MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-08-03 21:51:11 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(core): classify capacity exhaustion as terminal to prevent retry hangs (#28599)

Browse Source
This commit is contained in:
luisfelipe-alt
2026-07-30 10:59:01 -07:00
committed by GitHub
parent dc859e8e48
commit d55e366f6a
2 changed files with 74 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/core/src/utils/googleQuotaErrors.test.ts
+57
View File
@@ -107,6 +107,63 @@ describe('classifyGoogleError', () => {
expect((result as RetryableQuotaError).retryDelayMs).toBe(9000);
});
it('should return TerminalQuotaError for MODEL_CAPACITY_EXHAUSTED when no retry delay is specified', () => {
const apiError: GoogleApiError = {
code: 429,
message:
'No capacity available for model gemini-3.1-pro-preview on the server',
details: [
{
'@type': 'type.googleapis.com/google.rpc.ErrorInfo',
reason: 'MODEL_CAPACITY_EXHAUSTED',
domain: 'cloudcode-pa.googleapis.com',
metadata: { model: 'gemini-3.1-pro-preview' },
},
],
};
vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
const result = classifyGoogleError(new Error());
expect(result).toBeInstanceOf(TerminalQuotaError);
});
it('should return TerminalQuotaError for MODEL_CAPACITY_EXHAUSTED even when the domain is not a Cloud Code domain (domain-agnostic)', () => {
const apiError: GoogleApiError = {
code: 429,
message:
'No capacity available for model gemini-3.1-pro-preview on the server',
details: [
{
'@type': 'type.googleapis.com/google.rpc.ErrorInfo',
reason: 'MODEL_CAPACITY_EXHAUSTED',
domain: 'other.googleapis.com',
metadata: { model: 'gemini-3.1-pro-preview' },
},
],
};
vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
const result = classifyGoogleError(new Error());
expect(result).toBeInstanceOf(TerminalQuotaError);
});
it('should return TerminalQuotaError for MODEL_CAPACITY_EXCEEDED when no retry delay is specified', () => {
const apiError: GoogleApiError = {
code: 429,
message:
'No capacity available for model gemini-3.1-pro-preview on the server',
details: [
{
'@type': 'type.googleapis.com/google.rpc.ErrorInfo',
reason: 'MODEL_CAPACITY_EXCEEDED',
domain: 'cloudcode-pa.googleapis.com',
metadata: { model: 'gemini-3.1-pro-preview' },
},
],
};
vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
const result = classifyGoogleError(new Error());
expect(result).toBeInstanceOf(TerminalQuotaError);
});
it('should return original error if code is not 429, 499 or 503', () => {
const apiError: GoogleApiError = {
code: 500,
packages/core/src/utils/googleQuotaErrors.ts
+17
View File
@@ -330,6 +330,23 @@ export function classifyGoogleError(error: unknown): unknown {
);
}
if (
errorInfo.reason === 'MODEL_CAPACITY_EXHAUSTED' ||
errorInfo.reason === 'MODEL_CAPACITY_EXCEEDED'
) {
// If no server backoff delay is specified, treat capacity exhaustion as a terminal error
// to trigger immediate model fallback without retrying on the same exhausted model.
if (delaySeconds === undefined) {
return new TerminalQuotaError(
googleApiError.message,
googleApiError,
delaySeconds,
errorInfo.reason,
);
}
// Otherwise, fall through to RetryableQuotaError to honor the server's requested delay.
}
// New Cloud Code API quota handling
if (errorInfo.domain) {
if (isCloudCodeDomain(errorInfo.domain)) {