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

[app-server] read rate limits API (#5302)

Browse Source 
Adds a `GET account/rateLimits/read` API to app-server. This calls the
codex backend to fetch the user's current rate limits.

This would be helpful in checking rate limits without having to send a
message.

For calling the codex backend usage API, I generated the types and
manually copied the relevant ones into `codex-backend-openapi-types`.
It'll be nice to extend our internal openapi generator to support Rust
so we don't have to run these manual steps.

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This commit is contained in:
Owen Lin
2025-10-20 14:11:54 -07:00
committed by GitHub
parent 39a2446716
commit 5c680c6587
22 changed files with 726 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
codex-rs/core/src/client.rs
View File

@@ -1,17 +1,18 @@
use std::io::BufRead;
use std::path::Path;
use std::sync::Arc;
use std::sync::OnceLock;
use std::time::Duration;
use crate::AuthManager;
use crate::auth::CodexAuth;
use crate::error::ConnectionFailedError;
use crate::error::ResponseStreamFailed;
use crate::error::RetryLimitReachedError;
use crate::error::UnexpectedResponseError;
use bytes::Bytes;
use chrono::DateTime;
use chrono::Utc;
use codex_app_server_protocol::AuthMode;
use codex_otel::otel_event_manager::OtelEventManager;
use codex_protocol::ConversationId;
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
use codex_protocol::models::ResponseItem;
use eventsource_stream::Eventsource;
use futures::prelude::*;
use regex_lite::Regex;
@@ -27,6 +28,8 @@ use tracing::debug;
use tracing::trace;
use tracing::warn;
use crate::AuthManager;
use crate::auth::CodexAuth;
use crate::chat_completions::AggregateStreamExt;
use crate::chat_completions::stream_chat_completions;
use crate::client_common::Prompt;
@@ -38,7 +41,11 @@ use crate::client_common::create_text_param_for_request;
use crate::config::Config;
use crate::default_client::create_client;
use crate::error::CodexErr;
use crate::error::ConnectionFailedError;
use crate::error::ResponseStreamFailed;
use crate::error::Result;
use crate::error::RetryLimitReachedError;
use crate::error::UnexpectedResponseError;
use crate::error::UsageLimitReachedError;
use crate::flags::CODEX_RS_SSE_FIXTURE;
use crate::model_family::ModelFamily;
@@ -52,13 +59,6 @@ use crate::state::TaskKind;
use crate::token_data::PlanType;
use crate::tools::spec::create_tools_json_for_responses_api;
use crate::util::backoff;
use chrono::DateTime;
use chrono::Utc;
use codex_otel::otel_event_manager::OtelEventManager;
use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
use codex_protocol::models::ResponseItem;
use std::sync::Arc;
#[derive(Debug, Deserialize)]
struct ErrorResponse {
@@ -628,13 +628,13 @@ fn parse_rate_limit_window(
headers: &HeaderMap,
used_percent_header: &str,
window_minutes_header: &str,
resets_header: &str,
resets_at_header: &str,
) -> Option<RateLimitWindow> {
let used_percent: Option<f64> = parse_header_f64(headers, used_percent_header);
used_percent.and_then(|used_percent| {
let window_minutes = parse_header_i64(headers, window_minutes_header);
let resets_at = parse_header_i64(headers, resets_header);
let resets_at = parse_header_i64(headers, resets_at_header);
let has_data = used_percent != 0.0
|| window_minutes.is_some_and(|minutes| minutes != 0)