macOS: Same ChatGPT account works on Windows but fails with X-OpenAI-Internal-Codex-Responses-Lite on Codex CLI

Open 💬 11 comments Opened Jun 29, 2026 by ghz0319
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex CLI is running?

Codex CLI 0.142.4

What subscription do you have?

macOS CLI incorrectly routes ChatGPT-authenticated requests to Responses-Lite while Windows works

Which model were you using?

gpt5.4 and gpt5.5

What platform is your computer?

Mac OS 26.5.1 (25F80)

What terminal emulator and version are you using (if applicable)?

Apple Terminal.app 2.15 (470.2)

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1782746379s since unix epoch",
  "overallStatus": "ok",
  "codexVersion": "0.142.4",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/Users/doudousam/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/Users/doudousam/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/Users/doudousam/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/Users/doudousam/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/Users/doudousam/.codex/app-server-daemon/app-server-updater.pid (missing)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth file": "/Users/doudousam/.codex/auth.json",
        "auth storage mode": "File",
        "stored API key": "true",
        "stored ChatGPT tokens": "false",
        "stored agent identity": "false",
        "stored auth mode": "api_key"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "/Users/doudousam/.codex",
        "config.toml": "/Users/doudousam/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/Users/doudousam",
        "enabled feature flags": "shell_tool, unified_exec, shell_snapshot, terminal_resize_reflow, sqlite, hooks, enable_request_compression, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, plugin_sharing, image_generation, resize_all_images, skill_mcp_dependency_install, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, personality, fast_mode, tui_app_server, auto_compaction, remote_compaction_v2, workspace_dependencies",
        "feature flag overrides": "none",
        "feature flags enabled": "33",
        "log dir": "/Users/doudousam/.codex/log",
        "mcp servers": "5",
        "model": "gpt-5.5",
        "model provider": "openai_http",
        "sqlite home": "/Users/doudousam/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.50.1 (Apple Git-155)",
      "details": {
        "PATH git #1": "/usr/bin/git",
        "PATH git entries": "1",
        "git build options": "git version 2.50.1 (Apple Git-155); cpu: arm64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh; feature: fsmonitor--daemon; libcurl: 8.7.1; zlib: 1.2.12; SHA-1: SHA1_DC; SHA-256: SHA256_BLK",
        "git exec path": "/Library/Developer/CommandLineTools/usr/libexec/git-core",
        "git version": "git version 2.50.1 (Apple Git-155)",
        "repo detected": "false",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 16
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/Users/doudousam/.npm-global/bin/codex",
        "current executable": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin/codex",
        "install context": "npm (package /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)",
        "managed by bun": "false",
        "managed by npm": "true",
        "managed package root": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex",
        "npm update target": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex"
      },
      "remediation": null,
      "durationMs": 81
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "MCP configuration is locally consistent",
      "details": {
        "configured servers": "5",
        "disabled servers": "0",
        "stdio servers": "2",
        "streamable_http servers": "3"
      },
      "remediation": null,
      "durationMs": 3168
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "proxy env vars": "none"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "openai_http API base URL": "https://api.openai.com/v1 reachable (HTTP 404)",
        "openai_http API route probe": "https://api.openai.com/v1/<redacted> route exists (HTTP 401)",
        "reachability mode": "API key auth"
      },
      "remediation": null,
      "durationMs": 2128
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket is not enabled for the active provider",
      "details": {
        "model provider": "openai_http",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "supports websockets": "false",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running npm on macos-aarch64",
      "details": {
        "commit": "unknown",
        "current executable": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin/codex",
        "install method": "npm (package /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)",
        "platform": "macos-aarch64",
        "version": "0.142.4"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path/rg",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "none",
        "execve wrapper helper": "/Users/doudousam/.codex/tmp/arg0/codex-arg0X2EWE7/codex-execve-wrapper",
        "filesystem sandbox": "restricted",
        "network sandbox": "restricted"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/Users/doudousam/.codex (dir)",
        "active rollout files": "64 files, 71495608 total bytes, 1117118 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/Users/doudousam/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/Users/doudousam/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/Users/doudousam/.codex/log (dir)",
        "memories DB": "/Users/doudousam/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "sqlite home": "/Users/doudousam/.codex (dir)",
        "state DB": "/Users/doudousam/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 584
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "ok",
      "summary": "rollout files and state DB thread inventory agree",
      "details": {
        "default model provider": "openai_http",
        "rollout DB active files": "64",
        "rollout DB active rows": "64",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "0",
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai_http=35, openai=29",
        "rollout DB rows": "64",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "vscode=45, cli=9, exec=8, subagent:thread_spawn=2",
        "rollout DB stale rows": "0"
      },
      "remediation": null,
      "durationMs": 246
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language zh-Hans-US",
      "details": {
        "EDITOR": "not set",
        "LANG": "C.UTF-8",
        "LC_CTYPE": "UTF-8",
        "VISUAL": "not set",
        "os": "Mac OS 26.5.1 [64-bit]",
        "os language": "zh-Hans-US",
        "os type": "Mac OS",
        "os version": "26.5.1"
      },
      "remediation": null,
      "durationMs": 4
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "TERM_PROGRAM": "Apple_Terminal",
        "color output": "enabled",
        "effective locale": "UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "Apple Terminal",
        "terminal size": "120x30",
        "terminal version": "470.2"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "cwd",
        "terminal title project value": "doudousam",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 0
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.142.4",
        "check for update on startup": "true",
        "last checked at": "2026-06-29T14:14:44.970140Z",
        "latest version": "0.142.4",
        "latest version status": "current version is not older",
        "npm update target": "/Users/doudousam/.npm-global/lib/node_modules/@openai/codex",
        "update action": "npm install -g @openai/codex",
        "version cache": "/Users/doudousam/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 3633
    }
  }
}

What issue are you seeing?

After updating to Codex CLI 0.142.4 on macOS, every prompt fails immediately with the following error:

This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

Example prompt:

Explain this codebase

The same error also occurs with simple prompts such as:

Hello

I have already verified the following:

  • Updated to the latest Codex CLI (0.142.4)
  • Logged out and logged back in
  • Cleared the local authentication state
  • Tested multiple models, including:
  • gpt-5.5
  • gpt-5.4
  • gpt-5.4-mini
  • The issue persists across all of them.

The most important observation is that the exact same ChatGPT account works correctly on Windows, but fails consistently on macOS with the Responses-Lite error.

This suggests the issue may be specific to the macOS client or its local state rather than the account itself.

What steps can reproduce the bug?

Steps to reproduce:

  1. Use macOS with Apple Terminal.app.
  2. Install or update Codex CLI to 0.142.4.
  3. Log in with a ChatGPT account.
  4. Start Codex:

codex

  1. Send any prompt, for example:

Explain this codebase

or:

Hello

  1. The request fails with:

This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

I also tested with multiple models:

gpt-5.5
gpt-5.4
gpt-5.4-mini

All of them fail with the same error on macOS.

No thread id is available.

What is the expected behavior?

After signing in with a valid ChatGPT account, Codex CLI should execute prompts normally.

The same ChatGPT account already works correctly on Windows. Therefore, I expect the macOS client to behave identically and execute requests successfully without routing them to an unsupported Responses-Lite path.

Simple prompts such as:

Hello

or

Explain this codebase

should return normal model responses instead of:

This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

Additional information

Additional observations:

  • The same ChatGPT account works correctly on Windows using the same Codex version.
  • The issue only occurs on macOS.
  • I updated Codex CLI to the latest available version (0.142.4), but the problem persists.
  • I tested multiple models (gpt-5.5, gpt-5.4, and gpt-5.4-mini). The same error occurs regardless of the selected model.
  • I logged out, cleared the local authentication state, and logged in again. The behavior did not change.
  • My config.toml is using the default ChatGPT authentication (openai_http, wire_api = "responses"), without a custom proxy or custom API endpoint.
  • If additional debug logs, codex doctor --json output, or sanitized configuration files would help, I’m happy to provide them.
  • This issue appears to be platform-specific rather than account-specific, since the exact same ChatGPT account works normally on Windows.

View original on GitHub ↗

11 Comments

ghz0319 · 21 days ago

I can reproduce this consistently on macOS, while the exact same ChatGPT account works normally on Windows. If needed, I can provide:

  • codex doctor --json
  • sanitized config.toml
  • sanitized auth.json
  • debug logs
  • reproduction video
github-actions[bot] contributor · 21 days ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #30403
  • #30406
  • #30461
  • #30422
  • #30224

Powered by Codex Action

harshavardhan194 · 21 days ago

I’d like to work on this. I will reproduce the bug on macOS, investigate the Responses-Lite routing and platform-specific code paths, and open a PR with a fix and tests. Please assign this issue to me if possible

ghz0319 · 20 days ago

After today’s update, GPT-5.4 is working again, but GPT-5.5 is still not working. The issue remains unresolved for GPT-5.5.

ghz0319 · 20 days ago

Thanks for looking into this!

After today’s update, GPT-5.4 is working again on my macOS setup, but GPT-5.5 still fails with the same issue.

If you need me to test any fix or provide additional logs, I’d be happy to help.

harshavardhan194 · 20 days ago

I was unable to reproduce the issue on macOS using Codex CLI 0.142.4 with GPT-5.5. Since the same platform, CLI version, and model work correctly in my environment, this does not appear to be a general macOS client bug. At this point, the issue is more likely related to account-specific rollout, backend routing, or a machine-specific configuration.

lemieapp · 20 days ago

This happens to me when I use a proxy like Headroom because I’ve set it to ‘off’
Headroom running → Codex's request (carrying X-OpenAI-Internal-Codex-Responses-Lite) goes through headroom, which forwards it to an endpoint that actually serves gpt-5.5. Works.
Headroom NOT started → Codex talks directly to the real Responses-Lite endpoint with that internal header attached. That endpoint doesn't serve gpt-5.5, so it returns "This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite."

ghz0319 · 19 days ago

After the latest update, I tested Codex again.

GPT-5.5 still fails with the following error:

This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

Also, after switching from GPT-5.5 back to GPT-5.4 in the same conversation, the same error may continue to appear, so the session state seems to remain affected.

GPT-5.4 can work again in a new conversation, but GPT-5.5 is still unavailable.

ghz0319 · 17 days ago

codex-cli 0.142.5
config.toml uses wire_api = "responses", not responses-lite.
Still receives:
This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

ghz0319 · 17 days ago

Tested on codex-cli 0.142.5.

I found gpt-5.5 in ~/.codex/models_cache.json with:
"use_responses_lite": true

I changed it to false and verified the file contained:
"use_responses_lite": false

After restarting Codex, the same error still occurs:
This model is not supported when using X-OpenAI-Internal-Codex-Responses-Lite.

So the Lite routing does not appear to be controlled solely by models_cache.json.

harmonypiano · 17 days ago

found out that you can copy models_cache.json to model_catalog.json to make it persistent

then in your config.toml, add this (use absolute path):
model_catalog_json = "/absolute/path/to/model_catalog.json"