[BUG] Usage limit reached on new MAX models

[paflopes]

Bug Description
Agent stops after receiving a "Usage limit reached [404]" error from OpenAI. Also, I'm getting this error even though I have >90% of usage remaining.

And finally, the error response is being added to the opencode input box, which messes it up

Steps to Reproduce

1. Select gpt-5.1-codex-max-high model
2. Use it for a while

Expected Behavior
I think this is some kind of rate-limiting, so the expected behavior is to either retry it after a while, or just send the error as a message, and not print it in the input box.

Actual Behavior
The plugin does not retry.

Environment

• opencode version: 1.0.119
• Plugin version: 4.0.2
• Operating System: MacOS
• Node.js version: 24.9.0

Compliance Checklist
Please confirm:

• I'm using this plugin for personal development only
• I have an active ChatGPT Plus/Pro subscription
• This issue is not related to attempting commercial use or TOS violations
• I've reviewed the FAQ and Troubleshooting sections

[numman-ali]

Sorry away from laptop at the moment

Did you run this command

rm -rf ~/.cache/opencode/node_modules ~/.cache/opencode/bun.lock

Could you also paste your opencode config please?

[paflopes]

Hey @numman-ali, sure I cleared the cache with this command. Here's my opencode config:

{
  "$schema": "https://opencode.ai/config.json",
  "autoupdate": true,
  "model": "openai/gpt-5.1-codex-max-medium",
  "small_model": "google/gemini-2.5-flash",
  "lsp": {
    "jdtls": {
      "disabled": true
    }
  },
  "plugin": [
    "opencode-openai-codex-auth@4.0.2",
    "opencode-gemini-auth"
  ],
  "provider": {
    "openai": {
      "options": {
        "reasoningEffort": "medium",
        "reasoningSummary": "auto",
        "textVerbosity": "medium",
        "include": [
          "reasoning.encrypted_content"
        ],
        "store": false
      },
      "models": {
        "gpt-5.1-codex-low": {
          "name": "GPT 5.1 Codex Low (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "low",
            "reasoningSummary": "auto",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-medium": {
          "name": "GPT 5.1 Codex Medium (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "medium",
            "reasoningSummary": "auto",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-high": {
          "name": "GPT 5.1 Codex High (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "high",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-max": {
          "name": "GPT 5.1 Codex Max (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "high",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-max-low": {
          "name": "GPT 5.1 Codex Max Low (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "low",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-max-medium": {
          "name": "GPT 5.1 Codex Max Medium (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "medium",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-max-high": {
          "name": "GPT 5.1 Codex Max High (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "high",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-max-xhigh": {
          "name": "GPT 5.1 Codex Max Extra High (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "xhigh",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-mini-medium": {
          "name": "GPT 5.1 Codex Mini Medium (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "medium",
            "reasoningSummary": "auto",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-codex-mini-high": {
          "name": "GPT 5.1 Codex Mini High (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "high",
            "reasoningSummary": "detailed",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-low": {
          "name": "GPT 5.1 Low (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "low",
            "reasoningSummary": "auto",
            "textVerbosity": "low",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-medium": {
          "name": "GPT 5.1 Medium (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "medium",
            "reasoningSummary": "auto",
            "textVerbosity": "medium",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        },
        "gpt-5.1-high": {
          "name": "GPT 5.1 High (OAuth)",
          "limit": {
            "context": 272000,
            "output": 128000
          },
          "options": {
            "reasoningEffort": "high",
            "reasoningSummary": "detailed",
            "textVerbosity": "high",
            "include": [
              "reasoning.encrypted_content"
            ],
            "store": false
          }
        }
      }
    }
  },
  "mcp": {
    "pdf": {
      "type": "local",
      "command": ["npx", "@sylphx/pdf-reader-mcp"],
      "enabled": true
    },
    "markitdown": {
      "type": "local",
      "command": ["markitdown-mcp"],
      "enabled": false
    },
    "filesystem": {
      "type": "local",
      "command": [
        "server-filesystem"
      ],
      "enabled": false
    },
    "sequential-thinking": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ],
      "enabled": false
    },
    "basic-memory": {
      "type": "local",
      "command": [
        "uvx",
        "basic-memory",
        "mcp"
      ],
      "enabled": false
    },
    "ddg-search": {
      "type": "local",
      "command": [
        "uvx",
        "duckduckgo-mcp-server"
      ],
      "enabled": true
    },
    "time": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-server-time"
      ],
      "enabled": true
    },
    "context7": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@upstash/context7-mcp"
      ],
      "enabled": true
    }
  }
}

I think (Codex actually) the issue is that OpenAI is returning a 404 status code, which makes OpenCode not retry these errors. I'm testing mapping this status code to 421 to check how it behaves.

[paflopes]

Just one more detail, I see the 404 returned comes from CloudFlare, in case that helps

{
  "timestamp": "2025-11-27T19:36:54.053Z",
  "requestId": 10,
  "stage": "response",
  "status": 404,
  "ok": false,
  "statusText": "Not Found",
  "headers": {
    "cf-cache-status": "DYNAMIC",
    "cf-ray": "9a5413bb2ff39ca6-GIG",
    "connection": "keep-alive",
    "content-length": "22",
    "content-type": "application/json",
    "cross-origin-opener-policy": "same-origin-allow-popups",
    "date": "Thu, 27 Nov 2025 19:36:54 GMT",
    "nel": "{\"success_fraction\":0.01,\"report_to\":\"cf-nel\",\"max_age\":604800}",
    "referrer-policy": "strict-origin-when-cross-origin",
    "report-to": "{\"endpoints\":[{\"url\":\"https:\\/\\/a.nel.cloudflare.com\\/report\\/v4?s=C%2BKVu37blDzl%2ByYMLb4PvehwNUPXtXtSujhxsJb0G7oIXk739OudrIbfy%2BrjF9jBOLt0gmSVMhwHUzF1MYeU9LdRCWwE3jnxMewy6PFR8ko22uIgpNVioOYU%2BPjj\"}],\"group\":\"cf-nel\",\"max_age\":604800}",
    "server": "cloudflare",
    "strict-transport-security": "max-age=31536000; includeSubDomains; preload",
    "x-build": "875e266e75df",
    "x-content-type-options": "nosniff",
    "x-oai-request-id": "f8cde556-e1bd-4995-9c15-10e35b26c727",
    "set-cookie": "__cflb=0H28vzvP5FJafnkHxjEvhw3FMheEQkHpRxW2YKf7Z8w; SameSite=None; Secure; path=/; expires=Thu, 27-Nov-25 20:36:54 GMT; HttpOnly"
  }
}

[EvanNotFound]

I encountered this error as well.

Even after changing to non-max models, it will always persist 404 error.

I downgraded to v3.3.0 and non-max models works fine.

I think it is something that v4 is checking which causes openai to return 404 error

Edit: hitting the same error with 3.3.0 as well

[jasonish]

Hitting this issue as well, with 3.3.0 and 4.0.2. Codex CLI reports:

[EvanNotFound]

@jasonish i take back what i said. same here, not working for both 3.3.0 and 4.0.2, even for gpt-5.1-high, and my remaining usage is still at 88%

[EvanNotFound]

any follow up on this?

[EvanNotFound]

@hyprbased wrong thread. related issue should be #48