mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
Francis Chalissery
566f7bf631
Responses API safety buffering metadata currently stops at the transport boundary, so app-server clients cannot render the in-progress safety review state. This change: - decodes and deduplicates `safety_buffering` metadata from Responses API SSE and WebSocket events without suppressing the original response event - emits a typed core event containing the requested model plus backend use cases and reasons - forwards that event as `turn/safetyBuffering/updated` through app-server v2 and updates generated protocol schemas - keeps the side-channel event out of persisted rollouts and turn timing This supports the Codex Apps buffering UX and depends on the Responses API backend work in https://github.com/openai/openai/pull/1044569 and https://github.com/openai/openai/pull/1044571. Validation: - focused `codex-core` safety-buffering integration test passes - `cargo check -p codex-core -p codex-app-server -p codex-app-server-protocol` - `just fix -p codex-api -p codex-protocol -p codex-core -p codex-app-server-protocol -p codex-app-server -p codex-rollout -p codex-rollout-trace -p codex-otel` - `just fmt` - broad package test run: 4,430/4,492 passed; 62 unrelated local-environment/concurrency failures involved unavailable test binaries, MCP subprocess setup, and app-server timeouts
64 lines
2.1 KiB
Rust
64 lines
2.1 KiB
Rust
use anyhow::Ok;
|
|
use codex_protocol::protocol::EventMsg;
|
|
use codex_protocol::protocol::Op;
|
|
use codex_protocol::protocol::SafetyBufferingEvent;
|
|
use codex_protocol::user_input::UserInput;
|
|
use core_test_support::responses::ev_completed;
|
|
use core_test_support::responses::ev_response_created;
|
|
use core_test_support::responses::mount_sse_once;
|
|
use core_test_support::responses::sse;
|
|
use core_test_support::responses::start_mock_server;
|
|
use core_test_support::skip_if_no_network;
|
|
use core_test_support::test_codex::test_codex;
|
|
use core_test_support::wait_for_event;
|
|
use core_test_support::wait_for_event_match;
|
|
use pretty_assertions::assert_eq;
|
|
use serde_json::json;
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
|
async fn emits_safety_buffering_with_the_requested_model() -> anyhow::Result<()> {
|
|
skip_if_no_network!(Ok(()));
|
|
|
|
let server = start_mock_server().await;
|
|
let mut created = ev_response_created("resp-1");
|
|
created["safety_buffering"] = json!({
|
|
"use_cases": ["cyber"],
|
|
"reasons": ["policy-check"],
|
|
});
|
|
mount_sse_once(&server, sse(vec![created, ev_completed("resp-1")])).await;
|
|
|
|
let test = test_codex().build(&server).await?;
|
|
test.codex
|
|
.submit(Op::UserInput {
|
|
items: vec![UserInput::Text {
|
|
text: "Check this request".into(),
|
|
text_elements: Vec::new(),
|
|
}],
|
|
final_output_json_schema: None,
|
|
responsesapi_client_metadata: None,
|
|
additional_context: Default::default(),
|
|
thread_settings: Default::default(),
|
|
})
|
|
.await?;
|
|
|
|
let event = wait_for_event_match(&test.codex, |event| match event {
|
|
EventMsg::SafetyBuffering(event) => Some(event.clone()),
|
|
_ => None,
|
|
})
|
|
.await;
|
|
assert_eq!(
|
|
event,
|
|
SafetyBufferingEvent {
|
|
model: test.session_configured.model.clone(),
|
|
use_cases: vec!["cyber".to_string()],
|
|
reasons: vec!["policy-check".to_string()],
|
|
}
|
|
);
|
|
wait_for_event(&test.codex, |event| {
|
|
matches!(event, EventMsg::TurnComplete(_))
|
|
})
|
|
.await;
|
|
|
|
Ok(())
|
|
}
|