valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improved user message for rate-limit errors (#2695)

Browse Source 
This PR improves the error message presented to the user when logged in
with ChatGPT and a rate-limit error occurs. In particular, it provides
the user with information about when the rate limit will be reset. It
removes older code that attempted to do the same but relied on parsing
of error messages that are not generated by the ChatGPT endpoint. The
new code uses newly-added error fields.
This commit is contained in:
Eric Traut
2025-08-25 21:42:10 -07:00
committed by GitHub
parent e5283b6126
commit ab9250e714
2 changed files with 123 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

92
codex-rs/core/src/client.rs
View File

@@ -1,6 +1,5 @@
use std::io::BufRead;
use std::path::Path;
use std::sync::OnceLock;
use std::time::Duration;
use bytes::Bytes;
@@ -8,7 +7,6 @@ use codex_login::AuthManager;
use codex_login::AuthMode;
use eventsource_stream::Eventsource;
use futures::prelude::*;
use regex_lite::Regex;
use reqwest::StatusCode;
use serde::Deserialize;
use serde::Serialize;
@@ -54,8 +52,11 @@ struct ErrorResponse {
#[derive(Debug, Deserialize)]
struct Error {
r#type: Option<String>,
code: Option<String>,
message: Option<String>,
// Optional fields available on "usage_limit_reached" and "usage_not_included" errors
plan_type: Option<String>,
resets_in_seconds: Option<u64>,
}
#[derive(Debug, Clone)]
@@ -309,19 +310,20 @@ impl ModelClient {
if status == StatusCode::TOO_MANY_REQUESTS {
let body = res.json::<ErrorResponse>().await.ok();
if let Some(ErrorResponse {
error:
Error {
r#type: Some(error_type),
..
},
}) = body
{
if error_type == "usage_limit_reached" {
if let Some(ErrorResponse { error }) = body {
if error.r#type.as_deref() == Some("usage_limit_reached") {
// Prefer the plan_type provided in the error message if present
// because it's more up to date than the one encoded in the auth
// token.
let plan_type = error
.plan_type
.or_else(|| auth.and_then(|a| a.get_plan_type()));
let resets_in_seconds = error.resets_in_seconds;
return Err(CodexErr::UsageLimitReached(UsageLimitReachedError {
plan_type: auth.and_then(|a| a.get_plan_type()),
plan_type,
resets_in_seconds,
}));
} else if error_type == "usage_not_included" {
} else if error.r#type.as_deref() == Some("usage_not_included") {
return Err(CodexErr::UsageNotIncluded);
}
}
@@ -569,9 +571,8 @@ async fn process_sse<S>(
if let Some(error) = error {
match serde_json::from_value::<Error>(error.clone()) {
Ok(error) => {
let delay = try_parse_retry_after(&error);
let message = error.message.unwrap_or_default();
response_error = Some(CodexErr::Stream(message, delay));
response_error = Some(CodexErr::Stream(message, None));
}
Err(e) => {
debug!("failed to parse ErrorResponse: {e}");
@@ -659,40 +660,6 @@ async fn stream_from_fixture(
Ok(ResponseStream { rx_event })
}
fn rate_limit_regex() -> &'static Regex {
static RE: OnceLock<Regex> = OnceLock::new();
#[expect(clippy::unwrap_used)]
RE.get_or_init(|| Regex::new(r"Please try again in (\d+(?:\.\d+)?)(s|ms)").unwrap())
}
fn try_parse_retry_after(err: &Error) -> Option<Duration> {
if err.code != Some("rate_limit_exceeded".to_string()) {
return None;
}
// parse the Please try again in 1.898s format using regex
let re = rate_limit_regex();
if let Some(message) = &err.message
&& let Some(captures) = re.captures(message)
{
let seconds = captures.get(1);
let unit = captures.get(2);
if let (Some(value), Some(unit)) = (seconds, unit) {
let value = value.as_str().parse::<f64>().ok()?;
let unit = unit.as_str();
if unit == "s" {
return Some(Duration::from_secs_f64(value));
} else if unit == "ms" {
return Some(Duration::from_millis(value as u64));
}
}
}
None
}
#[cfg(test)]
mod tests {
use super::*;
@@ -913,7 +880,7 @@ mod tests {
msg,
"Rate limit reached for gpt-5 in organization org-AAA on tokens per min (TPM): Limit 30000, Used 22999, Requested 12528. Please try again in 11.054s. Visit https://platform.openai.com/account/rate-limits to learn more."
);
assert_eq!(*delay, Some(Duration::from_secs_f64(11.054)));
assert_eq!(*delay, None);
}
other => panic!("unexpected second event: {other:?}"),
}
@@ -1017,27 +984,4 @@ mod tests {
);
}
}
#[test]
fn test_try_parse_retry_after() {
let err = Error {
r#type: None,
message: Some("Rate limit reached for gpt-5 in organization org- on tokens per min (TPM): Limit 1, Used 1, Requested 19304. Please try again in 28ms. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
};
let delay = try_parse_retry_after(&err);
assert_eq!(delay, Some(Duration::from_millis(28)));
}
#[test]
fn test_try_parse_retry_after_no_delay() {
let err = Error {
r#type: None,
message: Some("Rate limit reached for gpt-5 in organization <ORG> on tokens per min (TPM): Limit 30000, Used 6899, Requested 24050. Please try again in 1.898s. Visit https://platform.openai.com/account/rate-limits to learn more.".to_string()),
code: Some("rate_limit_exceeded".to_string()),
};
let delay = try_parse_retry_after(&err);
assert_eq!(delay, Some(Duration::from_secs_f64(1.898)));
}
}

114
codex-rs/core/src/error.rs
View File

@@ -128,27 +128,70 @@ pub enum CodexErr {
#[derive(Debug)]
pub struct UsageLimitReachedError {
pub plan_type: Option<String>,
pub resets_in_seconds: Option<u64>,
}
impl std::fmt::Display for UsageLimitReachedError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
// Base message differs slightly for legacy ChatGPT Plus plan users.
if let Some(plan_type) = &self.plan_type
&& plan_type == "plus"
{
write!(
f,
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), or wait for limits to reset (every 5h and every week.)."
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again"
)?;
if let Some(secs) = self.resets_in_seconds {
let reset_duration = format_reset_duration(secs);
write!(f, " in {reset_duration}.")?;
} else {
write!(f, " later.")?;
}
} else {
write!(
f,
"You've hit your usage limit. Limits reset every 5h and every week."
)?;
write!(f, "You've hit your usage limit.")?;
if let Some(secs) = self.resets_in_seconds {
let reset_duration = format_reset_duration(secs);
write!(f, " Try again in {reset_duration}.")?;
} else {
write!(f, " Try again later.")?;
}
}
Ok(())
}
}
fn format_reset_duration(total_secs: u64) -> String {
let days = total_secs / 86_400;
let hours = (total_secs % 86_400) / 3_600;
let minutes = (total_secs % 3_600) / 60;
let mut parts: Vec<String> = Vec::new();
if days > 0 {
let unit = if days == 1 { "day" } else { "days" };
parts.push(format!("{} {}", days, unit));
}
if hours > 0 {
let unit = if hours == 1 { "hour" } else { "hours" };
parts.push(format!("{} {}", hours, unit));
}
if minutes > 0 {
let unit = if minutes == 1 { "minute" } else { "minutes" };
parts.push(format!("{} {}", minutes, unit));
}
if parts.is_empty() {
return "less than a minute".to_string();
}
match parts.len() {
1 => parts[0].clone(),
2 => format!("{} {}", parts[0], parts[1]),
_ => format!("{} {} {}", parts[0], parts[1], parts[2]),
}
}
#[derive(Debug)]
pub struct EnvVarError {
/// Name of the environment variable that is missing.
@@ -195,19 +238,23 @@ mod tests {
fn usage_limit_reached_error_formats_plus_plan() {
let err = UsageLimitReachedError {
plan_type: Some("plus".to_string()),
resets_in_seconds: None,
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing), or wait for limits to reset (every 5h and every week.)."
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again later."
);
}
#[test]
fn usage_limit_reached_error_formats_default_when_none() {
let err = UsageLimitReachedError { plan_type: None };
let err = UsageLimitReachedError {
plan_type: None,
resets_in_seconds: None,
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Limits reset every 5h and every week."
"You've hit your usage limit. Try again later."
);
}
@@ -215,10 +262,59 @@ mod tests {
fn usage_limit_reached_error_formats_default_for_other_plans() {
let err = UsageLimitReachedError {
plan_type: Some("pro".to_string()),
resets_in_seconds: None,
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Limits reset every 5h and every week."
"You've hit your usage limit. Try again later."
);
}
#[test]
fn usage_limit_reached_includes_minutes_when_available() {
let err = UsageLimitReachedError {
plan_type: None,
resets_in_seconds: Some(5 * 60),
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Try again in 5 minutes."
);
}
#[test]
fn usage_limit_reached_includes_hours_and_minutes() {
let err = UsageLimitReachedError {
plan_type: Some("plus".to_string()),
resets_in_seconds: Some(3 * 3600 + 32 * 60),
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Upgrade to Pro (https://openai.com/chatgpt/pricing) or try again in 3 hours 32 minutes."
);
}
#[test]
fn usage_limit_reached_includes_days_hours_minutes() {
let err = UsageLimitReachedError {
plan_type: None,
resets_in_seconds: Some(2 * 86_400 + 3 * 3600 + 5 * 60),
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Try again in 2 days 3 hours 5 minutes."
);
}
#[test]
fn usage_limit_reached_less_than_minute() {
let err = UsageLimitReachedError {
plan_type: None,
resets_in_seconds: Some(30),
};
assert_eq!(
err.to_string(),
"You've hit your usage limit. Try again in less than a minute."
);
}
}