Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0b34d1608f | ||
|
|
075dea509a | ||
|
|
c067f48a24 | ||
|
|
51f96cfb98 | ||
|
|
8f5d96a95b | ||
|
|
3e98b3ab24 | ||
|
|
24ed1ac002 | ||
|
|
64741a027e | ||
|
|
cdd4213ff5 | ||
|
|
f8973b3802 | ||
|
|
1e2c0f0a38 | ||
|
|
6fa7dc63e4 | ||
|
|
5c0a4c4640 | ||
|
|
8773671afd | ||
|
|
d9815d86c6 | ||
|
|
13009d0f0e | ||
|
|
bbae09bc48 | ||
|
|
c7c294996e | ||
|
|
3c638b08de | ||
|
|
be23a2b539 | ||
|
|
b98f5cb3e5 | ||
|
|
0f5576c77a | ||
|
|
0292f373f7 | ||
|
|
eea337ce36 | ||
|
|
fd3ea64949 | ||
|
|
046c110460 | ||
|
|
6eb65f1057 | ||
|
|
3a68c1dd2f | ||
|
|
fde1954eac | ||
|
|
25435c34b2 | ||
|
|
4a956e9c38 | ||
|
|
2a49814572 | ||
|
|
d1aa56bab3 | ||
|
|
cf322746a7 | ||
|
|
b25e733539 | ||
|
|
5a861976d7 | ||
|
|
bfe4965081 | ||
|
|
9d7ed8c071 | ||
|
|
88a40c1ea7 | ||
|
|
7049b5f1c0 | ||
|
|
c277ad630c | ||
|
|
fc9c62d46b | ||
|
|
3fe560d67e | ||
|
|
b2b33535ae | ||
|
|
4ea6ddcaee | ||
|
|
e9142bb027 | ||
|
|
d11098a478 | ||
|
|
61776b4e0a | ||
|
|
eabd21bccf | ||
|
|
fd54d4f833 | ||
|
|
78b5abb0cf |
@@ -92,6 +92,12 @@ clients — how it opens, the sigils, the key model, the match-and-rank algorith
|
||||
the two matchers must agree on, and the fixture table they are tested against.
|
||||
Read it before changing either bar or either matcher.
|
||||
|
||||
`docs/STRUCTURED-VIEW.md` is the contract for a structured session (an agent
|
||||
run as a daemon child over ACP instead of in a tmux pane) — the eight
|
||||
transcript row kinds, the two projections and their cursor/replay semantics,
|
||||
the handshake and declined capabilities, and the approval nonce rules. Read
|
||||
it before changing anything that renders a structured session.
|
||||
|
||||
`nix run .#dev` (or `just dev`) brings up the whole local stack under
|
||||
process-compose: a debug daemon on 127.0.0.1:7071, then Vite on :5173 once the
|
||||
daemon answers `/api/info`. The SPA proxies `/api/*` back to the daemon, so only
|
||||
|
||||
Generated
+1
@@ -1558,6 +1558,7 @@ version = "0.1.0"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"futures-util",
|
||||
"libc",
|
||||
"maestro-protocol",
|
||||
"maestro-testing",
|
||||
"maestro-tui",
|
||||
|
||||
+1
-1
@@ -10,7 +10,7 @@ repository = "https://git.naps.pt/naps62/maestro"
|
||||
publish = false
|
||||
|
||||
[workspace.dependencies]
|
||||
agent-client-protocol = "2.1"
|
||||
agent-client-protocol = { version = "2.1", features = ["unstable_tool_call_name"] }
|
||||
axum = { version = "0.7", features = ["ws"] }
|
||||
chrono = { version = "0.4", default-features = false, features = ["clock", "serde"] }
|
||||
clap = { version = "4.5", features = ["derive", "env"] }
|
||||
|
||||
+294
-41
@@ -19,6 +19,12 @@
|
||||
//! is dropped while nobody reads: #135 takes the receiver and persists each
|
||||
//! notification to the per-session event log before broadcasting it.
|
||||
//!
|
||||
//! A respawn after a daemon restart sets [`SpawnConfig::load_session`] and
|
||||
//! the handshake runs `session/load` with the stored id instead of
|
||||
//! `session/new`. The history the agent streams back while that request is
|
||||
//! in flight is *not* delivered: the daemon's event log already holds it,
|
||||
//! and replaying it would double every line.
|
||||
//!
|
||||
//! The child is a child of the daemon, full stop. It shares the daemon's
|
||||
//! process group, is marked to receive `SIGTERM` when the daemon dies
|
||||
//! (`PR_SET_PDEATHSIG` on Linux), and [`AcpSession::terminate`] is what both
|
||||
@@ -31,13 +37,15 @@ use std::collections::{HashMap, VecDeque};
|
||||
use std::ffi::OsString;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::{ExitStatus, Stdio};
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::Duration;
|
||||
|
||||
use agent_client_protocol::schema::v1::{
|
||||
CancelNotification, ClientCapabilities, FileSystemCapabilities, Implementation,
|
||||
InitializeRequest, NewSessionRequest, RequestPermissionOutcome, RequestPermissionRequest,
|
||||
RequestPermissionResponse, SessionId, SessionNotification,
|
||||
CancelNotification, ClientCapabilities, ContentBlock, FileSystemCapabilities, Implementation,
|
||||
InitializeRequest, LoadSessionRequest, NewSessionRequest, PromptRequest,
|
||||
RequestPermissionOutcome, RequestPermissionRequest, RequestPermissionResponse, SessionId,
|
||||
SessionNotification,
|
||||
};
|
||||
use agent_client_protocol::schema::ProtocolVersion;
|
||||
use agent_client_protocol::{ByteStreams, Client};
|
||||
@@ -82,6 +90,10 @@ pub struct SpawnConfig {
|
||||
pub env: HashMap<String, String>,
|
||||
/// Upper bound on the handshake; [`HANDSHAKE_TIMEOUT`] by default.
|
||||
pub handshake_timeout: Duration,
|
||||
/// An existing ACP session id to resume with `session/load` (#135)
|
||||
/// instead of opening a fresh one. The adapter must advertise
|
||||
/// `loadSession`; the handshake fails otherwise.
|
||||
pub load_session: Option<String>,
|
||||
}
|
||||
|
||||
impl SpawnConfig {
|
||||
@@ -90,8 +102,24 @@ impl SpawnConfig {
|
||||
cwd: cwd.into(),
|
||||
env,
|
||||
handshake_timeout: HANDSHAKE_TIMEOUT,
|
||||
load_session: None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Resume `session_id` with `session/load` instead of `session/new`.
|
||||
pub fn load_session(mut self, session_id: impl Into<String>) -> Self {
|
||||
self.load_session = Some(session_id.into());
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
/// A blocked ACP permission request delivered to the daemon.
|
||||
#[derive(Debug)]
|
||||
pub struct PermissionRequest {
|
||||
/// The prompt turn that was active when ACP delivered this callback.
|
||||
pub turn: u64,
|
||||
pub request: RequestPermissionRequest,
|
||||
pub response: oneshot::Sender<RequestPermissionOutcome>,
|
||||
}
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
@@ -135,9 +163,44 @@ fn is_executable(path: &Path) -> bool {
|
||||
|
||||
enum Command {
|
||||
Cancel,
|
||||
Prompt {
|
||||
text: String,
|
||||
turn: u64,
|
||||
done: oneshot::Sender<Result<(), String>>,
|
||||
},
|
||||
Close,
|
||||
}
|
||||
|
||||
enum ChildCommand {
|
||||
Signal(libc::c_int),
|
||||
Reap(oneshot::Sender<bool>),
|
||||
}
|
||||
|
||||
#[derive(Debug, Default)]
|
||||
struct PermissionTurnState {
|
||||
active: Option<u64>,
|
||||
}
|
||||
|
||||
impl PermissionTurnState {
|
||||
fn begin(&mut self, turn: u64) {
|
||||
self.active = Some(turn);
|
||||
}
|
||||
|
||||
fn cancel_active(&mut self) {
|
||||
self.active = None;
|
||||
}
|
||||
|
||||
fn finish(&mut self, turn: u64) {
|
||||
if self.active == Some(turn) {
|
||||
self.active = None;
|
||||
}
|
||||
}
|
||||
|
||||
fn callback_turn(&self) -> Option<u64> {
|
||||
self.active
|
||||
}
|
||||
}
|
||||
|
||||
/// Why the handshake did not produce a session id.
|
||||
enum ReadyError {
|
||||
/// The adapter answered with an error.
|
||||
@@ -162,7 +225,9 @@ pub struct AcpSession {
|
||||
session_id: String,
|
||||
pid: u32,
|
||||
commands: mpsc::UnboundedSender<Command>,
|
||||
child_commands: mpsc::UnboundedSender<ChildCommand>,
|
||||
updates: Mutex<Option<mpsc::UnboundedReceiver<SessionNotification>>>,
|
||||
permission_requests: Mutex<Option<mpsc::UnboundedReceiver<PermissionRequest>>>,
|
||||
exit: watch::Receiver<Option<ExitStatus>>,
|
||||
}
|
||||
|
||||
@@ -183,6 +248,18 @@ impl AcpSession {
|
||||
self.exit.borrow().is_some()
|
||||
}
|
||||
|
||||
/// Reap the child if it has already exited.
|
||||
pub async fn reap_if_exited(&self) -> bool {
|
||||
if self.has_exited() {
|
||||
return true;
|
||||
}
|
||||
let (sent, received) = oneshot::channel();
|
||||
if self.child_commands.send(ChildCommand::Reap(sent)).is_err() {
|
||||
return self.has_exited();
|
||||
}
|
||||
received.await.unwrap_or_else(|_| self.has_exited())
|
||||
}
|
||||
|
||||
/// Wait for the child to exit.
|
||||
pub async fn wait(&self) -> Option<ExitStatus> {
|
||||
wait_exit(&self.exit).await
|
||||
@@ -194,18 +271,39 @@ impl AcpSession {
|
||||
self.updates.lock().expect("updates mutex").take()
|
||||
}
|
||||
|
||||
pub fn take_permission_requests(&self) -> Option<mpsc::UnboundedReceiver<PermissionRequest>> {
|
||||
self.permission_requests
|
||||
.lock()
|
||||
.expect("permission requests")
|
||||
.take()
|
||||
}
|
||||
|
||||
/// Send `session/cancel`. Fire-and-forget: a closed connection means the
|
||||
/// child is already gone, which is the outcome cancel was after.
|
||||
pub fn cancel(&self) {
|
||||
let _ = self.commands.send(Command::Cancel);
|
||||
}
|
||||
|
||||
/// Send a user prompt and receive completion once the agent ends the turn.
|
||||
pub fn prompt(
|
||||
&self,
|
||||
text: String,
|
||||
turn: u64,
|
||||
) -> Result<oneshot::Receiver<Result<(), String>>, String> {
|
||||
let (done_tx, done_rx) = oneshot::channel();
|
||||
self.commands
|
||||
.send(Command::Prompt {
|
||||
text,
|
||||
turn,
|
||||
done: done_tx,
|
||||
})
|
||||
.map_err(|_| "ACP connection is closed".to_string())?;
|
||||
Ok(done_rx)
|
||||
}
|
||||
|
||||
/// End the child: `session/cancel`, wait `cancel_grace`, `SIGTERM`, wait
|
||||
/// `term_grace`, `SIGKILL`. Returns once the child has been reaped.
|
||||
pub async fn terminate(&self, cancel_grace: Duration, term_grace: Duration) {
|
||||
if self.has_exited() {
|
||||
return;
|
||||
}
|
||||
self.cancel();
|
||||
if tokio::time::timeout(cancel_grace, self.wait())
|
||||
.await
|
||||
@@ -227,16 +325,14 @@ impl AcpSession {
|
||||
}
|
||||
|
||||
fn signal(&self, sig: libc::c_int) {
|
||||
signal_pid(self.pid, sig);
|
||||
let _ = self.child_commands.send(ChildCommand::Signal(sig));
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for AcpSession {
|
||||
fn drop(&mut self) {
|
||||
self.signal(libc::SIGTERM);
|
||||
let _ = self.commands.send(Command::Close);
|
||||
if !self.has_exited() {
|
||||
self.signal(libc::SIGTERM);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -283,20 +379,20 @@ pub async fn spawn(config: SpawnConfig) -> Result<AcpSession, AcpError> {
|
||||
tokio::spawn(drain_stderr(stderr, pid, stderr_tail.clone()));
|
||||
|
||||
let (exit_tx, exit_rx) = watch::channel(None);
|
||||
tokio::spawn(async move {
|
||||
let status = child.wait().await.ok();
|
||||
tracing::debug!(pid, ?status, "{ADAPTER_BIN} exited");
|
||||
let _ = exit_tx.send(status);
|
||||
});
|
||||
let (child_commands_tx, child_commands_rx) = mpsc::unbounded_channel();
|
||||
tokio::spawn(supervise_child(child, pid, child_commands_rx, exit_tx));
|
||||
|
||||
let (updates_tx, updates_rx) = mpsc::unbounded_channel();
|
||||
let (permission_tx, permission_rx) = mpsc::unbounded_channel();
|
||||
let (commands_tx, commands_rx) = mpsc::unbounded_channel();
|
||||
let (ready_tx, ready_rx) = oneshot::channel();
|
||||
let transport = ByteStreams::new(stdin.compat_write(), stdout.compat());
|
||||
tokio::spawn(run_connection(
|
||||
transport,
|
||||
config.cwd.clone(),
|
||||
config.load_session.clone(),
|
||||
updates_tx,
|
||||
permission_tx,
|
||||
commands_rx,
|
||||
ready_tx,
|
||||
));
|
||||
@@ -308,7 +404,9 @@ pub async fn spawn(config: SpawnConfig) -> Result<AcpSession, AcpError> {
|
||||
session_id,
|
||||
pid,
|
||||
commands: commands_tx,
|
||||
child_commands: child_commands_tx,
|
||||
updates: Mutex::new(Some(updates_rx)),
|
||||
permission_requests: Mutex::new(Some(permission_rx)),
|
||||
exit: exit_rx,
|
||||
});
|
||||
}
|
||||
@@ -337,12 +435,12 @@ pub async fn spawn(config: SpawnConfig) -> Result<AcpSession, AcpError> {
|
||||
};
|
||||
// No half-started adapter survives a failed spawn.
|
||||
let _ = commands_tx.send(Command::Close);
|
||||
signal_pid(pid, libc::SIGTERM);
|
||||
let _ = child_commands_tx.send(ChildCommand::Signal(libc::SIGTERM));
|
||||
if tokio::time::timeout(TERM_GRACE, wait_exit(&exit_rx))
|
||||
.await
|
||||
.is_err()
|
||||
{
|
||||
signal_pid(pid, libc::SIGKILL);
|
||||
let _ = child_commands_tx.send(ChildCommand::Signal(libc::SIGKILL));
|
||||
wait_exit(&exit_rx).await;
|
||||
}
|
||||
Err(failure)
|
||||
@@ -354,11 +452,54 @@ async fn wait_exit(exit: &watch::Receiver<Option<ExitStatus>>) -> Option<ExitSta
|
||||
*status
|
||||
}
|
||||
|
||||
fn signal_pid(pid: u32, sig: libc::c_int) {
|
||||
// ESRCH just means the child is already gone.
|
||||
// SAFETY: plain syscall on a pid we spawned and have not reaped.
|
||||
unsafe {
|
||||
libc::kill(pid as libc::pid_t, sig);
|
||||
async fn supervise_child(
|
||||
mut child: tokio::process::Child,
|
||||
pid: u32,
|
||||
mut commands: mpsc::UnboundedReceiver<ChildCommand>,
|
||||
exit_tx: watch::Sender<Option<ExitStatus>>,
|
||||
) {
|
||||
loop {
|
||||
tokio::select! {
|
||||
status = child.wait() => {
|
||||
let status = status.ok();
|
||||
tracing::debug!(pid, ?status, "{ADAPTER_BIN} exited");
|
||||
let _ = exit_tx.send(status);
|
||||
return;
|
||||
}
|
||||
command = commands.recv() => match command {
|
||||
Some(ChildCommand::Signal(sig)) => {
|
||||
// This task alone owns `child`. It cannot reap the child
|
||||
// between receiving this command and sending the signal,
|
||||
// so its PID cannot be reused in that window.
|
||||
unsafe { libc::kill(pid as libc::pid_t, sig) };
|
||||
}
|
||||
Some(ChildCommand::Reap(done)) => match child.try_wait() {
|
||||
Ok(Some(status)) => {
|
||||
let _ = done.send(true);
|
||||
tracing::debug!(pid, ?status, "{ADAPTER_BIN} exited");
|
||||
let _ = exit_tx.send(Some(status));
|
||||
return;
|
||||
}
|
||||
Ok(None) => {
|
||||
let _ = done.send(false);
|
||||
}
|
||||
Err(error) => {
|
||||
tracing::warn!(pid, %error, "could not reap {ADAPTER_BIN}");
|
||||
let _ = done.send(false);
|
||||
}
|
||||
},
|
||||
None => {
|
||||
// The session vanished without a command receiver. This
|
||||
// task still owns the unreaped child, so this cannot hit
|
||||
// a reused PID.
|
||||
unsafe { libc::kill(pid as libc::pid_t, libc::SIGTERM) };
|
||||
let status = child.wait().await.ok();
|
||||
tracing::debug!(pid, ?status, "{ADAPTER_BIN} exited");
|
||||
let _ = exit_tx.send(status);
|
||||
return;
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -375,17 +516,33 @@ fn client_capabilities() -> ClientCapabilities {
|
||||
async fn run_connection<T>(
|
||||
transport: T,
|
||||
cwd: PathBuf,
|
||||
load_session: Option<String>,
|
||||
updates_tx: mpsc::UnboundedSender<SessionNotification>,
|
||||
permission_requests: mpsc::UnboundedSender<PermissionRequest>,
|
||||
mut commands_rx: mpsc::UnboundedReceiver<Command>,
|
||||
ready_tx: oneshot::Sender<Result<String, ReadyError>>,
|
||||
) where
|
||||
T: agent_client_protocol::ConnectTo<Client> + 'static,
|
||||
{
|
||||
// Set while `session/load` is in flight. Notification handlers run in
|
||||
// the dispatch loop, in arrival order, so everything the agent streams
|
||||
// before its load response sees the flag up and is dropped: that is the
|
||||
// history the event log already holds (#135).
|
||||
let replaying = Arc::new(AtomicBool::new(false));
|
||||
let replaying_seen = replaying.clone();
|
||||
// ACP callbacks have no turn id. The daemon never queues a later prompt
|
||||
// until a cancelled prompt settles, so this active turn is unambiguous.
|
||||
let permission_turn = Arc::new(Mutex::new(PermissionTurnState::default()));
|
||||
let permission_turn_seen = permission_turn.clone();
|
||||
let result = Client
|
||||
.builder()
|
||||
.name("maestro")
|
||||
.on_receive_notification(
|
||||
async move |notification: SessionNotification, _cx| {
|
||||
if replaying_seen.load(Ordering::SeqCst) {
|
||||
tracing::trace!("dropping replayed notification during session/load");
|
||||
return Ok(());
|
||||
}
|
||||
// A dropped receiver only means nobody wants updates any more.
|
||||
let _ = updates_tx.send(notification);
|
||||
Ok(())
|
||||
@@ -394,15 +551,30 @@ async fn run_connection<T>(
|
||||
)
|
||||
.on_receive_request(
|
||||
async move |request: RequestPermissionRequest, responder, _cx| {
|
||||
// Stub until #139: decline rather than grant something the
|
||||
// operator never saw.
|
||||
tracing::warn!(
|
||||
session = %request.session_id,
|
||||
"session/request_permission declined: not implemented yet (#139)"
|
||||
);
|
||||
responder.respond(RequestPermissionResponse::new(
|
||||
RequestPermissionOutcome::Cancelled,
|
||||
))
|
||||
let turn = permission_turn_seen
|
||||
.lock()
|
||||
.expect("permission turn state")
|
||||
.callback_turn();
|
||||
let Some(turn) = turn else {
|
||||
return responder.respond(RequestPermissionResponse::new(
|
||||
RequestPermissionOutcome::Cancelled,
|
||||
));
|
||||
};
|
||||
let (response, received) = oneshot::channel();
|
||||
if permission_requests
|
||||
.send(PermissionRequest {
|
||||
turn,
|
||||
request,
|
||||
response,
|
||||
})
|
||||
.is_err()
|
||||
{
|
||||
return responder.respond(RequestPermissionResponse::new(
|
||||
RequestPermissionOutcome::Cancelled,
|
||||
));
|
||||
}
|
||||
let outcome = received.await.unwrap_or(RequestPermissionOutcome::Cancelled);
|
||||
responder.respond(RequestPermissionResponse::new(outcome))
|
||||
},
|
||||
agent_client_protocol::on_receive_request!(),
|
||||
)
|
||||
@@ -410,32 +582,113 @@ async fn run_connection<T>(
|
||||
let init = InitializeRequest::new(ProtocolVersion::V1)
|
||||
.client_capabilities(client_capabilities())
|
||||
.client_info(Implementation::new("maestro", env!("CARGO_PKG_VERSION")));
|
||||
if let Err(e) = cx.send_request(init).block_task().await {
|
||||
let _ = ready_tx.send(Err(ready_error(e)));
|
||||
return Ok(());
|
||||
}
|
||||
let created = match cx
|
||||
.send_request(NewSessionRequest::new(cwd))
|
||||
.block_task()
|
||||
.await
|
||||
{
|
||||
let initialized = match cx.send_request(init).block_task().await {
|
||||
Ok(r) => r,
|
||||
Err(e) => {
|
||||
let _ = ready_tx.send(Err(ready_error(e)));
|
||||
return Ok(());
|
||||
}
|
||||
};
|
||||
let session_id = created.session_id.0.to_string();
|
||||
let session_id = match load_session {
|
||||
Some(existing) => {
|
||||
if !initialized.agent_capabilities.load_session {
|
||||
let _ = ready_tx.send(Err(ReadyError::Handshake(format!(
|
||||
"{ADAPTER_BIN} does not advertise loadSession; cannot resume session {existing}"
|
||||
))));
|
||||
return Ok(());
|
||||
}
|
||||
replaying.store(true, Ordering::SeqCst);
|
||||
let (loaded_tx, loaded_rx) = oneshot::channel();
|
||||
let replaying_done = replaying.clone();
|
||||
if let Err(e) = cx
|
||||
.send_request(LoadSessionRequest::new(existing.clone(), cwd))
|
||||
.on_receiving_result(move |result| {
|
||||
replaying_done.store(false, Ordering::SeqCst);
|
||||
async move {
|
||||
let _ = loaded_tx.send(result);
|
||||
Ok(())
|
||||
}
|
||||
})
|
||||
{
|
||||
let _ = ready_tx.send(Err(ready_error(e)));
|
||||
return Ok(());
|
||||
}
|
||||
match loaded_rx.await {
|
||||
Ok(Ok(_)) => {}
|
||||
Ok(Err(e)) => {
|
||||
let _ = ready_tx.send(Err(ready_error(e)));
|
||||
return Ok(());
|
||||
}
|
||||
Err(_) => {
|
||||
let _ = ready_tx.send(Err(ReadyError::Handshake(
|
||||
"session/load response was not delivered".into(),
|
||||
)));
|
||||
return Ok(());
|
||||
}
|
||||
}
|
||||
existing
|
||||
}
|
||||
None => match cx
|
||||
.send_request(NewSessionRequest::new(cwd))
|
||||
.block_task()
|
||||
.await
|
||||
{
|
||||
Ok(created) => created.session_id.0.to_string(),
|
||||
Err(e) => {
|
||||
let _ = ready_tx.send(Err(ready_error(e)));
|
||||
return Ok(());
|
||||
}
|
||||
},
|
||||
};
|
||||
let _ = ready_tx.send(Ok(session_id.clone()));
|
||||
|
||||
loop {
|
||||
tokio::select! {
|
||||
cmd = commands_rx.recv() => match cmd {
|
||||
Some(Command::Cancel) => {
|
||||
permission_turn
|
||||
.lock()
|
||||
.expect("permission turn state")
|
||||
.cancel_active();
|
||||
let _ = cx.send_notification(CancelNotification::new(
|
||||
SessionId::new(session_id.as_str()),
|
||||
));
|
||||
}
|
||||
Some(Command::Prompt { text, turn, done }) => {
|
||||
permission_turn
|
||||
.lock()
|
||||
.expect("permission turn state")
|
||||
.begin(turn);
|
||||
let request = PromptRequest::new(
|
||||
SessionId::new(session_id.as_str()),
|
||||
vec![ContentBlock::from(text)],
|
||||
);
|
||||
let done = Arc::new(Mutex::new(Some(done)));
|
||||
let callback_done = done.clone();
|
||||
let callback_turn = permission_turn.clone();
|
||||
if let Err(error) = cx.send_request(request).on_receiving_result(move |result| {
|
||||
let callback_done = callback_done.clone();
|
||||
let callback_turn = callback_turn.clone();
|
||||
async move {
|
||||
callback_turn
|
||||
.lock()
|
||||
.expect("permission turn state")
|
||||
.finish(turn);
|
||||
if let Some(done) = callback_done.lock().expect("prompt sender").take() {
|
||||
let _ = done.send(result.map(|_| ()).map_err(|e| e.to_string()));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}) {
|
||||
permission_turn
|
||||
.lock()
|
||||
.expect("permission turn state")
|
||||
.finish(turn);
|
||||
if let Some(done) = done.lock().expect("prompt sender").take() {
|
||||
let _ = done.send(Err(error.to_string()));
|
||||
}
|
||||
}
|
||||
}
|
||||
Some(Command::Close) | None => break,
|
||||
},
|
||||
_ = cx.incoming_closed() => break,
|
||||
|
||||
@@ -17,14 +17,35 @@ Environment knobs, all optional:
|
||||
signal SIGTERM
|
||||
FAKE_ACP_ECHO_ENV name of one env var to log at start
|
||||
FAKE_ACP_INIT_FAIL=1 answer `initialize` with a JSON-RPC error
|
||||
FAKE_ACP_DELAY_SESSION_NEW_MS=n wait n milliseconds before answering
|
||||
`session/new`
|
||||
FAKE_ACP_EXIT_AFTER_NEW=1 exit 0 right after answering `session/new`
|
||||
FAKE_ACP_EXIT_ON_CANCEL=1 exit 0 on `session/cancel` (default: keep running
|
||||
so the SIGTERM path is exercised)
|
||||
FAKE_ACP_IGNORE_EOF=1 keep running after stdin closes, until signalled
|
||||
FAKE_ACP_EMIT_ON_CANCEL=1 emit a final notification before handling cancel
|
||||
FAKE_ACP_CANCEL_SETTLES=1 complete the outstanding prompt on cancel
|
||||
FAKE_ACP_NO_LOAD=1 advertise `loadSession: false`
|
||||
FAKE_ACP_LOAD_REPLAY=n on `session/load`, replay n `agent_message_chunk`
|
||||
notifications ("replayed <i>") before answering,
|
||||
the way a real agent streams history back
|
||||
FAKE_ACP_LOAD_FAIL=1 answer `session/load` with a JSON-RPC error
|
||||
FAKE_ACP_DELAY_PROMPT_MS=n wait before answering `session/prompt`
|
||||
FAKE_ACP_PROMPT_FAIL=1 answer every `session/prompt` with a JSON-RPC error
|
||||
FAKE_ACP_PROMPT_FAIL_ONCE=1 answer only the first `session/prompt` with a
|
||||
JSON-RPC error
|
||||
FAKE_ACP_PERMISSION_AFTER_CANCEL=1 defer the first prompt's permission
|
||||
callback until a later prompt
|
||||
|
||||
Signals: SIGUSR1 emits one `agent_message_chunk` notification ("tick <n>",
|
||||
counting from 1) and logs `emit tick <n>`, so a test can make the agent
|
||||
speak on demand (#135).
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import signal
|
||||
import sys
|
||||
import time
|
||||
|
||||
LOG = os.environ.get("FAKE_ACP_LOG")
|
||||
|
||||
@@ -49,13 +70,36 @@ def on_sigterm(_signum, _frame):
|
||||
|
||||
signal.signal(signal.SIGTERM, on_sigterm)
|
||||
|
||||
session_id = f"fake-{os.getpid()}"
|
||||
ticks = 0
|
||||
prompt_failures = 0
|
||||
pending_prompt_id = None
|
||||
pending_permission_id = None
|
||||
delayed_permission = False
|
||||
|
||||
|
||||
def chunk(text):
|
||||
return {"jsonrpc": "2.0", "method": "session/update", "params": {
|
||||
"sessionId": session_id,
|
||||
"update": {"sessionUpdate": "agent_message_chunk",
|
||||
"content": {"type": "text", "text": text}},
|
||||
}}
|
||||
|
||||
|
||||
def on_sigusr1(_signum, _frame):
|
||||
global ticks
|
||||
ticks += 1
|
||||
send(chunk(f"tick {ticks}"))
|
||||
log(f"emit tick {ticks}")
|
||||
|
||||
|
||||
signal.signal(signal.SIGUSR1, on_sigusr1)
|
||||
|
||||
log(f"start pid={os.getpid()} cwd={os.getcwd()}")
|
||||
echo = os.environ.get("FAKE_ACP_ECHO_ENV")
|
||||
if echo:
|
||||
log(f"env {echo}={os.environ.get(echo, '')}")
|
||||
|
||||
session_id = f"fake-{os.getpid()}"
|
||||
|
||||
for raw in sys.stdin:
|
||||
raw = raw.strip()
|
||||
if not raw:
|
||||
@@ -64,6 +108,12 @@ for raw in sys.stdin:
|
||||
method = msg.get("method")
|
||||
if method is None:
|
||||
# A response to something we sent; nothing to do.
|
||||
if msg.get("id") == pending_permission_id:
|
||||
log("permission response " + json.dumps(msg.get("result"), sort_keys=True))
|
||||
send({"jsonrpc": "2.0", "id": pending_prompt_id,
|
||||
"result": {"stopReason": "end_turn"}})
|
||||
pending_prompt_id = None
|
||||
pending_permission_id = None
|
||||
continue
|
||||
log(f"recv {method}")
|
||||
rid = msg.get("id")
|
||||
@@ -77,22 +127,85 @@ for raw in sys.stdin:
|
||||
continue
|
||||
send({"jsonrpc": "2.0", "id": rid, "result": {
|
||||
"protocolVersion": params.get("protocolVersion", 1),
|
||||
"agentCapabilities": {"loadSession": True},
|
||||
"agentCapabilities": {
|
||||
"loadSession": os.environ.get("FAKE_ACP_NO_LOAD") != "1"},
|
||||
"agentInfo": {"name": "fake-acp-agent", "version": "0.0.0"},
|
||||
"authMethods": [],
|
||||
}})
|
||||
elif method == "session/new":
|
||||
time.sleep(int(os.environ.get("FAKE_ACP_DELAY_SESSION_NEW_MS", "0")) / 1000)
|
||||
send({"jsonrpc": "2.0", "id": rid, "result": {"sessionId": session_id}})
|
||||
send({"jsonrpc": "2.0", "method": "session/update", "params": {
|
||||
"sessionId": session_id,
|
||||
"update": {"sessionUpdate": "agent_message_chunk",
|
||||
"content": {"type": "text", "text": "hello from fake"}},
|
||||
}})
|
||||
send(chunk("hello from fake"))
|
||||
if os.environ.get("FAKE_ACP_EXIT_AFTER_NEW") == "1":
|
||||
sys.exit(0)
|
||||
elif method == "session/load":
|
||||
session_id = params.get("sessionId")
|
||||
log(f"recv session/load sessionId={session_id}")
|
||||
if os.environ.get("FAKE_ACP_LOAD_FAIL") == "1":
|
||||
send({"jsonrpc": "2.0", "id": rid,
|
||||
"error": {"code": -32000, "message": "fake load failure"}})
|
||||
continue
|
||||
for i in range(int(os.environ.get("FAKE_ACP_LOAD_REPLAY", "0"))):
|
||||
send(chunk(f"replayed {i + 1}"))
|
||||
send({"jsonrpc": "2.0", "id": rid, "result": {}})
|
||||
send(chunk("hello after load"))
|
||||
elif method == "session/cancel":
|
||||
if os.environ.get("FAKE_ACP_EMIT_ON_CANCEL") == "1":
|
||||
send(chunk("final on cancel"))
|
||||
if (os.environ.get("FAKE_ACP_CANCEL_SETTLES") == "1"
|
||||
and pending_prompt_id is not None):
|
||||
send({"jsonrpc": "2.0", "id": pending_prompt_id,
|
||||
"result": {"stopReason": "cancelled"}})
|
||||
pending_prompt_id = None
|
||||
pending_permission_id = None
|
||||
if os.environ.get("FAKE_ACP_EXIT_ON_CANCEL") == "1":
|
||||
sys.exit(0)
|
||||
elif method == "session/prompt":
|
||||
if os.environ.get("FAKE_ACP_PERMISSION_AFTER_CANCEL") == "1":
|
||||
if pending_prompt_id is None:
|
||||
pending_prompt_id = rid
|
||||
delayed_permission = True
|
||||
continue
|
||||
if delayed_permission:
|
||||
delayed_permission = False
|
||||
pending_permission_id = "permission-1"
|
||||
send({"jsonrpc": "2.0", "id": pending_permission_id,
|
||||
"method": "session/request_permission", "params": {
|
||||
"sessionId": session_id,
|
||||
"toolCall": {"toolCallId": "tool-1", "fields": {}},
|
||||
"options": [
|
||||
{"optionId": "once", "name": "Allow once", "kind": "allow_once"},
|
||||
{"optionId": "deny", "name": "Deny", "kind": "reject_once"}
|
||||
]
|
||||
}})
|
||||
continue
|
||||
if os.environ.get("FAKE_ACP_REQUEST_PERMISSION") == "1":
|
||||
pending_prompt_id = rid
|
||||
pending_permission_id = "permission-1"
|
||||
send({"jsonrpc": "2.0", "id": pending_permission_id,
|
||||
"method": "session/request_permission", "params": {
|
||||
"sessionId": session_id,
|
||||
"toolCall": {"toolCallId": "tool-1", "fields": {}},
|
||||
"options": [
|
||||
{"optionId": "once", "name": "Allow once", "kind": "allow_once"},
|
||||
{"optionId": "session", "name": "Allow session", "kind": "allow_always"},
|
||||
{"optionId": "deny", "name": "Deny", "kind": "reject_once"}
|
||||
]
|
||||
}})
|
||||
continue
|
||||
time.sleep(int(os.environ.get("FAKE_ACP_DELAY_PROMPT_MS", "0")) / 1000)
|
||||
fail_once = os.environ.get("FAKE_ACP_PROMPT_FAIL_ONCE") == "1"
|
||||
if os.environ.get("FAKE_ACP_PROMPT_FAIL") == "1" or (fail_once and prompt_failures == 0):
|
||||
prompt_failures += 1
|
||||
send({"jsonrpc": "2.0", "id": rid,
|
||||
"error": {"code": -32000, "message": "fake prompt failure"}})
|
||||
else:
|
||||
send({"jsonrpc": "2.0", "id": rid,
|
||||
"result": {"stopReason": "end_turn"}})
|
||||
elif rid is not None:
|
||||
send({"jsonrpc": "2.0", "id": rid,
|
||||
"error": {"code": -32601, "message": f"method not found: {method}"}})
|
||||
|
||||
if os.environ.get("FAKE_ACP_IGNORE_EOF") == "1":
|
||||
while True:
|
||||
signal.pause()
|
||||
|
||||
@@ -69,6 +69,24 @@ impl Fake {
|
||||
}
|
||||
panic!("log never contained {needle:?}:\n{}", self.log());
|
||||
}
|
||||
|
||||
fn pid(&self) -> u32 {
|
||||
self.log()
|
||||
.lines()
|
||||
.find_map(|line| line.strip_prefix("start pid="))
|
||||
.and_then(|rest| rest.split(' ').next())
|
||||
.and_then(|pid| pid.parse().ok())
|
||||
.expect("pid in log")
|
||||
}
|
||||
|
||||
async fn wait_for_exit(&self) {
|
||||
let pid = self.pid();
|
||||
let deadline = Instant::now() + Duration::from_secs(5);
|
||||
while pid_alive(pid) && Instant::now() < deadline {
|
||||
tokio::time::sleep(Duration::from_millis(20)).await;
|
||||
}
|
||||
assert!(!pid_alive(pid), "child {pid} still alive");
|
||||
}
|
||||
}
|
||||
|
||||
fn pid_alive(pid: u32) -> bool {
|
||||
@@ -274,6 +292,90 @@ async fn child_exit_before_handshake_reports_exited_early() {
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn drop_terminates_and_reaps_the_child() {
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut config = fake.config(cwd.path());
|
||||
config.env.insert("FAKE_ACP_IGNORE_EOF".into(), "1".into());
|
||||
let session = maestro_acp::spawn(config).await.expect("spawn");
|
||||
|
||||
drop(session);
|
||||
|
||||
fake.wait_for_log("signal SIGTERM").await;
|
||||
fake.wait_for_exit().await;
|
||||
}
|
||||
|
||||
fn chunk_text(n: &maestro_acp::schema::SessionNotification) -> String {
|
||||
match &n.update {
|
||||
SessionUpdate::AgentMessageChunk(chunk) => match &chunk.content {
|
||||
ContentBlock::Text(t) => t.text.clone(),
|
||||
other => panic!("unexpected content {other:?}"),
|
||||
},
|
||||
other => panic!("unexpected update {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn load_session_resumes_the_stored_id_and_drops_the_replay() {
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut config = fake.config(cwd.path()).load_session("fake-old");
|
||||
config.env.insert("FAKE_ACP_LOAD_REPLAY".into(), "3".into());
|
||||
|
||||
let session = maestro_acp::spawn(config).await.expect("spawn");
|
||||
assert_eq!(session.session_id(), "fake-old");
|
||||
let log = fake.log();
|
||||
assert!(
|
||||
log.contains("recv session/load sessionId=fake-old"),
|
||||
"{log}"
|
||||
);
|
||||
assert!(!log.contains("recv session/new"), "{log}");
|
||||
|
||||
// The three replayed chunks never reach the receiver: the event log
|
||||
// already holds them. The first notification after the response does.
|
||||
let mut updates = session.take_updates().expect("updates");
|
||||
let first = tokio::time::timeout(Duration::from_secs(5), updates.recv())
|
||||
.await
|
||||
.expect("update within 5s")
|
||||
.expect("channel open");
|
||||
assert_eq!(chunk_text(&first), "hello after load");
|
||||
// Nothing queued behind it either.
|
||||
tokio::time::sleep(Duration::from_millis(100)).await;
|
||||
assert!(updates.try_recv().is_err(), "replay leaked through");
|
||||
|
||||
session
|
||||
.terminate(Duration::from_millis(100), Duration::from_secs(2))
|
||||
.await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn load_session_requires_the_load_capability() {
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut config = fake.config(cwd.path()).load_session("fake-old");
|
||||
config.env.insert("FAKE_ACP_NO_LOAD".into(), "1".into());
|
||||
|
||||
let err = maestro_acp::spawn(config)
|
||||
.await
|
||||
.expect_err("no loadSession");
|
||||
assert!(matches!(err, AcpError::Handshake(_)), "{err}");
|
||||
assert!(err.to_string().contains("loadSession"), "{err}");
|
||||
assert!(!fake.log().contains("recv session/load"), "{}", fake.log());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn load_session_error_fails_the_spawn() {
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut config = fake.config(cwd.path()).load_session("fake-old");
|
||||
config.env.insert("FAKE_ACP_LOAD_FAIL".into(), "1".into());
|
||||
|
||||
let err = maestro_acp::spawn(config).await.expect_err("load fails");
|
||||
assert!(matches!(err, AcpError::Handshake(_)), "{err}");
|
||||
assert!(err.to_string().contains("fake load failure"), "{err}");
|
||||
}
|
||||
|
||||
/// End to end against the installed `claude-code-acp`. Needs Claude auth,
|
||||
/// takes seconds, so it is opt-in: `cargo test -p maestro-acp -- --ignored`.
|
||||
#[tokio::test]
|
||||
|
||||
@@ -66,6 +66,23 @@ pub fn decide(idle_for: Duration, awaiting_input: bool) -> ActivityState {
|
||||
}
|
||||
}
|
||||
|
||||
/// Derive a structured session's sidebar state from its ACP projection.
|
||||
pub fn decide_structured(
|
||||
turn_active: bool,
|
||||
pending_approval: bool,
|
||||
turn_failed: bool,
|
||||
) -> ActivityState {
|
||||
if turn_failed {
|
||||
ActivityState::Error
|
||||
} else if pending_approval {
|
||||
ActivityState::AwaitingInput
|
||||
} else if turn_active {
|
||||
ActivityState::Active
|
||||
} else {
|
||||
ActivityState::Idle
|
||||
}
|
||||
}
|
||||
|
||||
/// How long a session's pane must be continuously focused (a client's pane,
|
||||
/// not a sidebar highlight) before an `AwaitingInput` glow clears: the
|
||||
/// operator has looked, so the rail stops asking for attention.
|
||||
@@ -136,6 +153,17 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn structured_activity_follows_lifecycle_with_approval_precedence() {
|
||||
assert_eq!(decide_structured(false, false, false), ActivityState::Idle);
|
||||
assert_eq!(decide_structured(true, false, false), ActivityState::Active);
|
||||
assert_eq!(
|
||||
decide_structured(true, true, false),
|
||||
ActivityState::AwaitingInput
|
||||
);
|
||||
assert_eq!(decide_structured(false, false, true), ActivityState::Error);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn report_is_in_force_until_exactly_its_expiry() {
|
||||
let ttl = Duration::from_secs(300);
|
||||
|
||||
@@ -122,21 +122,23 @@ async fn run(config_override: Option<PathBuf>) -> Result<(), Box<dyn Error>> {
|
||||
// shutdown, and both must reach the adapter children below (#134). The
|
||||
// unit's `KillMode=process` signals only the daemon, so nothing else
|
||||
// would end them.
|
||||
let shutdown = async {
|
||||
let shutdown_manager = manager.clone();
|
||||
let shutdown = async move {
|
||||
let mut sigterm = tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate())
|
||||
.expect("install SIGTERM handler");
|
||||
tokio::select! {
|
||||
_ = tokio::signal::ctrl_c() => tracing::info!("ctrl-c received — shutting down"),
|
||||
_ = sigterm.recv() => tracing::info!("SIGTERM received — shutting down"),
|
||||
}
|
||||
// Axum waits for upgraded WebSockets to drain. Structured children
|
||||
// must be settled before that wait, while the signal path still owns
|
||||
// the shutdown order (#179).
|
||||
shutdown_manager.shutdown().await;
|
||||
};
|
||||
|
||||
axum::serve(listener, router)
|
||||
.tcp_nodelay(true)
|
||||
.with_graceful_shutdown(shutdown)
|
||||
.await?;
|
||||
// tmux sessions outlive the daemon by design; structured sessions'
|
||||
// adapter children do not (#134).
|
||||
manager.shutdown().await;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -21,6 +21,7 @@ pub mod hooks;
|
||||
pub mod local_api;
|
||||
pub mod panes;
|
||||
pub mod proc;
|
||||
pub mod projection;
|
||||
pub mod projects;
|
||||
pub mod pty;
|
||||
pub mod release;
|
||||
|
||||
@@ -21,12 +21,13 @@ use maestro_config::SpawnPreset;
|
||||
use maestro_protocol::{
|
||||
routes, ApiError, CatalogEvent, CreateSessionRequest, DaemonInfo, GitRoot, NameBatch,
|
||||
RenameSessionRequest, ReportActivityRequest, SendInputRequest, Session, SetFocusRequest,
|
||||
PROTOCOL_VERSION,
|
||||
StructuredApprovalDecision, StructuredEvent, StructuredPromptRequest, PROTOCOL_VERSION,
|
||||
};
|
||||
use serde::Deserialize;
|
||||
use uuid::Uuid;
|
||||
|
||||
use crate::session::SessionManager;
|
||||
use crate::session::{QueueAcpPrompt, SessionManager};
|
||||
use crate::sidecar::EventCursor;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct LocalApiState {
|
||||
@@ -64,7 +65,15 @@ pub fn router(state: LocalApiState) -> Router {
|
||||
.route(routes::NAMES, get(names))
|
||||
.route(routes::INFO, get(daemon_info))
|
||||
.route(routes::EVENTS, any(events_ws))
|
||||
.route(routes::patterns::ATTACH, any(attach_ws));
|
||||
.route(routes::patterns::ATTACH, any(attach_ws))
|
||||
.route(routes::patterns::STRUCTURED, any(structured_ws))
|
||||
.route(routes::patterns::STRUCTURED_REPLAY, get(structured_replay))
|
||||
.route(routes::patterns::STRUCTURED_PROMPT, post(structured_prompt))
|
||||
.route(routes::patterns::STRUCTURED_CANCEL, post(structured_cancel))
|
||||
.route(
|
||||
routes::patterns::STRUCTURED_APPROVAL,
|
||||
post(structured_approval),
|
||||
);
|
||||
#[cfg(feature = "haiku-autoname")]
|
||||
{
|
||||
router = router.route(routes::patterns::SESSION_PROMPT, post(session_prompt));
|
||||
@@ -170,6 +179,7 @@ fn session_error_status(code: &str) -> StatusCode {
|
||||
// The session outlived its pane: nothing to type into, and nothing
|
||||
// the daemon can do about it.
|
||||
"not_running" => StatusCode::CONFLICT,
|
||||
"shutting_down" => StatusCode::SERVICE_UNAVAILABLE,
|
||||
_ => StatusCode::BAD_GATEWAY,
|
||||
}
|
||||
}
|
||||
@@ -297,11 +307,10 @@ async fn rename_session(
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /api/sessions/:id/activity` (#105): an agent reports its own state.
|
||||
/// The report holds above the daemon's inference for a TTL, then inference
|
||||
/// resumes — an agent that dies mid-run cannot pin its session at `Error`
|
||||
/// forever. Unknown session is 404; an unknown state value is rejected by the
|
||||
/// JSON decoder (422) rather than coerced. Answers `204 No Content`.
|
||||
/// `POST /api/sessions/:id/activity` (#105): an agent reports a terminal
|
||||
/// session's state. Structured sessions acknowledge and ignore these reports
|
||||
/// because their activity comes from ACP. Unknown session is 404; an unknown
|
||||
/// state value is rejected by the JSON decoder (422). Answers `204 No Content`.
|
||||
async fn report_activity(
|
||||
State(s): State<LocalApiState>,
|
||||
Path(id): Path<Uuid>,
|
||||
@@ -368,6 +377,126 @@ fn error_response(status: StatusCode, code: &str, message: &str) -> Response {
|
||||
(status, Json(ApiError::new(code, message))).into_response()
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct ReplayQuery {
|
||||
since: Option<u64>,
|
||||
before: Option<u64>,
|
||||
limit: Option<usize>,
|
||||
}
|
||||
|
||||
const MAX_STRUCTURED_REPLAY_LIMIT: usize = 500;
|
||||
|
||||
async fn structured_replay(
|
||||
State(s): State<LocalApiState>,
|
||||
Path(id): Path<Uuid>,
|
||||
Query(query): Query<ReplayQuery>,
|
||||
) -> Response {
|
||||
if query.since.is_some() && query.before.is_some() {
|
||||
return error_response(
|
||||
StatusCode::BAD_REQUEST,
|
||||
"invalid_cursor",
|
||||
"use either since or before, not both",
|
||||
);
|
||||
}
|
||||
let cursor = match query.before {
|
||||
Some(before) => EventCursor::Before(Some(before)),
|
||||
None => EventCursor::Since(query.since.unwrap_or(0)),
|
||||
};
|
||||
match s
|
||||
.manager
|
||||
.read_acp_projection_replay(
|
||||
id,
|
||||
cursor,
|
||||
query
|
||||
.limit
|
||||
.unwrap_or(100)
|
||||
.clamp(1, MAX_STRUCTURED_REPLAY_LIMIT),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(Some(events)) => Json(events).into_response(),
|
||||
// A terminal session, or a structured session whose adapter is no
|
||||
// longer live, cannot provide a coherent replay continuation.
|
||||
Ok(None) => error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"not_structured",
|
||||
"session is not a live structured session",
|
||||
),
|
||||
Err(e) => {
|
||||
let info = e.to_error_info();
|
||||
error_response(session_error_status(&info.code), &info.code, &info.message)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn structured_prompt(
|
||||
State(s): State<LocalApiState>,
|
||||
Path(id): Path<Uuid>,
|
||||
Json(body): Json<StructuredPromptRequest>,
|
||||
) -> Response {
|
||||
match s.manager.queue_acp_prompt(id, body.prompt).await {
|
||||
Ok(QueueAcpPrompt::Queued) => StatusCode::NO_CONTENT.into_response(),
|
||||
Ok(QueueAcpPrompt::InFlight) => error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"turn_in_flight",
|
||||
"the structured session already has an active turn",
|
||||
),
|
||||
Ok(QueueAcpPrompt::Unavailable) => error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"not_structured",
|
||||
"session is not a live structured session",
|
||||
),
|
||||
Ok(QueueAcpPrompt::Failed(message)) => {
|
||||
error_response(StatusCode::BAD_GATEWAY, "acp_prompt_failed", &message)
|
||||
}
|
||||
Err(e) => {
|
||||
let info = e.to_error_info();
|
||||
error_response(session_error_status(&info.code), &info.code, &info.message)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn structured_cancel(State(s): State<LocalApiState>, Path(id): Path<Uuid>) -> Response {
|
||||
match s.manager.cancel_acp_turn(id).await {
|
||||
Ok(true) => StatusCode::NO_CONTENT.into_response(),
|
||||
Ok(false) => error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"not_structured",
|
||||
"session is not a live structured session",
|
||||
),
|
||||
Err(e) => {
|
||||
let info = e.to_error_info();
|
||||
error_response(session_error_status(&info.code), &info.code, &info.message)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn structured_approval(
|
||||
State(s): State<LocalApiState>,
|
||||
Path((id, nonce)): Path<(Uuid, String)>,
|
||||
Json(decision): Json<StructuredApprovalDecision>,
|
||||
) -> Response {
|
||||
let decision = match decision {
|
||||
StructuredApprovalDecision::AllowOnce => crate::session::ApprovalDecision::AllowOnce,
|
||||
StructuredApprovalDecision::AllowForSession => {
|
||||
crate::session::ApprovalDecision::AllowForSession
|
||||
}
|
||||
StructuredApprovalDecision::Deny => crate::session::ApprovalDecision::Deny,
|
||||
};
|
||||
match s.manager.resolve_acp_approval(id, &nonce, decision).await {
|
||||
Ok(Some(())) => StatusCode::NO_CONTENT.into_response(),
|
||||
Ok(None) => error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"not_structured",
|
||||
"session is not a live structured session",
|
||||
),
|
||||
Err(e) => {
|
||||
let info = e.to_error_info();
|
||||
error_response(session_error_status(&info.code), &info.code, &info.message)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Convenience constructor — pulls the bits `LocalApiState` needs from
|
||||
/// `DaemonConfig` so callers don't have to assemble it by hand. The project
|
||||
/// scanner starts with its cache cold; wire
|
||||
@@ -418,6 +547,75 @@ async fn attach_ws(
|
||||
}))
|
||||
}
|
||||
|
||||
#[allow(clippy::result_large_err)]
|
||||
async fn structured_ws(
|
||||
Path(id): Path<Uuid>,
|
||||
State(s): State<LocalApiState>,
|
||||
ws: axum::extract::WebSocketUpgrade,
|
||||
) -> Result<Response, Response> {
|
||||
let Some((snapshot, state, rx)) = s
|
||||
.manager
|
||||
.subscribe_acp_projection(id, EventCursor::Since(0))
|
||||
.await
|
||||
.map_err(|e| {
|
||||
let info = e.to_error_info();
|
||||
error_response(session_error_status(&info.code), &info.code, &info.message)
|
||||
})?
|
||||
else {
|
||||
return Err(error_response(
|
||||
StatusCode::CONFLICT,
|
||||
"not_structured",
|
||||
"session is not a live structured session",
|
||||
));
|
||||
};
|
||||
Ok(ws.on_upgrade(move |socket| async move {
|
||||
let _ = pump_structured(socket, snapshot, state, rx).await;
|
||||
}))
|
||||
}
|
||||
|
||||
async fn pump_structured(
|
||||
socket: axum::extract::ws::WebSocket,
|
||||
snapshot: maestro_protocol::TranscriptSnapshot,
|
||||
state: maestro_protocol::ReducedState,
|
||||
mut rx: tokio::sync::broadcast::Receiver<crate::projection::ProjectionUpdate>,
|
||||
) -> Result<(), axum::Error> {
|
||||
use axum::extract::ws::Message;
|
||||
use futures_util::{SinkExt, StreamExt};
|
||||
|
||||
let (mut sink, mut stream) = socket.split();
|
||||
for event in [
|
||||
StructuredEvent::TranscriptSnapshot { snapshot },
|
||||
StructuredEvent::ReducedState { state },
|
||||
] {
|
||||
if sink
|
||||
.send(Message::Text(
|
||||
serde_json::to_string(&event).expect("structured event encode"),
|
||||
))
|
||||
.await
|
||||
.is_err()
|
||||
{
|
||||
return Ok(());
|
||||
}
|
||||
}
|
||||
loop {
|
||||
tokio::select! {
|
||||
update = rx.recv() => match update {
|
||||
Ok(update) => {
|
||||
let event = StructuredEvent::ProjectionUpdate { transcript: update.transcript, state: update.state };
|
||||
if sink.send(Message::Text(serde_json::to_string(&event).expect("structured event encode"))).await.is_err() { break; }
|
||||
}
|
||||
Err(tokio::sync::broadcast::error::RecvError::Lagged(_)) => break,
|
||||
Err(tokio::sync::broadcast::error::RecvError::Closed) => break,
|
||||
},
|
||||
frame = stream.next() => match frame {
|
||||
None | Some(Err(_)) | Some(Ok(Message::Close(_))) => break,
|
||||
Some(Ok(_)) => {},
|
||||
},
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// WS /api/events — live catalog deltas for browser/TUI subscribers (NAP-248)
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
@@ -0,0 +1,850 @@
|
||||
//! Fold persisted ACP notifications into client-neutral transcript and state.
|
||||
|
||||
use std::collections::{HashMap, HashSet};
|
||||
|
||||
use maestro_acp::schema::{ContentChunk, SessionNotification, SessionUpdate, ToolCall};
|
||||
use maestro_protocol::{
|
||||
ActivityState, ReducedState, TranscriptDelta, TranscriptRow, TranscriptRowKind,
|
||||
TranscriptSnapshot,
|
||||
};
|
||||
use serde_json::Value;
|
||||
|
||||
/// A transcript delta paired with the state after the same ACP notification.
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct ProjectionUpdate {
|
||||
pub transcript: Option<TranscriptDelta>,
|
||||
pub state: ReducedState,
|
||||
}
|
||||
|
||||
/// A prompt lifecycle transition supplied by the prompt transport (#138).
|
||||
///
|
||||
/// ACP notifications do not delimit turns, so replaying them must not infer
|
||||
/// an in-flight prompt from an agent chunk.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum TurnLifecycle {
|
||||
Begin,
|
||||
Finish,
|
||||
Cancel,
|
||||
Failure,
|
||||
}
|
||||
|
||||
/// The one-pass ACP fold used for both persisted replay and live events.
|
||||
#[derive(Debug, Default)]
|
||||
pub struct Projection {
|
||||
rows: Vec<TranscriptRow>,
|
||||
row_index: HashMap<String, usize>,
|
||||
tools: HashMap<String, ToolCall>,
|
||||
pending_tool_updates: HashMap<String, Vec<maestro_acp::schema::ToolCallUpdateFields>>,
|
||||
state: ReducedState,
|
||||
active_turn: Option<u64>,
|
||||
turn_failed: bool,
|
||||
next_turn: u64,
|
||||
turn_tool_calls: HashSet<String>,
|
||||
}
|
||||
|
||||
impl Projection {
|
||||
/// Fold one durable event and return its client-visible changes.
|
||||
pub fn apply(&mut self, seq: u64, notification: &SessionNotification) -> ProjectionUpdate {
|
||||
let transcript = match ¬ification.update {
|
||||
SessionUpdate::UserMessageChunk(chunk) => {
|
||||
self.content(seq, chunk, TranscriptRowKind::User, "user")
|
||||
}
|
||||
SessionUpdate::AgentMessageChunk(chunk) => {
|
||||
self.agent_text();
|
||||
self.content(seq, chunk, TranscriptRowKind::AgentText, "agent")
|
||||
}
|
||||
SessionUpdate::AgentThoughtChunk(chunk) => {
|
||||
self.agent_thought();
|
||||
self.content(seq, chunk, TranscriptRowKind::AgentThought, "thought")
|
||||
}
|
||||
SessionUpdate::ToolCall(tool) => self.tool_call(tool),
|
||||
SessionUpdate::ToolCallUpdate(update) => self.tool_update(update),
|
||||
SessionUpdate::Plan(plan) => {
|
||||
let data = to_value(plan);
|
||||
self.state.plan = Some(data.clone());
|
||||
Some(self.replace("plan".into(), TranscriptRowKind::Plan, data))
|
||||
}
|
||||
SessionUpdate::UsageUpdate(usage) => {
|
||||
let value = to_value(usage);
|
||||
self.state.usage = Some(value.clone());
|
||||
self.state.context = Some(value);
|
||||
None
|
||||
}
|
||||
SessionUpdate::CurrentModeUpdate(mode) => {
|
||||
self.state.mode = Some(mode.current_mode_id.to_string());
|
||||
None
|
||||
}
|
||||
SessionUpdate::ConfigOptionUpdate(options) => {
|
||||
let value = to_value(options);
|
||||
self.state.model = model_from_options(&value).or_else(|| self.state.model.clone());
|
||||
None
|
||||
}
|
||||
// ACP deliberately adds notification variants over time. Known but
|
||||
// non-transcript updates become a generic notice instead of being
|
||||
// dropped or forcing clients to understand ACP's enum.
|
||||
_ => Some(self.append(
|
||||
format!("notice:{seq}"),
|
||||
TranscriptRowKind::Notice,
|
||||
to_value(¬ification.update),
|
||||
)),
|
||||
};
|
||||
ProjectionUpdate {
|
||||
transcript,
|
||||
state: self.state.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
/// The current transcript at `cursor`.
|
||||
pub fn snapshot(&self, cursor: u64) -> TranscriptSnapshot {
|
||||
TranscriptSnapshot {
|
||||
cursor,
|
||||
rows: self.rows.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
/// The state folded over every event seen so far.
|
||||
pub fn state(&self) -> ReducedState {
|
||||
self.state.clone()
|
||||
}
|
||||
|
||||
pub fn turn_active(&self) -> bool {
|
||||
self.active_turn.is_some()
|
||||
}
|
||||
|
||||
/// Sidebar activity derived from the live turn projection.
|
||||
pub fn activity(&self) -> ActivityState {
|
||||
crate::activity::decide_structured(
|
||||
self.active_turn.is_some(),
|
||||
self.state.pending_approval.is_some(),
|
||||
self.turn_failed,
|
||||
)
|
||||
}
|
||||
|
||||
/// Start a prompt turn and return its monotonically increasing token.
|
||||
pub fn begin_turn(&mut self) -> (u64, ProjectionUpdate) {
|
||||
self.next_turn += 1;
|
||||
let turn = self.next_turn;
|
||||
self.active_turn = Some(turn);
|
||||
self.turn_failed = false;
|
||||
self.state.turn.responding = true;
|
||||
self.state.turn.thinking = true;
|
||||
self.turn_tool_calls.clear();
|
||||
self.state.turn.active_tool_calls.clear();
|
||||
(
|
||||
turn,
|
||||
ProjectionUpdate {
|
||||
transcript: None,
|
||||
state: self.state(),
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
/// End `turn` only when it remains the active prompt turn.
|
||||
pub fn turn_lifecycle(
|
||||
&mut self,
|
||||
lifecycle: TurnLifecycle,
|
||||
turn: u64,
|
||||
) -> Option<ProjectionUpdate> {
|
||||
if !matches!(
|
||||
lifecycle,
|
||||
TurnLifecycle::Finish | TurnLifecycle::Cancel | TurnLifecycle::Failure
|
||||
) || self.active_turn != Some(turn)
|
||||
{
|
||||
return None;
|
||||
}
|
||||
self.active_turn = None;
|
||||
self.turn_failed = lifecycle == TurnLifecycle::Failure;
|
||||
self.state.turn.responding = false;
|
||||
self.state.turn.thinking = false;
|
||||
self.turn_tool_calls.clear();
|
||||
self.state.turn.active_tool_calls.clear();
|
||||
Some(ProjectionUpdate {
|
||||
transcript: None,
|
||||
state: self.state(),
|
||||
})
|
||||
}
|
||||
|
||||
pub fn active_turn(&self) -> Option<u64> {
|
||||
self.active_turn
|
||||
}
|
||||
|
||||
/// Add a daemon-originated permission row. The nonce belongs only in the
|
||||
/// reduced state, which is the client control surface, never in ACP data.
|
||||
pub fn request_approval(&mut self, nonce: String, request: Value) -> ProjectionUpdate {
|
||||
let row = self.append(
|
||||
format!("approval:{}", uuid::Uuid::new_v4()),
|
||||
TranscriptRowKind::Approval,
|
||||
request.clone(),
|
||||
);
|
||||
self.state.pending_approval = Some(serde_json::json!({
|
||||
"nonce": nonce,
|
||||
"request": request,
|
||||
}));
|
||||
ProjectionUpdate {
|
||||
transcript: Some(row),
|
||||
state: self.state(),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn restore_approval(&mut self, row: TranscriptRow) -> ProjectionUpdate {
|
||||
let transcript = if !self.row_index.contains_key(&row.id) {
|
||||
self.row_index.insert(row.id.clone(), self.rows.len());
|
||||
self.rows.push(row.clone());
|
||||
Some(TranscriptDelta::Append { row })
|
||||
} else {
|
||||
None
|
||||
};
|
||||
ProjectionUpdate {
|
||||
transcript,
|
||||
state: self.state(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Clear an approval only when it is still the one the client answered.
|
||||
pub fn resolve_approval(&mut self, nonce: &str) -> Option<ProjectionUpdate> {
|
||||
let pending = self.state.pending_approval.as_ref()?;
|
||||
if pending.get("nonce").and_then(Value::as_str) != Some(nonce) {
|
||||
return None;
|
||||
}
|
||||
self.state.pending_approval = None;
|
||||
Some(ProjectionUpdate {
|
||||
transcript: None,
|
||||
state: self.state(),
|
||||
})
|
||||
}
|
||||
|
||||
/// Terminal turn paths must not leave a recovered snapshot permanently
|
||||
/// blocked on an ACP request whose transport no longer exists.
|
||||
pub fn clear_approval(&mut self) -> Option<ProjectionUpdate> {
|
||||
self.state.pending_approval.take()?;
|
||||
Some(ProjectionUpdate {
|
||||
transcript: None,
|
||||
state: self.state(),
|
||||
})
|
||||
}
|
||||
|
||||
/// Undo an `append`ed row that a caller decides never happened — used
|
||||
/// when persisting the row's own event fails (#184), so a snapshot taken
|
||||
/// after the failure cannot show a row durable replay would never
|
||||
/// reproduce. Only ever called for a row that was just appended and
|
||||
/// never patched, so removing it by id fully reverses `append`.
|
||||
pub fn rollback_row(&mut self, id: &str) {
|
||||
let Some(index) = self.row_index.remove(id) else {
|
||||
return;
|
||||
};
|
||||
self.rows.remove(index);
|
||||
for (shifted_index, row) in self.rows.iter().enumerate().skip(index) {
|
||||
self.row_index.insert(row.id.clone(), shifted_index);
|
||||
}
|
||||
}
|
||||
|
||||
fn content(
|
||||
&mut self,
|
||||
seq: u64,
|
||||
chunk: &ContentChunk,
|
||||
kind: TranscriptRowKind,
|
||||
prefix: &str,
|
||||
) -> Option<TranscriptDelta> {
|
||||
let id = chunk
|
||||
.message_id
|
||||
.as_ref()
|
||||
.map(|id| format!("{prefix}:{id}"))
|
||||
.unwrap_or_else(|| format!("{prefix}:{seq}"));
|
||||
let data = to_value(chunk);
|
||||
if let Some(index) = self.row_index.get(&id).copied() {
|
||||
let row = &mut self.rows[index];
|
||||
append_text(&mut row.data, &data);
|
||||
return Some(TranscriptDelta::Patch { row: row.clone() });
|
||||
}
|
||||
Some(self.append(id, kind, data))
|
||||
}
|
||||
|
||||
fn tool_call(&mut self, tool: &ToolCall) -> Option<TranscriptDelta> {
|
||||
let id = format!("tool:{}", tool.tool_call_id);
|
||||
let tool_id = tool.tool_call_id.to_string();
|
||||
let mut canonical = tool.clone();
|
||||
if let Some(updates) = self.pending_tool_updates.get(&tool_id) {
|
||||
for fields in updates {
|
||||
canonical.update(fields.clone());
|
||||
}
|
||||
}
|
||||
let kind = if tool_has_diff(tool) {
|
||||
TranscriptRowKind::ToolDiff
|
||||
} else {
|
||||
TranscriptRowKind::ToolCall
|
||||
};
|
||||
self.tools.insert(tool_id, canonical.clone());
|
||||
self.track_tool_call(&canonical);
|
||||
Some(self.replace(
|
||||
id,
|
||||
if tool_has_diff(&canonical) {
|
||||
TranscriptRowKind::ToolDiff
|
||||
} else {
|
||||
kind
|
||||
},
|
||||
to_value(&canonical),
|
||||
))
|
||||
}
|
||||
|
||||
fn tool_update(
|
||||
&mut self,
|
||||
update: &maestro_acp::schema::ToolCallUpdate,
|
||||
) -> Option<TranscriptDelta> {
|
||||
let tool_id = update.tool_call_id.to_string();
|
||||
let Some(tool) = self.tools.get_mut(&tool_id) else {
|
||||
self.pending_tool_updates
|
||||
.entry(tool_id)
|
||||
.or_default()
|
||||
.push(update.fields.clone());
|
||||
return None;
|
||||
};
|
||||
tool.update(update.fields.clone());
|
||||
self.pending_tool_updates
|
||||
.entry(tool_id.clone())
|
||||
.or_default()
|
||||
.push(update.fields.clone());
|
||||
let row_id = format!("tool:{tool_id}");
|
||||
let index = *self
|
||||
.row_index
|
||||
.get(&row_id)
|
||||
.expect("a tracked tool call always has a transcript row");
|
||||
let row = {
|
||||
let row = &mut self.rows[index];
|
||||
row.kind = if tool_has_diff(tool) {
|
||||
TranscriptRowKind::ToolDiff
|
||||
} else {
|
||||
TranscriptRowKind::ToolCall
|
||||
};
|
||||
row.data = to_value(tool);
|
||||
row.clone()
|
||||
};
|
||||
self.sync_active_tool(&tool_id);
|
||||
Some(TranscriptDelta::Patch { row })
|
||||
}
|
||||
|
||||
fn append(&mut self, id: String, kind: TranscriptRowKind, data: Value) -> TranscriptDelta {
|
||||
let row = TranscriptRow { id, kind, data };
|
||||
self.row_index.insert(row.id.clone(), self.rows.len());
|
||||
self.rows.push(row.clone());
|
||||
TranscriptDelta::Append { row }
|
||||
}
|
||||
|
||||
fn replace(&mut self, id: String, kind: TranscriptRowKind, data: Value) -> TranscriptDelta {
|
||||
let Some(index) = self.row_index.get(&id).copied() else {
|
||||
return self.append(id, kind, data);
|
||||
};
|
||||
let row = &mut self.rows[index];
|
||||
row.kind = kind;
|
||||
row.data = data;
|
||||
TranscriptDelta::Patch { row: row.clone() }
|
||||
}
|
||||
|
||||
fn agent_text(&mut self) {
|
||||
if self.turn_active() {
|
||||
self.state.turn.responding = true;
|
||||
self.state.turn.thinking = false;
|
||||
}
|
||||
}
|
||||
|
||||
fn agent_thought(&mut self) {
|
||||
if self.turn_active() {
|
||||
self.state.turn.responding = true;
|
||||
self.state.turn.thinking = true;
|
||||
}
|
||||
}
|
||||
|
||||
fn track_tool_call(&mut self, tool: &ToolCall) {
|
||||
if self.turn_active() {
|
||||
self.turn_tool_calls.insert(tool.tool_call_id.to_string());
|
||||
self.sync_active_tool(&tool.tool_call_id.to_string());
|
||||
}
|
||||
}
|
||||
|
||||
fn sync_active_tool(&mut self, tool_id: &str) {
|
||||
if !self.turn_active() || !self.turn_tool_calls.contains(tool_id) {
|
||||
return;
|
||||
}
|
||||
let active = self.tools.get(tool_id).is_some_and(|tool| {
|
||||
matches!(
|
||||
tool.status,
|
||||
maestro_acp::schema::ToolCallStatus::Pending
|
||||
| maestro_acp::schema::ToolCallStatus::InProgress
|
||||
)
|
||||
});
|
||||
let active_tool_calls = &mut self.state.turn.active_tool_calls;
|
||||
if active {
|
||||
if !active_tool_calls.iter().any(|id| id == tool_id) {
|
||||
active_tool_calls.push(tool_id.to_owned());
|
||||
active_tool_calls.sort();
|
||||
}
|
||||
} else {
|
||||
active_tool_calls.retain(|id| id != tool_id);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn to_value(value: &impl serde::Serialize) -> Value {
|
||||
serde_json::to_value(value).expect("ACP schema values serialize")
|
||||
}
|
||||
|
||||
fn tool_has_diff(tool: &ToolCall) -> bool {
|
||||
tool.content
|
||||
.iter()
|
||||
.any(|content| matches!(content, maestro_acp::schema::ToolCallContent::Diff(_)))
|
||||
}
|
||||
|
||||
fn append_text(existing: &mut Value, next: &Value) {
|
||||
let Some(existing_text) = existing.pointer_mut("/content/text") else {
|
||||
*existing = next.clone();
|
||||
return;
|
||||
};
|
||||
let Some(next_text) = next.pointer("/content/text").and_then(Value::as_str) else {
|
||||
*existing = next.clone();
|
||||
return;
|
||||
};
|
||||
if let Some(text) = existing_text.as_str() {
|
||||
*existing_text = Value::String(format!("{text}{next_text}"));
|
||||
} else {
|
||||
*existing = next.clone();
|
||||
}
|
||||
}
|
||||
|
||||
fn model_from_options(value: &Value) -> Option<String> {
|
||||
value
|
||||
.get("configOptions")?
|
||||
.as_array()?
|
||||
.iter()
|
||||
.find(|option| {
|
||||
option.get("id").and_then(Value::as_str) == Some("model")
|
||||
|| option.get("category").and_then(Value::as_str) == Some("model")
|
||||
})?
|
||||
.get("currentValue")?
|
||||
.as_str()
|
||||
.map(str::to_owned)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use maestro_acp::schema::SessionNotification;
|
||||
use maestro_protocol::{TranscriptDelta, TranscriptRowKind};
|
||||
|
||||
use super::{Projection, TurnLifecycle};
|
||||
|
||||
fn event(value: serde_json::Value) -> SessionNotification {
|
||||
serde_json::from_value(serde_json::json!({
|
||||
"sessionId": "acp-1",
|
||||
"update": value,
|
||||
}))
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn folds_content_tool_diff_plan_and_notice_rows() {
|
||||
let mut projection = Projection::default();
|
||||
let events = [
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"user_message_chunk","content":{"type":"text","text":"hi"}}),
|
||||
),
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"hello"}}),
|
||||
),
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"think"}}),
|
||||
),
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"tool_call","toolCallId":"read-1","title":"Read","kind":"read"}),
|
||||
),
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"tool_call","toolCallId":"edit-1","title":"Edit","content":[{"type":"diff","path":"x.rs","oldText":"a","newText":"b"}]}),
|
||||
),
|
||||
event(serde_json::json!({"sessionUpdate":"plan","entries":[]})),
|
||||
event(
|
||||
serde_json::json!({"sessionUpdate":"available_commands_update","availableCommands":[]}),
|
||||
),
|
||||
];
|
||||
|
||||
let kinds: Vec<_> = events
|
||||
.iter()
|
||||
.enumerate()
|
||||
.filter_map(|(i, event)| projection.apply((i + 1) as u64, event).transcript)
|
||||
.map(|delta| match delta {
|
||||
TranscriptDelta::Append { row } => row.kind,
|
||||
other => panic!("expected append, got {other:?}"),
|
||||
})
|
||||
.collect();
|
||||
assert_eq!(
|
||||
kinds,
|
||||
[
|
||||
TranscriptRowKind::User,
|
||||
TranscriptRowKind::AgentText,
|
||||
TranscriptRowKind::AgentThought,
|
||||
TranscriptRowKind::ToolCall,
|
||||
TranscriptRowKind::ToolDiff,
|
||||
TranscriptRowKind::Plan,
|
||||
TranscriptRowKind::Notice,
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn tool_update_patches_the_original_stable_row() {
|
||||
let mut projection = Projection::default();
|
||||
let first = projection.apply(
|
||||
4,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":"bash-7", "title":"Run"
|
||||
})),
|
||||
);
|
||||
let updated = projection.apply(
|
||||
5,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call_update", "toolCallId":"bash-7", "status":"completed"
|
||||
})),
|
||||
);
|
||||
let id = match first.transcript.unwrap() {
|
||||
TranscriptDelta::Append { row } => row.id,
|
||||
other => panic!("expected append, got {other:?}"),
|
||||
};
|
||||
match updated.transcript.unwrap() {
|
||||
TranscriptDelta::Patch { row } => {
|
||||
assert_eq!(row.id, id);
|
||||
assert_eq!(row.data["status"], "completed");
|
||||
}
|
||||
other => panic!("expected patch, got {other:?}"),
|
||||
}
|
||||
assert_eq!(projection.snapshot(5).rows.len(), 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn duplicate_tool_calls_patch_one_stable_row() {
|
||||
let mut projection = Projection::default();
|
||||
projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":"bash-7", "title":"Run"
|
||||
})),
|
||||
);
|
||||
let duplicate = projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":"bash-7", "title":"Run again"
|
||||
})),
|
||||
);
|
||||
match duplicate.transcript.unwrap() {
|
||||
TranscriptDelta::Patch { row } => {
|
||||
assert_eq!(row.id, "tool:bash-7");
|
||||
assert_eq!(row.data["title"], "Run again");
|
||||
}
|
||||
other => panic!("expected patch, got {other:?}"),
|
||||
}
|
||||
assert_eq!(projection.snapshot(2).rows.len(), 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn early_tool_update_is_reconciled_when_the_call_arrives() {
|
||||
let mut projection = Projection::default();
|
||||
let early = projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call_update", "toolCallId":"bash-7", "status":"completed"
|
||||
})),
|
||||
);
|
||||
assert_eq!(early.transcript, None);
|
||||
let call = projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":"bash-7", "title":"Run", "status":"pending"
|
||||
})),
|
||||
);
|
||||
match call.transcript.unwrap() {
|
||||
TranscriptDelta::Append { row } => {
|
||||
assert_eq!(row.id, "tool:bash-7");
|
||||
assert_eq!(row.data["status"], "completed");
|
||||
}
|
||||
other => panic!("expected append, got {other:?}"),
|
||||
}
|
||||
assert!(projection.state().turn.active_tool_calls.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unknown_tool_stays_generic_and_keeps_its_raw_name() {
|
||||
let mut projection = Projection::default();
|
||||
let update = projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":"custom-1", "title":"Custom",
|
||||
"name":"vendor.custom", "kind":"future_kind"
|
||||
})),
|
||||
);
|
||||
match update.transcript.unwrap() {
|
||||
TranscriptDelta::Append { row } => {
|
||||
assert_eq!(row.kind, TranscriptRowKind::ToolCall);
|
||||
assert_eq!(row.data["name"], "vendor.custom");
|
||||
}
|
||||
other => panic!("expected generic tool row, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn folds_usage_mode_model_and_plan_into_whole_state() {
|
||||
let mut projection = Projection::default();
|
||||
for (seq, update) in [
|
||||
serde_json::json!({"sessionUpdate":"usage_update","used":12,"size":200}),
|
||||
serde_json::json!({"sessionUpdate":"current_mode_update","currentModeId":"plan"}),
|
||||
serde_json::json!({"sessionUpdate":"config_option_update","configOptions":[{"id":"model","name":"Model","category":"model","type":"select","currentValue":"opus","options":[]}]}),
|
||||
serde_json::json!({"sessionUpdate":"plan","entries":[]}),
|
||||
]
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
{
|
||||
projection.apply((seq + 1) as u64, &event(update));
|
||||
}
|
||||
let state = projection.state();
|
||||
assert_eq!(state.usage.as_ref().unwrap()["used"], 12);
|
||||
assert_eq!(state.context.as_ref().unwrap()["size"], 200);
|
||||
assert_eq!(state.mode.as_deref(), Some("plan"));
|
||||
assert_eq!(state.model.as_deref(), Some("opus"));
|
||||
assert_eq!(
|
||||
state.plan.as_ref().unwrap()["entries"],
|
||||
serde_json::json!([])
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn plans_replace_one_stable_row_and_state() {
|
||||
let mut projection = Projection::default();
|
||||
let first = projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({"sessionUpdate":"plan","entries":[{"content":"first","priority":"high","status":"pending"}]})),
|
||||
);
|
||||
assert!(matches!(
|
||||
first.transcript,
|
||||
Some(TranscriptDelta::Append { .. })
|
||||
));
|
||||
let replacement = projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({"sessionUpdate":"plan","entries":[{"content":"second","priority":"high","status":"completed"}]})),
|
||||
);
|
||||
match replacement.transcript.unwrap() {
|
||||
TranscriptDelta::Patch { row } => {
|
||||
assert_eq!(row.id, "plan");
|
||||
assert_eq!(row.data["entries"][0]["content"], "second");
|
||||
}
|
||||
other => panic!("expected patch, got {other:?}"),
|
||||
}
|
||||
assert_eq!(projection.snapshot(2).rows.len(), 1);
|
||||
assert_eq!(
|
||||
projection.state().plan.unwrap()["entries"][0]["content"],
|
||||
"second"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn turn_lifecycle_gates_chunks_and_normalizes_terminal_states() {
|
||||
let mut projection = Projection::default();
|
||||
projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"replay"}})),
|
||||
);
|
||||
assert_eq!(projection.state().turn, Default::default());
|
||||
|
||||
let (_, _) = projection.begin_turn();
|
||||
assert!(projection.state().turn.responding);
|
||||
assert!(projection.state().turn.thinking);
|
||||
projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"think"}})),
|
||||
);
|
||||
assert!(projection.state().turn.thinking);
|
||||
projection.apply(
|
||||
3,
|
||||
&event(serde_json::json!({"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"answer"}})),
|
||||
);
|
||||
assert!(projection.state().turn.responding);
|
||||
assert!(!projection.state().turn.thinking);
|
||||
|
||||
for terminal in [
|
||||
TurnLifecycle::Finish,
|
||||
TurnLifecycle::Cancel,
|
||||
TurnLifecycle::Failure,
|
||||
] {
|
||||
let (turn, _) = projection.begin_turn();
|
||||
projection.turn_lifecycle(terminal, turn);
|
||||
assert!(!projection.state().turn.responding);
|
||||
assert!(!projection.state().turn.thinking);
|
||||
}
|
||||
}
|
||||
|
||||
fn terminal_turn_drops_unfinished_tools(
|
||||
terminal: TurnLifecycle,
|
||||
unfinished_id: &str,
|
||||
next_id: &str,
|
||||
) {
|
||||
let mut projection = Projection::default();
|
||||
let (turn, _) = projection.begin_turn();
|
||||
projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":unfinished_id,
|
||||
"title":"Unfinished", "status":"in_progress"
|
||||
})),
|
||||
);
|
||||
assert_eq!(projection.state().turn.active_tool_calls, [unfinished_id]);
|
||||
|
||||
projection.turn_lifecycle(terminal, turn);
|
||||
assert!(projection.state().turn.active_tool_calls.is_empty());
|
||||
assert_eq!(projection.snapshot(1).rows.len(), 1);
|
||||
|
||||
projection.begin_turn();
|
||||
projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate":"tool_call", "toolCallId":next_id,
|
||||
"title":"Next", "status":"pending"
|
||||
})),
|
||||
);
|
||||
assert_eq!(projection.state().turn.active_tool_calls, [next_id]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cancelled_turn_does_not_reactivate_unfinished_tools() {
|
||||
terminal_turn_drops_unfinished_tools(TurnLifecycle::Cancel, "cancelled-1", "next-1");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_turn_does_not_reactivate_unfinished_tools() {
|
||||
terminal_turn_drops_unfinished_tools(TurnLifecycle::Failure, "failed-1", "next-1");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn approval_history_survives_pending_cleanup() {
|
||||
let mut projection = Projection::default();
|
||||
let update =
|
||||
projection.request_approval("secret".into(), serde_json::json!({"tool":"bash"}));
|
||||
let TranscriptDelta::Append { row } = update.transcript.unwrap() else {
|
||||
panic!("approval row")
|
||||
};
|
||||
assert_eq!(row.kind, TranscriptRowKind::Approval);
|
||||
assert!(row.data.get("nonce").is_none());
|
||||
assert!(!row.id.contains("secret"));
|
||||
let persisted =
|
||||
serde_json::to_string(&crate::sidecar::PersistedEvent::Approval { row: row.clone() })
|
||||
.unwrap();
|
||||
assert!(!persisted.contains("secret"));
|
||||
assert_eq!(
|
||||
projection.state().pending_approval.unwrap()["nonce"],
|
||||
"secret"
|
||||
);
|
||||
projection.clear_approval();
|
||||
assert!(projection.state().pending_approval.is_none());
|
||||
assert_eq!(projection.snapshot(0).rows, vec![row]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rollback_row_removes_only_that_row_and_keeps_others_addressable() {
|
||||
let mut projection = Projection::default();
|
||||
projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate": "user_message_chunk",
|
||||
"messageId": "m1",
|
||||
"content": {"type": "text", "text": "hi"},
|
||||
})),
|
||||
);
|
||||
let TranscriptDelta::Append { row } = projection
|
||||
.request_approval("nonce".into(), serde_json::json!({"tool": "bash"}))
|
||||
.transcript
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("approval row")
|
||||
};
|
||||
// A row after the one being rolled back, so removing the approval
|
||||
// (index 1) shifts this one from index 2 down to index 1 — proving
|
||||
// `row_index` gets reindexed, not just `rows`.
|
||||
projection.apply(
|
||||
2,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate": "user_message_chunk",
|
||||
"messageId": "m2",
|
||||
"content": {"type": "text", "text": "hey"},
|
||||
})),
|
||||
);
|
||||
assert_eq!(projection.snapshot(0).rows.len(), 3);
|
||||
|
||||
projection.rollback_row(&row.id);
|
||||
|
||||
assert_eq!(projection.snapshot(0).rows.len(), 2);
|
||||
assert_eq!(projection.snapshot(0).rows[0].kind, TranscriptRowKind::User);
|
||||
assert_eq!(projection.snapshot(0).rows[1].kind, TranscriptRowKind::User);
|
||||
|
||||
// The shifted row must still be independently patchable at its new
|
||||
// index.
|
||||
let update = projection.apply(
|
||||
3,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate": "user_message_chunk",
|
||||
"messageId": "m2",
|
||||
"content": {"type": "text", "text": " there"},
|
||||
})),
|
||||
);
|
||||
let TranscriptDelta::Patch { row } = update.transcript.unwrap() else {
|
||||
panic!("patched row")
|
||||
};
|
||||
assert_eq!(row.data.pointer("/content/text").unwrap(), "hey there");
|
||||
assert_eq!(projection.snapshot(0).rows.len(), 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rollback_row_is_a_no_op_for_an_unknown_id() {
|
||||
let mut projection = Projection::default();
|
||||
projection.apply(
|
||||
1,
|
||||
&event(serde_json::json!({
|
||||
"sessionUpdate": "user_message_chunk",
|
||||
"content": {"type": "text", "text": "hi"},
|
||||
})),
|
||||
);
|
||||
projection.rollback_row("approval:does-not-exist");
|
||||
assert_eq!(projection.snapshot(0).rows.len(), 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn recovered_approval_is_historical_not_pending() {
|
||||
let mut live = Projection::default();
|
||||
let TranscriptDelta::Append { row } = live
|
||||
.request_approval("daemon-nonce".into(), serde_json::json!({"tool":"bash"}))
|
||||
.transcript
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("approval row")
|
||||
};
|
||||
let mut recovered = Projection::default();
|
||||
let update = recovered.restore_approval(row.clone());
|
||||
assert_eq!(
|
||||
update.transcript,
|
||||
Some(TranscriptDelta::Append { row: row.clone() })
|
||||
);
|
||||
assert!(update.state.pending_approval.is_none());
|
||||
assert_eq!(recovered.snapshot(0).rows, vec![row]);
|
||||
let replay = serde_json::to_string(&recovered.snapshot(1).rows).unwrap();
|
||||
assert!(!replay.contains("daemon-nonce"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn stale_terminal_turn_cannot_clear_newer_approval() {
|
||||
let mut projection = Projection::default();
|
||||
let (first, _) = projection.begin_turn();
|
||||
projection.turn_lifecycle(TurnLifecycle::Cancel, first);
|
||||
let (second, _) = projection.begin_turn();
|
||||
projection.request_approval("second-nonce".into(), serde_json::json!({"tool":"bash"}));
|
||||
|
||||
assert!(projection
|
||||
.turn_lifecycle(TurnLifecycle::Finish, first)
|
||||
.is_none());
|
||||
assert_eq!(projection.active_turn(), Some(second));
|
||||
assert_eq!(
|
||||
projection.state().pending_approval.unwrap()["nonce"],
|
||||
"second-nonce"
|
||||
);
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -5,10 +5,23 @@
|
||||
//! original `cwd`, command, env, metadata, etc. Files are deleted on
|
||||
//! `KillSession`. Sessions whose sidecar is missing at recovery time are still
|
||||
//! advertised but with empty metadata (handled by the caller, not here).
|
||||
//!
|
||||
//! A structured session (#135) also owns `<id>.events.jsonl` next to its
|
||||
//! sidecar: every `session/update` notification and daemon approval row is one
|
||||
//! JSON object, appended before it is broadcast. The log is the source of
|
||||
//! truth for the transcript; `seq` is the line's 1-based position, so a
|
||||
//! client that holds seq `n` asks for [`EventCursor::Since`]`(n)`. A line
|
||||
//! that does not parse — including the partial line a hard kill leaves at
|
||||
//! the end — keeps its seq and is skipped on read. `delete` removes the log
|
||||
//! with the sidecar; `load_all` never reads one as a sidecar.
|
||||
|
||||
use std::collections::VecDeque;
|
||||
use std::fs::{File, OpenOptions};
|
||||
use std::io::{BufRead, BufReader, Read, Seek, SeekFrom, Write};
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use maestro_protocol::Session;
|
||||
use maestro_acp::schema::SessionNotification;
|
||||
use maestro_protocol::{Session, TranscriptRow};
|
||||
use uuid::Uuid;
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
@@ -38,6 +51,120 @@ impl SidecarStore {
|
||||
self.dir.join(format!("{id}.json"))
|
||||
}
|
||||
|
||||
/// Where the per-session event log lives (#135).
|
||||
pub fn events_path_for(&self, id: Uuid) -> PathBuf {
|
||||
self.dir.join(format!("{id}.events.jsonl"))
|
||||
}
|
||||
|
||||
/// Durable evidence that graceful daemon shutdown ended this structured
|
||||
/// session and the next daemon may resume it.
|
||||
pub fn recovery_path_for(&self, id: Uuid) -> PathBuf {
|
||||
self.dir.join(format!("{id}.recover"))
|
||||
}
|
||||
|
||||
/// Mark `id` as eligible for one structured-session recovery attempt.
|
||||
pub fn mark_for_recovery(&self, id: Uuid) -> Result<(), SidecarError> {
|
||||
std::fs::create_dir_all(&self.dir)?;
|
||||
std::fs::write(self.recovery_path_for(id), [])?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Consume the graceful-shutdown recovery marker for `id`.
|
||||
pub fn take_recovery_marker(&self, id: Uuid) -> Result<bool, SidecarError> {
|
||||
match std::fs::remove_file(self.recovery_path_for(id)) {
|
||||
Ok(()) => Ok(true),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => Ok(false),
|
||||
Err(error) => Err(error.into()),
|
||||
}
|
||||
}
|
||||
|
||||
/// Open the event log for `id` for appending, creating it (and the
|
||||
/// directory) when missing. One handle per live session: the caller
|
||||
/// keeps it for the session's lifetime rather than reopening per
|
||||
/// notification.
|
||||
///
|
||||
/// A log whose last line has no newline — what a hard kill mid-write
|
||||
/// leaves behind — is terminated first, so the next append starts a
|
||||
/// fresh line instead of gluing onto the fragment. The fragment keeps
|
||||
/// the seq of its line and reads as malformed.
|
||||
pub fn open_events(&self, id: Uuid) -> Result<EventLog, SidecarError> {
|
||||
std::fs::create_dir_all(&self.dir)?;
|
||||
let mut file = OpenOptions::new()
|
||||
.create(true)
|
||||
.read(true)
|
||||
.append(true)
|
||||
.open(self.events_path_for(id))?;
|
||||
let mut lines = 0u64;
|
||||
let mut last = None;
|
||||
let mut reader = BufReader::new(&mut file);
|
||||
let mut buf = [0u8; 64 * 1024];
|
||||
loop {
|
||||
let n = reader.read(&mut buf)?;
|
||||
if n == 0 {
|
||||
break;
|
||||
}
|
||||
lines += buf[..n].iter().filter(|&&b| b == b'\n').count() as u64;
|
||||
last = Some(buf[n - 1]);
|
||||
}
|
||||
if last.is_some_and(|b| b != b'\n') {
|
||||
file.write_all(b"\n")?;
|
||||
lines += 1;
|
||||
}
|
||||
file.seek(SeekFrom::End(0))?;
|
||||
Ok(EventLog {
|
||||
file: Box::new(file),
|
||||
last_seq: lines,
|
||||
})
|
||||
}
|
||||
|
||||
/// Read events from the log for `id`, at most `limit`, in ascending seq
|
||||
/// order. A missing log is an empty log. Lines that fail to parse are
|
||||
/// skipped but still consume a seq, so cursors stay stable.
|
||||
pub fn read_events(
|
||||
&self,
|
||||
id: Uuid,
|
||||
cursor: EventCursor,
|
||||
limit: usize,
|
||||
) -> Result<Vec<LoggedEvent>, SidecarError> {
|
||||
let file = match File::open(self.events_path_for(id)) {
|
||||
Ok(f) => f,
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => return Ok(Vec::new()),
|
||||
Err(e) => return Err(e.into()),
|
||||
};
|
||||
if limit == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
let mut out: VecDeque<LoggedEvent> = VecDeque::new();
|
||||
let mut seq = 0u64;
|
||||
for line in BufReader::new(file).split(b'\n') {
|
||||
let line = line?;
|
||||
seq += 1;
|
||||
let keep = match cursor {
|
||||
EventCursor::Since(since) => seq > since,
|
||||
EventCursor::Before(Some(before)) => seq < before,
|
||||
EventCursor::Before(None) => true,
|
||||
};
|
||||
if !keep {
|
||||
if matches!(cursor, EventCursor::Before(Some(_))) {
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
let Ok(event) = PersistedEvent::decode(&line) else {
|
||||
continue;
|
||||
};
|
||||
out.push_back(LoggedEvent { seq, event });
|
||||
match cursor {
|
||||
EventCursor::Since(_) if out.len() >= limit => break,
|
||||
EventCursor::Before(_) if out.len() > limit => {
|
||||
out.pop_front();
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
Ok(out.into())
|
||||
}
|
||||
|
||||
/// Atomically write `session` to `<dir>/<id>.json`. Creates the directory
|
||||
/// if it does not exist.
|
||||
pub fn write(&self, session: &Session) -> Result<(), SidecarError> {
|
||||
@@ -59,13 +186,13 @@ impl SidecarStore {
|
||||
}
|
||||
}
|
||||
|
||||
/// Delete the sidecar for `id`. No-op if it does not exist.
|
||||
/// Delete the sidecar, event log, and recovery marker for `id`. No-op for
|
||||
/// whichever does not exist.
|
||||
pub fn delete(&self, id: Uuid) -> Result<(), SidecarError> {
|
||||
match std::fs::remove_file(self.path_for(id)) {
|
||||
Ok(()) => Ok(()),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(()),
|
||||
Err(e) => Err(e.into()),
|
||||
}
|
||||
remove_if_present(&self.events_path_for(id))?;
|
||||
remove_if_present(&self.dir.join(format!("{id}.approvals.jsonl")))?;
|
||||
remove_if_present(&self.recovery_path_for(id))?;
|
||||
remove_if_present(&self.path_for(id))
|
||||
}
|
||||
|
||||
/// Read every sidecar JSON in the directory. Files that fail to parse are
|
||||
@@ -81,6 +208,8 @@ impl SidecarStore {
|
||||
for entry in entries {
|
||||
let entry = entry?;
|
||||
let path = entry.path();
|
||||
// `.events.jsonl` logs (#135) sit in the same directory and are
|
||||
// never sidecars.
|
||||
if path.extension().and_then(|s| s.to_str()) != Some("json") {
|
||||
continue;
|
||||
}
|
||||
@@ -95,3 +224,419 @@ impl SidecarStore {
|
||||
Ok(out)
|
||||
}
|
||||
}
|
||||
|
||||
fn remove_if_present(path: &Path) -> Result<(), SidecarError> {
|
||||
match std::fs::remove_file(path) {
|
||||
Ok(()) => Ok(()),
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(()),
|
||||
Err(e) => Err(e.into()),
|
||||
}
|
||||
}
|
||||
|
||||
/// Which slice of a session's event log to read.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum EventCursor {
|
||||
/// Forward: events with `seq` strictly greater than the cursor, the
|
||||
/// first `limit` of them. `Since(0)` is the whole log from the start.
|
||||
/// What a client catching up after a reconnect asks for.
|
||||
Since(u64),
|
||||
/// Backward: events with `seq` strictly less than the cursor, the last
|
||||
/// `limit` of them, still returned in ascending order. `None` means the
|
||||
/// tail of the log, for a first paint. The next page passes the smallest
|
||||
/// seq it received.
|
||||
Before(Option<u64>),
|
||||
}
|
||||
|
||||
/// One line of a session's event log.
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct LoggedEvent {
|
||||
/// 1-based line position in the log; the cursor for [`EventCursor`].
|
||||
pub seq: u64,
|
||||
pub event: PersistedEvent,
|
||||
}
|
||||
|
||||
/// A single entry in the structured event history.
|
||||
///
|
||||
/// ACP notifications retain their original JSON representation, so existing
|
||||
/// event logs remain readable. Daemon-generated rows use an envelope so they
|
||||
/// can share the same cursor sequence without pretending to be ACP traffic.
|
||||
#[derive(Debug, Clone, PartialEq, serde::Serialize, serde::Deserialize)]
|
||||
#[serde(tag = "maestroEvent", rename_all = "snake_case")]
|
||||
pub enum PersistedEvent {
|
||||
Approval {
|
||||
row: TranscriptRow,
|
||||
},
|
||||
#[serde(skip)]
|
||||
Notification(Box<SessionNotification>),
|
||||
}
|
||||
|
||||
impl PersistedEvent {
|
||||
fn decode(line: &[u8]) -> Result<Self, serde_json::Error> {
|
||||
serde_json::from_slice::<SessionNotification>(line)
|
||||
.map(|notification| Self::Notification(Box::new(notification)))
|
||||
.or_else(|_| serde_json::from_slice(line))
|
||||
}
|
||||
}
|
||||
|
||||
impl From<SessionNotification> for PersistedEvent {
|
||||
fn from(notification: SessionNotification) -> Self {
|
||||
Self::Notification(Box::new(notification))
|
||||
}
|
||||
}
|
||||
|
||||
impl From<&SessionNotification> for PersistedEvent {
|
||||
fn from(notification: &SessionNotification) -> Self {
|
||||
Self::Notification(Box::new(notification.clone()))
|
||||
}
|
||||
}
|
||||
|
||||
impl From<&PersistedEvent> for PersistedEvent {
|
||||
fn from(event: &PersistedEvent) -> Self {
|
||||
event.clone()
|
||||
}
|
||||
}
|
||||
|
||||
/// What an [`EventLog`] appends onto: something seekable by length and
|
||||
/// truncatable back to one, so a failed append can be rolled off the end
|
||||
/// again. A real [`File`] in production; an in-memory fault double in tests
|
||||
/// (#184) — the same [`EventLog::append`] rollback logic runs over both, so
|
||||
/// the behavior under test is the production behavior, not a stand-in for
|
||||
/// it.
|
||||
pub(crate) trait LogSink: Write + Send {
|
||||
fn len(&mut self) -> std::io::Result<u64>;
|
||||
fn truncate(&mut self, len: u64) -> std::io::Result<()>;
|
||||
}
|
||||
|
||||
impl LogSink for File {
|
||||
fn len(&mut self) -> std::io::Result<u64> {
|
||||
Ok(self.metadata()?.len())
|
||||
}
|
||||
|
||||
fn truncate(&mut self, len: u64) -> std::io::Result<()> {
|
||||
self.set_len(len)
|
||||
}
|
||||
}
|
||||
|
||||
/// Outcome of a failed [`EventLog::append`].
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum AppendError {
|
||||
/// The write or flush failed, but the log was rolled back to exactly the
|
||||
/// byte it was at before the call: `last_seq` and the file agree, and
|
||||
/// this same [`EventLog`] is safe to keep appending to. The event itself
|
||||
/// was never persisted or broadcast.
|
||||
#[error("event append failed, rolled back cleanly: {0}")]
|
||||
Failed(#[source] SidecarError),
|
||||
/// The append failed *and* the rollback did not restore the log to its
|
||||
/// prior length, so the file's line count and `last_seq` may now
|
||||
/// disagree. The caller must not append to this [`EventLog`] again —
|
||||
/// treat the session as dead rather than promise consistency it cannot
|
||||
/// keep.
|
||||
#[error("event append failed ({cause}) and rollback did not restore consistency ({rollback})")]
|
||||
Fatal {
|
||||
cause: SidecarError,
|
||||
rollback: SidecarError,
|
||||
},
|
||||
}
|
||||
|
||||
impl From<SidecarError> for AppendError {
|
||||
fn from(error: SidecarError) -> Self {
|
||||
AppendError::Failed(error)
|
||||
}
|
||||
}
|
||||
|
||||
/// An open, append-only handle on one session's event log. Obtained from
|
||||
/// [`SidecarStore::open_events`]; held for the session's lifetime.
|
||||
pub struct EventLog {
|
||||
file: Box<dyn LogSink>,
|
||||
last_seq: u64,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for EventLog {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.debug_struct("EventLog")
|
||||
.field("last_seq", &self.last_seq)
|
||||
.finish_non_exhaustive()
|
||||
}
|
||||
}
|
||||
|
||||
impl EventLog {
|
||||
/// Wrap an arbitrary sink as an [`EventLog`], for tests that need to
|
||||
/// inject a deterministic append failure (#184) — a partial write, a
|
||||
/// flush that fails after the bytes are already down, or a rollback that
|
||||
/// cannot itself complete.
|
||||
#[cfg(test)]
|
||||
pub(crate) fn for_test(file: impl LogSink + 'static, last_seq: u64) -> Self {
|
||||
Self {
|
||||
file: Box::new(file),
|
||||
last_seq,
|
||||
}
|
||||
}
|
||||
|
||||
/// The seq of the last line, `0` for an empty log.
|
||||
pub fn last_seq(&self) -> u64 {
|
||||
self.last_seq
|
||||
}
|
||||
|
||||
/// Append one notification as a line and return its seq. The line is
|
||||
/// handed to the kernel in a single write before this returns, so a
|
||||
/// caller that broadcasts afterwards never announces an event the log
|
||||
/// would not replay — short of the machine losing power.
|
||||
///
|
||||
/// A `write_all` that errors partway can leave an unterminated prefix on
|
||||
/// disk; a `flush` that errors after a *complete* `write_all` leaves
|
||||
/// ambiguity about whether that full, well-formed line should count —
|
||||
/// counting it would silently shift every later seq by one, since
|
||||
/// `last_seq` was never bumped for it. Both cases are rolled back to the
|
||||
/// exact pre-append length before returning, so `last_seq` and the file
|
||||
/// never disagree and the same [`EventLog`] can be appended to again
|
||||
/// immediately. If the rollback itself fails, the log's consistency can
|
||||
/// no longer be promised and [`AppendError::Fatal`] is returned instead.
|
||||
pub fn append(&mut self, event: impl Into<PersistedEvent>) -> Result<u64, AppendError> {
|
||||
let event = event.into();
|
||||
let mut line = match &event {
|
||||
PersistedEvent::Notification(notification) => serde_json::to_vec(notification)
|
||||
.map_err(|e| AppendError::from(SidecarError::from(e)))?,
|
||||
_ => {
|
||||
serde_json::to_vec(&event).map_err(|e| AppendError::from(SidecarError::from(e)))?
|
||||
}
|
||||
};
|
||||
line.push(b'\n');
|
||||
|
||||
let pre_len = self
|
||||
.file
|
||||
.len()
|
||||
.map_err(|e| AppendError::from(SidecarError::from(e)))?;
|
||||
|
||||
if let Err(cause) = self.file.write_all(&line) {
|
||||
return Err(self.rollback_after(pre_len, cause));
|
||||
}
|
||||
if let Err(cause) = self.file.flush() {
|
||||
return Err(self.rollback_after(pre_len, cause));
|
||||
}
|
||||
|
||||
self.last_seq += 1;
|
||||
Ok(self.last_seq)
|
||||
}
|
||||
|
||||
fn rollback_after(&mut self, pre_len: u64, cause: std::io::Error) -> AppendError {
|
||||
match self.file.truncate(pre_len) {
|
||||
Ok(()) => AppendError::Failed(SidecarError::Io(cause)),
|
||||
Err(rollback) => AppendError::Fatal {
|
||||
cause: SidecarError::Io(cause),
|
||||
rollback: SidecarError::Io(rollback),
|
||||
},
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Bytes shared between a [`FaultyLogSink`] moved into an [`EventLog`] and
|
||||
/// the test that planted it, so the test can inspect what actually ended up
|
||||
/// on the "disk" after a fault without reaching into `EventLog`'s private
|
||||
/// `file` field.
|
||||
#[cfg(test)]
|
||||
#[derive(Clone, Default)]
|
||||
pub(crate) struct SharedBuf(std::sync::Arc<std::sync::Mutex<Vec<u8>>>);
|
||||
|
||||
#[cfg(test)]
|
||||
impl SharedBuf {
|
||||
pub(crate) fn snapshot(&self) -> Vec<u8> {
|
||||
self.0.lock().unwrap().clone()
|
||||
}
|
||||
}
|
||||
|
||||
/// An in-memory [`LogSink`] double that injects one deterministic fault — a
|
||||
/// short write, a flush that fails after a full write, or a rollback that
|
||||
/// cannot itself complete — then behaves like a healthy sink from then on.
|
||||
/// Lets a test prove the *same* [`EventLog`] recovers, rather than one with a
|
||||
/// handle swapped in from a healthy disk, which production never does
|
||||
/// (#184).
|
||||
#[cfg(test)]
|
||||
#[derive(Default)]
|
||||
pub(crate) struct FaultyLogSink {
|
||||
pub(crate) buf: SharedBuf,
|
||||
/// Accept this many bytes on the next `write` call, then fail the
|
||||
/// *following* call — a short write followed by an error, exactly what
|
||||
/// `write_all` sees from a real fd that dies mid-line. `Write::write`
|
||||
/// must not report an error on a call that made partial progress, so
|
||||
/// the fault is delivered one call later, via `pending_write_error`.
|
||||
pub(crate) fail_write_after: Option<usize>,
|
||||
pub(crate) pending_write_error: bool,
|
||||
pub(crate) fail_flush_once: bool,
|
||||
pub(crate) fail_truncate: bool,
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
impl Write for FaultyLogSink {
|
||||
fn write(&mut self, data: &[u8]) -> std::io::Result<usize> {
|
||||
if self.pending_write_error {
|
||||
self.pending_write_error = false;
|
||||
return Err(std::io::Error::other("fault: write failed mid-line"));
|
||||
}
|
||||
if let Some(allowed) = self.fail_write_after.take() {
|
||||
let allowed = allowed.min(data.len());
|
||||
if allowed == 0 {
|
||||
// No progress was made, so it's fine to report the error
|
||||
// from this same call.
|
||||
return Err(std::io::Error::other("fault: write failed mid-line"));
|
||||
}
|
||||
self.buf
|
||||
.0
|
||||
.lock()
|
||||
.unwrap()
|
||||
.extend_from_slice(&data[..allowed]);
|
||||
self.pending_write_error = true;
|
||||
return Ok(allowed);
|
||||
}
|
||||
self.buf.0.lock().unwrap().extend_from_slice(data);
|
||||
Ok(data.len())
|
||||
}
|
||||
|
||||
fn flush(&mut self) -> std::io::Result<()> {
|
||||
if self.fail_flush_once {
|
||||
self.fail_flush_once = false;
|
||||
return Err(std::io::Error::other(
|
||||
"fault: flush failed after a full write",
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
impl LogSink for FaultyLogSink {
|
||||
fn len(&mut self) -> std::io::Result<u64> {
|
||||
Ok(self.buf.0.lock().unwrap().len() as u64)
|
||||
}
|
||||
|
||||
fn truncate(&mut self, len: u64) -> std::io::Result<()> {
|
||||
if self.fail_truncate {
|
||||
return Err(std::io::Error::other("fault: rollback truncate failed"));
|
||||
}
|
||||
self.buf.0.lock().unwrap().truncate(len as usize);
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn sample_event(id: &str) -> PersistedEvent {
|
||||
PersistedEvent::Approval {
|
||||
row: TranscriptRow {
|
||||
id: id.to_owned(),
|
||||
kind: maestro_protocol::TranscriptRowKind::Approval,
|
||||
data: serde_json::json!({"tool": "bash"}),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/// Replays `bytes` as a real on-disk log via the production read path,
|
||||
/// so "live and durable agree" is checked with the same code a
|
||||
/// reconnecting client would hit, not a hand-rolled line splitter.
|
||||
fn replay(bytes: &[u8]) -> Vec<LoggedEvent> {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
std::fs::create_dir_all(store.dir()).unwrap();
|
||||
std::fs::write(store.events_path_for(id), bytes).unwrap();
|
||||
store.read_events(id, EventCursor::Since(0), 100).unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn append_rolls_back_a_partial_write_and_the_same_instance_recovers() {
|
||||
let buf = SharedBuf::default();
|
||||
let writer = FaultyLogSink {
|
||||
buf: buf.clone(),
|
||||
fail_write_after: Some(5),
|
||||
..Default::default()
|
||||
};
|
||||
let mut log = EventLog::for_test(writer, 0);
|
||||
|
||||
let err = log.append(sample_event("r1")).unwrap_err();
|
||||
assert!(
|
||||
matches!(err, AppendError::Failed(_)),
|
||||
"a repairable rollback must not be reported fatal"
|
||||
);
|
||||
assert_eq!(log.last_seq(), 0, "cursor must stay put on a failed append");
|
||||
assert!(
|
||||
buf.snapshot().is_empty(),
|
||||
"the partial prefix a failed write_all leaves behind must be truncated away"
|
||||
);
|
||||
|
||||
let seq = log
|
||||
.append(sample_event("r1"))
|
||||
.expect("the same instance must be able to append again after a clean rollback");
|
||||
assert_eq!(seq, 1);
|
||||
assert_eq!(log.last_seq(), 1);
|
||||
|
||||
let bytes = buf.snapshot();
|
||||
assert_eq!(
|
||||
bytes.iter().filter(|&&b| b == b'\n').count(),
|
||||
1,
|
||||
"exactly one well-formed line, not a partial prefix glued to the recovered append"
|
||||
);
|
||||
|
||||
let replayed = replay(&bytes);
|
||||
assert_eq!(replayed.len(), 1);
|
||||
assert_eq!(replayed[0].seq, log.last_seq());
|
||||
let PersistedEvent::Approval { row } = &replayed[0].event else {
|
||||
panic!("approval event");
|
||||
};
|
||||
assert_eq!(row.id, "r1");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn append_rolls_back_when_flush_fails_after_a_full_write() {
|
||||
let buf = SharedBuf::default();
|
||||
let writer = FaultyLogSink {
|
||||
buf: buf.clone(),
|
||||
fail_flush_once: true,
|
||||
..Default::default()
|
||||
};
|
||||
let mut log = EventLog::for_test(writer, 0);
|
||||
|
||||
let err = log.append(sample_event("r1")).unwrap_err();
|
||||
assert!(matches!(err, AppendError::Failed(_)));
|
||||
assert_eq!(log.last_seq(), 0);
|
||||
assert!(
|
||||
buf.snapshot().is_empty(),
|
||||
"a full-but-unflushed line must not survive uncounted by last_seq — it would \
|
||||
silently shift every later seq by one"
|
||||
);
|
||||
|
||||
let seq = log
|
||||
.append(sample_event("r1"))
|
||||
.expect("the same instance must recover once flush stops failing");
|
||||
assert_eq!(seq, 1);
|
||||
|
||||
let bytes = buf.snapshot();
|
||||
let replayed = replay(&bytes);
|
||||
assert_eq!(replayed.len(), 1);
|
||||
assert_eq!(replayed[0].seq, log.last_seq());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn append_reports_fatal_when_rollback_cannot_restore_consistency() {
|
||||
let buf = SharedBuf::default();
|
||||
let writer = FaultyLogSink {
|
||||
buf,
|
||||
fail_write_after: Some(3),
|
||||
fail_truncate: true,
|
||||
..Default::default()
|
||||
};
|
||||
let mut log = EventLog::for_test(writer, 0);
|
||||
|
||||
let err = log.append(sample_event("r1")).unwrap_err();
|
||||
assert!(
|
||||
matches!(err, AppendError::Fatal { .. }),
|
||||
"an unrepairable rollback must be surfaced as fatal, never silently treated as \
|
||||
a clean recoverable failure"
|
||||
);
|
||||
assert_eq!(
|
||||
log.last_seq(),
|
||||
0,
|
||||
"a fatal append must not advance the cursor either"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,11 +6,20 @@ mod common;
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::Arc;
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use common::{wait_for_async, DaemonFixture};
|
||||
use common::{init_bare_repo, init_repo, push_all_to_origin, wait_for_async, DaemonFixture};
|
||||
use maestro_acp::schema::{ContentBlock, SessionUpdate};
|
||||
use maestro_acp::{ADAPTER_BIN, INSTALL_COMMAND};
|
||||
use maestro_protocol::{ActivityState, CreateSessionRequest, SessionStatus, SessionView};
|
||||
use maestro_daemon::projection::TurnLifecycle;
|
||||
use maestro_daemon::sidecar::{EventCursor, SidecarStore};
|
||||
use maestro_daemon::worktree::WorktreeManager;
|
||||
use maestro_daemon::SessionManager;
|
||||
use maestro_protocol::{
|
||||
ActivityState, CreateSessionRequest, SessionStatus, SessionView, TranscriptDelta,
|
||||
TranscriptRowKind, WorktreeSpec,
|
||||
};
|
||||
use tempfile::TempDir;
|
||||
|
||||
fn fake_agent() -> PathBuf {
|
||||
@@ -61,13 +70,31 @@ impl Fake {
|
||||
fn pid(&self) -> u32 {
|
||||
self.log()
|
||||
.lines()
|
||||
.find_map(|l| l.strip_prefix("start pid="))
|
||||
.and_then(|rest| rest.split(' ').next())
|
||||
.and_then(|p| p.parse().ok())
|
||||
.filter_map(|line| {
|
||||
line.strip_prefix("start pid=")?
|
||||
.split(' ')
|
||||
.next()?
|
||||
.parse()
|
||||
.ok()
|
||||
})
|
||||
.next_back()
|
||||
.expect("pid in log")
|
||||
}
|
||||
}
|
||||
|
||||
fn event_text(event: &maestro_daemon::sidecar::LoggedEvent) -> &str {
|
||||
let maestro_daemon::sidecar::PersistedEvent::Notification(notification) = &event.event else {
|
||||
panic!("unexpected daemon event")
|
||||
};
|
||||
match ¬ification.update {
|
||||
SessionUpdate::AgentMessageChunk(chunk) => match &chunk.content {
|
||||
ContentBlock::Text(text) => &text.text,
|
||||
other => panic!("unexpected content {other:?}"),
|
||||
},
|
||||
other => panic!("unexpected update {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
fn structured(cwd: &Path, env: HashMap<String, String>) -> CreateSessionRequest {
|
||||
CreateSessionRequest {
|
||||
view: SessionView::Structured,
|
||||
@@ -109,6 +136,7 @@ async fn structured_spawn_starts_the_adapter_in_cwd_with_session_env() {
|
||||
|
||||
assert_eq!(session.view, SessionView::Structured);
|
||||
assert_eq!(session.status, SessionStatus::Running);
|
||||
assert_eq!(session.activity, ActivityState::Idle);
|
||||
let acp_id = session.acp_session_id.clone().expect("acp session id");
|
||||
assert!(acp_id.starts_with("fake-"), "{acp_id}");
|
||||
|
||||
@@ -140,20 +168,540 @@ async fn structured_spawn_starts_the_adapter_in_cwd_with_session_env() {
|
||||
.unwrap();
|
||||
assert_eq!(sidecar.acp_session_id.as_deref(), Some(acp_id.as_str()));
|
||||
|
||||
// The raw notification stream is reachable for #135, handed out once.
|
||||
let mut updates = fx
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fx.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| !events.is_empty())
|
||||
})
|
||||
.await;
|
||||
|
||||
// Live delivery happens only after the notification is durable.
|
||||
let (replay, mut updates) = fx
|
||||
.manager
|
||||
.take_acp_updates(session.id)
|
||||
.subscribe_acp_events_with_replay(session.id, EventCursor::Since(0), 10)
|
||||
.await
|
||||
.expect("updates receiver");
|
||||
assert!(fx.manager.take_acp_updates(session.id).await.is_none());
|
||||
let first = tokio::time::timeout(Duration::from_secs(5), updates.recv())
|
||||
.expect("replay read")
|
||||
.expect("event subscription");
|
||||
assert_eq!(replay.len(), 1);
|
||||
assert!(updates.try_recv().is_err(), "replay duplicated onto live");
|
||||
unsafe {
|
||||
libc::kill(fake.pid() as libc::pid_t, libc::SIGUSR1);
|
||||
}
|
||||
let live = tokio::time::timeout(Duration::from_secs(5), updates.recv())
|
||||
.await
|
||||
.expect("an update within 5s")
|
||||
.expect("channel open");
|
||||
assert_eq!(first.session_id.0.as_ref(), acp_id);
|
||||
.expect("broadcast open");
|
||||
assert_eq!(event_text(&live), "tick 1");
|
||||
let stored = fx
|
||||
.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(live.seq - 1), 1)
|
||||
.expect("read event logged before broadcast");
|
||||
assert_eq!(stored, vec![live]);
|
||||
|
||||
fx.manager.kill(session.id, false).await.expect("kill");
|
||||
assert!(!fx
|
||||
.sidecar_dir()
|
||||
.join(format!("{}.events.jsonl", session.id))
|
||||
.exists());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_activity_tracks_turn_completion_and_failure() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_DELAY_PROMPT_MS".into(), "100".into());
|
||||
env.insert("FAKE_ACP_PROMPT_FAIL_ONCE".into(), "1".into());
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(matches!(
|
||||
fx.manager
|
||||
.queue_acp_prompt(session.id, "fail".into())
|
||||
.await
|
||||
.unwrap(),
|
||||
maestro_daemon::session::QueueAcpPrompt::Queued
|
||||
));
|
||||
assert_eq!(
|
||||
fx.manager
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.unwrap()
|
||||
.activity,
|
||||
ActivityState::Active
|
||||
);
|
||||
wait_for_async(Duration::from_secs(2), || async {
|
||||
fx.manager
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.is_some_and(|candidate| candidate.activity == ActivityState::Error)
|
||||
})
|
||||
.await;
|
||||
|
||||
assert!(matches!(
|
||||
fx.manager
|
||||
.queue_acp_prompt(session.id, "succeed".into())
|
||||
.await
|
||||
.unwrap(),
|
||||
maestro_daemon::session::QueueAcpPrompt::Queued
|
||||
));
|
||||
assert_eq!(
|
||||
fx.manager
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.unwrap()
|
||||
.activity,
|
||||
ActivityState::Active
|
||||
);
|
||||
wait_for_async(Duration::from_secs(2), || async {
|
||||
fx.manager
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.is_some_and(|candidate| candidate.activity == ActivityState::Idle)
|
||||
})
|
||||
.await;
|
||||
|
||||
fx.manager.kill(session.id, false).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn projection_snapshot_and_live_stream_share_one_fold() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), fake.env()))
|
||||
.await
|
||||
.expect("create");
|
||||
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fx.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| events.len() == 1)
|
||||
})
|
||||
.await;
|
||||
|
||||
// The cursor does not truncate either projection: a reconnect needs the
|
||||
// source row for future patches and whole reduced state from the session.
|
||||
let (snapshot, state, mut live) = fx
|
||||
.manager
|
||||
.subscribe_acp_projection(session.id, EventCursor::Since(1))
|
||||
.await
|
||||
.expect("projection subscription")
|
||||
.expect("structured session");
|
||||
assert_eq!(snapshot.cursor, 1);
|
||||
assert_eq!(snapshot.rows.len(), 1);
|
||||
assert_eq!(snapshot.rows[0].kind, TranscriptRowKind::AgentText);
|
||||
assert_eq!(state.turn, Default::default());
|
||||
|
||||
let maestro_daemon::session::BeginAcpTurn::Started(_, turn) = fx
|
||||
.manager
|
||||
.begin_acp_turn(session.id)
|
||||
.await
|
||||
.expect("begin lifecycle")
|
||||
else {
|
||||
panic!("structured turn should start");
|
||||
};
|
||||
let begin = tokio::time::timeout(Duration::from_secs(5), live.recv())
|
||||
.await
|
||||
.expect("begin lifecycle broadcast")
|
||||
.expect("projection broadcast");
|
||||
assert_eq!(begin.transcript, None);
|
||||
assert!(begin.state.turn.responding);
|
||||
assert!(begin.state.turn.thinking);
|
||||
|
||||
unsafe {
|
||||
libc::kill(fake.pid() as libc::pid_t, libc::SIGUSR1);
|
||||
}
|
||||
let agent_update = tokio::time::timeout(Duration::from_secs(5), live.recv())
|
||||
.await
|
||||
.expect("live projection")
|
||||
.expect("projection broadcast");
|
||||
match agent_update.transcript {
|
||||
Some(TranscriptDelta::Append { row }) => {
|
||||
assert_eq!(row.kind, TranscriptRowKind::AgentText);
|
||||
assert_eq!(row.data["content"]["text"], "tick 1");
|
||||
}
|
||||
other => panic!("expected one appended transcript row, got {other:?}"),
|
||||
}
|
||||
assert!(agent_update.state.turn.responding);
|
||||
assert!(!agent_update.state.turn.thinking);
|
||||
|
||||
assert!(fx
|
||||
.manager
|
||||
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Finish, turn)
|
||||
.await
|
||||
.expect("finish lifecycle"));
|
||||
let finish = tokio::time::timeout(Duration::from_secs(5), live.recv())
|
||||
.await
|
||||
.expect("finish lifecycle broadcast")
|
||||
.expect("projection broadcast");
|
||||
assert_eq!(finish.transcript, None);
|
||||
assert_eq!(finish.state.turn, Default::default());
|
||||
|
||||
fx.manager.kill(session.id, false).await.expect("kill");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn stale_turn_completion_cannot_end_the_next_turn() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), fake.env()))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let maestro_daemon::session::BeginAcpTurn::Started(_, first) =
|
||||
fx.manager.begin_acp_turn(session.id).await.unwrap()
|
||||
else {
|
||||
panic!("first turn should start");
|
||||
};
|
||||
assert!(fx.manager.cancel_acp_turn(session.id).await.unwrap());
|
||||
let maestro_daemon::session::BeginAcpTurn::Started(_, second) =
|
||||
fx.manager.begin_acp_turn(session.id).await.unwrap()
|
||||
else {
|
||||
panic!("second turn should start");
|
||||
};
|
||||
assert!(second > first);
|
||||
assert!(!fx
|
||||
.manager
|
||||
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Finish, first)
|
||||
.await
|
||||
.unwrap());
|
||||
assert!(matches!(
|
||||
fx.manager.begin_acp_turn(session.id).await.unwrap(),
|
||||
maestro_daemon::session::BeginAcpTurn::InFlight
|
||||
));
|
||||
assert!(fx
|
||||
.manager
|
||||
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Finish, second)
|
||||
.await
|
||||
.unwrap());
|
||||
|
||||
fx.manager.kill(session.id, false).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn cancelled_prompt_that_never_settles_fails_the_session() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_PERMISSION_AFTER_CANCEL".into(), "1".into());
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(matches!(
|
||||
fx.manager
|
||||
.queue_acp_prompt(session.id, "first".into())
|
||||
.await
|
||||
.unwrap(),
|
||||
maestro_daemon::session::QueueAcpPrompt::Queued
|
||||
));
|
||||
assert!(fx.manager.cancel_acp_turn(session.id).await.unwrap());
|
||||
let second = fx
|
||||
.manager
|
||||
.queue_acp_prompt(session.id, "second".into())
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
matches!(second, maestro_daemon::session::QueueAcpPrompt::Unavailable),
|
||||
"{second:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
fx.manager.status(session.id).await,
|
||||
Some(SessionStatus::Dead)
|
||||
);
|
||||
assert!(!fake.log().contains("permission response"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn cancellation_settlement_allows_the_next_prompt_permission() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_REQUEST_PERMISSION".into(), "1".into());
|
||||
env.insert("FAKE_ACP_CANCEL_SETTLES".into(), "1".into());
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(matches!(
|
||||
fx.manager
|
||||
.queue_acp_prompt(session.id, "first".into())
|
||||
.await
|
||||
.unwrap(),
|
||||
maestro_daemon::session::QueueAcpPrompt::Queued
|
||||
));
|
||||
assert!(fx.manager.cancel_acp_turn(session.id).await.unwrap());
|
||||
assert!(matches!(
|
||||
fx.manager
|
||||
.queue_acp_prompt(session.id, "second".into())
|
||||
.await
|
||||
.unwrap(),
|
||||
maestro_daemon::session::QueueAcpPrompt::Queued
|
||||
));
|
||||
|
||||
let nonce = tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
let (_, state, _) = fx
|
||||
.manager
|
||||
.subscribe_acp_projection(session.id, EventCursor::Since(0))
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
if let Some(pending) = state.pending_approval {
|
||||
break pending["nonce"].as_str().unwrap().to_owned();
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(fx
|
||||
.manager
|
||||
.resolve_acp_approval(
|
||||
session.id,
|
||||
&nonce,
|
||||
maestro_daemon::session::ApprovalDecision::AllowOnce,
|
||||
)
|
||||
.await
|
||||
.unwrap()
|
||||
.is_some());
|
||||
wait_for_async(Duration::from_secs(2), || {
|
||||
let log = fake.log();
|
||||
async move { log.contains("permission response") }
|
||||
})
|
||||
.await;
|
||||
fx.manager.kill(session.id, false).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn recovery_loads_the_acp_session_without_duplicating_history() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_LOAD_REPLAY".into(), "2".into());
|
||||
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.expect("create");
|
||||
let acp_id = session.acp_session_id.clone().expect("acp id");
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fx.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| events.len() == 1)
|
||||
})
|
||||
.await;
|
||||
unsafe {
|
||||
libc::kill(fake.pid() as libc::pid_t, libc::SIGUSR1);
|
||||
}
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fx.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| events.len() == 2)
|
||||
})
|
||||
.await;
|
||||
|
||||
let old_pid = fake.pid();
|
||||
fx.manager.shutdown().await;
|
||||
wait_for_exit(old_pid).await;
|
||||
assert!(
|
||||
fx.sidecar_dir()
|
||||
.join(format!("{}.recover", session.id))
|
||||
.exists(),
|
||||
"graceful shutdown must record recovery provenance"
|
||||
);
|
||||
|
||||
let revived = SessionManager::new(
|
||||
Arc::new(fx.tmux.tmux.clone()),
|
||||
SidecarStore::new(fx.sidecar_dir()),
|
||||
WorktreeManager::new(None),
|
||||
fx.fifo_dir(),
|
||||
);
|
||||
assert_eq!(revived.recover().await.expect("recover"), 1);
|
||||
assert_eq!(
|
||||
revived.status(session.id).await,
|
||||
Some(SessionStatus::Running)
|
||||
);
|
||||
assert_eq!(
|
||||
revived
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.unwrap()
|
||||
.activity,
|
||||
ActivityState::Idle
|
||||
);
|
||||
let log = fake.log();
|
||||
assert!(
|
||||
log.contains(&format!("recv session/load sessionId={acp_id}")),
|
||||
"{log}"
|
||||
);
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
revived
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| events.len() == 3)
|
||||
})
|
||||
.await;
|
||||
|
||||
let (replay, mut live) = revived
|
||||
.subscribe_acp_events_with_replay(session.id, EventCursor::Since(0), 10)
|
||||
.await
|
||||
.expect("replay read")
|
||||
.expect("recovered event subscription");
|
||||
assert_eq!(replay.len(), 3);
|
||||
assert!(live.try_recv().is_err(), "replay duplicated onto live");
|
||||
let new_pid = fake.pid();
|
||||
assert_ne!(new_pid, old_pid);
|
||||
unsafe {
|
||||
libc::kill(new_pid as libc::pid_t, libc::SIGUSR1);
|
||||
}
|
||||
let event = tokio::time::timeout(Duration::from_secs(5), live.recv())
|
||||
.await
|
||||
.expect("live event after recovery")
|
||||
.expect("broadcast open");
|
||||
assert_eq!(event.seq, 4);
|
||||
assert_eq!(event_text(&event), "tick 1");
|
||||
|
||||
let stored = revived
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.expect("recovered log");
|
||||
assert_eq!(stored.len(), 4, "session/load replay must not be appended");
|
||||
assert_eq!(
|
||||
stored.iter().map(event_text).collect::<Vec<_>>(),
|
||||
["hello from fake", "tick 1", "hello after load", "tick 1"]
|
||||
);
|
||||
|
||||
revived.kill(session.id, false).await.expect("kill");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn shutdown_preserves_a_pristine_structured_worktree_for_recovery() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let repo = TempDir::new().unwrap();
|
||||
init_repo(repo.path());
|
||||
let origin = TempDir::new().unwrap();
|
||||
init_bare_repo(origin.path());
|
||||
|
||||
let branch = "feature/restart";
|
||||
let worktree = repo
|
||||
.path()
|
||||
.join("worktrees")
|
||||
.join("feature")
|
||||
.join("restart");
|
||||
let session = fx
|
||||
.manager
|
||||
.create(CreateSessionRequest {
|
||||
view: SessionView::Structured,
|
||||
cwd: repo.path().to_path_buf(),
|
||||
command: "claude".into(),
|
||||
env: fake.env(),
|
||||
metadata: HashMap::new(),
|
||||
worktree: Some(WorktreeSpec {
|
||||
base_repo: repo.path().to_path_buf(),
|
||||
branch: branch.into(),
|
||||
create_branch: true,
|
||||
}),
|
||||
})
|
||||
.await
|
||||
.expect("create");
|
||||
assert_eq!(session.cwd, worktree);
|
||||
push_all_to_origin(repo.path(), origin.path());
|
||||
|
||||
fx.manager.shutdown().await;
|
||||
|
||||
assert!(
|
||||
worktree.is_dir(),
|
||||
"shutdown must not settle a pristine worktree"
|
||||
);
|
||||
let sidecar: maestro_protocol::Session = serde_json::from_slice(
|
||||
&std::fs::read(fx.sidecar_dir().join(format!("{}.json", session.id))).unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
sidecar.worktree.as_ref().map(|wt| &wt.path),
|
||||
Some(&worktree)
|
||||
);
|
||||
|
||||
let revived = SessionManager::new(
|
||||
Arc::new(fx.tmux.tmux.clone()),
|
||||
SidecarStore::new(fx.sidecar_dir()),
|
||||
WorktreeManager::new(None),
|
||||
fx.fifo_dir(),
|
||||
);
|
||||
assert_eq!(revived.recover().await.expect("recover"), 1);
|
||||
assert_eq!(
|
||||
revived.status(session.id).await,
|
||||
Some(SessionStatus::Running)
|
||||
);
|
||||
assert!(fake.log().contains("recv session/load"), "{}", fake.log());
|
||||
assert!(worktree.is_dir(), "recovery must retain the worktree");
|
||||
|
||||
revived.kill(session.id, false).await.expect("dismiss");
|
||||
assert!(
|
||||
!worktree.exists(),
|
||||
"operator dismissal still cleans a pristine tree"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn failed_recovery_cleans_its_fifo() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), fake.env()))
|
||||
.await
|
||||
.expect("create");
|
||||
let old_pid = fake.pid();
|
||||
fx.manager.shutdown().await;
|
||||
wait_for_exit(old_pid).await;
|
||||
|
||||
let events_path = fx
|
||||
.sidecar_dir()
|
||||
.join(format!("{}.events.jsonl", session.id));
|
||||
std::fs::remove_file(&events_path).unwrap();
|
||||
std::fs::create_dir(&events_path).unwrap();
|
||||
let revived = SessionManager::new(
|
||||
Arc::new(fx.tmux.tmux.clone()),
|
||||
SidecarStore::new(fx.sidecar_dir()),
|
||||
WorktreeManager::new(None),
|
||||
fx.fifo_dir(),
|
||||
);
|
||||
|
||||
assert!(revived.recover().await.is_err());
|
||||
assert!(!fx.fifo_dir().join(format!("{}.fifo", session.id)).exists());
|
||||
let failed_pid = fake.pid();
|
||||
assert_ne!(failed_pid, old_pid);
|
||||
wait_for_exit(failed_pid).await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
@@ -264,6 +812,176 @@ async fn shutdown_reaps_every_adapter_child() {
|
||||
assert_eq!(sidecar.status, SessionStatus::Dead);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn dismissal_during_shutdown_does_not_restore_recovery_artifacts() {
|
||||
let fx = DaemonFixture::new();
|
||||
let dismissed = Fake::new();
|
||||
let blocker = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = dismissed.env();
|
||||
env.insert("FAKE_ACP_EXIT_ON_CANCEL".into(), "1".into());
|
||||
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.expect("create");
|
||||
fx.manager
|
||||
.create(structured(cwd.path(), blocker.env()))
|
||||
.await
|
||||
.expect("create blocker");
|
||||
|
||||
let manager = fx.manager.clone();
|
||||
let shutdown = tokio::spawn(async move { manager.shutdown().await });
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
dismissed.log().contains("recv session/cancel")
|
||||
})
|
||||
.await;
|
||||
|
||||
fx.manager.kill(session.id, false).await.expect("dismiss");
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.json", session.id))
|
||||
.exists(),
|
||||
"dismissal must finish before shutdown settles its stale snapshot"
|
||||
);
|
||||
shutdown.await.expect("shutdown task");
|
||||
|
||||
assert!(!fx.manager.has(session.id).await);
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.recover", session.id))
|
||||
.exists(),
|
||||
"dismissal must leave no recovery marker"
|
||||
);
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.json", session.id))
|
||||
.exists(),
|
||||
"dismissal must leave no sidecar"
|
||||
);
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.events.jsonl", session.id))
|
||||
.exists(),
|
||||
"dismissal must leave no event log"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn shutdown_does_not_recover_an_adapter_that_already_exited() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_EXIT_AFTER_NEW".into(), "1".into());
|
||||
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.expect("create");
|
||||
wait_for_exit(fake.pid()).await;
|
||||
|
||||
fx.manager.shutdown().await;
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.recover", session.id))
|
||||
.exists(),
|
||||
"a naturally exited adapter is not recoverable"
|
||||
);
|
||||
|
||||
let revived = SessionManager::new(
|
||||
Arc::new(fx.tmux.tmux.clone()),
|
||||
SidecarStore::new(fx.sidecar_dir()),
|
||||
WorktreeManager::new(None),
|
||||
fx.fifo_dir(),
|
||||
);
|
||||
assert_eq!(revived.recover().await.expect("recover"), 1);
|
||||
assert_eq!(revived.status(session.id).await, Some(SessionStatus::Dead));
|
||||
assert!(
|
||||
!fake.log().contains("recv session/load"),
|
||||
"a naturally dead adapter must not be resumed: {}",
|
||||
fake.log()
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn shutdown_waits_for_structured_creation_and_rejects_new_creates() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_DELAY_SESSION_NEW_MS".into(), "500".into());
|
||||
|
||||
let create_cwd = cwd.path().to_path_buf();
|
||||
let manager = fx.manager.clone();
|
||||
let create = tokio::spawn(async move { manager.create(structured(&create_cwd, env)).await });
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fake.log().contains("recv session/new")
|
||||
})
|
||||
.await;
|
||||
|
||||
let manager = fx.manager.clone();
|
||||
let shutdown = tokio::spawn(async move { manager.shutdown().await });
|
||||
tokio::time::sleep(Duration::from_millis(50)).await;
|
||||
assert!(
|
||||
!shutdown.is_finished(),
|
||||
"shutdown returned before create finished"
|
||||
);
|
||||
|
||||
let session = create.await.expect("create task").expect("create");
|
||||
let pid = fake.pid();
|
||||
shutdown.await.expect("shutdown task");
|
||||
|
||||
wait_for_exit(pid).await;
|
||||
assert!(fake.log().contains("signal SIGTERM"), "{}", fake.log());
|
||||
assert_eq!(
|
||||
fx.manager.status(session.id).await,
|
||||
Some(SessionStatus::Dead)
|
||||
);
|
||||
assert!(matches!(
|
||||
fx.manager.create(structured(cwd.path(), fake.env())).await,
|
||||
Err(maestro_daemon::SessionError::ShuttingDown)
|
||||
));
|
||||
|
||||
// A repeated signal must not attempt to terminate the child again.
|
||||
fx.manager.shutdown().await;
|
||||
assert_eq!(fake.log().matches("signal SIGTERM").count(), 1);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn shutdown_drains_final_notifications_to_the_log() {
|
||||
let fx = DaemonFixture::new();
|
||||
let fake = Fake::new();
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_EMIT_ON_CANCEL".into(), "1".into());
|
||||
|
||||
let session = fx
|
||||
.manager
|
||||
.create(structured(cwd.path(), env))
|
||||
.await
|
||||
.expect("create");
|
||||
wait_for_async(Duration::from_secs(5), || async {
|
||||
fx.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.is_ok_and(|events| events.len() == 1)
|
||||
})
|
||||
.await;
|
||||
|
||||
fx.manager.shutdown().await;
|
||||
|
||||
let stored = fx
|
||||
.manager
|
||||
.read_acp_events(session.id, EventCursor::Since(0), 10)
|
||||
.expect("event log after shutdown");
|
||||
assert_eq!(
|
||||
stored.iter().map(event_text).collect::<Vec<_>>(),
|
||||
["hello from fake", "final on cancel"]
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn adapter_exit_marks_the_session_dead_and_keeps_it_listed() {
|
||||
let fx = DaemonFixture::new();
|
||||
@@ -289,8 +1007,38 @@ async fn adapter_exit_marks_the_session_dead_and_keeps_it_listed() {
|
||||
fx.manager.status(session.id).await == Some(SessionStatus::Dead)
|
||||
})
|
||||
.await;
|
||||
assert_eq!(
|
||||
fx.manager
|
||||
.snapshot()
|
||||
.await
|
||||
.into_iter()
|
||||
.find(|candidate| candidate.id == session.id)
|
||||
.unwrap()
|
||||
.activity,
|
||||
ActivityState::Error
|
||||
);
|
||||
assert!(fx.manager.has(session.id).await);
|
||||
assert!(
|
||||
!fx.sidecar_dir()
|
||||
.join(format!("{}.recover", session.id))
|
||||
.exists(),
|
||||
"a naturally exited adapter is never marked for recovery"
|
||||
);
|
||||
|
||||
fx.manager.kill(session.id, false).await.expect("dismiss");
|
||||
assert!(!fx.manager.has(session.id).await);
|
||||
let revived = SessionManager::new(
|
||||
Arc::new(fx.tmux.tmux.clone()),
|
||||
SidecarStore::new(fx.sidecar_dir()),
|
||||
WorktreeManager::new(None),
|
||||
fx.fifo_dir(),
|
||||
);
|
||||
assert_eq!(revived.recover().await.expect("recover"), 1);
|
||||
assert_eq!(revived.status(session.id).await, Some(SessionStatus::Dead));
|
||||
assert!(
|
||||
!fake.log().contains("recv session/load"),
|
||||
"a naturally dead adapter must not be resumed: {}",
|
||||
fake.log()
|
||||
);
|
||||
|
||||
revived.kill(session.id, false).await.expect("dismiss");
|
||||
assert!(!revived.has(session.id).await);
|
||||
}
|
||||
|
||||
@@ -4,12 +4,17 @@ mod common;
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::net::{Ipv4Addr, SocketAddr};
|
||||
use std::path::Path;
|
||||
use std::time::Duration;
|
||||
|
||||
use common::DaemonFixture;
|
||||
use futures_util::{SinkExt, StreamExt};
|
||||
use maestro_daemon::local_api;
|
||||
use maestro_protocol::{ApiError, CreateSessionRequest, Session, WorktreeSpec};
|
||||
use maestro_protocol::{
|
||||
ActivityState, ApiError, CreateSessionRequest, Session, SessionStatus, SessionView,
|
||||
WorktreeSpec,
|
||||
};
|
||||
use tempfile::TempDir;
|
||||
use tokio::net::TcpListener;
|
||||
use tokio::sync::oneshot;
|
||||
use tokio_tungstenite::tungstenite::Message as WsMessage;
|
||||
@@ -86,6 +91,589 @@ fn ws_url(addr: SocketAddr, path: &str) -> String {
|
||||
format!("ws://{addr}{path}")
|
||||
}
|
||||
|
||||
struct FakeAcp {
|
||||
dir: TempDir,
|
||||
}
|
||||
|
||||
impl FakeAcp {
|
||||
fn new() -> Self {
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
|
||||
let dir = TempDir::new().unwrap();
|
||||
let bin = dir.path().join("bin");
|
||||
std::fs::create_dir_all(&bin).unwrap();
|
||||
let adapter = bin.join("claude-code-acp");
|
||||
std::fs::copy(
|
||||
Path::new(env!("CARGO_MANIFEST_DIR")).join("../maestro-acp/tests/fake_acp_agent.py"),
|
||||
&adapter,
|
||||
)
|
||||
.unwrap();
|
||||
std::fs::set_permissions(&adapter, std::fs::Permissions::from_mode(0o755)).unwrap();
|
||||
Self { dir }
|
||||
}
|
||||
|
||||
fn env(&self) -> HashMap<String, String> {
|
||||
HashMap::from([
|
||||
(
|
||||
"PATH".into(),
|
||||
format!(
|
||||
"{}:{}",
|
||||
self.dir.path().join("bin").display(),
|
||||
std::env::var("PATH").unwrap()
|
||||
),
|
||||
),
|
||||
(
|
||||
"FAKE_ACP_LOG".into(),
|
||||
self.dir.path().join("agent.log").display().to_string(),
|
||||
),
|
||||
])
|
||||
}
|
||||
|
||||
fn pid(&self) -> u32 {
|
||||
std::fs::read_to_string(self.dir.path().join("agent.log"))
|
||||
.unwrap_or_default()
|
||||
.lines()
|
||||
.filter_map(|line| {
|
||||
line.strip_prefix("start pid=")?
|
||||
.split(' ')
|
||||
.next()?
|
||||
.parse()
|
||||
.ok()
|
||||
})
|
||||
.next_back()
|
||||
.expect("fake ACP started")
|
||||
}
|
||||
|
||||
fn log(&self) -> String {
|
||||
std::fs::read_to_string(self.dir.path().join("agent.log")).unwrap_or_default()
|
||||
}
|
||||
}
|
||||
|
||||
async fn structured_session(h: &Harness, fake: &FakeAcp) -> Uuid {
|
||||
structured_session_with_env(h, fake.env()).await
|
||||
}
|
||||
|
||||
async fn structured_session_with_env(h: &Harness, env: HashMap<String, String>) -> Uuid {
|
||||
h.manager
|
||||
.create(CreateSessionRequest {
|
||||
view: SessionView::Structured,
|
||||
cwd: "/tmp".into(),
|
||||
command: "claude".into(),
|
||||
env,
|
||||
metadata: HashMap::new(),
|
||||
worktree: None,
|
||||
})
|
||||
.await
|
||||
.unwrap()
|
||||
.id
|
||||
}
|
||||
|
||||
async fn wait_for_session_activity(h: &Harness, id: Uuid, expected: ActivityState) {
|
||||
tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
let sessions: Vec<Session> = reqwest::get(url(h.addr, "/api/sessions"))
|
||||
.await
|
||||
.unwrap()
|
||||
.json()
|
||||
.await
|
||||
.unwrap();
|
||||
if sessions
|
||||
.iter()
|
||||
.find(|session| session.id == id)
|
||||
.is_some_and(|session| session.activity == expected)
|
||||
{
|
||||
return;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap_or_else(|_| panic!("session {id} did not reach {expected:?}"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_ws_sends_snapshot_then_live_projection() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let id = structured_session(&h, &fake).await;
|
||||
let (mut ws, _) = connect_async(ws_url(h.addr, &format!("/api/structured/{id}")))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let first = ws.next().await.unwrap().unwrap().into_text().unwrap();
|
||||
let second = ws.next().await.unwrap().unwrap().into_text().unwrap();
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&first).unwrap()["type"],
|
||||
"transcript_snapshot"
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&second).unwrap()["type"],
|
||||
"reduced_state"
|
||||
);
|
||||
|
||||
let response = reqwest::Client::new()
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "hello"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
let live = tokio::time::timeout(Duration::from_secs(1), ws.next())
|
||||
.await
|
||||
.expect("projection update arrives on the subscribed stream")
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
.into_text()
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&live).unwrap()["type"],
|
||||
"projection_update"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_prompt_rejects_a_second_in_flight_turn_and_cancel_clears_it() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_DELAY_PROMPT_MS".into(), "200".into());
|
||||
let id = structured_session_with_env(&h, env).await;
|
||||
let client = reqwest::Client::new();
|
||||
let first = client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "first"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(first.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
let second = client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "second"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(second.status(), reqwest::StatusCode::CONFLICT);
|
||||
let error: ApiError = second.json().await.unwrap();
|
||||
assert_eq!(error.error.code, "turn_in_flight");
|
||||
|
||||
let cancel = client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/cancel"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(cancel.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
let next = client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "next"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(next.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
if fake.log().matches("recv session/prompt").count() == 2 {
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.expect("both prompt commands reach ACP");
|
||||
let log = fake.log();
|
||||
let first_prompt = log.find("recv session/prompt").unwrap();
|
||||
let cancel = log.find("recv session/cancel").unwrap();
|
||||
let second_prompt = log.rfind("recv session/prompt").unwrap();
|
||||
assert!(first_prompt < cancel && cancel < second_prompt, "{log}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_approval_is_secret_single_use_and_race_safe() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_REQUEST_PERMISSION".into(), "1".into());
|
||||
let id = structured_session_with_env(&h, env).await;
|
||||
let client = reqwest::Client::new();
|
||||
let (mut ws, _) = connect_async(ws_url(h.addr, &format!("/api/structured/{id}")))
|
||||
.await
|
||||
.unwrap();
|
||||
ws.next().await.unwrap().unwrap();
|
||||
ws.next().await.unwrap().unwrap();
|
||||
assert_eq!(
|
||||
client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt")
|
||||
))
|
||||
.json(&serde_json::json!({"prompt":"needs permission"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
reqwest::StatusCode::NO_CONTENT
|
||||
);
|
||||
|
||||
let nonce = tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
let event: serde_json::Value =
|
||||
serde_json::from_str(&ws.next().await.unwrap().unwrap().into_text().unwrap())
|
||||
.unwrap();
|
||||
if let Some(nonce) = event["state"]["pending_approval"]["nonce"].as_str() {
|
||||
assert_eq!(event["transcript"]["row"]["kind"], "approval");
|
||||
assert!(event["transcript"]["row"]["data"].get("nonce").is_none());
|
||||
break nonce.to_owned();
|
||||
}
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_session_activity(&h, id, ActivityState::AwaitingInput).await;
|
||||
assert!(
|
||||
!fake.log().contains(&nonce),
|
||||
"daemon nonce leaked to ACP agent"
|
||||
);
|
||||
|
||||
let path = format!("/api/sessions/{id}/structured/approvals/{nonce}");
|
||||
let (a, b) = tokio::join!(
|
||||
client
|
||||
.post(url(h.addr, &path))
|
||||
.json(&serde_json::json!("allow_once"))
|
||||
.send(),
|
||||
client
|
||||
.post(url(h.addr, &path))
|
||||
.json(&serde_json::json!("deny"))
|
||||
.send(),
|
||||
);
|
||||
assert_eq!(a.unwrap().status(), reqwest::StatusCode::NO_CONTENT);
|
||||
assert_eq!(b.unwrap().status(), reqwest::StatusCode::NO_CONTENT);
|
||||
assert_eq!(
|
||||
client
|
||||
.post(url(h.addr, &path))
|
||||
.json(&serde_json::json!("deny"))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
reqwest::StatusCode::NO_CONTENT
|
||||
);
|
||||
tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
if fake.log().contains("permission response") {
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
let log = fake.log();
|
||||
assert!(
|
||||
log.contains("\"optionId\": \"once\"") || log.contains("\"optionId\": \"deny\""),
|
||||
"{log}"
|
||||
);
|
||||
tokio::time::timeout(Duration::from_secs(1), async {
|
||||
loop {
|
||||
let event: serde_json::Value =
|
||||
serde_json::from_str(&ws.next().await.unwrap().unwrap().into_text().unwrap())
|
||||
.unwrap();
|
||||
if event["state"]["pending_approval"].is_null() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
})
|
||||
.await
|
||||
.expect("resolved approval clears the reduced state");
|
||||
wait_for_session_activity(&h, id, ActivityState::Idle).await;
|
||||
assert_eq!(
|
||||
client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!(
|
||||
"/api/sessions/{}/structured/approvals/{nonce}",
|
||||
Uuid::new_v4()
|
||||
)
|
||||
))
|
||||
.json(&serde_json::json!("deny"))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
reqwest::StatusCode::NOT_FOUND
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_prompt_failure_clears_the_turn() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_PROMPT_FAIL_ONCE".into(), "1".into());
|
||||
let id = structured_session_with_env(&h, env).await;
|
||||
let client = reqwest::Client::new();
|
||||
let path = format!("/api/sessions/{id}/structured/prompt");
|
||||
let (mut ws, _) = connect_async(ws_url(h.addr, &format!("/api/structured/{id}")))
|
||||
.await
|
||||
.unwrap();
|
||||
ws.next().await.unwrap().unwrap();
|
||||
ws.next().await.unwrap().unwrap();
|
||||
let first = client
|
||||
.post(url(h.addr, &path))
|
||||
.json(&serde_json::json!({"prompt":"fails"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(first.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
let mut saw_active_turn = false;
|
||||
tokio::time::timeout(Duration::from_secs(1), async {
|
||||
while let Some(Ok(message)) = ws.next().await {
|
||||
let event: serde_json::Value =
|
||||
serde_json::from_str(&message.into_text().unwrap()).unwrap();
|
||||
let turn = &event["state"]["turn"];
|
||||
if turn["responding"] == true {
|
||||
saw_active_turn = true;
|
||||
}
|
||||
if saw_active_turn && turn["responding"] == false && turn["thinking"] == false {
|
||||
return;
|
||||
}
|
||||
}
|
||||
panic!("structured websocket closed before the failed turn cleared");
|
||||
})
|
||||
.await
|
||||
.expect("failed turn clears promptly");
|
||||
wait_for_session_activity(&h, id, ActivityState::Error).await;
|
||||
let second = client
|
||||
.post(url(h.addr, &path))
|
||||
.json(&serde_json::json!({"prompt":"available"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(second.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
assert!(second.bytes().await.unwrap().is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_prompt_rejects_unknown_and_unavailable_sessions() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let client = reqwest::Client::new();
|
||||
let prompt = |id| {
|
||||
client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "hello"}))
|
||||
};
|
||||
|
||||
let unknown = prompt(Uuid::new_v4()).send().await.unwrap();
|
||||
assert_eq!(unknown.status(), reqwest::StatusCode::NOT_FOUND);
|
||||
let error: ApiError = unknown.json().await.unwrap();
|
||||
assert_eq!(error.error.code, "not_found");
|
||||
|
||||
let terminal = h
|
||||
.manager
|
||||
.create(CreateSessionRequest {
|
||||
view: SessionView::Terminal,
|
||||
cwd: "/tmp".into(),
|
||||
command: "sh".into(),
|
||||
env: HashMap::new(),
|
||||
metadata: HashMap::new(),
|
||||
worktree: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
let non_structured = prompt(terminal.id).send().await.unwrap();
|
||||
assert_eq!(non_structured.status(), reqwest::StatusCode::CONFLICT);
|
||||
let error: ApiError = non_structured.json().await.unwrap();
|
||||
assert_eq!(error.error.code, "not_structured");
|
||||
|
||||
let fake = FakeAcp::new();
|
||||
let dead = structured_session(&h, &fake).await;
|
||||
h.manager.shutdown().await;
|
||||
assert_eq!(h.manager.status(dead).await, Some(SessionStatus::Dead));
|
||||
let unavailable = prompt(dead).send().await.unwrap();
|
||||
assert_eq!(unavailable.status(), reqwest::StatusCode::CONFLICT);
|
||||
let error: ApiError = unavailable.json().await.unwrap();
|
||||
assert_eq!(error.error.code, "not_structured");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_replay_honors_cursors_and_limit() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let id = structured_session(&h, &fake).await;
|
||||
let client = reqwest::Client::new();
|
||||
|
||||
let events: Vec<serde_json::Value> = tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
let events: Vec<serde_json::Value> = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/replay?since=0&limit=1"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.json()
|
||||
.await
|
||||
.unwrap();
|
||||
if !events.is_empty() {
|
||||
return events;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(events.len(), 1);
|
||||
assert_eq!(events[0]["cursor"], 1);
|
||||
assert!(events[0].get("notification").is_none());
|
||||
|
||||
let invalid = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/replay?since=0&before=2"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(invalid.status(), reqwest::StatusCode::BAD_REQUEST);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_replay_pages_projected_events_in_cursor_order() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let id = structured_session(&h, &fake).await;
|
||||
let client = reqwest::Client::new();
|
||||
unsafe { libc::kill(fake.pid() as libc::pid_t, libc::SIGUSR1) };
|
||||
let events: Vec<serde_json::Value> = tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
let events: Vec<serde_json::Value> = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/replay?before=99&limit=2"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.json()
|
||||
.await
|
||||
.unwrap();
|
||||
if events.len() == 2 {
|
||||
return events;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
events
|
||||
.iter()
|
||||
.map(|event| event["cursor"].as_u64().unwrap())
|
||||
.collect::<Vec<_>>(),
|
||||
vec![1, 2]
|
||||
);
|
||||
let boundary: Vec<serde_json::Value> = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/replay?before=2&limit=10"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap()
|
||||
.json()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(boundary.len(), 1);
|
||||
assert_eq!(boundary[0]["cursor"], 1);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_replay_rejects_unknown_terminal_and_dead_sessions() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let client = reqwest::Client::new();
|
||||
let unknown = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{}/structured/replay", Uuid::new_v4()),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(unknown.status(), reqwest::StatusCode::NOT_FOUND);
|
||||
let terminal = h
|
||||
.manager
|
||||
.create(CreateSessionRequest {
|
||||
view: SessionView::Terminal,
|
||||
cwd: "/tmp".into(),
|
||||
command: "sh".into(),
|
||||
env: HashMap::new(),
|
||||
metadata: HashMap::new(),
|
||||
worktree: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
let response = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{}/structured/replay", terminal.id),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.status(), reqwest::StatusCode::CONFLICT);
|
||||
|
||||
let fake = FakeAcp::new();
|
||||
let dead = structured_session(&h, &fake).await;
|
||||
h.manager.shutdown().await;
|
||||
assert_eq!(h.manager.status(dead).await, Some(SessionStatus::Dead));
|
||||
let response = client
|
||||
.get(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{dead}/structured/replay"),
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.status(), reqwest::StatusCode::CONFLICT);
|
||||
let error: ApiError = response.json().await.unwrap();
|
||||
assert_eq!(error.error.code, "not_structured");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn structured_ws_rejects_a_dead_session() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
let fake = FakeAcp::new();
|
||||
let id = structured_session(&h, &fake).await;
|
||||
h.manager.shutdown().await;
|
||||
assert_eq!(h.manager.status(id).await, Some(SessionStatus::Dead));
|
||||
|
||||
let err = connect_async(ws_url(h.addr, &format!("/api/structured/{id}")))
|
||||
.await
|
||||
.expect_err("dead structured session must not upgrade");
|
||||
let message = err.to_string();
|
||||
assert!(
|
||||
message.contains("409") || message.to_lowercase().contains("conflict"),
|
||||
"{message}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn info_returns_daemon_identity() {
|
||||
let h = spawn("naps-laptop").await;
|
||||
@@ -789,6 +1377,73 @@ async fn events_ws_sends_a_snapshot_then_streams_deltas() {
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn events_ws_streams_structured_activity_without_hook_overrides() {
|
||||
let h = spawn("konishi").await;
|
||||
let fake = FakeAcp::new();
|
||||
let mut env = fake.env();
|
||||
env.insert("FAKE_ACP_DELAY_PROMPT_MS".into(), "500".into());
|
||||
let (mut ws, _) = connect_async(ws_url(h.addr, "/api/events"))
|
||||
.await
|
||||
.expect("events ws");
|
||||
assert!(matches!(
|
||||
next_event(&mut ws).await,
|
||||
maestro_protocol::CatalogEvent::Snapshot { .. }
|
||||
));
|
||||
|
||||
let id = structured_session_with_env(&h, env).await;
|
||||
let maestro_protocol::CatalogEvent::SessionAdded { session } = next_event(&mut ws).await else {
|
||||
panic!("expected structured SessionAdded")
|
||||
};
|
||||
assert_eq!(session.activity, ActivityState::Idle);
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
let prompt = client
|
||||
.post(url(
|
||||
h.addr,
|
||||
&format!("/api/sessions/{id}/structured/prompt"),
|
||||
))
|
||||
.json(&serde_json::json!({"prompt": "hello"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(prompt.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
let report = client
|
||||
.post(url(h.addr, &format!("/api/sessions/{id}/activity")))
|
||||
.json(&serde_json::json!({"state": "Error"}))
|
||||
.send()
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(report.status(), reqwest::StatusCode::NO_CONTENT);
|
||||
wait_for_session_activity(&h, id, ActivityState::Active).await;
|
||||
|
||||
let mut activities = Vec::new();
|
||||
tokio::time::timeout(Duration::from_secs(2), async {
|
||||
loop {
|
||||
if let maestro_protocol::CatalogEvent::SessionUpdated { session } =
|
||||
next_event(&mut ws).await
|
||||
{
|
||||
activities.push(session.activity);
|
||||
if session.activity == ActivityState::Idle {
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
.await
|
||||
.expect("structured turn returns to idle");
|
||||
assert!(
|
||||
activities.contains(&ActivityState::Active),
|
||||
"{activities:?}"
|
||||
);
|
||||
assert!(
|
||||
!activities.contains(&ActivityState::Error),
|
||||
"{activities:?}"
|
||||
);
|
||||
|
||||
h.manager.kill(id, false).await.unwrap();
|
||||
}
|
||||
|
||||
/// Each subscriber has its own lag domain now that the publisher task is gone:
|
||||
/// two clients connected at different times both get their own Snapshot.
|
||||
#[tokio::test]
|
||||
|
||||
@@ -6,8 +6,8 @@ use std::collections::HashMap;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use chrono::{DateTime, Utc};
|
||||
use maestro_daemon::sidecar::SidecarStore;
|
||||
use maestro_protocol::{Session, SessionStatus, SessionView};
|
||||
use maestro_daemon::sidecar::{PersistedEvent, SidecarStore};
|
||||
use maestro_protocol::{Session, SessionStatus, SessionView, TranscriptRow, TranscriptRowKind};
|
||||
use serde_json::Value;
|
||||
use tempfile::TempDir;
|
||||
use uuid::Uuid;
|
||||
@@ -68,15 +68,30 @@ fn delete_removes_file_and_is_idempotent() {
|
||||
let s = sample(id);
|
||||
|
||||
store.write(&s).unwrap();
|
||||
store.mark_for_recovery(id).unwrap();
|
||||
assert!(store.path_for(id).exists());
|
||||
assert!(store.recovery_path_for(id).exists());
|
||||
|
||||
store.delete(id).unwrap();
|
||||
assert!(!store.path_for(id).exists());
|
||||
assert!(!store.recovery_path_for(id).exists());
|
||||
|
||||
// second delete is a no-op
|
||||
store.delete(id).unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn recovery_marker_is_consumed_once() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
|
||||
assert!(!store.take_recovery_marker(id).unwrap());
|
||||
store.mark_for_recovery(id).unwrap();
|
||||
assert!(store.take_recovery_marker(id).unwrap());
|
||||
assert!(!store.take_recovery_marker(id).unwrap());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn load_all_recovers_every_sidecar_and_skips_garbage() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
@@ -146,3 +161,237 @@ fn write_creates_parent_directory() {
|
||||
assert!(nested.exists());
|
||||
assert!(store.path_for(s.id).exists());
|
||||
}
|
||||
|
||||
// ---- per-session event log (#135) ----
|
||||
|
||||
use maestro_acp::schema::{ContentBlock, SessionNotification, SessionUpdate, TextContent};
|
||||
use maestro_daemon::sidecar::EventCursor;
|
||||
|
||||
fn note(text: &str) -> SessionNotification {
|
||||
SessionNotification::new(
|
||||
"acp-1",
|
||||
SessionUpdate::AgentMessageChunk(maestro_acp::schema::ContentChunk::new(
|
||||
ContentBlock::Text(TextContent::new(text)),
|
||||
)),
|
||||
)
|
||||
}
|
||||
|
||||
fn text_of(n: &SessionNotification) -> &str {
|
||||
match &n.update {
|
||||
SessionUpdate::AgentMessageChunk(chunk) => match &chunk.content {
|
||||
ContentBlock::Text(t) => &t.text,
|
||||
other => panic!("unexpected content {other:?}"),
|
||||
},
|
||||
other => panic!("unexpected update {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
fn event_text(event: &maestro_daemon::sidecar::LoggedEvent) -> &str {
|
||||
let maestro_daemon::sidecar::PersistedEvent::Notification(notification) = &event.event else {
|
||||
panic!("expected ACP notification")
|
||||
};
|
||||
text_of(notification)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn append_assigns_line_position_as_seq_and_reads_back() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
|
||||
let mut log = store.open_events(id).expect("open");
|
||||
assert_eq!(log.last_seq(), 0);
|
||||
assert_eq!(log.append(note("a")).unwrap(), 1);
|
||||
assert_eq!(log.append(note("b")).unwrap(), 2);
|
||||
assert_eq!(log.append(note("c")).unwrap(), 3);
|
||||
assert_eq!(log.last_seq(), 3);
|
||||
|
||||
let path = store.events_path_for(id);
|
||||
assert!(path.ends_with(format!("{id}.events.jsonl")), "{path:?}");
|
||||
let raw = std::fs::read_to_string(&path).unwrap();
|
||||
assert_eq!(raw.lines().count(), 3, "one object per line:\n{raw}");
|
||||
for line in raw.lines() {
|
||||
let v: Value = serde_json::from_str(line).expect("each line is one JSON object");
|
||||
assert_eq!(v["sessionId"], "acp-1");
|
||||
}
|
||||
|
||||
let all = store.read_events(id, EventCursor::Since(0), 100).unwrap();
|
||||
assert_eq!(all.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![1, 2, 3]);
|
||||
assert_eq!(
|
||||
all.iter().map(event_text).collect::<Vec<_>>(),
|
||||
vec!["a", "b", "c"]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn since_reads_forward_and_before_reads_backward_with_limit() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
for i in 1..=6 {
|
||||
log.append(note(&format!("n{i}"))).unwrap();
|
||||
}
|
||||
|
||||
// `since` is exclusive: what a client that already holds seq 2 needs.
|
||||
let fwd = store.read_events(id, EventCursor::Since(2), 3).unwrap();
|
||||
assert_eq!(fwd.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![3, 4, 5]);
|
||||
// Past the end: nothing, not an error.
|
||||
assert!(store
|
||||
.read_events(id, EventCursor::Since(6), 3)
|
||||
.unwrap()
|
||||
.is_empty());
|
||||
|
||||
// `before` is exclusive and pages backward: the `limit` events closest
|
||||
// to the cursor, still in ascending seq order.
|
||||
let back = store
|
||||
.read_events(id, EventCursor::Before(Some(5)), 2)
|
||||
.unwrap();
|
||||
assert_eq!(back.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![3, 4]);
|
||||
// No cursor: the tail of the log, for a first paint.
|
||||
let tail = store.read_events(id, EventCursor::Before(None), 2).unwrap();
|
||||
assert_eq!(tail.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![5, 6]);
|
||||
// Paging past the start runs out cleanly.
|
||||
let start = store
|
||||
.read_events(id, EventCursor::Before(Some(2)), 10)
|
||||
.unwrap();
|
||||
assert_eq!(start.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![1]);
|
||||
assert!(store
|
||||
.read_events(id, EventCursor::Before(Some(1)), 10)
|
||||
.unwrap()
|
||||
.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn missing_log_reads_as_empty() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
assert!(store
|
||||
.read_events(id, EventCursor::Since(0), 10)
|
||||
.unwrap()
|
||||
.is_empty());
|
||||
assert!(store
|
||||
.read_events(id, EventCursor::Before(None), 10)
|
||||
.unwrap()
|
||||
.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn malformed_lines_are_skipped_but_keep_their_seq() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
log.append(note("first")).unwrap();
|
||||
drop(log);
|
||||
|
||||
// Garbage in the middle and a line that is JSON but not a notification.
|
||||
let path = store.events_path_for(id);
|
||||
let mut raw = std::fs::read_to_string(&path).unwrap();
|
||||
raw.push_str("{not json\n");
|
||||
raw.push_str("{\"unrelated\": true}\n");
|
||||
std::fs::write(&path, raw).unwrap();
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
assert_eq!(log.last_seq(), 3);
|
||||
assert_eq!(log.append(note("fourth")).unwrap(), 4);
|
||||
|
||||
let all = store.read_events(id, EventCursor::Since(0), 10).unwrap();
|
||||
assert_eq!(all.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![1, 4]);
|
||||
assert_eq!(event_text(&all[1]), "fourth");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn truncated_last_line_still_opens_and_the_next_append_starts_a_fresh_line() {
|
||||
// A hard kill mid-write leaves a partial line with no newline.
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
log.append(note("whole")).unwrap();
|
||||
drop(log);
|
||||
|
||||
let path = store.events_path_for(id);
|
||||
let mut raw = std::fs::read(&path).unwrap();
|
||||
raw.extend_from_slice(br#"{"sessionId":"acp-1","update":{"sessionUpd"#);
|
||||
std::fs::write(&path, &raw).unwrap();
|
||||
|
||||
// Reads: the partial line is skipped, nothing else is lost.
|
||||
let all = store.read_events(id, EventCursor::Since(0), 10).unwrap();
|
||||
assert_eq!(all.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![1]);
|
||||
|
||||
// Reopening terminates the partial line so the next append does not
|
||||
// glue onto it; the partial keeps a seq of its own.
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
assert_eq!(log.last_seq(), 2);
|
||||
assert_eq!(log.append(note("after")).unwrap(), 3);
|
||||
let all = store.read_events(id, EventCursor::Since(0), 10).unwrap();
|
||||
assert_eq!(all.iter().map(|e| e.seq).collect::<Vec<_>>(), vec![1, 3]);
|
||||
assert_eq!(event_text(&all[1]), "after");
|
||||
let raw = std::fs::read_to_string(&path).unwrap();
|
||||
assert_eq!(raw.lines().count(), 3, "{raw}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn delete_removes_the_event_log_and_load_all_ignores_it() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
store.write(&sample(id)).unwrap();
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
log.append(note("x")).unwrap();
|
||||
drop(log);
|
||||
let legacy_approvals = dir.path().join(format!("{id}.approvals.jsonl"));
|
||||
std::fs::write(&legacy_approvals, b"obsolete").unwrap();
|
||||
assert!(store.events_path_for(id).exists());
|
||||
|
||||
let loaded = store.load_all().unwrap();
|
||||
assert_eq!(loaded.len(), 1, "the .jsonl must not be read as a sidecar");
|
||||
|
||||
store.delete(id).unwrap();
|
||||
assert!(!store.path_for(id).exists());
|
||||
assert!(!store.events_path_for(id).exists());
|
||||
assert!(!legacy_approvals.exists());
|
||||
// Idempotent with the log already gone.
|
||||
store.delete(id).unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn approval_rows_share_event_cursors_with_legacy_acp_lines() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let store = SidecarStore::new(dir.path());
|
||||
let id = Uuid::new_v4();
|
||||
let legacy = serde_json::to_vec(¬e("before")).unwrap();
|
||||
std::fs::create_dir_all(dir.path()).unwrap();
|
||||
std::fs::write(store.events_path_for(id), [legacy, b"\n".to_vec()].concat()).unwrap();
|
||||
|
||||
let mut log = store.open_events(id).unwrap();
|
||||
assert_eq!(
|
||||
log.append(PersistedEvent::Approval {
|
||||
row: TranscriptRow {
|
||||
id: "approval:secret".into(),
|
||||
kind: TranscriptRowKind::Approval,
|
||||
data: serde_json::json!({"tool": "bash"}),
|
||||
},
|
||||
})
|
||||
.unwrap(),
|
||||
2
|
||||
);
|
||||
assert_eq!(log.append(note("after")).unwrap(), 3);
|
||||
|
||||
let all = store.read_events(id, EventCursor::Since(0), 10).unwrap();
|
||||
assert_eq!(
|
||||
all.iter().map(|event| event.seq).collect::<Vec<_>>(),
|
||||
[1, 2, 3]
|
||||
);
|
||||
assert!(matches!(all[1].event, PersistedEvent::Approval { .. }));
|
||||
assert_eq!(event_text(&all[0]), "before");
|
||||
assert_eq!(event_text(&all[2]), "after");
|
||||
|
||||
let since = store.read_events(id, EventCursor::Since(1), 1).unwrap();
|
||||
assert_eq!(since[0].seq, 2);
|
||||
let before = store
|
||||
.read_events(id, EventCursor::Before(Some(3)), 1)
|
||||
.unwrap();
|
||||
assert_eq!(before[0].seq, 2);
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ path = "src/lib.rs"
|
||||
[dependencies]
|
||||
chrono.workspace = true
|
||||
futures-util.workspace = true
|
||||
libc.workspace = true
|
||||
maestro-protocol = { workspace = true, features = ["client"] }
|
||||
maestro-testing.workspace = true
|
||||
serde.workspace = true
|
||||
|
||||
@@ -87,6 +87,14 @@ impl Daemon {
|
||||
}
|
||||
}
|
||||
|
||||
/// Send the daemon the same SIGTERM systemd uses, without waiting for its
|
||||
/// graceful HTTP shutdown to finish.
|
||||
pub fn send_sigterm(&self) {
|
||||
let child = self.child.as_ref().expect("daemon is running");
|
||||
let result = unsafe { libc::kill(child.id() as libc::pid_t, libc::SIGTERM) };
|
||||
assert_eq!(result, 0, "send SIGTERM to daemon");
|
||||
}
|
||||
|
||||
/// Re-spawn the daemon on the same port + state. The previous tmux
|
||||
/// server (under `TMUX_TMPDIR`) is left running so `recover()` can adopt
|
||||
/// its sessions.
|
||||
|
||||
@@ -15,7 +15,7 @@ use std::time::{Duration, Instant};
|
||||
use futures_util::{SinkExt, StreamExt};
|
||||
use maestro_e2e::util::wait_for_async;
|
||||
use maestro_e2e::{Daemon, TestClient};
|
||||
use maestro_protocol::{CreateSessionRequest, WorktreeSpec};
|
||||
use maestro_protocol::{CreateSessionRequest, SessionStatus, SessionView, WorktreeSpec};
|
||||
use tempfile::TempDir;
|
||||
use tokio_tungstenite::tungstenite::Message as WsMessage;
|
||||
|
||||
@@ -36,6 +36,61 @@ fn create_req(cwd: &std::path::Path, command: &str) -> CreateSessionRequest {
|
||||
}
|
||||
}
|
||||
|
||||
struct FakeAcp {
|
||||
_dir: TempDir,
|
||||
env: HashMap<String, String>,
|
||||
}
|
||||
|
||||
fn fake_acp(log: &std::path::Path) -> FakeAcp {
|
||||
let dir = tempfile::tempdir().expect("fake adapter dir");
|
||||
let adapter = dir.path().join("claude-code-acp");
|
||||
std::fs::copy(
|
||||
concat!(
|
||||
env!("CARGO_MANIFEST_DIR"),
|
||||
"/../maestro-acp/tests/fake_acp_agent.py"
|
||||
),
|
||||
&adapter,
|
||||
)
|
||||
.expect("copy fake adapter");
|
||||
let mut permissions = std::fs::metadata(&adapter)
|
||||
.expect("adapter metadata")
|
||||
.permissions();
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
permissions.set_mode(0o755);
|
||||
}
|
||||
std::fs::set_permissions(&adapter, permissions).expect("make fake adapter executable");
|
||||
let env = HashMap::from([
|
||||
(
|
||||
"PATH".into(),
|
||||
format!(
|
||||
"{}:{}",
|
||||
dir.path().display(),
|
||||
std::env::var("PATH").unwrap_or_default()
|
||||
),
|
||||
),
|
||||
("FAKE_ACP_LOG".into(), log.to_string_lossy().into_owned()),
|
||||
]);
|
||||
FakeAcp { _dir: dir, env }
|
||||
}
|
||||
|
||||
fn fake_acp_pid(log: &std::path::Path) -> Option<u32> {
|
||||
std::fs::read_to_string(log).ok()?.lines().find_map(|line| {
|
||||
line.strip_prefix("start pid=")?
|
||||
.split(' ')
|
||||
.next()?
|
||||
.parse()
|
||||
.ok()
|
||||
})
|
||||
}
|
||||
|
||||
fn pid_alive(pid: u32) -> bool {
|
||||
std::fs::read_to_string(format!("/proc/{pid}/stat"))
|
||||
.map(|stat| !stat.contains(") Z "))
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
/// A worktree spec built through its wire shape. The daemon and clients ship
|
||||
/// together (#87 dropped `cleanup_on_kill` from the struct), so the JSON
|
||||
/// object carries only the fields the lifecycle actually honours.
|
||||
@@ -995,6 +1050,66 @@ async fn daemon_restart_recovers_session() {
|
||||
client.kill_session(s.id).await.expect("kill");
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread")]
|
||||
async fn sigterm_stops_structured_child_before_events_ws_drains() {
|
||||
let (mut daemon, client) = bring_up().await;
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let log = cwd.path().join("fake-acp.log");
|
||||
let fake = fake_acp(&log);
|
||||
let session = client
|
||||
.spawn_session(&CreateSessionRequest {
|
||||
view: SessionView::Structured,
|
||||
cwd: cwd.path().to_path_buf(),
|
||||
command: "claude".into(),
|
||||
env: fake.env.clone(),
|
||||
metadata: HashMap::new(),
|
||||
worktree: None,
|
||||
})
|
||||
.await
|
||||
.expect("spawn structured session");
|
||||
let ws_url = daemon.client().events_url().expect("events URL");
|
||||
let (_events_ws, _) = tokio_tungstenite::connect_async(ws_url)
|
||||
.await
|
||||
.expect("events WS handshake");
|
||||
wait_for_async("fake ACP starts", Duration::from_secs(5), || {
|
||||
let log = log.clone();
|
||||
async move { fake_acp_pid(&log).is_some() }
|
||||
})
|
||||
.await;
|
||||
let pid = fake_acp_pid(&log).expect("fake ACP pid");
|
||||
|
||||
daemon.send_sigterm();
|
||||
|
||||
wait_for_async(
|
||||
"fake ACP exits after SIGTERM",
|
||||
Duration::from_secs(5),
|
||||
|| async { !pid_alive(pid) },
|
||||
)
|
||||
.await;
|
||||
let sidecar_path = daemon
|
||||
.state_dir()
|
||||
.join("sessions")
|
||||
.join(format!("{}.json", session.id));
|
||||
wait_for_async(
|
||||
"dead structured session sidecar",
|
||||
Duration::from_secs(5),
|
||||
|| {
|
||||
let sidecar_path = sidecar_path.clone();
|
||||
async move {
|
||||
std::fs::read(&sidecar_path)
|
||||
.ok()
|
||||
.and_then(|json| {
|
||||
serde_json::from_slice::<maestro_protocol::Session>(&json).ok()
|
||||
})
|
||||
.is_some_and(|saved| saved.status == SessionStatus::Dead)
|
||||
}
|
||||
},
|
||||
)
|
||||
.await;
|
||||
|
||||
daemon.stop();
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread")]
|
||||
async fn concurrent_spawns_each_get_unique_ids() {
|
||||
let (_daemon, client) = bring_up().await;
|
||||
|
||||
@@ -156,9 +156,9 @@ pub enum SessionStatus {
|
||||
Dead,
|
||||
}
|
||||
|
||||
/// Inferred session activity, orthogonal to [`SessionStatus`] (NAP-340). The
|
||||
/// daemon derives this from tmux pane state, PTY quiescence, and `/proc`
|
||||
/// inspection — never by parsing the terminal byte stream.
|
||||
/// Session activity, orthogonal to [`SessionStatus`] (NAP-340). Terminal
|
||||
/// sessions use pane/process inference and agent reports; structured sessions
|
||||
/// use their ACP turn lifecycle (docs/SIDEBAR.md).
|
||||
///
|
||||
/// Deserializes leniently (#110, SIDEBAR.md Precedence): an unknown variant
|
||||
/// from a newer daemon becomes [`ActivityState::Idle`] instead of failing the
|
||||
@@ -166,15 +166,14 @@ pub enum SessionStatus {
|
||||
/// forgiven.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Default)]
|
||||
pub enum ActivityState {
|
||||
/// Producing output, or the foreground process is busy.
|
||||
/// Producing output, the foreground process is busy, or an ACP turn is active.
|
||||
Active,
|
||||
/// Foreground process alive but quiescent. The forward-compatible default.
|
||||
#[default]
|
||||
Idle,
|
||||
/// Blocked on a `read()` from the pty — waiting on the user.
|
||||
/// Blocked on terminal input or waiting for an ACP approval.
|
||||
AwaitingInput,
|
||||
/// The agent running in the session reported a failure (#102). Never
|
||||
/// inferred by the daemon; only set when an agent reports it (#105).
|
||||
/// An agent reported a failure, or a structured session/turn failed.
|
||||
Error,
|
||||
}
|
||||
|
||||
@@ -755,6 +754,132 @@ pub enum CatalogEvent {
|
||||
},
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Structured-session projections
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/// One client-neutral item in a structured session transcript.
|
||||
///
|
||||
/// `data` preserves the ACP payload without committing clients to an ACP
|
||||
/// dependency. Rendering choices, including markdown and tool-card treatment,
|
||||
/// stay with the client.
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
pub struct TranscriptRow {
|
||||
/// Stable within one session, so later deltas can address this row.
|
||||
pub id: String,
|
||||
pub kind: TranscriptRowKind,
|
||||
pub data: Value,
|
||||
}
|
||||
|
||||
/// The semantic shape of a [`TranscriptRow`].
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum TranscriptRowKind {
|
||||
User,
|
||||
AgentText,
|
||||
AgentThought,
|
||||
ToolCall,
|
||||
ToolDiff,
|
||||
Approval,
|
||||
Plan,
|
||||
Notice,
|
||||
}
|
||||
|
||||
/// A complete transcript at a durable event-log position.
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
pub struct TranscriptSnapshot {
|
||||
pub cursor: u64,
|
||||
#[serde(default)]
|
||||
pub rows: Vec<TranscriptRow>,
|
||||
}
|
||||
|
||||
/// One durable, client-neutral replay step from a structured session.
|
||||
///
|
||||
/// Results are ordered by increasing `cursor`. `since` returns the first
|
||||
/// matching steps; `before` returns the final matching steps, still increasing.
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
pub struct StructuredReplayEvent {
|
||||
/// Durable ACP-log position represented by this projected step.
|
||||
pub cursor: u64,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub transcript: Option<TranscriptDelta>,
|
||||
pub state: ReducedState,
|
||||
}
|
||||
|
||||
/// A change to a transcript row.
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
pub enum TranscriptDelta {
|
||||
Append { row: TranscriptRow },
|
||||
Patch { row: TranscriptRow },
|
||||
Remove { id: String },
|
||||
}
|
||||
|
||||
/// Per-turn indicators derived from the ACP stream.
|
||||
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct TurnState {
|
||||
#[serde(default)]
|
||||
pub responding: bool,
|
||||
#[serde(default)]
|
||||
pub thinking: bool,
|
||||
#[serde(default)]
|
||||
pub active_tool_calls: Vec<String>,
|
||||
}
|
||||
|
||||
/// A whole-session view derived from ACP notifications.
|
||||
///
|
||||
/// Values whose shape ACP owns are carried as JSON so this wire protocol stays
|
||||
/// forward-compatible when ACP adds fields or variants.
|
||||
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
|
||||
pub struct ReducedState {
|
||||
#[serde(default)]
|
||||
pub turn: TurnState,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub pending_approval: Option<Value>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub plan: Option<Value>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub usage: Option<Value>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub context: Option<Value>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub model: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub mode: Option<String>,
|
||||
}
|
||||
|
||||
/// Server messages sent over a structured-session WebSocket.
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
pub enum StructuredEvent {
|
||||
TranscriptSnapshot {
|
||||
snapshot: TranscriptSnapshot,
|
||||
},
|
||||
ReducedState {
|
||||
state: ReducedState,
|
||||
},
|
||||
ProjectionUpdate {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
transcript: Option<TranscriptDelta>,
|
||||
state: ReducedState,
|
||||
},
|
||||
}
|
||||
|
||||
/// HTTP body for `POST /api/sessions/:id/structured/prompt`.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct StructuredPromptRequest {
|
||||
pub prompt: String,
|
||||
}
|
||||
|
||||
/// Operator decision for a pending ACP permission request.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum StructuredApprovalDecision {
|
||||
AllowOnce,
|
||||
AllowForSession,
|
||||
Deny,
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Client ↔ Daemon control messages (text frames on the attach WS)
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -1144,6 +1269,31 @@ mod tests {
|
||||
assert_eq!(structured, round_trip(&structured));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn structured_projection_types_round_trip_and_default() {
|
||||
let row = TranscriptRow {
|
||||
id: "tool:read-1".into(),
|
||||
kind: TranscriptRowKind::ToolCall,
|
||||
data: serde_json::json!({"name": "vendor.read", "title": "Read"}),
|
||||
};
|
||||
let snapshot = TranscriptSnapshot {
|
||||
cursor: 7,
|
||||
rows: vec![row.clone()],
|
||||
};
|
||||
assert_eq!(snapshot, round_trip(&snapshot));
|
||||
assert_eq!(
|
||||
TranscriptDelta::Patch { row: row.clone() },
|
||||
round_trip(&TranscriptDelta::Patch { row })
|
||||
);
|
||||
|
||||
let state: ReducedState = serde_json::from_value(serde_json::json!({})).unwrap();
|
||||
assert_eq!(state, ReducedState::default());
|
||||
assert_eq!(
|
||||
serde_json::to_value(TranscriptRowKind::AgentThought).unwrap(),
|
||||
serde_json::json!("agent_thought")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn acp_session_id_defaults_to_none_and_round_trips() {
|
||||
// A payload from before #134 carries no `acp_session_id`; it must
|
||||
|
||||
@@ -71,6 +71,31 @@ pub fn attach(id: Uuid) -> String {
|
||||
format!("{API_PREFIX}/attach/{id}")
|
||||
}
|
||||
|
||||
/// `WS /api/structured/:id` — transcript/state snapshots and live deltas.
|
||||
pub fn structured(id: Uuid) -> String {
|
||||
format!("{API_PREFIX}/structured/{id}")
|
||||
}
|
||||
|
||||
/// `GET /api/sessions/:id/structured/replay` — cursor-bounded ACP history.
|
||||
pub fn structured_replay(id: Uuid) -> String {
|
||||
format!("{SESSIONS}/{id}/structured/replay")
|
||||
}
|
||||
|
||||
/// `POST /api/sessions/:id/structured/prompt` — send an ACP prompt.
|
||||
pub fn structured_prompt(id: Uuid) -> String {
|
||||
format!("{SESSIONS}/{id}/structured/prompt")
|
||||
}
|
||||
|
||||
/// `POST /api/sessions/:id/structured/cancel` — cancel an ACP turn.
|
||||
pub fn structured_cancel(id: Uuid) -> String {
|
||||
format!("{SESSIONS}/{id}/structured/cancel")
|
||||
}
|
||||
|
||||
/// `POST /api/sessions/:id/structured/approvals/:nonce` — answer ACP permission.
|
||||
pub fn structured_approval(id: Uuid, nonce: &str) -> String {
|
||||
format!("{SESSIONS}/{id}/structured/approvals/{nonce}")
|
||||
}
|
||||
|
||||
/// Axum-style patterns for the two parameterised routes, so the server
|
||||
/// registers the same paths [`session`] and [`attach`] build.
|
||||
pub mod patterns {
|
||||
@@ -80,6 +105,11 @@ pub mod patterns {
|
||||
pub const SESSION_PROMPT: &str = "/api/sessions/:id/prompt";
|
||||
pub const SESSION_FOCUS: &str = "/api/sessions/:id/focus";
|
||||
pub const ATTACH: &str = "/api/attach/:id";
|
||||
pub const STRUCTURED: &str = "/api/structured/:id";
|
||||
pub const STRUCTURED_REPLAY: &str = "/api/sessions/:id/structured/replay";
|
||||
pub const STRUCTURED_PROMPT: &str = "/api/sessions/:id/structured/prompt";
|
||||
pub const STRUCTURED_CANCEL: &str = "/api/sessions/:id/structured/cancel";
|
||||
pub const STRUCTURED_APPROVAL: &str = "/api/sessions/:id/structured/approvals/:nonce";
|
||||
}
|
||||
|
||||
/// A daemon base URL that could not be turned into a WebSocket base.
|
||||
@@ -206,6 +236,22 @@ mod tests {
|
||||
attach(id()),
|
||||
"/api/attach/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50"
|
||||
);
|
||||
assert_eq!(
|
||||
structured(id()),
|
||||
"/api/structured/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50"
|
||||
);
|
||||
assert_eq!(
|
||||
structured_replay(id()),
|
||||
"/api/sessions/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50/structured/replay"
|
||||
);
|
||||
assert_eq!(
|
||||
structured_prompt(id()),
|
||||
"/api/sessions/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50/structured/prompt"
|
||||
);
|
||||
assert_eq!(
|
||||
structured_cancel(id()),
|
||||
"/api/sessions/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50/structured/cancel"
|
||||
);
|
||||
assert_eq!(
|
||||
attach_url("https://laptop.lan:7070", id()).unwrap(),
|
||||
"wss://laptop.lan:7070/api/attach/6f1a7c0e-0f5e-4a2b-9a3d-6b1c2d3e4f50"
|
||||
@@ -240,6 +286,22 @@ mod tests {
|
||||
patterns::ATTACH.trim_end_matches(":id"),
|
||||
attach(id()).trim_end_matches(&id().to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
patterns::STRUCTURED.trim_end_matches(":id"),
|
||||
structured(id()).trim_end_matches(&id().to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
patterns::STRUCTURED_REPLAY.trim_end_matches(":id/structured/replay"),
|
||||
session(id()).trim_end_matches(&id().to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
patterns::STRUCTURED_PROMPT.trim_end_matches(":id/structured/prompt"),
|
||||
session(id()).trim_end_matches(&id().to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
patterns::STRUCTURED_CANCEL.trim_end_matches(":id/structured/cancel"),
|
||||
session(id()).trim_end_matches(&id().to_string())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -258,5 +320,9 @@ mod tests {
|
||||
assert!(path.starts_with(API_PREFIX), "{path} escapes {API_PREFIX}");
|
||||
}
|
||||
assert!(attach(id()).starts_with(API_PREFIX));
|
||||
assert!(structured(id()).starts_with(API_PREFIX));
|
||||
assert!(structured_replay(id()).starts_with(API_PREFIX));
|
||||
assert!(structured_prompt(id()).starts_with(API_PREFIX));
|
||||
assert!(structured_cancel(id()).starts_with(API_PREFIX));
|
||||
}
|
||||
}
|
||||
|
||||
+18
-6
@@ -18,10 +18,14 @@ wizard, and cleans up — only the unified `maestro` binary ends up persisted in
|
||||
|
||||
**Updating is the same command.** Re-running `./install.sh` detects an existing
|
||||
systemd unit, refreshes it, and runs `systemctl --user restart maestro` instead
|
||||
of `start`. No `--update` flag needed. **The restart keeps your sessions:** the unit sets
|
||||
of `start`. No `--update` flag needed. **The restart keeps your terminal sessions:** the unit sets
|
||||
`KillMode=process`, so systemd signals only the daemon — the tmux server (and
|
||||
every session) survives, and the new daemon re-adopts them on start. A unit
|
||||
written before this default lacks the line; re-run `./install.sh` to refresh it.
|
||||
every tmux-backed session) survives, and the new daemon re-adopts them on
|
||||
start. Structured sessions (an agent run as a daemon child over ACP) are not
|
||||
tmux panes, so shutdown ends their active turn; the transcript survives and
|
||||
the next daemon attempts one resume (`docs/RESTART.md#structured-sessions`). A
|
||||
unit written before this default lacks the line; re-run `./install.sh` to
|
||||
refresh it.
|
||||
|
||||
Inside the script, `cargo install --git https://git.naps.pt/naps62/maestro …`
|
||||
uses your already-configured git credentials for this host (HTTPS helper or
|
||||
@@ -94,7 +98,10 @@ running a local daemon, for a host that only talks to another machine's.
|
||||
|
||||
The daemon unit carries the same `KillMode=process` as the wizard-written one,
|
||||
so `systemctl --user restart maestro-daemon` leaves the tmux server and every
|
||||
session alive.
|
||||
terminal session alive. Structured sessions end their active turn on
|
||||
shutdown and resume once on the next daemon: ACP state comes back via
|
||||
`session/load`, while the event log only replays Maestro's own transcript
|
||||
projection (`docs/RESTART.md#structured-sessions`).
|
||||
|
||||
## Thin builds for single-role hosts
|
||||
|
||||
@@ -208,8 +215,13 @@ When the adapter is missing the spawn still creates the session, marked dead
|
||||
with the install command above as its activity detail, so the sidebar says
|
||||
what to run. The adapter is a child of the daemon: it ends with a `DELETE
|
||||
/api/sessions/:id` (`session/cancel`, then `SIGTERM`) and with the daemon
|
||||
itself. Terminal sessions keep surviving restarts through tmux; structured
|
||||
ones do not yet.
|
||||
itself. A daemon restart ends an in-flight structured turn, but preserves its
|
||||
worktree, session record, and event-log transcript. The replacement daemon
|
||||
starts a new adapter, resumes it with `session/load`, and replays the
|
||||
transcript. Terminal sessions keep surviving restarts through tmux. See
|
||||
`docs/STRUCTURED-VIEW.md` for the full contract — row kinds, projections, the
|
||||
handshake, and the approval and recovery rules — and `docs/RESTART.md` for
|
||||
what a client observes across the restart.
|
||||
|
||||
## The browser UI
|
||||
|
||||
|
||||
+39
-4
@@ -2,10 +2,16 @@
|
||||
|
||||
Maestro is upgraded in place: the operator reinstalls the binary and systemd
|
||||
restarts the daemon under every browser tab and TUI that is attached to it.
|
||||
tmux keeps the sessions alive across that (see `docs/INSTALL.md`), but clients
|
||||
lose their sockets. This document is the contract for what a client does about
|
||||
it — what the daemon publishes, how a client tells a restart from a blip, and
|
||||
what the user sees while it happens.
|
||||
tmux keeps **terminal** sessions alive across that (see `docs/INSTALL.md`),
|
||||
but clients lose their sockets either way. This document is the contract for
|
||||
what a client does about it — what the daemon publishes, how a client tells a
|
||||
restart from a blip, and what the user sees while it happens.
|
||||
|
||||
A **structured** session (`docs/STRUCTURED-VIEW.md`) has no tmux pane behind
|
||||
it to survive on: its agent is a child of the daemon process itself, so a
|
||||
restart takes it down with the daemon. See
|
||||
[Structured sessions](#structured-sessions) below for exactly what that
|
||||
costs and what it doesn't.
|
||||
|
||||
## What the daemon publishes
|
||||
|
||||
@@ -68,6 +74,35 @@ resolves, so a blocked client is never a trapped one. It clears itself the
|
||||
moment a probe succeeds — there is no "retry" button, because the client is
|
||||
already retrying.
|
||||
|
||||
## Structured sessions
|
||||
|
||||
Everything above describes a **client's** view of a restart, and it holds for
|
||||
a structured session exactly as written — the same three verdicts, the same
|
||||
status indicator, the same overlay. What differs is what survives on the
|
||||
**daemon** side, because a structured session's agent is a daemon child, not
|
||||
a tmux pane:
|
||||
|
||||
- A restart **ends the active turn**. There is no adapter process left to
|
||||
finish it, and no tmux pane keeping it alive underneath.
|
||||
- The **transcript survives**, in the per-session event log
|
||||
(`docs/STRUCTURED-VIEW.md#persistence-recovery-and-dead-sessions`) — a
|
||||
graceful shutdown marks the session for one resume attempt. Recovery is
|
||||
two separate operations, not one: the next daemon calls `session/load` so
|
||||
the adapter restores its own ACP session, but whatever history the
|
||||
adapter emits during that call is discarded, not replayed into anything —
|
||||
the daemon already has that history on disk. Separately, the daemon
|
||||
rebuilds its own projection by folding the persisted event log back
|
||||
through it. An ungraceful death (a crash, `kill -9`) leaves no resume
|
||||
marker, and the session stays dead permanently.
|
||||
- **Pending approvals and their nonces do not survive.** Both live only in
|
||||
the old daemon's memory; any ACP permission request still mid-flight when
|
||||
the daemon exits is answered `Cancelled` on the way down, and a resumed
|
||||
session starts with no pending approval at all.
|
||||
|
||||
`docs/STRUCTURED-VIEW.md` is the full contract for all of this — the event
|
||||
log's shape, the recovery marker, and exactly which kind of session death is
|
||||
resumable.
|
||||
|
||||
## Timing
|
||||
|
||||
- **Grace window** — 1200 ms between the socket dropping and the overlay
|
||||
|
||||
+22
-5
@@ -231,7 +231,24 @@ cutover points land within one tick.
|
||||
|
||||
## Precedence
|
||||
|
||||
An agent-reported `ActivityState` (#105) overrides the daemon's inference for
|
||||
### Activity source by session kind
|
||||
|
||||
The daemon supplies one `activity` field to both clients, but its source depends
|
||||
on the session kind:
|
||||
|
||||
| Session kind | Source |
|
||||
|---|---|
|
||||
| Terminal | The existing agent-report override and five-minute TTL, falling back to PTY quiescence, foreground process and `/proc` input-block inference. |
|
||||
| Structured | ACP state directly: a pending approval is `AwaitingInput`; otherwise an in-flight turn is `Active`; no turn is `Idle`. A failed turn or dead structured session is `Error`, and the next turn clears a failed-turn error. |
|
||||
|
||||
Structured sessions never enter the terminal inference path and ignore activity
|
||||
reports inherited through agent hooks. They have no PTY whose output or blocked
|
||||
read could describe their state. This is a second source, not a replacement for
|
||||
the terminal source.
|
||||
|
||||
### Terminal report override
|
||||
|
||||
For terminal sessions, an agent-reported `ActivityState` (#105) overrides the daemon's inference for
|
||||
**five minutes** (the TTL is fixed by the daemon; re-reporting extends it).
|
||||
When the TTL expires, inference resumes and the session's reported detail —
|
||||
if any — clears with the report. Clients never blend the two: whichever source
|
||||
@@ -281,10 +298,10 @@ session is genuinely `Active` again — new work, not merely a refocus. Only
|
||||
after that fresh `Active` cycle does the *next* `AwaitingInput` glow again.
|
||||
Unfocusing and refocusing alone never re-arms it.
|
||||
|
||||
This applies uniformly to `AwaitingInput` from either source — the daemon's
|
||||
own inference or an agent's report (#105) — since the rail draws them
|
||||
identically. It does not touch `Error`; that state's own TTL (below) is
|
||||
unrelated and unaffected by focus.
|
||||
This applies uniformly to `AwaitingInput` from terminal inference, an agent
|
||||
report (#105), or a structured session's pending approval, since the rail draws
|
||||
them identically. It does not touch `Error`; terminal reports keep their TTL,
|
||||
while a structured failed-turn error clears when the next turn starts.
|
||||
|
||||
Each client reports its own pane's focus with `POST /api/sessions/:id/focus`
|
||||
(`{"focused": bool}`) whenever the pane it is showing changes — on attach, on
|
||||
|
||||
@@ -0,0 +1,372 @@
|
||||
# STRUCTURED-VIEW.md — the structured session contract
|
||||
|
||||
The contract for a structured session (`view: Structured`, #133): an agent run
|
||||
as a daemon child over the Agent Client Protocol (ACP) instead of in a tmux
|
||||
pane. Alongside `docs/WORKTREES.md`, `docs/SIDEBAR.md` and `docs/RESTART.md`,
|
||||
read this before changing anything that renders a structured session — both
|
||||
the web and TUI renderers are written against it.
|
||||
|
||||
It covers the eight transcript row kinds, what the daemon decides versus what
|
||||
a client decides, the two projections and their delta/cursor semantics, the
|
||||
ACP handshake and the capabilities it declines, the adapter's install
|
||||
command, and the approval nonce rules. **Non-goal: the detached runner.** It
|
||||
does not exist yet, and nothing here describes it.
|
||||
|
||||
## What a structured session is
|
||||
|
||||
A terminal session's agent runs inside a tmux pane; a structured session's
|
||||
agent runs as a subprocess of the daemon itself, speaking ACP over stdio. The
|
||||
daemon is the ACP **client**; the adapter process, `claude-code-acp`, is the
|
||||
ACP **agent** — it wraps Claude Code's own SDK and translates the model's
|
||||
tool calls into ACP `session/update` notifications instead of drawing them to
|
||||
a pane. `crates/maestro-acp` owns the daemon's side of that connection;
|
||||
`crates/maestro-daemon/src/projection.rs` folds what it receives into the two
|
||||
projections below.
|
||||
|
||||
The child is a real child of the daemon process: same process group, and on
|
||||
Linux marked with `PR_SET_PDEATHSIG` so it dies with the daemon even if the
|
||||
daemon exits without cleaning up; other platforms have no such signal and
|
||||
depend on an orderly shutdown/drop to terminate it. The ordinary path on
|
||||
every platform is `AcpSession::terminate` (`session/cancel`, a short grace,
|
||||
`SIGTERM`, then `SIGKILL`), called from both `DELETE /api/sessions/:id` and
|
||||
daemon shutdown.
|
||||
`docs/WORKTREES.md`'s kill-guard rule — an unforced kill refused while the
|
||||
session's worktree holds unsaved work — applies to a structured session
|
||||
exactly as it does to a terminal one; only what gets terminated differs (an
|
||||
ACP handle instead of a tmux pane).
|
||||
|
||||
## The adapter
|
||||
|
||||
`ADAPTER_BIN` (`claude-code-acp`) is resolved by walking `PATH` — the
|
||||
session's own `PATH` env var if the spawn request set one, the daemon's
|
||||
otherwise — and taking the first executable file named `claude-code-acp` on
|
||||
it. Install it once per host:
|
||||
|
||||
```sh
|
||||
npm install -g --prefix ~/.local @zed-industries/claude-code-acp
|
||||
```
|
||||
|
||||
That is `maestro_acp::INSTALL_COMMAND`, and it is not just documentation: it
|
||||
is baked into `AcpError::AdapterMissing`'s message. When the adapter cannot
|
||||
be found, spawn still creates the session — **Dead**, with that install
|
||||
command as its `activity_detail` — so the sidebar names the fix instead of
|
||||
the session silently never appearing (see `docs/INSTALL.md` for the full
|
||||
install writeup, including the systemd `PATH` caveat). The adapter also needs
|
||||
a logged-in Claude Code (`claude /login`); a missing login surfaces the same
|
||||
way, via the adapter's own stderr tail in the failure message.
|
||||
|
||||
The handshake is bounded by `HANDSHAKE_TIMEOUT` (60s) — long enough for a
|
||||
slow machine to boot a node process and the Claude Code SDK behind it, never
|
||||
long enough to hang a spawn indefinitely. Any handshake failure — missing
|
||||
adapter, early exit, a protocol error, or the timeout — leaves no orphaned
|
||||
process: `spawn` closes and reaps the child itself before returning the
|
||||
error.
|
||||
|
||||
## The ACP handshake
|
||||
|
||||
`initialize` is where the daemon states what kind of client it is. It
|
||||
declares, deliberately, almost nothing:
|
||||
|
||||
| Capability | Declared | Why |
|
||||
| --- | --- | --- |
|
||||
| `fs.readTextFile` | `false` | The adapter uses Claude Code's own Read tool instead of asking the daemon to read a file on its behalf — the same tool a terminal-view Claude Code session uses. |
|
||||
| `fs.writeTextFile` | `false` | Same reasoning, for Write. |
|
||||
| `terminal` | `false` | The adapter runs Claude Code's own Bash tool rather than asking the daemon to open a terminal for it. |
|
||||
|
||||
Declining all three keeps the daemon out of the file/terminal surface
|
||||
entirely — the adapter already has direct access to the session's `cwd`, and
|
||||
routing every read, write, and shell command through the daemon would only
|
||||
add a hop with no new capability. Every other capability namespace ACP
|
||||
defines (session extensions, auth, elicitation) is simply left at its
|
||||
default; the daemon does not advertise support because `claude-code-acp` has
|
||||
never asked for it, not because it was weighed and refused.
|
||||
|
||||
The one client method that *is* implemented for real is
|
||||
`session/request_permission` (#139) — see [Approvals](#approvals) below.
|
||||
Before #139 it was a stub that declined every request; that stub is gone now
|
||||
that a live implementation exists.
|
||||
|
||||
`session/new` opens a fresh ACP session on every ordinary spawn. A respawn
|
||||
after a daemon restart instead sets `SpawnConfig::load_session(id)` and runs
|
||||
`session/load` with the ACP session id the original handshake returned
|
||||
(`Session::acp_session_id` on the wire) — the adapter must advertise
|
||||
`agent_capabilities.load_session`, or the handshake fails outright naming
|
||||
that. Whatever history the adapter streams back while `session/load` is in
|
||||
flight is dropped on arrival, deliberately: the daemon's own event log
|
||||
already holds that history, and forwarding it too would duplicate every row
|
||||
in the projections below.
|
||||
|
||||
## The eight transcript row kinds
|
||||
|
||||
`TranscriptRowKind` (`maestro-protocol`) is the alphabet a structured
|
||||
transcript is written in. Every row has a stable `id` (so later deltas can
|
||||
address it), a `kind`, and a `data: Value` that preserves the underlying ACP
|
||||
payload — clients depend on ACP's *shape* without depending on ACP as a
|
||||
crate.
|
||||
|
||||
| Kind | Carries | Row identity |
|
||||
| --- | --- | --- |
|
||||
| `User` | An echoed `user_message_chunk` — the prompt text as ACP saw it. | `user:<message_id>`, or `user:<seq>` when the chunk carries no id. |
|
||||
| `AgentText` | An `agent_message_chunk` — the agent's visible reply, streamed. | `agent:<message_id>` / `agent:<seq>`. Later chunks for the same id are appended into `data.content.text` in place, not appended as new rows. |
|
||||
| `AgentThought` | An `agent_thought_chunk` — the model's reasoning stream. | `thought:<message_id>` / `thought:<seq>`, coalesced the same way as `AgentText`. |
|
||||
| `ToolCall` | A `tool_call` / `tool_call_update` pair whose content carries no diff. | `tool:<tool_call_id>` — one row for the call's whole life; updates patch it in place, they never create a second row. |
|
||||
| `ToolDiff` | The same tool-call machinery, when the tool's content includes a `Diff` block. | Same `tool:<tool_call_id>` identity as `ToolCall`; the *kind* flips between the two as the tool's own content changes, not the row. |
|
||||
| `Approval` | A daemon-originated permission request (`RequestPermissionRequest`), serialized without its nonce. | `approval:<uuid>` — minted fresh per request, unrelated to the ACP request's own id. |
|
||||
| `Plan` | A `plan` update — the agent's current step list. | The fixed id `"plan"`. Each new plan **replaces** the row wholesale; entries are not diffed against the previous plan. |
|
||||
| `Notice` | The raw JSON of any `session/update` variant the projection does not special-case. | `notice:<seq>`. |
|
||||
|
||||
`Notice` is the projection's forward-compatibility seam: ACP adds
|
||||
notification variants over time, and an unrecognised one becomes a generic
|
||||
row instead of being silently dropped or making the daemon reject the whole
|
||||
stream. A client that does not know what to do with a `Notice` can render it
|
||||
as an opaque, collapsed line — that is a reasonable floor, not a client bug.
|
||||
|
||||
Rendering is entirely a client concern. The projection's job stops at
|
||||
folding ACP into these eight shapes; markdown formatting, diff rendering,
|
||||
tool-card treatment, and how a `Notice` is presented are all renderer
|
||||
choices, not daemon ones.
|
||||
|
||||
## Daemon decisions vs. client decisions
|
||||
|
||||
**The daemon decides:**
|
||||
|
||||
- Which ACP `session/update` becomes which row kind, and under what id — the
|
||||
fold in `projection.rs` is the one place this logic lives, so the web and
|
||||
TUI renderers can never disagree about it.
|
||||
- Turn lifecycle: when a turn begins, and whether an ACP response, a cancel,
|
||||
or a failure ends it (`TurnState.responding` / `.thinking` /
|
||||
`.active_tool_calls` are derived, not renderer-computed).
|
||||
- Approval nonce minting, secrecy, and the single-active-approval rule (see
|
||||
below) — a client never sees an ACP permission request before the daemon
|
||||
has already turned it into an `Approval` row and a nonce.
|
||||
- What happens to an ACP update variant nobody has taught the daemon about
|
||||
yet (falls back to `Notice` rather than erroring).
|
||||
- Persistence and replay: what is written to the event log, in what order,
|
||||
and how a restart resumes it.
|
||||
|
||||
**A client decides:**
|
||||
|
||||
- How each row kind is drawn — markdown for `AgentText`/`AgentThought`, a
|
||||
diff view for `ToolDiff`, a tool card for `ToolCall`, a checklist for
|
||||
`Plan`, and a floor presentation for `Notice`.
|
||||
- How `responding` vs. `thinking` are distinguished visually, if at all.
|
||||
- How the operator is asked to resolve an `Approval` row — the daemon only
|
||||
exposes the three-way decision (`AllowOnce` / `AllowForSession` / `Deny`),
|
||||
never the UI that solicits it.
|
||||
- Scrolling, collapsing, and every other presentation-only behaviour.
|
||||
|
||||
## The two projections
|
||||
|
||||
`Projection` (daemon-only) is folded once from the durable ACP stream and
|
||||
exposes two independent views, both defined in `maestro-protocol`:
|
||||
|
||||
- **`TranscriptSnapshot { cursor, rows }`** — the complete ordered list of
|
||||
transcript rows built so far, plus the log position (`cursor`) it reflects.
|
||||
It is intentionally always the *whole* transcript, not a windowed one: a
|
||||
tool row patched much later must still find its original entry.
|
||||
- **`ReducedState`** — one whole-session snapshot folded over every event
|
||||
seen: `turn` (the per-turn indicators above), `pending_approval`, `plan`,
|
||||
`usage`/`context`, `model`, and `mode`. Like `TranscriptSnapshot`, it is
|
||||
always full-history, never a delta — a client that only wants "is a turn
|
||||
active right now" never has to replay anything to answer that.
|
||||
|
||||
Changes to the transcript travel as `TranscriptDelta`, tagged `type`:
|
||||
`Append { row }` (a new row), `Patch { row }` (an existing row, addressed by
|
||||
`id`, replaced wholesale), and `Remove { id }`. `Remove` is defined on the
|
||||
wire for forward compatibility; nothing in the current projection emits it —
|
||||
every row, once appended, is only ever patched or left alone.
|
||||
|
||||
### Cursor and replay semantics
|
||||
|
||||
The event log's own line position is the cursor: 1-based, shared by ACP
|
||||
notifications and daemon-generated rows alike (`sidecar.rs`'s
|
||||
`PersistedEvent` envelope is what lets an `Approval` row share a cursor
|
||||
sequence with raw ACP JSON without pretending to be ACP traffic). Two ways to
|
||||
read it:
|
||||
|
||||
- **`WS /api/structured/:id`** — on connect, sends a `TranscriptSnapshot` and
|
||||
a `ReducedState` covering the whole log as it stands, then streams
|
||||
`ProjectionUpdate { transcript, state }` for everything that happens next.
|
||||
There is no client-supplied resume cursor on this socket: every connection
|
||||
gets the full snapshot, not a gap-filled continuation, so a client never
|
||||
needs the replay endpoint just to obtain the current transcript. Use
|
||||
replay instead for cursor-bounded pagination through the durable log —
|
||||
history from before this connection, fetched a page at a time.
|
||||
- **`GET /api/sessions/:id/structured/replay`** — cursor-bounded pagination
|
||||
over the durable log, returning one `StructuredReplayEvent` (`cursor`,
|
||||
`transcript`, `state`) per matching line. `?since=<n>` returns the first
|
||||
page after `n` (`since=0` selects from the beginning, i.e. the first
|
||||
page); a client pages forward from there using the cursor of the last
|
||||
event returned. `?before=<n>` returns the page immediately before `n`,
|
||||
still in ascending order — passing both is a `400`. `?limit` defaults to
|
||||
100 and is clamped to 500. Each call re-folds
|
||||
the entire log from scratch to compute the state at every returned cursor,
|
||||
so a page reflects exactly the *durable* state at its cursor, not an
|
||||
approximation of it — at the cost of redoing the whole fold per request.
|
||||
That durable state is not always identical to what a live client saw at
|
||||
that moment, though: turn lifecycle transitions are broadcast live without
|
||||
a durable event backing them (see [Prompt and cancel](#prompt-and-cancel-bounded-liveness)),
|
||||
and a restored `Approval` row carries no pending nonce, because the nonce
|
||||
never reached disk (see [Approvals](#approvals)) — replay is exact and
|
||||
reconstructible, not a perfect record of everything the live view showed.
|
||||
A session that is not a live structured session (terminal, or a dead
|
||||
adapter) answers `409 not_structured` from either route rather than a
|
||||
coherent-looking but stale reply.
|
||||
|
||||
## Approvals
|
||||
|
||||
An ACP `session/request_permission` callback becomes an `Approval` row plus a
|
||||
pending decision, entirely on the daemon side:
|
||||
|
||||
- **Generation.** The daemon mints the nonce itself — a fresh
|
||||
`Uuid::new_v4()` string per request — rather than using anything ACP's own
|
||||
request carries. ACP permission callbacks have no request id of their own
|
||||
that would double as one.
|
||||
- **Live-only placement.** The nonce lives in exactly one place: the
|
||||
in-memory `pending_approvals` map keyed by nonce, and its mirror in
|
||||
`ReducedState.pending_approval.nonce` on the live wire. It is never part of
|
||||
the `Approval` row's `data` — the row is `RequestPermissionRequest`
|
||||
serialized *without* the nonce.
|
||||
- **Secrecy from the agent and from durable history.** The adapter itself
|
||||
never learns the nonce — it is a daemon-to-client secret, never sent back
|
||||
over the ACP connection. It is likewise never written to the event log:
|
||||
restoring an `Approval` row from disk (`Projection::restore_approval`)
|
||||
produces a historical row with no `pending_approval` in state, because the
|
||||
nonce that would make it "pending" never made it to disk in the first
|
||||
place. A restart therefore cannot resume a pending approval — see
|
||||
[Persistence](#persistence-recovery-and-dead-sessions).
|
||||
- **One live approval at a time.** A new permission request mints its own
|
||||
nonce, then cancels whatever was already pending (`cancel_pending_approvals`)
|
||||
before installing itself as the new pending approval — ACP serializes
|
||||
requests through one connection, so this only ever fires if an adapter
|
||||
nonetheless overlaps two. Either way, the prior pending request is
|
||||
cancelled/cleared before the new one is installed, so the newest request
|
||||
wins.
|
||||
- **Single-use and duplicate resolution.**
|
||||
`POST /api/sessions/:id/structured/approvals/:nonce` **always answers
|
||||
`204`** for a known, live structured session — whether the nonce is the
|
||||
one currently pending, one already consumed by an earlier answer, or one
|
||||
that never existed. Only an unknown or non-structured *session* answers
|
||||
otherwise (`404` / `409`). This is deliberate: two clients racing to answer the same
|
||||
approval must not turn a harmless duplicate click into a client-visible
|
||||
error. Whichever `POST` reaches the daemon first removes the nonce from
|
||||
`pending_approvals` and is the one whose decision actually reaches the
|
||||
adapter; every later `POST` for that nonce is a no-op `204`.
|
||||
- **Cancellation vs. denial.** A turn cancel or a session shutdown resolves
|
||||
any pending approval with ACP's `Cancelled` outcome, not a `Deny` decision
|
||||
— the adapter should read those as "the operation was withdrawn," not "the
|
||||
operator refused it."
|
||||
- **Decision mapping.** `AllowOnce` and `AllowForSession` select the ACP
|
||||
option of kind `AllowOnce` / `AllowAlways` from the request's own option
|
||||
list. `Deny` prefers a one-shot refusal (`RejectOnce`) and falls back to a
|
||||
permanent one (`RejectAlways`) only when that is the sole rejection option
|
||||
offered; if neither is present, it answers `Cancelled`.
|
||||
|
||||
## Prompt and cancel: bounded liveness
|
||||
|
||||
`POST /api/sessions/:id/structured/prompt` and `.../cancel` are serialized
|
||||
against each other through one per-session `operation` lock
|
||||
(`AcpEventStream::operation`), because ACP permission callbacks carry no
|
||||
per-request id — the daemon's own notion of "the active turn" is the only
|
||||
thing a callback can be attributed to, so at most one turn may ever be
|
||||
in flight, and a cancelled turn must fully settle before the next prompt is
|
||||
allowed to claim the daemon's idea of "the active turn."
|
||||
|
||||
- A prompt claims the turn and dispatches it to ACP as one operation. While a
|
||||
turn is active, a second prompt gets `409 turn_in_flight` rather than
|
||||
queuing — one active turn per session, never a hidden queue of prompts.
|
||||
- Cancel sends `session/cancel`, clears any pending approval as `Cancelled`,
|
||||
and ends the turn's client-visible lifecycle immediately. If the cancelled
|
||||
turn was still *dispatched* to ACP (waiting on its response), the daemon
|
||||
cannot simply forget it: ACP has not confirmed the cancel yet, and a new
|
||||
prompt claiming "the active turn" while the old one is still outstanding
|
||||
would make the next permission callback ambiguous between the two.
|
||||
- So a cancelled-but-still-dispatched turn must **settle within
|
||||
`CANCEL_GRACE` (500ms)** — either ACP acknowledges the prompt (however it
|
||||
resolves) or that grace period runs out. If it settles in time, the next
|
||||
prompt proceeds normally. If it does not, the daemon does not guess: it
|
||||
marks the whole structured session dead (`fail_cancelled_acp_turn`) rather
|
||||
than risk a callback resolving against the wrong turn. This is the bounded
|
||||
half of "bounded liveness" — a structured session's prompt/cancel dance
|
||||
either resolves promptly or the session is declared unusable, never left
|
||||
in an indefinite ambiguous state.
|
||||
|
||||
## Persistence, recovery, and dead sessions
|
||||
|
||||
A structured session's durable state is three files in the sidecar
|
||||
directory: the sidecar itself (`<id>.json`), plus two next to it:
|
||||
|
||||
- **`<id>.events.jsonl`** — the unified event log. Each line is either a raw
|
||||
ACP `SessionNotification` (kept in its original JSON so old logs stay
|
||||
readable) or a `{"maestroEvent": "approval", "row": …}` envelope for a
|
||||
daemon-generated row. Both share the same 1-based line-position cursor. A
|
||||
line a hard kill left half-written is terminated before the next append, so
|
||||
it keeps its position and is skipped as malformed rather than corrupting
|
||||
what follows. An append that fails *while the daemon is running* — a
|
||||
`write_all` that errors after only a prefix reached disk, or a `flush` that
|
||||
errors after a complete write — is rolled back to the exact byte length the
|
||||
file was at before the call, so `last_seq` and the file's line count never
|
||||
disagree and the same log handle can be appended to again immediately (#184).
|
||||
If that rollback itself cannot restore the prior length, the append is
|
||||
fatal: the log's consistency can no longer be promised, so the caller kills
|
||||
the session instead of appending to it again.
|
||||
- **`<id>.recover`** — an empty marker file. Its only meaning is "the daemon
|
||||
that wrote this shut down gracefully while this session was running, and
|
||||
the next daemon may attempt to resume it." It is consumed (deleted) the
|
||||
moment a recovery attempt reads it — one recovery attempt per graceful
|
||||
shutdown, never a standing flag.
|
||||
|
||||
Three ways a structured session ends up `Dead`, each with different
|
||||
persistence consequences:
|
||||
|
||||
1. **The adapter exits, or a notification append to the event log fails,
|
||||
while the daemon keeps running.** (An approval-row append failure is
|
||||
narrower: as long as the log rolled back cleanly, it only cancels the
|
||||
pending approval and rolls the unpersisted `Approval` row back out of the
|
||||
live transcript, without marking the session dead — a snapshot taken after
|
||||
the failure must never show a row durable replay could not reproduce
|
||||
(#184). If the rollback itself did not restore the log's prior length,
|
||||
this narrower path does not apply either: the session is marked dead the
|
||||
same as any other append failure, since the log can no longer promise
|
||||
`last_seq` matches its file.)
|
||||
`mark_session_dead` applies the same natural-exit worktree rule
|
||||
as a terminal session's own pane exiting (`docs/WORKTREES.md`): a pristine
|
||||
worktree is removed, one holding unsaved work is left on disk. No recovery
|
||||
marker is written. This death is permanent — a later daemon restart's
|
||||
`recover()` finds the sidecar, sees no marker, and leaves the session
|
||||
`Dead` without attempting to resume it.
|
||||
2. **A cancelled turn fails to settle within `CANCEL_GRACE`.** Same
|
||||
consequence as (1): the session is marked dead through the same path, no
|
||||
marker, no future resumption.
|
||||
3. **Graceful daemon shutdown**, while the session was still `Running`.
|
||||
`mark_session_dead_after_shutdown` marks the session dead **without**
|
||||
applying the worktree exit rule — the tree is kept exactly as it is,
|
||||
pristine or not, because there is nothing "natural" about this exit — and
|
||||
writes the `.recover` marker. The sidecar on disk therefore says `Dead`,
|
||||
but is eligible for resumption.
|
||||
|
||||
Recovery, on the next daemon's `recover()`: for every `Structured` sidecar
|
||||
not already adopted, the marker is consumed. When one was present and the
|
||||
sidecar carries a stored `acp_session_id`, the daemon spawns a fresh adapter
|
||||
with `SpawnConfig::load_session(acp_session_id)`, replays the
|
||||
entire durable event log into a new `Projection` (rebuilding the transcript
|
||||
and reduced state exactly as they were, with any restored `Approval` row
|
||||
landing as history — never as a re-armed pending approval, since its nonce
|
||||
never reached disk), and only then reopens the log for further appends. What
|
||||
the adapter streams back while its own `session/load` is in flight is
|
||||
discarded rather than appended, so the replayed history is not duplicated
|
||||
(see [The ACP handshake](#the-acp-handshake)). Success flips the session back
|
||||
to `Running`/`Idle`; failure (no stored `acp_session_id`, or the handshake
|
||||
itself failing) leaves it `Dead` with the failure reason as
|
||||
`activity_detail` — the same "tell the operator what to fix" pattern as a
|
||||
missing adapter binary.
|
||||
|
||||
Pending approvals and their nonces never survive any of this. They live only
|
||||
in the in-memory `pending_approvals` map and the live `ReducedState`, both
|
||||
gone the instant the daemon that held them exits. Whatever ACP permission
|
||||
request was mid-flight when the old daemon died was already answered
|
||||
`Cancelled` on that daemon's own shutdown path, so a resumed session always
|
||||
starts with no pending approval.
|
||||
|
||||
See `docs/RESTART.md` for what a *client* observes across a daemon restart,
|
||||
now that structured sessions exist alongside terminal ones.
|
||||
Reference in New Issue
Block a user