fix: cool down Sub2API large context upstream failures

config/platform-infra/sub2api-codex-pool.yaml

@@ -30,6 +30,10 @@ pool:
         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, 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]
         durationMinutes: 30
@@ -56,6 +60,7 @@ profiles:
       accountName: unidesk-codex-gptclub
       configFile: config.toml.gptclub
       authFile: auth.json.gptclub
+      capacity: 10
       priority: 100
     - profile: only
       accountName: unidesk-codex-only