fix: cool down Sub2API large context upstream failures

scripts/platform-infra-sub2api-codex-routing-contract-test.ts

@@ -48,6 +48,11 @@ if (parsed.pool?.defaultTempUnschedulable?.enabled === true) {
   const gateway502Rule = rules.find((rule) => rule.statusCode === 502);
   const gateway502Keywords = new Set((gateway502Rule?.keywords ?? []).map((keyword) => keyword.toLowerCase()));
   assertCondition(gateway502Keywords.has("recovered upstream error"), "502 temporary-unschedulable rule must catch recovered upstream error wrappers", gateway502Rule);
+  const largeContext413Rule = rules.find((rule) => rule.statusCode === 413);
+  const largeContext413Keywords = new Set((largeContext413Rule?.keywords ?? []).map((keyword) => keyword.toLowerCase()));
+  for (const keyword of ["openai_error", "context length", "maximum context"]) {
+    assertCondition(largeContext413Keywords.has(keyword), "413 temporary-unschedulable rule must catch large-context upstream failures", { keyword, largeContext413Rule });
+  }
   const gateway504Rule = rules.find((rule) => rule.statusCode === 504);
   const gateway504Keywords = new Set((gateway504Rule?.keywords ?? []).map((keyword) => keyword.toLowerCase()));
   for (const keyword of ["gateway timeout", "unknown error", "context deadline exceeded"]) {
@@ -78,6 +83,7 @@ console.log(JSON.stringify({
     "optional WebSocket mode overrides use supported values",
     "temporary unschedulable rules are structurally valid when enabled",
     "generic recovered upstream error wrappers are caught by cooldown rules",
+    "large-context upstream failures are caught by the 413 cooldown rule",
     "gateway timeout wrappers are caught by the 504 cooldown rule",
     "Codex weekly-limit prompts are caught by account-state and quota cooldown rules",
     "upstream model-routing failures are caught by the 503 cooldown rule",

scripts/platform-infra-sub2api-codex-temp-unsched-contract-test.ts

@@ -31,6 +31,7 @@ const accountState403Rule = rules.find((rule) => rule.error_code === 403);
 const quota429Rule = rules.find((rule) => rule.error_code === 429);
 const serviceUnavailable503Rule = rules.find((rule) => rule.error_code === 503);
 const gatewayTimeout504Rule = rules.find((rule) => rule.error_code === 504);
+const largeContext413Rule = rules.find((rule) => rule.error_code === 413);
 for (const keyword of ["weekly limit", "less than 10% of your weekly limit left", "run /status for a breakdown"]) {
   assertCondition(accountState403Rule?.keywords?.includes(keyword), "403 rendered rule must preserve Codex weekly-limit account-state keyword", { keyword, accountState403Rule });
   assertCondition(quota429Rule?.keywords?.includes(keyword), "429 rendered rule must preserve Codex weekly-limit quota keyword", { keyword, quota429Rule });
@@ -38,6 +39,9 @@ for (const keyword of ["weekly limit", "less than 10% of your weekly limit left"
 for (const keyword of ["model_not_found", "no available channel for model"]) {
   assertCondition(serviceUnavailable503Rule?.keywords?.includes(keyword), "503 rendered rule must catch upstream model-routing failures", { keyword, serviceUnavailable503Rule });
 }
+for (const keyword of ["openai_error", "context length", "maximum context"]) {
+  assertCondition(largeContext413Rule?.keywords?.includes(keyword), "413 rendered rule must catch large-context upstream failures", { keyword, largeContext413Rule });
+}
 for (const keyword of ["gateway timeout", "unknown error", "context deadline exceeded"]) {
   assertCondition(gatewayTimeout504Rule?.keywords?.includes(keyword), "504 rendered rule must preserve gateway-timeout cooldown keyword", { keyword, gatewayTimeout504Rule });
 }
@@ -56,6 +60,7 @@ console.log(JSON.stringify({
     "temporary unschedulable policy renders to Sub2API credential field names",
     "temporary unschedulable rendering follows the input policy without hard-coded policy gates",
     "Codex weekly-limit prompt keywords render into 403 and 429 cooldown rules",
+    "large-context upstream failures render into the 413 cooldown rule",
     "upstream model-routing failures render into the 503 cooldown rule",
     "gateway timeout wrappers render into the 504 cooldown rule",
     "disabled policies clear runtime rules",

scripts/src/platform-infra-sub2api-codex.ts

@@ -682,6 +682,12 @@ export function defaultCodexTempUnschedulablePolicy(): CodexTempUnschedulablePol
         durationMinutes: 30,
         description: "Gateway upstream failures, including recovered upstream error wrappers, should cool down longer.",
       },
+      {
+        statusCode: 413,
+        keywords: ["openai_error", "payload too large", "request too large", "context length", "context window", "maximum context"],
+        durationMinutes: 30,
+        description: "Large-context upstream failures should cool down the selected account so a larger-context channel can handle the request.",
+      },
       {
         statusCode: 503,
         keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "upstream", "recovered upstream error", "model_not_found", "no available channel for model"],