[app-server & core] introduce new codex error code and v2 app-server error events (#6938)

This PR does two things:
1. populate a new `codex_error_code` protocol in error events sent from
core to client;
2. old v1 core events `codex/event/stream_error` and `codex/event/error`
will now both become `error`. We also show codex error code for
turncompleted -> error status.

new events in app server test:
```
< {
<   "method": "codex/event/stream_error",
<   "params": {
<     "conversationId": "019aa34c-0c14-70e0-9706-98520a760d67",
<     "id": "0",
<     "msg": {
<       "codex_error_code": {
<         "response_stream_disconnected": {
<           "http_status_code": 401
<         }
<       },
<       "message": "Reconnecting... 2/5",
<       "type": "stream_error"
<     }
<   }
< }

 {
<   "method": "error",
<   "params": {
<     "error": {
<       "codexErrorCode": {
<         "responseStreamDisconnected": {
<           "httpStatusCode": 401
<         }
<       },
<       "message": "Reconnecting... 2/5"
<     }
<   }
< }

< {
<   "method": "turn/completed",
<   "params": {
<     "turn": {
<       "error": {
<         "codexErrorCode": {
<           "responseTooManyFailedAttempts": {
<             "httpStatusCode": 401
<           }
<         },
<         "message": "exceeded retry limit, last status: 401 Unauthorized, request id: 9a1b495a1a97ed3e-SJC"
<       },
<       "id": "0",
<       "items": [],
<       "status": "failed"
<     }
<   }
< }
```
This commit is contained in:
Celia Chen
2025-11-20 15:06:55 -08:00
committed by GitHub
Unverified
parent 3f92ad4190
commit 9bce050385
16 changed files with 329 additions and 38 deletions
+10 -4
View File
@@ -79,7 +79,6 @@ use crate::protocol::ApplyPatchApprovalRequestEvent;
use crate::protocol::AskForApproval;
use crate::protocol::BackgroundEventEvent;
use crate::protocol::DeprecationNoticeEvent;
use crate::protocol::ErrorEvent;
use crate::protocol::Event;
use crate::protocol::EventMsg;
use crate::protocol::ExecApprovalRequestEvent;
@@ -129,6 +128,7 @@ use codex_protocol::models::ContentItem;
use codex_protocol::models::FunctionCallOutputPayload;
use codex_protocol::models::ResponseInputItem;
use codex_protocol::models::ResponseItem;
use codex_protocol::protocol::CodexErrorInfo;
use codex_protocol::protocol::InitialHistory;
use codex_protocol::user_input::UserInput;
use codex_utils_readiness::Readiness;
@@ -1189,9 +1189,14 @@ impl Session {
&self,
turn_context: &TurnContext,
message: impl Into<String>,
codex_error: CodexErr,
) {
let codex_error_code = CodexErrorInfo::ResponseStreamDisconnected {
http_status_code: codex_error.http_status_code_value(),
};
let event = EventMsg::StreamError(StreamErrorEvent {
message: message.into(),
codex_error_code: Some(codex_error_code),
});
self.send_event(turn_context, event).await;
}
@@ -1437,6 +1442,7 @@ mod handlers {
use crate::tasks::UndoTask;
use crate::tasks::UserShellCommandTask;
use codex_protocol::custom_prompts::CustomPrompt;
use codex_protocol::protocol::CodexErrorInfo;
use codex_protocol::protocol::ErrorEvent;
use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
@@ -1683,6 +1689,7 @@ mod handlers {
id: sub_id.clone(),
msg: EventMsg::Error(ErrorEvent {
message: "Failed to shutdown rollout recorder".to_string(),
codex_error_code: Some(CodexErrorInfo::Other),
}),
};
sess.send_event_raw(event).await;
@@ -1937,9 +1944,7 @@ pub(crate) async fn run_task(
}
Err(e) => {
info!("Turn error: {e:#}");
let event = EventMsg::Error(ErrorEvent {
message: e.to_string(),
});
let event = EventMsg::Error(e.to_error_event(None));
sess.send_event(&turn_context, event).await;
// let the user continue the conversation
break;
@@ -2064,6 +2069,7 @@ async fn run_turn(
sess.notify_stream_error(
&turn_context,
format!("Reconnecting... {retries}/{max_retries}"),
e,
)
.await;
+3 -7
View File
@@ -10,7 +10,6 @@ use crate::error::Result as CodexResult;
use crate::features::Feature;
use crate::protocol::AgentMessageEvent;
use crate::protocol::CompactedItem;
use crate::protocol::ErrorEvent;
use crate::protocol::EventMsg;
use crate::protocol::TaskStartedEvent;
use crate::protocol::TurnContextItem;
@@ -128,9 +127,7 @@ async fn run_compact_task_inner(
continue;
}
sess.set_total_tokens_full(turn_context.as_ref()).await;
let event = EventMsg::Error(ErrorEvent {
message: e.to_string(),
});
let event = EventMsg::Error(e.to_error_event(None));
sess.send_event(&turn_context, event).await;
return;
}
@@ -141,14 +138,13 @@ async fn run_compact_task_inner(
sess.notify_stream_error(
turn_context.as_ref(),
format!("Reconnecting... {retries}/{max_retries}"),
e,
)
.await;
tokio::time::sleep(delay).await;
continue;
} else {
let event = EventMsg::Error(ErrorEvent {
message: e.to_string(),
});
let event = EventMsg::Error(e.to_error_event(None));
sess.send_event(&turn_context, event).await;
return;
}
+3 -4
View File
@@ -6,7 +6,6 @@ use crate::codex::TurnContext;
use crate::error::Result as CodexResult;
use crate::protocol::AgentMessageEvent;
use crate::protocol::CompactedItem;
use crate::protocol::ErrorEvent;
use crate::protocol::EventMsg;
use crate::protocol::RolloutItem;
use crate::protocol::TaskStartedEvent;
@@ -30,9 +29,9 @@ pub(crate) async fn run_remote_compact_task(sess: Arc<Session>, turn_context: Ar
async fn run_remote_compact_task_inner(sess: &Arc<Session>, turn_context: &Arc<TurnContext>) {
if let Err(err) = run_remote_compact_task_inner_impl(sess, turn_context).await {
let event = EventMsg::Error(ErrorEvent {
message: format!("Error running remote compact task: {err}"),
});
let event = EventMsg::Error(
err.to_error_event(Some("Error running remote compact task".to_string())),
);
sess.send_event(turn_context, event).await;
}
}
+84
View File
@@ -10,6 +10,8 @@ use chrono::Local;
use chrono::Utc;
use codex_async_utils::CancelErr;
use codex_protocol::ConversationId;
use codex_protocol::protocol::CodexErrorInfo;
use codex_protocol::protocol::ErrorEvent;
use codex_protocol::protocol::RateLimitSnapshot;
use reqwest::StatusCode;
use serde_json;
@@ -430,6 +432,57 @@ impl CodexErr {
pub fn downcast_ref<T: std::any::Any>(&self) -> Option<&T> {
(self as &dyn std::any::Any).downcast_ref::<T>()
}
/// Translate core error to client-facing protocol error.
pub fn to_codex_protocol_error(&self) -> CodexErrorInfo {
match self {
CodexErr::ContextWindowExceeded => CodexErrorInfo::ContextWindowExceeded,
CodexErr::UsageLimitReached(_)
| CodexErr::QuotaExceeded
| CodexErr::UsageNotIncluded => CodexErrorInfo::UsageLimitExceeded,
CodexErr::RetryLimit(_) => CodexErrorInfo::ResponseTooManyFailedAttempts {
http_status_code: self.http_status_code_value(),
},
CodexErr::ConnectionFailed(_) => CodexErrorInfo::HttpConnectionFailed {
http_status_code: self.http_status_code_value(),
},
CodexErr::ResponseStreamFailed(_) => CodexErrorInfo::ResponseStreamConnectionFailed {
http_status_code: self.http_status_code_value(),
},
CodexErr::RefreshTokenFailed(_) => CodexErrorInfo::Unauthorized,
CodexErr::SessionConfiguredNotFirstEvent
| CodexErr::InternalServerError
| CodexErr::InternalAgentDied => CodexErrorInfo::InternalServerError,
CodexErr::UnsupportedOperation(_) | CodexErr::ConversationNotFound(_) => {
CodexErrorInfo::BadRequest
}
CodexErr::Sandbox(_) => CodexErrorInfo::SandboxError,
_ => CodexErrorInfo::Other,
}
}
pub fn to_error_event(&self, message_prefix: Option<String>) -> ErrorEvent {
let error_message = self.to_string();
let message: String = match message_prefix {
Some(prefix) => format!("{prefix}: {error_message}"),
None => error_message,
};
ErrorEvent {
message,
codex_error_code: Some(self.to_codex_protocol_error()),
}
}
pub fn http_status_code_value(&self) -> Option<u16> {
let http_status_code = match self {
CodexErr::RetryLimit(err) => Some(err.status),
CodexErr::UnexpectedStatus(err) => Some(err.status),
CodexErr::ConnectionFailed(err) => err.source.status(),
CodexErr::ResponseStreamFailed(err) => err.source.status(),
_ => None,
};
http_status_code.as_ref().map(StatusCode::as_u16)
}
}
pub fn get_error_message_ui(e: &CodexErr) -> String {
@@ -478,6 +531,10 @@ mod tests {
use chrono::Utc;
use codex_protocol::protocol::RateLimitWindow;
use pretty_assertions::assert_eq;
use reqwest::Response;
use reqwest::ResponseBuilderExt;
use reqwest::StatusCode;
use reqwest::Url;
fn rate_limit_snapshot() -> RateLimitSnapshot {
let primary_reset_at = Utc
@@ -573,6 +630,33 @@ mod tests {
assert_eq!(get_error_message_ui(&err), "stdout only");
}
#[test]
fn to_error_event_handles_response_stream_failed() {
let response = http::Response::builder()
.status(StatusCode::TOO_MANY_REQUESTS)
.url(Url::parse("http://example.com").unwrap())
.body("")
.unwrap();
let source = Response::from(response).error_for_status_ref().unwrap_err();
let err = CodexErr::ResponseStreamFailed(ResponseStreamFailed {
source,
request_id: Some("req-123".to_string()),
});
let event = err.to_error_event(Some("prefix".to_string()));
assert_eq!(
event.message,
"prefix: Error while reading the server response: HTTP status client error (429 Too Many Requests) for url (http://example.com/), request id: req-123"
);
assert_eq!(
event.codex_error_code,
Some(CodexErrorInfo::ResponseStreamConnectionFailed {
http_status_code: Some(429)
})
);
}
#[test]
fn sandbox_denied_reports_exit_code_when_no_output_available() {
let output = ExecToolCallOutput {