit_file>>>\nsrc/lib.rs\nfn answer() -> i32 { 42 }\n<<<END>>>",
        "<<<TOOL finish>>>\n",
    ];
    let mut step = 0usize;
    let (trace, journal) = run_loop_metered(&root, "make answer return 42", 8, reader, |_prompt| {
        let turn = turns[step.min(turns.len() - 1)];
        step += 1;
        Ok(turn.to_string())
    });

    assert_eq!(trace.applied.len(), 1, "one edit applied");
    assert!(!journal.is_empty(), "journal recorded steps");

    // Every step carries its own measured energy + provenance — not one lump.
    for record in &journal.steps {
        assert_eq!(record.energy_uj, 1000, "{} step energy", record.kind);
        assert_eq!(record.provenance, "hw_shunt");
        assert!(record.ok, "{} step should succeed", record.kind);
    }
    let kinds: Vec<&str> = journal.steps.iter().map(|record| record.kind.as_str()).collect();
    assert!(kinds.contains(&"generate"), "a generate step was metered: {kinds:?}");
    assert!(kinds.contains(&"edit"), "the edit step was metered: {kinds:?}");

    // The summary sums the per-step energy and splits it by kind.
    let summary = journal.summary();
    assert_eq!(summary.total_energy_uj, journal.steps.len() as u64 * 1000);
    assert_eq!(summary.errors, 0);
    assert!(summary.energy_by_kind.get("edit").copied().unwrap_or(0) >= 1000);

    std::fs::remove_dir_all(&root).ok();
}