fix: cool down Sub2API Cloudflare timeouts

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

@@ -58,6 +58,11 @@ if (parsed.pool?.defaultTempUnschedulable?.enabled === true) {
   for (const keyword of ["gateway timeout", "unknown error", "context deadline exceeded"]) {
     assertCondition(gateway504Keywords.has(keyword), "504 temporary-unschedulable rule must catch gateway timeout wrappers", { keyword, gateway504Rule });
   }
+  const cloudflare524Rule = rules.find((rule) => rule.statusCode === 524);
+  const cloudflare524Keywords = new Set((cloudflare524Rule?.keywords ?? []).map((keyword) => keyword.toLowerCase()));
+  for (const keyword of ["timeout", "a timeout occurred", "cloudflare"]) {
+    assertCondition(cloudflare524Keywords.has(keyword), "524 temporary-unschedulable rule must catch Cloudflare timeout wrappers", { keyword, cloudflare524Rule });
+  }
   const accountState403Rule = rules.find((rule) => rule.statusCode === 403);
   const quota429Rule = rules.find((rule) => rule.statusCode === 429);
   const serviceUnavailable503Rule = rules.find((rule) => rule.statusCode === 503);
@@ -85,6 +90,7 @@ console.log(JSON.stringify({
     "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",
+    "Cloudflare timeout wrappers are caught by the 524 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",
     "Responses smoke model is YAML-declared",

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

@@ -32,6 +32,7 @@ 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);
+const cloudflare524Rule = rules.find((rule) => rule.error_code === 524);
 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 });
@@ -45,6 +46,9 @@ for (const keyword of ["openai_error", "context length", "maximum context"]) {
 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 });
 }
+for (const keyword of ["timeout", "a timeout occurred", "cloudflare"]) {
+  assertCondition(cloudflare524Rule?.keywords?.includes(keyword), "524 rendered rule must catch Cloudflare timeout wrappers", { keyword, cloudflare524Rule });
+}
 
 const disabled = renderSub2ApiTempUnschedulableCredentials({ enabled: false, rules: policy.rules }) as {
   temp_unschedulable_enabled?: boolean;
@@ -63,6 +67,7 @@ console.log(JSON.stringify({
     "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",
+    "Cloudflare timeout wrappers render into the 524 cooldown rule",
     "disabled policies clear runtime rules",
   ],
 }));

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

@@ -700,6 +700,12 @@ export function defaultCodexTempUnschedulablePolicy(): CodexTempUnschedulablePol
         durationMinutes: 30,
         description: "Gateway timeout responses should cool down the selected account so another account can handle the next request.",
       },
+      {
+        statusCode: 524,
+        keywords: ["timeout", "a timeout occurred", "cloudflare", "gateway timeout", "upstream", "context deadline exceeded"],
+        durationMinutes: 30,
+        description: "Cloudflare 524 timeout responses should cool down the selected account so another account can handle the next request.",
+      },
       {
         statusCode: 529,
         keywords: ["capacity", "overloaded", "temporarily unavailable", "temporary", "recovered upstream error"],