mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
Francis Chalissery
7c22d376e5
## Summary - read the request-scoped safety-buffering treatment from HTTP response headers and per-turn WebSocket metadata through one shared header parser - combine that treatment with Responses API safety-buffering signals - propagate `showBufferingUi` and nullable `fasterModel` through the existing `model/safetyBuffering/updated` app-server notification - update the app-server documentation and generated JSON and TypeScript schemas The public implementation contains no model mapping or real model identifier. Tests and protocol examples use generic `current-model` and `faster-model` placeholders only. ## Dependencies - server-side treatment evaluation: https://github.com/openai/openai/pull/1060247 - initial Responses API safety-buffering propagation: https://github.com/openai/codex/pull/29371 - Codex App UI: https://github.com/openai/openai/pull/1057789 ## Validation - Codex API tests: 129 passed - focused Codex core safety-buffering integration test passed - app-server protocol tests passed after regenerating schema fixtures - Clippy fix and repository formatting completed successfully The broader app-server run compiled all changed crates and completed with 1,269 passing tests. Its remaining failures were unrelated environment limitations: macOS sandbox application was denied, one expected test binary was unavailable, and several existing subprocess tests timed out as a result.
75 lines
2.5 KiB
Rust
75 lines
2.5 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_response_once;
|
|
use core_test_support::responses::sse;
|
|
use core_test_support::responses::sse_response;
|
|
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;
|
|
|
|
const FASTER_MODEL: &str = "faster-model";
|
|
|
|
#[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_response_once(
|
|
&server,
|
|
sse_response(sse(vec![created, ev_completed("resp-1")]))
|
|
.insert_header("x-codex-safety-buffering-enabled", "true")
|
|
.insert_header("x-codex-safety-buffering-faster-model", FASTER_MODEL),
|
|
)
|
|
.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()],
|
|
show_buffering_ui: true,
|
|
faster_model: Some(FASTER_MODEL.to_string()),
|
|
}
|
|
);
|
|
wait_for_event(&test.codex, |event| {
|
|
matches!(event, EventMsg::TurnComplete(_))
|
|
})
|
|
.await;
|
|
|
|
Ok(())
|
|
}
|