Files
storkit/server/src/agents/gates.rs

431 lines
15 KiB
Rust
Raw Normal View History

use std::path::Path;
use std::process::Command;
use std::time::Duration;
use wait_timeout::ChildExt;
/// Maximum time any single test command is allowed to run before being killed.
const TEST_TIMEOUT: Duration = Duration::from_secs(600); // 10 minutes
/// Detect whether the base branch in a worktree is `master` or `main`.
/// Falls back to `"master"` if neither is found.
pub(crate) fn detect_worktree_base_branch(wt_path: &Path) -> String {
for branch in &["master", "main"] {
let ok = Command::new("git")
.args(["rev-parse", "--verify", branch])
.current_dir(wt_path)
.output()
.map(|o| o.status.success())
.unwrap_or(false);
if ok {
return branch.to_string();
}
}
"master".to_string()
}
/// Return `true` if the git worktree at `wt_path` has commits on its current
/// branch that are not present on the base branch (`master` or `main`).
///
/// Used during server startup reconciliation to detect stories whose agent work
/// was committed while the server was offline.
pub(crate) fn worktree_has_committed_work(wt_path: &Path) -> bool {
let base_branch = detect_worktree_base_branch(wt_path);
let output = Command::new("git")
.args(["log", &format!("{base_branch}..HEAD"), "--oneline"])
.current_dir(wt_path)
.output();
match output {
Ok(out) if out.status.success() => {
!String::from_utf8_lossy(&out.stdout).trim().is_empty()
}
_ => false,
}
}
/// Check whether the given directory has any uncommitted git changes.
/// Returns `Err` with a descriptive message if there are any.
pub(crate) fn check_uncommitted_changes(path: &Path) -> Result<(), String> {
let output = Command::new("git")
.args(["status", "--porcelain"])
.current_dir(path)
.output()
.map_err(|e| format!("Failed to run git status: {e}"))?;
let stdout = String::from_utf8_lossy(&output.stdout);
if !stdout.trim().is_empty() {
return Err(format!(
"Worktree has uncommitted changes. Please commit all work before \
the agent exits:\n{stdout}"
));
}
Ok(())
}
/// Run the project's test suite.
///
/// Uses `script/test` if present, treating it as the canonical single test entry point.
/// Falls back to `cargo nextest run` / `cargo test` when `script/test` is absent.
/// Returns `(tests_passed, output)`.
pub(crate) fn run_project_tests(path: &Path) -> Result<(bool, String), String> {
let script_test = path.join("script").join("test");
if script_test.exists() {
let mut output = String::from("=== script/test ===\n");
let (success, out) = run_command_with_timeout(&script_test, &[], path)?;
output.push_str(&out);
output.push('\n');
return Ok((success, output));
}
// Fallback: cargo nextest run / cargo test
let mut output = String::from("=== tests ===\n");
let (success, test_out) = match run_command_with_timeout("cargo", &["nextest", "run"], path) {
Ok(result) => result,
Err(_) => {
// nextest not available — fall back to cargo test
run_command_with_timeout("cargo", &["test"], path)
.map_err(|e| format!("Failed to run cargo test: {e}"))?
}
};
output.push_str(&test_out);
output.push('\n');
Ok((success, output))
}
/// Run a command with a timeout. Returns `(success, combined_output)`.
/// Kills the child process if it exceeds `TEST_TIMEOUT`.
///
/// Stdout and stderr are drained in background threads to avoid a pipe-buffer
/// deadlock: if the child fills the 64 KB OS pipe buffer while the parent
/// blocks on `waitpid`, neither side can make progress.
fn run_command_with_timeout(
program: impl AsRef<std::ffi::OsStr>,
args: &[&str],
dir: &Path,
) -> Result<(bool, String), String> {
let mut child = Command::new(program)
.args(args)
.current_dir(dir)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.map_err(|e| format!("Failed to spawn command: {e}"))?;
// Drain stdout/stderr in background threads so the pipe buffers never fill.
let stdout_handle = child.stdout.take().map(|r| {
std::thread::spawn(move || {
let mut s = String::new();
let mut r = r;
std::io::Read::read_to_string(&mut r, &mut s).ok();
s
})
});
let stderr_handle = child.stderr.take().map(|r| {
std::thread::spawn(move || {
let mut s = String::new();
let mut r = r;
std::io::Read::read_to_string(&mut r, &mut s).ok();
s
})
});
match child.wait_timeout(TEST_TIMEOUT) {
Ok(Some(status)) => {
let stdout = stdout_handle
.and_then(|h| h.join().ok())
.unwrap_or_default();
let stderr = stderr_handle
.and_then(|h| h.join().ok())
.unwrap_or_default();
Ok((status.success(), format!("{stdout}{stderr}")))
}
Ok(None) => {
// Timed out — kill the child.
let _ = child.kill();
let _ = child.wait();
Err(format!(
"Command timed out after {} seconds",
TEST_TIMEOUT.as_secs()
))
}
Err(e) => Err(format!("Failed to wait for command: {e}")),
}
}
/// Run `cargo clippy` and the project test suite (via `script/test` if present,
/// otherwise `cargo nextest run` / `cargo test`) in the given directory.
/// Returns `(gates_passed, combined_output)`.
pub(crate) fn run_acceptance_gates(path: &Path) -> Result<(bool, String), String> {
let mut all_output = String::new();
let mut all_passed = true;
// ── cargo clippy ──────────────────────────────────────────────
let clippy = Command::new("cargo")
.args(["clippy", "--all-targets", "--all-features"])
.current_dir(path)
.output()
.map_err(|e| format!("Failed to run cargo clippy: {e}"))?;
all_output.push_str("=== cargo clippy ===\n");
let clippy_stdout = String::from_utf8_lossy(&clippy.stdout);
let clippy_stderr = String::from_utf8_lossy(&clippy.stderr);
if !clippy_stdout.is_empty() {
all_output.push_str(&clippy_stdout);
}
if !clippy_stderr.is_empty() {
all_output.push_str(&clippy_stderr);
}
all_output.push('\n');
if !clippy.status.success() {
all_passed = false;
}
// ── tests (script/test if available, else cargo nextest/test) ─
let (test_success, test_out) = run_project_tests(path)?;
all_output.push_str(&test_out);
if !test_success {
all_passed = false;
}
Ok((all_passed, all_output))
}
/// Run `script/test_coverage` in the given directory if the script exists.
///
/// Used as a QA gate before advancing a story from `3_qa/` to `4_merge/`.
/// Returns `(passed, output)`. If the script does not exist, returns `(true, …)`.
pub(crate) fn run_coverage_gate(path: &Path) -> Result<(bool, String), String> {
let script = path.join("script").join("test_coverage");
if !script.exists() {
return Ok((
true,
"script/test_coverage not found; coverage gate skipped.\n".to_string(),
));
}
let mut output = String::from("=== script/test_coverage ===\n");
let result = Command::new(&script)
.current_dir(path)
.output()
.map_err(|e| format!("Failed to run script/test_coverage: {e}"))?;
let combined = format!(
"{}{}",
String::from_utf8_lossy(&result.stdout),
String::from_utf8_lossy(&result.stderr)
);
output.push_str(&combined);
output.push('\n');
Ok((result.status.success(), output))
}
#[cfg(test)]
mod tests {
use super::*;
fn init_git_repo(repo: &std::path::Path) {
Command::new("git")
.args(["init"])
.current_dir(repo)
.output()
.unwrap();
Command::new("git")
.args(["config", "user.email", "test@test.com"])
.current_dir(repo)
.output()
.unwrap();
Command::new("git")
.args(["config", "user.name", "Test"])
.current_dir(repo)
.output()
.unwrap();
Command::new("git")
.args(["commit", "--allow-empty", "-m", "init"])
.current_dir(repo)
.output()
.unwrap();
}
// ── run_project_tests tests ───────────────────────────────────
#[cfg(unix)]
#[test]
fn run_project_tests_uses_script_test_when_present_and_passes() {
use std::fs;
use std::os::unix::fs::PermissionsExt;
use tempfile::tempdir;
let tmp = tempdir().unwrap();
let path = tmp.path();
let script_dir = path.join("script");
fs::create_dir_all(&script_dir).unwrap();
let script_test = script_dir.join("test");
fs::write(&script_test, "#!/usr/bin/env bash\necho 'all tests passed'\nexit 0\n").unwrap();
let mut perms = fs::metadata(&script_test).unwrap().permissions();
perms.set_mode(0o755);
fs::set_permissions(&script_test, perms).unwrap();
let (passed, output) = run_project_tests(path).unwrap();
assert!(passed, "script/test exiting 0 should pass");
assert!(output.contains("script/test"), "output should mention script/test");
}
#[cfg(unix)]
#[test]
fn run_project_tests_reports_failure_when_script_test_exits_nonzero() {
use std::fs;
use std::os::unix::fs::PermissionsExt;
use tempfile::tempdir;
let tmp = tempdir().unwrap();
let path = tmp.path();
let script_dir = path.join("script");
fs::create_dir_all(&script_dir).unwrap();
let script_test = script_dir.join("test");
fs::write(&script_test, "#!/usr/bin/env bash\nexit 1\n").unwrap();
let mut perms = fs::metadata(&script_test).unwrap().permissions();
perms.set_mode(0o755);
fs::set_permissions(&script_test, perms).unwrap();
let (passed, output) = run_project_tests(path).unwrap();
assert!(!passed, "script/test exiting 1 should fail");
assert!(output.contains("script/test"), "output should mention script/test");
}
// ── run_coverage_gate tests ───────────────────────────────────────────────
#[cfg(unix)]
#[test]
fn coverage_gate_passes_when_script_absent() {
use tempfile::tempdir;
let tmp = tempdir().unwrap();
let (passed, output) = run_coverage_gate(tmp.path()).unwrap();
assert!(passed, "coverage gate should pass when script is absent");
assert!(
output.contains("not found"),
"output should mention script not found"
);
}
#[cfg(unix)]
#[test]
fn coverage_gate_passes_when_script_exits_zero() {
use std::fs;
use std::os::unix::fs::PermissionsExt;
use tempfile::tempdir;
let tmp = tempdir().unwrap();
let path = tmp.path();
let script_dir = path.join("script");
fs::create_dir_all(&script_dir).unwrap();
let script = script_dir.join("test_coverage");
fs::write(
&script,
"#!/usr/bin/env bash\necho 'Rust line coverage: 85%'\necho 'PASS: Coverage 85% meets threshold 0%'\nexit 0\n",
)
.unwrap();
let mut perms = fs::metadata(&script).unwrap().permissions();
perms.set_mode(0o755);
fs::set_permissions(&script, perms).unwrap();
let (passed, output) = run_coverage_gate(path).unwrap();
assert!(passed, "coverage gate should pass when script exits 0");
assert!(
output.contains("script/test_coverage"),
"output should mention script/test_coverage"
);
}
#[cfg(unix)]
#[test]
fn coverage_gate_fails_when_script_exits_nonzero() {
use std::fs;
use std::os::unix::fs::PermissionsExt;
use tempfile::tempdir;
let tmp = tempdir().unwrap();
let path = tmp.path();
let script_dir = path.join("script");
fs::create_dir_all(&script_dir).unwrap();
let script = script_dir.join("test_coverage");
fs::write(
&script,
"#!/usr/bin/env bash\necho 'FAIL: Coverage 40% is below threshold 80%'\nexit 1\n",
)
.unwrap();
let mut perms = fs::metadata(&script).unwrap().permissions();
perms.set_mode(0o755);
fs::set_permissions(&script, perms).unwrap();
let (passed, output) = run_coverage_gate(path).unwrap();
assert!(!passed, "coverage gate should fail when script exits 1");
assert!(
output.contains("script/test_coverage"),
"output should mention script/test_coverage"
);
}
// ── worktree_has_committed_work tests ─────────────────────────────────────
#[test]
fn worktree_has_committed_work_false_on_fresh_repo() {
let tmp = tempfile::tempdir().unwrap();
let repo = tmp.path();
// init_git_repo creates the initial commit on the default branch.
// HEAD IS the base branch — no commits ahead.
init_git_repo(repo);
assert!(!worktree_has_committed_work(repo));
}
#[test]
fn worktree_has_committed_work_true_after_commit_on_feature_branch() {
use std::fs;
let tmp = tempfile::tempdir().unwrap();
let project_root = tmp.path().join("project");
fs::create_dir_all(&project_root).unwrap();
init_git_repo(&project_root);
// Create a git worktree on a feature branch.
let wt_path = tmp.path().join("wt");
Command::new("git")
.args([
"worktree",
"add",
&wt_path.to_string_lossy(),
"-b",
"feature/story-99_test",
])
.current_dir(&project_root)
.output()
.unwrap();
// No commits on the feature branch yet — same as base branch.
assert!(!worktree_has_committed_work(&wt_path));
// Add a commit to the feature branch in the worktree.
fs::write(wt_path.join("work.txt"), "done").unwrap();
Command::new("git")
.args(["add", "."])
.current_dir(&wt_path)
.output()
.unwrap();
Command::new("git")
.args([
"-c",
"user.email=test@test.com",
"-c",
"user.name=Test",
"commit",
"-m",
"coder: implement story",
])
.current_dir(&wt_path)
.output()
.unwrap();
// Now the feature branch is ahead of the base branch.
assert!(worktree_has_committed_work(&wt_path));
}
}