Files
codex/codex-rs/core/tests/suite/resume_warning.rs
Owen Lin 5bc82c5b93 feat(app-server): propagate traces across tasks and core ops (#14387)
## Summary

This PR keeps app-server RPC request trace context alive for the full
lifetime of the work that request kicks off (e.g. for `thread/start`,
this is `app-server rpc handler -> tokio background task -> core op
submissions`). Previously we lose trace lineage once the request handler
returns or hands work off to background tasks.

This approach is especially relevant for `thread/start` and other RPC
handlers that run in a non-blocking way. In the near future we'll most
likely want to make all app-server handlers run in a non-blocking way by
default, and only queue operations that must operate in order (e.g.
thread RPCs per thread?), so we want to make sure tracing in app-server
just generally works.

Depends on https://github.com/openai/codex/pull/14300

**Before**
<img width="155" height="207" alt="image"
src="https://github.com/user-attachments/assets/c9487459-36f1-436c-beb7-fafeb40737af"
/>


**After**
<img width="299" height="337" alt="image"
src="https://github.com/user-attachments/assets/727392b2-d072-4427-9dc4-0502d8652dea"
/>

## What changed

- Keep request-scoped trace context around until we send the final
response or error, or the connection closes.
- Thread that trace context through detached `thread/start` work so
background startup stays attached to the originating request.
- Pass request trace context through to downstream core operations,
including:
  - thread creation
  - resume/fork flows
  - turn submission
  - review
  - interrupt
  - realtime conversation operations
- Add tracing tests that verify:
  - remote W3C trace context is preserved for `thread/start`
  - remote W3C trace context is preserved for `turn/start`
  - downstream core spans stay under the originating request span
  - request-scoped tracing state is cleaned up correctly
- Clean up shutdown behavior so detached background tasks and spawned
threads are drained before process exit.
2026-03-11 20:18:31 -07:00

124 lines
4.6 KiB
Rust

#![allow(clippy::unwrap_used, clippy::expect_used)]
use codex_core::CodexAuth;
use codex_core::NewThread;
use codex_protocol::ThreadId;
use codex_protocol::config_types::ModeKind;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::InitialHistory;
use codex_protocol::protocol::ResumedHistory;
use codex_protocol::protocol::RolloutItem;
use codex_protocol::protocol::TurnCompleteEvent;
use codex_protocol::protocol::TurnContextItem;
use codex_protocol::protocol::TurnStartedEvent;
use codex_protocol::protocol::UserMessageEvent;
use codex_protocol::protocol::WarningEvent;
use core::time::Duration;
use core_test_support::load_default_config_for_test;
use core_test_support::wait_for_event;
use tempfile::TempDir;
fn resume_history(
config: &codex_core::config::Config,
previous_model: &str,
rollout_path: &std::path::Path,
) -> InitialHistory {
let turn_id = "resume-warning-seed-turn".to_string();
let turn_ctx = TurnContextItem {
turn_id: Some(turn_id.clone()),
trace_id: None,
cwd: config.cwd.clone(),
current_date: None,
timezone: None,
approval_policy: config.permissions.approval_policy.value(),
sandbox_policy: config.permissions.sandbox_policy.get().clone(),
network: None,
model: previous_model.to_string(),
personality: None,
collaboration_mode: None,
realtime_active: None,
effort: config.model_reasoning_effort,
summary: config
.model_reasoning_summary
.unwrap_or(ReasoningSummary::Auto),
user_instructions: None,
developer_instructions: None,
final_output_json_schema: None,
truncation_policy: None,
};
InitialHistory::Resumed(ResumedHistory {
conversation_id: ThreadId::default(),
history: vec![
RolloutItem::EventMsg(EventMsg::TurnStarted(TurnStartedEvent {
turn_id: turn_id.clone(),
model_context_window: None,
collaboration_mode_kind: ModeKind::Default,
})),
RolloutItem::EventMsg(EventMsg::UserMessage(UserMessageEvent {
message: "seed".to_string(),
images: None,
local_images: vec![],
text_elements: vec![],
})),
RolloutItem::TurnContext(turn_ctx),
RolloutItem::EventMsg(EventMsg::TurnComplete(TurnCompleteEvent {
turn_id,
last_agent_message: None,
})),
],
rollout_path: rollout_path.to_path_buf(),
})
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn emits_warning_when_resumed_model_differs() {
// Arrange a config with a current model and a prior rollout recorded under a different model.
let home = TempDir::new().expect("tempdir");
let mut config = load_default_config_for_test(&home).await;
config.model = Some("current-model".to_string());
// Ensure cwd is absolute (the helper sets it to the temp dir already).
assert!(config.cwd.is_absolute());
let rollout_path = home.path().join("rollout.jsonl");
std::fs::write(&rollout_path, "").expect("create rollout placeholder");
let initial_history = resume_history(&config, "previous-model", &rollout_path);
let thread_manager = codex_core::test_support::thread_manager_with_models_provider(
CodexAuth::from_api_key("test"),
config.model_provider.clone(),
);
let auth_manager =
codex_core::test_support::auth_manager_from_auth(CodexAuth::from_api_key("test"));
// Act: resume the conversation.
let NewThread {
thread: conversation,
..
} = thread_manager
.resume_thread_with_history(config, initial_history, auth_manager, false, None)
.await
.expect("resume conversation");
// Assert: a Warning event is emitted describing the model mismatch.
let warning = wait_for_event(&conversation, |ev| {
matches!(
ev,
EventMsg::Warning(WarningEvent { message })
if message.contains("previous-model") && message.contains("current-model")
)
})
.await;
let EventMsg::Warning(WarningEvent { message }) = warning else {
panic!("expected warning event");
};
assert!(message.contains("previous-model"));
assert!(message.contains("current-model"));
// Drain the TurnComplete/Shutdown window to avoid leaking tasks between tests.
// The warning is emitted during initialization, so a short sleep is sufficient.
tokio::time::sleep(Duration::from_millis(50)).await;
}