mirrors/pikasTech-unidesk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: let recovered upstream error probes trigger cooldown

Browse Source
This commit is contained in:
Codex
2026-06-09 10:38:12 +00:00
parent 6ebcc22b8f
commit 229f81e07c
5 changed files with 26 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/src/platform-infra-sub2api-codex.ts
+10 -10
View File
@@ -654,43 +654,43 @@ export function defaultCodexTempUnschedulablePolicy(): CodexTempUnschedulablePol
rules: [
{
statusCode: 401,
keywords: ["unauthorized", "invalid api key", "invalid_api_key", "authentication"],
keywords: ["unauthorized", "invalid api key", "invalid_api_key", "authentication", "recovered upstream error"],
durationMinutes: 120,
description: "Credential/auth failures should leave the scheduler quickly and retry after a two-hour cooldown.",
description: "Credential/auth failures should use the longest cooldown.",
},
{
statusCode: 403,
keywords: ["forbidden", "access denied", "quota", "billing", "capacity"],
keywords: ["forbidden", "access denied", "quota", "billing", "capacity", "recovered upstream error"],
durationMinutes: 120,
description: "Permission, quota, or account-state failures should fail over to another account for at least two hours.",
description: "Permission, quota, or account-state failures should use the longest cooldown.",
},
{
statusCode: 429,
keywords: ["capacity", "rate limit", "rate_limit", "quota", "too many requests", "overloaded", "resource_exhausted"],
keywords: ["capacity", "rate limit", "rate_limit", "quota", "too many requests", "overloaded", "resource_exhausted", "recovered upstream error"],
durationMinutes: 10,
description: "Capacity and rate-limit responses are often temporary; start with a ten-minute cooldown and use another account.",
},
{
statusCode: 500,
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream"],
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream", "recovered upstream error"],
durationMinutes: 10,
description: "Transient upstream server failures should start with a ten-minute cooldown and prefer another account.",
},
{
statusCode: 502,
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream", "bad gateway", "upstream request failed", "websocket dial", "handshake response"],
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream", "bad gateway", "upstream request failed", "websocket dial", "handshake response", "recovered upstream error"],
durationMinutes: 30,
description: "Gateway upstream failures are more disruptive than transient capacity signals and should cool down longer.",
description: "Gateway upstream failures, including recovered upstream error wrappers, should cool down longer.",
},
{
statusCode: 503,
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream"],
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream", "recovered upstream error"],
durationMinutes: 30,
description: "Service unavailable responses should cool down longer than one-off transient failures.",
},
{
statusCode: 529,
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary"],
keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "recovered upstream error"],
durationMinutes: 30,
description: "Provider overloaded responses should cool down longer than generic transient failures and use another account.",
},