Don't retry "insufficient_quota" errors (#6340)

This PR makes an "insufficient quota" error fatal so we don't attempt to
retry it multiple times in the agent loop.

We have multiple bug reports from users about intermittent retry
behaviors, and this could explain some of them. With this change, we'll
eliminate the retries and surface a clear error message.

The PR is a nearly identical copy of [this
PR](https://github.com/openai/codex/pull/4837) contributed by
@abimaelmartell. The original PR has gone stale. Rather than wait for
the contributor to resolve merge conflicts, I wanted to get this change
in.

codex-rs/core/src/client.rs

@@ -447,6 +447,8 @@ impl ModelClient {
                             return Err(StreamAttemptError::Fatal(codex_err));
                         } else if error.r#type.as_deref() == Some("usage_not_included") {
                             return Err(StreamAttemptError::Fatal(CodexErr::UsageNotIncluded));
+                        } else if is_quota_exceeded_error(&error) {
+                            return Err(StreamAttemptError::Fatal(CodexErr::QuotaExceeded));
                         }
                     }
                 }
@@ -844,6 +846,8 @@ async fn process_sse<S>(
                             Ok(error) => {
                                 if is_context_window_error(&error) {
                                     response_error = Some(CodexErr::ContextWindowExceeded);
+                                } else if is_quota_exceeded_error(&error) {
+                                    response_error = Some(CodexErr::QuotaExceeded);
                                 } else {
                                     let delay = try_parse_retry_after(&error);
                                     let message = error.message.clone().unwrap_or_default();
@@ -975,6 +979,10 @@ fn is_context_window_error(error: &Error) -> bool {
     error.code.as_deref() == Some("context_length_exceeded")
 }
 
+fn is_quota_exceeded_error(error: &Error) -> bool {
+    error.code.as_deref() == Some("insufficient_quota")
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -1307,6 +1315,41 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn quota_exceeded_error_is_fatal() {
+        let raw_error = r#"{"type":"response.failed","sequence_number":3,"response":{"id":"resp_fatal_quota","object":"response","created_at":1759771626,"status":"failed","background":false,"error":{"code":"insufficient_quota","message":"You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors."},"incomplete_details":null}}"#;
+
+        let sse1 = format!("event: response.failed\ndata: {raw_error}\n\n");
+        let provider = ModelProviderInfo {
+            name: "test".to_string(),
+            base_url: Some("https://test.com".to_string()),
+            env_key: Some("TEST_API_KEY".to_string()),
+            env_key_instructions: None,
+            experimental_bearer_token: None,
+            wire_api: WireApi::Responses,
+            query_params: None,
+            http_headers: None,
+            env_http_headers: None,
+            request_max_retries: Some(0),
+            stream_max_retries: Some(0),
+            stream_idle_timeout_ms: Some(1000),
+            requires_openai_auth: false,
+        };
+
+        let otel_event_manager = otel_event_manager();
+
+        let events = collect_events(&[sse1.as_bytes()], provider, otel_event_manager).await;
+
+        assert_eq!(events.len(), 1);
+
+        match &events[0] {
+            Err(err @ CodexErr::QuotaExceeded) => {
+                assert_eq!(err.to_string(), CodexErr::QuotaExceeded.to_string());
+            }
+            other => panic!("unexpected quota exceeded event: {other:?}"),
+        }
+    }
+
     // ────────────────────────────
     // Table-driven test from `main`
     // ────────────────────────────

codex-rs/core/src/codex.rs

@@ -1928,6 +1928,7 @@ async fn run_turn(
                 return Err(CodexErr::UsageLimitReached(e));
             }
             Err(CodexErr::UsageNotIncluded) => return Err(CodexErr::UsageNotIncluded),
+            Err(e @ CodexErr::QuotaExceeded) => return Err(e),
             Err(e @ CodexErr::RefreshTokenFailed(_)) => return Err(e),
             Err(e) => {
                 // Use the configured provider-specific stream retry budget.

codex-rs/core/src/error.rs

@@ -109,6 +109,9 @@ pub enum CodexErr {
     #[error("{0}")]
     ConnectionFailed(ConnectionFailedError),
 
+    #[error("Quota exceeded. Check your plan and billing details.")]
+    QuotaExceeded,
+
     #[error(
         "To use Codex with your ChatGPT plan, upgrade to Plus: https://openai.com/chatgpt/pricing."
     )]

codex-rs/core/tests/suite/mod.rs

@@ -26,6 +26,7 @@ mod model_overrides;
 mod model_tools;
 mod otel;
 mod prompt_caching;
+mod quota_exceeded;
 mod read_file;
 mod resume;
 mod review;

codex-rs/core/tests/suite/quota_exceeded.rs

@@ -0,0 +1,75 @@
+use std::time::Duration;
+
+use anyhow::Result;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::Op;
+use codex_protocol::user_input::UserInput;
+use core_test_support::responses::ev_response_created;
+use core_test_support::responses::mount_sse_once;
+use core_test_support::responses::sse;
+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_with_timeout;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn quota_exceeded_emits_single_error_event() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = start_mock_server().await;
+    let mut builder = test_codex();
+
+    mount_sse_once(
+        &server,
+        sse(vec![
+            ev_response_created("resp-1"),
+            json!({
+                "type": "response.failed",
+                "response": {
+                    "id": "resp-1",
+                    "error": {
+                        "code": "insufficient_quota",
+                        "message": "You exceeded your current quota, please check your plan and billing details."
+                    }
+                }
+            }),
+        ]),
+    )
+    .await;
+
+    let test = builder.build(&server).await?;
+
+    test.codex
+        .submit(Op::UserInput {
+            items: vec![UserInput::Text {
+                text: "quota?".into(),
+            }],
+        })
+        .await
+        .unwrap();
+
+    let mut error_events = 0;
+
+    loop {
+        let event =
+            wait_for_event_with_timeout(&test.codex, |_| true, Duration::from_secs(5)).await;
+
+        match event {
+            EventMsg::Error(err) => {
+                error_events += 1;
+                assert_eq!(
+                    err.message,
+                    "Quota exceeded. Check your plan and billing details."
+                );
+            }
+            EventMsg::TaskComplete(_) => break,
+            _ => {}
+        }
+    }
+
+    assert_eq!(error_events, 1, "expected exactly one Codex:Error event");
+
+    Ok(())
+}