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

feat: lower default retry wait time and increase number of tries (#720)

Browse Source 
In total we now guarantee that we will wait for at least 60s before
giving up.

---------

Signed-off-by: Thibault Sottiaux <tibo@openai.com>
This commit is contained in:
Thibault Sottiaux
2025-04-28 21:11:30 -07:00
committed by GitHub
parent e79549f039
commit d09dbba7ec
3 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
codex-cli/src/utils/agent/agent-loop.ts
View File

@@ -34,7 +34,7 @@ import OpenAI, { APIConnectionTimeoutError } from "openai";
// Wait time before retrying after rate limit errors (ms). // Wait time before retrying after rate limit errors (ms).
const RATE_LIMIT_RETRY_WAIT_MS = parseInt( const RATE_LIMIT_RETRY_WAIT_MS = parseInt(
process.env["OPENAI_RATE_LIMIT_RETRY_WAIT_MS"] || "2500", process.env["OPENAI_RATE_LIMIT_RETRY_WAIT_MS"] || "500",
10, 10,
); );
@@ -671,7 +671,7 @@ export class AgentLoop {
let stream; let stream;
// Retry loop for transient errors. Up to MAX_RETRIES attempts. // Retry loop for transient errors. Up to MAX_RETRIES attempts.
const MAX_RETRIES = 5; const MAX_RETRIES = 8;
for (let attempt = 1; attempt <= MAX_RETRIES; attempt++) { for (let attempt = 1; attempt <= MAX_RETRIES; attempt++) {
try { try {
let reasoning: Reasoning | undefined; let reasoning: Reasoning | undefined;

10
codex-cli/tests/agent-rate-limit-error.test.ts
View File

@@ -98,10 +98,8 @@ describe("AgentLoop – rate‑limit handling", () => {
// is in progress. // is in progress.
const runPromise = agent.run(userMsg as any); const runPromise = agent.run(userMsg as any);
// The agent waits 15 000 ms between retries (rate‑limit back‑off) and does // Should be done in at most 180 seconds.
// this four times (after attempts 1‑4). Fast‑forward a bit more to cover await vi.advanceTimersByTimeAsync(180_000);
// any additional small `setTimeout` calls inside the implementation.
await vi.advanceTimersByTimeAsync(61_000); // 4 * 15s + 1s safety margin
// Ensure the promise settles without throwing. // Ensure the promise settles without throwing.
await expect(runPromise).resolves.not.toThrow(); await expect(runPromise).resolves.not.toThrow();
@@ -110,8 +108,8 @@ describe("AgentLoop – rate‑limit handling", () => {
await vi.advanceTimersByTimeAsync(20); await vi.advanceTimersByTimeAsync(20);
// The OpenAI client should have been called the maximum number of retry // The OpenAI client should have been called the maximum number of retry
// attempts (5). // attempts (8).
expect(openAiState.createSpy).toHaveBeenCalledTimes(5); expect(openAiState.createSpy).toHaveBeenCalledTimes(8);
// Finally, verify that the user sees a helpful system message. // Finally, verify that the user sees a helpful system message.
const sysMsg = received.find( const sysMsg = received.find(

4
codex-cli/tests/agent-server-retry.test.ts
View File

@@ -122,7 +122,7 @@ describe("AgentLoop – automatic retry on 5xx errors", () => {
expect(assistant?.content?.[0]?.text).toBe("ok"); expect(assistant?.content?.[0]?.text).toBe("ok");
}); });
it("fails after 3 attempts and surfaces system message", async () => { it("fails after a few attempts and surfaces system message", async () => {
openAiState.createSpy = vi.fn(async () => { openAiState.createSpy = vi.fn(async () => {
const err: any = new Error("Internal Server Error"); const err: any = new Error("Internal Server Error");
err.status = 502; // any 5xx err.status = 502; // any 5xx
@@ -154,7 +154,7 @@ describe("AgentLoop – automatic retry on 5xx errors", () => {
await new Promise((r) => setTimeout(r, 20)); await new Promise((r) => setTimeout(r, 20));
expect(openAiState.createSpy).toHaveBeenCalledTimes(5); expect(openAiState.createSpy).toHaveBeenCalledTimes(8);
const sysMsg = received.find( const sysMsg = received.find(
(i) => (i) =>