mirror of
https://github.com/openai/codex.git
synced 2026-11-15 21:50:46 +00:00
Preserve WebSocket continuations when steering a turn (#48508)
## Why Steering an active WebSocket response previously dropped the connection and resent the full history. Draining the response preserves the connection and allows the follow-up request to continue with `previous_response_id`. ## What changed - Drain WebSocket responses when steering. For models using `use_responses_lite`, first send `response.interrupt` with `mode: "discard_partial_items"` once the response ID is available. - Treat `response.incomplete` with reason `interrupted` as completion with `end_turn: false`, preserving token usage and allowing the turn to continue. Other incomplete reasons remain errors. ## Testing Update the steering integration test to cover completed and discarded reasoning items, asserting connection reuse, incremental follow-up input, and token usage from the interrupted response. GitOrigin-RevId: bc714b713e797cf1a67e3b26ffbf7664cb92eb33
This commit is contained in:
@@ -21,6 +21,7 @@ use std::sync::Arc;
|
||||
use std::task::Context;
|
||||
use std::task::Poll;
|
||||
use tokio::sync::mpsc;
|
||||
use tokio::sync::oneshot;
|
||||
|
||||
pub const WS_REQUEST_HEADER_TRACEPARENT_CLIENT_METADATA_KEY: &str = "ws_request_header_traceparent";
|
||||
pub const WS_REQUEST_HEADER_TRACESTATE_CLIENT_METADATA_KEY: &str = "ws_request_header_tracestate";
|
||||
@@ -413,6 +414,8 @@ pub struct ResponseStream {
|
||||
pub rx_event: mpsc::Receiver<Result<ResponseEvent, ApiError>>,
|
||||
/// Server-assigned `x-request-id` response header, when present.
|
||||
pub upstream_request_id: Option<String>,
|
||||
/// Requests a graceful interrupt. Keep consuming events through completion.
|
||||
pub interrupt: Option<oneshot::Sender<()>>,
|
||||
}
|
||||
|
||||
impl Stream for ResponseStream {
|
||||
|
||||
Reference in New Issue
Block a user