github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-09 03:28:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: treat HTTP 502/503/504 as failover-eligible (timeout reason) (#21017)

Browse Source 
* fix: treat HTTP 502/503/504 as failover-eligible (timeout reason)

When a model API returns 502 Bad Gateway, 503 Service Unavailable, or
504 Gateway Timeout, the error object carries the status code directly.
resolveFailoverReasonFromError() only checked 402/429/401/403/408/400,
so 5xx server errors fell through to message-based classification which
requires the status code to appear at the start of the error message.

Many API SDKs (Google, Anthropic) set err.status = 503 without prefixing
the message with '503', so the message classifier never matched and
failover never triggered — the run retried the same broken model.

Add 502/503/504 to the status-code branch, returning 'timeout' (matching
the existing behavior of isTransientHttpError in the message classifier).

Fixes #20999

* Changelog: add failover 502/503/504 note with credits

* Failover: classify HTTP 504 as transient in message parser

* Changelog: credit taw0002 and vincentkoc for failover fix

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
This commit is contained in:
taw0002
2026-02-23 01:01:57 -07:00
committed by GitHub
parent 07edadfa8a
commit 3c57bf4c85
5 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/agents/failover-error.test.ts
View File

@@ -13,7 +13,10 @@ describe("failover-error", () => {
expect(resolveFailoverReasonFromError({ status: 403 })).toBe("auth");
expect(resolveFailoverReasonFromError({ status: 408 })).toBe("timeout");
expect(resolveFailoverReasonFromError({ status: 400 })).toBe("format");
// Transient server errors (502/503/504) should trigger failover as timeout.
expect(resolveFailoverReasonFromError({ status: 502 })).toBe("timeout");
expect(resolveFailoverReasonFromError({ status: 503 })).toBe("timeout");
expect(resolveFailoverReasonFromError({ status: 504 })).toBe("timeout");
});
it("infers format errors from error messages", () => {

2
src/agents/failover-error.ts
View File

@@ -163,7 +163,7 @@ export function resolveFailoverReasonFromError(err: unknown): FailoverReason | n
if (status === 408) {
return "timeout";
}
if (status === 503) {
if (status === 502 || status === 503 || status === 504) {
return "timeout";
}
if (status === 400) {

2
src/agents/pi-embedded-helpers.isbillingerrormessage.test.ts
View File

@@ -270,12 +270,12 @@ describe("isTransientHttpError", () => {
expect(isTransientHttpError("500 Internal Server Error")).toBe(true);
expect(isTransientHttpError("502 Bad Gateway")).toBe(true);
expect(isTransientHttpError("503 Service Unavailable")).toBe(true);
expect(isTransientHttpError("504 Gateway Timeout")).toBe(true);
expect(isTransientHttpError("521 <!DOCTYPE html><html></html>")).toBe(true);
expect(isTransientHttpError("529 Overloaded")).toBe(true);
});
it("returns false for non-retryable or non-http text", () => {
expect(isTransientHttpError("504 Gateway Timeout")).toBe(false);
expect(isTransientHttpError("429 Too Many Requests")).toBe(false);
expect(isTransientHttpError("network timeout")).toBe(false);
});

2
src/agents/pi-embedded-helpers/errors.ts
View File

@@ -120,7 +120,7 @@ const HTTP_STATUS_PREFIX_RE = /^(?:http\s*)?(\d{3})\s+(.+)$/i;
const HTTP_STATUS_CODE_PREFIX_RE = /^(?:http\s*)?(\d{3})(?:\s+([\s\S]+))?$/i;
const HTML_ERROR_PREFIX_RE = /^\s*(?:<!doctype\s+html\b|<html\b)/i;
const CLOUDFLARE_HTML_ERROR_CODES = new Set([521, 522, 523, 524, 525, 526, 530]);
const TRANSIENT_HTTP_ERROR_CODES = new Set([500, 502, 503, 521, 522, 523, 524, 529]);
const TRANSIENT_HTTP_ERROR_CODES = new Set([500, 502, 503, 504, 521, 522, 523, 524, 529]);
const HTTP_ERROR_HINTS = [
"error",
"bad request",