hyperhive/hive-c0re/src/lifecycle/tests.rs

//! Unit tests for the lifecycle module (moved verbatim from the old
//! single-file `lifecycle.rs` `#[cfg(test)]` block).

use super::*;

/// Regression test: `setup_proposed` must seed both agent.nix and flake.nix
/// in the initial commit. Before commit 5b5a93e flake.nix was missing from
/// the scaffold, requiring manual creation (seen with the damocles agent).
///
/// Exercises the template arm: there is no forge to clone from in a test
/// (`forge::is_present` needs the priv socket), so `setup_proposed` falls
/// through to `seed_template` — which is the arm this asserts about.
#[tokio::test]
async fn setup_proposed_seeds_flake_nix() {
    let dir = tempfile::tempdir().expect("tempdir");
    let proposed = dir.path().join("proposed");
    setup_proposed(&proposed, "test-agent")
        .await
        .expect("setup_proposed");

    // Both files must exist on disk.
    assert!(proposed.join("agent.nix").exists(), "agent.nix missing");
    assert!(proposed.join("flake.nix").exists(), "flake.nix missing");

    // flake.nix must export nixosModules.default (the meta-flake contract).
    let flake = std::fs::read_to_string(proposed.join("flake.nix")).unwrap();
    assert!(
        flake.contains("nixosModules.default"),
        "flake.nix does not export nixosModules.default"
    );

    // Both files must be tracked in the initial git commit.
    let out = git_command()
        .current_dir(&proposed)
        .args(["show", "--name-only", "--format=", "HEAD"])
        .output()
        .await
        .expect("git show");
    let tracked = String::from_utf8_lossy(&out.stdout);
    assert!(tracked.contains("agent.nix"), "agent.nix not committed");
    assert!(tracked.contains("flake.nix"), "flake.nix not committed");
}

#[test]
fn bridge_gateway_ip_extracts_verbatim_address() {
    // HIVE_NETWORK_SUBNET carries the bridge IP verbatim, not the
    // canonical network — the gateway is the address before the `/`.
    assert_eq!(
        bridge_gateway_ip("10.42.0.1/24").as_deref(),
        Some("10.42.0.1")
    );
    // Non-`.1` operator override: the gateway is wherever the bridge is.
    assert_eq!(
        bridge_gateway_ip("10.42.0.254/24").as_deref(),
        Some("10.42.0.254")
    );
    assert_eq!(
        bridge_gateway_ip("172.30.0.1/16").as_deref(),
        Some("172.30.0.1")
    );
}

#[test]
fn bridge_gateway_ip_rejects_bad_input() {
    assert!(bridge_gateway_ip("notanip/24").is_none());
    assert!(bridge_gateway_ip("10.42.0.1").is_none()); // no prefix
    assert!(bridge_gateway_ip("10.42.0.1/33").is_none()); // prefix > 32
    assert!(bridge_gateway_ip("10.42.0.999/24").is_none()); // octet > 255
    assert!(bridge_gateway_ip("10.42.0/24").is_none()); // 3 octets
}

/// The presence control for the two rejection tests below: with both
/// variables set and well-formed, the settings are built. Without this,
/// a `network_isolation_from_vars` that rejected *everything* would pass
/// every absence assertion and look like a working guard.
#[test]
fn network_isolation_accepts_a_well_formed_pair() {
    let iso = network_isolation_from_vars(Some("hive0"), Some("10.42.0.1/24"))
        .expect("well-formed bridge + subnet must be accepted");
    assert_eq!(iso.bridge, "hive0");
    // The gateway is the verbatim bridge address, prefix stripped.
    assert_eq!(iso.gateway_ip, "10.42.0.1");
}

/// A missing or empty variable is fatal, not a fallback to the host
/// netns. Empty is tested alongside unset because `std::env::var` on a
/// variable set to `""` returns `Ok("")`, so treating only `None` as
/// missing would let an empty value through.
#[test]
fn network_isolation_rejects_missing_or_empty_vars() {
    assert!(network_isolation_from_vars(None, Some("10.42.0.1/24")).is_err());
    assert!(network_isolation_from_vars(Some("hive0"), None).is_err());
    assert!(network_isolation_from_vars(None, None).is_err());
    assert!(network_isolation_from_vars(Some(""), Some("10.42.0.1/24")).is_err());
    assert!(network_isolation_from_vars(Some("hive0"), Some("")).is_err());
}

/// A malformed subnet is fatal too. Previously this logged a warning and
/// silently produced a container on the host netns — a dropped security
/// boundary with nothing in the journal saying so.
#[test]
fn network_isolation_rejects_a_malformed_subnet() {
    assert!(network_isolation_from_vars(Some("hive0"), Some("notanip/24")).is_err());
    assert!(network_isolation_from_vars(Some("hive0"), Some("10.42.0.1")).is_err());
    assert!(network_isolation_from_vars(Some("hive0"), Some("10.42.0.1/33")).is_err());
    assert!(network_isolation_from_vars(Some("hive0"), Some("10.42.0.999/24")).is_err());
}

/// The error has to name the variable an operator must fix — these are
/// read at startup, so the message is the whole diagnostic.
#[test]
fn network_isolation_errors_name_the_offending_variable() {
    let e = network_isolation_from_vars(None, Some("10.42.0.1/24")).unwrap_err();
    assert!(
        format!("{e:#}").contains("HIVE_NETWORK_BRIDGE"),
        "bridge error must name the variable, got: {e:#}"
    );
    let e = network_isolation_from_vars(Some("hive0"), None).unwrap_err();
    assert!(
        format!("{e:#}").contains("HIVE_NETWORK_SUBNET"),
        "subnet error must name the variable, got: {e:#}"
    );
    let e = network_isolation_from_vars(Some("hive0"), Some("nope/24")).unwrap_err();
    let msg = format!("{e:#}");
    assert!(
        msg.contains("HIVE_NETWORK_SUBNET") && msg.contains("nope/24"),
        "malformed-subnet error must name the variable and the bad value, got: {msg}"
    );
}

/// `setup_proposed` is idempotent: calling it on an existing repo is a
/// no-op (the fresh guard skips all writes).
#[tokio::test]
async fn setup_proposed_idempotent() {
    let dir = tempfile::tempdir().expect("tempdir");
    let proposed = dir.path().join("proposed");
    setup_proposed(&proposed, "test-agent")
        .await
        .expect("first call");
    // Second call must not error even though .git already exists.
    setup_proposed(&proposed, "test-agent")
        .await
        .expect("second call");
    // Still one commit.
    let out = git_command()
        .current_dir(&proposed)
        .args(["rev-list", "--count", "HEAD"])
        .output()
        .await
        .expect("git rev-list");
    let count = String::from_utf8_lossy(&out.stdout).trim().to_owned();
    assert_eq!(
        count, "1",
        "expected exactly one commit after idempotent call"
    );
}

/// Build a two-commit repo and return `(dir, repo_path, first, second)`.
async fn two_commit_repo() -> (tempfile::TempDir, std::path::PathBuf, String, String) {
    let dir = tempfile::tempdir().expect("tempdir");
    let repo = dir.path().join("proposed");
    setup_proposed(&repo, "test-agent")
        .await
        .expect("setup_proposed");
    let first = git_rev_parse(&repo, "HEAD").await.expect("rev-parse first");

    std::fs::write(repo.join("second.txt"), "second").expect("write second.txt");
    git(&repo, &["add", "second.txt"]).await.expect("git add");
    git(
        &repo,
        &[
            "-c",
            "user.name=test",
            "-c",
            "user.email=test@example.com",
            "commit",
            "-m",
            "second",
        ],
    )
    .await
    .expect("git commit");
    let second = git_rev_parse(&repo, "HEAD")
        .await
        .expect("rev-parse second");

    assert_ne!(first, second, "second commit did not advance HEAD");
    (dir, repo, first, second)
}

/// `git_is_ancestor` answers reachability in both directions. This is the
/// check that decides whether moving a branch is a real fast-forward or a
/// rewind that discards commits.
#[tokio::test]
async fn is_ancestor_distinguishes_direction() {
    let (_dir, repo, first, second) = two_commit_repo().await;

    assert!(
        git_is_ancestor(&repo, &first, &second)
            .await
            .expect("ancestor check forward"),
        "first must be an ancestor of second"
    );
    assert!(
        !git_is_ancestor(&repo, &second, &first)
            .await
            .expect("ancestor check reverse"),
        "second must NOT be an ancestor of first"
    );
}

/// Regression test for the deploy path that ate a committed agent config:
/// `git_update_ref_cas` must refuse to move a ref whose current value is not
/// the expected one, and must leave the ref untouched when it refuses. A bare
/// `update-ref` accepts that move and silently drops everything in between.
#[tokio::test]
async fn update_ref_cas_refuses_stale_expectation() {
    let (_dir, repo, first, second) = two_commit_repo().await;

    // Park a ref at `first`, then CAS it forward with the correct old value.
    git_update_ref(&repo, "refs/heads/cas", &first)
        .await
        .expect("plant ref");
    git_update_ref_cas(&repo, "refs/heads/cas", &second, &first)
        .await
        .expect("CAS with the correct old value must succeed");
    assert_eq!(
        git_rev_parse(&repo, "refs/heads/cas").await.unwrap(),
        second
    );

    // Now retry with the SAME (now stale) expectation, as a racing deploy
    // holding a pre-merge sha would: it must fail rather than rewind.
    assert!(
        git_update_ref_cas(&repo, "refs/heads/cas", &first, &first)
            .await
            .is_err(),
        "CAS accepted a stale old value"
    );
    assert_eq!(
        git_rev_parse(&repo, "refs/heads/cas").await.unwrap(),
        second,
        "ref moved even though the CAS failed"
    );
}

/// `systemctl is-active` prints the state with a trailing newline, which is
/// the whole reason this parser trims rather than comparing raw.
#[test]
fn unit_state_reads_what_is_active_prints() {
    assert_eq!(UnitState::from_is_active("active\n"), UnitState::Active);
    assert_eq!(UnitState::from_is_active("failed\n"), UnitState::Failed);
    assert_eq!(UnitState::from_is_active("inactive\n"), UnitState::Other);
    // No trailing newline, in case the capture ever changes shape.
    assert_eq!(UnitState::from_is_active("failed"), UnitState::Failed);
}

/// The asymmetry that matters: an unrecognised state must fall to `Other`,
/// never to `Failed`.
///
/// `Failed` is what the dashboard will render as *this agent gave up*, so a
/// wrong `Failed` invents an incident, while a wrong `Other` merely fails to
/// distinguish one from a deliberate stop — the behaviour we have today.
/// Guessing in the safe direction is the property, not an implementation
/// detail of the `match`.
#[test]
fn an_unknown_state_is_never_reported_as_failed() {
    for s in [
        "activating",
        "deactivating",
        "reloading",
        "maintenance",
        "unknown",
        "",
        "Failed",  // capitalised: systemd prints lowercase, so this is not a state
        "failed*", // `is-active` never emits this; a substring match would take it
    ] {
        assert_eq!(
            UnitState::from_is_active(s),
            UnitState::Other,
            "{s:?} must not be read as a give-up"
        );
    }
}