[app-server] feat: add Declined status for command exec (#7101)

Add a `Declined` status for when we request an approval from the user
and the user declines. This allows us to distinguish from commands that
actually ran, but failed.

This behaves similarly to apply_patch / FileChange, which does the same
thing.
This commit is contained in:
Owen Lin
2025-11-21 09:19:39 -08:00
committed by GitHub
parent d363a0968e
commit 2ae1f81d84
4 changed files with 254 additions and 36 deletions

View File

@@ -8,6 +8,7 @@ use app_test_support::create_shell_command_sse_response;
use app_test_support::format_with_current_shell_display;
use app_test_support::to_response;
use codex_app_server_protocol::ApprovalDecision;
use codex_app_server_protocol::CommandExecutionRequestApprovalResponse;
use codex_app_server_protocol::CommandExecutionStatus;
use codex_app_server_protocol::FileChangeRequestApprovalResponse;
use codex_app_server_protocol::ItemCompletedNotification;
@@ -329,6 +330,145 @@ async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
Ok(())
}
#[tokio::test]
async fn turn_start_exec_approval_decline_v2() -> Result<()> {
skip_if_no_network!(Ok(()));
let tmp = TempDir::new()?;
let codex_home = tmp.path().to_path_buf();
let workspace = tmp.path().join("workspace");
std::fs::create_dir(&workspace)?;
let responses = vec![
create_shell_command_sse_response(
vec![
"python3".to_string(),
"-c".to_string(),
"print(42)".to_string(),
],
None,
Some(5000),
"call-decline",
)?,
create_final_assistant_message_sse_response("done")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
let mut mcp = McpProcess::new(codex_home.as_path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let start_id = mcp
.send_thread_start_request(ThreadStartParams {
model: Some("mock-model".to_string()),
..Default::default()
})
.await?;
let start_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
)
.await??;
let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
let turn_id = mcp
.send_turn_start_request(TurnStartParams {
thread_id: thread.id.clone(),
input: vec![V2UserInput::Text {
text: "run python".to_string(),
}],
cwd: Some(workspace.clone()),
..Default::default()
})
.await?;
let turn_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
)
.await??;
let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
let started_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let started_notif = mcp
.read_stream_until_notification_message("item/started")
.await?;
let started: ItemStartedNotification =
serde_json::from_value(started_notif.params.clone().expect("item/started params"))?;
if let ThreadItem::CommandExecution { .. } = started.item {
return Ok::<ThreadItem, anyhow::Error>(started.item);
}
}
})
.await??;
let ThreadItem::CommandExecution { id, status, .. } = started_command_execution else {
unreachable!("loop ensures we break on command execution items");
};
assert_eq!(id, "call-decline");
assert_eq!(status, CommandExecutionStatus::InProgress);
let server_req = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await??;
let ServerRequest::CommandExecutionRequestApproval { request_id, params } = server_req else {
panic!("expected CommandExecutionRequestApproval request")
};
assert_eq!(params.item_id, "call-decline");
assert_eq!(params.thread_id, thread.id);
assert_eq!(params.turn_id, turn.id);
mcp.send_response(
request_id,
serde_json::to_value(CommandExecutionRequestApprovalResponse {
decision: ApprovalDecision::Decline,
accept_settings: None,
})?,
)
.await?;
let completed_command_execution = timeout(DEFAULT_READ_TIMEOUT, async {
loop {
let completed_notif = mcp
.read_stream_until_notification_message("item/completed")
.await?;
let completed: ItemCompletedNotification = serde_json::from_value(
completed_notif
.params
.clone()
.expect("item/completed params"),
)?;
if let ThreadItem::CommandExecution { .. } = completed.item {
return Ok::<ThreadItem, anyhow::Error>(completed.item);
}
}
})
.await??;
let ThreadItem::CommandExecution {
id,
status,
exit_code,
aggregated_output,
..
} = completed_command_execution
else {
unreachable!("loop ensures we break on command execution items");
};
assert_eq!(id, "call-decline");
assert_eq!(status, CommandExecutionStatus::Declined);
assert!(exit_code.is_none());
assert!(aggregated_output.is_none());
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await??;
Ok(())
}
#[tokio::test]
async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
skip_if_no_network!(Ok(()));