feat(app-server): turn/steer API (#10821)

This PR adds a dedicated `turn/steer` API for appending user input to an
in-flight turn.

## Motivation
Currently, steering in the app is implemented by just calling
`turn/start` while a turn is running. This has some really weird quirks:
- Client gets back a new `turn.id`, even though streamed
events/approvals remained tied to the original active turn ID.
- All the various turn-level override params on `turn/start` do not
apply to the "steer", and would only apply to the next real turn.
- There can also be a race condition where the client thinks the turn is
active but the server has already completed it, so there might be bugs
if the client has baked in some client-specific behavior thinking it's a
steer when in fact the server kicked off a new turn. This is
particularly possible when running a client against a remote app-server.

Having a dedicated `turn/steer` API eliminates all those quirks.

`turn/steer` behavior:
- Requires an active turn on threadId. Returns a JSON-RPC error if there
is no active turn.
- If expectedTurnId is provided, it must match the active turn (more
useful when connecting to a remote app-server).
- Does not emit `turn/started`.
- Does not accept turn overrides (`cwd`, `model`, `sandbox`, etc.) or
`outputSchema` to accurately reflect that these are not applied when
steering.
This commit is contained in:
Owen Lin
2026-02-05 16:35:04 -08:00
committed by GitHub
parent 729b016515
commit 0d8b2b74c4
18 changed files with 768 additions and 13 deletions

View File

@@ -26,3 +26,4 @@ mod thread_start;
mod thread_unarchive;
mod turn_interrupt;
mod turn_start;
mod turn_steer;

View File

@@ -0,0 +1,179 @@
#![cfg(unix)]
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_mock_responses_server_sequence;
use app_test_support::create_mock_responses_server_sequence_unchecked;
use app_test_support::create_shell_command_sse_response;
use app_test_support::to_response;
use codex_app_server_protocol::JSONRPCError;
use codex_app_server_protocol::JSONRPCNotification;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::ThreadStartParams;
use codex_app_server_protocol::ThreadStartResponse;
use codex_app_server_protocol::TurnStartParams;
use codex_app_server_protocol::TurnStartResponse;
use codex_app_server_protocol::TurnSteerParams;
use codex_app_server_protocol::TurnSteerResponse;
use codex_app_server_protocol::UserInput as V2UserInput;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test]
async fn turn_steer_requires_active_turn() -> Result<()> {
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let server = create_mock_responses_server_sequence(vec![]).await;
create_config_toml(&codex_home, &server.uri())?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
let steer_req = mcp
.send_turn_steer_request(TurnSteerParams {
thread_id: thread.id,
input: vec![V2UserInput::Text {
text: "steer".to_string(),
text_elements: Vec::new(),
}],
expected_turn_id: "turn-does-not-exist".to_string(),
})
.await?;
let steer_err: JSONRPCError = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_error_message(RequestId::Integer(steer_req)),
)
.await??;
assert_eq!(steer_err.error.code, -32600);
Ok(())
}
#[tokio::test]
async fn turn_steer_returns_active_turn_id() -> Result<()> {
#[cfg(target_os = "windows")]
let shell_command = vec![
"powershell".to_string(),
"-Command".to_string(),
"Start-Sleep -Seconds 10".to_string(),
];
#[cfg(not(target_os = "windows"))]
let shell_command = vec!["sleep".to_string(), "10".to_string()];
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home)?;
let working_directory = tmp.path().join("workdir");
std::fs::create_dir(&working_directory)?;
let server =
create_mock_responses_server_sequence_unchecked(vec![create_shell_command_sse_response(
shell_command.clone(),
Some(&working_directory),
Some(10_000),
"call_sleep",
)?])
.await;
create_config_toml(&codex_home, &server.uri())?;
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let thread_req = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let thread_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(thread_resp)?;
let turn_req = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run sleep".to_string(),
text_elements: Vec::new(),
}],
cwd: Some(working_directory.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
let _task_started: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_started"),
)
.await??;
let steer_req = mcp
.send_turn_steer_request(TurnSteerParams {
thread_id: thread.id,
input: vec![V2UserInput::Text {
text: "steer".to_string(),
text_elements: Vec::new(),
}],
expected_turn_id: turn.id.clone(),
})
.await?;
let steer_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(steer_req)),
)
.await??;
let steer: TurnSteerResponse = to_response::<TurnSteerResponse>(steer_resp)?;
assert_eq!(steer.turn_id, turn.id);
Ok(())
}
fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "danger-full-access"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "responses"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}