Compare commits

..
10 changed files with 1010 additions and 45 deletions
+41 -3
View File
@@ -42,9 +42,10 @@ use std::sync::{Arc, Mutex};
use std::time::Duration;
use agent_client_protocol::schema::v1::{
CancelNotification, ClientCapabilities, FileSystemCapabilities, Implementation,
InitializeRequest, LoadSessionRequest, 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};
@@ -153,6 +154,10 @@ fn is_executable(path: &Path) -> bool {
enum Command {
Cancel,
Prompt {
text: String,
done: oneshot::Sender<Result<(), String>>,
},
Close,
}
@@ -236,6 +241,18 @@ impl AcpSession {
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) -> Result<oneshot::Receiver<Result<(), String>>, String> {
let (done_tx, done_rx) = oneshot::channel();
self.commands
.send(Command::Prompt {
text,
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) {
@@ -562,6 +579,27 @@ async fn run_connection<T>(
SessionId::new(session_id.as_str()),
));
}
Some(Command::Prompt { text, done }) => {
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();
if let Err(error) = cx.send_request(request).on_receiving_result(move |result| {
let callback_done = callback_done.clone();
async move {
if let Some(done) = callback_done.lock().expect("prompt sender").take() {
let _ = done.send(result.map(|_| ()).map_err(|e| e.to_string()));
}
Ok(())
}
}) {
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,
@@ -29,6 +29,10 @@ Environment knobs, all optional:
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
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
@@ -65,6 +69,7 @@ signal.signal(signal.SIGTERM, on_sigterm)
session_id = f"fake-{os.getpid()}"
ticks = 0
prompt_failures = 0
def chunk(text):
@@ -137,6 +142,16 @@ for raw in sys.stdin:
send(chunk("final on cancel"))
if os.environ.get("FAKE_ACP_EXIT_ON_CANCEL") == "1":
sys.exit(0)
elif method == "session/prompt":
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}"}})
+192 -2
View File
@@ -21,12 +21,14 @@ use maestro_config::SpawnPreset;
use maestro_protocol::{
routes, ApiError, CatalogEvent, CreateSessionRequest, DaemonInfo, GitRoot, NameBatch,
RenameSessionRequest, ReportActivityRequest, SendInputRequest, Session, SetFocusRequest,
PROTOCOL_VERSION,
StructuredEvent, StructuredPromptRequest, PROTOCOL_VERSION,
};
use serde::Deserialize;
use uuid::Uuid;
use crate::projection::TurnLifecycle;
use crate::session::SessionManager;
use crate::sidecar::EventCursor;
#[derive(Debug, Clone)]
pub struct LocalApiState {
@@ -64,7 +66,11 @@ 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));
#[cfg(feature = "haiku-autoname")]
{
router = router.route(routes::patterns::SESSION_PROMPT, post(session_prompt));
@@ -369,6 +375,121 @@ 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 {
let (acp, turn) = match s.manager.begin_acp_turn(id).await {
Ok(crate::session::BeginAcpTurn::Started(acp, turn)) => (acp, turn),
Ok(crate::session::BeginAcpTurn::InFlight) => {
return error_response(
StatusCode::CONFLICT,
"turn_in_flight",
"the structured session already has an active turn",
)
}
Ok(crate::session::BeginAcpTurn::Unavailable) => {
return error_response(
StatusCode::CONFLICT,
"not_structured",
"session is not a live structured session",
)
}
Err(e) => {
let info = e.to_error_info();
return error_response(session_error_status(&info.code), &info.code, &info.message);
}
};
match acp.prompt(body.prompt) {
Ok(done) => {
let manager = s.manager.clone();
tokio::spawn(async move {
let lifecycle = match done.await {
Ok(Ok(())) => TurnLifecycle::Finish,
Ok(Err(_)) | Err(_) => TurnLifecycle::Failure,
};
let _ = manager.apply_acp_turn_lifecycle(id, lifecycle, turn).await;
});
StatusCode::NO_CONTENT.into_response()
}
Err(message) => {
let _ = s
.manager
.apply_acp_turn_lifecycle(id, TurnLifecycle::Failure, turn)
.await;
error_response(StatusCode::BAD_GATEWAY, "acp_prompt_failed", &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)
}
}
}
/// 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
@@ -419,6 +540,75 @@ 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)
// ---------------------------------------------------------------------------
+57 -30
View File
@@ -35,7 +35,8 @@ pub struct Projection {
tools: HashMap<String, ToolCall>,
pending_tool_updates: HashMap<String, Vec<maestro_acp::schema::ToolCallUpdateFields>>,
state: ReducedState,
turn_active: bool,
active_turn: Option<u64>,
next_turn: u64,
turn_tool_calls: HashSet<String>,
}
@@ -104,28 +105,54 @@ impl Projection {
self.state.clone()
}
/// Apply a transport-owned prompt lifecycle transition.
pub fn turn_lifecycle(&mut self, lifecycle: TurnLifecycle) -> ProjectionUpdate {
match lifecycle {
TurnLifecycle::Begin => {
self.turn_active = true;
self.state.turn.responding = true;
self.state.turn.thinking = true;
self.turn_tool_calls.clear();
self.state.turn.active_tool_calls.clear();
}
TurnLifecycle::Finish | TurnLifecycle::Cancel | TurnLifecycle::Failure => {
self.turn_active = false;
self.state.turn.responding = false;
self.state.turn.thinking = false;
self.turn_tool_calls.clear();
self.state.turn.active_tool_calls.clear();
}
pub fn turn_active(&self) -> bool {
self.active_turn.is_some()
}
/// 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.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;
}
ProjectionUpdate {
self.active_turn = None;
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
}
fn content(
@@ -230,28 +257,28 @@ impl Projection {
}
fn agent_text(&mut self) {
if self.turn_active {
if self.turn_active() {
self.state.turn.responding = true;
self.state.turn.thinking = false;
}
}
fn agent_thought(&mut self) {
if self.turn_active {
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 {
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) {
if !self.turn_active() || !self.turn_tool_calls.contains(tool_id) {
return;
}
let active = self.tools.get(tool_id).is_some_and(|tool| {
@@ -538,7 +565,7 @@ mod tests {
);
assert_eq!(projection.state().turn, Default::default());
projection.turn_lifecycle(TurnLifecycle::Begin);
let (_, _) = projection.begin_turn();
assert!(projection.state().turn.responding);
assert!(projection.state().turn.thinking);
projection.apply(
@@ -558,8 +585,8 @@ mod tests {
TurnLifecycle::Cancel,
TurnLifecycle::Failure,
] {
projection.turn_lifecycle(TurnLifecycle::Begin);
projection.turn_lifecycle(terminal);
let (turn, _) = projection.begin_turn();
projection.turn_lifecycle(terminal, turn);
assert!(!projection.state().turn.responding);
assert!(!projection.state().turn.thinking);
}
@@ -571,7 +598,7 @@ mod tests {
next_id: &str,
) {
let mut projection = Projection::default();
projection.turn_lifecycle(TurnLifecycle::Begin);
let (turn, _) = projection.begin_turn();
projection.apply(
1,
&event(serde_json::json!({
@@ -581,11 +608,11 @@ mod tests {
);
assert_eq!(projection.state().turn.active_tool_calls, [unfinished_id]);
projection.turn_lifecycle(terminal);
projection.turn_lifecycle(terminal, turn);
assert!(projection.state().turn.active_tool_calls.is_empty());
assert_eq!(projection.snapshot(1).rows.len(), 1);
projection.turn_lifecycle(TurnLifecycle::Begin);
projection.begin_turn();
projection.apply(
2,
&event(serde_json::json!({
+131 -4
View File
@@ -15,7 +15,7 @@ use chrono::Utc;
use maestro_acp::{AcpSession, SpawnConfig};
use maestro_protocol::{
ActivityState, CatalogEvent, CreateSessionRequest, ErrorInfo, NameSource, Session,
SessionStatus, SessionView, WorktreeSpec, NAME_KEY, NAME_SOURCE_KEY,
SessionStatus, SessionView, StructuredReplayEvent, WorktreeSpec, NAME_KEY, NAME_SOURCE_KEY,
};
use tokio::sync::{broadcast, watch, Mutex};
use uuid::Uuid;
@@ -103,6 +103,15 @@ pub struct SessionRecord {
acp_event_pump: Option<watch::Receiver<bool>>,
}
impl SessionRecord {
fn is_live_structured(&self) -> bool {
self.session.view == SessionView::Structured
&& self.session.status == SessionStatus::Running
&& self.acp.is_some()
&& self.acp_events.is_some()
}
}
#[derive(Debug)]
struct AcpEventStream {
log: EventLog,
@@ -139,6 +148,14 @@ pub enum SessionError {
KillGuarded(maestro_protocol::InTheWay),
}
/// The result of claiming the next prompt turn for a structured ACP session.
#[derive(Debug)]
pub enum BeginAcpTurn {
Started(Arc<AcpSession>, u64),
InFlight,
Unavailable,
}
impl SessionError {
pub fn to_error_info(&self) -> ErrorInfo {
let code = match self {
@@ -333,6 +350,9 @@ impl SessionManager {
let Some(record) = sessions.get(&id) else {
return Ok(None);
};
if !record.is_live_structured() {
return Ok(None);
}
let Some(stream) = &record.acp_events else {
return Ok(None);
};
@@ -357,6 +377,60 @@ impl SessionManager {
.map_err(SessionError::Sidecar)
}
/// Replay durable structured-session data as client-neutral projections.
///
/// The complete log is folded before selecting the requested cursor range,
/// so each returned state is exactly the state at its cursor.
pub async fn read_acp_projection_replay(
&self,
id: Uuid,
cursor: EventCursor,
limit: usize,
) -> Result<Option<Vec<StructuredReplayEvent>>, SessionError> {
let stream = {
let sessions = self.inner.sessions.lock().await;
let record = sessions.get(&id).ok_or(SessionError::NotFound(id))?;
if !record.is_live_structured() {
return Ok(None);
}
record.acp_events.clone()
};
let Some(stream) = stream else {
return Ok(None);
};
let stream = stream.lock().await;
let events = self
.inner
.sidecar
.read_events(id, EventCursor::Since(0), usize::MAX)?;
let mut projection = Projection::default();
let mut replay = Vec::new();
for event in events {
let update = projection.apply(event.seq, &event.notification);
let include = match cursor {
EventCursor::Since(since) => event.seq > since,
EventCursor::Before(Some(before)) => event.seq < before,
EventCursor::Before(None) => true,
};
if include {
replay.push(StructuredReplayEvent {
cursor: event.seq,
transcript: update.transcript,
state: update.state,
});
}
}
drop(stream);
match cursor {
EventCursor::Since(_) => replay.truncate(limit),
EventCursor::Before(_) if replay.len() > limit => {
replay.drain(..replay.len() - limit);
}
_ => {}
}
Ok(Some(replay))
}
/// Subscribe to the two projections of a structured session's ACP log.
///
/// The transcript snapshot and whole reduced state are folded once by the
@@ -379,9 +453,10 @@ impl SessionManager {
> {
let stream = {
let sessions = self.inner.sessions.lock().await;
let Some(record) = sessions.get(&id) else {
let record = sessions.get(&id).ok_or(SessionError::NotFound(id))?;
if !record.is_live_structured() {
return Ok(None);
};
}
let Some(stream) = &record.acp_events else {
return Ok(None);
};
@@ -402,6 +477,7 @@ impl SessionManager {
&self,
id: Uuid,
lifecycle: TurnLifecycle,
turn: u64,
) -> Result<bool, SessionError> {
let stream = {
let sessions = self.inner.sessions.lock().await;
@@ -412,7 +488,58 @@ impl SessionManager {
return Ok(false);
};
let mut stream = stream.lock().await;
let projected = stream.projection.turn_lifecycle(lifecycle);
let Some(projected) = stream.projection.turn_lifecycle(lifecycle, turn) else {
return Ok(false);
};
let _ = stream.projected_live.send(projected);
Ok(true)
}
/// Begin an ACP turn only when the previous one has ended. The projection
/// lock makes the rejection and lifecycle update one indivisible action.
pub async fn begin_acp_turn(&self, id: Uuid) -> Result<BeginAcpTurn, SessionError> {
let (acp, stream) = {
let sessions = self.inner.sessions.lock().await;
let record = sessions.get(&id).ok_or(SessionError::NotFound(id))?;
if !record.is_live_structured() {
return Ok(BeginAcpTurn::Unavailable);
}
(record.acp.clone(), record.acp_events.clone())
};
let (Some(acp), Some(stream)) = (acp, stream) else {
return Ok(BeginAcpTurn::Unavailable);
};
let mut stream = stream.lock().await;
if stream.projection.turn_active() {
return Ok(BeginAcpTurn::InFlight);
}
let (turn, update) = stream.projection.begin_turn();
let _ = stream.projected_live.send(update);
Ok(BeginAcpTurn::Started(acp, turn))
}
/// Cancel an ACP turn and immediately clear its client-facing lifecycle.
pub async fn cancel_acp_turn(&self, id: Uuid) -> Result<bool, SessionError> {
let (acp, stream) = {
let sessions = self.inner.sessions.lock().await;
let record = sessions.get(&id).ok_or(SessionError::NotFound(id))?;
if !record.is_live_structured() {
return Ok(false);
}
(record.acp.clone(), record.acp_events.clone())
};
let (Some(acp), Some(stream)) = (acp, stream) else {
return Ok(false);
};
let mut stream = stream.lock().await;
let Some(turn) = stream.projection.active_turn() else {
return Ok(true);
};
acp.cancel();
let projected = stream
.projection
.turn_lifecycle(TurnLifecycle::Cancel, turn)
.expect("active turn remains current while stream is locked");
let _ = stream.projected_live.send(projected);
Ok(true)
}
+1 -1
View File
@@ -247,7 +247,7 @@ pub enum EventCursor {
}
/// One line of a session's event log.
#[derive(Debug, Clone, PartialEq)]
#[derive(Debug, Clone, PartialEq, serde::Serialize)]
pub struct LoggedEvent {
/// 1-based line position in the log; the cursor for [`EventCursor`].
pub seq: u64,
+48 -4
View File
@@ -232,11 +232,14 @@ async fn projection_snapshot_and_live_stream_share_one_fold() {
assert_eq!(snapshot.rows[0].kind, TranscriptRowKind::AgentText);
assert_eq!(state.turn, Default::default());
assert!(fx
let maestro_daemon::session::BeginAcpTurn::Started(_, turn) = fx
.manager
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Begin)
.begin_acp_turn(session.id)
.await
.expect("begin lifecycle"));
.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")
@@ -264,7 +267,7 @@ async fn projection_snapshot_and_live_stream_share_one_fold() {
assert!(fx
.manager
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Finish)
.apply_acp_turn_lifecycle(session.id, TurnLifecycle::Finish, turn)
.await
.expect("finish lifecycle"));
let finish = tokio::time::timeout(Duration::from_secs(5), live.recv())
@@ -277,6 +280,47 @@ async fn projection_snapshot_and_live_stream_share_one_fold() {
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 recovery_loads_the_acp_session_without_duplicating_history() {
let fx = DaemonFixture::new();
+429 -1
View File
@@ -4,12 +4,16 @@ 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::{
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 +90,430 @@ 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")
}
}
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
}
#[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::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");
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;
+36
View File
@@ -794,6 +794,19 @@ pub struct TranscriptSnapshot {
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")]
@@ -836,6 +849,29 @@ pub struct ReducedState {
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,
}
// ---------------------------------------------------------------------------
// Client ↔ Daemon control messages (text frames on the attach WS)
// ---------------------------------------------------------------------------
+60
View File
@@ -71,6 +71,26 @@ 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")
}
/// Axum-style patterns for the two parameterised routes, so the server
/// registers the same paths [`session`] and [`attach`] build.
pub mod patterns {
@@ -80,6 +100,10 @@ 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";
}
/// A daemon base URL that could not be turned into a WebSocket base.
@@ -206,6 +230,22 @@ 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 +280,22 @@ 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 +314,9 @@ 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));
}
}