mirror of
https://github.com/openai/codex.git
synced 2026-09-20 12:47:38 +00:00
e325e3acd9
## Why Remote environment registration can return an explicit `503` `registration_conflict` after the registry finishes its own recovery attempts. Retrying ambiguous failures is unsafe because a timed-out request may still have replaced a newer registration. ## What changed - Retry only explicit `registration_conflict` responses with jittered backoff, both during initial registration and after a rejected relay connection. - Apply the existing connection timeout to the complete registration attempt, including response-body diagnostics. - Keep retry waits and in-flight requests cancellable while preserving the Noise identity and initialized session across successful recovery. ## Testing Added unit coverage for retry eligibility and timeout handling, plus relay tests for identity and session preservation and prompt shutdown during registration. GitOrigin-RevId: 374e6fdac4755f377cbea9400c76a228b790945a
55 lines
2.2 KiB
Rust
55 lines
2.2 KiB
Rust
//! Retry only explicit registration conflicts after the registry's write-retry loop has finished.
|
|
//! Ambiguous failures must not be replayed: a timed-out request can still replace a newer registration.
|
|
//! The enclosing remote-transport future owns cancellation; retries spawn no background work.
|
|
|
|
use http::StatusCode;
|
|
use tokio::time::sleep;
|
|
use tracing::warn;
|
|
|
|
use super::EnvironmentRegistryClient;
|
|
use crate::EnvironmentRegistryRegistrationResponse;
|
|
use crate::ExecServerError;
|
|
use crate::NoiseChannelPublicKey;
|
|
use crate::client::registry_recovery_retry_delay;
|
|
|
|
impl EnvironmentRegistryClient {
|
|
pub(super) async fn register_environment_with_retry(
|
|
&self,
|
|
environment_id: &str,
|
|
executor_public_key: &NoiseChannelPublicKey,
|
|
) -> Result<EnvironmentRegistryRegistrationResponse, ExecServerError> {
|
|
// Competing executors for the same environment must not retry in lockstep.
|
|
let retry_key = uuid::Uuid::new_v4().to_string();
|
|
let mut attempt = 0_u32;
|
|
loop {
|
|
match self
|
|
.register_environment(environment_id, executor_public_key)
|
|
.await
|
|
{
|
|
Ok(response) => return Ok(response),
|
|
Err(ExecServerError::EnvironmentRegistryHttp { status, code, .. })
|
|
if status == StatusCode::SERVICE_UNAVAILABLE
|
|
&& code.as_deref() == Some("registration_conflict") =>
|
|
{
|
|
let delay = registry_recovery_retry_delay(&retry_key, attempt);
|
|
attempt = attempt.saturating_add(1);
|
|
// Do not log response bodies or transport errors: they can contain credentials.
|
|
warn!(
|
|
noise_event = "registration",
|
|
noise_outcome = "retry",
|
|
retry_attempt = attempt,
|
|
retry_delay_ms = delay.as_millis() as u64,
|
|
"Noise executor retrying registry registration conflict"
|
|
);
|
|
sleep(delay).await;
|
|
}
|
|
Err(error) => return Err(error),
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
#[path = "registration_retry_tests.rs"]
|
|
mod tests;
|