boxmaker/crates/memoryd/tests/honcho_worker_more.rs

//! The Honcho worker's other duties (M5c spec, section 5): with nothing to send it decides what
//! `brokerd` could not answer for; after a restart nothing is sent again, and a session with a
//! decided turn waits again (a session without one does not); a running turn is never decided;
//! a retraction waits (nothing decides one); a ledger that cannot be written stops it; no log
//! line holds a turn's text. Then `memoryd` itself: a reported turn reaches Honcho, woken at
//! once, and a key that cannot be read stops the start. Do not edit.

#[path = "support/brokerd.rs"]
mod brokerd;
#[path = "support/honcho.rs"]
mod honcho;
#[path = "support/logs.rs"]
mod logs;
#[path = "support/tmp.rs"]
mod tmp;
#[path = "support/turns.rs"]
mod turns;
#[path = "support/worker.rs"]
mod worker;

use std::process::{Command, Stdio};
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};

use brokerd::{Answer, FakeBrokerd};
use bxcore::{Envelope, Message, SessionId, SessionUpdated, read_frame, write_frame};
use honcho::{FakeHoncho, Mode};
use logs::assistant;
use memoryd::config::Config;
use memoryd::honcho::ledger::{Item, Record};
use memoryd::honcho::worker::{Step, Tuning};
use memoryd::serve::{self, StartError};
use tmp::TempDir;
use turns::{clean, running, sid, spoken};
use worker::{FAST, Home};

fn turn(text: &str, speaker: &str, reply: &str) -> Vec<bxcore::LogRecord> {
    vec![spoken(text, Some(speaker)), assistant(2, Some(reply), &[])]
}

fn messages(fake: &FakeHoncho) -> usize {
    fake.requests()
        .iter()
        .filter(|r| r.path.ends_with("/messages"))
        .count()
}

fn is_sent(records: &[Record], session: &str, turn: u64) -> bool {
    let item = Item::Turn {
        session: sid(session),
        turn,
    };
    records
        .iter()
        .any(|r| matches!(r, Record::Sent { item: i, .. } if *i == item))
}

fn decided(records: &[Record], session: &str, turn: u64) -> bool {
    let item = Item::Turn {
        session: sid(session),
        turn,
    };
    records
        .iter()
        .any(|r| matches!(r, Record::Decided { item: i, .. } if *i == item))
}

#[test]
fn the_default_waits() {
    assert_eq!(
        Tuning::DEFAULT,
        Tuning {
            backoff: Duration::from_secs(5),
            backoff_max: Duration::from_secs(600),
            idle: Duration::from_secs(30),
        }
    );
}

#[test]
fn with_nothing_to_send_undecided_turns_are_decided() {
    let fake = FakeHoncho::start();
    let home = Home::new("worker-retry");
    home.log("mm-a", &[turn("a", "kyle", "a")]);
    *home.answer.lock().unwrap() = Err("brokerd is down".to_string());
    home.report("mm-a", 1);
    assert!(!decided(&home.records(), "mm-a", 1));
    let mut w = home.worker(&fake, FAST);
    assert_eq!(w.step(), Step::Idle, "brokerd still down");
    *home.answer.lock().unwrap() = Ok(clean());
    assert_eq!(w.step(), Step::Done, "decided now");
    assert!(decided(&home.records(), "mm-a", 1));
    assert_eq!(w.step(), Step::Done, "sent");
    assert!(is_sent(&home.records(), "mm-a", 1));
}

#[test]
fn an_outage_that_ends_is_followed_by_the_retry() {
    let fake = FakeHoncho::start();
    let home = Home::new("worker-after-outage");
    home.log("mm-a", &[turn("a", "kyle", "a")]);
    home.log("mm-b", &[turn("b", "kyle", "b")]);
    home.report("mm-a", 1);
    *home.answer.lock().unwrap() = Err("brokerd is down".to_string());
    home.report("mm-b", 1);
    let mut w = home.worker(&fake, FAST);
    fake.set(Mode::Status(502));
    assert!(matches!(w.step(), Step::Backoff(_)));
    *home.answer.lock().unwrap() = Ok(clean());
    fake.set(Mode::Fixtures);
    assert_eq!(w.step(), Step::Done);
    // mm-a is sent, and the outage's end decided mm-b before any idle step.
    assert!(decided(&home.records(), "mm-b", 1));
}

#[test]
fn a_restart_sends_nothing_again_and_resumes_the_sessions_it_knows() {
    let fake = FakeHoncho::start();
    let mut home = Home::new("worker-restart");
    home.log("mm-a", &[turn("a", "kyle", "a")]);
    home.report("mm-a", 1);
    home.worker(&fake, FAST).step();
    assert_eq!(messages(&fake), 1);
    // While memoryd is down: mm-a has a second turn, never reported; mm-z, never seen, one.
    home.log("mm-a", &[turn("a", "kyle", "a"), turn("b", "kyle", "b")]);
    home.log("mm-z", &[turn("z", "kyle", "z")]);
    home.restart();
    let mut w = home.worker(&fake, FAST);
    assert_eq!(w.step(), Step::Done, "mm-a's second turn decided");
    assert_eq!(w.step(), Step::Done, "and sent");
    assert_eq!(w.step(), Step::Idle);
    let records = home.records();
    assert!(is_sent(&records, "mm-a", 2));
    assert!(!decided(&records, "mm-z", 1), "a session never reported");
    assert_eq!(messages(&fake), 2, "turn 1 was sent again");
}

#[test]
fn a_restart_never_decides_a_running_turn() {
    let fake = FakeHoncho::start();
    let mut home = Home::new("worker-running");
    home.log("mm-a", &[turn("a", "kyle", "a")]);
    home.report("mm-a", 1);
    home.worker(&fake, FAST).step();
    home.log("mm-a", &[turn("a", "kyle", "a"), running(Some("kyle"))]);
    home.restart();
    let mut w = home.worker(&fake, FAST);
    assert_eq!(w.step(), Step::Idle);
    assert!(!decided(&home.records(), "mm-a", 2));
}

#[test]
fn a_retraction_waits() {
    // Nothing decides a retraction any more (M5c spec, section 4, 2026-09-28): one in the
    // ledger is neither sent nor failed.
    let fake = FakeHoncho::start();
    let mut home = Home::new("worker-later");
    let retract = r#"{"type":"decided","time":"2026-09-28T10:00:00.000Z","item":{"type":"edit","id":"2026-09-28-0001","part":0},"action":{"type":"retract","session":"mm-a","text":"a note"}}"#;
    std::fs::write(home.ledger_path(), format!("{retract}\n")).unwrap();
    home.restart();
    let mut w = home.worker(&fake, FAST);
    assert_eq!(w.step(), Step::Idle);
    assert_eq!(home.records().len(), 1, "the retraction was failed or sent");
    assert!(fake.requests().is_empty());
}

#[test]
fn a_ledger_that_cannot_be_written_stops_the_worker() {
    let fake = FakeHoncho::start();
    let home = Home::new("worker-ledger");
    home.log("mm-a", &[turn("a", "kyle", "a")]);
    home.report("mm-a", 1);
    let mut w = home.worker(&fake, FAST);
    let ledger = home.ledger_path();
    let kept = std::fs::read_to_string(&ledger).unwrap();
    std::fs::remove_file(&ledger).unwrap();
    std::fs::create_dir(&ledger).unwrap();
    assert_eq!(w.step(), Step::Stopped);
    assert_eq!(w.step(), Step::Stopped);
    assert_eq!(
        messages(&fake),
        1,
        "sent once; its sent line could not be written"
    );
    let lines = home.lines();
    assert_eq!(lines.len(), 1, "{lines:?}");
    assert!(lines[0].ends_with(
        "; the Honcho worker stops until memoryd restarts; see docs/runbook.md#honcho-ledger-damaged"
    ));
    std::fs::remove_dir(&ledger).unwrap();
    std::fs::write(&ledger, kept).unwrap();
}

#[test]
fn no_log_line_holds_a_turns_text() {
    let fake = FakeHoncho::start();
    let home = Home::new("worker-quiet");
    for (session, status) in [("mm-a", 503), ("mm-b", 422), ("mm-c", 401)] {
        home.log(
            session,
            &[turn("private-question", "kyle", "private-answer")],
        );
        home.report(session, 1);
        let mut w = home.worker(&fake, FAST);
        fake.set(Mode::Status(status));
        w.step();
    }
    let lines = home.lines();
    assert_eq!(lines.len(), 3, "{lines:?}");
    for line in lines {
        assert!(!line.contains("private"), "{line}");
    }
}

/// `memoryd serve`'s config for `home`, with `[honcho]` at `url`.
fn serve_config(home: &TempDir, url: &str, extra: &str) -> String {
    let soul = home.write("etc/soul.md", "You are Boxmaker.\n");
    format!(
        "[paths]\nhome = \"{}\"\n[memory]\nsoul_starter = \"{}\"\n[honcho]\nurl = \"{url}\"\nagent = \"boxmaker0\"\nowner = \"kyle\"\ntrusted = \"boxmaker0-trusted\"\nuntrusted = \"boxmaker0-untrusted\"\nfleet = \"fleet\"\n{extra}",
        home.path().display(),
        soul.display()
    )
}

#[test]
fn memoryd_sends_a_reported_turn_at_once() {
    let fake = FakeHoncho::start();
    let dir = TempDir::new("worker-serve");
    turns::write_turns(dir.path(), "mm-a", &[turn("a", "kyle", "a")]);
    let config = Config::parse(&serve_config(&dir, &fake.url, "")).unwrap();
    let _brokerd = FakeBrokerd::start(&config.state_socket(), Answer::State(clean()));
    let lines = Arc::new(Mutex::new(Vec::new()));
    let sink = Arc::clone(&lines);
    let log: serve::Log = Arc::new(move |l: &str| sink.lock().unwrap().push(l.to_string()));
    let running = serve::start(config.clone(), log).unwrap();
    std::thread::spawn(move || running.run());
    // The worker has slept since start (30 s when idle): the report wakes it.
    std::thread::sleep(Duration::from_millis(100));
    let mut stream = std::os::unix::net::UnixStream::connect(config.loop_socket()).unwrap();
    stream
        .set_read_timeout(Some(Duration::from_secs(10)))
        .unwrap();
    let report = Envelope {
        v: 1,
        id: 1,
        r#final: true,
        msg: Message::SessionUpdated(SessionUpdated {
            session: SessionId::new("mm-a").unwrap(),
            turn: 1,
        }),
    };
    write_frame(&mut stream, &report).unwrap();
    assert!(matches!(
        read_frame(&mut stream).unwrap().msg,
        Message::Ok(_)
    ));
    let deadline = Instant::now() + Duration::from_secs(10);
    while Instant::now() < deadline && messages(&fake) == 0 {
        std::thread::sleep(Duration::from_millis(10));
    }
    assert_eq!(messages(&fake), 1, "{:?}", lines.lock().unwrap());
}

#[test]
fn a_key_that_cannot_be_read_stops_the_start() {
    let fake = FakeHoncho::start();
    let dir = TempDir::new("worker-key-start");
    let text = serve_config(
        &dir,
        &fake.url,
        "[secrets.honcho_trusted]\nenv = \"MEMORYD_TEST_UNSET_KEY\"\n",
    );
    let config = Config::parse(&text).unwrap();
    let log: serve::Log = Arc::new(|_: &str| {});
    let err = match serve::start(config.clone(), log) {
        Err(err) => err,
        Ok(_) => panic!("memoryd started"),
    };
    assert!(matches!(err, StartError::Secret(_)), "{err:?}");
    assert!(!config.loop_socket().exists(), "a socket was bound");
    // The process: exit 1 with the secret's own lines and pointer, not the start pointer.
    let path = dir.write("memoryd.toml", &text);
    let mut child = Daemon(
        Command::new(env!("CARGO_BIN_EXE_memoryd"))
            .args(["serve", "--config"])
            .arg(&path)
            .env_remove("MEMORYD_TEST_UNSET_KEY")
            .stdin(Stdio::null())
            .stdout(Stdio::null())
            .stderr(Stdio::piped())
            .spawn()
            .unwrap(),
    );
    let deadline = Instant::now() + Duration::from_secs(10);
    let mut code = None;
    while Instant::now() < deadline {
        if let Ok(Some(status)) = child.0.try_wait() {
            code = status.code();
            break;
        }
        std::thread::sleep(Duration::from_millis(20));
    }
    let _ = child.0.kill();
    let _ = child.0.wait();
    let mut stderr = String::new();
    if let Some(mut pipe) = child.0.stderr.take() {
        let _ = std::io::Read::read_to_string(&mut pipe, &mut stderr);
    }
    assert_eq!(code, Some(1), "{stderr}");
    assert!(
        stderr.starts_with("memoryd: secret honcho_trusted: "),
        "{stderr}"
    );
    assert!(
        stderr.ends_with("\nsee docs/runbook.md#secret-unavailable\n"),
        "{stderr}"
    );
    assert!(!stderr.contains("memoryd-start-failed"), "{stderr}");
}

/// A `memoryd` process, killed and waited for when dropped.
struct Daemon(std::process::Child);

impl Drop for Daemon {
    fn drop(&mut self) {
        let _ = self.0.kill();
        let _ = self.0.wait();
    }
}