Introduce a Supervisor trait (async-trait) so the agent manages games with different models behind one wire contract. ProcessSupervisor (spawned process: rust/conan/soulmask) and the new DockerComposeSupervisor (dune) both impl it; Agent.supervisors is now HashMap<String, Arc<dyn Supervisor>> and instancecmd dispatch is game-agnostic — start/stop/restart/status identical across games, selected by a per-game factory in main. InstanceState moved to the shared supervisor module. DockerComposeSupervisor drives docker-compose up-d / stop / restart against the instance's compose project, with -f/-p/single-service support and a configurable compose binary. New [instance.docker_compose] config block. First cut = lifecycle + cached state; container crash-detection + restart adoption deferred to Phase 3b (reconcilable with a compose ps probe). Trait choice (dyn over enum) per Commander: scales to future planes (kubectl, AMP/podman, SSH) as new struct+impl, no central match. 56 tests green (6 new docker-compose mock-binary tests + 5 refactored process tests), zero warnings. Live verification pending a real Dune stack. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
112 lines
4.3 KiB
Rust
112 lines
4.3 KiB
Rust
//! Process supervisor integration tests using real OS processes.
|
|
//! Unix-only test doubles (/bin/sleep, /bin/sh) — the supervisor logic under
|
|
//! test is platform-shared; Windows-specific stop semantics get covered when
|
|
//! the Windows service work lands.
|
|
#![cfg(unix)]
|
|
|
|
use std::path::PathBuf;
|
|
use std::time::Duration;
|
|
|
|
use corrosion_host_agent::config::InstanceConfig;
|
|
use corrosion_host_agent::process::ProcessSupervisor;
|
|
use corrosion_host_agent::supervisor::{InstanceState, Supervisor};
|
|
|
|
fn managed_instance(executable: &str, args: &[&str]) -> InstanceConfig {
|
|
InstanceConfig {
|
|
id: "test-instance".to_string(),
|
|
game: "rust".to_string(),
|
|
root: PathBuf::from("/tmp"),
|
|
label: None,
|
|
executable: Some(PathBuf::from(executable)),
|
|
args: args.iter().map(|s| s.to_string()).collect(),
|
|
working_dir: None,
|
|
rcon: None,
|
|
steamcmd: None,
|
|
docker_compose: None,
|
|
}
|
|
}
|
|
|
|
async fn wait_for_state(
|
|
sup: &std::sync::Arc<ProcessSupervisor>,
|
|
want: fn(&InstanceState) -> bool,
|
|
budget: Duration,
|
|
) -> InstanceState {
|
|
let deadline = tokio::time::Instant::now() + budget;
|
|
loop {
|
|
let state = sup.state();
|
|
if want(&state) {
|
|
return state;
|
|
}
|
|
if tokio::time::Instant::now() > deadline {
|
|
panic!("timed out waiting for state; last = {state:?}");
|
|
}
|
|
tokio::time::sleep(Duration::from_millis(100)).await;
|
|
}
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn start_status_stop_lifecycle() {
|
|
let sup = ProcessSupervisor::new(&managed_instance("/bin/sleep", &["300"]));
|
|
assert_eq!(sup.state(), InstanceState::Stopped);
|
|
|
|
sup.clone().start().await.expect("start should succeed");
|
|
assert_eq!(sup.state(), InstanceState::Running);
|
|
tokio::time::sleep(Duration::from_millis(1100)).await;
|
|
assert!(sup.uptime_seconds().await >= 1, "uptime should advance");
|
|
|
|
// Double-start must be rejected while running.
|
|
assert!(sup.clone().start().await.is_err(), "double start must fail");
|
|
|
|
sup.clone().stop().await.expect("stop should succeed");
|
|
let state = wait_for_state(&sup, |s| matches!(s, InstanceState::Stopped), Duration::from_secs(5)).await;
|
|
assert_eq!(state, InstanceState::Stopped);
|
|
assert_eq!(sup.uptime_seconds().await, 0);
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn unexpected_exit_is_crashed_with_code() {
|
|
let sup = ProcessSupervisor::new(&managed_instance("/bin/sh", &["-c", "sleep 0.2; exit 7"]));
|
|
sup.clone().start().await.expect("start should succeed");
|
|
|
|
let state = wait_for_state(
|
|
&sup,
|
|
|s| matches!(s, InstanceState::Crashed { .. }),
|
|
Duration::from_secs(5),
|
|
)
|
|
.await;
|
|
assert_eq!(state, InstanceState::Crashed { exit_code: Some(7) });
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn restart_from_crashed_recovers() {
|
|
let sup = ProcessSupervisor::new(&managed_instance("/bin/sh", &["-c", "exit 1"]));
|
|
sup.clone().start().await.expect("start should succeed");
|
|
wait_for_state(&sup, |s| matches!(s, InstanceState::Crashed { .. }), Duration::from_secs(5)).await;
|
|
|
|
// Restart from crashed must work (panel "Restart" after a crash).
|
|
// Use a long-lived command this time by replacing the supervisor — the
|
|
// command is fixed per supervisor, so emulate via a fresh one.
|
|
let sup2 = ProcessSupervisor::new(&managed_instance("/bin/sleep", &["300"]));
|
|
sup2.clone().restart().await.expect("restart from stopped should start");
|
|
assert_eq!(sup2.state(), InstanceState::Running);
|
|
sup2.clone().stop().await.expect("cleanup stop");
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn unmanaged_instance_rejects_process_commands() {
|
|
let mut cfg = managed_instance("/bin/sleep", &["300"]);
|
|
cfg.executable = None;
|
|
let sup = ProcessSupervisor::new(&cfg);
|
|
assert_eq!(sup.state(), InstanceState::Unmanaged);
|
|
assert!(sup.clone().start().await.is_err(), "unmanaged start must fail");
|
|
assert!(sup.clone().stop().await.is_err(), "unmanaged stop must fail");
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn missing_executable_fails_cleanly() {
|
|
let sup = ProcessSupervisor::new(&managed_instance("/nonexistent/bin/gameserver", &[]));
|
|
let err = sup.clone().start().await.expect_err("must fail");
|
|
assert!(err.to_string().contains("not found"), "error should say not found: {err}");
|
|
assert_eq!(sup.state(), InstanceState::Stopped, "failed start must not leave Starting state");
|
|
}
|