agent-manager/tests/ai_test.rs

//! Integration tests for `am ai` (issues #96 #97): the command resolves
//! the `aichat` catalog agent, so a fake `aichat.cmd` shim is placed on
//! PATH and emits a canned command. The safety pipeline (dry-run default,
//! classification, confirmation, --yes) is exercised end to end through
//! the real command dispatch.

mod common;

use agent_manager::cli::Cli;
use clap::Parser;
use std::path::PathBuf;
use std::sync::atomic::{AtomicU32, Ordering};
use std::sync::Mutex;

/// Serialize PATH mutation and process spawning between parallel tests.
static ENV_LOCK: Mutex<()> = Mutex::new(());
static COUNTER: AtomicU32 = AtomicU32::new(0);

const AICHAT_DEF: &str = r#"
agents:
  - name: aichat
    display_name: AIChat
    description: fake shim for tests
    category: shell-ai
    install:
      type: binary
      repo: sigoden/aichat
      binary: aichat
    run: aichat
    installable: false
"#;

fn fresh_dir(tag: &str) -> PathBuf {
    let id = COUNTER.fetch_add(1, Ordering::SeqCst);
    let dir = std::env::temp_dir().join(format!("am-ai-{tag}-{}-{id}", std::process::id()));
    std::fs::create_dir_all(&dir).unwrap();
    dir
}

/// Write a fake `aichat.cmd` into `dir` and prepend `dir` to PATH.
fn fake_aichat(dir: &PathBuf, body: &str) {
    std::fs::write(dir.join("aichat.cmd"), body).unwrap();
    let mut paths = vec![dir.clone()];
    if let Some(existing) = std::env::var_os("PATH") {
        paths.extend(std::env::split_paths(&existing));
    }
    std::env::set_var("PATH", std::env::join_paths(paths).unwrap());
}

/// Build the App for an `am ai` invocation with the aichat shim on PATH.
fn app_for(shim_body: &str, settings: &str, args: &[&str]) -> (agent_manager::app::App, PathBuf) {
    let dir = fresh_dir("app");
    fake_aichat(&dir, shim_body);
    let cfg = common::write_config(&dir, &format!("{settings}{AICHAT_DEF}"));
    let mut full = vec!["am".to_string(), "--config".to_string(), cfg.display().to_string()];
    full.extend(args.iter().map(|s| s.to_string()));
    let cli = Cli::parse_from(full);
    let mut app = agent_manager::app::App::from_cli(cli).expect("app should build");
    common::isolate(&mut app, &dir);
    (app, dir)
}

fn run(args: &[&str], shim_body: &str, settings: &str) -> (String, String, i32) {
    let _g = ENV_LOCK.lock().unwrap_or_else(|e| e.into_inner());
    let (app, dir) = app_for(shim_body, settings, args);
    let cmd = app.cli.command.as_ref().expect("a command was parsed");
    let code = agent_manager::commands::execute_command(&app, cmd).unwrap_or_else(|e| {
        eprintln!("ERR: {e:#}");
        1
    });
    let log = std::fs::read_to_string(app.paths.log_dir.join("agent-manager.log"))
        .unwrap_or_default();
    // Events journal lives next to state.json (isolated dir).
    let mut events = String::new();
    if let Ok(rd) = std::fs::read_dir(&dir) {
        for e in rd.flatten() {
            let name = e.file_name().to_string_lossy().to_string();
            if name.starts_with("events-") && name.ends_with(".jsonl") {
                events.push_str(&std::fs::read_to_string(e.path()).unwrap_or_default());
            }
        }
    }
    (log, events, code)
}

#[test]
fn ai_exec_dry_run_is_the_default_and_never_executes() {
    let (log, events, code) = run(
        &["ai", "--exec", "supprime tout"],
        "@echo off\r\necho rm -rf /tmp/nonexistent-xyz\r\n",
        "",
    );
    assert_eq!(code, 0);
    assert!(
        log.contains("non exécutée") || log.contains("not executed"),
        "dry-run policy must abort, log: {log}"
    );
    assert!(!log.contains("exécution:"), "nothing must run, log: {log}");
    assert!(
        events.contains("shell_ai") && events.contains("executed=false"),
        "journal must record the aborted exec, events: {events}"
    );
}

#[test]
fn ai_exec_with_yes_executes_through_the_shell() {
    // Shim emits a harmless command; --yes skips the policy gate.
    let (log, events, code) = run(
        &["ai", "--exec", "dis bonjour", "--yes"],
        "@echo off\r\necho echo hello-from-shim\r\n",
        "",
    );
    assert_eq!(code, 0);
    assert!(
        log.contains("exécution: echo hello-from-shim"),
        "the generated command must run, log: {log}"
    );
    assert!(
        events.contains("executed=true"),
        "journal must record the execution, events: {events}"
    );
}

#[test]
fn ai_conversational_passes_prompt_and_context_to_aichat() {
    // Shim echoes its arguments; conversational mode passes -f . + prompt.
    let (log, events, code) = run(
        &["ai", "liste les fichiers"],
        "@echo off\r\necho %*\r\n",
        "",
    );
    assert_eq!(code, 0);
    assert!(
        log.contains("shell-ai:") || events.contains("mode=chat"),
        "conversational mode must be journalized, log: {log} events: {events}"
    );
    assert!(events.contains("mode=chat"), "events: {events}");
}

#[test]
fn ai_exec_respects_configured_confirm_mode() {
    // default_safety: confirm + risky command => the confirmation prompt is
    // reached; without stdin input the prompt is declined (empty answer).
    let (log, events, code) = run(
        &["ai", "--exec", "supprime"],
        "@echo off\r\necho rm -rf /tmp/nonexistent-xyz\r\n",
        "  shell_ai:\n    default_safety: confirm\n",
    );
    assert_eq!(code, 0);
    assert!(
        log.contains("annulé") || log.contains("cancelled") || log.contains("non exécutée")
            || log.contains("not executed"),
        "declined confirmation must abort, log: {log}"
    );
    assert!(!log.contains("exécution:"), "log: {log}");
    assert!(events.contains("executed=false"), "events: {events}");
}